diff --git "a/checkpoint-2671200/trainer_state.json" "b/checkpoint-2671200/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2671200/trainer_state.json" @@ -0,0 +1,31607 @@ +{ + "best_metric": 3.97987961769104, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/passive/lstm/4/checkpoints/checkpoint-2671200", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2671200, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.8196, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5533, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0635, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 7.0042, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.9533, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.9322, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.7756, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 6.6613, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 6.5605, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 6.4804, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 6.4189, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 6.3513, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 6.2866, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 6.2208, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 6.1649, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 6.0949, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986582483983168e-05, + "loss": 6.0579, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985743889232116e-05, + "loss": 6.0075, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984905294481064e-05, + "loss": 5.9647, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.9239, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.8918, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 5.8513, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 5.8219, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.980713958606178e-05, + "loss": 5.7784, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.979875363855125e-05, + "loss": 5.7661, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.979036769104073e-05, + "loss": 5.7274, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.978198174353021e-05, + "loss": 5.7087, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773612174823426e-05, + "loss": 5.6689, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.97652262273129e-05, + "loss": 5.6523, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.975684027980238e-05, + "loss": 5.6324, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.974845433229186e-05, + "loss": 5.6059, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.974008476358507e-05, + "loss": 5.5968, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.973169881607455e-05, + "loss": 5.5723, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.972331286856403e-05, + "loss": 5.5537, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714926921053515e-05, + "loss": 5.5465, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.9706557352346724e-05, + "loss": 5.5243, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.9698171404836204e-05, + "loss": 5.5144, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.9689785457325684e-05, + "loss": 5.4689, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.9681399509815164e-05, + "loss": 5.4752, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.9673013562304644e-05, + "loss": 5.4362, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.9664627614794124e-05, + "loss": 5.4425, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.9656241667283604e-05, + "loss": 5.4201, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.9647855719773084e-05, + "loss": 5.4185, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.9639469772262564e-05, + "loss": 5.389, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.9631083824752044e-05, + "loss": 5.3955, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962271425604525e-05, + "loss": 5.3851, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.961432830853473e-05, + "loss": 5.3771, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960594236102421e-05, + "loss": 5.3689, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959755641351369e-05, + "loss": 5.3395, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958917046600318e-05, + "loss": 5.3322, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958080089729639e-05, + "loss": 5.3311, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957241494978587e-05, + "loss": 5.3187, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956402900227535e-05, + "loss": 5.3127, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955564305476483e-05, + "loss": 5.29, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954728986486177e-05, + "loss": 5.2844, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953890391735125e-05, + "loss": 5.267, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530517969840727e-05, + "loss": 5.2882, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522132022330207e-05, + "loss": 5.2425, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.9513746074819686e-05, + "loss": 5.2583, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.9505360127309166e-05, + "loss": 5.2469, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.9496974179798646e-05, + "loss": 5.2273, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948858823228813e-05, + "loss": 5.2259, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948020228477761e-05, + "loss": 5.2129, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.9471816337267086e-05, + "loss": 5.2021, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.9463430389756566e-05, + "loss": 5.1949, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.9455044442246046e-05, + "loss": 5.2091, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.9446658494735526e-05, + "loss": 5.1846, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.9438272547225006e-05, + "loss": 5.1752, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.9429886599714486e-05, + "loss": 5.1647, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421500652203966e-05, + "loss": 5.1633, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413131083497175e-05, + "loss": 5.1684, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404745135986655e-05, + "loss": 5.1636, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396359188476135e-05, + "loss": 5.1401, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.938798961976935e-05, + "loss": 5.1545, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.937960367225883e-05, + "loss": 5.1482, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.937121772474831e-05, + "loss": 5.1205, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936283177723779e-05, + "loss": 5.1193, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935444582972727e-05, + "loss": 5.1089, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.934607626102048e-05, + "loss": 5.1017, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933769031350996e-05, + "loss": 5.0958, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932930436599944e-05, + "loss": 5.0998, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932091841848892e-05, + "loss": 5.097, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931254884978213e-05, + "loss": 5.098, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930416290227161e-05, + "loss": 5.0739, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.9295793333564825e-05, + "loss": 5.0562, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.9287407386054305e-05, + "loss": 5.0612, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.9279021438543785e-05, + "loss": 5.0632, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.9270635491033264e-05, + "loss": 5.0611, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.9262249543522744e-05, + "loss": 5.0452, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.9253863596012224e-05, + "loss": 5.0429, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.9245477648501704e-05, + "loss": 5.0427, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.9237091700991184e-05, + "loss": 5.0344, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922872213228439e-05, + "loss": 5.0245, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922033618477387e-05, + "loss": 5.0217, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921195023726335e-05, + "loss": 5.0082, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920356428975283e-05, + "loss": 5.0206, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919517834224231e-05, + "loss": 5.0085, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918680877353552e-05, + "loss": 4.9863, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917842282602501e-05, + "loss": 4.9927, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917003687851449e-05, + "loss": 4.9899, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916165093100397e-05, + "loss": 4.9978, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915326498349345e-05, + "loss": 4.9792, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914487903598292e-05, + "loss": 4.9753, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.91364930884724e-05, + "loss": 4.9611, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912810714096188e-05, + "loss": 4.9671, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911973757225509e-05, + "loss": 4.9459, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911136800354831e-05, + "loss": 4.9572, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910298205603779e-05, + "loss": 4.9442, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.9094612487330996e-05, + "loss": 4.9469, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.9086226539820476e-05, + "loss": 4.9352, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907784059230996e-05, + "loss": 4.9385, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906945464479944e-05, + "loss": 4.9251, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906106869728892e-05, + "loss": 4.93, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052682749778396e-05, + "loss": 4.9215, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.9044296802267876e-05, + "loss": 4.9146, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.9035910854757356e-05, + "loss": 4.9269, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.9027541286050565e-05, + "loss": 4.9104, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019155338540045e-05, + "loss": 4.9092, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010769391029525e-05, + "loss": 4.898, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.9002383443519005e-05, + "loss": 4.9027, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8993997496008485e-05, + "loss": 4.8985, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.89856279273017e-05, + "loss": 4.8913, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.897724197979118e-05, + "loss": 4.8959, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.896885603228066e-05, + "loss": 4.8833, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.896048646357387e-05, + "loss": 4.8825, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.895210051606335e-05, + "loss": 4.863, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.894371456855283e-05, + "loss": 4.8677, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893532862104231e-05, + "loss": 4.8685, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892694267353179e-05, + "loss": 4.8599, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891855672602127e-05, + "loss": 4.8503, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891017077851075e-05, + "loss": 4.8745, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890178483100023e-05, + "loss": 4.8557, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889339888348971e-05, + "loss": 4.8489, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888502931478292e-05, + "loss": 4.8487, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766433672724e-05, + "loss": 4.8422, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886825741976188e-05, + "loss": 4.8447, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.8859871472251365e-05, + "loss": 4.8411, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.8851485524740845e-05, + "loss": 4.8362, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.8843099577230325e-05, + "loss": 4.8387, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.8834713629719805e-05, + "loss": 4.8376, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882632768220928e-05, + "loss": 4.8255, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.8817958113502494e-05, + "loss": 4.8153, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.8809572165991974e-05, + "loss": 4.8277, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.8801186218481454e-05, + "loss": 4.8137, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879280027097093e-05, + "loss": 4.8173, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878443070226414e-05, + "loss": 4.8072, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877604475475362e-05, + "loss": 4.8057, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876767518604683e-05, + "loss": 4.8111, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875928923853632e-05, + "loss": 4.7981, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.87509032910258e-05, + "loss": 4.7943, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.7635955810546875, + "eval_runtime": 297.4563, + "eval_samples_per_second": 1282.847, + "eval_steps_per_second": 40.09, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874251734351528e-05, + "loss": 4.783, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873413139600475e-05, + "loss": 4.7806, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872574544849423e-05, + "loss": 4.8048, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871735950098371e-05, + "loss": 4.7898, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.870897355347319e-05, + "loss": 4.7811, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.87006039847664e-05, + "loss": 4.7777, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692234416059616e-05, + "loss": 4.7775, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683848468549096e-05, + "loss": 4.7603, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675462521038576e-05, + "loss": 4.771, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667076573528056e-05, + "loss": 4.7689, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658690626017536e-05, + "loss": 4.7704, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.8650304678507016e-05, + "loss": 4.769, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8641935109800225e-05, + "loss": 4.7524, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633549162289705e-05, + "loss": 4.7516, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.8625163214779185e-05, + "loss": 4.7411, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.8616777267268665e-05, + "loss": 4.743, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608391319758145e-05, + "loss": 4.7498, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.8600005372247625e-05, + "loss": 4.7388, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591619424737105e-05, + "loss": 4.7452, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.8583249856030314e-05, + "loss": 4.7575, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574863908519794e-05, + "loss": 4.7386, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566477961009274e-05, + "loss": 4.7427, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558092013498754e-05, + "loss": 4.7257, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854972244479197e-05, + "loss": 4.745, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854133649728145e-05, + "loss": 4.7226, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853295054977093e-05, + "loss": 4.7257, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852456460226041e-05, + "loss": 4.7134, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851617865474989e-05, + "loss": 4.7211, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850779270723937e-05, + "loss": 4.712, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849940675972885e-05, + "loss": 4.7091, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849102081221833e-05, + "loss": 4.7152, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848263486470781e-05, + "loss": 4.7162, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847424891719729e-05, + "loss": 4.7084, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846586296968676e-05, + "loss": 4.7128, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845749340097998e-05, + "loss": 4.7019, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844910745346946e-05, + "loss": 4.7113, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844072150595894e-05, + "loss": 4.6829, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843233555844842e-05, + "loss": 4.6993, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.84239496109379e-05, + "loss": 4.6752, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.8415580042231114e-05, + "loss": 4.6953, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840721047352432e-05, + "loss": 4.6785, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.83988245260138e-05, + "loss": 4.6918, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839043857850328e-05, + "loss": 4.6699, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838205263099276e-05, + "loss": 4.6883, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373666683482236e-05, + "loss": 4.6845, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.8365280735971716e-05, + "loss": 4.6811, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.8356894788461196e-05, + "loss": 4.6892, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.8348508840950676e-05, + "loss": 4.6584, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834013927224389e-05, + "loss": 4.6615, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833175332473337e-05, + "loss": 4.6757, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832336737722285e-05, + "loss": 4.6685, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831498142971233e-05, + "loss": 4.6657, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830659548220181e-05, + "loss": 4.6596, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829822591349502e-05, + "loss": 4.6531, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.82898399659845e-05, + "loss": 4.6472, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828145401847398e-05, + "loss": 4.6627, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.827306807096346e-05, + "loss": 4.6387, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.826468212345294e-05, + "loss": 4.6484, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825631255474615e-05, + "loss": 4.6559, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8247942986039366e-05, + "loss": 4.6382, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.8239557038528846e-05, + "loss": 4.6388, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.8231171091018326e-05, + "loss": 4.6367, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222785143507806e-05, + "loss": 4.6257, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214399195997286e-05, + "loss": 4.6304, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.8206013248486766e-05, + "loss": 4.6474, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.8197627300976246e-05, + "loss": 4.6297, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189241353465726e-05, + "loss": 4.6231, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180855405955206e-05, + "loss": 4.6217, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172485837248415e-05, + "loss": 4.6225, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164099889737895e-05, + "loss": 4.6364, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155713942227375e-05, + "loss": 4.6298, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147327994716854e-05, + "loss": 4.6178, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8138942047206334e-05, + "loss": 4.6345, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.8130556099695814e-05, + "loss": 4.6323, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812218653098903e-05, + "loss": 4.6152, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811380058347851e-05, + "loss": 4.6143, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810541463596799e-05, + "loss": 4.6118, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809702868845747e-05, + "loss": 4.6097, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808864274094695e-05, + "loss": 4.6053, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808027317224016e-05, + "loss": 4.6089, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807188722472964e-05, + "loss": 4.6157, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806350127721912e-05, + "loss": 4.6172, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.80551153297086e-05, + "loss": 4.6048, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804672938219807e-05, + "loss": 4.5804, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803835981349129e-05, + "loss": 4.5992, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.802997386598077e-05, + "loss": 4.6015, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802158791847025e-05, + "loss": 4.6036, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801320197095973e-05, + "loss": 4.5946, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004832402252944e-05, + "loss": 4.5931, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799646283354615e-05, + "loss": 4.5982, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798807688603563e-05, + "loss": 4.5898, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797969093852511e-05, + "loss": 4.584, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797130499101459e-05, + "loss": 4.5911, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796291904350407e-05, + "loss": 4.5763, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954533095993546e-05, + "loss": 4.5954, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794616352728676e-05, + "loss": 4.5872, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793777757977624e-05, + "loss": 4.5658, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792939163226572e-05, + "loss": 4.5788, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.79210056847552e-05, + "loss": 4.577, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791261973724468e-05, + "loss": 4.5884, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790423378973416e-05, + "loss": 4.5752, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789584784222364e-05, + "loss": 4.5705, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788746189471312e-05, + "loss": 4.5652, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787909232600633e-05, + "loss": 4.5733, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.787070637849581e-05, + "loss": 4.5548, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786232043098529e-05, + "loss": 4.5642, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.78539508622785e-05, + "loss": 4.5629, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845581293571715e-05, + "loss": 4.5614, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837195346061195e-05, + "loss": 4.5525, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828809398550675e-05, + "loss": 4.5627, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.7820423451040155e-05, + "loss": 4.554, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7812037503529635e-05, + "loss": 4.5552, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803651556019115e-05, + "loss": 4.5562, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.7795265608508595e-05, + "loss": 4.5467, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786879660998075e-05, + "loss": 4.5713, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.7778493713487555e-05, + "loss": 4.5551, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770107765977035e-05, + "loss": 4.5535, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761738197270244e-05, + "loss": 4.5443, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.7753352249759724e-05, + "loss": 4.5514, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.7744966302249204e-05, + "loss": 4.5496, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.7736580354738684e-05, + "loss": 4.5407, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.7728194407228164e-05, + "loss": 4.5566, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.7719808459717644e-05, + "loss": 4.5439, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.7711422512207124e-05, + "loss": 4.5394, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.7703036564696604e-05, + "loss": 4.533, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769466699598982e-05, + "loss": 4.5351, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.76862810484793e-05, + "loss": 4.5339, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767789510096878e-05, + "loss": 4.5351, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766950915345826e-05, + "loss": 4.5235, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766112320594773e-05, + "loss": 4.5513, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765273725843721e-05, + "loss": 4.541, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764435131092669e-05, + "loss": 4.5306, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.76359817422199e-05, + "loss": 4.5295, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762759579470938e-05, + "loss": 4.5228, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761920984719886e-05, + "loss": 4.5362, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761082389968834e-05, + "loss": 4.5316, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760243795217783e-05, + "loss": 4.5262, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759406838347104e-05, + "loss": 4.5327, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758568243596052e-05, + "loss": 4.5294, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757729648845e-05, + "loss": 4.5263, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756891054093948e-05, + "loss": 4.5178, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756052459342896e-05, + "loss": 4.5313, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755213864591844e-05, + "loss": 4.5184, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543769077211646e-05, + "loss": 4.5206, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535383129701126e-05, + "loss": 4.5143, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7526997182190606e-05, + "loss": 4.5167, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518611234680086e-05, + "loss": 4.518, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510225287169566e-05, + "loss": 4.508, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7501839339659046e-05, + "loss": 4.51, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.485311508178711, + "eval_runtime": 296.7853, + "eval_samples_per_second": 1285.748, + "eval_steps_per_second": 40.181, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493453392148526e-05, + "loss": 4.4984, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748506744463801e-05, + "loss": 4.4971, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747668149712749e-05, + "loss": 4.523, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746829554961697e-05, + "loss": 4.5155, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7459909602106446e-05, + "loss": 4.5049, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451523654595926e-05, + "loss": 4.5021, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443137707085406e-05, + "loss": 4.5059, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434751759574886e-05, + "loss": 4.4901, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426365812064366e-05, + "loss": 4.5078, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7417979864553846e-05, + "loss": 4.5001, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.7409593917043326e-05, + "loss": 4.5039, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401207969532806e-05, + "loss": 4.5053, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.7392838400826015e-05, + "loss": 4.4866, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384452453315495e-05, + "loss": 4.4917, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.7376066505804975e-05, + "loss": 4.4863, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736768055829446e-05, + "loss": 4.4861, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735929461078394e-05, + "loss": 4.4895, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735090866327342e-05, + "loss": 4.483, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.73425227157629e-05, + "loss": 4.49, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733415314705611e-05, + "loss": 4.509, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732576719954559e-05, + "loss": 4.4882, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731738125203507e-05, + "loss": 4.4914, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730899530452455e-05, + "loss": 4.4831, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730060935701403e-05, + "loss": 4.4962, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729223978830724e-05, + "loss": 4.478, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728385384079672e-05, + "loss": 4.4884, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.72754678932862e-05, + "loss": 4.4713, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726708194577568e-05, + "loss": 4.4746, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725869599826516e-05, + "loss": 4.4728, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725031005075464e-05, + "loss": 4.4698, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724192410324412e-05, + "loss": 4.4768, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.72335381557336e-05, + "loss": 4.4822, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722516858702681e-05, + "loss": 4.4746, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721678263951629e-05, + "loss": 4.4821, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720839669200577e-05, + "loss": 4.4662, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720001074449525e-05, + "loss": 4.4836, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719162479698473e-05, + "loss": 4.4525, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718323884947421e-05, + "loss": 4.4732, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717485290196369e-05, + "loss": 4.4472, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716646695445317e-05, + "loss": 4.4704, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715808100694265e-05, + "loss": 4.4563, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714969505943213e-05, + "loss": 4.4721, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141309111921614e-05, + "loss": 4.4505, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7132939543214823e-05, + "loss": 4.4631, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.7124553595704303e-05, + "loss": 4.4645, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711616764819378e-05, + "loss": 4.4647, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710778170068326e-05, + "loss": 4.4672, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709939575317274e-05, + "loss": 4.4466, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709100980566222e-05, + "loss": 4.4422, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708264023695543e-05, + "loss": 4.4635, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707425428944491e-05, + "loss": 4.4575, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706586834193439e-05, + "loss": 4.4509, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.7057482394423865e-05, + "loss": 4.4492, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704909644691335e-05, + "loss": 4.4442, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704072687820657e-05, + "loss": 4.4342, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703235730949978e-05, + "loss": 4.4529, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702397136198926e-05, + "loss": 4.4316, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701558541447874e-05, + "loss": 4.4432, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700719946696822e-05, + "loss": 4.4526, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.69988135194577e-05, + "loss": 4.4345, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699042757194717e-05, + "loss": 4.4347, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698204162443665e-05, + "loss": 4.4387, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697365567692613e-05, + "loss": 4.4246, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696526972941561e-05, + "loss": 4.4262, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695688378190509e-05, + "loss": 4.448, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694849783439457e-05, + "loss": 4.4317, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.6940128265687786e-05, + "loss": 4.4256, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.6931742318177266e-05, + "loss": 4.4246, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.6923356370666746e-05, + "loss": 4.4297, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6914970423156226e-05, + "loss": 4.4423, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.6906584475645706e-05, + "loss": 4.4369, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898198528135186e-05, + "loss": 4.425, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6889828959428395e-05, + "loss": 4.4411, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881443011917875e-05, + "loss": 4.4372, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873057064407355e-05, + "loss": 4.4257, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864671116896834e-05, + "loss": 4.423, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856285169386314e-05, + "loss": 4.4285, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6847899221875794e-05, + "loss": 4.422, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839529653169004e-05, + "loss": 4.4198, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831143705658483e-05, + "loss": 4.421, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.68227741369517e-05, + "loss": 4.4278, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681438818944118e-05, + "loss": 4.4331, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680600224193066e-05, + "loss": 4.4194, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679761629442014e-05, + "loss": 4.4037, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678923034690962e-05, + "loss": 4.4125, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.67808443993991e-05, + "loss": 4.4183, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677245845188858e-05, + "loss": 4.4239, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676407250437806e-05, + "loss": 4.4135, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675570293567127e-05, + "loss": 4.4137, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674731698816075e-05, + "loss": 4.422, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673893104065023e-05, + "loss": 4.4077, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673054509313971e-05, + "loss": 4.408, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672215914562919e-05, + "loss": 4.4132, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671377319811867e-05, + "loss": 4.4043, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670538725060815e-05, + "loss": 4.4239, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669700130309763e-05, + "loss": 4.4081, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668861535558711e-05, + "loss": 4.3943, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668022940807659e-05, + "loss": 4.4074, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.66718598393698e-05, + "loss": 4.405, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666347389185928e-05, + "loss": 4.4209, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665508794434876e-05, + "loss": 4.4088, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664670199683824e-05, + "loss": 4.3992, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.6638332428131446e-05, + "loss": 4.3928, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.6629946480620926e-05, + "loss": 4.4048, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.6621560533110406e-05, + "loss": 4.3879, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661317458559989e-05, + "loss": 4.3987, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660478863808937e-05, + "loss": 4.3945, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659640269057885e-05, + "loss": 4.3951, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658801674306833e-05, + "loss": 4.3852, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657964717436154e-05, + "loss": 4.4041, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657126122685102e-05, + "loss": 4.3877, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.65628752793405e-05, + "loss": 4.3888, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655448933182998e-05, + "loss": 4.3972, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654610338431946e-05, + "loss": 4.3847, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653771743680894e-05, + "loss": 4.407, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529331489298414e-05, + "loss": 4.3941, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6520945541787894e-05, + "loss": 4.396, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512559594277374e-05, + "loss": 4.3851, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650417364676686e-05, + "loss": 4.3915, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649580407806007e-05, + "loss": 4.3912, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487434509353286e-05, + "loss": 4.3799, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479048561842766e-05, + "loss": 4.3956, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470662614332246e-05, + "loss": 4.3899, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646227666682172e-05, + "loss": 4.382, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.64538907193112e-05, + "loss": 4.3838, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644550477180068e-05, + "loss": 4.382, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643711882429016e-05, + "loss": 4.3726, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642873287677964e-05, + "loss": 4.386, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642034692926912e-05, + "loss": 4.3731, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.64119609817586e-05, + "loss": 4.3947, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640359141305181e-05, + "loss": 4.3898, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395205465541295e-05, + "loss": 4.3766, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6386819518030775e-05, + "loss": 4.3757, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378433570520255e-05, + "loss": 4.3752, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370047623009734e-05, + "loss": 4.3854, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361661675499214e-05, + "loss": 4.3823, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353292106792424e-05, + "loss": 4.3775, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6344906159281903e-05, + "loss": 4.3813, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336520211771383e-05, + "loss": 4.3802, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328134264260863e-05, + "loss": 4.3821, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.631974831675034e-05, + "loss": 4.368, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631136236923982e-05, + "loss": 4.3874, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.63029764217293e-05, + "loss": 4.375, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294590474218776e-05, + "loss": 4.3716, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628622090551199e-05, + "loss": 4.3736, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627783495800148e-05, + "loss": 4.3733, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626944901049096e-05, + "loss": 4.3699, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626106306298043e-05, + "loss": 4.3614, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625267711546991e-05, + "loss": 4.3635, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.3503098487854, + "eval_runtime": 298.7878, + "eval_samples_per_second": 1277.13, + "eval_steps_per_second": 39.911, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624430754676313e-05, + "loss": 4.366, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623592159925261e-05, + "loss": 4.3539, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622753565174208e-05, + "loss": 4.3803, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621914970423156e-05, + "loss": 4.3737, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621076375672104e-05, + "loss": 4.371, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620237780921052e-05, + "loss": 4.3565, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.61939918617e-05, + "loss": 4.3692, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618562229299322e-05, + "loss": 4.3488, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.61772363454827e-05, + "loss": 4.3718, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616885039797218e-05, + "loss": 4.3646, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616046445046166e-05, + "loss": 4.3623, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.6152094881754866e-05, + "loss": 4.3719, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.6143708934244346e-05, + "loss": 4.3486, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.6135322986733826e-05, + "loss": 4.3578, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6126937039223306e-05, + "loss": 4.3476, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.6118551091712786e-05, + "loss": 4.3546, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110165144202266e-05, + "loss": 4.3518, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.6101779196691746e-05, + "loss": 4.351, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.6093393249181225e-05, + "loss": 4.3545, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085007301670705e-05, + "loss": 4.374, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6076621354160185e-05, + "loss": 4.3545, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068235406649665e-05, + "loss": 4.3585, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6059849459139145e-05, + "loss": 4.3527, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605149626923609e-05, + "loss": 4.3645, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604311032172557e-05, + "loss": 4.3473, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603472437421505e-05, + "loss": 4.3536, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602633842670453e-05, + "loss": 4.342, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601795247919401e-05, + "loss": 4.3423, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600958291048722e-05, + "loss": 4.3417, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.60011969629767e-05, + "loss": 4.3464, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599281101546618e-05, + "loss": 4.3444, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598442506795566e-05, + "loss": 4.3545, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597603912044514e-05, + "loss": 4.3469, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596765317293462e-05, + "loss": 4.3501, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959283604227835e-05, + "loss": 4.3438, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.5950897656717315e-05, + "loss": 4.3539, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.5942511709206795e-05, + "loss": 4.3321, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593412576169627e-05, + "loss": 4.3447, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592573981418575e-05, + "loss": 4.3244, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591735386667523e-05, + "loss": 4.3428, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590896791916471e-05, + "loss": 4.3352, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590058197165419e-05, + "loss": 4.3491, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589219602414367e-05, + "loss": 4.3286, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588382645543688e-05, + "loss": 4.3387, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587544050792636e-05, + "loss": 4.3403, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586705456041584e-05, + "loss": 4.3472, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585868499170905e-05, + "loss": 4.3398, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585029904419853e-05, + "loss": 4.3289, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584191309668801e-05, + "loss": 4.3185, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583354352798122e-05, + "loss": 4.3417, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.58251575804707e-05, + "loss": 4.3376, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581677163296018e-05, + "loss": 4.3305, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580838568544966e-05, + "loss": 4.3252, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.579999973793914e-05, + "loss": 4.3281, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579161379042862e-05, + "loss": 4.3129, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.57832278429181e-05, + "loss": 4.336, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577484189540758e-05, + "loss": 4.3121, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576645594789706e-05, + "loss": 4.3272, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575808637919027e-05, + "loss": 4.3331, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.574970043167976e-05, + "loss": 4.3224, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574131448416924e-05, + "loss": 4.3169, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573292853665872e-05, + "loss": 4.323, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.57245425891482e-05, + "loss": 4.3082, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571615664163768e-05, + "loss": 4.3169, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570777069412716e-05, + "loss": 4.3294, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569938474661663e-05, + "loss": 4.318, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691015177909846e-05, + "loss": 4.3113, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682629230399326e-05, + "loss": 4.307, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.5674259661692535e-05, + "loss": 4.3167, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.5665873714182015e-05, + "loss": 4.3244, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.5657487766671495e-05, + "loss": 4.3242, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564911819796471e-05, + "loss": 4.3157, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564073225045419e-05, + "loss": 4.3263, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563234630294367e-05, + "loss": 4.3276, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562396035543315e-05, + "loss": 4.3122, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561557440792263e-05, + "loss": 4.3101, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.5607188460412104e-05, + "loss": 4.3195, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.5598802512901584e-05, + "loss": 4.3138, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.5590416565391064e-05, + "loss": 4.3115, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.5582030617880544e-05, + "loss": 4.309, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.5573644670370024e-05, + "loss": 4.3161, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556527510166323e-05, + "loss": 4.3218, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555688915415271e-05, + "loss": 4.3123, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554850320664219e-05, + "loss": 4.2978, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554011725913168e-05, + "loss": 4.2994, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553174769042489e-05, + "loss": 4.3071, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552336174291437e-05, + "loss": 4.3161, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551497579540385e-05, + "loss": 4.3091, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550658984789333e-05, + "loss": 4.3011, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549820390038281e-05, + "loss": 4.3141, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.548981795287229e-05, + "loss": 4.3055, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548143200536177e-05, + "loss": 4.3014, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547304605785125e-05, + "loss": 4.3026, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546467648914446e-05, + "loss": 4.307, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545629054163394e-05, + "loss": 4.3167, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544790459412342e-05, + "loss": 4.2978, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.54395186466129e-05, + "loss": 4.2884, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543114907790611e-05, + "loss": 4.3041, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542276313039559e-05, + "loss": 4.3004, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541437718288507e-05, + "loss": 4.3134, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540599123537455e-05, + "loss": 4.3062, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539762166666776e-05, + "loss": 4.2939, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538923571915724e-05, + "loss": 4.2904, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538086615045045e-05, + "loss": 4.3045, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537248020293993e-05, + "loss": 4.2848, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536409425542941e-05, + "loss": 4.2953, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535570830791889e-05, + "loss": 4.2902, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534732236040837e-05, + "loss": 4.2965, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533893641289785e-05, + "loss": 4.2843, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533055046538733e-05, + "loss": 4.3029, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322180896680547e-05, + "loss": 4.2869, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5313794949170027e-05, + "loss": 4.2844, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305409001659507e-05, + "loss": 4.3002, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297023054148986e-05, + "loss": 4.2845, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528863710663846e-05, + "loss": 4.3092, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528025115912794e-05, + "loss": 4.2978, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527186521161742e-05, + "loss": 4.2939, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.5263495642910635e-05, + "loss": 4.2864, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525510969540011e-05, + "loss": 4.2907, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524672374788959e-05, + "loss": 4.29, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523833780037907e-05, + "loss": 4.283, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.522995185286855e-05, + "loss": 4.2968, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.5221565905358035e-05, + "loss": 4.2914, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.5213179957847515e-05, + "loss": 4.2847, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.5204794010336995e-05, + "loss": 4.2842, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.5196424441630204e-05, + "loss": 4.2854, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.5188038494119684e-05, + "loss": 4.2774, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517966892541289e-05, + "loss": 4.2936, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517128297790237e-05, + "loss": 4.2761, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516289703039185e-05, + "loss": 4.297, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515451108288133e-05, + "loss": 4.289, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514614151417454e-05, + "loss": 4.2876, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513775556666402e-05, + "loss": 4.2785, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512938599795724e-05, + "loss": 4.2813, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512100005044672e-05, + "loss": 4.2909, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.51126141029362e-05, + "loss": 4.2895, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510422815542568e-05, + "loss": 4.2791, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509584220791516e-05, + "loss": 4.2875, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508745626040464e-05, + "loss": 4.2858, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507907031289412e-05, + "loss": 4.2912, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.50706843653836e-05, + "loss": 4.2776, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506229841787308e-05, + "loss": 4.294, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505392884916629e-05, + "loss": 4.2847, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504554290165577e-05, + "loss": 4.2784, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503715695414525e-05, + "loss": 4.2796, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502877100663473e-05, + "loss": 4.2858, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502038505912421e-05, + "loss": 4.2772, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5011999111613687e-05, + "loss": 4.2655, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500361316410317e-05, + "loss": 4.2807, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 4.267075538635254, + "eval_runtime": 298.4528, + "eval_samples_per_second": 1278.564, + "eval_steps_per_second": 39.956, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499522721659265e-05, + "loss": 4.2696, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4986841269082126e-05, + "loss": 4.2637, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978455321571606e-05, + "loss": 4.2863, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970069374061086e-05, + "loss": 4.2831, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4961683426550566e-05, + "loss": 4.2807, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953297479040046e-05, + "loss": 4.2735, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4944911531529526e-05, + "loss": 4.2768, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936525584019006e-05, + "loss": 4.257, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928139636508486e-05, + "loss": 4.2819, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4919753688997966e-05, + "loss": 4.2777, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911367741487446e-05, + "loss": 4.2724, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4902981793976926e-05, + "loss": 4.2839, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4894612225270135e-05, + "loss": 4.2619, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488622627775962e-05, + "loss": 4.271, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.48778403302491e-05, + "loss": 4.2626, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486945438273858e-05, + "loss": 4.2609, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486106843522806e-05, + "loss": 4.2666, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485268248771754e-05, + "loss": 4.2643, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844296540207015e-05, + "loss": 4.2683, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4835910592696495e-05, + "loss": 4.2839, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482754102398971e-05, + "loss": 4.2714, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.4819155076479184e-05, + "loss": 4.2754, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.4810769128968664e-05, + "loss": 4.2652, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480239956026188e-05, + "loss": 4.2746, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479401361275136e-05, + "loss": 4.2626, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478562766524084e-05, + "loss": 4.2673, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477724171773032e-05, + "loss": 4.2616, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.47688557702198e-05, + "loss": 4.2554, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476046982270928e-05, + "loss": 4.2552, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475208387519876e-05, + "loss": 4.2622, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474369792768824e-05, + "loss": 4.2621, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473531198017772e-05, + "loss": 4.2702, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.47269260326672e-05, + "loss": 4.2639, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471854008515668e-05, + "loss": 4.266, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471015413764616e-05, + "loss": 4.259, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470178456893937e-05, + "loss": 4.2701, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469339862142885e-05, + "loss": 4.2518, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468501267391833e-05, + "loss": 4.2591, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467662672640781e-05, + "loss": 4.2439, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668257157701024e-05, + "loss": 4.2582, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.4659871210190504e-05, + "loss": 4.2545, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465150164148371e-05, + "loss": 4.2653, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464311569397319e-05, + "loss": 4.2483, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463472974646267e-05, + "loss": 4.2577, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462634379895215e-05, + "loss": 4.2588, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461795785144163e-05, + "loss": 4.2625, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460958828273484e-05, + "loss": 4.2589, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460120233522432e-05, + "loss": 4.2471, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.45928163877138e-05, + "loss": 4.2369, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458443044020328e-05, + "loss": 4.2645, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457604449269276e-05, + "loss": 4.2558, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456765854518224e-05, + "loss": 4.2491, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455928897647546e-05, + "loss": 4.2494, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455090302896494e-05, + "loss": 4.2469, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454251708145442e-05, + "loss": 4.2327, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.45341311339439e-05, + "loss": 4.2507, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452574518643337e-05, + "loss": 4.2367, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517375617726587e-05, + "loss": 4.2449, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4508989670216067e-05, + "loss": 4.2563, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4500603722705546e-05, + "loss": 4.2427, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449221777519502e-05, + "loss": 4.2367, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4483848206488236e-05, + "loss": 4.2496, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475462258977715e-05, + "loss": 4.2274, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.4467076311467195e-05, + "loss": 4.2394, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.4458690363956675e-05, + "loss": 4.2469, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.4450304416446155e-05, + "loss": 4.2431, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4441918468935635e-05, + "loss": 4.2351, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.4433532521425115e-05, + "loss": 4.2344, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425162952718324e-05, + "loss": 4.2355, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.4416777005207804e-05, + "loss": 4.2467, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.4408391057697284e-05, + "loss": 4.2466, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.4400005110186764e-05, + "loss": 4.2405, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.4391619162676244e-05, + "loss": 4.2489, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.4383233215165724e-05, + "loss": 4.2513, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437486364645893e-05, + "loss": 4.2381, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436647769894841e-05, + "loss": 4.2295, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.43580917514379e-05, + "loss": 4.2491, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.434970580392738e-05, + "loss": 4.2398, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434131985641686e-05, + "loss": 4.2321, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433295028771007e-05, + "loss": 4.2354, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432456434019955e-05, + "loss": 4.2416, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431617839268903e-05, + "loss": 4.2501, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430779244517851e-05, + "loss": 4.2334, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429942287647172e-05, + "loss": 4.2232, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.42910369289612e-05, + "loss": 4.2317, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428265098145068e-05, + "loss": 4.2276, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427426503394016e-05, + "loss": 4.2415, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426587908642964e-05, + "loss": 4.2359, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425749313891912e-05, + "loss": 4.2248, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.42491071914086e-05, + "loss": 4.2399, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4240721243898084e-05, + "loss": 4.2299, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232351675191293e-05, + "loss": 4.2326, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4223965727680773e-05, + "loss": 4.2266, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421557978017025e-05, + "loss": 4.2331, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420719383265973e-05, + "loss": 4.2442, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4198807885149206e-05, + "loss": 4.2317, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190421937638686e-05, + "loss": 4.214, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182035990128166e-05, + "loss": 4.2297, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4173650042617646e-05, + "loss": 4.2308, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416529685271459e-05, + "loss": 4.2371, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415691090520407e-05, + "loss": 4.2374, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414852495769355e-05, + "loss": 4.2236, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414013901018303e-05, + "loss": 4.2181, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413175306267251e-05, + "loss": 4.2319, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412338349396573e-05, + "loss": 4.2106, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411499754645521e-05, + "loss": 4.2258, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410661159894468e-05, + "loss": 4.2196, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409822565143416e-05, + "loss": 4.2265, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.408983970392364e-05, + "loss": 4.2149, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408145375641312e-05, + "loss": 4.2306, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407308418770633e-05, + "loss": 4.2151, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406469824019581e-05, + "loss": 4.2147, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405631229268529e-05, + "loss": 4.2305, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.4047926345174776e-05, + "loss": 4.2195, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4039540397664256e-05, + "loss": 4.2371, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031154450153736e-05, + "loss": 4.2277, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.4022784881446945e-05, + "loss": 4.2216, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.4014398933936425e-05, + "loss": 4.2266, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.4006012986425905e-05, + "loss": 4.215, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.3997627038915385e-05, + "loss": 4.2253, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.3989241091404865e-05, + "loss": 4.2133, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.3980871522698074e-05, + "loss": 4.2301, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.3972485575187554e-05, + "loss": 4.2177, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396411600648076e-05, + "loss": 4.2163, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395573005897024e-05, + "loss": 4.2159, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394734411145973e-05, + "loss": 4.2206, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393895816394921e-05, + "loss": 4.21, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393057221643869e-05, + "loss": 4.2243, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392218626892817e-05, + "loss": 4.2099, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391380032141765e-05, + "loss": 4.23, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390541437390713e-05, + "loss": 4.2195, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389702842639661e-05, + "loss": 4.2217, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388864247888609e-05, + "loss": 4.2135, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388025653137557e-05, + "loss": 4.2127, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387187058386504e-05, + "loss": 4.2275, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386350101515826e-05, + "loss": 4.2195, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385511506764774e-05, + "loss": 4.2104, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384672912013722e-05, + "loss": 4.2236, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.38383431726267e-05, + "loss": 4.218, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.382995722511618e-05, + "loss": 4.2266, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382157127760566e-05, + "loss": 4.2119, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381318533009514e-05, + "loss": 4.2238, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380483214019208e-05, + "loss": 4.2177, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379644619268156e-05, + "loss": 4.2127, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378806024517104e-05, + "loss": 4.2166, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3779674297660516e-05, + "loss": 4.2168, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771288350149996e-05, + "loss": 4.2151, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3762902402639476e-05, + "loss": 4.2014, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3754516455128956e-05, + "loss": 4.2148, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 4.210258960723877, + "eval_runtime": 298.139, + "eval_samples_per_second": 1279.91, + "eval_steps_per_second": 39.998, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.3746130507618436e-05, + "loss": 4.2084, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.3737744560107916e-05, + "loss": 4.2003, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.3729358612597396e-05, + "loss": 4.2206, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.3720972665086876e-05, + "loss": 4.2213, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371260309638009e-05, + "loss": 4.2147, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370421714886957e-05, + "loss": 4.2099, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369583120135905e-05, + "loss": 4.2104, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368744525384853e-05, + "loss": 4.1984, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367905930633801e-05, + "loss": 4.2136, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367067335882749e-05, + "loss": 4.2181, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366228741131697e-05, + "loss": 4.2094, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365390146380645e-05, + "loss": 4.2173, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364554827390339e-05, + "loss": 4.2043, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363716232639287e-05, + "loss": 4.2101, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362877637888235e-05, + "loss": 4.1988, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362039043137183e-05, + "loss": 4.1975, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.3612004483861316e-05, + "loss": 4.2022, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.3603618536350796e-05, + "loss": 4.2017, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.3595232588840276e-05, + "loss": 4.2053, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.3586846641329756e-05, + "loss": 4.2165, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.3578477072622965e-05, + "loss": 4.2147, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.3570091125112445e-05, + "loss": 4.2127, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.3561721556405654e-05, + "loss": 4.2022, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.3553335608895134e-05, + "loss": 4.2141, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.3544949661384614e-05, + "loss": 4.1977, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.3536563713874094e-05, + "loss": 4.209, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.3528177766363574e-05, + "loss": 4.1981, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.3519791818853054e-05, + "loss": 4.1914, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.3511405871342534e-05, + "loss": 4.199, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.3503019923832014e-05, + "loss": 4.1964, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349465035512523e-05, + "loss": 4.2033, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.34862644076147e-05, + "loss": 4.2066, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347787846010418e-05, + "loss": 4.2079, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.34695088913974e-05, + "loss": 4.2067, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346113932269061e-05, + "loss": 4.1963, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345275337518009e-05, + "loss": 4.207, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344436742766957e-05, + "loss": 4.1954, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343598148015905e-05, + "loss": 4.1928, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342759553264852e-05, + "loss": 4.1901, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341920958513801e-05, + "loss": 4.1958, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341082363762749e-05, + "loss": 4.1995, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340243769011697e-05, + "loss": 4.2033, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339405174260645e-05, + "loss": 4.1904, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338566579509593e-05, + "loss": 4.197, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337727984758541e-05, + "loss": 4.2014, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336889390007489e-05, + "loss": 4.2018, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3360524331368096e-05, + "loss": 4.2036, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.3352154762661305e-05, + "loss": 4.189, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.3343768815150785e-05, + "loss": 4.1747, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.3335382867640265e-05, + "loss": 4.2073, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.3326996920129745e-05, + "loss": 4.1979, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.3318610972619225e-05, + "loss": 4.1945, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331024140391244e-05, + "loss": 4.193, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330185545640192e-05, + "loss": 4.1838, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329348588769513e-05, + "loss": 4.1783, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328509994018461e-05, + "loss": 4.1908, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327671399267409e-05, + "loss": 4.1778, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326832804516357e-05, + "loss": 4.1876, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.325994209765305e-05, + "loss": 4.1991, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325155615014253e-05, + "loss": 4.1848, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324317020263201e-05, + "loss": 4.1787, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323478425512149e-05, + "loss": 4.194, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322639830761097e-05, + "loss": 4.1728, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321801236010045e-05, + "loss": 4.1786, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.320962641258993e-05, + "loss": 4.1907, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320125684388314e-05, + "loss": 4.1879, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.3192870896372626e-05, + "loss": 4.1772, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3184484948862106e-05, + "loss": 4.1777, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.3176099001351586e-05, + "loss": 4.1769, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.3167713053841065e-05, + "loss": 4.1864, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315932710633054e-05, + "loss": 4.1921, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315094115882002e-05, + "loss": 4.1817, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.3142571590113234e-05, + "loss": 4.1914, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.3134185642602714e-05, + "loss": 4.1954, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.3125816073895924e-05, + "loss": 4.1902, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.3117430126385403e-05, + "loss": 4.1701, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109044178874883e-05, + "loss": 4.1905, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.3100658231364363e-05, + "loss": 4.1873, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309227228385384e-05, + "loss": 4.1729, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308388633634332e-05, + "loss": 4.1847, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.30755003888328e-05, + "loss": 4.1818, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306711444132228e-05, + "loss": 4.1937, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305872849381176e-05, + "loss": 4.1798, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305035892510497e-05, + "loss": 4.1619, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304197297759445e-05, + "loss": 4.1803, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303358703008393e-05, + "loss": 4.1753, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302520108257341e-05, + "loss": 4.1823, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301681513506289e-05, + "loss": 4.1798, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.30084455663561e-05, + "loss": 4.1716, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300005961884558e-05, + "loss": 4.1811, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299167367133506e-05, + "loss": 4.179, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298328772382455e-05, + "loss": 4.1725, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297490177631403e-05, + "loss": 4.176, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296653220760724e-05, + "loss": 4.1836, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295814626009672e-05, + "loss": 4.1891, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.29497603125862e-05, + "loss": 4.1754, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294137436507568e-05, + "loss": 4.1634, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293298841756516e-05, + "loss": 4.1737, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292460247005464e-05, + "loss": 4.1758, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291621652254412e-05, + "loss": 4.1842, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.2907846953837326e-05, + "loss": 4.1843, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.2899461006326806e-05, + "loss": 4.1659, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.2891075058816286e-05, + "loss": 4.1681, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.2882689111305766e-05, + "loss": 4.1811, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.2874303163795246e-05, + "loss": 4.1582, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286593359508846e-05, + "loss": 4.1752, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285756402638167e-05, + "loss": 4.1625, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284917807887115e-05, + "loss": 4.1754, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284079213136063e-05, + "loss": 4.1624, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283240618385011e-05, + "loss": 4.1773, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282402023633959e-05, + "loss": 4.1692, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281563428882907e-05, + "loss": 4.159, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807248341318543e-05, + "loss": 4.179, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2798862393808023e-05, + "loss": 4.1635, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279049282510124e-05, + "loss": 4.1856, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278210687759072e-05, + "loss": 4.1788, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.2773737308883935e-05, + "loss": 4.1674, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2765351361373415e-05, + "loss": 4.1778, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.2756965413862895e-05, + "loss": 4.1628, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2748579466352375e-05, + "loss": 4.1693, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274019351884185e-05, + "loss": 4.1674, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273180757133133e-05, + "loss": 4.1763, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272342162382081e-05, + "loss": 4.1664, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271503567631029e-05, + "loss": 4.164, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270664972879977e-05, + "loss": 4.1684, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269826378128925e-05, + "loss": 4.1667, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.268987783377873e-05, + "loss": 4.1572, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268150826507194e-05, + "loss": 4.1738, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267312231756142e-05, + "loss": 4.156, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.2664736370050904e-05, + "loss": 4.1855, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.2656350422540384e-05, + "loss": 4.1628, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264798085383359e-05, + "loss": 4.1739, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.263959490632307e-05, + "loss": 4.1608, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263120895881255e-05, + "loss": 4.1674, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.262282301130203e-05, + "loss": 4.1762, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261445344259524e-05, + "loss": 4.1679, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260606749508472e-05, + "loss": 4.1644, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.25976815475742e-05, + "loss": 4.1753, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258929560006368e-05, + "loss": 4.1684, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258092603135689e-05, + "loss": 4.1751, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257254008384637e-05, + "loss": 4.158, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256415413633586e-05, + "loss": 4.1733, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255576818882534e-05, + "loss": 4.167, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254738224131482e-05, + "loss": 4.1652, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.25389962938043e-05, + "loss": 4.1689, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253061034629378e-05, + "loss": 4.1658, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252222439878326e-05, + "loss": 4.1728, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.2513854830076466e-05, + "loss": 4.1443, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.2505485261369675e-05, + "loss": 4.1712, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 4.1686110496521, + "eval_runtime": 297.5283, + "eval_samples_per_second": 1282.537, + "eval_steps_per_second": 40.08, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2497099313859155e-05, + "loss": 4.1608, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.2488713366348635e-05, + "loss": 4.1521, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2480327418838115e-05, + "loss": 4.1693, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2471941471327595e-05, + "loss": 4.1733, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2463555523817075e-05, + "loss": 4.1635, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455169576306555e-05, + "loss": 4.1594, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2446783628796035e-05, + "loss": 4.1626, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.2438397681285515e-05, + "loss": 4.1519, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.2430011733774995e-05, + "loss": 4.1641, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2421625786264475e-05, + "loss": 4.1665, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413239838753955e-05, + "loss": 4.1673, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.2404853891243435e-05, + "loss": 4.1654, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.2396484322536644e-05, + "loss": 4.1582, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388098375026124e-05, + "loss": 4.1594, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2379712427515604e-05, + "loss": 4.1499, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2371326480005084e-05, + "loss": 4.1461, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2362940532494564e-05, + "loss": 4.1551, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2354554584984044e-05, + "loss": 4.1518, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346168637473524e-05, + "loss": 4.1572, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233778268996301e-05, + "loss": 4.1687, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.232939674245249e-05, + "loss": 4.1689, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232101079494197e-05, + "loss": 4.1637, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231262484743145e-05, + "loss": 4.1556, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230425527872466e-05, + "loss": 4.1648, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229586933121414e-05, + "loss": 4.1517, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228748338370362e-05, + "loss": 4.1636, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227909743619309e-05, + "loss": 4.1539, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227071148868257e-05, + "loss": 4.1412, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226234191997579e-05, + "loss": 4.1546, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225395597246527e-05, + "loss": 4.1497, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224557002495475e-05, + "loss": 4.1544, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223720045624796e-05, + "loss": 4.1617, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2228814508737444e-05, + "loss": 4.1589, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2220428561226924e-05, + "loss": 4.1593, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.22120426137164e-05, + "loss": 4.1496, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220365666620588e-05, + "loss": 4.1664, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219527071869536e-05, + "loss": 4.148, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2186901149988566e-05, + "loss": 4.1426, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2178515202478046e-05, + "loss": 4.1497, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170129254967526e-05, + "loss": 4.1438, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2161743307457006e-05, + "loss": 4.1537, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2153357359946486e-05, + "loss": 4.161, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2144971412435966e-05, + "loss": 4.142, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2136585464925446e-05, + "loss": 4.1502, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128199517414926e-05, + "loss": 4.1581, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.211981356990441e-05, + "loss": 4.1594, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211144400119762e-05, + "loss": 4.1582, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.21030580536871e-05, + "loss": 4.1451, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209467210617658e-05, + "loss": 4.1225, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208628615866606e-05, + "loss": 4.1642, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207790021115554e-05, + "loss": 4.1525, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.206953064244875e-05, + "loss": 4.1529, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206114469493823e-05, + "loss": 4.1443, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205275874742771e-05, + "loss": 4.1394, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204437279991719e-05, + "loss": 4.1345, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.20360032312104e-05, + "loss": 4.1417, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202761728369988e-05, + "loss": 4.1368, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2019231336189366e-05, + "loss": 4.143, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2010845388678846e-05, + "loss": 4.1565, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.2002459441168326e-05, + "loss": 4.1368, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994073493657806e-05, + "loss": 4.1346, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.1985687546147286e-05, + "loss": 4.1503, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197730159863676e-05, + "loss": 4.1329, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.1968932029929975e-05, + "loss": 4.1353, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.1960546082419455e-05, + "loss": 4.1425, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195216013490893e-05, + "loss": 4.1441, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194377418739841e-05, + "loss": 4.1323, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.1935404618691624e-05, + "loss": 4.1328, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927018671181104e-05, + "loss": 4.1323, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191864910247432e-05, + "loss": 4.1471, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.19102631549638e-05, + "loss": 4.1446, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190187720745328e-05, + "loss": 4.1411, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189349125994276e-05, + "loss": 4.1441, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188510531243223e-05, + "loss": 4.1506, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187675212252918e-05, + "loss": 4.1478, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186836617501866e-05, + "loss": 4.1309, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.185998022750814e-05, + "loss": 4.1424, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185159427999762e-05, + "loss": 4.1475, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.18432083324871e-05, + "loss": 4.1269, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183482238497658e-05, + "loss": 4.1416, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182643643746606e-05, + "loss": 4.1403, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818066868759274e-05, + "loss": 4.1474, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.1809680921248753e-05, + "loss": 4.1388, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180129497373823e-05, + "loss": 4.1207, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179290902622771e-05, + "loss": 4.1343, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1784523078717187e-05, + "loss": 4.1322, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776137131206667e-05, + "loss": 4.1433, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1767751183696146e-05, + "loss": 4.1345, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1759365236185626e-05, + "loss": 4.1319, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1750979288675106e-05, + "loss": 4.1367, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1742593341164586e-05, + "loss": 4.1409, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1734207393654066e-05, + "loss": 4.1251, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1725821446143546e-05, + "loss": 4.1321, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1717451877436755e-05, + "loss": 4.1441, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170906592992624e-05, + "loss": 4.1455, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170067998241572e-05, + "loss": 4.1323, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.16922940349052e-05, + "loss": 4.1233, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168392446619841e-05, + "loss": 4.1309, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167553851868789e-05, + "loss": 4.1307, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166715257117737e-05, + "loss": 4.1424, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165876662366685e-05, + "loss": 4.1435, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165038067615633e-05, + "loss": 4.1293, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164199472864581e-05, + "loss": 4.1265, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163360878113529e-05, + "loss": 4.1346, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.16252392124285e-05, + "loss": 4.1184, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161685326491798e-05, + "loss": 4.1331, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160846731740746e-05, + "loss": 4.1171, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160008136989694e-05, + "loss": 4.1337, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159169542238642e-05, + "loss": 4.1238, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.15833094748759e-05, + "loss": 4.1328, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157492352736538e-05, + "loss": 4.1263, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156653757985486e-05, + "loss": 4.1231, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155816801114807e-05, + "loss": 4.134, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.1549798442441285e-05, + "loss": 4.1222, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.1541412494930765e-05, + "loss": 4.1468, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153302654742024e-05, + "loss": 4.1369, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152464059990972e-05, + "loss": 4.1285, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.1516271031202934e-05, + "loss": 4.1365, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.1507885083692414e-05, + "loss": 4.1194, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.1499499136181893e-05, + "loss": 4.1295, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.1491113188671373e-05, + "loss": 4.1287, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148272724116085e-05, + "loss": 4.1311, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147434129365033e-05, + "loss": 4.1269, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146597172494354e-05, + "loss": 4.126, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145758577743302e-05, + "loss": 4.1291, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.14491998299225e-05, + "loss": 4.1264, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144081388241198e-05, + "loss": 4.1203, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143242793490146e-05, + "loss": 4.1329, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142404198739094e-05, + "loss": 4.1134, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141565603988042e-05, + "loss": 4.1415, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.14072700923699e-05, + "loss": 4.1269, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139888414485938e-05, + "loss": 4.1324, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139049819734886e-05, + "loss": 4.1159, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138211224983834e-05, + "loss": 4.1302, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137372630232783e-05, + "loss": 4.1348, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136534035481731e-05, + "loss": 4.1299, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135697078611052e-05, + "loss": 4.1205, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.13485848386e-05, + "loss": 4.1358, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134019889108948e-05, + "loss": 4.1277, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133182932238269e-05, + "loss": 4.1372, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132344337487217e-05, + "loss": 4.1176, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131505742736165e-05, + "loss": 4.1347, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130667147985113e-05, + "loss": 4.1277, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1298301911144336e-05, + "loss": 4.1264, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.128993234243755e-05, + "loss": 4.1281, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128154639492703e-05, + "loss": 4.1276, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127316044741651e-05, + "loss": 4.1289, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126477449990599e-05, + "loss": 4.1097, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125638855239547e-05, + "loss": 4.1325, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.1370439529418945, + "eval_runtime": 292.5057, + "eval_samples_per_second": 1304.559, + "eval_steps_per_second": 40.768, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124800260488495e-05, + "loss": 4.1186, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.1239616657374425e-05, + "loss": 4.1132, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.1231230709863905e-05, + "loss": 4.1264, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122287751996085e-05, + "loss": 4.1326, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121449157245033e-05, + "loss": 4.1245, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120610562493981e-05, + "loss": 4.1218, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119771967742929e-05, + "loss": 4.1283, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.1189350108722505e-05, + "loss": 4.1124, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.1180964161211985e-05, + "loss": 4.1258, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.1172578213701465e-05, + "loss": 4.1276, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.1164192266190945e-05, + "loss": 4.1263, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.1155822697484154e-05, + "loss": 4.1284, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.1147436749973634e-05, + "loss": 4.1186, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.1139050802463114e-05, + "loss": 4.119, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.1130664854952594e-05, + "loss": 4.1151, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.1122278907442074e-05, + "loss": 4.1059, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111390933873528e-05, + "loss": 4.1192, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110552339122476e-05, + "loss": 4.1133, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109713744371424e-05, + "loss": 4.1171, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108875149620372e-05, + "loss": 4.1283, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108038192749694e-05, + "loss": 4.1328, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107199597998642e-05, + "loss": 4.1298, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.10636100324759e-05, + "loss": 4.1149, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105522408496537e-05, + "loss": 4.125, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104683813745485e-05, + "loss": 4.1155, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103845218994433e-05, + "loss": 4.1233, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103008262123755e-05, + "loss": 4.1171, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102171305253076e-05, + "loss": 4.1054, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101332710502024e-05, + "loss": 4.1195, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100494115750972e-05, + "loss": 4.1078, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.09965552099992e-05, + "loss": 4.1159, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988185641292406e-05, + "loss": 4.1244, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.097979969378189e-05, + "loss": 4.1195, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097141374627137e-05, + "loss": 4.1207, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963027798760846e-05, + "loss": 4.1108, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0954641851250326e-05, + "loss": 4.1301, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0946255903739806e-05, + "loss": 4.1145, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0937869956229286e-05, + "loss": 4.1041, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0929484008718766e-05, + "loss": 4.1143, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921114440011975e-05, + "loss": 4.1062, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0912728492501455e-05, + "loss": 4.1144, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0904342544990935e-05, + "loss": 4.1185, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.0895956597480414e-05, + "loss": 4.1117, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.0887570649969894e-05, + "loss": 4.1106, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.0879184702459374e-05, + "loss": 4.1203, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087079875494886e-05, + "loss": 4.1204, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086241280743834e-05, + "loss": 4.124, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085404323873155e-05, + "loss": 4.1064, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084565729122103e-05, + "loss": 4.0854, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083727134371051e-05, + "loss": 4.1318, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082890177500372e-05, + "loss": 4.113, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.08205158274932e-05, + "loss": 4.1189, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081212987998268e-05, + "loss": 4.1113, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080374393247216e-05, + "loss": 4.1002, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079535798496164e-05, + "loss": 4.1004, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078697203745112e-05, + "loss": 4.1068, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.07785860899406e-05, + "loss": 4.099, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077020014243008e-05, + "loss": 4.1035, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0761830573723295e-05, + "loss": 4.1235, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0753444626212775e-05, + "loss": 4.0992, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.0745058678702255e-05, + "loss": 4.0965, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0736672731191735e-05, + "loss": 4.1175, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.0728303162484944e-05, + "loss": 4.0938, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.071993359377815e-05, + "loss": 4.0995, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071154764626763e-05, + "loss": 4.1087, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070316169875711e-05, + "loss": 4.1084, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069477575124659e-05, + "loss": 4.0953, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068638980373607e-05, + "loss": 4.1047, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067800385622555e-05, + "loss": 4.0914, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.066963428751877e-05, + "loss": 4.1113, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066124834000825e-05, + "loss": 4.109, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065286239249773e-05, + "loss": 4.1046, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064447644498721e-05, + "loss": 4.1093, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063609049747668e-05, + "loss": 4.1103, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062770454996616e-05, + "loss": 4.1171, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.061931860245564e-05, + "loss": 4.0953, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.061093265494512e-05, + "loss": 4.1071, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0602579465042066e-05, + "loss": 4.1127, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0594193517531546e-05, + "loss": 4.0875, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0585807570021026e-05, + "loss": 4.1099, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0577421622510506e-05, + "loss": 4.1023, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569035674999986e-05, + "loss": 4.1152, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0560649727489466e-05, + "loss": 4.1068, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0552263779978946e-05, + "loss": 4.0897, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0543877832468426e-05, + "loss": 4.0924, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.0535491884957906e-05, + "loss": 4.1015, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.0527122316251115e-05, + "loss": 4.1104, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.0518736368740595e-05, + "loss": 4.0962, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.0510350421230075e-05, + "loss": 4.0982, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.0501980852523284e-05, + "loss": 4.1009, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.0493594905012764e-05, + "loss": 4.1062, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.0485208957502244e-05, + "loss": 4.0958, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047683938879546e-05, + "loss": 4.0973, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046845344128494e-05, + "loss": 4.108, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046006749377442e-05, + "loss": 4.11, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.04516815462639e-05, + "loss": 4.1011, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044329559875338e-05, + "loss": 4.089, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043490965124286e-05, + "loss": 4.0985, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042652370373234e-05, + "loss": 4.0945, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041813775622182e-05, + "loss": 4.1104, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.04097518087113e-05, + "loss": 4.1038, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040136586120078e-05, + "loss": 4.0983, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039297991369026e-05, + "loss": 4.0946, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038459396617974e-05, + "loss": 4.0944, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037622439747295e-05, + "loss": 4.0873, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036783844996243e-05, + "loss": 4.0975, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.035945250245191e-05, + "loss": 4.0842, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035106655494139e-05, + "loss": 4.1018, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0342713365038333e-05, + "loss": 4.0918, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033432741752781e-05, + "loss": 4.0953, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032594147001729e-05, + "loss": 4.0921, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031755552250677e-05, + "loss": 4.089, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030916957499625e-05, + "loss": 4.1028, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030078362748573e-05, + "loss": 4.09, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029239767997521e-05, + "loss": 4.1127, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284011732464686e-05, + "loss": 4.1041, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0275625784954166e-05, + "loss": 4.0955, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026725621624738e-05, + "loss": 4.0998, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025887026873686e-05, + "loss": 4.089, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025048432122634e-05, + "loss": 4.0945, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024209837371582e-05, + "loss": 4.1008, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023372880500904e-05, + "loss": 4.0945, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022534285749852e-05, + "loss": 4.0949, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021695690998799e-05, + "loss": 4.0949, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020857096247747e-05, + "loss": 4.0948, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020018501496695e-05, + "loss": 4.0951, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019181544626016e-05, + "loss": 4.0836, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018342949874964e-05, + "loss": 4.098, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017504355123912e-05, + "loss": 4.085, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.01666576037286e-05, + "loss": 4.1096, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0158288035021816e-05, + "loss": 4.094, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.0149902087511296e-05, + "loss": 4.0969, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.0141516140000776e-05, + "loss": 4.0853, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.0133130192490256e-05, + "loss": 4.0975, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.0124744244979736e-05, + "loss": 4.0994, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.0116374676272945e-05, + "loss": 4.0981, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.0107988728762425e-05, + "loss": 4.0908, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.0099602781251905e-05, + "loss": 4.1024, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.0091233212545114e-05, + "loss": 4.0937, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.0082847265034594e-05, + "loss": 4.1088, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.0074461317524074e-05, + "loss": 4.085, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.0066075370013554e-05, + "loss": 4.1026, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.0057689422503034e-05, + "loss": 4.0952, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.0049303474992513e-05, + "loss": 4.0942, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.0040917527482e-05, + "loss": 4.0967, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003253157997148e-05, + "loss": 4.0944, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002414563246096e-05, + "loss": 4.0967, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001575968495044e-05, + "loss": 4.0783, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000737373743992e-05, + "loss": 4.0986, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 4.112791061401367, + "eval_runtime": 293.9671, + "eval_samples_per_second": 1298.074, + "eval_steps_per_second": 40.566, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.99989877899294e-05, + "loss": 4.0834, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999060184241887e-05, + "loss": 4.0815, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998221589490835e-05, + "loss": 4.0927, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997382994739783e-05, + "loss": 4.1024, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996544399988731e-05, + "loss": 4.0953, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995705805237679e-05, + "loss": 4.0876, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994867210486627e-05, + "loss": 4.1019, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994028615735575e-05, + "loss": 4.0795, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993190020984523e-05, + "loss": 4.0898, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992351426233471e-05, + "loss": 4.0994, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991512831482419e-05, + "loss": 4.0931, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990675874611741e-05, + "loss": 4.0943, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989837279860689e-05, + "loss": 4.0942, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.988998685109637e-05, + "loss": 4.0822, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988160090358585e-05, + "loss": 4.0802, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987321495607533e-05, + "loss": 4.0762, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986482900856481e-05, + "loss": 4.0851, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985644306105429e-05, + "loss": 4.0864, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984805711354376e-05, + "loss": 4.0837, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.983967116603324e-05, + "loss": 4.0947, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983128521852272e-05, + "loss": 4.1015, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.98228992710122e-05, + "loss": 4.0989, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981451332350168e-05, + "loss": 4.0868, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980612737599116e-05, + "loss": 4.0896, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979774142848065e-05, + "loss": 4.0908, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.978935548097013e-05, + "loss": 4.0874, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978098591226334e-05, + "loss": 4.0885, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977259996475282e-05, + "loss": 4.0789, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.97642140172423e-05, + "loss": 4.0872, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975582806973178e-05, + "loss": 4.0778, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974744212222126e-05, + "loss": 4.0828, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973905617471074e-05, + "loss": 4.0933, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.9730686606003946e-05, + "loss": 4.0919, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.9722300658493426e-05, + "loss": 4.09, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.9713914710982906e-05, + "loss": 4.0846, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.9705545142276115e-05, + "loss": 4.0909, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.96971591947656e-05, + "loss": 4.0876, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968877324725508e-05, + "loss": 4.0762, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968038729974456e-05, + "loss": 4.0846, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967200135223404e-05, + "loss": 4.0739, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966361540472352e-05, + "loss": 4.0826, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.9655229457213e-05, + "loss": 4.0897, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964684350970248e-05, + "loss": 4.079, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.9638457562191955e-05, + "loss": 4.0826, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9630071614681435e-05, + "loss": 4.0927, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9621685667170915e-05, + "loss": 4.0882, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.9613299719660395e-05, + "loss": 4.0902, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.9604930150953604e-05, + "loss": 4.08, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.9596544203443084e-05, + "loss": 4.0562, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958815825593257e-05, + "loss": 4.0975, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.957977230842205e-05, + "loss": 4.0834, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957140273971526e-05, + "loss": 4.0872, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956301679220474e-05, + "loss": 4.0824, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955463084469422e-05, + "loss": 4.0729, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.95462448971837e-05, + "loss": 4.0683, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953787532847691e-05, + "loss": 4.0779, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.952948938096639e-05, + "loss": 4.0706, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952110343345587e-05, + "loss": 4.0704, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951271748594535e-05, + "loss": 4.0937, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950433153843483e-05, + "loss": 4.0724, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949596196972804e-05, + "loss": 4.0661, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.9487576022217524e-05, + "loss": 4.0902, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.947920645351073e-05, + "loss": 4.0597, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947082050600021e-05, + "loss": 4.067, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946243455848969e-05, + "loss": 4.0822, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.94540649897829e-05, + "loss": 4.0797, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944567904227238e-05, + "loss": 4.066, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943729309476186e-05, + "loss": 4.0719, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942890714725134e-05, + "loss": 4.0659, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942052119974082e-05, + "loss": 4.0822, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.94121352522303e-05, + "loss": 4.0768, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940374930471978e-05, + "loss": 4.076, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939536335720926e-05, + "loss": 4.0787, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938697740969874e-05, + "loss": 4.0819, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937859146218822e-05, + "loss": 4.0894, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937022189348144e-05, + "loss": 4.0646, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936183594597092e-05, + "loss": 4.0802, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.93534499984604e-05, + "loss": 4.084, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934506405094988e-05, + "loss": 4.0554, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9336694482243087e-05, + "loss": 4.0794, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9328308534732566e-05, + "loss": 4.077, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9319922587222046e-05, + "loss": 4.0866, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.9311536639711526e-05, + "loss": 4.0772, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9303150692201006e-05, + "loss": 4.0634, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9294764744690486e-05, + "loss": 4.0583, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928637879717996e-05, + "loss": 4.0728, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927799284966944e-05, + "loss": 4.0805, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.9269623280962655e-05, + "loss": 4.0701, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926123733345214e-05, + "loss": 4.0669, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.9252851385941615e-05, + "loss": 4.0706, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.9244465438431095e-05, + "loss": 4.0809, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923609586972431e-05, + "loss": 4.0694, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.9227709922213784e-05, + "loss": 4.0678, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.9219323974703264e-05, + "loss": 4.0761, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9210938027192744e-05, + "loss": 4.0827, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9202552079682224e-05, + "loss": 4.0715, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919418251097543e-05, + "loss": 4.0634, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918579656346491e-05, + "loss": 4.064, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917741061595439e-05, + "loss": 4.0684, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916902466844388e-05, + "loss": 4.0808, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916065509973709e-05, + "loss": 4.0784, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9152285531030305e-05, + "loss": 4.0711, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9143899583519785e-05, + "loss": 4.066, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913551363600926e-05, + "loss": 4.0628, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912712768849874e-05, + "loss": 4.0664, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911874174098822e-05, + "loss": 4.0696, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.91103557934777e-05, + "loss": 4.056, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910198622477091e-05, + "loss": 4.0758, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909360027726039e-05, + "loss": 4.0635, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908521432974987e-05, + "loss": 4.0658, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907682838223935e-05, + "loss": 4.0616, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9068442434728833e-05, + "loss": 4.0574, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9060056487218313e-05, + "loss": 4.0783, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9051670539707793e-05, + "loss": 4.0607, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904328459219727e-05, + "loss": 4.0867, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903491502349048e-05, + "loss": 4.0757, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902652907597996e-05, + "loss": 4.0694, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901814312846944e-05, + "loss": 4.0713, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.900975718095892e-05, + "loss": 4.065, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.90013712334484e-05, + "loss": 4.0654, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899298528593788e-05, + "loss": 4.072, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898461571723109e-05, + "loss": 4.0635, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897622976972057e-05, + "loss": 4.0705, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896784382221005e-05, + "loss": 4.0638, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.895945787469953e-05, + "loss": 4.0683, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895107192718902e-05, + "loss": 4.0667, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.89426859796785e-05, + "loss": 4.0552, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893431641097171e-05, + "loss": 4.0718, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892593046346119e-05, + "loss": 4.0577, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891754451595067e-05, + "loss": 4.0795, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.890915856844015e-05, + "loss": 4.0673, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890077262092962e-05, + "loss": 4.0691, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.88923866734191e-05, + "loss": 4.058, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888400072590858e-05, + "loss": 4.0755, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.8875631157201796e-05, + "loss": 4.0677, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886724520969127e-05, + "loss": 4.0726, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.8858875640984485e-05, + "loss": 4.0651, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.8850489693473965e-05, + "loss": 4.0734, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.8842103745963445e-05, + "loss": 4.0674, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.8833717798452925e-05, + "loss": 4.0849, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.8825331850942405e-05, + "loss": 4.0557, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.8816945903431885e-05, + "loss": 4.0745, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.8808559955921365e-05, + "loss": 4.07, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8800174008410845e-05, + "loss": 4.07, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8791788060900325e-05, + "loss": 4.0616, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8783418492193534e-05, + "loss": 4.0707, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.8775032544683014e-05, + "loss": 4.0668, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.8766646597172494e-05, + "loss": 4.0604, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8758260649661973e-05, + "loss": 4.0685, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 4.092667102813721, + "eval_runtime": 288.0666, + "eval_samples_per_second": 1324.662, + "eval_steps_per_second": 41.397, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8749874702151453e-05, + "loss": 4.0578, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874150513344467e-05, + "loss": 4.0538, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873311918593415e-05, + "loss": 4.0638, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872473323842363e-05, + "loss": 4.0773, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871634729091311e-05, + "loss": 4.0708, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870796134340259e-05, + "loss": 4.0576, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.869957539589207e-05, + "loss": 4.0763, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869118944838155e-05, + "loss": 4.0535, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868280350087103e-05, + "loss": 4.0619, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867441755336051e-05, + "loss": 4.0774, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866604798465372e-05, + "loss": 4.0626, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.86576620371432e-05, + "loss": 4.068, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.864929246843641e-05, + "loss": 4.0697, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864090652092589e-05, + "loss": 4.0581, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8632520573415374e-05, + "loss": 4.0545, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8624134625904854e-05, + "loss": 4.0516, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8615748678394334e-05, + "loss": 4.0572, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860736273088381e-05, + "loss": 4.0601, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.859899316217702e-05, + "loss": 4.0569, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.85906072146665e-05, + "loss": 4.0692, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858222126715598e-05, + "loss": 4.0746, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.8573835319645456e-05, + "loss": 4.074, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856546575093867e-05, + "loss": 4.0648, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855707980342815e-05, + "loss": 4.0596, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854869385591763e-05, + "loss": 4.0687, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854030790840711e-05, + "loss": 4.0605, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853193833970033e-05, + "loss": 4.0582, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852355239218981e-05, + "loss": 4.0569, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851516644467928e-05, + "loss": 4.0576, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850678049716876e-05, + "loss": 4.0564, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849839454965824e-05, + "loss": 4.057, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849000860214772e-05, + "loss": 4.0653, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.84816226546372e-05, + "loss": 4.0711, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847323670712668e-05, + "loss": 4.0607, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.8464883517223625e-05, + "loss": 4.062, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.8456513948516834e-05, + "loss": 4.0576, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.8448128001006314e-05, + "loss": 4.0674, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.8439742053495794e-05, + "loss": 4.0522, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843135610598528e-05, + "loss": 4.0584, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.8422970158474754e-05, + "loss": 4.0474, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.8414584210964234e-05, + "loss": 4.0602, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.8406198263453714e-05, + "loss": 4.0611, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.8397812315943194e-05, + "loss": 4.0535, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.83894427472364e-05, + "loss": 4.0589, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838105679972588e-05, + "loss": 4.0654, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837267085221536e-05, + "loss": 4.0634, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836428490470484e-05, + "loss": 4.0656, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835591533599805e-05, + "loss": 4.058, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834752938848753e-05, + "loss": 4.0279, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.833914344097702e-05, + "loss": 4.0688, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.83307574934665e-05, + "loss": 4.0591, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832237154595598e-05, + "loss": 4.0647, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831398559844546e-05, + "loss": 4.0588, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830559965093494e-05, + "loss": 4.0481, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829723008222815e-05, + "loss": 4.0429, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828884413471763e-05, + "loss": 4.0502, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828047456601084e-05, + "loss": 4.0492, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827208861850032e-05, + "loss": 4.0432, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.82637026709898e-05, + "loss": 4.0697, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825531672347928e-05, + "loss": 4.0501, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824693077596876e-05, + "loss": 4.037, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823854482845824e-05, + "loss": 4.0683, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.8230158880947717e-05, + "loss": 4.0376, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.8221772933437197e-05, + "loss": 4.0401, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821338698592668e-05, + "loss": 4.0591, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820500103841616e-05, + "loss": 4.0515, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819663146970937e-05, + "loss": 4.0459, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818824552219885e-05, + "loss": 4.0462, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.817985957468833e-05, + "loss": 4.0427, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817147362717781e-05, + "loss": 4.0554, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816308767966729e-05, + "loss": 4.0522, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8154701732156765e-05, + "loss": 4.0535, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.8146315784646245e-05, + "loss": 4.053, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8137929837135725e-05, + "loss": 4.0571, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.8129560268428934e-05, + "loss": 4.0674, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812117432091842e-05, + "loss": 4.0392, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811280475221164e-05, + "loss": 4.053, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810441880470112e-05, + "loss": 4.0626, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809603285719059e-05, + "loss": 4.0344, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808764690968007e-05, + "loss": 4.0489, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.807926096216955e-05, + "loss": 4.0572, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807087501465903e-05, + "loss": 4.0595, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806248906714851e-05, + "loss": 4.0583, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805410311963799e-05, + "loss": 4.0363, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804571717212747e-05, + "loss": 4.0334, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803734760342068e-05, + "loss": 4.0517, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.802897803471389e-05, + "loss": 4.0541, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8020592087203375e-05, + "loss": 4.0421, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.8012206139692855e-05, + "loss": 4.0469, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.8003820192182335e-05, + "loss": 4.0435, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.7995434244671815e-05, + "loss": 4.0546, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.7987064675965024e-05, + "loss": 4.0479, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.7978678728454504e-05, + "loss": 4.0454, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.7970292780943984e-05, + "loss": 4.049, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.7961906833433464e-05, + "loss": 4.0577, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7953520885922944e-05, + "loss": 4.0503, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7945134938412423e-05, + "loss": 4.0415, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.7936748990901903e-05, + "loss": 4.0406, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7928363043391383e-05, + "loss": 4.0459, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.791999347468459e-05, + "loss": 4.0574, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791162390597781e-05, + "loss": 4.0523, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790323795846729e-05, + "loss": 4.0468, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789485201095677e-05, + "loss": 4.045, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788646606344625e-05, + "loss": 4.0374, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787809649473946e-05, + "loss": 4.0468, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.786971054722894e-05, + "loss": 4.0387, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786132459971842e-05, + "loss": 4.0373, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.78529386522079e-05, + "loss": 4.0527, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.7844569083501106e-05, + "loss": 4.0394, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.7836183135990586e-05, + "loss": 4.0429, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.7827797188480066e-05, + "loss": 4.0386, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.7819411240969546e-05, + "loss": 4.0346, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.7811025293459026e-05, + "loss": 4.0532, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780265572475224e-05, + "loss": 4.0381, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779426977724172e-05, + "loss": 4.0605, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.77858838297312e-05, + "loss": 4.0494, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777749788222068e-05, + "loss": 4.0476, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.776911193471016e-05, + "loss": 4.0474, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776074236600337e-05, + "loss": 4.0431, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775235641849285e-05, + "loss": 4.0393, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774397047098233e-05, + "loss": 4.051, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773558452347181e-05, + "loss": 4.0477, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772719857596129e-05, + "loss": 4.0434, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771881262845077e-05, + "loss": 4.0397, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771042668094025e-05, + "loss": 4.0455, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770204073342973e-05, + "loss": 4.0429, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.7693671164722946e-05, + "loss": 4.0324, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.7685285217212426e-05, + "loss": 4.0496, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.76768992697019e-05, + "loss": 4.0289, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766851332219138e-05, + "loss": 4.0638, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.7660143753484595e-05, + "loss": 4.0419, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765175780597407e-05, + "loss": 4.0475, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764337185846355e-05, + "loss": 4.0346, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763498591095303e-05, + "loss": 4.0544, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762659996344251e-05, + "loss": 4.044, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761821401593199e-05, + "loss": 4.0494, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.760982806842147e-05, + "loss": 4.0431, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.7601458499714684e-05, + "loss": 4.0464, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.7593072552204164e-05, + "loss": 4.0463, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7584686604693644e-05, + "loss": 4.0635, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7576300657183124e-05, + "loss": 4.0325, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7567914709672604e-05, + "loss": 4.0538, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.7559528762162084e-05, + "loss": 4.0507, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.7551142814651564e-05, + "loss": 4.0475, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.7542756867141044e-05, + "loss": 4.039, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753438729843425e-05, + "loss": 4.0475, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752600135092373e-05, + "loss": 4.0443, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751761540341321e-05, + "loss": 4.04, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.750924583470642e-05, + "loss": 4.0459, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 4.077329158782959, + "eval_runtime": 290.0772, + "eval_samples_per_second": 1315.481, + "eval_steps_per_second": 41.11, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.75008598871959e-05, + "loss": 4.0367, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749247393968538e-05, + "loss": 4.0295, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748408799217487e-05, + "loss": 4.0437, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747570204466435e-05, + "loss": 4.0546, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746731609715383e-05, + "loss": 4.0504, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745893014964331e-05, + "loss": 4.0386, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745054420213279e-05, + "loss": 4.0479, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744215825462226e-05, + "loss": 4.0362, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743377230711174e-05, + "loss": 4.0366, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742538635960122e-05, + "loss": 4.0524, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.74170004120907e-05, + "loss": 4.0415, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740861446458018e-05, + "loss": 4.0492, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740022851706966e-05, + "loss": 4.0485, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739184256955914e-05, + "loss": 4.0329, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738345662204862e-05, + "loss": 4.0335, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.73750706745381e-05, + "loss": 4.0267, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736668472702758e-05, + "loss": 4.0392, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.73583151583208e-05, + "loss": 4.0404, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.734992921081028e-05, + "loss": 4.0295, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734154326329976e-05, + "loss": 4.0459, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7333173694592966e-05, + "loss": 4.0521, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7324787747082446e-05, + "loss": 4.0486, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7316401799571926e-05, + "loss": 4.0436, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7308015852061406e-05, + "loss": 4.039, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.7299629904550886e-05, + "loss": 4.0462, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.7291243957040366e-05, + "loss": 4.0404, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7282858009529846e-05, + "loss": 4.0356, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727447206201932e-05, + "loss": 4.0324, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.7266086114508806e-05, + "loss": 4.0408, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.7257700166998286e-05, + "loss": 4.033, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.72493305982915e-05, + "loss": 4.0363, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.7240944650780975e-05, + "loss": 4.0415, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.7232558703270455e-05, + "loss": 4.0453, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.7224172755759935e-05, + "loss": 4.0452, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.7215786808249415e-05, + "loss": 4.0335, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.7207417239542624e-05, + "loss": 4.0419, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7199031292032104e-05, + "loss": 4.0455, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7190645344521584e-05, + "loss": 4.0243, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7182259397011064e-05, + "loss": 4.0382, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7173873449500544e-05, + "loss": 4.0268, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7165487501990024e-05, + "loss": 4.0387, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.7157101554479504e-05, + "loss": 4.0367, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714873198577272e-05, + "loss": 4.0333, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.71403460382622e-05, + "loss": 4.0381, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713196009075168e-05, + "loss": 4.0446, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712357414324116e-05, + "loss": 4.0421, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711518819573064e-05, + "loss": 4.0451, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710681862702385e-05, + "loss": 4.0354, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709843267951333e-05, + "loss": 4.0103, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709004673200281e-05, + "loss": 4.0468, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708166078449229e-05, + "loss": 4.0367, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.70732912157855e-05, + "loss": 4.043, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706490526827498e-05, + "loss": 4.0356, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705651932076446e-05, + "loss": 4.0278, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704813337325394e-05, + "loss": 4.0209, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.7039747425743424e-05, + "loss": 4.0279, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.7031361478232904e-05, + "loss": 4.031, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.7022975530722384e-05, + "loss": 4.0159, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7014589583211864e-05, + "loss": 4.0474, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700622001450507e-05, + "loss": 4.0322, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699783406699455e-05, + "loss": 4.0165, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.698944811948403e-05, + "loss": 4.0426, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6981062171973506e-05, + "loss": 4.0198, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6972676224462986e-05, + "loss": 4.0212, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.69643066557562e-05, + "loss": 4.0364, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695592070824568e-05, + "loss": 4.0307, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694755113953889e-05, + "loss": 4.0233, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.693916519202838e-05, + "loss": 4.0247, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693077924451786e-05, + "loss": 4.0242, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692239329700734e-05, + "loss": 4.0299, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691400734949681e-05, + "loss": 4.0362, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690562140198629e-05, + "loss": 4.03, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689723545447577e-05, + "loss": 4.0294, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688884950696525e-05, + "loss": 4.0307, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688047993825846e-05, + "loss": 4.047, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.6872110369551675e-05, + "loss": 4.0219, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.6863724422041155e-05, + "loss": 4.031, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685533847453063e-05, + "loss": 4.0355, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.6846952527020115e-05, + "loss": 4.0197, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683858295831333e-05, + "loss": 4.0284, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683019701080281e-05, + "loss": 4.0348, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.6821811063292284e-05, + "loss": 4.0391, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.68134414945855e-05, + "loss": 4.0399, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680505554707498e-05, + "loss": 4.0121, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679666959956445e-05, + "loss": 4.0156, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678828365205393e-05, + "loss": 4.0299, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.677989770454341e-05, + "loss": 4.0322, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677151175703289e-05, + "loss": 4.0216, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676312580952237e-05, + "loss": 4.0268, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675473986201185e-05, + "loss": 4.0236, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674637029330507e-05, + "loss": 4.0348, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673798434579455e-05, + "loss": 4.0272, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.672959839828403e-05, + "loss": 4.024, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672121245077351e-05, + "loss": 4.0328, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671282650326299e-05, + "loss": 4.0354, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670444055575247e-05, + "loss": 4.0325, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669605460824195e-05, + "loss": 4.0173, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668766866073143e-05, + "loss": 4.0175, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.667929909202464e-05, + "loss": 4.0262, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667092952331785e-05, + "loss": 4.0343, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666254357580733e-05, + "loss": 4.0341, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665415762829681e-05, + "loss": 4.0258, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664577168078629e-05, + "loss": 4.0247, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.66374021120795e-05, + "loss": 4.0181, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.662901616456898e-05, + "loss": 4.0251, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662063021705846e-05, + "loss": 4.02, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661224426954794e-05, + "loss": 4.017, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660385832203742e-05, + "loss": 4.0292, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659548875333063e-05, + "loss": 4.0201, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658710280582011e-05, + "loss": 4.0219, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657871685830959e-05, + "loss": 4.0184, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657033091079907e-05, + "loss": 4.0144, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656194496328855e-05, + "loss": 4.0306, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655355901577803e-05, + "loss": 4.0245, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654517306826751e-05, + "loss": 4.0353, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653678712075699e-05, + "loss": 4.0299, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.65284175520502e-05, + "loss": 4.0286, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652003160453969e-05, + "loss": 4.0278, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651164565702917e-05, + "loss": 4.023, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650325970951864e-05, + "loss": 4.0222, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.6494890140811856e-05, + "loss": 4.0294, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.6486520572105065e-05, + "loss": 4.0247, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.6478134624594545e-05, + "loss": 4.028, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6469748677084025e-05, + "loss": 4.0149, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6461362729573505e-05, + "loss": 4.028, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6452976782062985e-05, + "loss": 4.0203, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6444607213356194e-05, + "loss": 4.0153, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.6436221265845674e-05, + "loss": 4.0261, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6427835318335154e-05, + "loss": 4.0066, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.641944937082464e-05, + "loss": 4.0461, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.6411063423314114e-05, + "loss": 4.0207, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.6402677475803594e-05, + "loss": 4.029, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639430790709681e-05, + "loss": 4.015, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638592195958629e-05, + "loss": 4.0317, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637753601207576e-05, + "loss": 4.0255, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.636915006456524e-05, + "loss": 4.0314, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636076411705472e-05, + "loss": 4.0227, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.63523781695442e-05, + "loss": 4.0247, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634402497964115e-05, + "loss": 4.0258, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633563903213063e-05, + "loss": 4.0464, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632725308462011e-05, + "loss": 4.0099, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631886713710959e-05, + "loss": 4.0361, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631048118959907e-05, + "loss": 4.0317, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630209524208855e-05, + "loss": 4.0244, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629370929457803e-05, + "loss": 4.0199, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628532334706751e-05, + "loss": 4.0263, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.6276953778360717e-05, + "loss": 4.0239, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626858420965393e-05, + "loss": 4.0224, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626019826214341e-05, + "loss": 4.0216, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 4.063990116119385, + "eval_runtime": 297.3307, + "eval_samples_per_second": 1283.389, + "eval_steps_per_second": 40.107, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.6251812314632886e-05, + "loss": 4.0162, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.6243426367122366e-05, + "loss": 4.0114, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.6235040419611845e-05, + "loss": 4.0224, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622665447210133e-05, + "loss": 4.0314, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621826852459081e-05, + "loss": 4.0324, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.620988257708029e-05, + "loss": 4.0214, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620149662956977e-05, + "loss": 4.0306, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619311068205925e-05, + "loss": 4.0178, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618474111335246e-05, + "loss": 4.0158, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617635516584194e-05, + "loss": 4.0306, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616796921833142e-05, + "loss": 4.0295, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.615959964962463e-05, + "loss": 4.0297, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615121370211411e-05, + "loss": 4.0249, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614282775460359e-05, + "loss": 4.0146, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613444180709307e-05, + "loss": 4.0162, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612605585958255e-05, + "loss": 4.0022, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611766991207203e-05, + "loss": 4.0222, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.610928396456152e-05, + "loss": 4.0216, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.6100914395854726e-05, + "loss": 4.009, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.6092528448344206e-05, + "loss": 4.0255, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.6084142500833686e-05, + "loss": 4.0331, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.6075756553323166e-05, + "loss": 4.0288, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.6067370605812646e-05, + "loss": 4.0254, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.6058984658302126e-05, + "loss": 4.0227, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.60505987107916e-05, + "loss": 4.0253, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604221276328108e-05, + "loss": 4.0235, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6033859573378024e-05, + "loss": 4.0142, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.6025473625867504e-05, + "loss": 4.011, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.6017087678356984e-05, + "loss": 4.0217, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.6008701730846464e-05, + "loss": 4.0122, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600031578333595e-05, + "loss": 4.0226, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.5991929835825423e-05, + "loss": 4.02, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.5983543888314903e-05, + "loss": 4.0214, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597515794080438e-05, + "loss": 4.0297, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596677199329386e-05, + "loss": 4.0124, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595840242458707e-05, + "loss": 4.0242, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595001647707655e-05, + "loss": 4.0267, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594163052956603e-05, + "loss": 4.0043, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593324458205551e-05, + "loss": 4.0213, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592487501334872e-05, + "loss": 4.0082, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591648906583821e-05, + "loss": 4.0136, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590811949713142e-05, + "loss": 4.0192, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.58997335496209e-05, + "loss": 4.0142, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589134760211038e-05, + "loss": 4.0193, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588296165459986e-05, + "loss": 4.0234, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587457570708934e-05, + "loss": 4.0252, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586618975957882e-05, + "loss": 4.0241, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5857820190872026e-05, + "loss": 4.0163, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5849434243361506e-05, + "loss": 3.9931, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5841064674654715e-05, + "loss": 4.0258, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.5832678727144195e-05, + "loss": 4.0165, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.5824292779633675e-05, + "loss": 4.0276, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.5815906832123155e-05, + "loss": 4.0158, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580752088461264e-05, + "loss": 4.0052, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.579913493710212e-05, + "loss": 4.0095, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.57907489895916e-05, + "loss": 4.0025, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578236304208108e-05, + "loss": 4.014, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577397709457056e-05, + "loss": 3.9957, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576559114706004e-05, + "loss": 4.033, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575720519954952e-05, + "loss": 4.0147, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574883563084273e-05, + "loss": 3.9955, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574044968333221e-05, + "loss": 4.0246, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573208011462542e-05, + "loss": 3.9997, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.57236941671149e-05, + "loss": 4.0037, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571530821960438e-05, + "loss": 4.0133, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570692227209386e-05, + "loss": 4.0114, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569853632458334e-05, + "loss": 4.0038, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.5690150377072826e-05, + "loss": 4.0104, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.5681764429562306e-05, + "loss": 4.0015, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.5673378482051786e-05, + "loss": 4.0128, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.5665008913344995e-05, + "loss": 4.0176, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.5656639344638204e-05, + "loss": 4.0115, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.5648253397127684e-05, + "loss": 4.0152, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5639867449617164e-05, + "loss": 4.0084, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5631481502106644e-05, + "loss": 4.0327, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.5623095554596124e-05, + "loss": 3.9989, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.5614709607085604e-05, + "loss": 4.0168, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560632365957508e-05, + "loss": 4.0079, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5597937712064564e-05, + "loss": 4.0092, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5589551764554044e-05, + "loss": 4.0075, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558119857465099e-05, + "loss": 4.0166, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557281262714047e-05, + "loss": 4.0214, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556442667962995e-05, + "loss": 4.02, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555604073211943e-05, + "loss": 3.9939, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554765478460891e-05, + "loss": 3.9967, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.553926883709838e-05, + "loss": 4.011, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553088288958786e-05, + "loss": 4.0158, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552249694207734e-05, + "loss": 4.0032, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551412737337055e-05, + "loss": 4.0066, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550574142586003e-05, + "loss": 4.0068, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549737185715325e-05, + "loss": 4.0114, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.5488985909642733e-05, + "loss": 4.0113, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548059996213221e-05, + "loss": 4.0047, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.547221401462169e-05, + "loss": 4.012, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5463828067111167e-05, + "loss": 4.0151, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.5455442119600647e-05, + "loss": 4.0159, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5447056172090126e-05, + "loss": 3.9997, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5438670224579606e-05, + "loss": 3.9998, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.5430300655872816e-05, + "loss": 4.0085, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.5421914708362296e-05, + "loss": 4.0144, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.5413528760851775e-05, + "loss": 4.0158, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.5405142813341255e-05, + "loss": 4.0055, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539677324463447e-05, + "loss": 4.0088, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538838729712395e-05, + "loss": 4.0009, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538000134961343e-05, + "loss": 4.0071, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537161540210291e-05, + "loss": 4.0051, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536322945459239e-05, + "loss": 4.0, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535487626468933e-05, + "loss": 4.0074, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534649031717881e-05, + "loss": 4.0029, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533810436966829e-05, + "loss": 4.0018, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.532971842215777e-05, + "loss": 4.002, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532133247464725e-05, + "loss": 3.9953, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531294652713673e-05, + "loss": 4.0126, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530457695842994e-05, + "loss": 4.0062, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.5296191010919425e-05, + "loss": 4.0163, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.5287805063408905e-05, + "loss": 4.0078, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.5279419115898385e-05, + "loss": 4.0139, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.5271033168387865e-05, + "loss": 4.0091, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.5262647220877345e-05, + "loss": 3.9997, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.5254261273366825e-05, + "loss": 4.0109, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.5245875325856305e-05, + "loss": 4.0059, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.5237489378345785e-05, + "loss": 4.0045, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.5229103430835265e-05, + "loss": 4.0124, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.5220733862128474e-05, + "loss": 4.0015, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.5212347914617954e-05, + "loss": 4.0068, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.5203961967107434e-05, + "loss": 4.0, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5195576019596914e-05, + "loss": 3.9994, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518719007208639e-05, + "loss": 4.0061, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.51788205033796e-05, + "loss": 3.996, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517043455586909e-05, + "loss": 4.0242, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516204860835857e-05, + "loss": 4.0049, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515366266084804e-05, + "loss": 4.0104, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514527671333752e-05, + "loss": 3.9991, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5136890765827e-05, + "loss": 4.0124, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512850481831648e-05, + "loss": 4.007, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512011887080596e-05, + "loss": 4.0126, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511174930209917e-05, + "loss": 4.0058, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510336335458865e-05, + "loss": 4.0036, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509497740707813e-05, + "loss": 4.0042, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508660783837134e-05, + "loss": 4.0269, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507822189086083e-05, + "loss": 3.9959, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.506983594335031e-05, + "loss": 4.0179, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506144999583979e-05, + "loss": 4.0139, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505306404832927e-05, + "loss": 4.0044, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504467810081875e-05, + "loss": 4.01, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.5036308532111956e-05, + "loss": 4.0042, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5027922584601436e-05, + "loss": 4.006, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.5019536637090916e-05, + "loss": 4.0047, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.5011150689580396e-05, + "loss": 4.0042, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 4.052966117858887, + "eval_runtime": 295.7764, + "eval_samples_per_second": 1290.133, + "eval_steps_per_second": 40.318, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.5002764742069876e-05, + "loss": 4.0102, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.4994378794559356e-05, + "loss": 3.9898, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.4985992847048836e-05, + "loss": 4.002, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.4977606899538316e-05, + "loss": 4.0189, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4969220952027796e-05, + "loss": 4.0103, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.4960835004517276e-05, + "loss": 4.0054, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4952449057006756e-05, + "loss": 4.0198, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.4944063109496236e-05, + "loss": 3.9986, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.4935677161985716e-05, + "loss": 3.9956, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.4927291214475195e-05, + "loss": 4.015, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.4918905266964675e-05, + "loss": 4.0114, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4910519319454155e-05, + "loss": 4.0082, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4902149750747364e-05, + "loss": 4.0155, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4893763803236844e-05, + "loss": 3.9941, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4885377855726324e-05, + "loss": 3.9977, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.4876991908215804e-05, + "loss": 3.9883, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4868605960705284e-05, + "loss": 4.005, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.4860220013194764e-05, + "loss": 4.0043, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.4851834065684244e-05, + "loss": 3.9953, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.4843448118173724e-05, + "loss": 4.0006, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483507854946694e-05, + "loss": 4.025, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482669260195642e-05, + "loss": 4.0072, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.48183066544459e-05, + "loss": 4.01, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.480992070693538e-05, + "loss": 4.0038, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480153475942486e-05, + "loss": 4.0095, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479314881191434e-05, + "loss": 4.0029, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478477924320755e-05, + "loss": 4.0005, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477639329569703e-05, + "loss": 3.9923, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476800734818651e-05, + "loss": 4.005, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.475962140067599e-05, + "loss": 3.9931, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475123545316546e-05, + "loss": 4.0048, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474284950565494e-05, + "loss": 4.0021, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473446355814443e-05, + "loss": 4.0108, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.4726093989437645e-05, + "loss": 4.01, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471770804192712e-05, + "loss": 4.0006, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.4709338473220334e-05, + "loss": 4.0048, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.4700952525709814e-05, + "loss": 4.0104, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469256657819929e-05, + "loss": 3.9851, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468418063068877e-05, + "loss": 4.0022, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467579468317825e-05, + "loss": 3.9954, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.4667408735667727e-05, + "loss": 3.9951, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.4659022788157207e-05, + "loss": 4.0079, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.4650636840646686e-05, + "loss": 3.9999, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.4642250893136166e-05, + "loss": 4.0023, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.4633864945625646e-05, + "loss": 4.0043, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.4625478998115126e-05, + "loss": 4.0081, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461709305060461e-05, + "loss": 4.007, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460873986070155e-05, + "loss": 4.0036, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460035391319103e-05, + "loss": 3.9738, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459196796568051e-05, + "loss": 4.0059, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458358201816999e-05, + "loss": 4.0017, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.45752124494632e-05, + "loss": 4.0105, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456682650195268e-05, + "loss": 4.0011, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455844055444216e-05, + "loss": 3.9938, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455005460693164e-05, + "loss": 3.9872, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454166865942112e-05, + "loss": 3.9898, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4533299090714336e-05, + "loss": 3.9949, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.4524913143203816e-05, + "loss": 3.9785, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.4516527195693296e-05, + "loss": 4.018, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.4508141248182776e-05, + "loss": 4.0002, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.4499755300672256e-05, + "loss": 3.9803, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.4491369353161736e-05, + "loss": 4.0041, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.4482983405651216e-05, + "loss": 3.9864, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.4474597458140696e-05, + "loss": 3.9876, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.4466227889433905e-05, + "loss": 3.9981, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4457841941923385e-05, + "loss": 3.9977, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4449455994412865e-05, + "loss": 3.9833, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.4441070046902345e-05, + "loss": 3.9999, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.4432684099391825e-05, + "loss": 3.9839, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442433090948877e-05, + "loss": 3.9936, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441594496197825e-05, + "loss": 4.0015, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440755901446773e-05, + "loss": 3.9954, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.439917306695721e-05, + "loss": 3.9962, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439078711944669e-05, + "loss": 3.9937, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438240117193617e-05, + "loss": 4.0161, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437401522442565e-05, + "loss": 3.981, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436564565571886e-05, + "loss": 4.0029, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435725970820834e-05, + "loss": 3.9915, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.434887376069782e-05, + "loss": 3.993, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.43404878131873e-05, + "loss": 3.9953, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433210186567677e-05, + "loss": 3.9945, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432371591816626e-05, + "loss": 4.0089, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431532997065574e-05, + "loss": 4.0041, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430694402314522e-05, + "loss": 3.9793, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429857445443843e-05, + "loss": 3.9797, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429018850692791e-05, + "loss": 3.9877, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428180255941739e-05, + "loss": 4.0008, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427341661190687e-05, + "loss": 3.9906, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426503066439635e-05, + "loss": 3.9871, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425664471688583e-05, + "loss": 3.9987, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.4248275148179036e-05, + "loss": 3.9932, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.4239889200668516e-05, + "loss": 3.9968, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.4231503253157996e-05, + "loss": 3.9876, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.4223117305647476e-05, + "loss": 3.9967, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421474773694069e-05, + "loss": 3.9977, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420636178943017e-05, + "loss": 4.0009, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419797584191965e-05, + "loss": 3.9841, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.418958989440913e-05, + "loss": 3.9832, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418120394689861e-05, + "loss": 3.9938, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417281799938809e-05, + "loss": 3.9956, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416443205187757e-05, + "loss": 4.0032, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415604610436705e-05, + "loss": 3.9895, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414766015685653e-05, + "loss": 3.9906, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.413927420934601e-05, + "loss": 3.9879, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.4130888261835485e-05, + "loss": 3.986, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4122502314324965e-05, + "loss": 3.9894, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411414912442191e-05, + "loss": 3.9894, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410576317691139e-05, + "loss": 3.9925, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.4097377229400876e-05, + "loss": 3.9864, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.4088991281890356e-05, + "loss": 3.9864, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.4080605334379836e-05, + "loss": 3.9872, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.4072235765673045e-05, + "loss": 3.9755, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.4063849818162525e-05, + "loss": 3.9957, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4055463870652005e-05, + "loss": 3.9959, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4047077923141485e-05, + "loss": 3.9984, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403869197563096e-05, + "loss": 3.9966, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403030602812044e-05, + "loss": 3.9969, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402192008060992e-05, + "loss": 3.9927, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.4013550511903134e-05, + "loss": 3.9828, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.4005164564392614e-05, + "loss": 3.9963, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.3996778616882094e-05, + "loss": 3.9894, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.3988392669371574e-05, + "loss": 3.9901, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398002310066478e-05, + "loss": 3.9958, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397163715315426e-05, + "loss": 3.9851, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396325120564374e-05, + "loss": 3.9919, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395486525813322e-05, + "loss": 3.983, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.39464793106227e-05, + "loss": 3.9868, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393809336311218e-05, + "loss": 3.9906, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.392972379440539e-05, + "loss": 3.984, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392133784689487e-05, + "loss": 4.0045, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391295189938435e-05, + "loss": 3.9934, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390456595187383e-05, + "loss": 3.9928, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389618000436331e-05, + "loss": 3.9862, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.38877940568528e-05, + "loss": 3.992, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.387940810934228e-05, + "loss": 3.9988, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387103854063549e-05, + "loss": 3.9981, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386265259312497e-05, + "loss": 3.9903, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385426664561445e-05, + "loss": 3.9852, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384588069810393e-05, + "loss": 3.9916, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383749475059341e-05, + "loss": 4.0103, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.382910880308289e-05, + "loss": 3.9854, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382072285557237e-05, + "loss": 3.9967, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381233690806185e-05, + "loss": 3.9992, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.3803967339355056e-05, + "loss": 3.9917, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.3795581391844536e-05, + "loss": 3.996, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.3787195444334016e-05, + "loss": 3.989, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.377882587562723e-05, + "loss": 3.9916, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377043992811671e-05, + "loss": 3.9939, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376205398060619e-05, + "loss": 3.9864, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 4.043806552886963, + "eval_runtime": 295.2229, + "eval_samples_per_second": 1292.552, + "eval_steps_per_second": 40.393, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375366803309567e-05, + "loss": 3.9872, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.3745282085585145e-05, + "loss": 3.9732, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.3736896138074625e-05, + "loss": 3.9888, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.3728510190564105e-05, + "loss": 4.0058, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.3720124243053585e-05, + "loss": 3.994, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.3711738295543065e-05, + "loss": 3.992, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.3703352348032545e-05, + "loss": 3.9964, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.3694966400522025e-05, + "loss": 3.9895, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.3686580453011505e-05, + "loss": 3.9809, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.3678210884304714e-05, + "loss": 4.0031, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.366984131559793e-05, + "loss": 3.9913, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366145536808741e-05, + "loss": 3.9957, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365308579938062e-05, + "loss": 4.0003, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.36446998518701e-05, + "loss": 3.9783, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363631390435958e-05, + "loss": 3.9824, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362792795684906e-05, + "loss": 3.9726, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.361954200933854e-05, + "loss": 3.9893, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361115606182802e-05, + "loss": 3.988, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.36027701143175e-05, + "loss": 3.9819, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359438416680698e-05, + "loss": 3.985, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358599821929646e-05, + "loss": 4.0109, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357762865058967e-05, + "loss": 3.9909, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.3569242703079154e-05, + "loss": 3.9923, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.3560856755568634e-05, + "loss": 3.9917, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.3552470808058114e-05, + "loss": 3.9954, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.3544084860547594e-05, + "loss": 3.9879, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.3535698913037074e-05, + "loss": 3.9843, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.3527312965526554e-05, + "loss": 3.9845, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.3518927018016034e-05, + "loss": 3.9855, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351055744930924e-05, + "loss": 3.9795, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350218788060245e-05, + "loss": 3.9898, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349380193309193e-05, + "loss": 3.9842, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348541598558141e-05, + "loss": 3.999, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347703003807089e-05, + "loss": 3.9921, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.346866046936411e-05, + "loss": 3.9868, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346029090065732e-05, + "loss": 3.9959, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.34519049531468e-05, + "loss": 3.9935, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344351900563628e-05, + "loss": 3.9677, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343513305812576e-05, + "loss": 3.9869, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.3426763489418966e-05, + "loss": 3.9792, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.3418377541908446e-05, + "loss": 3.9819, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.3409991594397926e-05, + "loss": 3.9912, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.3401605646887406e-05, + "loss": 3.9869, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.3393219699376886e-05, + "loss": 3.9843, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.3384833751866366e-05, + "loss": 3.9937, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.3376447804355846e-05, + "loss": 3.9912, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.3368061856845326e-05, + "loss": 3.9902, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.3359675909334806e-05, + "loss": 3.9899, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.3351289961824286e-05, + "loss": 3.9647, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.3342904014313766e-05, + "loss": 3.9875, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.3334518066803246e-05, + "loss": 3.9932, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.3326148498096455e-05, + "loss": 3.9921, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.3317762550585935e-05, + "loss": 3.9856, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.3309376603075415e-05, + "loss": 3.9791, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.3300990655564895e-05, + "loss": 3.9725, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.3292604708054375e-05, + "loss": 3.9709, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328425151815132e-05, + "loss": 3.9842, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.32758655706408e-05, + "loss": 3.9657, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326747962313028e-05, + "loss": 3.9949, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.325909367561976e-05, + "loss": 3.9873, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325070772810924e-05, + "loss": 3.9698, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324232178059872e-05, + "loss": 3.9882, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.32339358330882e-05, + "loss": 3.9701, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322556626438141e-05, + "loss": 3.9742, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321718031687089e-05, + "loss": 3.9788, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.320879436936037e-05, + "loss": 3.9875, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320040842184985e-05, + "loss": 3.9703, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319202247433933e-05, + "loss": 3.9826, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318363652682881e-05, + "loss": 3.9692, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317525057931829e-05, + "loss": 3.9814, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316686463180777e-05, + "loss": 3.9846, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315851144190471e-05, + "loss": 3.9841, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315012549439419e-05, + "loss": 3.9797, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314173954688367e-05, + "loss": 3.9812, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313335359937315e-05, + "loss": 4.0002, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312498403066636e-05, + "loss": 3.9679, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311659808315584e-05, + "loss": 3.9893, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310821213564532e-05, + "loss": 3.9788, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.30998261881348e-05, + "loss": 3.9754, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309144024062428e-05, + "loss": 3.9766, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308305429311376e-05, + "loss": 3.979, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307466834560324e-05, + "loss": 3.9914, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306628239809272e-05, + "loss": 3.9924, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.30578964505822e-05, + "loss": 3.9677, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.304951050307168e-05, + "loss": 3.9662, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304112455556116e-05, + "loss": 3.9738, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303273860805064e-05, + "loss": 3.9858, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302436903934386e-05, + "loss": 3.9748, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301598309183334e-05, + "loss": 3.9736, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300759714432282e-05, + "loss": 3.9819, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.299921119681229e-05, + "loss": 3.9774, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.2990841628105506e-05, + "loss": 3.9865, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.2982455680594986e-05, + "loss": 3.9702, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297406973308446e-05, + "loss": 3.9836, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296568378557394e-05, + "loss": 3.9771, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295729783806342e-05, + "loss": 3.9908, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.2948928269356635e-05, + "loss": 3.9683, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.2940542321846115e-05, + "loss": 3.9704, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.2932156374335595e-05, + "loss": 3.9822, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.2923770426825075e-05, + "loss": 3.9795, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291540085811829e-05, + "loss": 3.9875, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.2907014910607764e-05, + "loss": 3.9762, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.2898628963097244e-05, + "loss": 3.974, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.2890243015586724e-05, + "loss": 3.9727, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288187344687993e-05, + "loss": 3.9765, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287348749936941e-05, + "loss": 3.974, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286511793066263e-05, + "loss": 3.9724, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285673198315211e-05, + "loss": 3.9792, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284834603564159e-05, + "loss": 3.9705, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.283996008813107e-05, + "loss": 3.9731, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283157414062055e-05, + "loss": 3.9749, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.2823204571913765e-05, + "loss": 3.9618, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281481862440324e-05, + "loss": 3.9851, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280643267689272e-05, + "loss": 3.9768, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.27980467293822e-05, + "loss": 3.9807, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.278967716067541e-05, + "loss": 3.985, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278129121316489e-05, + "loss": 3.9826, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277290526565437e-05, + "loss": 3.9751, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276451931814385e-05, + "loss": 3.9711, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275613337063333e-05, + "loss": 3.981, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274774742312281e-05, + "loss": 3.9753, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.2739361475612293e-05, + "loss": 3.9727, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.2730975528101773e-05, + "loss": 3.9835, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272260595939498e-05, + "loss": 3.9746, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271422001188446e-05, + "loss": 3.9766, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270583406437394e-05, + "loss": 3.9702, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269744811686342e-05, + "loss": 3.9684, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.26890621693529e-05, + "loss": 3.9788, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268069260064611e-05, + "loss": 3.9712, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267230665313559e-05, + "loss": 3.9829, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266392070562507e-05, + "loss": 3.9865, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265555113691828e-05, + "loss": 3.976, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264716518940776e-05, + "loss": 3.9704, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.263877924189725e-05, + "loss": 3.9842, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263039329438673e-05, + "loss": 3.9799, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262200734687621e-05, + "loss": 3.9814, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261362139936569e-05, + "loss": 3.9735, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260523545185517e-05, + "loss": 3.9734, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.2596865883148376e-05, + "loss": 3.9828, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.2588479935637856e-05, + "loss": 3.9947, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2580093988127336e-05, + "loss": 3.9683, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.2571708040616816e-05, + "loss": 3.9836, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.2563322093106296e-05, + "loss": 3.9839, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255493614559577e-05, + "loss": 3.9765, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254655019808525e-05, + "loss": 3.9812, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253816425057473e-05, + "loss": 3.9741, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.2529794681867945e-05, + "loss": 3.976, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252142511316116e-05, + "loss": 3.9851, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251303916565064e-05, + "loss": 3.9658, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 4.035228729248047, + "eval_runtime": 292.4421, + "eval_samples_per_second": 1304.843, + "eval_steps_per_second": 40.777, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250465321814012e-05, + "loss": 3.9868, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.24962672706296e-05, + "loss": 3.9614, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.2487881323119074e-05, + "loss": 3.973, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.2479495375608554e-05, + "loss": 3.9883, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.2471109428098034e-05, + "loss": 3.985, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.2462723480587514e-05, + "loss": 3.9736, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.2454337533076994e-05, + "loss": 3.9814, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.2445951585566474e-05, + "loss": 3.9725, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.2437565638055953e-05, + "loss": 3.9676, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.2429179690545433e-05, + "loss": 3.9849, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242079374303491e-05, + "loss": 3.9796, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241240779552439e-05, + "loss": 3.9837, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240403822681761e-05, + "loss": 3.9868, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239565227930709e-05, + "loss": 3.9653, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238726633179657e-05, + "loss": 3.967, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.237888038428605e-05, + "loss": 3.9586, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237049443677553e-05, + "loss": 3.9776, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236210848926501e-05, + "loss": 3.97, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235372254175448e-05, + "loss": 3.9704, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234533659424396e-05, + "loss": 3.9725, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233695064673344e-05, + "loss": 3.9909, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.232856469922292e-05, + "loss": 3.9829, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.23201787517124e-05, + "loss": 3.9762, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231179280420188e-05, + "loss": 3.9785, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230340685669136e-05, + "loss": 3.9826, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229503728798458e-05, + "loss": 3.9757, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228665134047406e-05, + "loss": 3.9661, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227826539296354e-05, + "loss": 3.973, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.226987944545302e-05, + "loss": 3.9678, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226150987674623e-05, + "loss": 3.97, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225312392923571e-05, + "loss": 3.9738, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.2244754360528916e-05, + "loss": 3.9735, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.2236368413018396e-05, + "loss": 3.979, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.2227982465507876e-05, + "loss": 3.9797, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.2219596517997356e-05, + "loss": 3.9747, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221122694929057e-05, + "loss": 3.9804, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220284100178005e-05, + "loss": 3.9816, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219445505426953e-05, + "loss": 3.9563, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218606910675901e-05, + "loss": 3.9799, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217768315924849e-05, + "loss": 3.9569, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.216929721173797e-05, + "loss": 3.9695, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216091126422745e-05, + "loss": 3.9749, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215252531671693e-05, + "loss": 3.9799, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214413936920641e-05, + "loss": 3.9673, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213575342169589e-05, + "loss": 3.9746, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212736747418537e-05, + "loss": 3.9801, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.2118981526674844e-05, + "loss": 3.9746, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211061195796806e-05, + "loss": 3.9796, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210222601045754e-05, + "loss": 3.9481, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209384006294702e-05, + "loss": 3.9714, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.20854541154365e-05, + "loss": 3.9804, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207706816792598e-05, + "loss": 3.9785, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.2068698599219196e-05, + "loss": 3.9719, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.2060312651708676e-05, + "loss": 3.9628, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205192670419815e-05, + "loss": 3.965, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204354075668763e-05, + "loss": 3.9527, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.2035171187980845e-05, + "loss": 3.9772, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202678524047032e-05, + "loss": 3.9525, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.20183992929598e-05, + "loss": 3.9773, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201001334544928e-05, + "loss": 3.974, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200166015554622e-05, + "loss": 3.9583, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.19932742080357e-05, + "loss": 3.974, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198488826052519e-05, + "loss": 3.9564, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197650231301467e-05, + "loss": 3.9615, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196811636550415e-05, + "loss": 3.9635, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.195973041799362e-05, + "loss": 3.9724, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195136084928684e-05, + "loss": 3.9559, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194297490177632e-05, + "loss": 3.9687, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193458895426579e-05, + "loss": 3.9567, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192620300675527e-05, + "loss": 3.965, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191781705924475e-05, + "loss": 3.9755, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.190943111173423e-05, + "loss": 3.9723, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190104516422371e-05, + "loss": 3.9654, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189265921671319e-05, + "loss": 3.9711, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188428964800641e-05, + "loss": 3.9821, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187592007929962e-05, + "loss": 3.9574, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.1867534131789096e-05, + "loss": 3.9743, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.1859148184278576e-05, + "loss": 3.9627, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.1850762236768056e-05, + "loss": 3.9681, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.1842392668061265e-05, + "loss": 3.9637, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1834006720550745e-05, + "loss": 3.9651, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.1825620773040225e-05, + "loss": 3.98, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1817234825529705e-05, + "loss": 3.9777, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.1808848878019185e-05, + "loss": 3.9628, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1800462930508665e-05, + "loss": 3.9458, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1792076982998145e-05, + "loss": 3.9596, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.1783691035487625e-05, + "loss": 3.9711, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177533784558457e-05, + "loss": 3.9614, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176695189807405e-05, + "loss": 3.9618, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.175856595056353e-05, + "loss": 3.9695, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175018000305301e-05, + "loss": 3.9651, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174179405554249e-05, + "loss": 3.9676, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173340810803197e-05, + "loss": 3.9616, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172503853932518e-05, + "loss": 3.9726, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171665259181466e-05, + "loss": 3.9605, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170826664430414e-05, + "loss": 3.9769, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.169988069679362e-05, + "loss": 3.9565, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.16914947492831e-05, + "loss": 3.9576, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.1683125180576315e-05, + "loss": 3.97, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1674739233065795e-05, + "loss": 3.9651, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.1666353285555275e-05, + "loss": 3.9732, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.1657967338044755e-05, + "loss": 3.9643, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.1649597769337964e-05, + "loss": 3.9639, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1641211821827444e-05, + "loss": 3.9593, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1632825874316924e-05, + "loss": 3.964, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.1624439926806403e-05, + "loss": 3.9565, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.1616053979295883e-05, + "loss": 3.9611, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160768441058909e-05, + "loss": 3.9652, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.159929846307857e-05, + "loss": 3.9579, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159091251556805e-05, + "loss": 3.9566, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158252656805753e-05, + "loss": 3.9648, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157414062054702e-05, + "loss": 3.9471, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.15657546730365e-05, + "loss": 3.9706, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155736872552598e-05, + "loss": 3.9637, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.154899915681919e-05, + "loss": 3.9697, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154061320930867e-05, + "loss": 3.9713, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153222726179815e-05, + "loss": 3.9728, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152384131428763e-05, + "loss": 3.9627, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.15154553667771e-05, + "loss": 3.9606, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150706941926658e-05, + "loss": 3.9654, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.149868347175606e-05, + "loss": 3.9645, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149029752424554e-05, + "loss": 3.9549, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148191157673502e-05, + "loss": 3.9744, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147354200802824e-05, + "loss": 3.9586, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146515606051772e-05, + "loss": 3.965, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1456786491810926e-05, + "loss": 3.9569, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.1448400544300406e-05, + "loss": 3.9535, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.1440014596789886e-05, + "loss": 3.9694, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.1431628649279366e-05, + "loss": 3.9594, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.1423242701768846e-05, + "loss": 3.9638, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.1414873133062055e-05, + "loss": 3.9762, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.1406487185551535e-05, + "loss": 3.9629, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.1398101238041015e-05, + "loss": 3.9607, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.1389715290530495e-05, + "loss": 3.9707, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.1381329343019975e-05, + "loss": 3.9702, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.1372943395509455e-05, + "loss": 3.9686, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136457382680267e-05, + "loss": 3.9597, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135618787929215e-05, + "loss": 3.9619, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134780193178163e-05, + "loss": 3.9746, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.133941598427111e-05, + "loss": 3.9798, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133103003676059e-05, + "loss": 3.9607, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.13226604680538e-05, + "loss": 3.9663, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131427452054328e-05, + "loss": 3.9723, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130588857303276e-05, + "loss": 3.9654, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129750262552224e-05, + "loss": 3.9669, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.128913305681545e-05, + "loss": 3.9623, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128074710930493e-05, + "loss": 3.9626, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127236116179441e-05, + "loss": 3.9742, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.1263991593087624e-05, + "loss": 3.9536, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 4.028975486755371, + "eval_runtime": 286.7047, + "eval_samples_per_second": 1330.955, + "eval_steps_per_second": 41.593, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.1255605645577104e-05, + "loss": 3.9609, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.1247219698066584e-05, + "loss": 3.9546, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.1238833750556064e-05, + "loss": 3.957, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.1230447803045544e-05, + "loss": 3.9767, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.1222061855535024e-05, + "loss": 3.974, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.1213675908024504e-05, + "loss": 3.9628, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.1205289960513984e-05, + "loss": 3.9682, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.1196904013003464e-05, + "loss": 3.9628, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.118853444429667e-05, + "loss": 3.959, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118014849678615e-05, + "loss": 3.9725, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117176254927563e-05, + "loss": 3.9628, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116337660176511e-05, + "loss": 3.969, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115502341186206e-05, + "loss": 3.9747, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114663746435154e-05, + "loss": 3.9553, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113826789564475e-05, + "loss": 3.9554, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.112988194813423e-05, + "loss": 3.9464, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112149600062371e-05, + "loss": 3.9636, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111311005311319e-05, + "loss": 3.9615, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110472410560267e-05, + "loss": 3.9572, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109633815809215e-05, + "loss": 3.96, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.1087952210581627e-05, + "loss": 3.9777, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.1079566263071107e-05, + "loss": 3.9661, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107118031556058e-05, + "loss": 3.9683, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.1062794368050066e-05, + "loss": 3.9628, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.1054408420539546e-05, + "loss": 3.9742, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.1046022473029026e-05, + "loss": 3.9614, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.1037636525518506e-05, + "loss": 3.9604, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.1029250578007986e-05, + "loss": 3.9579, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.1020881009301195e-05, + "loss": 3.9571, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.1012495061790675e-05, + "loss": 3.9584, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.1004109114280155e-05, + "loss": 3.9591, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.0995723166769635e-05, + "loss": 3.963, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.0987337219259115e-05, + "loss": 3.9667, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0978951271748595e-05, + "loss": 3.9655, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0970565324238075e-05, + "loss": 3.9677, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.0962195755531284e-05, + "loss": 3.965, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.0953809808020764e-05, + "loss": 3.9679, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094542386051025e-05, + "loss": 3.9458, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093703791299973e-05, + "loss": 3.9683, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.092866834429294e-05, + "loss": 3.9424, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092028239678242e-05, + "loss": 3.9622, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.09118964492719e-05, + "loss": 3.962, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090351050176138e-05, + "loss": 3.9674, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089512455425086e-05, + "loss": 3.9532, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088673860674034e-05, + "loss": 3.9673, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087835265922982e-05, + "loss": 3.9657, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.08699667117193e-05, + "loss": 3.9664, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086159714301251e-05, + "loss": 3.9635, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085321119550199e-05, + "loss": 3.9379, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084482524799147e-05, + "loss": 3.9577, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083643930048095e-05, + "loss": 3.9706, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082805335297043e-05, + "loss": 3.9646, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.0819683784263644e-05, + "loss": 3.9601, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.0811297836753124e-05, + "loss": 3.9503, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.08029118892426e-05, + "loss": 3.9533, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079452594173208e-05, + "loss": 3.9401, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078613999422156e-05, + "loss": 3.9691, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077777042551477e-05, + "loss": 3.9384, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.076940085680798e-05, + "loss": 3.9655, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076101490929746e-05, + "loss": 3.9632, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075262896178694e-05, + "loss": 3.9504, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074424301427642e-05, + "loss": 3.9577, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.07358570667659e-05, + "loss": 3.9457, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072747111925538e-05, + "loss": 3.9501, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.07191015505486e-05, + "loss": 3.9471, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071071560303807e-05, + "loss": 3.966, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070232965552755e-05, + "loss": 3.9488, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069394370801703e-05, + "loss": 3.9514, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068555776050651e-05, + "loss": 3.9466, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067717181299599e-05, + "loss": 3.9541, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.066878586548547e-05, + "loss": 3.966, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066041629677868e-05, + "loss": 3.9583, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065203034926816e-05, + "loss": 3.9501, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064364440175764e-05, + "loss": 3.9607, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063525845424712e-05, + "loss": 3.9699, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.0626888885540336e-05, + "loss": 3.946, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0618502938029816e-05, + "loss": 3.9633, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.0610116990519296e-05, + "loss": 3.9517, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.0601731043008776e-05, + "loss": 3.9552, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.0593345095498256e-05, + "loss": 3.9491, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0584959147987736e-05, + "loss": 3.9565, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0576573200477216e-05, + "loss": 3.9681, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.0568187252966696e-05, + "loss": 3.9655, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.0559801305456176e-05, + "loss": 3.953, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.0551431736749385e-05, + "loss": 3.9316, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.0543045789238865e-05, + "loss": 3.9522, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.0534659841728345e-05, + "loss": 3.9555, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.0526273894217824e-05, + "loss": 3.9575, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051790432551104e-05, + "loss": 3.9429, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0509518378000517e-05, + "loss": 3.9586, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0501132430489997e-05, + "loss": 3.9558, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0492746482979477e-05, + "loss": 3.9569, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.048436053546896e-05, + "loss": 3.945, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0475974587958433e-05, + "loss": 3.9621, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0467588640447913e-05, + "loss": 3.9464, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0459202692937393e-05, + "loss": 3.9666, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0450849503034338e-05, + "loss": 3.9501, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.044246355552382e-05, + "loss": 3.9427, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.04340776080133e-05, + "loss": 3.9555, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.042570803930651e-05, + "loss": 3.9576, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.041732209179599e-05, + "loss": 3.9616, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.040893614428547e-05, + "loss": 3.9551, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.040055019677495e-05, + "loss": 3.9511, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.039216424926443e-05, + "loss": 3.9479, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0383778301753907e-05, + "loss": 3.9562, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0375408733047123e-05, + "loss": 3.9431, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0367022785536603e-05, + "loss": 3.9534, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0358636838026076e-05, + "loss": 3.9535, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035025089051556e-05, + "loss": 3.9518, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.034186494300504e-05, + "loss": 3.9405, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.033347899549452e-05, + "loss": 3.9548, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0325093047984e-05, + "loss": 3.9418, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.031670710047348e-05, + "loss": 3.9553, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.030832115296296e-05, + "loss": 3.9535, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.029993520545244e-05, + "loss": 3.9543, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.029154925794192e-05, + "loss": 3.9586, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.028317968923513e-05, + "loss": 3.9588, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.027479374172461e-05, + "loss": 3.9564, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.026640779421409e-05, + "loss": 3.9456, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.025802184670357e-05, + "loss": 3.9557, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.024965227799678e-05, + "loss": 3.9538, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.024126633048626e-05, + "loss": 3.9453, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0232880382975744e-05, + "loss": 3.9585, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0224494435465224e-05, + "loss": 3.9498, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0216124866758433e-05, + "loss": 3.9549, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0207738919247913e-05, + "loss": 3.946, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0199352971737393e-05, + "loss": 3.9464, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0190967024226873e-05, + "loss": 3.9534, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0182581076716353e-05, + "loss": 3.9485, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0174195129205836e-05, + "loss": 3.9486, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0165825560499045e-05, + "loss": 3.9679, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0157439612988525e-05, + "loss": 3.9544, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0149053665478005e-05, + "loss": 3.9494, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0140667717967485e-05, + "loss": 3.9582, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0132281770456965e-05, + "loss": 3.9561, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.012389582294644e-05, + "loss": 3.9574, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.011550987543592e-05, + "loss": 3.9536, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0107156685532867e-05, + "loss": 3.9495, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0098770738022347e-05, + "loss": 3.9632, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0090384790511826e-05, + "loss": 3.9657, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0081998843001306e-05, + "loss": 3.9511, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.007361289549079e-05, + "loss": 3.9535, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0065243326784e-05, + "loss": 3.9634, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.005685737927348e-05, + "loss": 3.9503, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.004847143176296e-05, + "loss": 3.9575, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.004008548425244e-05, + "loss": 3.9528, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0031699536741915e-05, + "loss": 3.9517, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0023313589231395e-05, + "loss": 3.9617, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0014927641720875e-05, + "loss": 3.9461, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0006541694210355e-05, + "loss": 3.95, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 4.022657871246338, + "eval_runtime": 289.9381, + "eval_samples_per_second": 1316.112, + "eval_steps_per_second": 41.129, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9998155746699835e-05, + "loss": 3.9413, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9989769799189315e-05, + "loss": 3.9447, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9981383851678795e-05, + "loss": 3.9664, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9972997904168275e-05, + "loss": 3.9638, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9964611956657755e-05, + "loss": 3.9523, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9956226009147238e-05, + "loss": 3.9583, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9947840061636718e-05, + "loss": 3.9509, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9939454114126198e-05, + "loss": 3.9456, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9931068166615678e-05, + "loss": 3.9636, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.992268221910515e-05, + "loss": 3.9506, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991429627159463e-05, + "loss": 3.9602, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9905926702887847e-05, + "loss": 3.9609, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.989754075537733e-05, + "loss": 3.9491, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9889154807866804e-05, + "loss": 3.9445, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9880768860356284e-05, + "loss": 3.9343, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9872382912845764e-05, + "loss": 3.9491, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9863996965335244e-05, + "loss": 3.9501, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9855611017824723e-05, + "loss": 3.9464, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9847225070314207e-05, + "loss": 3.948, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9838855501607416e-05, + "loss": 3.9716, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9830469554096896e-05, + "loss": 3.9551, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9822083606586376e-05, + "loss": 3.9547, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9813697659075856e-05, + "loss": 3.9518, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9805311711565336e-05, + "loss": 3.9658, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9796925764054816e-05, + "loss": 3.9441, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.97885398165443e-05, + "loss": 3.9505, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.978015386903378e-05, + "loss": 3.9449, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.977176792152326e-05, + "loss": 3.9477, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.976338197401274e-05, + "loss": 3.9468, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.975499602650222e-05, + "loss": 3.9474, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.974664283659916e-05, + "loss": 3.9537, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.973825688908864e-05, + "loss": 3.9574, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.972987094157812e-05, + "loss": 3.9515, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.97214849940676e-05, + "loss": 3.96, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.971311542536081e-05, + "loss": 3.9499, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9704745856654022e-05, + "loss": 3.9584, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9696359909143502e-05, + "loss": 3.9355, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9687973961632982e-05, + "loss": 3.9596, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9679588014122462e-05, + "loss": 3.9314, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9671202066611942e-05, + "loss": 3.9511, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9662816119101422e-05, + "loss": 3.9478, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.96544301715909e-05, + "loss": 3.9559, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.964604422408038e-05, + "loss": 3.9412, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.963765827656986e-05, + "loss": 3.9576, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9629272329059345e-05, + "loss": 3.954, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9620886381548818e-05, + "loss": 3.9538, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9612516812842034e-05, + "loss": 3.9552, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9604130865331514e-05, + "loss": 3.9296, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.959574491782099e-05, + "loss": 3.9494, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.958735897031047e-05, + "loss": 3.9572, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.957897302279995e-05, + "loss": 3.9504, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.957058707528943e-05, + "loss": 3.9517, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.956220112777891e-05, + "loss": 3.9389, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.955381518026839e-05, + "loss": 3.9446, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.95454456115616e-05, + "loss": 3.929, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9537059664051083e-05, + "loss": 3.9582, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9528673716540563e-05, + "loss": 3.9266, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9520287769030043e-05, + "loss": 3.9551, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9511901821519523e-05, + "loss": 3.9514, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9503532252812732e-05, + "loss": 3.9385, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.949514630530221e-05, + "loss": 3.9439, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.948676035779169e-05, + "loss": 3.9416, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.947837441028117e-05, + "loss": 3.9381, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9469988462770655e-05, + "loss": 3.9355, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9461618894063864e-05, + "loss": 3.9558, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9453232946553344e-05, + "loss": 3.9409, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9444846999042824e-05, + "loss": 3.9388, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9436461051532304e-05, + "loss": 3.936, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9428075104021784e-05, + "loss": 3.9412, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9419689156511264e-05, + "loss": 3.9534, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9411303209000747e-05, + "loss": 3.9516, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9402917261490227e-05, + "loss": 3.9389, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9394547692783436e-05, + "loss": 3.9516, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9386161745272916e-05, + "loss": 3.9579, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9377775797762396e-05, + "loss": 3.9347, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9369389850251876e-05, + "loss": 3.9508, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.936102028154509e-05, + "loss": 3.945, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9352650712838298e-05, + "loss": 3.9455, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9344264765327778e-05, + "loss": 3.9387, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9335878817817258e-05, + "loss": 3.9429, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9327492870306737e-05, + "loss": 3.9553, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9319106922796217e-05, + "loss": 3.9603, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.93107209752857e-05, + "loss": 3.9384, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9302335027775174e-05, + "loss": 3.9219, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9293949080264654e-05, + "loss": 3.9402, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.928557951155787e-05, + "loss": 3.946, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.927719356404735e-05, + "loss": 3.9462, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9268807616536826e-05, + "loss": 3.9394, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9260421669026306e-05, + "loss": 3.945, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9252052100319522e-05, + "loss": 3.946, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9243666152809002e-05, + "loss": 3.9439, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9235280205298475e-05, + "loss": 3.9356, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9226894257787955e-05, + "loss": 3.9486, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.921850831027744e-05, + "loss": 3.9376, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.921012236276692e-05, + "loss": 3.9531, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.92017364152564e-05, + "loss": 3.9435, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.919335046774588e-05, + "loss": 3.9304, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9184980899039088e-05, + "loss": 3.945, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9176594951528568e-05, + "loss": 3.9473, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9168209004018047e-05, + "loss": 3.9528, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.915983943531126e-05, + "loss": 3.9425, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.915145348780074e-05, + "loss": 3.9436, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.914306754029022e-05, + "loss": 3.9356, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.91346815927797e-05, + "loss": 3.9479, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.912629564526918e-05, + "loss": 3.932, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.911790969775866e-05, + "loss": 3.9401, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.910952375024814e-05, + "loss": 3.9431, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9101154181541352e-05, + "loss": 3.942, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9092768234030832e-05, + "loss": 3.9324, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9084382286520312e-05, + "loss": 3.9418, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9075996339009792e-05, + "loss": 3.936, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9067626770303e-05, + "loss": 3.9455, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9059240822792484e-05, + "loss": 3.9406, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9050854875281964e-05, + "loss": 3.9402, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9042468927771444e-05, + "loss": 3.952, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9034099359064653e-05, + "loss": 3.9482, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9025713411554133e-05, + "loss": 3.9456, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9017327464043613e-05, + "loss": 3.9363, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9008941516533093e-05, + "loss": 3.9447, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9000571947826306e-05, + "loss": 3.9398, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8992186000315786e-05, + "loss": 3.938, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8983816431608995e-05, + "loss": 3.951, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8975430484098475e-05, + "loss": 3.9374, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8967044536587955e-05, + "loss": 3.9467, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8958658589077438e-05, + "loss": 3.9323, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8950272641566918e-05, + "loss": 3.9355, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8941886694056398e-05, + "loss": 3.942, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8933500746545878e-05, + "loss": 3.9394, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8925114799035358e-05, + "loss": 3.934, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8916728851524838e-05, + "loss": 3.9599, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.890834290401431e-05, + "loss": 3.9432, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8899973335307527e-05, + "loss": 3.943, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.889158738779701e-05, + "loss": 3.9423, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8883201440286483e-05, + "loss": 3.9432, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8874815492775963e-05, + "loss": 3.9492, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8866429545265443e-05, + "loss": 3.9458, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8858043597754923e-05, + "loss": 3.9402, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8849657650244403e-05, + "loss": 3.9543, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8841271702733887e-05, + "loss": 3.9501, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8832902134027096e-05, + "loss": 3.9453, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8824516186516576e-05, + "loss": 3.9419, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8816130239006056e-05, + "loss": 3.9479, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8807744291495536e-05, + "loss": 3.9442, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8799374722788748e-05, + "loss": 3.9455, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8790988775278228e-05, + "loss": 3.9423, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8782602827767708e-05, + "loss": 3.9446, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8774216880257188e-05, + "loss": 3.9494, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8765830932746668e-05, + "loss": 3.9354, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8757461364039877e-05, + "loss": 3.9383, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 4.01777458190918, + "eval_runtime": 298.4773, + "eval_samples_per_second": 1278.459, + "eval_steps_per_second": 39.953, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8749075416529357e-05, + "loss": 3.9322, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.874068946901884e-05, + "loss": 3.9357, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.873230352150832e-05, + "loss": 3.9551, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.872393395280153e-05, + "loss": 3.9497, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.871554800529101e-05, + "loss": 3.9451, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.870716205778049e-05, + "loss": 3.9446, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8698792489073702e-05, + "loss": 3.9422, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8690406541563182e-05, + "loss": 3.9326, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.868202059405266e-05, + "loss": 3.9483, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.867363464654214e-05, + "loss": 3.9451, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866524869903162e-05, + "loss": 3.949, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.865687913032483e-05, + "loss": 3.9525, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8648509561618043e-05, + "loss": 3.9396, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8640123614107523e-05, + "loss": 3.9363, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8631737666597003e-05, + "loss": 3.9293, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8623351719086483e-05, + "loss": 3.9312, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8614965771575963e-05, + "loss": 3.9417, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8606579824065443e-05, + "loss": 3.9337, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8598193876554923e-05, + "loss": 3.94, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8589807929044403e-05, + "loss": 3.9627, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8581421981533886e-05, + "loss": 3.9431, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8573036034023366e-05, + "loss": 3.9476, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8564650086512846e-05, + "loss": 3.9394, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.855626413900232e-05, + "loss": 3.9521, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8547894570295535e-05, + "loss": 3.9378, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8539508622785015e-05, + "loss": 3.9398, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8531122675274495e-05, + "loss": 3.9341, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8522753106567708e-05, + "loss": 3.9415, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8514367159057188e-05, + "loss": 3.9339, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8505981211546667e-05, + "loss": 3.9354, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.849759526403614e-05, + "loss": 3.9405, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8489209316525624e-05, + "loss": 3.9511, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8480823369015104e-05, + "loss": 3.9393, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8472437421504584e-05, + "loss": 3.9467, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8464067852797793e-05, + "loss": 3.9384, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8455681905287273e-05, + "loss": 3.9486, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8447295957776753e-05, + "loss": 3.9288, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8438910010266233e-05, + "loss": 3.9431, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8430524062755716e-05, + "loss": 3.9241, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8422154494048925e-05, + "loss": 3.945, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8413768546538405e-05, + "loss": 3.9346, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8405382599027885e-05, + "loss": 3.9476, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8396996651517365e-05, + "loss": 3.9289, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8388610704006845e-05, + "loss": 3.9456, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8380224756496325e-05, + "loss": 3.9439, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8371838808985805e-05, + "loss": 3.9451, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.836345286147529e-05, + "loss": 3.9476, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8355083292768497e-05, + "loss": 3.921, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8346697345257977e-05, + "loss": 3.9319, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8338311397747457e-05, + "loss": 3.9452, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8329925450236937e-05, + "loss": 3.9433, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8321539502726417e-05, + "loss": 3.9381, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8313153555215897e-05, + "loss": 3.9354, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.830476760770538e-05, + "loss": 3.9318, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.829638166019486e-05, + "loss": 3.9235, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.828801209148807e-05, + "loss": 3.9385, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.827962614397755e-05, + "loss": 3.9227, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.827124019646703e-05, + "loss": 3.9361, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8262854248956506e-05, + "loss": 3.9463, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8254468301445986e-05, + "loss": 3.9306, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8246082353935466e-05, + "loss": 3.9284, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8237712785228682e-05, + "loss": 3.9317, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8229326837718155e-05, + "loss": 3.9228, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8220940890207635e-05, + "loss": 3.9272, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.821255494269712e-05, + "loss": 3.9462, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8204185373990328e-05, + "loss": 3.9329, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8195799426479807e-05, + "loss": 3.9291, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8187413478969287e-05, + "loss": 3.9271, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8179027531458767e-05, + "loss": 3.9302, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8170641583948247e-05, + "loss": 3.942, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8162255636437727e-05, + "loss": 3.9393, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.815386968892721e-05, + "loss": 3.9321, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.814548374141669e-05, + "loss": 3.9422, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.81371141727099e-05, + "loss": 3.9447, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.812872822519938e-05, + "loss": 3.9286, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.812034227768886e-05, + "loss": 3.9357, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.811195633017834e-05, + "loss": 3.9348, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.810357038266782e-05, + "loss": 3.9361, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8095184435157303e-05, + "loss": 3.9314, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8086814866450512e-05, + "loss": 3.9315, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8078428918939992e-05, + "loss": 3.946, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8070042971429472e-05, + "loss": 3.9424, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8061657023918952e-05, + "loss": 3.9338, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8053271076408432e-05, + "loss": 3.9116, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8044901507701644e-05, + "loss": 3.9303, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8036515560191124e-05, + "loss": 3.9361, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8028129612680604e-05, + "loss": 3.937, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8019743665170084e-05, + "loss": 3.9332, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8011374096463293e-05, + "loss": 3.9308, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8002988148952773e-05, + "loss": 3.9363, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7994602201442257e-05, + "loss": 3.9298, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7986216253931736e-05, + "loss": 3.9255, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7977830306421216e-05, + "loss": 3.9421, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.796944435891069e-05, + "loss": 3.9238, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.796105841140017e-05, + "loss": 3.9441, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.795267246388965e-05, + "loss": 3.9387, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7944302895182865e-05, + "loss": 3.9195, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7935916947672342e-05, + "loss": 3.935, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7927531000161822e-05, + "loss": 3.9332, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7919145052651302e-05, + "loss": 3.943, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7910759105140782e-05, + "loss": 3.933, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7902389536433994e-05, + "loss": 3.9317, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7894003588923474e-05, + "loss": 3.9253, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7885617641412954e-05, + "loss": 3.9398, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7877231693902434e-05, + "loss": 3.9212, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7868845746391914e-05, + "loss": 3.9277, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7860459798881394e-05, + "loss": 3.9347, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7852073851370874e-05, + "loss": 3.9311, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7843687903860354e-05, + "loss": 3.9203, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7835318335153566e-05, + "loss": 3.9334, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7826948766446776e-05, + "loss": 3.9271, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7818562818936256e-05, + "loss": 3.9319, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7810176871425735e-05, + "loss": 3.932, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7801790923915215e-05, + "loss": 3.9277, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7793404976404695e-05, + "loss": 3.949, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7785019028894175e-05, + "loss": 3.9391, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.777663308138366e-05, + "loss": 3.9356, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.776824713387314e-05, + "loss": 3.9258, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7759877565166348e-05, + "loss": 3.9331, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7751491617655828e-05, + "loss": 3.9305, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7743105670145308e-05, + "loss": 3.9239, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7734719722634788e-05, + "loss": 3.9417, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7726333775124268e-05, + "loss": 3.9302, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.771796420641748e-05, + "loss": 3.9306, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.770957825890696e-05, + "loss": 3.9285, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.770119231139644e-05, + "loss": 3.9257, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.769280636388592e-05, + "loss": 3.9286, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.768443679517913e-05, + "loss": 3.9306, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.767606722647234e-05, + "loss": 3.9211, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.766768127896182e-05, + "loss": 3.9497, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.76592953314513e-05, + "loss": 3.9408, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.765090938394078e-05, + "loss": 3.9317, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.764252343643026e-05, + "loss": 3.9313, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.763413748891974e-05, + "loss": 3.9285, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7625784299016683e-05, + "loss": 3.9412, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7617398351506163e-05, + "loss": 3.9361, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7609012403995643e-05, + "loss": 3.9305, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7600626456485123e-05, + "loss": 3.945, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7592240508974603e-05, + "loss": 3.9354, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7583854561464083e-05, + "loss": 3.9383, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7575468613953566e-05, + "loss": 3.9324, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7567082666443046e-05, + "loss": 3.94, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7558696718932526e-05, + "loss": 3.9352, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7550327150225735e-05, + "loss": 3.9357, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7541941202715215e-05, + "loss": 3.9338, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7533571634008427e-05, + "loss": 3.9367, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7525185686497907e-05, + "loss": 3.9383, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7516799738987387e-05, + "loss": 3.9245, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7508413791476867e-05, + "loss": 3.9291, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 4.012925624847412, + "eval_runtime": 297.3302, + "eval_samples_per_second": 1283.391, + "eval_steps_per_second": 40.107, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7500027843966347e-05, + "loss": 3.9222, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.749164189645582e-05, + "loss": 3.9241, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7483255948945304e-05, + "loss": 3.9463, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7474870001434784e-05, + "loss": 3.9435, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7466484053924264e-05, + "loss": 3.9351, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7458098106413744e-05, + "loss": 3.9321, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7449712158903224e-05, + "loss": 3.9337, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7441326211392704e-05, + "loss": 3.9216, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7432940263882184e-05, + "loss": 3.9414, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7424554316371664e-05, + "loss": 3.9355, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7416168368861143e-05, + "loss": 3.9363, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7407782421350627e-05, + "loss": 3.9413, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7399396473840107e-05, + "loss": 3.9264, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7391010526329587e-05, + "loss": 3.9278, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7382624578819067e-05, + "loss": 3.9246, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.737423863130854e-05, + "loss": 3.9253, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7365869062601756e-05, + "loss": 3.9292, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7357483115091236e-05, + "loss": 3.9235, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7349097167580712e-05, + "loss": 3.9312, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7340711220070192e-05, + "loss": 3.9549, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7332325272559672e-05, + "loss": 3.9329, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7323939325049152e-05, + "loss": 3.9347, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7315553377538632e-05, + "loss": 3.9358, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7307167430028112e-05, + "loss": 3.9398, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7298797861321325e-05, + "loss": 3.9267, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.729042829261454e-05, + "loss": 3.9354, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282042345104014e-05, + "loss": 3.9247, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7273656397593494e-05, + "loss": 3.928, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7265270450082973e-05, + "loss": 3.9248, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7256884502572453e-05, + "loss": 3.9264, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7248514933865666e-05, + "loss": 3.9314, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7240128986355146e-05, + "loss": 3.9407, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7231743038844626e-05, + "loss": 3.9316, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7223357091334106e-05, + "loss": 3.9407, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7214987522627315e-05, + "loss": 3.9246, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7206601575116798e-05, + "loss": 3.9436, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7198215627606278e-05, + "loss": 3.9158, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7189829680095758e-05, + "loss": 3.936, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7181443732585238e-05, + "loss": 3.9123, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7173057785074718e-05, + "loss": 3.9356, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7164671837564198e-05, + "loss": 3.924, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7156302268857407e-05, + "loss": 3.9407, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.714791632134689e-05, + "loss": 3.9223, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.713953037383637e-05, + "loss": 3.9337, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.713114442632585e-05, + "loss": 3.935, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.712277485761906e-05, + "loss": 3.9382, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.711438891010854e-05, + "loss": 3.935, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.710600296259802e-05, + "loss": 3.9174, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.70976170150875e-05, + "loss": 3.9185, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7089231067576983e-05, + "loss": 3.9386, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7080845120066463e-05, + "loss": 3.9352, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7072459172555943e-05, + "loss": 3.9276, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7064073225045423e-05, + "loss": 3.9266, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7055687277534896e-05, + "loss": 3.9255, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7047301330024376e-05, + "loss": 3.9131, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.703893176131759e-05, + "loss": 3.9273, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7030545813807075e-05, + "loss": 3.9149, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7022159866296548e-05, + "loss": 3.9286, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7013773918786028e-05, + "loss": 3.9373, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7005404350079244e-05, + "loss": 3.9179, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6997018402568724e-05, + "loss": 3.9213, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.69886324550582e-05, + "loss": 3.9259, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.698024650754768e-05, + "loss": 3.9132, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6971876938840896e-05, + "loss": 3.917, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.696349099133037e-05, + "loss": 3.9383, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.695510504381985e-05, + "loss": 3.924, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.694671909630933e-05, + "loss": 3.9195, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6938333148798813e-05, + "loss": 3.9171, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6929963580092022e-05, + "loss": 3.9236, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6921594011385238e-05, + "loss": 3.9326, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6913208063874718e-05, + "loss": 3.9302, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6904822116364198e-05, + "loss": 3.9217, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6896436168853674e-05, + "loss": 3.9322, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6888050221343154e-05, + "loss": 3.931, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6879664273832634e-05, + "loss": 3.9207, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6871278326322114e-05, + "loss": 3.9263, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862908757615323e-05, + "loss": 3.9296, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6854522810104803e-05, + "loss": 3.9289, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6846136862594283e-05, + "loss": 3.9239, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6837750915083766e-05, + "loss": 3.9206, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6829364967573246e-05, + "loss": 3.9342, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6820979020062726e-05, + "loss": 3.9366, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6812593072552206e-05, + "loss": 3.9226, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6804239882649144e-05, + "loss": 3.9091, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6795853935138628e-05, + "loss": 3.9181, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6787467987628108e-05, + "loss": 3.9268, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6779082040117588e-05, + "loss": 3.9289, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6770696092607068e-05, + "loss": 3.9219, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6762310145096548e-05, + "loss": 3.9194, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6753924197586028e-05, + "loss": 3.9322, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6745538250075508e-05, + "loss": 3.9174, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.673716868136872e-05, + "loss": 3.92, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.67287827338582e-05, + "loss": 3.93, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.672039678634768e-05, + "loss": 3.9187, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.671201083883716e-05, + "loss": 3.9357, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.670362489132664e-05, + "loss": 3.9259, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.669525532261985e-05, + "loss": 3.9132, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.668686937510933e-05, + "loss": 3.9274, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.667848342759881e-05, + "loss": 3.9224, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6670097480088292e-05, + "loss": 3.9383, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6661711532577772e-05, + "loss": 3.9299, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6653325585067252e-05, + "loss": 3.9216, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6644939637556732e-05, + "loss": 3.9128, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6636553690046205e-05, + "loss": 3.9308, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.662818412133942e-05, + "loss": 3.9132, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.66197981738289e-05, + "loss": 3.9226, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6611412226318384e-05, + "loss": 3.9253, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6603026278807858e-05, + "loss": 3.9215, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6594640331297338e-05, + "loss": 3.9113, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6586254383786817e-05, + "loss": 3.9305, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6577868436276297e-05, + "loss": 3.9159, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6569482488765777e-05, + "loss": 3.9187, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.656111292005899e-05, + "loss": 3.9266, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.655272697254847e-05, + "loss": 3.9154, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.654434102503795e-05, + "loss": 3.9378, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.653595507752743e-05, + "loss": 3.9293, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.652758550882064e-05, + "loss": 3.9308, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6519199561310122e-05, + "loss": 3.9166, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.651082999260333e-05, + "loss": 3.9242, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.650244404509281e-05, + "loss": 3.9258, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.649405809758229e-05, + "loss": 3.9133, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.648567215007177e-05, + "loss": 3.9322, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.647728620256125e-05, + "loss": 3.9233, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.646890025505073e-05, + "loss": 3.9218, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6460530686343944e-05, + "loss": 3.9224, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6452144738833424e-05, + "loss": 3.9203, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6443758791322903e-05, + "loss": 3.9146, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6435372843812383e-05, + "loss": 3.9263, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6426986896301863e-05, + "loss": 3.9138, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6418600948791343e-05, + "loss": 3.9363, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6410215001280823e-05, + "loss": 3.9364, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6401829053770307e-05, + "loss": 3.9207, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6393459485063516e-05, + "loss": 3.9213, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6385073537552996e-05, + "loss": 3.9215, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6376687590042476e-05, + "loss": 3.9307, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6368301642531956e-05, + "loss": 3.9276, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6359932073825168e-05, + "loss": 3.9245, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6351546126314648e-05, + "loss": 3.9337, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6343160178804128e-05, + "loss": 3.9292, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6334774231293608e-05, + "loss": 3.931, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6326388283783088e-05, + "loss": 3.9209, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6318002336272568e-05, + "loss": 3.9352, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6309616388762044e-05, + "loss": 3.9272, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6301230441251524e-05, + "loss": 3.9195, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6292844493741004e-05, + "loss": 3.9276, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.628447492503422e-05, + "loss": 3.9299, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.627610535632743e-05, + "loss": 3.9255, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.626771940881691e-05, + "loss": 3.914, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6259349840110122e-05, + "loss": 3.9188, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 4.009148120880127, + "eval_runtime": 288.6374, + "eval_samples_per_second": 1322.043, + "eval_steps_per_second": 41.315, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6250963892599602e-05, + "loss": 3.9197, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.624257794508908e-05, + "loss": 3.9147, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.623419199757856e-05, + "loss": 3.9361, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.622580605006804e-05, + "loss": 3.9337, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6217420102557515e-05, + "loss": 3.9327, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.6209034155046998e-05, + "loss": 3.9178, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6200648207536478e-05, + "loss": 3.9299, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6192262260025958e-05, + "loss": 3.9106, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6183876312515438e-05, + "loss": 3.9348, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6175490365004918e-05, + "loss": 3.9279, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6167104417494398e-05, + "loss": 3.9241, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6158734848787607e-05, + "loss": 3.9365, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.615036528008082e-05, + "loss": 3.9162, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.61419793325703e-05, + "loss": 3.9218, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.613359338505978e-05, + "loss": 3.9105, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.612520743754926e-05, + "loss": 3.9198, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.611682149003874e-05, + "loss": 3.9179, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.610843554252822e-05, + "loss": 3.9169, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.61000495950177e-05, + "loss": 3.9218, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.609166364750718e-05, + "loss": 3.9431, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.608329407880039e-05, + "loss": 3.9242, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.60749245100936e-05, + "loss": 3.9294, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.606653856258308e-05, + "loss": 3.9283, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.605815261507256e-05, + "loss": 3.931, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.604976666756204e-05, + "loss": 3.9201, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6041397098855253e-05, + "loss": 3.9238, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6033011151344733e-05, + "loss": 3.9158, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6024625203834213e-05, + "loss": 3.9175, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6016239256323693e-05, + "loss": 3.9146, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6007853308813173e-05, + "loss": 3.923, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.5999467361302653e-05, + "loss": 3.9208, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5991097792595865e-05, + "loss": 3.9322, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5982711845085345e-05, + "loss": 3.9255, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5974325897574825e-05, + "loss": 3.9292, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5965956328868034e-05, + "loss": 3.9205, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5957570381357514e-05, + "loss": 3.9319, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5949184433846994e-05, + "loss": 3.913, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5940798486336478e-05, + "loss": 3.9252, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5932412538825958e-05, + "loss": 3.905, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5924026591315438e-05, + "loss": 3.9231, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5915640643804917e-05, + "loss": 3.9187, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5907254696294397e-05, + "loss": 3.9331, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5898868748783877e-05, + "loss": 3.9143, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5890482801273354e-05, + "loss": 3.9237, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.588211323256657e-05, + "loss": 3.9266, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.587372728505605e-05, + "loss": 3.9305, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5865341337545523e-05, + "loss": 3.9251, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5856955390035003e-05, + "loss": 3.9136, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.584858582132822e-05, + "loss": 3.9074, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.58401998738177e-05, + "loss": 3.9303, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5831813926307175e-05, + "loss": 3.9258, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5823427978796655e-05, + "loss": 3.9202, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5815042031286135e-05, + "loss": 3.9153, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5806656083775615e-05, + "loss": 3.9199, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5798270136265095e-05, + "loss": 3.9018, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5789884188754575e-05, + "loss": 3.9222, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5781514620047788e-05, + "loss": 3.9058, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5773145051340997e-05, + "loss": 3.9197, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5764759103830477e-05, + "loss": 3.9264, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5756373156319957e-05, + "loss": 3.9156, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5747987208809437e-05, + "loss": 3.9085, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.573961764010265e-05, + "loss": 3.9173, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.573123169259213e-05, + "loss": 3.9032, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.572284574508161e-05, + "loss": 3.9121, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.571445979757109e-05, + "loss": 3.9239, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.570607385006057e-05, + "loss": 3.9164, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5697704281353778e-05, + "loss": 3.9105, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.568931833384326e-05, + "loss": 3.907, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.568094876513647e-05, + "loss": 3.9164, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.567256281762595e-05, + "loss": 3.9207, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.566417687011543e-05, + "loss": 3.9228, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.565579092260491e-05, + "loss": 3.9169, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.564740497509439e-05, + "loss": 3.9246, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.563901902758387e-05, + "loss": 3.9261, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5630633080073353e-05, + "loss": 3.9125, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5622247132562833e-05, + "loss": 3.9147, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5613877563856043e-05, + "loss": 3.9216, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5605491616345522e-05, + "loss": 3.9219, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5597105668835002e-05, + "loss": 3.9166, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5588719721324482e-05, + "loss": 3.9143, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5580333773813962e-05, + "loss": 3.9233, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5571947826303442e-05, + "loss": 3.9282, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.5563578257596655e-05, + "loss": 3.9168, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5555192310086135e-05, + "loss": 3.9039, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5546806362575615e-05, + "loss": 3.9047, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5538420415065095e-05, + "loss": 3.9156, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5530034467554575e-05, + "loss": 3.9223, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.5521648520044055e-05, + "loss": 3.9166, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5513278951337267e-05, + "loss": 3.9071, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5504893003826747e-05, + "loss": 3.9223, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5496507056316227e-05, + "loss": 3.9161, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5488121108805707e-05, + "loss": 3.9106, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5479735161295187e-05, + "loss": 3.9145, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5471365592588396e-05, + "loss": 3.9195, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.546297964507788e-05, + "loss": 3.9279, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.545459369756736e-05, + "loss": 3.9136, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5446207750056832e-05, + "loss": 3.902, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5437821802546312e-05, + "loss": 3.9212, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5429435855035792e-05, + "loss": 3.9139, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5421049907525272e-05, + "loss": 3.9283, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5412663960014756e-05, + "loss": 3.922, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5404294391307965e-05, + "loss": 3.9114, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5395908443797445e-05, + "loss": 3.9061, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5387522496286925e-05, + "loss": 3.9244, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5379136548776405e-05, + "loss": 3.9041, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5370750601265885e-05, + "loss": 3.9159, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5362381032559097e-05, + "loss": 3.91, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5353995085048577e-05, + "loss": 3.9181, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5345609137538057e-05, + "loss": 3.901, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5337223190027537e-05, + "loss": 3.9217, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5328853621320746e-05, + "loss": 3.9071, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5320500431417694e-05, + "loss": 3.9086, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5312114483907174e-05, + "loss": 3.9212, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5303728536396654e-05, + "loss": 3.909, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5295342588886134e-05, + "loss": 3.9325, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5286956641375607e-05, + "loss": 3.9224, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5278570693865087e-05, + "loss": 3.9182, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.527018474635457e-05, + "loss": 3.9075, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.526179879884405e-05, + "loss": 3.9164, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.525342923013726e-05, + "loss": 3.9151, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.524504328262674e-05, + "loss": 3.9076, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.523665733511622e-05, + "loss": 3.9218, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.52282713876057e-05, + "loss": 3.9145, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.521988544009518e-05, + "loss": 3.9144, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5211499492584663e-05, + "loss": 3.9115, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5203113545074143e-05, + "loss": 3.913, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5194727597563623e-05, + "loss": 3.9076, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5186358028856832e-05, + "loss": 3.9197, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.517798846015004e-05, + "loss": 3.9062, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5169602512639524e-05, + "loss": 3.9256, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5161216565129004e-05, + "loss": 3.9215, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5152830617618484e-05, + "loss": 3.9207, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5144444670107964e-05, + "loss": 3.9113, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5136058722597444e-05, + "loss": 3.9151, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5127672775086924e-05, + "loss": 3.9206, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5119286827576404e-05, + "loss": 3.9212, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5110917258869617e-05, + "loss": 3.9116, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5102531311359097e-05, + "loss": 3.9224, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5094145363848577e-05, + "loss": 3.9177, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5085759416338057e-05, + "loss": 3.9237, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5077389847631266e-05, + "loss": 3.9147, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5069003900120746e-05, + "loss": 3.9263, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5060617952610226e-05, + "loss": 3.9224, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.505223200509971e-05, + "loss": 3.9133, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.504384605758919e-05, + "loss": 3.9181, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.503546011007867e-05, + "loss": 3.9249, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5027074162568142e-05, + "loss": 3.9147, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5018688215057622e-05, + "loss": 3.9028, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5010318646350838e-05, + "loss": 3.9176, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 4.005160808563232, + "eval_runtime": 287.53, + "eval_samples_per_second": 1327.135, + "eval_steps_per_second": 41.474, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.5001932698840318e-05, + "loss": 3.9074, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.4993546751329798e-05, + "loss": 3.9077, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4985160803819278e-05, + "loss": 3.925, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4976774856308758e-05, + "loss": 3.9264, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4968388908798234e-05, + "loss": 3.9227, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4960002961287714e-05, + "loss": 3.9151, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4951617013777194e-05, + "loss": 3.9197, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.4943231066266674e-05, + "loss": 3.9013, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4934845118756157e-05, + "loss": 3.9233, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4926459171245637e-05, + "loss": 3.9222, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4918073223735117e-05, + "loss": 3.9151, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4909687276224594e-05, + "loss": 3.9269, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4901317707517806e-05, + "loss": 3.9091, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4892931760007286e-05, + "loss": 3.9148, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4884545812496766e-05, + "loss": 3.9063, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4876159864986246e-05, + "loss": 3.9067, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4867773917475726e-05, + "loss": 3.9116, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4859387969965206e-05, + "loss": 3.9079, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4851018401258415e-05, + "loss": 3.9153, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4842632453747895e-05, + "loss": 3.9335, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.483424650623738e-05, + "loss": 3.9199, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.482586055872686e-05, + "loss": 3.923, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.481747461121634e-05, + "loss": 3.9163, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.480908866370582e-05, + "loss": 3.9235, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.48007027161953e-05, + "loss": 3.913, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4792316768684775e-05, + "loss": 3.9175, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4783930821174255e-05, + "loss": 3.9115, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4775561252467467e-05, + "loss": 3.9093, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4767175304956947e-05, + "loss": 3.9059, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4758789357446427e-05, + "loss": 3.9172, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4750403409935907e-05, + "loss": 3.9141, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4742017462425387e-05, + "loss": 3.9236, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4733631514914867e-05, + "loss": 3.9167, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.472526194620808e-05, + "loss": 3.9201, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4716892377501292e-05, + "loss": 3.9111, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4708506429990772e-05, + "loss": 3.9247, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.470012048248025e-05, + "loss": 3.9077, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469173453496973e-05, + "loss": 3.9136, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.468334858745921e-05, + "loss": 3.8976, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.467496263994869e-05, + "loss": 3.9132, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4666576692438172e-05, + "loss": 3.9127, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4658190744927652e-05, + "loss": 3.925, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.464980479741713e-05, + "loss": 3.9058, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.464141884990661e-05, + "loss": 3.9156, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4633032902396088e-05, + "loss": 3.9167, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4624646954885568e-05, + "loss": 3.921, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4616261007375048e-05, + "loss": 3.9156, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.460789143866826e-05, + "loss": 3.9036, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.459950549115774e-05, + "loss": 3.8977, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.459111954364722e-05, + "loss": 3.9246, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.45827335961367e-05, + "loss": 3.9165, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.457434764862618e-05, + "loss": 3.9124, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.456597807991939e-05, + "loss": 3.9102, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4557592132408873e-05, + "loss": 3.9118, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4549206184898353e-05, + "loss": 3.8952, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4540820237387833e-05, + "loss": 3.9094, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4532450668681042e-05, + "loss": 3.9013, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.452408109997425e-05, + "loss": 3.9106, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4515695152463734e-05, + "loss": 3.9207, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4507309204953214e-05, + "loss": 3.9079, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4498923257442694e-05, + "loss": 3.9001, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4490537309932174e-05, + "loss": 3.9159, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4482167741225383e-05, + "loss": 3.8942, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4473781793714863e-05, + "loss": 3.9062, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4465395846204343e-05, + "loss": 3.9136, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4457009898693827e-05, + "loss": 3.9115, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4448623951183307e-05, + "loss": 3.9019, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4440238003672783e-05, + "loss": 3.9009, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4431852056162263e-05, + "loss": 3.9043, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4423482487455476e-05, + "loss": 3.9119, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4415096539944956e-05, + "loss": 3.9142, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4406710592434435e-05, + "loss": 3.9102, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4398324644923915e-05, + "loss": 3.9164, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4389938697413395e-05, + "loss": 3.919, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4381552749902875e-05, + "loss": 3.9069, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4373166802392355e-05, + "loss": 3.8996, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4364780854881835e-05, + "loss": 3.9203, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4356411286175044e-05, + "loss": 3.9156, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4348025338664528e-05, + "loss": 3.9048, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4339639391154008e-05, + "loss": 3.9062, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4331253443643488e-05, + "loss": 3.9149, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4322867496132964e-05, + "loss": 3.9226, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4314497927426177e-05, + "loss": 3.9051, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4306111979915657e-05, + "loss": 3.895, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4297726032405137e-05, + "loss": 3.9029, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4289340084894617e-05, + "loss": 3.9021, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.428097051618783e-05, + "loss": 3.9132, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.427258456867731e-05, + "loss": 3.9104, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4264198621166786e-05, + "loss": 3.897, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4255812673656266e-05, + "loss": 3.9153, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.424744310494948e-05, + "loss": 3.9059, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.423905715743896e-05, + "loss": 3.9081, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4230671209928438e-05, + "loss": 3.9033, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4222285262417918e-05, + "loss": 3.9103, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.421391569371113e-05, + "loss": 3.9209, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.420552974620061e-05, + "loss": 3.9102, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.419714379869009e-05, + "loss": 3.8918, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.418875785117957e-05, + "loss": 3.9101, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.418037190366905e-05, + "loss": 3.9095, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.417198595615853e-05, + "loss": 3.9156, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.416361638745174e-05, + "loss": 3.9163, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.415523043994122e-05, + "loss": 3.9052, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.41468444924307e-05, + "loss": 3.9005, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4138458544920182e-05, + "loss": 3.9152, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.413008897621339e-05, + "loss": 3.8931, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.412170302870287e-05, + "loss": 3.9089, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.411331708119235e-05, + "loss": 3.903, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.410493113368183e-05, + "loss": 3.9092, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.409654518617131e-05, + "loss": 3.8962, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.408815923866079e-05, + "loss": 3.9129, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.407977329115027e-05, + "loss": 3.8985, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4071403722443484e-05, + "loss": 3.8994, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4063017774932964e-05, + "loss": 3.9145, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.405463182742244e-05, + "loss": 3.9056, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404624587991192e-05, + "loss": 3.9218, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4037876311205136e-05, + "loss": 3.9126, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4029490363694616e-05, + "loss": 3.9073, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4021104416184093e-05, + "loss": 3.9101, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4012718468673573e-05, + "loss": 3.9021, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4004332521163053e-05, + "loss": 3.911, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3995946573652533e-05, + "loss": 3.9005, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3987560626142012e-05, + "loss": 3.9165, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3979174678631496e-05, + "loss": 3.9024, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3970788731120972e-05, + "loss": 3.9045, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3962402783610452e-05, + "loss": 3.9046, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3954033214903665e-05, + "loss": 3.9096, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3945647267393145e-05, + "loss": 3.8989, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.393726131988262e-05, + "loss": 3.912, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3928875372372105e-05, + "loss": 3.8997, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3920489424861585e-05, + "loss": 3.9183, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3912103477351065e-05, + "loss": 3.9122, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3903717529840545e-05, + "loss": 3.9137, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3895347961133754e-05, + "loss": 3.9049, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3886978392426966e-05, + "loss": 3.9066, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3878592444916446e-05, + "loss": 3.9175, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3870206497405926e-05, + "loss": 3.9099, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3861820549895406e-05, + "loss": 3.9033, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3853434602384886e-05, + "loss": 3.9168, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3845048654874366e-05, + "loss": 3.9104, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3836662707363846e-05, + "loss": 3.9197, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3828276759853326e-05, + "loss": 3.9078, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3819890812342806e-05, + "loss": 3.9145, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3811521243636018e-05, + "loss": 3.9137, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.3803135296125498e-05, + "loss": 3.9049, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3794749348614978e-05, + "loss": 3.9109, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3786363401104455e-05, + "loss": 3.9135, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3777977453593935e-05, + "loss": 3.9088, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.376960788488715e-05, + "loss": 3.8958, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3761221937376627e-05, + "loss": 3.9095, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 4.001758575439453, + "eval_runtime": 296.2053, + "eval_samples_per_second": 1288.265, + "eval_steps_per_second": 40.259, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.3752835989866107e-05, + "loss": 3.9042, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.3744450042355587e-05, + "loss": 3.8996, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.37360804736488e-05, + "loss": 3.9163, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3727694526138276e-05, + "loss": 3.9183, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.371930857862776e-05, + "loss": 3.913, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.371092263111724e-05, + "loss": 3.9101, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.370253668360672e-05, + "loss": 3.9102, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.36941507360962e-05, + "loss": 3.8967, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.368576478858568e-05, + "loss": 3.912, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.367737884107516e-05, + "loss": 3.9171, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.3668992893564636e-05, + "loss": 3.9085, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.366062332485785e-05, + "loss": 3.9176, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.365225375615106e-05, + "loss": 3.9047, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.364386780864054e-05, + "loss": 3.9079, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.363548186113002e-05, + "loss": 3.8984, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.36270959136195e-05, + "loss": 3.9007, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.361870996610898e-05, + "loss": 3.9022, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.361032401859846e-05, + "loss": 3.9, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3601954449891673e-05, + "loss": 3.9069, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3593568502381153e-05, + "loss": 3.9207, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3585182554870633e-05, + "loss": 3.9177, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.357679660736011e-05, + "loss": 3.9139, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.356841065984959e-05, + "loss": 3.9095, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.356002471233907e-05, + "loss": 3.9175, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3551638764828553e-05, + "loss": 3.9036, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3543269196121762e-05, + "loss": 3.9137, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3534883248611242e-05, + "loss": 3.9041, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3526497301100722e-05, + "loss": 3.8975, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.3518111353590202e-05, + "loss": 3.902, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.350972540607968e-05, + "loss": 3.9034, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3501355837372894e-05, + "loss": 3.909, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3492986268666103e-05, + "loss": 3.9133, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3484600321155583e-05, + "loss": 3.9134, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3476214373645063e-05, + "loss": 3.9132, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3467844804938276e-05, + "loss": 3.9034, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.3459458857427756e-05, + "loss": 3.912, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.3451072909917236e-05, + "loss": 3.9044, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.3442686962406716e-05, + "loss": 3.9004, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3434317393699928e-05, + "loss": 3.8984, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3425931446189405e-05, + "loss": 3.9037, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3417545498678885e-05, + "loss": 3.91, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.3409159551168368e-05, + "loss": 3.9153, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.3400773603657848e-05, + "loss": 3.9011, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.3392387656147328e-05, + "loss": 3.9066, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.3384001708636808e-05, + "loss": 3.9118, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.3375615761126284e-05, + "loss": 3.9113, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.3367229813615764e-05, + "loss": 3.911, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3358860244908977e-05, + "loss": 3.898, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.335047429739846e-05, + "loss": 3.8845, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.3342088349887937e-05, + "loss": 3.9171, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.3333702402377417e-05, + "loss": 3.9113, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.3325316454866897e-05, + "loss": 3.9048, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.3316930507356377e-05, + "loss": 3.9064, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.330856093864959e-05, + "loss": 3.8981, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.330017499113907e-05, + "loss": 3.8918, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.329178904362855e-05, + "loss": 3.9002, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.328340309611803e-05, + "loss": 3.8928, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.327501714860751e-05, + "loss": 3.9029, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.326666395870445e-05, + "loss": 3.9133, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.325827801119393e-05, + "loss": 3.8979, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.324989206368341e-05, + "loss": 3.892, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.324150611617289e-05, + "loss": 3.9093, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.323312016866237e-05, + "loss": 3.8869, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.322473422115185e-05, + "loss": 3.8958, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.321634827364133e-05, + "loss": 3.907, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.320796232613081e-05, + "loss": 3.905, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3199592757424023e-05, + "loss": 3.8952, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3191206809913503e-05, + "loss": 3.8955, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.3182820862402983e-05, + "loss": 3.8945, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.3174434914892463e-05, + "loss": 3.9038, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.316604896738194e-05, + "loss": 3.908, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.315766301987142e-05, + "loss": 3.8991, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.31492770723609e-05, + "loss": 3.9084, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3140891124850382e-05, + "loss": 3.9113, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.313252155614359e-05, + "loss": 3.9087, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.312413560863307e-05, + "loss": 3.8916, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.311574966112255e-05, + "loss": 3.9085, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.310736371361203e-05, + "loss": 3.9105, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.309897776610151e-05, + "loss": 3.8926, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.309059181859099e-05, + "loss": 3.905, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.308220587108047e-05, + "loss": 3.9037, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3073836302373684e-05, + "loss": 3.9167, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3065450354863164e-05, + "loss": 3.9014, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.3057064407352644e-05, + "loss": 3.8841, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.304867845984212e-05, + "loss": 3.8998, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.30402925123316e-05, + "loss": 3.8968, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.3031906564821083e-05, + "loss": 3.9035, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3023536996114296e-05, + "loss": 3.9022, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.3015151048603772e-05, + "loss": 3.8932, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3006765101093252e-05, + "loss": 3.9054, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.2998379153582732e-05, + "loss": 3.9014, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.2989993206072212e-05, + "loss": 3.8951, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.2981607258561692e-05, + "loss": 3.9003, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.2973221311051176e-05, + "loss": 3.9058, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.2964851742344385e-05, + "loss": 3.9128, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2956465794833865e-05, + "loss": 3.9004, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2948079847323345e-05, + "loss": 3.887, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2939710278616554e-05, + "loss": 3.9017, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.2931324331106037e-05, + "loss": 3.9003, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.2922938383595517e-05, + "loss": 3.9087, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.2914552436084997e-05, + "loss": 3.9097, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2906166488574477e-05, + "loss": 3.8949, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2897780541063954e-05, + "loss": 3.8952, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2889394593553433e-05, + "loss": 3.9076, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2881008646042913e-05, + "loss": 3.8864, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2872622698532393e-05, + "loss": 3.9036, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.2864253129825606e-05, + "loss": 3.891, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2855867182315086e-05, + "loss": 3.9053, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2847481234804566e-05, + "loss": 3.8895, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2839095287294046e-05, + "loss": 3.9054, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.2830709339783526e-05, + "loss": 3.8969, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2822323392273006e-05, + "loss": 3.8877, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.2813937444762486e-05, + "loss": 3.9069, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.2805551497251966e-05, + "loss": 3.8945, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.2797181928545178e-05, + "loss": 3.9144, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.2788795981034658e-05, + "loss": 3.9083, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2780426412327867e-05, + "loss": 3.8965, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.2772040464817347e-05, + "loss": 3.9057, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.276365451730683e-05, + "loss": 3.894, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.275528494860004e-05, + "loss": 3.9013, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.274689900108952e-05, + "loss": 3.8955, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.2738513053579e-05, + "loss": 3.9069, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.273012710606848e-05, + "loss": 3.8968, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2721741158557956e-05, + "loss": 3.8956, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.271335521104744e-05, + "loss": 3.9007, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.270496926353692e-05, + "loss": 3.9001, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.26965833160264e-05, + "loss": 3.8901, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.268819736851588e-05, + "loss": 3.9071, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.267981142100536e-05, + "loss": 3.8904, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.267142547349484e-05, + "loss": 3.9178, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2663039525984316e-05, + "loss": 3.8984, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.265466995727753e-05, + "loss": 3.9078, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.264628400976701e-05, + "loss": 3.8957, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.2637898062256488e-05, + "loss": 3.9025, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.2629512114745968e-05, + "loss": 3.9083, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.2621126167235448e-05, + "loss": 3.9024, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.261275659852866e-05, + "loss": 3.8963, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.260437065101814e-05, + "loss": 3.9108, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.259598470350762e-05, + "loss": 3.9041, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.25875987559971e-05, + "loss": 3.9112, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.257921280848658e-05, + "loss": 3.8963, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.257084323977979e-05, + "loss": 3.9096, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.256245729226927e-05, + "loss": 3.9053, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.2554071344758753e-05, + "loss": 3.9012, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2545685397248233e-05, + "loss": 3.9054, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2537299449737713e-05, + "loss": 3.9038, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2528913502227192e-05, + "loss": 3.9084, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.252052755471667e-05, + "loss": 3.8817, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.251214160720615e-05, + "loss": 3.908, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.9984071254730225, + "eval_runtime": 295.809, + "eval_samples_per_second": 1289.991, + "eval_steps_per_second": 40.313, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.250377203849936e-05, + "loss": 3.8954, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.249538609098884e-05, + "loss": 3.8922, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.248700014347832e-05, + "loss": 3.9064, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.24786141959678e-05, + "loss": 3.9136, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.247022824845728e-05, + "loss": 3.9047, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.246184230094676e-05, + "loss": 3.8984, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.245345635343624e-05, + "loss": 3.9034, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244507040592572e-05, + "loss": 3.89, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.24366844584152e-05, + "loss": 3.9042, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.242829851090468e-05, + "loss": 3.9084, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.241991256339416e-05, + "loss": 3.9056, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.241152661588364e-05, + "loss": 3.9064, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.240315704717685e-05, + "loss": 3.9022, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.239477109966633e-05, + "loss": 3.8985, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.238638515215581e-05, + "loss": 3.893, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2377999204645293e-05, + "loss": 3.8884, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2369613257134773e-05, + "loss": 3.8989, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2361227309624253e-05, + "loss": 3.8942, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2352841362113733e-05, + "loss": 3.8987, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.234445541460321e-05, + "loss": 3.9128, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.233606946709269e-05, + "loss": 3.913, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.232768351958217e-05, + "loss": 3.9033, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.231929757207165e-05, + "loss": 3.9003, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2310928003364862e-05, + "loss": 3.908, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2302542055854342e-05, + "loss": 3.8953, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2294156108343822e-05, + "loss": 3.9094, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2285770160833302e-05, + "loss": 3.8972, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2277384213322782e-05, + "loss": 3.8879, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2268998265812262e-05, + "loss": 3.8988, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2260612318301742e-05, + "loss": 3.8949, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2252226370791222e-05, + "loss": 3.9006, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2243856802084434e-05, + "loss": 3.9073, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2235470854573914e-05, + "loss": 3.9038, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.222708490706339e-05, + "loss": 3.9036, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2218731717160336e-05, + "loss": 3.8936, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2210345769649816e-05, + "loss": 3.9122, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2201959822139296e-05, + "loss": 3.8949, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2193573874628776e-05, + "loss": 3.8879, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2185187927118256e-05, + "loss": 3.8949, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2176801979607736e-05, + "loss": 3.8904, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2168416032097216e-05, + "loss": 3.902, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2160030084586696e-05, + "loss": 3.9113, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2151644137076176e-05, + "loss": 3.8906, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.2143274568369388e-05, + "loss": 3.8988, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2134888620858865e-05, + "loss": 3.9067, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2126502673348345e-05, + "loss": 3.9063, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2118116725837824e-05, + "loss": 3.9055, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2109747157131037e-05, + "loss": 3.892, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2101361209620517e-05, + "loss": 3.8708, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2092975262109997e-05, + "loss": 3.914, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.2084589314599477e-05, + "loss": 3.9036, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2076219745892686e-05, + "loss": 3.9008, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.206783379838217e-05, + "loss": 3.8952, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.205944785087165e-05, + "loss": 3.8908, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.205106190336113e-05, + "loss": 3.885, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.204267595585061e-05, + "loss": 3.8907, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.203429000834009e-05, + "loss": 3.8894, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.202590406082957e-05, + "loss": 3.896, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2017518113319046e-05, + "loss": 3.9081, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2009132165808526e-05, + "loss": 3.8879, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.200074621829801e-05, + "loss": 3.8859, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.199236027078749e-05, + "loss": 3.9021, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1983990702080698e-05, + "loss": 3.8846, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1975604754570178e-05, + "loss": 3.8876, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1967218807059658e-05, + "loss": 3.896, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1958832859549138e-05, + "loss": 3.8979, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1950446912038618e-05, + "loss": 3.8885, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.19420609645281e-05, + "loss": 3.8895, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1933675017017578e-05, + "loss": 3.8862, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.192530544831079e-05, + "loss": 3.901, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.191691950080027e-05, + "loss": 3.8976, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.190853355328975e-05, + "loss": 3.8955, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.1900147605779227e-05, + "loss": 3.8951, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1891778037072443e-05, + "loss": 3.9032, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1883392089561922e-05, + "loss": 3.9019, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.18750061420514e-05, + "loss": 3.8872, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.186662019454088e-05, + "loss": 3.8999, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.185823424703036e-05, + "loss": 3.9064, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.184984829951984e-05, + "loss": 3.8832, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1841495109616784e-05, + "loss": 3.8971, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1833109162106264e-05, + "loss": 3.8981, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1824723214595744e-05, + "loss": 3.905, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1816337267085224e-05, + "loss": 3.8944, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.18079513195747e-05, + "loss": 3.8802, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.179956537206418e-05, + "loss": 3.8894, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.1791179424553664e-05, + "loss": 3.8921, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.1782793477043144e-05, + "loss": 3.8986, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1774423908336353e-05, + "loss": 3.8919, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1766037960825833e-05, + "loss": 3.8878, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1757652013315313e-05, + "loss": 3.8955, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.1749266065804793e-05, + "loss": 3.8994, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.1740880118294273e-05, + "loss": 3.8869, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.1732494170783756e-05, + "loss": 3.8908, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.1724108223273232e-05, + "loss": 3.9032, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1715738654566445e-05, + "loss": 3.9037, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1707352707055925e-05, + "loss": 3.8943, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.16989667595454e-05, + "loss": 3.8832, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.169058081203488e-05, + "loss": 3.8929, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1682194864524365e-05, + "loss": 3.8907, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1673825295817577e-05, + "loss": 3.9051, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1665439348307054e-05, + "loss": 3.906, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1657069779600266e-05, + "loss": 3.8914, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1648683832089746e-05, + "loss": 3.889, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1640297884579226e-05, + "loss": 3.8981, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1631911937068706e-05, + "loss": 3.8813, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1623525989558186e-05, + "loss": 3.8982, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1615140042047666e-05, + "loss": 3.8804, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1606754094537146e-05, + "loss": 3.8978, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1598368147026626e-05, + "loss": 3.8865, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1589982199516106e-05, + "loss": 3.8939, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1581596252005586e-05, + "loss": 3.892, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.15732266832988e-05, + "loss": 3.8867, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.156484073578828e-05, + "loss": 3.8971, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.1556454788277758e-05, + "loss": 3.8889, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.1548068840767235e-05, + "loss": 3.9108, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1539682893256715e-05, + "loss": 3.9013, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1531296945746195e-05, + "loss": 3.8945, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.152292737703941e-05, + "loss": 3.8974, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1514541429528887e-05, + "loss": 3.8876, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1506155482018367e-05, + "loss": 3.8942, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.1497769534507847e-05, + "loss": 3.89, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.1489383586997327e-05, + "loss": 3.8961, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1480997639486807e-05, + "loss": 3.8925, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1472611691976287e-05, + "loss": 3.891, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1464225744465767e-05, + "loss": 3.8959, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.145585617575898e-05, + "loss": 3.8935, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.144747022824846e-05, + "loss": 3.8877, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.143908428073794e-05, + "loss": 3.8985, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1430698333227416e-05, + "loss": 3.8812, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1422312385716896e-05, + "loss": 3.9086, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1413942817010112e-05, + "loss": 3.8959, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.140555686949959e-05, + "loss": 3.903, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1397170921989068e-05, + "loss": 3.8845, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.1388784974478548e-05, + "loss": 3.9003, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.1380399026968028e-05, + "loss": 3.9011, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1372013079457508e-05, + "loss": 3.9, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1363627131946988e-05, + "loss": 3.8902, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1355241184436468e-05, + "loss": 3.9048, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.134687161572968e-05, + "loss": 3.8965, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.133848566821916e-05, + "loss": 3.9056, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.133009972070864e-05, + "loss": 3.8873, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.132171377319812e-05, + "loss": 3.9036, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1313327825687597e-05, + "loss": 3.8983, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.130494187817708e-05, + "loss": 3.8961, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.129655593066656e-05, + "loss": 3.8988, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.128816998315604e-05, + "loss": 3.8983, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.127980041444925e-05, + "loss": 3.9014, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.127141446693873e-05, + "loss": 3.8792, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.126302851942821e-05, + "loss": 3.9046, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.995394706726074, + "eval_runtime": 294.7837, + "eval_samples_per_second": 1294.478, + "eval_steps_per_second": 40.453, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.125464257191769e-05, + "loss": 3.8902, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1246256624407173e-05, + "loss": 3.886, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.123788705570038e-05, + "loss": 3.8998, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.122950110818986e-05, + "loss": 3.9062, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.122113153948307e-05, + "loss": 3.899, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.121274559197255e-05, + "loss": 3.8958, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.1204376023265766e-05, + "loss": 3.902, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.1195990075755243e-05, + "loss": 3.8846, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.1187604128244723e-05, + "loss": 3.8976, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.1179218180734203e-05, + "loss": 3.9002, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.1170832233223683e-05, + "loss": 3.8969, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.1162462664516895e-05, + "loss": 3.9027, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.1154093095810108e-05, + "loss": 3.8921, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.1145707148299588e-05, + "loss": 3.8908, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.1137321200789068e-05, + "loss": 3.8905, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.1128935253278544e-05, + "loss": 3.8819, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.1120549305768024e-05, + "loss": 3.8919, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.1112163358257504e-05, + "loss": 3.8863, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.1103777410746988e-05, + "loss": 3.8929, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.1095391463236468e-05, + "loss": 3.9053, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.1087005515725948e-05, + "loss": 3.9081, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.1078619568215424e-05, + "loss": 3.9038, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.1070233620704904e-05, + "loss": 3.8912, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.1061847673194384e-05, + "loss": 3.8996, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.1053461725683864e-05, + "loss": 3.8913, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.1045075778173344e-05, + "loss": 3.8997, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.1036689830662827e-05, + "loss": 3.8953, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.1028303883152307e-05, + "loss": 3.883, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.1019934314445516e-05, + "loss": 3.8958, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.1011564745738725e-05, + "loss": 3.8844, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1003178798228205e-05, + "loss": 3.8942, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.099479285071769e-05, + "loss": 3.9011, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.098640690320717e-05, + "loss": 3.8961, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.097802095569665e-05, + "loss": 3.8967, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.0969651386989858e-05, + "loss": 3.8889, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.096128181828307e-05, + "loss": 3.9076, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.095289587077255e-05, + "loss": 3.8941, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.094450992326203e-05, + "loss": 3.8816, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.093612397575151e-05, + "loss": 3.8915, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.092773802824099e-05, + "loss": 3.8852, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.091935208073047e-05, + "loss": 3.8944, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.091096613321995e-05, + "loss": 3.9003, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.090258018570943e-05, + "loss": 3.89, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.0894194238198906e-05, + "loss": 3.8888, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.088580829068839e-05, + "loss": 3.9007, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.087742234317787e-05, + "loss": 3.9009, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.086903639566735e-05, + "loss": 3.9033, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.086066682696056e-05, + "loss": 3.8858, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.085229725825377e-05, + "loss": 3.8643, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.084391131074325e-05, + "loss": 3.9133, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.083552536323273e-05, + "loss": 3.8936, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.082713941572221e-05, + "loss": 3.8991, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.081875346821169e-05, + "loss": 3.8918, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.081036752070117e-05, + "loss": 3.8818, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.080198157319065e-05, + "loss": 3.8816, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.079359562568013e-05, + "loss": 3.8875, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.0785226056973343e-05, + "loss": 3.8826, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.0776840109462823e-05, + "loss": 3.8864, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.0768454161952303e-05, + "loss": 3.9079, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.0760068214441783e-05, + "loss": 3.8821, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.0751698645734992e-05, + "loss": 3.88, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.0743312698224472e-05, + "loss": 3.901, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.0734926750713952e-05, + "loss": 3.875, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.0726557182007165e-05, + "loss": 3.8826, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.0718171234496645e-05, + "loss": 3.8912, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.0709785286986125e-05, + "loss": 3.8931, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0701415718279334e-05, + "loss": 3.8802, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0693029770768814e-05, + "loss": 3.8898, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0684643823258297e-05, + "loss": 3.8764, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.0676257875747777e-05, + "loss": 3.8939, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.0667871928237257e-05, + "loss": 3.8914, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.0659485980726734e-05, + "loss": 3.8889, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0651100033216214e-05, + "loss": 3.8938, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0642714085705694e-05, + "loss": 3.8958, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0634328138195173e-05, + "loss": 3.9016, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.0625958569488386e-05, + "loss": 3.8802, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.0617572621977866e-05, + "loss": 3.8932, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.0609186674467346e-05, + "loss": 3.8996, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0600800726956826e-05, + "loss": 3.8748, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0592431158250035e-05, + "loss": 3.8957, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0584045210739515e-05, + "loss": 3.8905, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0575659263228998e-05, + "loss": 3.9026, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.0567273315718478e-05, + "loss": 3.8939, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.0558887368207958e-05, + "loss": 3.8752, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.0550501420697438e-05, + "loss": 3.8775, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.0542131851990647e-05, + "loss": 3.8893, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.0533745904480127e-05, + "loss": 3.8956, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0525359956969607e-05, + "loss": 3.8849, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.051697400945909e-05, + "loss": 3.8838, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.0508588061948567e-05, + "loss": 3.889, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.0500202114438047e-05, + "loss": 3.8939, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.0491816166927527e-05, + "loss": 3.8834, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.0483430219417007e-05, + "loss": 3.8852, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.0475077029513952e-05, + "loss": 3.8952, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.0466691082003432e-05, + "loss": 3.8975, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0458305134492912e-05, + "loss": 3.8885, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.044991918698239e-05, + "loss": 3.8784, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.044153323947187e-05, + "loss": 3.8897, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.0433147291961348e-05, + "loss": 3.8842, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.0424761344450828e-05, + "loss": 3.8987, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.0416375396940308e-05, + "loss": 3.8929, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.040800582823352e-05, + "loss": 3.8895, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.0399619880723e-05, + "loss": 3.8867, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.039125031201621e-05, + "loss": 3.8863, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.038286436450569e-05, + "loss": 3.881, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.0374494795798906e-05, + "loss": 3.889, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.0366108848288386e-05, + "loss": 3.8782, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.0357722900777862e-05, + "loss": 3.8951, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.0349336953267342e-05, + "loss": 3.8831, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.0340951005756822e-05, + "loss": 3.887, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.0332565058246302e-05, + "loss": 3.8818, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.0324179110735782e-05, + "loss": 3.8792, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.0315793163225262e-05, + "loss": 3.894, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.0307407215714745e-05, + "loss": 3.8837, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0299021268204222e-05, + "loss": 3.9047, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.0290651699497434e-05, + "loss": 3.8963, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.0282265751986914e-05, + "loss": 3.889, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.027387980447639e-05, + "loss": 3.8906, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.0265493856965874e-05, + "loss": 3.8832, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.0257107909455354e-05, + "loss": 3.8887, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.0248721961944834e-05, + "loss": 3.8924, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.0240352393238043e-05, + "loss": 3.8883, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.0231966445727523e-05, + "loss": 3.8881, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.0223580498217003e-05, + "loss": 3.8857, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.0215194550706483e-05, + "loss": 3.8892, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.0206808603195966e-05, + "loss": 3.8889, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.0198422655685446e-05, + "loss": 3.8771, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.0190036708174926e-05, + "loss": 3.8908, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.0181667139468135e-05, + "loss": 3.8808, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0173281191957615e-05, + "loss": 3.9029, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.0164895244447095e-05, + "loss": 3.891, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.0156525675740308e-05, + "loss": 3.8931, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.0148139728229788e-05, + "loss": 3.8819, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.0139753780719268e-05, + "loss": 3.8943, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.0131367833208748e-05, + "loss": 3.8935, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.0122981885698224e-05, + "loss": 3.8944, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0114595938187704e-05, + "loss": 3.8854, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0106209990677184e-05, + "loss": 3.8982, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0097824043166667e-05, + "loss": 3.8901, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.0089438095656147e-05, + "loss": 3.905, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.0081052148145627e-05, + "loss": 3.881, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.0072682579438836e-05, + "loss": 3.8996, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.0064296631928316e-05, + "loss": 3.8914, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.0055910684417796e-05, + "loss": 3.8901, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0047524736907276e-05, + "loss": 3.892, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0039138789396756e-05, + "loss": 3.894, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.0030752841886236e-05, + "loss": 3.8934, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.002238327317945e-05, + "loss": 3.8743, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.001399732566893e-05, + "loss": 3.8984, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.9936978816986084, + "eval_runtime": 294.2185, + "eval_samples_per_second": 1296.965, + "eval_steps_per_second": 40.531, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.0005611378158405e-05, + "loss": 3.8808, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.9997225430647885e-05, + "loss": 3.8813, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.998883948313737e-05, + "loss": 3.8908, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.998045353562685e-05, + "loss": 3.902, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.997206758811633e-05, + "loss": 3.8964, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.996368164060581e-05, + "loss": 3.8858, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.9955295693095285e-05, + "loss": 3.9002, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.9946909745584765e-05, + "loss": 3.8791, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.9938523798074245e-05, + "loss": 3.8901, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9930137850563725e-05, + "loss": 3.8996, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9921751903053208e-05, + "loss": 3.8917, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.9913365955542688e-05, + "loss": 3.8944, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9904996386835897e-05, + "loss": 3.8946, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.9896610439325377e-05, + "loss": 3.8821, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9888224491814857e-05, + "loss": 3.8813, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9879838544304337e-05, + "loss": 3.8772, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9871452596793817e-05, + "loss": 3.8862, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9863066649283297e-05, + "loss": 3.886, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.9854680701772777e-05, + "loss": 3.8823, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.984631113306599e-05, + "loss": 3.8971, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9837925185555466e-05, + "loss": 3.9041, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9829539238044946e-05, + "loss": 3.8994, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.982115329053443e-05, + "loss": 3.8899, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.981276734302391e-05, + "loss": 3.8909, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.980438139551339e-05, + "loss": 3.8929, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.979599544800287e-05, + "loss": 3.8904, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.978760950049235e-05, + "loss": 3.8928, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.9779223552981826e-05, + "loss": 3.8815, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.9770837605471306e-05, + "loss": 3.8876, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.9762451657960786e-05, + "loss": 3.8805, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.975406571045027e-05, + "loss": 3.8858, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9745696141743478e-05, + "loss": 3.8963, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.9737310194232958e-05, + "loss": 3.895, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.9728924246722438e-05, + "loss": 3.891, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.9720538299211918e-05, + "loss": 3.8877, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.971216873050513e-05, + "loss": 3.8951, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.970378278299461e-05, + "loss": 3.8915, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.969539683548409e-05, + "loss": 3.8796, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.968701088797357e-05, + "loss": 3.8878, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.967862494046305e-05, + "loss": 3.8787, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.967023899295253e-05, + "loss": 3.8882, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.966186942424574e-05, + "loss": 3.897, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.9653483476735223e-05, + "loss": 3.8825, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.9645097529224703e-05, + "loss": 3.887, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9636711581714183e-05, + "loss": 3.9004, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.962832563420366e-05, + "loss": 3.8918, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.961993968669314e-05, + "loss": 3.8958, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.961155373918262e-05, + "loss": 3.8855, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.96031677916721e-05, + "loss": 3.8613, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.959479822296531e-05, + "loss": 3.9012, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.958641227545479e-05, + "loss": 3.8894, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.957802632794427e-05, + "loss": 3.8921, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.956964038043375e-05, + "loss": 3.8899, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.956125443292323e-05, + "loss": 3.8795, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.955286848541271e-05, + "loss": 3.8747, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.954448253790219e-05, + "loss": 3.8823, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.953609659039167e-05, + "loss": 3.8777, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.9527727021684884e-05, + "loss": 3.8783, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.9519341074174364e-05, + "loss": 3.8988, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.951095512666384e-05, + "loss": 3.8799, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.950256917915332e-05, + "loss": 3.8743, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.94941832316428e-05, + "loss": 3.8966, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.9485813662936013e-05, + "loss": 3.8667, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.9477427715425493e-05, + "loss": 3.8763, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9469041767914972e-05, + "loss": 3.8903, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9460655820404452e-05, + "loss": 3.889, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.945228625169766e-05, + "loss": 3.8768, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.944390030418714e-05, + "loss": 3.8811, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.9435514356676625e-05, + "loss": 3.8752, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.9427144787969834e-05, + "loss": 3.8885, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9418758840459314e-05, + "loss": 3.8854, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9410372892948794e-05, + "loss": 3.8846, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9401986945438274e-05, + "loss": 3.8871, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9393600997927754e-05, + "loss": 3.891, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9385215050417234e-05, + "loss": 3.897, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.9376845481710446e-05, + "loss": 3.8737, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.9368459534199926e-05, + "loss": 3.8899, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.9360073586689406e-05, + "loss": 3.8944, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.9351687639178886e-05, + "loss": 3.8672, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.9343318070472095e-05, + "loss": 3.8897, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.933493212296158e-05, + "loss": 3.8886, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.932654617545106e-05, + "loss": 3.8991, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.931816022794054e-05, + "loss": 3.8866, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.9309774280430015e-05, + "loss": 3.8743, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.9301388332919495e-05, + "loss": 3.8683, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.9293018764212707e-05, + "loss": 3.8826, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9284632816702187e-05, + "loss": 3.8903, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9276246869191667e-05, + "loss": 3.8839, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.926787730048488e-05, + "loss": 3.8757, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.925949135297436e-05, + "loss": 3.8817, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.925110540546384e-05, + "loss": 3.8925, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.9242719457953316e-05, + "loss": 3.8813, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.92343335104428e-05, + "loss": 3.8802, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.922594756293228e-05, + "loss": 3.8876, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.921756161542176e-05, + "loss": 3.8924, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.920917566791124e-05, + "loss": 3.8851, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.920080609920445e-05, + "loss": 3.8772, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.919242015169393e-05, + "loss": 3.8798, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.918403420418341e-05, + "loss": 3.8801, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.917564825667289e-05, + "loss": 3.8947, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9167262309162372e-05, + "loss": 3.8913, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.915887636165185e-05, + "loss": 3.885, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.915049041414133e-05, + "loss": 3.8816, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9142104466630808e-05, + "loss": 3.8771, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.913373489792402e-05, + "loss": 3.8822, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.91253489504135e-05, + "loss": 3.8829, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.911696300290298e-05, + "loss": 3.8722, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.910857705539246e-05, + "loss": 3.8903, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.910019110788194e-05, + "loss": 3.8781, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.909180516037142e-05, + "loss": 3.8782, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.90834192128609e-05, + "loss": 3.8778, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9075033265350377e-05, + "loss": 3.8714, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.9066663696643593e-05, + "loss": 3.8935, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9058277749133073e-05, + "loss": 3.8766, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9049891801622553e-05, + "loss": 3.9014, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9041522232915762e-05, + "loss": 3.8904, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9033136285405242e-05, + "loss": 3.8857, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.9024750337894722e-05, + "loss": 3.8847, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.9016364390384202e-05, + "loss": 3.8813, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.9007994821677414e-05, + "loss": 3.8824, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.8999608874166894e-05, + "loss": 3.8877, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.8991239305460103e-05, + "loss": 3.8803, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8982853357949583e-05, + "loss": 3.8859, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8974467410439063e-05, + "loss": 3.8782, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.8966081462928547e-05, + "loss": 3.8837, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.8957695515418027e-05, + "loss": 3.8832, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.8949309567907503e-05, + "loss": 3.872, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.8940923620396983e-05, + "loss": 3.886, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8932537672886463e-05, + "loss": 3.8763, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8924151725375943e-05, + "loss": 3.8966, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8915765777865423e-05, + "loss": 3.8848, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.8907396209158635e-05, + "loss": 3.8877, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.8899010261648115e-05, + "loss": 3.8758, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.8890624314137595e-05, + "loss": 3.8947, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.8882238366627075e-05, + "loss": 3.884, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.8873852419116555e-05, + "loss": 3.8904, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8865466471606032e-05, + "loss": 3.8825, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8857080524095512e-05, + "loss": 3.8928, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.8848710955388728e-05, + "loss": 3.8863, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.8840325007878208e-05, + "loss": 3.9021, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.8831939060367684e-05, + "loss": 3.8764, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.8823553112857164e-05, + "loss": 3.8934, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8815183544150377e-05, + "loss": 3.889, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8806797596639857e-05, + "loss": 3.8898, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8798411649129337e-05, + "loss": 3.8811, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8790025701618816e-05, + "loss": 3.8898, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8781639754108296e-05, + "loss": 3.8878, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.8773270185401506e-05, + "loss": 3.8778, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.8764884237890985e-05, + "loss": 3.8893, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.9924795627593994, + "eval_runtime": 295.3852, + "eval_samples_per_second": 1291.842, + "eval_steps_per_second": 40.371, + "step": 1908000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8756498290380465e-05, + "loss": 3.8778, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.874811234286995e-05, + "loss": 3.8756, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.873972639535943e-05, + "loss": 3.8853, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.873134044784891e-05, + "loss": 3.8965, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.872295450033839e-05, + "loss": 3.892, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.8714568552827865e-05, + "loss": 3.8791, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.8706182605317345e-05, + "loss": 3.8976, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.8697813036610558e-05, + "loss": 3.8743, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.8689427089100038e-05, + "loss": 3.8827, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.8681041141589518e-05, + "loss": 3.8959, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.8672655194078998e-05, + "loss": 3.8831, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.8664269246568477e-05, + "loss": 3.8901, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.865591605666542e-05, + "loss": 3.8919, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.8647530109154902e-05, + "loss": 3.879, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.8639144161644382e-05, + "loss": 3.8766, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.8630758214133862e-05, + "loss": 3.8754, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.862237226662334e-05, + "loss": 3.8813, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.861398631911282e-05, + "loss": 3.8816, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.860561675040603e-05, + "loss": 3.8776, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.859723080289551e-05, + "loss": 3.8933, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.858884485538499e-05, + "loss": 3.8971, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.858045890787447e-05, + "loss": 3.8971, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.857207296036395e-05, + "loss": 3.8887, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.856368701285343e-05, + "loss": 3.8816, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.855530106534291e-05, + "loss": 3.8903, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.854693149663612e-05, + "loss": 3.8848, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.8538545549125604e-05, + "loss": 3.882, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.8530159601615084e-05, + "loss": 3.8801, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.8521773654104563e-05, + "loss": 3.8816, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.8513387706594043e-05, + "loss": 3.8782, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.850500175908352e-05, + "loss": 3.8813, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.8496615811573e-05, + "loss": 3.8892, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.848822986406248e-05, + "loss": 3.8938, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.8479860295355692e-05, + "loss": 3.8824, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.8471474347845172e-05, + "loss": 3.8856, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.8463104779138385e-05, + "loss": 3.8838, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.8454718831627865e-05, + "loss": 3.8918, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.844633288411734e-05, + "loss": 3.8749, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.8437946936606825e-05, + "loss": 3.8814, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.8429560989096305e-05, + "loss": 3.8714, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.8421175041585785e-05, + "loss": 3.8856, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.8412805472878994e-05, + "loss": 3.8863, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.8404419525368474e-05, + "loss": 3.8796, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.8396033577857954e-05, + "loss": 3.8846, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.8387647630347434e-05, + "loss": 3.8907, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.8379261682836914e-05, + "loss": 3.887, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.8370875735326397e-05, + "loss": 3.8906, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.8362489787815873e-05, + "loss": 3.8839, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.8354103840305353e-05, + "loss": 3.8548, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.8345734271598566e-05, + "loss": 3.8919, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.8337348324088046e-05, + "loss": 3.8837, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.8328962376577526e-05, + "loss": 3.8883, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.8320576429067006e-05, + "loss": 3.8845, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.8312190481556486e-05, + "loss": 3.8732, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.8303820912849698e-05, + "loss": 3.8702, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.8295434965339175e-05, + "loss": 3.8743, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.8287049017828655e-05, + "loss": 3.8782, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.8278663070318135e-05, + "loss": 3.8722, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.8270293501611347e-05, + "loss": 3.8957, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.8261907554100827e-05, + "loss": 3.8763, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.825353798539404e-05, + "loss": 3.8643, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.824515203788352e-05, + "loss": 3.8944, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.8236766090372996e-05, + "loss": 3.8667, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.822838014286248e-05, + "loss": 3.8687, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.821999419535196e-05, + "loss": 3.8862, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.821160824784144e-05, + "loss": 3.8804, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.820323867913465e-05, + "loss": 3.876, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.819485273162413e-05, + "loss": 3.8751, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.818646678411361e-05, + "loss": 3.8702, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.817808083660309e-05, + "loss": 3.8829, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.816969488909257e-05, + "loss": 3.8799, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.816130894158205e-05, + "loss": 3.8803, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.8152922994071528e-05, + "loss": 3.8802, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.8144537046561008e-05, + "loss": 3.884, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.813616747785422e-05, + "loss": 3.8945, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.8127797909147433e-05, + "loss": 3.8677, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.8119411961636913e-05, + "loss": 3.8826, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.8111026014126393e-05, + "loss": 3.8915, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.8102640066615873e-05, + "loss": 3.8653, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.809425411910535e-05, + "loss": 3.8797, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.8085884550398562e-05, + "loss": 3.887, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.8077498602888042e-05, + "loss": 3.8912, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.8069112655377522e-05, + "loss": 3.8883, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.8060726707867002e-05, + "loss": 3.8651, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.8052340760356482e-05, + "loss": 3.8613, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.8043954812845962e-05, + "loss": 3.8827, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.8035568865335442e-05, + "loss": 3.8846, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.8027182917824922e-05, + "loss": 3.8723, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.8018829727921867e-05, + "loss": 3.878, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.8010443780411347e-05, + "loss": 3.8753, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.8002057832900823e-05, + "loss": 3.8862, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.7993671885390303e-05, + "loss": 3.8786, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.7985285937879783e-05, + "loss": 3.8747, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.7976899990369263e-05, + "loss": 3.8784, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.7968530421662476e-05, + "loss": 3.8875, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.7960144474151956e-05, + "loss": 3.8831, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.7951758526641436e-05, + "loss": 3.8736, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.7943372579130915e-05, + "loss": 3.874, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.7934986631620395e-05, + "loss": 3.8741, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.7926617062913605e-05, + "loss": 3.8875, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.7918231115403088e-05, + "loss": 3.8819, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.7909845167892568e-05, + "loss": 3.8799, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.7901459220382048e-05, + "loss": 3.878, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.7893073272871528e-05, + "loss": 3.872, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.7884687325361004e-05, + "loss": 3.8809, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.7876317756654217e-05, + "loss": 3.8737, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.7867931809143697e-05, + "loss": 3.8681, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.785954586163318e-05, + "loss": 3.8868, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.7851159914122657e-05, + "loss": 3.8743, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.7842773966612137e-05, + "loss": 3.8755, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.7834388019101617e-05, + "loss": 3.8704, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.7826002071591097e-05, + "loss": 3.8671, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.7817616124080576e-05, + "loss": 3.8864, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.780924655537379e-05, + "loss": 3.8749, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.7800876986667e-05, + "loss": 3.8939, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.7792491039156478e-05, + "loss": 3.8841, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.7784105091645958e-05, + "loss": 3.8819, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.7775719144135438e-05, + "loss": 3.8796, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.7767333196624918e-05, + "loss": 3.8802, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.7758947249114398e-05, + "loss": 3.8735, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.775057768040761e-05, + "loss": 3.8854, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.774219173289709e-05, + "loss": 3.8798, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.773380578538657e-05, + "loss": 3.8785, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.772541983787605e-05, + "loss": 3.8724, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.771703389036553e-05, + "loss": 3.8797, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.770864794285501e-05, + "loss": 3.8785, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.770026199534449e-05, + "loss": 3.8681, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.769187604783397e-05, + "loss": 3.8833, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.768349010032345e-05, + "loss": 3.8647, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.767510415281293e-05, + "loss": 3.899, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.766673458410614e-05, + "loss": 3.8794, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.765834863659562e-05, + "loss": 3.884, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.76499626890851e-05, + "loss": 3.8708, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.7641576741574582e-05, + "loss": 3.8904, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.7633190794064062e-05, + "loss": 3.8784, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.762482122535727e-05, + "loss": 3.8856, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.761643527784675e-05, + "loss": 3.8787, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.760806570913996e-05, + "loss": 3.8827, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.7599679761629444e-05, + "loss": 3.8819, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.7591293814118924e-05, + "loss": 3.899, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.7582907866608404e-05, + "loss": 3.8704, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.7574521919097884e-05, + "loss": 3.888, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.7566135971587364e-05, + "loss": 3.8877, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.7557766402880573e-05, + "loss": 3.8836, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.7549380455370053e-05, + "loss": 3.8736, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.7540994507859536e-05, + "loss": 3.8847, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.7532608560349016e-05, + "loss": 3.8805, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.7524222612838492e-05, + "loss": 3.8762, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.7515836665327972e-05, + "loss": 3.8818, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.9905948638916016, + "eval_runtime": 293.8595, + "eval_samples_per_second": 1298.549, + "eval_steps_per_second": 40.581, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.7507450717817452e-05, + "loss": 3.8729, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7499064770306932e-05, + "loss": 3.8686, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.7490678822796412e-05, + "loss": 3.8803, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.7482292875285892e-05, + "loss": 3.8911, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.7473906927775372e-05, + "loss": 3.8898, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.7465520980264852e-05, + "loss": 3.8778, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.7457135032754332e-05, + "loss": 3.8869, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.7448749085243812e-05, + "loss": 3.8741, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.7440363137733292e-05, + "loss": 3.8757, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.7431977190222772e-05, + "loss": 3.8914, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.7423591242712252e-05, + "loss": 3.8804, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.7415205295201732e-05, + "loss": 3.889, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.7406835726494944e-05, + "loss": 3.8881, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.7398449778984424e-05, + "loss": 3.8713, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.7390063831473904e-05, + "loss": 3.8707, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.738167788396338e-05, + "loss": 3.8656, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.737329193645286e-05, + "loss": 3.8771, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.7364905988942344e-05, + "loss": 3.8798, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.7356520041431824e-05, + "loss": 3.868, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.7348134093921304e-05, + "loss": 3.8868, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.7339748146410784e-05, + "loss": 3.8923, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.733136219890026e-05, + "loss": 3.8872, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.732297625138974e-05, + "loss": 3.8857, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.731459030387922e-05, + "loss": 3.88, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.73062043563687e-05, + "loss": 3.8853, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.7297818408858184e-05, + "loss": 3.8799, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.7289465218955125e-05, + "loss": 3.8734, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.7281079271444605e-05, + "loss": 3.8712, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.7272693323934085e-05, + "loss": 3.8788, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.7264323755227298e-05, + "loss": 3.873, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.7255937807716778e-05, + "loss": 3.8775, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.7247551860206258e-05, + "loss": 3.8817, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.7239165912695734e-05, + "loss": 3.8864, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.7230779965185214e-05, + "loss": 3.8853, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.7222394017674694e-05, + "loss": 3.8731, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.7214024448967907e-05, + "loss": 3.8825, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.7205638501457387e-05, + "loss": 3.888, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.7197252553946867e-05, + "loss": 3.8646, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.7188866606436347e-05, + "loss": 3.8791, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.718049703772956e-05, + "loss": 3.8689, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.7172111090219036e-05, + "loss": 3.8817, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.7163725142708516e-05, + "loss": 3.8789, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.7155339195198e-05, + "loss": 3.8751, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.714695324768748e-05, + "loss": 3.8804, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.713856730017696e-05, + "loss": 3.8854, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.713018135266644e-05, + "loss": 3.8842, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.7121795405155915e-05, + "loss": 3.8866, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.7113409457645395e-05, + "loss": 3.876, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.7105023510134875e-05, + "loss": 3.8525, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.709665394142809e-05, + "loss": 3.8876, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.7088267993917568e-05, + "loss": 3.8788, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.7079882046407048e-05, + "loss": 3.8834, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.7071496098896528e-05, + "loss": 3.8779, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.7063110151386008e-05, + "loss": 3.8718, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.7054724203875488e-05, + "loss": 3.8644, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.7046338256364967e-05, + "loss": 3.8682, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.7037952308854447e-05, + "loss": 3.8752, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.702958274014766e-05, + "loss": 3.8612, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.702119679263714e-05, + "loss": 3.8912, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.701281084512662e-05, + "loss": 3.8746, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.7004424897616096e-05, + "loss": 3.8609, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.699605532890931e-05, + "loss": 3.886, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.698768576020252e-05, + "loss": 3.8621, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.6979316191495734e-05, + "loss": 3.8646, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.697093024398521e-05, + "loss": 3.881, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.696254429647469e-05, + "loss": 3.8762, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.695415834896417e-05, + "loss": 3.869, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.6945772401453654e-05, + "loss": 3.8694, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.6937386453943134e-05, + "loss": 3.8666, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.6929000506432614e-05, + "loss": 3.8753, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.6920630937725823e-05, + "loss": 3.8815, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.6912244990215303e-05, + "loss": 3.8744, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.6903859042704783e-05, + "loss": 3.8764, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.6895473095194263e-05, + "loss": 3.8757, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.6887087147683746e-05, + "loss": 3.8907, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.6878701200173222e-05, + "loss": 3.8662, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6870315252662702e-05, + "loss": 3.8787, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.6861929305152182e-05, + "loss": 3.8799, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.685355973644539e-05, + "loss": 3.8645, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.6845190167738607e-05, + "loss": 3.8736, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.6836804220228087e-05, + "loss": 3.8811, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.6828418272717567e-05, + "loss": 3.8863, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.6820032325207044e-05, + "loss": 3.8851, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.6811646377696524e-05, + "loss": 3.8582, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.6803260430186004e-05, + "loss": 3.8613, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.6794874482675484e-05, + "loss": 3.8751, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.6786488535164967e-05, + "loss": 3.8783, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.6778102587654447e-05, + "loss": 3.8666, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.6769733018947656e-05, + "loss": 3.8726, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.6761347071437136e-05, + "loss": 3.8709, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.6752961123926616e-05, + "loss": 3.8814, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.6744575176416096e-05, + "loss": 3.8732, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.6736189228905576e-05, + "loss": 3.8712, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.6727803281395056e-05, + "loss": 3.8772, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.671943371268827e-05, + "loss": 3.8816, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.6711047765177748e-05, + "loss": 3.8792, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.6702661817667225e-05, + "loss": 3.8655, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.6694275870156705e-05, + "loss": 3.8688, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.6685889922646185e-05, + "loss": 3.8748, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.6677503975135668e-05, + "loss": 3.8819, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.6669118027625148e-05, + "loss": 3.88, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.6660732080114628e-05, + "loss": 3.8745, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.665237889021157e-05, + "loss": 3.8728, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.6643992942701046e-05, + "loss": 3.8675, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.663560699519053e-05, + "loss": 3.874, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.662722104768001e-05, + "loss": 3.8683, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.6618851478973222e-05, + "loss": 3.8667, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.66104655314627e-05, + "loss": 3.8782, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.660207958395218e-05, + "loss": 3.8693, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.659369363644166e-05, + "loss": 3.8701, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.658530768893114e-05, + "loss": 3.866, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.6576921741420622e-05, + "loss": 3.8627, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.6568535793910102e-05, + "loss": 3.8794, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.656014984639958e-05, + "loss": 3.8738, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.6551763898889058e-05, + "loss": 3.8833, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.654339433018227e-05, + "loss": 3.8786, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.653500838267175e-05, + "loss": 3.8793, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.652662243516123e-05, + "loss": 3.875, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.651823648765071e-05, + "loss": 3.875, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.650985054014019e-05, + "loss": 3.871, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.650146459262967e-05, + "loss": 3.8786, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.649307864511915e-05, + "loss": 3.8729, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.648469269760863e-05, + "loss": 3.8778, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.647632312890184e-05, + "loss": 3.8658, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.6467937181391323e-05, + "loss": 3.8774, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.6459551233880803e-05, + "loss": 3.8704, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.6451165286370283e-05, + "loss": 3.8653, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.6442795717663492e-05, + "loss": 3.8746, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.64344261489567e-05, + "loss": 3.8604, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.6426040201446184e-05, + "loss": 3.8966, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.6417654253935664e-05, + "loss": 3.8724, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.6409268306425144e-05, + "loss": 3.8817, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.6400882358914624e-05, + "loss": 3.8663, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.6392496411404104e-05, + "loss": 3.8817, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.6384126842697313e-05, + "loss": 3.8758, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.6375757273990526e-05, + "loss": 3.8806, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.6367371326480006e-05, + "loss": 3.8722, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.6358985378969486e-05, + "loss": 3.8731, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.6350599431458966e-05, + "loss": 3.8771, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.6342213483948446e-05, + "loss": 3.8965, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.6333827536437926e-05, + "loss": 3.8632, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.6325441588927405e-05, + "loss": 3.8887, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.6317055641416885e-05, + "loss": 3.8831, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.6308669693906365e-05, + "loss": 3.8774, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.6300283746395845e-05, + "loss": 3.8709, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.6291914177689058e-05, + "loss": 3.8793, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.6283528230178534e-05, + "loss": 3.8752, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.6275142282668014e-05, + "loss": 3.8744, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.6266756335157494e-05, + "loss": 3.8744, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.989058017730713, + "eval_runtime": 281.948, + "eval_samples_per_second": 1353.409, + "eval_steps_per_second": 42.295, + "step": 2060640 + }, + { + "epoch": 1.0, + "learning_rate": 1.6258370387646978e-05, + "loss": 3.8693, + "step": 2060800 + }, + { + "epoch": 1.0, + "learning_rate": 1.6249984440136458e-05, + "loss": 3.8653, + "step": 2061312 + }, + { + "epoch": 1.0, + "learning_rate": 1.6241614871429667e-05, + "loss": 3.8749, + "step": 2061824 + }, + { + "epoch": 1.0, + "learning_rate": 1.6233228923919147e-05, + "loss": 3.8844, + "step": 2062336 + }, + { + "epoch": 1.0, + "learning_rate": 1.6224842976408627e-05, + "loss": 3.8878, + "step": 2062848 + }, + { + "epoch": 1.0, + "learning_rate": 1.6216457028898107e-05, + "loss": 3.8717, + "step": 2063360 + }, + { + "epoch": 1.0, + "learning_rate": 1.620808746019132e-05, + "loss": 3.8836, + "step": 2063872 + }, + { + "epoch": 1.0, + "learning_rate": 1.61997015126808e-05, + "loss": 3.8717, + "step": 2064384 + }, + { + "epoch": 1.0, + "learning_rate": 1.619131556517028e-05, + "loss": 3.8684, + "step": 2064896 + }, + { + "epoch": 1.0, + "learning_rate": 1.618292961765976e-05, + "loss": 3.8838, + "step": 2065408 + }, + { + "epoch": 1.0, + "learning_rate": 1.617454367014924e-05, + "loss": 3.8836, + "step": 2065920 + }, + { + "epoch": 1.0, + "learning_rate": 1.6166157722638715e-05, + "loss": 3.8845, + "step": 2066432 + }, + { + "epoch": 1.0, + "learning_rate": 1.615778815393193e-05, + "loss": 3.8794, + "step": 2066944 + }, + { + "epoch": 1.0, + "learning_rate": 1.614940220642141e-05, + "loss": 3.8675, + "step": 2067456 + }, + { + "epoch": 1.0, + "learning_rate": 1.6141016258910888e-05, + "loss": 3.8705, + "step": 2067968 + }, + { + "epoch": 1.0, + "learning_rate": 1.6132630311400368e-05, + "loss": 3.8536, + "step": 2068480 + }, + { + "epoch": 1.0, + "learning_rate": 1.6124244363889848e-05, + "loss": 3.8763, + "step": 2068992 + }, + { + "epoch": 1.0, + "learning_rate": 1.6115858416379328e-05, + "loss": 3.8736, + "step": 2069504 + }, + { + "epoch": 1.0, + "learning_rate": 1.6107472468868808e-05, + "loss": 3.8643, + "step": 2070016 + }, + { + "epoch": 1.0, + "learning_rate": 1.6099086521358288e-05, + "loss": 3.8799, + "step": 2070528 + }, + { + "epoch": 1.0, + "learning_rate": 1.60907169526515e-05, + "loss": 3.888, + "step": 2071040 + }, + { + "epoch": 1.0, + "learning_rate": 1.608233100514098e-05, + "loss": 3.8827, + "step": 2071552 + }, + { + "epoch": 1.0, + "learning_rate": 1.607394505763046e-05, + "loss": 3.8785, + "step": 2072064 + }, + { + "epoch": 1.0, + "learning_rate": 1.606557548892367e-05, + "loss": 3.8764, + "step": 2072576 + }, + { + "epoch": 1.0, + "learning_rate": 1.605718954141315e-05, + "loss": 3.8794, + "step": 2073088 + }, + { + "epoch": 1.0, + "learning_rate": 1.6048803593902632e-05, + "loss": 3.8781, + "step": 2073600 + }, + { + "epoch": 1.0, + "learning_rate": 1.6040417646392112e-05, + "loss": 3.8688, + "step": 2074112 + }, + { + "epoch": 1.0, + "learning_rate": 1.6032031698881592e-05, + "loss": 3.8662, + "step": 2074624 + }, + { + "epoch": 1.0, + "learning_rate": 1.602364575137107e-05, + "loss": 3.8743, + "step": 2075136 + }, + { + "epoch": 1.0, + "learning_rate": 1.601525980386055e-05, + "loss": 3.8682, + "step": 2075648 + }, + { + "epoch": 1.01, + "learning_rate": 1.600687385635003e-05, + "loss": 3.877, + "step": 2076160 + }, + { + "epoch": 1.01, + "learning_rate": 1.599850428764324e-05, + "loss": 3.8745, + "step": 2076672 + }, + { + "epoch": 1.01, + "learning_rate": 1.599011834013272e-05, + "loss": 3.8759, + "step": 2077184 + }, + { + "epoch": 1.01, + "learning_rate": 1.5981748771425934e-05, + "loss": 3.8841, + "step": 2077696 + }, + { + "epoch": 1.01, + "learning_rate": 1.5973362823915414e-05, + "loss": 3.8684, + "step": 2078208 + }, + { + "epoch": 1.01, + "learning_rate": 1.5964993255208623e-05, + "loss": 3.8802, + "step": 2078720 + }, + { + "epoch": 1.01, + "learning_rate": 1.5956607307698103e-05, + "loss": 3.8825, + "step": 2079232 + }, + { + "epoch": 1.01, + "learning_rate": 1.5948221360187586e-05, + "loss": 3.8585, + "step": 2079744 + }, + { + "epoch": 1.01, + "learning_rate": 1.5939835412677066e-05, + "loss": 3.8764, + "step": 2080256 + }, + { + "epoch": 1.01, + "learning_rate": 1.5931449465166543e-05, + "loss": 3.8657, + "step": 2080768 + }, + { + "epoch": 1.01, + "learning_rate": 1.5923063517656023e-05, + "loss": 3.8727, + "step": 2081280 + }, + { + "epoch": 1.01, + "learning_rate": 1.5914693948949235e-05, + "loss": 3.8751, + "step": 2081792 + }, + { + "epoch": 1.01, + "learning_rate": 1.5906308001438715e-05, + "loss": 3.8707, + "step": 2082304 + }, + { + "epoch": 1.01, + "learning_rate": 1.5897922053928195e-05, + "loss": 3.8752, + "step": 2082816 + }, + { + "epoch": 1.01, + "learning_rate": 1.5889536106417675e-05, + "loss": 3.8794, + "step": 2083328 + }, + { + "epoch": 1.01, + "learning_rate": 1.5881150158907155e-05, + "loss": 3.8812, + "step": 2083840 + }, + { + "epoch": 1.01, + "learning_rate": 1.5872764211396635e-05, + "loss": 3.8801, + "step": 2084352 + }, + { + "epoch": 1.01, + "learning_rate": 1.5864378263886115e-05, + "loss": 3.8735, + "step": 2084864 + }, + { + "epoch": 1.01, + "learning_rate": 1.5855992316375595e-05, + "loss": 3.8457, + "step": 2085376 + }, + { + "epoch": 1.01, + "learning_rate": 1.584760636886507e-05, + "loss": 3.8814, + "step": 2085888 + }, + { + "epoch": 1.01, + "learning_rate": 1.5839220421354555e-05, + "loss": 3.8742, + "step": 2086400 + }, + { + "epoch": 1.01, + "learning_rate": 1.5830834473844035e-05, + "loss": 3.8815, + "step": 2086912 + }, + { + "epoch": 1.01, + "learning_rate": 1.5822448526333515e-05, + "loss": 3.8736, + "step": 2087424 + }, + { + "epoch": 1.01, + "learning_rate": 1.5814078957626724e-05, + "loss": 3.8619, + "step": 2087936 + }, + { + "epoch": 1.01, + "learning_rate": 1.5805693010116204e-05, + "loss": 3.8671, + "step": 2088448 + }, + { + "epoch": 1.01, + "learning_rate": 1.5797307062605684e-05, + "loss": 3.8601, + "step": 2088960 + }, + { + "epoch": 1.01, + "learning_rate": 1.5788937493898896e-05, + "loss": 3.8712, + "step": 2089472 + }, + { + "epoch": 1.01, + "learning_rate": 1.5780551546388376e-05, + "loss": 3.8541, + "step": 2089984 + }, + { + "epoch": 1.01, + "learning_rate": 1.5772165598877856e-05, + "loss": 3.8888, + "step": 2090496 + }, + { + "epoch": 1.01, + "learning_rate": 1.5763779651367336e-05, + "loss": 3.8748, + "step": 2091008 + }, + { + "epoch": 1.01, + "learning_rate": 1.5755410082660545e-05, + "loss": 3.8543, + "step": 2091520 + }, + { + "epoch": 1.01, + "learning_rate": 1.5747024135150025e-05, + "loss": 3.8802, + "step": 2092032 + }, + { + "epoch": 1.01, + "learning_rate": 1.5738638187639508e-05, + "loss": 3.8601, + "step": 2092544 + }, + { + "epoch": 1.01, + "learning_rate": 1.5730252240128988e-05, + "loss": 3.8626, + "step": 2093056 + }, + { + "epoch": 1.01, + "learning_rate": 1.5721882671422197e-05, + "loss": 3.8699, + "step": 2093568 + }, + { + "epoch": 1.01, + "learning_rate": 1.5713496723911677e-05, + "loss": 3.8711, + "step": 2094080 + }, + { + "epoch": 1.01, + "learning_rate": 1.5705110776401157e-05, + "loss": 3.8638, + "step": 2094592 + }, + { + "epoch": 1.01, + "learning_rate": 1.5696724828890637e-05, + "loss": 3.8682, + "step": 2095104 + }, + { + "epoch": 1.01, + "learning_rate": 1.5688338881380117e-05, + "loss": 3.8595, + "step": 2095616 + }, + { + "epoch": 1.01, + "learning_rate": 1.567996931267333e-05, + "loss": 3.8711, + "step": 2096128 + }, + { + "epoch": 1.01, + "learning_rate": 1.567158336516281e-05, + "loss": 3.8752, + "step": 2096640 + }, + { + "epoch": 1.01, + "learning_rate": 1.566319741765229e-05, + "loss": 3.8707, + "step": 2097152 + }, + { + "epoch": 1.01, + "learning_rate": 1.565481147014177e-05, + "loss": 3.8756, + "step": 2097664 + }, + { + "epoch": 1.01, + "learning_rate": 1.564642552263125e-05, + "loss": 3.866, + "step": 2098176 + }, + { + "epoch": 1.01, + "learning_rate": 1.5638039575120726e-05, + "loss": 3.8912, + "step": 2098688 + }, + { + "epoch": 1.01, + "learning_rate": 1.562965362761021e-05, + "loss": 3.858, + "step": 2099200 + }, + { + "epoch": 1.01, + "learning_rate": 1.562126768009969e-05, + "loss": 3.8784, + "step": 2099712 + }, + { + "epoch": 1.01, + "learning_rate": 1.5612898111392902e-05, + "loss": 3.8675, + "step": 2100224 + }, + { + "epoch": 1.01, + "learning_rate": 1.560451216388238e-05, + "loss": 3.8685, + "step": 2100736 + }, + { + "epoch": 1.01, + "learning_rate": 1.559612621637186e-05, + "loss": 3.8673, + "step": 2101248 + }, + { + "epoch": 1.01, + "learning_rate": 1.558775664766507e-05, + "loss": 3.8772, + "step": 2101760 + }, + { + "epoch": 1.01, + "learning_rate": 1.5579387078958283e-05, + "loss": 3.8814, + "step": 2102272 + }, + { + "epoch": 1.01, + "learning_rate": 1.5571001131447763e-05, + "loss": 3.8788, + "step": 2102784 + }, + { + "epoch": 1.01, + "learning_rate": 1.5562631562740972e-05, + "loss": 3.8549, + "step": 2103296 + }, + { + "epoch": 1.01, + "learning_rate": 1.5554245615230452e-05, + "loss": 3.856, + "step": 2103808 + }, + { + "epoch": 1.01, + "learning_rate": 1.5545859667719932e-05, + "loss": 3.8686, + "step": 2104320 + }, + { + "epoch": 1.01, + "learning_rate": 1.5537473720209416e-05, + "loss": 3.8767, + "step": 2104832 + }, + { + "epoch": 1.01, + "learning_rate": 1.5529087772698896e-05, + "loss": 3.8637, + "step": 2105344 + }, + { + "epoch": 1.01, + "learning_rate": 1.5520701825188376e-05, + "loss": 3.8656, + "step": 2105856 + }, + { + "epoch": 1.01, + "learning_rate": 1.5512315877677852e-05, + "loss": 3.8681, + "step": 2106368 + }, + { + "epoch": 1.02, + "learning_rate": 1.5503929930167332e-05, + "loss": 3.8708, + "step": 2106880 + }, + { + "epoch": 1.02, + "learning_rate": 1.5495543982656812e-05, + "loss": 3.8719, + "step": 2107392 + }, + { + "epoch": 1.02, + "learning_rate": 1.5487158035146292e-05, + "loss": 3.8667, + "step": 2107904 + }, + { + "epoch": 1.02, + "learning_rate": 1.5478772087635772e-05, + "loss": 3.8734, + "step": 2108416 + }, + { + "epoch": 1.02, + "learning_rate": 1.5470386140125255e-05, + "loss": 3.8747, + "step": 2108928 + }, + { + "epoch": 1.02, + "learning_rate": 1.5462000192614735e-05, + "loss": 3.8779, + "step": 2109440 + }, + { + "epoch": 1.02, + "learning_rate": 1.5453614245104212e-05, + "loss": 3.8608, + "step": 2109952 + }, + { + "epoch": 1.02, + "learning_rate": 1.5445244676397424e-05, + "loss": 3.862, + "step": 2110464 + }, + { + "epoch": 1.02, + "learning_rate": 1.5436858728886904e-05, + "loss": 3.868, + "step": 2110976 + }, + { + "epoch": 1.02, + "learning_rate": 1.542847278137638e-05, + "loss": 3.8757, + "step": 2111488 + }, + { + "epoch": 1.02, + "learning_rate": 1.5420086833865864e-05, + "loss": 3.8775, + "step": 2112000 + }, + { + "epoch": 1.02, + "learning_rate": 1.5411700886355344e-05, + "loss": 3.8703, + "step": 2112512 + }, + { + "epoch": 1.02, + "learning_rate": 1.5403314938844824e-05, + "loss": 3.8705, + "step": 2113024 + }, + { + "epoch": 1.02, + "learning_rate": 1.5394928991334304e-05, + "loss": 3.8632, + "step": 2113536 + }, + { + "epoch": 1.02, + "learning_rate": 1.5386543043823784e-05, + "loss": 3.869, + "step": 2114048 + }, + { + "epoch": 1.02, + "learning_rate": 1.5378157096313264e-05, + "loss": 3.8663, + "step": 2114560 + }, + { + "epoch": 1.02, + "learning_rate": 1.536980390641021e-05, + "loss": 3.8613, + "step": 2115072 + }, + { + "epoch": 1.02, + "learning_rate": 1.5361417958899685e-05, + "loss": 3.8728, + "step": 2115584 + }, + { + "epoch": 1.02, + "learning_rate": 1.5353032011389165e-05, + "loss": 3.8657, + "step": 2116096 + }, + { + "epoch": 1.02, + "learning_rate": 1.5344646063878645e-05, + "loss": 3.8629, + "step": 2116608 + }, + { + "epoch": 1.02, + "learning_rate": 1.5336260116368125e-05, + "loss": 3.8638, + "step": 2117120 + }, + { + "epoch": 1.02, + "learning_rate": 1.5327874168857605e-05, + "loss": 3.8573, + "step": 2117632 + }, + { + "epoch": 1.02, + "learning_rate": 1.5319488221347085e-05, + "loss": 3.8768, + "step": 2118144 + }, + { + "epoch": 1.02, + "learning_rate": 1.5311102273836565e-05, + "loss": 3.8689, + "step": 2118656 + }, + { + "epoch": 1.02, + "learning_rate": 1.5302732705129778e-05, + "loss": 3.879, + "step": 2119168 + }, + { + "epoch": 1.02, + "learning_rate": 1.5294346757619258e-05, + "loss": 3.8691, + "step": 2119680 + }, + { + "epoch": 1.02, + "learning_rate": 1.5285960810108738e-05, + "loss": 3.8773, + "step": 2120192 + }, + { + "epoch": 1.02, + "learning_rate": 1.5277574862598214e-05, + "loss": 3.8709, + "step": 2120704 + }, + { + "epoch": 1.02, + "learning_rate": 1.5269205293891427e-05, + "loss": 3.8641, + "step": 2121216 + }, + { + "epoch": 1.02, + "learning_rate": 1.526081934638091e-05, + "loss": 3.8749, + "step": 2121728 + }, + { + "epoch": 1.02, + "learning_rate": 1.5252433398870387e-05, + "loss": 3.8692, + "step": 2122240 + }, + { + "epoch": 1.02, + "learning_rate": 1.5244047451359867e-05, + "loss": 3.8671, + "step": 2122752 + }, + { + "epoch": 1.02, + "learning_rate": 1.523569426145681e-05, + "loss": 3.8759, + "step": 2123264 + }, + { + "epoch": 1.02, + "learning_rate": 1.522730831394629e-05, + "loss": 3.8638, + "step": 2123776 + }, + { + "epoch": 1.02, + "learning_rate": 1.521892236643577e-05, + "loss": 3.8702, + "step": 2124288 + }, + { + "epoch": 1.02, + "learning_rate": 1.521053641892525e-05, + "loss": 3.8625, + "step": 2124800 + }, + { + "epoch": 1.02, + "learning_rate": 1.5202150471414731e-05, + "loss": 3.8618, + "step": 2125312 + }, + { + "epoch": 1.02, + "learning_rate": 1.5193764523904211e-05, + "loss": 3.8691, + "step": 2125824 + }, + { + "epoch": 1.02, + "learning_rate": 1.518539495519742e-05, + "loss": 3.8611, + "step": 2126336 + }, + { + "epoch": 1.02, + "learning_rate": 1.5177009007686902e-05, + "loss": 3.8875, + "step": 2126848 + }, + { + "epoch": 1.02, + "learning_rate": 1.5168623060176382e-05, + "loss": 3.8697, + "step": 2127360 + }, + { + "epoch": 1.02, + "learning_rate": 1.5160237112665859e-05, + "loss": 3.8748, + "step": 2127872 + }, + { + "epoch": 1.02, + "learning_rate": 1.515185116515534e-05, + "loss": 3.8633, + "step": 2128384 + }, + { + "epoch": 1.02, + "learning_rate": 1.5143481596448553e-05, + "loss": 3.8752, + "step": 2128896 + }, + { + "epoch": 1.02, + "learning_rate": 1.5135095648938033e-05, + "loss": 3.8735, + "step": 2129408 + }, + { + "epoch": 1.02, + "learning_rate": 1.5126709701427511e-05, + "loss": 3.8757, + "step": 2129920 + }, + { + "epoch": 1.02, + "learning_rate": 1.5118323753916991e-05, + "loss": 3.8693, + "step": 2130432 + }, + { + "epoch": 1.02, + "learning_rate": 1.5109954185210203e-05, + "loss": 3.8683, + "step": 2130944 + }, + { + "epoch": 1.02, + "learning_rate": 1.5101568237699685e-05, + "loss": 3.871, + "step": 2131456 + }, + { + "epoch": 1.02, + "learning_rate": 1.5093182290189162e-05, + "loss": 3.8917, + "step": 2131968 + }, + { + "epoch": 1.02, + "learning_rate": 1.5084796342678642e-05, + "loss": 3.8625, + "step": 2132480 + }, + { + "epoch": 1.02, + "learning_rate": 1.5076410395168122e-05, + "loss": 3.8818, + "step": 2132992 + }, + { + "epoch": 1.02, + "learning_rate": 1.5068040826461332e-05, + "loss": 3.8776, + "step": 2133504 + }, + { + "epoch": 1.02, + "learning_rate": 1.5059654878950812e-05, + "loss": 3.869, + "step": 2134016 + }, + { + "epoch": 1.02, + "learning_rate": 1.5051268931440294e-05, + "loss": 3.8723, + "step": 2134528 + }, + { + "epoch": 1.02, + "learning_rate": 1.5042882983929774e-05, + "loss": 3.8697, + "step": 2135040 + }, + { + "epoch": 1.02, + "learning_rate": 1.5034497036419254e-05, + "loss": 3.871, + "step": 2135552 + }, + { + "epoch": 1.02, + "learning_rate": 1.5026127467712465e-05, + "loss": 3.8712, + "step": 2136064 + }, + { + "epoch": 1.02, + "learning_rate": 1.5017741520201945e-05, + "loss": 3.8702, + "step": 2136576 + }, + { + "epoch": 1.03, + "eval_loss": 3.9874329566955566, + "eval_runtime": 283.4404, + "eval_samples_per_second": 1346.283, + "eval_steps_per_second": 42.072, + "step": 2136960 + }, + { + "epoch": 0.0, + "learning_rate": 1.5009355572691425e-05, + "loss": 3.8811, + "step": 2137088 + }, + { + "epoch": 0.0, + "learning_rate": 1.5000969625180904e-05, + "loss": 3.8574, + "step": 2137600 + }, + { + "epoch": 0.0, + "learning_rate": 1.4992583677670386e-05, + "loss": 3.8677, + "step": 2138112 + }, + { + "epoch": 0.0, + "learning_rate": 1.4984197730159866e-05, + "loss": 3.8838, + "step": 2138624 + }, + { + "epoch": 0.0, + "learning_rate": 1.4975811782649343e-05, + "loss": 3.8761, + "step": 2139136 + }, + { + "epoch": 0.0, + "learning_rate": 1.4967425835138824e-05, + "loss": 3.8697, + "step": 2139648 + }, + { + "epoch": 0.0, + "learning_rate": 1.4959039887628304e-05, + "loss": 3.8836, + "step": 2140160 + }, + { + "epoch": 0.0, + "learning_rate": 1.4950653940117784e-05, + "loss": 3.8638, + "step": 2140672 + }, + { + "epoch": 0.0, + "learning_rate": 1.4942267992607264e-05, + "loss": 3.8625, + "step": 2141184 + }, + { + "epoch": 0.0, + "learning_rate": 1.4933882045096744e-05, + "loss": 3.8781, + "step": 2141696 + }, + { + "epoch": 0.0, + "learning_rate": 1.4925496097586222e-05, + "loss": 3.877, + "step": 2142208 + }, + { + "epoch": 0.0, + "learning_rate": 1.4917110150075702e-05, + "loss": 3.8753, + "step": 2142720 + }, + { + "epoch": 0.0, + "learning_rate": 1.4908740581368917e-05, + "loss": 3.8816, + "step": 2143232 + }, + { + "epoch": 0.0, + "learning_rate": 1.4900354633858396e-05, + "loss": 3.861, + "step": 2143744 + }, + { + "epoch": 0.0, + "learning_rate": 1.4891968686347873e-05, + "loss": 3.8628, + "step": 2144256 + }, + { + "epoch": 0.0, + "learning_rate": 1.4883582738837355e-05, + "loss": 3.8552, + "step": 2144768 + }, + { + "epoch": 0.0, + "learning_rate": 1.4875196791326835e-05, + "loss": 3.8712, + "step": 2145280 + }, + { + "epoch": 0.0, + "learning_rate": 1.4866810843816315e-05, + "loss": 3.8703, + "step": 2145792 + }, + { + "epoch": 0.0, + "learning_rate": 1.4858424896305795e-05, + "loss": 3.8609, + "step": 2146304 + }, + { + "epoch": 0.0, + "learning_rate": 1.4850038948795275e-05, + "loss": 3.8679, + "step": 2146816 + }, + { + "epoch": 0.0, + "learning_rate": 1.4841653001284756e-05, + "loss": 3.8909, + "step": 2147328 + }, + { + "epoch": 0.0, + "learning_rate": 1.4833267053774233e-05, + "loss": 3.8719, + "step": 2147840 + }, + { + "epoch": 0.0, + "learning_rate": 1.4824881106263713e-05, + "loss": 3.8779, + "step": 2148352 + }, + { + "epoch": 0.0, + "learning_rate": 1.4816495158753194e-05, + "loss": 3.8715, + "step": 2148864 + }, + { + "epoch": 0.0, + "learning_rate": 1.4808109211242674e-05, + "loss": 3.8754, + "step": 2149376 + }, + { + "epoch": 0.0, + "learning_rate": 1.4799739642535883e-05, + "loss": 3.8701, + "step": 2149888 + }, + { + "epoch": 0.0, + "learning_rate": 1.4791353695025365e-05, + "loss": 3.8664, + "step": 2150400 + }, + { + "epoch": 0.0, + "learning_rate": 1.4782967747514845e-05, + "loss": 3.8608, + "step": 2150912 + }, + { + "epoch": 0.0, + "learning_rate": 1.4774598178808056e-05, + "loss": 3.8722, + "step": 2151424 + }, + { + "epoch": 0.0, + "learning_rate": 1.4766212231297536e-05, + "loss": 3.8603, + "step": 2151936 + }, + { + "epoch": 0.01, + "learning_rate": 1.4757826283787016e-05, + "loss": 3.8721, + "step": 2152448 + }, + { + "epoch": 0.01, + "learning_rate": 1.4749440336276496e-05, + "loss": 3.869, + "step": 2152960 + }, + { + "epoch": 0.01, + "learning_rate": 1.4741054388765976e-05, + "loss": 3.8764, + "step": 2153472 + }, + { + "epoch": 0.01, + "learning_rate": 1.4732668441255457e-05, + "loss": 3.8762, + "step": 2153984 + }, + { + "epoch": 0.01, + "learning_rate": 1.4724282493744934e-05, + "loss": 3.8674, + "step": 2154496 + }, + { + "epoch": 0.01, + "learning_rate": 1.4715912925038148e-05, + "loss": 3.8742, + "step": 2155008 + }, + { + "epoch": 0.01, + "learning_rate": 1.4707526977527628e-05, + "loss": 3.8784, + "step": 2155520 + }, + { + "epoch": 0.01, + "learning_rate": 1.4699141030017108e-05, + "loss": 3.8528, + "step": 2156032 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690755082506586e-05, + "loss": 3.8696, + "step": 2156544 + }, + { + "epoch": 0.01, + "learning_rate": 1.4682369134996066e-05, + "loss": 3.8617, + "step": 2157056 + }, + { + "epoch": 0.01, + "learning_rate": 1.4673983187485546e-05, + "loss": 3.8646, + "step": 2157568 + }, + { + "epoch": 0.01, + "learning_rate": 1.4665613618778759e-05, + "loss": 3.8756, + "step": 2158080 + }, + { + "epoch": 0.01, + "learning_rate": 1.4657227671268237e-05, + "loss": 3.8669, + "step": 2158592 + }, + { + "epoch": 0.01, + "learning_rate": 1.4648841723757717e-05, + "loss": 3.8709, + "step": 2159104 + }, + { + "epoch": 0.01, + "learning_rate": 1.4640455776247197e-05, + "loss": 3.873, + "step": 2159616 + }, + { + "epoch": 0.01, + "learning_rate": 1.4632069828736677e-05, + "loss": 3.8755, + "step": 2160128 + }, + { + "epoch": 0.01, + "learning_rate": 1.4623683881226158e-05, + "loss": 3.877, + "step": 2160640 + }, + { + "epoch": 0.01, + "learning_rate": 1.4615297933715638e-05, + "loss": 3.8701, + "step": 2161152 + }, + { + "epoch": 0.01, + "learning_rate": 1.4606911986205115e-05, + "loss": 3.843, + "step": 2161664 + }, + { + "epoch": 0.01, + "learning_rate": 1.4598542417498329e-05, + "loss": 3.8762, + "step": 2162176 + }, + { + "epoch": 0.01, + "learning_rate": 1.4590156469987809e-05, + "loss": 3.8706, + "step": 2162688 + }, + { + "epoch": 0.01, + "learning_rate": 1.458178690128102e-05, + "loss": 3.8761, + "step": 2163200 + }, + { + "epoch": 0.01, + "learning_rate": 1.45734009537705e-05, + "loss": 3.8711, + "step": 2163712 + }, + { + "epoch": 0.01, + "learning_rate": 1.456501500625998e-05, + "loss": 3.861, + "step": 2164224 + }, + { + "epoch": 0.01, + "learning_rate": 1.455662905874946e-05, + "loss": 3.8561, + "step": 2164736 + }, + { + "epoch": 0.01, + "learning_rate": 1.454825949004267e-05, + "loss": 3.8569, + "step": 2165248 + }, + { + "epoch": 0.01, + "learning_rate": 1.453987354253215e-05, + "loss": 3.8657, + "step": 2165760 + }, + { + "epoch": 0.01, + "learning_rate": 1.453148759502163e-05, + "loss": 3.8485, + "step": 2166272 + }, + { + "epoch": 0.01, + "learning_rate": 1.4523101647511112e-05, + "loss": 3.8848, + "step": 2166784 + }, + { + "epoch": 0.01, + "learning_rate": 1.4514715700000589e-05, + "loss": 3.869, + "step": 2167296 + }, + { + "epoch": 0.01, + "learning_rate": 1.4506329752490069e-05, + "loss": 3.8507, + "step": 2167808 + }, + { + "epoch": 0.01, + "learning_rate": 1.449794380497955e-05, + "loss": 3.8728, + "step": 2168320 + }, + { + "epoch": 0.01, + "learning_rate": 1.4489574236272763e-05, + "loss": 3.8556, + "step": 2168832 + }, + { + "epoch": 0.01, + "learning_rate": 1.4481188288762241e-05, + "loss": 3.8551, + "step": 2169344 + }, + { + "epoch": 0.01, + "learning_rate": 1.4472802341251721e-05, + "loss": 3.8675, + "step": 2169856 + }, + { + "epoch": 0.01, + "learning_rate": 1.4464416393741201e-05, + "loss": 3.8692, + "step": 2170368 + }, + { + "epoch": 0.01, + "learning_rate": 1.4456046825034413e-05, + "loss": 3.854, + "step": 2170880 + }, + { + "epoch": 0.01, + "learning_rate": 1.4447660877523892e-05, + "loss": 3.8702, + "step": 2171392 + }, + { + "epoch": 0.01, + "learning_rate": 1.4439274930013372e-05, + "loss": 3.8554, + "step": 2171904 + }, + { + "epoch": 0.01, + "learning_rate": 1.4430888982502852e-05, + "loss": 3.865, + "step": 2172416 + }, + { + "epoch": 0.01, + "learning_rate": 1.4422503034992333e-05, + "loss": 3.8714, + "step": 2172928 + }, + { + "epoch": 0.01, + "learning_rate": 1.4414117087481813e-05, + "loss": 3.8653, + "step": 2173440 + }, + { + "epoch": 0.01, + "learning_rate": 1.4405747518775022e-05, + "loss": 3.8679, + "step": 2173952 + }, + { + "epoch": 0.01, + "learning_rate": 1.4397361571264504e-05, + "loss": 3.8638, + "step": 2174464 + }, + { + "epoch": 0.01, + "learning_rate": 1.4388975623753984e-05, + "loss": 3.8883, + "step": 2174976 + }, + { + "epoch": 0.01, + "learning_rate": 1.4380606055047195e-05, + "loss": 3.8527, + "step": 2175488 + }, + { + "epoch": 0.01, + "learning_rate": 1.4372220107536675e-05, + "loss": 3.8741, + "step": 2176000 + }, + { + "epoch": 0.01, + "learning_rate": 1.4363834160026155e-05, + "loss": 3.8617, + "step": 2176512 + }, + { + "epoch": 0.01, + "learning_rate": 1.4355448212515634e-05, + "loss": 3.8629, + "step": 2177024 + }, + { + "epoch": 0.01, + "learning_rate": 1.4347062265005114e-05, + "loss": 3.8653, + "step": 2177536 + }, + { + "epoch": 0.01, + "learning_rate": 1.4338676317494596e-05, + "loss": 3.8667, + "step": 2178048 + }, + { + "epoch": 0.01, + "learning_rate": 1.4330290369984073e-05, + "loss": 3.8808, + "step": 2178560 + }, + { + "epoch": 0.01, + "learning_rate": 1.4321904422473553e-05, + "loss": 3.8762, + "step": 2179072 + }, + { + "epoch": 0.01, + "learning_rate": 1.4313518474963034e-05, + "loss": 3.8501, + "step": 2179584 + }, + { + "epoch": 0.01, + "learning_rate": 1.4305132527452514e-05, + "loss": 3.8517, + "step": 2180096 + }, + { + "epoch": 0.01, + "learning_rate": 1.4296746579941994e-05, + "loss": 3.8596, + "step": 2180608 + }, + { + "epoch": 0.01, + "learning_rate": 1.4288360632431474e-05, + "loss": 3.8726, + "step": 2181120 + }, + { + "epoch": 0.01, + "learning_rate": 1.4279991063724685e-05, + "loss": 3.8601, + "step": 2181632 + }, + { + "epoch": 0.01, + "learning_rate": 1.4271605116214165e-05, + "loss": 3.8576, + "step": 2182144 + }, + { + "epoch": 0.01, + "learning_rate": 1.4263235547507376e-05, + "loss": 3.8693, + "step": 2182656 + }, + { + "epoch": 0.02, + "learning_rate": 1.4254849599996856e-05, + "loss": 3.8667, + "step": 2183168 + }, + { + "epoch": 0.02, + "learning_rate": 1.4246463652486336e-05, + "loss": 3.869, + "step": 2183680 + }, + { + "epoch": 0.02, + "learning_rate": 1.4238077704975816e-05, + "loss": 3.861, + "step": 2184192 + }, + { + "epoch": 0.02, + "learning_rate": 1.4229691757465297e-05, + "loss": 3.8694, + "step": 2184704 + }, + { + "epoch": 0.02, + "learning_rate": 1.4221322188758506e-05, + "loss": 3.8691, + "step": 2185216 + }, + { + "epoch": 0.02, + "learning_rate": 1.4212936241247988e-05, + "loss": 3.8743, + "step": 2185728 + }, + { + "epoch": 0.02, + "learning_rate": 1.4204550293737468e-05, + "loss": 3.8567, + "step": 2186240 + }, + { + "epoch": 0.02, + "learning_rate": 1.4196164346226948e-05, + "loss": 3.8584, + "step": 2186752 + }, + { + "epoch": 0.02, + "learning_rate": 1.4187778398716426e-05, + "loss": 3.8652, + "step": 2187264 + }, + { + "epoch": 0.02, + "learning_rate": 1.4179408830009639e-05, + "loss": 3.8678, + "step": 2187776 + }, + { + "epoch": 0.02, + "learning_rate": 1.4171022882499119e-05, + "loss": 3.877, + "step": 2188288 + }, + { + "epoch": 0.02, + "learning_rate": 1.4162636934988598e-05, + "loss": 3.8618, + "step": 2188800 + }, + { + "epoch": 0.02, + "learning_rate": 1.415426736628181e-05, + "loss": 3.8643, + "step": 2189312 + }, + { + "epoch": 0.02, + "learning_rate": 1.414588141877129e-05, + "loss": 3.8612, + "step": 2189824 + }, + { + "epoch": 0.02, + "learning_rate": 1.413749547126077e-05, + "loss": 3.8594, + "step": 2190336 + }, + { + "epoch": 0.02, + "learning_rate": 1.4129109523750247e-05, + "loss": 3.8655, + "step": 2190848 + }, + { + "epoch": 0.02, + "learning_rate": 1.4120723576239727e-05, + "loss": 3.8628, + "step": 2191360 + }, + { + "epoch": 0.02, + "learning_rate": 1.4112337628729207e-05, + "loss": 3.8673, + "step": 2191872 + }, + { + "epoch": 0.02, + "learning_rate": 1.4103951681218689e-05, + "loss": 3.8618, + "step": 2192384 + }, + { + "epoch": 0.02, + "learning_rate": 1.4095565733708169e-05, + "loss": 3.8598, + "step": 2192896 + }, + { + "epoch": 0.02, + "learning_rate": 1.4087179786197649e-05, + "loss": 3.8613, + "step": 2193408 + }, + { + "epoch": 0.02, + "learning_rate": 1.4078793838687129e-05, + "loss": 3.8484, + "step": 2193920 + }, + { + "epoch": 0.02, + "learning_rate": 1.407042426998034e-05, + "loss": 3.8696, + "step": 2194432 + }, + { + "epoch": 0.02, + "learning_rate": 1.406203832246982e-05, + "loss": 3.8693, + "step": 2194944 + }, + { + "epoch": 0.02, + "learning_rate": 1.40536523749593e-05, + "loss": 3.8708, + "step": 2195456 + }, + { + "epoch": 0.02, + "learning_rate": 1.4045266427448781e-05, + "loss": 3.8704, + "step": 2195968 + }, + { + "epoch": 0.02, + "learning_rate": 1.4036880479938258e-05, + "loss": 3.8715, + "step": 2196480 + }, + { + "epoch": 0.02, + "learning_rate": 1.402851091123147e-05, + "loss": 3.8666, + "step": 2196992 + }, + { + "epoch": 0.02, + "learning_rate": 1.4020124963720952e-05, + "loss": 3.8591, + "step": 2197504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4011739016210429e-05, + "loss": 3.8707, + "step": 2198016 + }, + { + "epoch": 0.02, + "learning_rate": 1.4003353068699908e-05, + "loss": 3.8637, + "step": 2198528 + }, + { + "epoch": 0.02, + "learning_rate": 1.399496712118939e-05, + "loss": 3.8632, + "step": 2199040 + }, + { + "epoch": 0.02, + "learning_rate": 1.3986597552482603e-05, + "loss": 3.8713, + "step": 2199552 + }, + { + "epoch": 0.02, + "learning_rate": 1.3978211604972081e-05, + "loss": 3.8591, + "step": 2200064 + }, + { + "epoch": 0.02, + "learning_rate": 1.396982565746156e-05, + "loss": 3.8672, + "step": 2200576 + }, + { + "epoch": 0.02, + "learning_rate": 1.396143970995104e-05, + "loss": 3.8599, + "step": 2201088 + }, + { + "epoch": 0.02, + "learning_rate": 1.395305376244052e-05, + "loss": 3.8606, + "step": 2201600 + }, + { + "epoch": 0.02, + "learning_rate": 1.394466781493e-05, + "loss": 3.8655, + "step": 2202112 + }, + { + "epoch": 0.02, + "learning_rate": 1.3936281867419482e-05, + "loss": 3.8582, + "step": 2202624 + }, + { + "epoch": 0.02, + "learning_rate": 1.3927912298712691e-05, + "loss": 3.8797, + "step": 2203136 + }, + { + "epoch": 0.02, + "learning_rate": 1.3919526351202173e-05, + "loss": 3.8683, + "step": 2203648 + }, + { + "epoch": 0.02, + "learning_rate": 1.3911140403691653e-05, + "loss": 3.8707, + "step": 2204160 + }, + { + "epoch": 0.02, + "learning_rate": 1.3902754456181133e-05, + "loss": 3.8597, + "step": 2204672 + }, + { + "epoch": 0.02, + "learning_rate": 1.3894384887474344e-05, + "loss": 3.8668, + "step": 2205184 + }, + { + "epoch": 0.02, + "learning_rate": 1.3885998939963824e-05, + "loss": 3.8735, + "step": 2205696 + }, + { + "epoch": 0.02, + "learning_rate": 1.3877612992453304e-05, + "loss": 3.8729, + "step": 2206208 + }, + { + "epoch": 0.02, + "learning_rate": 1.3869227044942784e-05, + "loss": 3.8674, + "step": 2206720 + }, + { + "epoch": 0.02, + "learning_rate": 1.3860857476235994e-05, + "loss": 3.8615, + "step": 2207232 + }, + { + "epoch": 0.02, + "learning_rate": 1.3852471528725474e-05, + "loss": 3.8679, + "step": 2207744 + }, + { + "epoch": 0.02, + "learning_rate": 1.3844085581214954e-05, + "loss": 3.8849, + "step": 2208256 + }, + { + "epoch": 0.02, + "learning_rate": 1.3835699633704436e-05, + "loss": 3.8618, + "step": 2208768 + }, + { + "epoch": 0.02, + "learning_rate": 1.3827313686193913e-05, + "loss": 3.8733, + "step": 2209280 + }, + { + "epoch": 0.02, + "learning_rate": 1.3818927738683393e-05, + "loss": 3.8733, + "step": 2209792 + }, + { + "epoch": 0.02, + "learning_rate": 1.3810541791172874e-05, + "loss": 3.8685, + "step": 2210304 + }, + { + "epoch": 0.02, + "learning_rate": 1.3802155843662354e-05, + "loss": 3.87, + "step": 2210816 + }, + { + "epoch": 0.02, + "learning_rate": 1.3793786274955565e-05, + "loss": 3.8657, + "step": 2211328 + }, + { + "epoch": 0.02, + "learning_rate": 1.3785400327445045e-05, + "loss": 3.865, + "step": 2211840 + }, + { + "epoch": 0.02, + "learning_rate": 1.3777030758738257e-05, + "loss": 3.8699, + "step": 2212352 + }, + { + "epoch": 0.02, + "learning_rate": 1.3768644811227736e-05, + "loss": 3.8634, + "step": 2212864 + }, + { + "epoch": 0.03, + "eval_loss": 3.985875368118286, + "eval_runtime": 287.3174, + "eval_samples_per_second": 1328.116, + "eval_steps_per_second": 41.505, + "step": 2213280 + }, + { + "epoch": 1.0, + "learning_rate": 1.3760258863717216e-05, + "loss": 3.8661, + "step": 2213376 + }, + { + "epoch": 1.0, + "learning_rate": 1.3751872916206696e-05, + "loss": 3.8518, + "step": 2213888 + }, + { + "epoch": 1.0, + "learning_rate": 1.3743503347499908e-05, + "loss": 3.8646, + "step": 2214400 + }, + { + "epoch": 1.0, + "learning_rate": 1.3735117399989386e-05, + "loss": 3.8825, + "step": 2214912 + }, + { + "epoch": 1.0, + "learning_rate": 1.3726731452478866e-05, + "loss": 3.8718, + "step": 2215424 + }, + { + "epoch": 1.0, + "learning_rate": 1.3718345504968346e-05, + "loss": 3.8665, + "step": 2215936 + }, + { + "epoch": 1.0, + "learning_rate": 1.3709959557457828e-05, + "loss": 3.8732, + "step": 2216448 + }, + { + "epoch": 1.0, + "learning_rate": 1.3701573609947308e-05, + "loss": 3.8661, + "step": 2216960 + }, + { + "epoch": 1.0, + "learning_rate": 1.3693187662436788e-05, + "loss": 3.8579, + "step": 2217472 + }, + { + "epoch": 1.0, + "learning_rate": 1.3684801714926266e-05, + "loss": 3.8779, + "step": 2217984 + }, + { + "epoch": 1.0, + "learning_rate": 1.3676432146219478e-05, + "loss": 3.8676, + "step": 2218496 + }, + { + "epoch": 1.0, + "learning_rate": 1.3668046198708958e-05, + "loss": 3.8735, + "step": 2219008 + }, + { + "epoch": 1.0, + "learning_rate": 1.3659693008805902e-05, + "loss": 3.8768, + "step": 2219520 + }, + { + "epoch": 1.0, + "learning_rate": 1.3651307061295382e-05, + "loss": 3.8556, + "step": 2220032 + }, + { + "epoch": 1.0, + "learning_rate": 1.364292111378486e-05, + "loss": 3.8593, + "step": 2220544 + }, + { + "epoch": 1.0, + "learning_rate": 1.363453516627434e-05, + "loss": 3.8481, + "step": 2221056 + }, + { + "epoch": 1.0, + "learning_rate": 1.362614921876382e-05, + "loss": 3.8667, + "step": 2221568 + }, + { + "epoch": 1.0, + "learning_rate": 1.36177632712533e-05, + "loss": 3.8678, + "step": 2222080 + }, + { + "epoch": 1.0, + "learning_rate": 1.3609377323742782e-05, + "loss": 3.8585, + "step": 2222592 + }, + { + "epoch": 1.0, + "learning_rate": 1.3600991376232261e-05, + "loss": 3.8629, + "step": 2223104 + }, + { + "epoch": 1.0, + "learning_rate": 1.3592605428721738e-05, + "loss": 3.8862, + "step": 2223616 + }, + { + "epoch": 1.0, + "learning_rate": 1.358421948121122e-05, + "loss": 3.8673, + "step": 2224128 + }, + { + "epoch": 1.0, + "learning_rate": 1.3575849912504432e-05, + "loss": 3.8711, + "step": 2224640 + }, + { + "epoch": 1.0, + "learning_rate": 1.3567463964993912e-05, + "loss": 3.8709, + "step": 2225152 + }, + { + "epoch": 1.0, + "learning_rate": 1.355907801748339e-05, + "loss": 3.8754, + "step": 2225664 + }, + { + "epoch": 1.0, + "learning_rate": 1.355069206997287e-05, + "loss": 3.8647, + "step": 2226176 + }, + { + "epoch": 1.0, + "learning_rate": 1.354230612246235e-05, + "loss": 3.8624, + "step": 2226688 + }, + { + "epoch": 1.0, + "learning_rate": 1.353392017495183e-05, + "loss": 3.8623, + "step": 2227200 + }, + { + "epoch": 1.0, + "learning_rate": 1.3525534227441312e-05, + "loss": 3.8628, + "step": 2227712 + }, + { + "epoch": 1.0, + "learning_rate": 1.3517148279930792e-05, + "loss": 3.8589, + "step": 2228224 + }, + { + "epoch": 1.01, + "learning_rate": 1.3508778711224001e-05, + "loss": 3.8687, + "step": 2228736 + }, + { + "epoch": 1.01, + "learning_rate": 1.3500392763713483e-05, + "loss": 3.8623, + "step": 2229248 + }, + { + "epoch": 1.01, + "learning_rate": 1.3492006816202963e-05, + "loss": 3.8777, + "step": 2229760 + }, + { + "epoch": 1.01, + "learning_rate": 1.3483620868692443e-05, + "loss": 3.8683, + "step": 2230272 + }, + { + "epoch": 1.01, + "learning_rate": 1.347523492118192e-05, + "loss": 3.8657, + "step": 2230784 + }, + { + "epoch": 1.01, + "learning_rate": 1.3466881731278862e-05, + "loss": 3.8741, + "step": 2231296 + }, + { + "epoch": 1.01, + "learning_rate": 1.3458495783768344e-05, + "loss": 3.8709, + "step": 2231808 + }, + { + "epoch": 1.01, + "learning_rate": 1.3450109836257824e-05, + "loss": 3.8468, + "step": 2232320 + }, + { + "epoch": 1.01, + "learning_rate": 1.3441723888747304e-05, + "loss": 3.867, + "step": 2232832 + }, + { + "epoch": 1.01, + "learning_rate": 1.3433354320040515e-05, + "loss": 3.8581, + "step": 2233344 + }, + { + "epoch": 1.01, + "learning_rate": 1.3424968372529995e-05, + "loss": 3.8605, + "step": 2233856 + }, + { + "epoch": 1.01, + "learning_rate": 1.3416582425019475e-05, + "loss": 3.8698, + "step": 2234368 + }, + { + "epoch": 1.01, + "learning_rate": 1.3408212856312685e-05, + "loss": 3.8674, + "step": 2234880 + }, + { + "epoch": 1.01, + "learning_rate": 1.3399826908802165e-05, + "loss": 3.8637, + "step": 2235392 + }, + { + "epoch": 1.01, + "learning_rate": 1.3391440961291645e-05, + "loss": 3.8724, + "step": 2235904 + }, + { + "epoch": 1.01, + "learning_rate": 1.3383055013781125e-05, + "loss": 3.8694, + "step": 2236416 + }, + { + "epoch": 1.01, + "learning_rate": 1.3374669066270607e-05, + "loss": 3.869, + "step": 2236928 + }, + { + "epoch": 1.01, + "learning_rate": 1.3366283118760087e-05, + "loss": 3.8691, + "step": 2237440 + }, + { + "epoch": 1.01, + "learning_rate": 1.3357897171249567e-05, + "loss": 3.8426, + "step": 2237952 + }, + { + "epoch": 1.01, + "learning_rate": 1.3349511223739045e-05, + "loss": 3.8674, + "step": 2238464 + }, + { + "epoch": 1.01, + "learning_rate": 1.3341125276228525e-05, + "loss": 3.8717, + "step": 2238976 + }, + { + "epoch": 1.01, + "learning_rate": 1.3332739328718005e-05, + "loss": 3.8706, + "step": 2239488 + }, + { + "epoch": 1.01, + "learning_rate": 1.3324353381207485e-05, + "loss": 3.8666, + "step": 2240000 + }, + { + "epoch": 1.01, + "learning_rate": 1.3315983812500696e-05, + "loss": 3.8591, + "step": 2240512 + }, + { + "epoch": 1.01, + "learning_rate": 1.3307597864990176e-05, + "loss": 3.8535, + "step": 2241024 + }, + { + "epoch": 1.01, + "learning_rate": 1.3299211917479656e-05, + "loss": 3.8492, + "step": 2241536 + }, + { + "epoch": 1.01, + "learning_rate": 1.3290825969969137e-05, + "loss": 3.8646, + "step": 2242048 + }, + { + "epoch": 1.01, + "learning_rate": 1.3282440022458617e-05, + "loss": 3.8477, + "step": 2242560 + }, + { + "epoch": 1.01, + "learning_rate": 1.3274070453751828e-05, + "loss": 3.8751, + "step": 2243072 + }, + { + "epoch": 1.01, + "learning_rate": 1.3265684506241308e-05, + "loss": 3.8664, + "step": 2243584 + }, + { + "epoch": 1.01, + "learning_rate": 1.3257298558730788e-05, + "loss": 3.8492, + "step": 2244096 + }, + { + "epoch": 1.01, + "learning_rate": 1.3248912611220268e-05, + "loss": 3.8675, + "step": 2244608 + }, + { + "epoch": 1.01, + "learning_rate": 1.3240526663709748e-05, + "loss": 3.8507, + "step": 2245120 + }, + { + "epoch": 1.01, + "learning_rate": 1.3232140716199226e-05, + "loss": 3.8553, + "step": 2245632 + }, + { + "epoch": 1.01, + "learning_rate": 1.3223754768688706e-05, + "loss": 3.8585, + "step": 2246144 + }, + { + "epoch": 1.01, + "learning_rate": 1.3215368821178186e-05, + "loss": 3.8692, + "step": 2246656 + }, + { + "epoch": 1.01, + "learning_rate": 1.3206999252471397e-05, + "loss": 3.853, + "step": 2247168 + }, + { + "epoch": 1.01, + "learning_rate": 1.3198613304960877e-05, + "loss": 3.8649, + "step": 2247680 + }, + { + "epoch": 1.01, + "learning_rate": 1.3190227357450358e-05, + "loss": 3.8496, + "step": 2248192 + }, + { + "epoch": 1.01, + "learning_rate": 1.3181857788743571e-05, + "loss": 3.861, + "step": 2248704 + }, + { + "epoch": 1.01, + "learning_rate": 1.3173488220036782e-05, + "loss": 3.8659, + "step": 2249216 + }, + { + "epoch": 1.01, + "learning_rate": 1.3165102272526262e-05, + "loss": 3.8643, + "step": 2249728 + }, + { + "epoch": 1.01, + "learning_rate": 1.3156716325015742e-05, + "loss": 3.8621, + "step": 2250240 + }, + { + "epoch": 1.01, + "learning_rate": 1.3148330377505222e-05, + "loss": 3.8637, + "step": 2250752 + }, + { + "epoch": 1.01, + "learning_rate": 1.31399444299947e-05, + "loss": 3.8817, + "step": 2251264 + }, + { + "epoch": 1.01, + "learning_rate": 1.313155848248418e-05, + "loss": 3.8489, + "step": 2251776 + }, + { + "epoch": 1.01, + "learning_rate": 1.312317253497366e-05, + "loss": 3.8707, + "step": 2252288 + }, + { + "epoch": 1.01, + "learning_rate": 1.311478658746314e-05, + "loss": 3.8584, + "step": 2252800 + }, + { + "epoch": 1.01, + "learning_rate": 1.3106400639952621e-05, + "loss": 3.8578, + "step": 2253312 + }, + { + "epoch": 1.01, + "learning_rate": 1.3098014692442101e-05, + "loss": 3.8582, + "step": 2253824 + }, + { + "epoch": 1.01, + "learning_rate": 1.308964512373531e-05, + "loss": 3.8629, + "step": 2254336 + }, + { + "epoch": 1.01, + "learning_rate": 1.3081259176224792e-05, + "loss": 3.8759, + "step": 2254848 + }, + { + "epoch": 1.01, + "learning_rate": 1.3072873228714272e-05, + "loss": 3.8743, + "step": 2255360 + }, + { + "epoch": 1.01, + "learning_rate": 1.3064487281203752e-05, + "loss": 3.85, + "step": 2255872 + }, + { + "epoch": 1.01, + "learning_rate": 1.3056117712496963e-05, + "loss": 3.8478, + "step": 2256384 + }, + { + "epoch": 1.01, + "learning_rate": 1.3047731764986443e-05, + "loss": 3.8563, + "step": 2256896 + }, + { + "epoch": 1.01, + "learning_rate": 1.3039345817475923e-05, + "loss": 3.8677, + "step": 2257408 + }, + { + "epoch": 1.01, + "learning_rate": 1.3030976248769134e-05, + "loss": 3.8582, + "step": 2257920 + }, + { + "epoch": 1.01, + "learning_rate": 1.3022590301258613e-05, + "loss": 3.8555, + "step": 2258432 + }, + { + "epoch": 1.01, + "learning_rate": 1.3014204353748093e-05, + "loss": 3.8658, + "step": 2258944 + }, + { + "epoch": 1.02, + "learning_rate": 1.3005818406237575e-05, + "loss": 3.8584, + "step": 2259456 + }, + { + "epoch": 1.02, + "learning_rate": 1.2997432458727052e-05, + "loss": 3.8693, + "step": 2259968 + }, + { + "epoch": 1.02, + "learning_rate": 1.2989046511216532e-05, + "loss": 3.8537, + "step": 2260480 + }, + { + "epoch": 1.02, + "learning_rate": 1.2980660563706013e-05, + "loss": 3.8678, + "step": 2260992 + }, + { + "epoch": 1.02, + "learning_rate": 1.2972274616195493e-05, + "loss": 3.8604, + "step": 2261504 + }, + { + "epoch": 1.02, + "learning_rate": 1.2963888668684973e-05, + "loss": 3.8738, + "step": 2262016 + }, + { + "epoch": 1.02, + "learning_rate": 1.2955502721174453e-05, + "loss": 3.8522, + "step": 2262528 + }, + { + "epoch": 1.02, + "learning_rate": 1.2947116773663933e-05, + "loss": 3.8532, + "step": 2263040 + }, + { + "epoch": 1.02, + "learning_rate": 1.2938730826153411e-05, + "loss": 3.8649, + "step": 2263552 + }, + { + "epoch": 1.02, + "learning_rate": 1.2930361257446624e-05, + "loss": 3.8626, + "step": 2264064 + }, + { + "epoch": 1.02, + "learning_rate": 1.2921975309936104e-05, + "loss": 3.8718, + "step": 2264576 + }, + { + "epoch": 1.02, + "learning_rate": 1.2913589362425582e-05, + "loss": 3.8602, + "step": 2265088 + }, + { + "epoch": 1.02, + "learning_rate": 1.2905203414915062e-05, + "loss": 3.8602, + "step": 2265600 + }, + { + "epoch": 1.02, + "learning_rate": 1.2896833846208276e-05, + "loss": 3.857, + "step": 2266112 + }, + { + "epoch": 1.02, + "learning_rate": 1.2888447898697756e-05, + "loss": 3.8593, + "step": 2266624 + }, + { + "epoch": 1.02, + "learning_rate": 1.2880061951187233e-05, + "loss": 3.8577, + "step": 2267136 + }, + { + "epoch": 1.02, + "learning_rate": 1.2871692382480447e-05, + "loss": 3.8559, + "step": 2267648 + }, + { + "epoch": 1.02, + "learning_rate": 1.2863306434969927e-05, + "loss": 3.8622, + "step": 2268160 + }, + { + "epoch": 1.02, + "learning_rate": 1.2854920487459407e-05, + "loss": 3.8555, + "step": 2268672 + }, + { + "epoch": 1.02, + "learning_rate": 1.2846550918752618e-05, + "loss": 3.8568, + "step": 2269184 + }, + { + "epoch": 1.02, + "learning_rate": 1.2838164971242098e-05, + "loss": 3.8569, + "step": 2269696 + }, + { + "epoch": 1.02, + "learning_rate": 1.2829779023731577e-05, + "loss": 3.8455, + "step": 2270208 + }, + { + "epoch": 1.02, + "learning_rate": 1.2821393076221056e-05, + "loss": 3.8693, + "step": 2270720 + }, + { + "epoch": 1.02, + "learning_rate": 1.2813007128710536e-05, + "loss": 3.8612, + "step": 2271232 + }, + { + "epoch": 1.02, + "learning_rate": 1.2804621181200016e-05, + "loss": 3.8648, + "step": 2271744 + }, + { + "epoch": 1.02, + "learning_rate": 1.2796235233689496e-05, + "loss": 3.8685, + "step": 2272256 + }, + { + "epoch": 1.02, + "learning_rate": 1.2787849286178977e-05, + "loss": 3.8686, + "step": 2272768 + }, + { + "epoch": 1.02, + "learning_rate": 1.2779463338668457e-05, + "loss": 3.8589, + "step": 2273280 + }, + { + "epoch": 1.02, + "learning_rate": 1.2771093769961668e-05, + "loss": 3.8573, + "step": 2273792 + }, + { + "epoch": 1.02, + "learning_rate": 1.2762707822451148e-05, + "loss": 3.8655, + "step": 2274304 + }, + { + "epoch": 1.02, + "learning_rate": 1.2754321874940628e-05, + "loss": 3.8599, + "step": 2274816 + }, + { + "epoch": 1.02, + "learning_rate": 1.2745935927430108e-05, + "loss": 3.8559, + "step": 2275328 + }, + { + "epoch": 1.02, + "learning_rate": 1.2737549979919588e-05, + "loss": 3.8678, + "step": 2275840 + }, + { + "epoch": 1.02, + "learning_rate": 1.2729164032409066e-05, + "loss": 3.8589, + "step": 2276352 + }, + { + "epoch": 1.02, + "learning_rate": 1.2720794463702279e-05, + "loss": 3.8619, + "step": 2276864 + }, + { + "epoch": 1.02, + "learning_rate": 1.271240851619176e-05, + "loss": 3.855, + "step": 2277376 + }, + { + "epoch": 1.02, + "learning_rate": 1.2704022568681237e-05, + "loss": 3.8535, + "step": 2277888 + }, + { + "epoch": 1.02, + "learning_rate": 1.269565299997445e-05, + "loss": 3.8627, + "step": 2278400 + }, + { + "epoch": 1.02, + "learning_rate": 1.2687267052463931e-05, + "loss": 3.8551, + "step": 2278912 + }, + { + "epoch": 1.02, + "learning_rate": 1.2678881104953411e-05, + "loss": 3.8691, + "step": 2279424 + }, + { + "epoch": 1.02, + "learning_rate": 1.2670495157442887e-05, + "loss": 3.8724, + "step": 2279936 + }, + { + "epoch": 1.02, + "learning_rate": 1.2662109209932369e-05, + "loss": 3.8639, + "step": 2280448 + }, + { + "epoch": 1.02, + "learning_rate": 1.2653723262421849e-05, + "loss": 3.8567, + "step": 2280960 + }, + { + "epoch": 1.02, + "learning_rate": 1.2645337314911329e-05, + "loss": 3.8691, + "step": 2281472 + }, + { + "epoch": 1.02, + "learning_rate": 1.2636951367400809e-05, + "loss": 3.8658, + "step": 2281984 + }, + { + "epoch": 1.02, + "learning_rate": 1.2628565419890289e-05, + "loss": 3.8664, + "step": 2282496 + }, + { + "epoch": 1.02, + "learning_rate": 1.26201958511835e-05, + "loss": 3.8587, + "step": 2283008 + }, + { + "epoch": 1.02, + "learning_rate": 1.261180990367298e-05, + "loss": 3.8593, + "step": 2283520 + }, + { + "epoch": 1.02, + "learning_rate": 1.2603423956162461e-05, + "loss": 3.8694, + "step": 2284032 + }, + { + "epoch": 1.02, + "learning_rate": 1.2595038008651941e-05, + "loss": 3.88, + "step": 2284544 + }, + { + "epoch": 1.02, + "learning_rate": 1.2586652061141418e-05, + "loss": 3.8546, + "step": 2285056 + }, + { + "epoch": 1.02, + "learning_rate": 1.2578282492434632e-05, + "loss": 3.871, + "step": 2285568 + }, + { + "epoch": 1.02, + "learning_rate": 1.2569896544924112e-05, + "loss": 3.8718, + "step": 2286080 + }, + { + "epoch": 1.02, + "learning_rate": 1.2561510597413592e-05, + "loss": 3.8633, + "step": 2286592 + }, + { + "epoch": 1.02, + "learning_rate": 1.255312464990307e-05, + "loss": 3.8667, + "step": 2287104 + }, + { + "epoch": 1.02, + "learning_rate": 1.254473870239255e-05, + "loss": 3.8606, + "step": 2287616 + }, + { + "epoch": 1.02, + "learning_rate": 1.253635275488203e-05, + "loss": 3.8616, + "step": 2288128 + }, + { + "epoch": 1.02, + "learning_rate": 1.252796680737151e-05, + "loss": 3.8707, + "step": 2288640 + }, + { + "epoch": 1.02, + "learning_rate": 1.2519580859860992e-05, + "loss": 3.852, + "step": 2289152 + }, + { + "epoch": 1.03, + "eval_loss": 3.98465633392334, + "eval_runtime": 286.9234, + "eval_samples_per_second": 1329.94, + "eval_steps_per_second": 41.562, + "step": 2289600 + }, + { + "epoch": 0.0, + "learning_rate": 1.25112112911542e-05, + "loss": 3.8721, + "step": 2289664 + }, + { + "epoch": 0.0, + "learning_rate": 1.250282534364368e-05, + "loss": 3.8506, + "step": 2290176 + }, + { + "epoch": 0.0, + "learning_rate": 1.2494439396133162e-05, + "loss": 3.8594, + "step": 2290688 + }, + { + "epoch": 0.0, + "learning_rate": 1.2486053448622642e-05, + "loss": 3.8736, + "step": 2291200 + }, + { + "epoch": 0.0, + "learning_rate": 1.247766750111212e-05, + "loss": 3.8724, + "step": 2291712 + }, + { + "epoch": 0.0, + "learning_rate": 1.24692815536016e-05, + "loss": 3.8613, + "step": 2292224 + }, + { + "epoch": 0.0, + "learning_rate": 1.2460895606091082e-05, + "loss": 3.868, + "step": 2292736 + }, + { + "epoch": 0.0, + "learning_rate": 1.245250965858056e-05, + "loss": 3.8588, + "step": 2293248 + }, + { + "epoch": 0.0, + "learning_rate": 1.244412371107004e-05, + "loss": 3.8543, + "step": 2293760 + }, + { + "epoch": 0.0, + "learning_rate": 1.243573776355952e-05, + "loss": 3.8732, + "step": 2294272 + }, + { + "epoch": 0.0, + "learning_rate": 1.2427351816049e-05, + "loss": 3.8663, + "step": 2294784 + }, + { + "epoch": 0.0, + "learning_rate": 1.241896586853848e-05, + "loss": 3.8706, + "step": 2295296 + }, + { + "epoch": 0.0, + "learning_rate": 1.2410596299831693e-05, + "loss": 3.8751, + "step": 2295808 + }, + { + "epoch": 0.0, + "learning_rate": 1.2402210352321173e-05, + "loss": 3.8526, + "step": 2296320 + }, + { + "epoch": 0.0, + "learning_rate": 1.2393824404810651e-05, + "loss": 3.8542, + "step": 2296832 + }, + { + "epoch": 0.0, + "learning_rate": 1.2385438457300131e-05, + "loss": 3.845, + "step": 2297344 + }, + { + "epoch": 0.0, + "learning_rate": 1.2377052509789613e-05, + "loss": 3.8651, + "step": 2297856 + }, + { + "epoch": 0.0, + "learning_rate": 1.2368666562279091e-05, + "loss": 3.8585, + "step": 2298368 + }, + { + "epoch": 0.0, + "learning_rate": 1.236028061476857e-05, + "loss": 3.8583, + "step": 2298880 + }, + { + "epoch": 0.0, + "learning_rate": 1.235189466725805e-05, + "loss": 3.8601, + "step": 2299392 + }, + { + "epoch": 0.0, + "learning_rate": 1.2343525098551263e-05, + "loss": 3.8776, + "step": 2299904 + }, + { + "epoch": 0.0, + "learning_rate": 1.2335139151040742e-05, + "loss": 3.8702, + "step": 2300416 + }, + { + "epoch": 0.0, + "learning_rate": 1.2326753203530223e-05, + "loss": 3.8628, + "step": 2300928 + }, + { + "epoch": 0.0, + "learning_rate": 1.2318367256019703e-05, + "loss": 3.8678, + "step": 2301440 + }, + { + "epoch": 0.0, + "learning_rate": 1.2309981308509181e-05, + "loss": 3.8693, + "step": 2301952 + }, + { + "epoch": 0.0, + "learning_rate": 1.2301595360998661e-05, + "loss": 3.864, + "step": 2302464 + }, + { + "epoch": 0.0, + "learning_rate": 1.2293225792291874e-05, + "loss": 3.8556, + "step": 2302976 + }, + { + "epoch": 0.0, + "learning_rate": 1.2284839844781354e-05, + "loss": 3.8611, + "step": 2303488 + }, + { + "epoch": 0.0, + "learning_rate": 1.2276453897270832e-05, + "loss": 3.8559, + "step": 2304000 + }, + { + "epoch": 0.0, + "learning_rate": 1.2268067949760314e-05, + "loss": 3.8585, + "step": 2304512 + }, + { + "epoch": 0.01, + "learning_rate": 1.2259682002249794e-05, + "loss": 3.8624, + "step": 2305024 + }, + { + "epoch": 0.01, + "learning_rate": 1.2251296054739272e-05, + "loss": 3.862, + "step": 2305536 + }, + { + "epoch": 0.01, + "learning_rate": 1.2242926486032484e-05, + "loss": 3.8654, + "step": 2306048 + }, + { + "epoch": 0.01, + "learning_rate": 1.2234540538521964e-05, + "loss": 3.8664, + "step": 2306560 + }, + { + "epoch": 0.01, + "learning_rate": 1.2226154591011444e-05, + "loss": 3.8633, + "step": 2307072 + }, + { + "epoch": 0.01, + "learning_rate": 1.2217785022304655e-05, + "loss": 3.8701, + "step": 2307584 + }, + { + "epoch": 0.01, + "learning_rate": 1.2209399074794135e-05, + "loss": 3.8699, + "step": 2308096 + }, + { + "epoch": 0.01, + "learning_rate": 1.2201013127283615e-05, + "loss": 3.8442, + "step": 2308608 + }, + { + "epoch": 0.01, + "learning_rate": 1.2192627179773095e-05, + "loss": 3.8675, + "step": 2309120 + }, + { + "epoch": 0.01, + "learning_rate": 1.2184241232262575e-05, + "loss": 3.8483, + "step": 2309632 + }, + { + "epoch": 0.01, + "learning_rate": 1.2175855284752055e-05, + "loss": 3.8581, + "step": 2310144 + }, + { + "epoch": 0.01, + "learning_rate": 1.2167469337241535e-05, + "loss": 3.8625, + "step": 2310656 + }, + { + "epoch": 0.01, + "learning_rate": 1.2159083389731015e-05, + "loss": 3.8687, + "step": 2311168 + }, + { + "epoch": 0.01, + "learning_rate": 1.2150697442220495e-05, + "loss": 3.8574, + "step": 2311680 + }, + { + "epoch": 0.01, + "learning_rate": 1.2142311494709975e-05, + "loss": 3.8641, + "step": 2312192 + }, + { + "epoch": 0.01, + "learning_rate": 1.2133941926003186e-05, + "loss": 3.8695, + "step": 2312704 + }, + { + "epoch": 0.01, + "learning_rate": 1.2125555978492665e-05, + "loss": 3.8642, + "step": 2313216 + }, + { + "epoch": 0.01, + "learning_rate": 1.2117170030982145e-05, + "loss": 3.8678, + "step": 2313728 + }, + { + "epoch": 0.01, + "learning_rate": 1.2108784083471627e-05, + "loss": 3.8358, + "step": 2314240 + }, + { + "epoch": 0.01, + "learning_rate": 1.2100398135961105e-05, + "loss": 3.8609, + "step": 2314752 + }, + { + "epoch": 0.01, + "learning_rate": 1.2092012188450585e-05, + "loss": 3.8697, + "step": 2315264 + }, + { + "epoch": 0.01, + "learning_rate": 1.2083626240940065e-05, + "loss": 3.8668, + "step": 2315776 + }, + { + "epoch": 0.01, + "learning_rate": 1.2075240293429545e-05, + "loss": 3.8638, + "step": 2316288 + }, + { + "epoch": 0.01, + "learning_rate": 1.2066870724722756e-05, + "loss": 3.8518, + "step": 2316800 + }, + { + "epoch": 0.01, + "learning_rate": 1.2058484777212236e-05, + "loss": 3.8552, + "step": 2317312 + }, + { + "epoch": 0.01, + "learning_rate": 1.2050098829701718e-05, + "loss": 3.8416, + "step": 2317824 + }, + { + "epoch": 0.01, + "learning_rate": 1.2041712882191196e-05, + "loss": 3.868, + "step": 2318336 + }, + { + "epoch": 0.01, + "learning_rate": 1.2033343313484408e-05, + "loss": 3.8434, + "step": 2318848 + }, + { + "epoch": 0.01, + "learning_rate": 1.2024957365973888e-05, + "loss": 3.8684, + "step": 2319360 + }, + { + "epoch": 0.01, + "learning_rate": 1.2016571418463367e-05, + "loss": 3.8615, + "step": 2319872 + }, + { + "epoch": 0.01, + "learning_rate": 1.2008185470952847e-05, + "loss": 3.8499, + "step": 2320384 + }, + { + "epoch": 0.01, + "learning_rate": 1.1999799523442328e-05, + "loss": 3.8649, + "step": 2320896 + }, + { + "epoch": 0.01, + "learning_rate": 1.1991413575931808e-05, + "loss": 3.8478, + "step": 2321408 + }, + { + "epoch": 0.01, + "learning_rate": 1.1983044007225017e-05, + "loss": 3.8505, + "step": 2321920 + }, + { + "epoch": 0.01, + "learning_rate": 1.1974658059714499e-05, + "loss": 3.8522, + "step": 2322432 + }, + { + "epoch": 0.01, + "learning_rate": 1.1966272112203979e-05, + "loss": 3.8654, + "step": 2322944 + }, + { + "epoch": 0.01, + "learning_rate": 1.1957886164693457e-05, + "loss": 3.8486, + "step": 2323456 + }, + { + "epoch": 0.01, + "learning_rate": 1.1949500217182937e-05, + "loss": 3.8585, + "step": 2323968 + }, + { + "epoch": 0.01, + "learning_rate": 1.194113064847615e-05, + "loss": 3.8472, + "step": 2324480 + }, + { + "epoch": 0.01, + "learning_rate": 1.193274470096563e-05, + "loss": 3.8533, + "step": 2324992 + }, + { + "epoch": 0.01, + "learning_rate": 1.192435875345511e-05, + "loss": 3.8647, + "step": 2325504 + }, + { + "epoch": 0.01, + "learning_rate": 1.191597280594459e-05, + "loss": 3.8635, + "step": 2326016 + }, + { + "epoch": 0.01, + "learning_rate": 1.190758685843407e-05, + "loss": 3.8571, + "step": 2326528 + }, + { + "epoch": 0.01, + "learning_rate": 1.1899200910923548e-05, + "loss": 3.8611, + "step": 2327040 + }, + { + "epoch": 0.01, + "learning_rate": 1.189081496341303e-05, + "loss": 3.8735, + "step": 2327552 + }, + { + "epoch": 0.01, + "learning_rate": 1.188244539470624e-05, + "loss": 3.8486, + "step": 2328064 + }, + { + "epoch": 0.01, + "learning_rate": 1.187405944719572e-05, + "loss": 3.8658, + "step": 2328576 + }, + { + "epoch": 0.01, + "learning_rate": 1.18656734996852e-05, + "loss": 3.855, + "step": 2329088 + }, + { + "epoch": 0.01, + "learning_rate": 1.185728755217468e-05, + "loss": 3.8579, + "step": 2329600 + }, + { + "epoch": 0.01, + "learning_rate": 1.184890160466416e-05, + "loss": 3.8546, + "step": 2330112 + }, + { + "epoch": 0.01, + "learning_rate": 1.184051565715364e-05, + "loss": 3.8576, + "step": 2330624 + }, + { + "epoch": 0.01, + "learning_rate": 1.183212970964312e-05, + "loss": 3.8726, + "step": 2331136 + }, + { + "epoch": 0.01, + "learning_rate": 1.18237437621326e-05, + "loss": 3.8697, + "step": 2331648 + }, + { + "epoch": 0.01, + "learning_rate": 1.181537419342581e-05, + "loss": 3.8547, + "step": 2332160 + }, + { + "epoch": 0.01, + "learning_rate": 1.1807004624719021e-05, + "loss": 3.8374, + "step": 2332672 + }, + { + "epoch": 0.01, + "learning_rate": 1.1798618677208501e-05, + "loss": 3.8517, + "step": 2333184 + }, + { + "epoch": 0.01, + "learning_rate": 1.1790232729697983e-05, + "loss": 3.8626, + "step": 2333696 + }, + { + "epoch": 0.01, + "learning_rate": 1.1781846782187461e-05, + "loss": 3.8552, + "step": 2334208 + }, + { + "epoch": 0.01, + "learning_rate": 1.1773460834676941e-05, + "loss": 3.8506, + "step": 2334720 + }, + { + "epoch": 0.01, + "learning_rate": 1.1765091265970154e-05, + "loss": 3.8618, + "step": 2335232 + }, + { + "epoch": 0.02, + "learning_rate": 1.1756705318459634e-05, + "loss": 3.8587, + "step": 2335744 + }, + { + "epoch": 0.02, + "learning_rate": 1.1748319370949112e-05, + "loss": 3.8593, + "step": 2336256 + }, + { + "epoch": 0.02, + "learning_rate": 1.1739933423438593e-05, + "loss": 3.8521, + "step": 2336768 + }, + { + "epoch": 0.02, + "learning_rate": 1.1731547475928073e-05, + "loss": 3.8658, + "step": 2337280 + }, + { + "epoch": 0.02, + "learning_rate": 1.1723161528417552e-05, + "loss": 3.852, + "step": 2337792 + }, + { + "epoch": 0.02, + "learning_rate": 1.1714791959710764e-05, + "loss": 3.8698, + "step": 2338304 + }, + { + "epoch": 0.02, + "learning_rate": 1.1706406012200244e-05, + "loss": 3.85, + "step": 2338816 + }, + { + "epoch": 0.02, + "learning_rate": 1.1698020064689724e-05, + "loss": 3.8496, + "step": 2339328 + }, + { + "epoch": 0.02, + "learning_rate": 1.1689634117179202e-05, + "loss": 3.861, + "step": 2339840 + }, + { + "epoch": 0.02, + "learning_rate": 1.1681248169668684e-05, + "loss": 3.8585, + "step": 2340352 + }, + { + "epoch": 0.02, + "learning_rate": 1.1672878600961895e-05, + "loss": 3.8666, + "step": 2340864 + }, + { + "epoch": 0.02, + "learning_rate": 1.1664492653451375e-05, + "loss": 3.8599, + "step": 2341376 + }, + { + "epoch": 0.02, + "learning_rate": 1.1656106705940855e-05, + "loss": 3.8556, + "step": 2341888 + }, + { + "epoch": 0.02, + "learning_rate": 1.1647720758430335e-05, + "loss": 3.852, + "step": 2342400 + }, + { + "epoch": 0.02, + "learning_rate": 1.1639334810919815e-05, + "loss": 3.8576, + "step": 2342912 + }, + { + "epoch": 0.02, + "learning_rate": 1.1630948863409295e-05, + "loss": 3.8513, + "step": 2343424 + }, + { + "epoch": 0.02, + "learning_rate": 1.1622562915898775e-05, + "loss": 3.855, + "step": 2343936 + }, + { + "epoch": 0.02, + "learning_rate": 1.1614176968388254e-05, + "loss": 3.8587, + "step": 2344448 + }, + { + "epoch": 0.02, + "learning_rate": 1.1605807399681467e-05, + "loss": 3.852, + "step": 2344960 + }, + { + "epoch": 0.02, + "learning_rate": 1.1597437830974676e-05, + "loss": 3.8493, + "step": 2345472 + }, + { + "epoch": 0.02, + "learning_rate": 1.1589051883464156e-05, + "loss": 3.8587, + "step": 2345984 + }, + { + "epoch": 0.02, + "learning_rate": 1.1580665935953638e-05, + "loss": 3.8418, + "step": 2346496 + }, + { + "epoch": 0.02, + "learning_rate": 1.1572279988443116e-05, + "loss": 3.8636, + "step": 2347008 + }, + { + "epoch": 0.02, + "learning_rate": 1.1563894040932596e-05, + "loss": 3.8576, + "step": 2347520 + }, + { + "epoch": 0.02, + "learning_rate": 1.1555508093422076e-05, + "loss": 3.8632, + "step": 2348032 + }, + { + "epoch": 0.02, + "learning_rate": 1.1547122145911558e-05, + "loss": 3.8626, + "step": 2348544 + }, + { + "epoch": 0.02, + "learning_rate": 1.1538752577204767e-05, + "loss": 3.8648, + "step": 2349056 + }, + { + "epoch": 0.02, + "learning_rate": 1.1530366629694248e-05, + "loss": 3.8571, + "step": 2349568 + }, + { + "epoch": 0.02, + "learning_rate": 1.1521980682183728e-05, + "loss": 3.8553, + "step": 2350080 + }, + { + "epoch": 0.02, + "learning_rate": 1.1513594734673206e-05, + "loss": 3.8586, + "step": 2350592 + }, + { + "epoch": 0.02, + "learning_rate": 1.1505208787162686e-05, + "loss": 3.8569, + "step": 2351104 + }, + { + "epoch": 0.02, + "learning_rate": 1.1496822839652168e-05, + "loss": 3.8482, + "step": 2351616 + }, + { + "epoch": 0.02, + "learning_rate": 1.1488436892141648e-05, + "loss": 3.8689, + "step": 2352128 + }, + { + "epoch": 0.02, + "learning_rate": 1.1480050944631126e-05, + "loss": 3.8516, + "step": 2352640 + }, + { + "epoch": 0.02, + "learning_rate": 1.1471664997120606e-05, + "loss": 3.8591, + "step": 2353152 + }, + { + "epoch": 0.02, + "learning_rate": 1.1463295428413819e-05, + "loss": 3.8512, + "step": 2353664 + }, + { + "epoch": 0.02, + "learning_rate": 1.1454909480903297e-05, + "loss": 3.8477, + "step": 2354176 + }, + { + "epoch": 0.02, + "learning_rate": 1.144653991219651e-05, + "loss": 3.8626, + "step": 2354688 + }, + { + "epoch": 0.02, + "learning_rate": 1.143815396468599e-05, + "loss": 3.8532, + "step": 2355200 + }, + { + "epoch": 0.02, + "learning_rate": 1.142976801717547e-05, + "loss": 3.8581, + "step": 2355712 + }, + { + "epoch": 0.02, + "learning_rate": 1.142138206966495e-05, + "loss": 3.8695, + "step": 2356224 + }, + { + "epoch": 0.02, + "learning_rate": 1.141299612215443e-05, + "loss": 3.8591, + "step": 2356736 + }, + { + "epoch": 0.02, + "learning_rate": 1.140462655344764e-05, + "loss": 3.8543, + "step": 2357248 + }, + { + "epoch": 0.02, + "learning_rate": 1.1396240605937122e-05, + "loss": 3.8629, + "step": 2357760 + }, + { + "epoch": 0.02, + "learning_rate": 1.13878546584266e-05, + "loss": 3.865, + "step": 2358272 + }, + { + "epoch": 0.02, + "learning_rate": 1.137946871091608e-05, + "loss": 3.8631, + "step": 2358784 + }, + { + "epoch": 0.02, + "learning_rate": 1.137108276340556e-05, + "loss": 3.8512, + "step": 2359296 + }, + { + "epoch": 0.02, + "learning_rate": 1.136269681589504e-05, + "loss": 3.8564, + "step": 2359808 + }, + { + "epoch": 0.02, + "learning_rate": 1.135432724718825e-05, + "loss": 3.8702, + "step": 2360320 + }, + { + "epoch": 0.02, + "learning_rate": 1.134594129967773e-05, + "loss": 3.8745, + "step": 2360832 + }, + { + "epoch": 0.02, + "learning_rate": 1.1337555352167212e-05, + "loss": 3.8581, + "step": 2361344 + }, + { + "epoch": 0.02, + "learning_rate": 1.132916940465669e-05, + "loss": 3.8622, + "step": 2361856 + }, + { + "epoch": 0.02, + "learning_rate": 1.132078345714617e-05, + "loss": 3.8677, + "step": 2362368 + }, + { + "epoch": 0.02, + "learning_rate": 1.1312413888439383e-05, + "loss": 3.8613, + "step": 2362880 + }, + { + "epoch": 0.02, + "learning_rate": 1.1304027940928861e-05, + "loss": 3.8602, + "step": 2363392 + }, + { + "epoch": 0.02, + "learning_rate": 1.1295641993418341e-05, + "loss": 3.8593, + "step": 2363904 + }, + { + "epoch": 0.02, + "learning_rate": 1.1287256045907823e-05, + "loss": 3.8578, + "step": 2364416 + }, + { + "epoch": 0.02, + "learning_rate": 1.1278870098397303e-05, + "loss": 3.8692, + "step": 2364928 + }, + { + "epoch": 0.02, + "learning_rate": 1.1270484150886781e-05, + "loss": 3.8476, + "step": 2365440 + }, + { + "epoch": 0.03, + "eval_loss": 3.983637809753418, + "eval_runtime": 290.8119, + "eval_samples_per_second": 1312.157, + "eval_steps_per_second": 41.006, + "step": 2365920 + }, + { + "epoch": 0.0, + "learning_rate": 1.1262098203376261e-05, + "loss": 3.8328, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.1253712255865743e-05, + "loss": 3.8513, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.1245326308355221e-05, + "loss": 3.8538, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.1236940360844701e-05, + "loss": 3.8711, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.122855441333418e-05, + "loss": 3.871, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.122016846582366e-05, + "loss": 3.8564, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.121178251831314e-05, + "loss": 3.8629, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.120339657080262e-05, + "loss": 3.8582, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.11950106232921e-05, + "loss": 3.8548, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.118662467578158e-05, + "loss": 3.8667, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.117823872827106e-05, + "loss": 3.8604, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1169869159564273e-05, + "loss": 3.8655, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.1161499590857482e-05, + "loss": 3.8727, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.1153113643346964e-05, + "loss": 3.8508, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.1144727695836444e-05, + "loss": 3.852, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.1136341748325924e-05, + "loss": 3.8416, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1127955800815402e-05, + "loss": 3.8604, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1119569853304884e-05, + "loss": 3.859, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.1111183905794364e-05, + "loss": 3.8527, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1102797958283842e-05, + "loss": 3.857, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1094412010773322e-05, + "loss": 3.875, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1086026063262803e-05, + "loss": 3.862, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.1077640115752282e-05, + "loss": 3.8645, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1069254168241762e-05, + "loss": 3.8601, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1060868220731242e-05, + "loss": 3.8706, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1052482273220723e-05, + "loss": 3.8578, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1044096325710202e-05, + "loss": 3.8569, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1035710378199681e-05, + "loss": 3.8547, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.1027324430689161e-05, + "loss": 3.8531, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.1018938483178641e-05, + "loss": 3.8547, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1010552535668121e-05, + "loss": 3.8575, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.1002166588157601e-05, + "loss": 3.8579, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.0993797019450814e-05, + "loss": 3.8619, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0985411071940292e-05, + "loss": 3.8614, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0977025124429772e-05, + "loss": 3.8652, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.0968671934526715e-05, + "loss": 3.8624, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.0960285987016195e-05, + "loss": 3.8664, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.0951900039505675e-05, + "loss": 3.8419, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.0943514091995155e-05, + "loss": 3.8654, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.0935128144484635e-05, + "loss": 3.8387, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.0926742196974115e-05, + "loss": 3.8577, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.0918356249463595e-05, + "loss": 3.8595, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.0909970301953075e-05, + "loss": 3.8654, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.0901584354442553e-05, + "loss": 3.8509, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.0893198406932035e-05, + "loss": 3.8642, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.0884828838225246e-05, + "loss": 3.865, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.0876442890714726e-05, + "loss": 3.8635, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.0868056943204206e-05, + "loss": 3.8601, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.0859670995693686e-05, + "loss": 3.8355, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.0851285048183166e-05, + "loss": 3.8555, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0842899100672645e-05, + "loss": 3.8669, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.0834513153162125e-05, + "loss": 3.8623, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0826143584455336e-05, + "loss": 3.8575, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.0817757636944816e-05, + "loss": 3.8483, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.0809371689434296e-05, + "loss": 3.8525, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.0800985741923776e-05, + "loss": 3.8385, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.0792616173216989e-05, + "loss": 3.8653, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.0784230225706469e-05, + "loss": 3.839, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.0775844278195947e-05, + "loss": 3.8618, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0767458330685427e-05, + "loss": 3.8605, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0759072383174908e-05, + "loss": 3.8495, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0750686435664387e-05, + "loss": 3.8558, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0742300488153867e-05, + "loss": 3.844, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0733914540643347e-05, + "loss": 3.8483, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0725544971936559e-05, + "loss": 3.8443, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.0717159024426037e-05, + "loss": 3.8656, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0708773076915517e-05, + "loss": 3.8493, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0700387129404999e-05, + "loss": 3.8507, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.0692001181894477e-05, + "loss": 3.8454, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.068363161318769e-05, + "loss": 3.8524, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.067524566567717e-05, + "loss": 3.8629, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.0666859718166648e-05, + "loss": 3.859, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.0658473770656128e-05, + "loss": 3.8508, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.065010420194934e-05, + "loss": 3.8599, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.064171825443882e-05, + "loss": 3.8685, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.06333323069283e-05, + "loss": 3.842, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.062494635941778e-05, + "loss": 3.8631, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0616593169514724e-05, + "loss": 3.8522, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.0608207222004203e-05, + "loss": 3.8535, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.0599837653297413e-05, + "loss": 3.8492, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.0591451705786894e-05, + "loss": 3.8555, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.0583065758276374e-05, + "loss": 3.8679, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.0574679810765854e-05, + "loss": 3.8657, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0566293863255332e-05, + "loss": 3.8521, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.0557924294548545e-05, + "loss": 3.8332, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.0549538347038025e-05, + "loss": 3.8524, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0541152399527505e-05, + "loss": 3.8562, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.0532766452016985e-05, + "loss": 3.8576, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.0524380504506465e-05, + "loss": 3.8446, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0515994556995945e-05, + "loss": 3.858, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0507608609485425e-05, + "loss": 3.8552, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0499222661974905e-05, + "loss": 3.8584, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.0490836714464385e-05, + "loss": 3.8463, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.0482450766953863e-05, + "loss": 3.8617, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0474064819443344e-05, + "loss": 3.8476, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.0465695250736555e-05, + "loss": 3.8673, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0457309303226035e-05, + "loss": 3.8515, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0448923355715515e-05, + "loss": 3.8449, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0440537408204995e-05, + "loss": 3.8563, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0432151460694475e-05, + "loss": 3.8588, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0423781891987686e-05, + "loss": 3.8605, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0415395944477166e-05, + "loss": 3.8568, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.0407026375770378e-05, + "loss": 3.8537, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0398640428259858e-05, + "loss": 3.848, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.0390254480749336e-05, + "loss": 3.8567, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.0381868533238816e-05, + "loss": 3.8445, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0373482585728298e-05, + "loss": 3.8539, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.0365096638217776e-05, + "loss": 3.8555, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0356710690707256e-05, + "loss": 3.853, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.0348324743196736e-05, + "loss": 3.8429, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.0339938795686218e-05, + "loss": 3.8549, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.0331552848175696e-05, + "loss": 3.8442, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0323183279468909e-05, + "loss": 3.8584, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.0314797331958389e-05, + "loss": 3.8534, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.0306411384447867e-05, + "loss": 3.8549, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0298025436937347e-05, + "loss": 3.8602, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.0289639489426828e-05, + "loss": 3.862, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0281253541916308e-05, + "loss": 3.8581, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.0272867594405787e-05, + "loss": 3.849, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.0264498025699e-05, + "loss": 3.8561, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.0256112078188479e-05, + "loss": 3.8565, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.0247726130677957e-05, + "loss": 3.8479, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.0239340183167437e-05, + "loss": 3.8607, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0230954235656919e-05, + "loss": 3.8502, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.0222568288146399e-05, + "loss": 3.8585, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.0214182340635877e-05, + "loss": 3.8476, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.0205796393125359e-05, + "loss": 3.8474, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.019742682441857e-05, + "loss": 3.8557, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.0189057255711782e-05, + "loss": 3.8509, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.018067130820126e-05, + "loss": 3.8495, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.0172301739494471e-05, + "loss": 3.8703, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.0163915791983953e-05, + "loss": 3.8586, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.0155529844473431e-05, + "loss": 3.849, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.0147143896962911e-05, + "loss": 3.8595, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.0138774328256124e-05, + "loss": 3.859, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.0130388380745604e-05, + "loss": 3.8608, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0122002433235082e-05, + "loss": 3.8537, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0113616485724563e-05, + "loss": 3.8501, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.0105230538214043e-05, + "loss": 3.8655, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.0096844590703522e-05, + "loss": 3.8694, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0088458643193002e-05, + "loss": 3.8547, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0080072695682483e-05, + "loss": 3.8566, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0071703126975694e-05, + "loss": 3.8659, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0063317179465174e-05, + "loss": 3.8542, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0054931231954654e-05, + "loss": 3.8603, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.0046545284444134e-05, + "loss": 3.8549, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0038159336933612e-05, + "loss": 3.8542, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0029773389423094e-05, + "loss": 3.8652, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0021387441912574e-05, + "loss": 3.8462, + "step": 2441728 + }, + { + "epoch": 0.03, + "learning_rate": 1.0013017873205785e-05, + "loss": 3.8537, + "step": 2442240 + }, + { + "epoch": 0.03, + "eval_loss": 3.9825358390808105, + "eval_runtime": 293.4877, + "eval_samples_per_second": 1300.194, + "eval_steps_per_second": 40.632, + "step": 2442240 + }, + { + "epoch": 0.0, + "learning_rate": 1.0004631925695265e-05, + "loss": 3.8468, + "step": 2442752 + }, + { + "epoch": 0.0, + "learning_rate": 9.996245978184744e-06, + "loss": 3.8474, + "step": 2443264 + }, + { + "epoch": 0.0, + "learning_rate": 9.987860030674224e-06, + "loss": 3.8691, + "step": 2443776 + }, + { + "epoch": 0.0, + "learning_rate": 9.979474083163703e-06, + "loss": 3.8684, + "step": 2444288 + }, + { + "epoch": 0.0, + "learning_rate": 9.971088135653184e-06, + "loss": 3.856, + "step": 2444800 + }, + { + "epoch": 0.0, + "learning_rate": 9.962702188142664e-06, + "loss": 3.8577, + "step": 2445312 + }, + { + "epoch": 0.0, + "learning_rate": 9.954316240632143e-06, + "loss": 3.8555, + "step": 2445824 + }, + { + "epoch": 0.0, + "learning_rate": 9.945930293121623e-06, + "loss": 3.8469, + "step": 2446336 + }, + { + "epoch": 0.0, + "learning_rate": 9.937544345611104e-06, + "loss": 3.8671, + "step": 2446848 + }, + { + "epoch": 0.0, + "learning_rate": 9.929158398100584e-06, + "loss": 3.8551, + "step": 2447360 + }, + { + "epoch": 0.0, + "learning_rate": 9.920772450590062e-06, + "loss": 3.8654, + "step": 2447872 + }, + { + "epoch": 0.0, + "learning_rate": 9.912386503079544e-06, + "loss": 3.865, + "step": 2448384 + }, + { + "epoch": 0.0, + "learning_rate": 9.904016934372755e-06, + "loss": 3.8551, + "step": 2448896 + }, + { + "epoch": 0.0, + "learning_rate": 9.895630986862233e-06, + "loss": 3.8471, + "step": 2449408 + }, + { + "epoch": 0.0, + "learning_rate": 9.887245039351715e-06, + "loss": 3.8385, + "step": 2449920 + }, + { + "epoch": 0.0, + "learning_rate": 9.878859091841195e-06, + "loss": 3.8523, + "step": 2450432 + }, + { + "epoch": 0.0, + "learning_rate": 9.870473144330675e-06, + "loss": 3.8543, + "step": 2450944 + }, + { + "epoch": 0.0, + "learning_rate": 9.862087196820153e-06, + "loss": 3.8486, + "step": 2451456 + }, + { + "epoch": 0.0, + "learning_rate": 9.853701249309635e-06, + "loss": 3.8508, + "step": 2451968 + }, + { + "epoch": 0.0, + "learning_rate": 9.845315301799115e-06, + "loss": 3.8757, + "step": 2452480 + }, + { + "epoch": 0.0, + "learning_rate": 9.836929354288593e-06, + "loss": 3.8587, + "step": 2452992 + }, + { + "epoch": 0.0, + "learning_rate": 9.828543406778073e-06, + "loss": 3.86, + "step": 2453504 + }, + { + "epoch": 0.0, + "learning_rate": 9.820157459267554e-06, + "loss": 3.8572, + "step": 2454016 + }, + { + "epoch": 0.0, + "learning_rate": 9.811771511757033e-06, + "loss": 3.871, + "step": 2454528 + }, + { + "epoch": 0.0, + "learning_rate": 9.803401943050245e-06, + "loss": 3.8494, + "step": 2455040 + }, + { + "epoch": 0.0, + "learning_rate": 9.795015995539725e-06, + "loss": 3.8542, + "step": 2455552 + }, + { + "epoch": 0.0, + "learning_rate": 9.786630048029205e-06, + "loss": 3.8507, + "step": 2456064 + }, + { + "epoch": 0.0, + "learning_rate": 9.778244100518683e-06, + "loss": 3.852, + "step": 2456576 + }, + { + "epoch": 0.0, + "learning_rate": 9.769874531811896e-06, + "loss": 3.8519, + "step": 2457088 + }, + { + "epoch": 0.01, + "learning_rate": 9.761488584301376e-06, + "loss": 3.8519, + "step": 2457600 + }, + { + "epoch": 0.01, + "learning_rate": 9.753102636790856e-06, + "loss": 3.8554, + "step": 2458112 + }, + { + "epoch": 0.01, + "learning_rate": 9.744716689280336e-06, + "loss": 3.8598, + "step": 2458624 + }, + { + "epoch": 0.01, + "learning_rate": 9.736347120573546e-06, + "loss": 3.853, + "step": 2459136 + }, + { + "epoch": 0.01, + "learning_rate": 9.727961173063026e-06, + "loss": 3.8643, + "step": 2459648 + }, + { + "epoch": 0.01, + "learning_rate": 9.719591604356239e-06, + "loss": 3.858, + "step": 2460160 + }, + { + "epoch": 0.01, + "learning_rate": 9.711205656845717e-06, + "loss": 3.8633, + "step": 2460672 + }, + { + "epoch": 0.01, + "learning_rate": 9.702819709335199e-06, + "loss": 3.8423, + "step": 2461184 + }, + { + "epoch": 0.01, + "learning_rate": 9.694433761824679e-06, + "loss": 3.8627, + "step": 2461696 + }, + { + "epoch": 0.01, + "learning_rate": 9.686047814314157e-06, + "loss": 3.837, + "step": 2462208 + }, + { + "epoch": 0.01, + "learning_rate": 9.677661866803637e-06, + "loss": 3.8573, + "step": 2462720 + }, + { + "epoch": 0.01, + "learning_rate": 9.669275919293119e-06, + "loss": 3.8522, + "step": 2463232 + }, + { + "epoch": 0.01, + "learning_rate": 9.66090635058633e-06, + "loss": 3.8603, + "step": 2463744 + }, + { + "epoch": 0.01, + "learning_rate": 9.652520403075808e-06, + "loss": 3.8462, + "step": 2464256 + }, + { + "epoch": 0.01, + "learning_rate": 9.64413445556529e-06, + "loss": 3.8618, + "step": 2464768 + }, + { + "epoch": 0.01, + "learning_rate": 9.63574850805477e-06, + "loss": 3.8606, + "step": 2465280 + }, + { + "epoch": 0.01, + "learning_rate": 9.627362560544248e-06, + "loss": 3.8601, + "step": 2465792 + }, + { + "epoch": 0.01, + "learning_rate": 9.618976613033727e-06, + "loss": 3.86, + "step": 2466304 + }, + { + "epoch": 0.01, + "learning_rate": 9.610590665523209e-06, + "loss": 3.8336, + "step": 2466816 + }, + { + "epoch": 0.01, + "learning_rate": 9.602204718012687e-06, + "loss": 3.8543, + "step": 2467328 + }, + { + "epoch": 0.01, + "learning_rate": 9.5938351493059e-06, + "loss": 3.8634, + "step": 2467840 + }, + { + "epoch": 0.01, + "learning_rate": 9.58544920179538e-06, + "loss": 3.8557, + "step": 2468352 + }, + { + "epoch": 0.01, + "learning_rate": 9.57706325428486e-06, + "loss": 3.8569, + "step": 2468864 + }, + { + "epoch": 0.01, + "learning_rate": 9.568677306774338e-06, + "loss": 3.845, + "step": 2469376 + }, + { + "epoch": 0.01, + "learning_rate": 9.56029135926382e-06, + "loss": 3.8506, + "step": 2469888 + }, + { + "epoch": 0.01, + "learning_rate": 9.5519054117533e-06, + "loss": 3.8337, + "step": 2470400 + }, + { + "epoch": 0.01, + "learning_rate": 9.54353584304651e-06, + "loss": 3.864, + "step": 2470912 + }, + { + "epoch": 0.01, + "learning_rate": 9.53514989553599e-06, + "loss": 3.8359, + "step": 2471424 + }, + { + "epoch": 0.01, + "learning_rate": 9.52676394802547e-06, + "loss": 3.859, + "step": 2471936 + }, + { + "epoch": 0.01, + "learning_rate": 9.51837800051495e-06, + "loss": 3.8563, + "step": 2472448 + }, + { + "epoch": 0.01, + "learning_rate": 9.50999205300443e-06, + "loss": 3.8431, + "step": 2472960 + }, + { + "epoch": 0.01, + "learning_rate": 9.501622484297641e-06, + "loss": 3.8486, + "step": 2473472 + }, + { + "epoch": 0.01, + "learning_rate": 9.493236536787121e-06, + "loss": 3.8463, + "step": 2473984 + }, + { + "epoch": 0.01, + "learning_rate": 9.484850589276601e-06, + "loss": 3.8429, + "step": 2474496 + }, + { + "epoch": 0.01, + "learning_rate": 9.476464641766081e-06, + "loss": 3.8401, + "step": 2475008 + }, + { + "epoch": 0.01, + "learning_rate": 9.468078694255561e-06, + "loss": 3.8621, + "step": 2475520 + }, + { + "epoch": 0.01, + "learning_rate": 9.45969274674504e-06, + "loss": 3.8459, + "step": 2476032 + }, + { + "epoch": 0.01, + "learning_rate": 9.45130679923452e-06, + "loss": 3.8453, + "step": 2476544 + }, + { + "epoch": 0.01, + "learning_rate": 9.442920851724e-06, + "loss": 3.8432, + "step": 2477056 + }, + { + "epoch": 0.01, + "learning_rate": 9.434551283017212e-06, + "loss": 3.8475, + "step": 2477568 + }, + { + "epoch": 0.01, + "learning_rate": 9.426165335506692e-06, + "loss": 3.8587, + "step": 2478080 + }, + { + "epoch": 0.01, + "learning_rate": 9.417795766799902e-06, + "loss": 3.8575, + "step": 2478592 + }, + { + "epoch": 0.01, + "learning_rate": 9.409409819289384e-06, + "loss": 3.8462, + "step": 2479104 + }, + { + "epoch": 0.01, + "learning_rate": 9.401023871778864e-06, + "loss": 3.8584, + "step": 2479616 + }, + { + "epoch": 0.01, + "learning_rate": 9.392637924268342e-06, + "loss": 3.8661, + "step": 2480128 + }, + { + "epoch": 0.01, + "learning_rate": 9.384251976757822e-06, + "loss": 3.8412, + "step": 2480640 + }, + { + "epoch": 0.01, + "learning_rate": 9.375866029247304e-06, + "loss": 3.8565, + "step": 2481152 + }, + { + "epoch": 0.01, + "learning_rate": 9.367480081736782e-06, + "loss": 3.8508, + "step": 2481664 + }, + { + "epoch": 0.01, + "learning_rate": 9.359110513029993e-06, + "loss": 3.8516, + "step": 2482176 + }, + { + "epoch": 0.01, + "learning_rate": 9.350724565519474e-06, + "loss": 3.8457, + "step": 2482688 + }, + { + "epoch": 0.01, + "learning_rate": 9.342338618008954e-06, + "loss": 3.8489, + "step": 2483200 + }, + { + "epoch": 0.01, + "learning_rate": 9.333952670498433e-06, + "loss": 3.8615, + "step": 2483712 + }, + { + "epoch": 0.01, + "learning_rate": 9.325566722987913e-06, + "loss": 3.8668, + "step": 2484224 + }, + { + "epoch": 0.01, + "learning_rate": 9.317180775477394e-06, + "loss": 3.8438, + "step": 2484736 + }, + { + "epoch": 0.01, + "learning_rate": 9.308811206770605e-06, + "loss": 3.8286, + "step": 2485248 + }, + { + "epoch": 0.01, + "learning_rate": 9.300425259260085e-06, + "loss": 3.85, + "step": 2485760 + }, + { + "epoch": 0.01, + "learning_rate": 9.292039311749565e-06, + "loss": 3.8524, + "step": 2486272 + }, + { + "epoch": 0.01, + "learning_rate": 9.283653364239045e-06, + "loss": 3.8539, + "step": 2486784 + }, + { + "epoch": 0.01, + "learning_rate": 9.275267416728523e-06, + "loss": 3.8445, + "step": 2487296 + }, + { + "epoch": 0.01, + "learning_rate": 9.266897848021736e-06, + "loss": 3.8531, + "step": 2487808 + }, + { + "epoch": 0.02, + "learning_rate": 9.258511900511216e-06, + "loss": 3.8529, + "step": 2488320 + }, + { + "epoch": 0.02, + "learning_rate": 9.250125953000696e-06, + "loss": 3.8521, + "step": 2488832 + }, + { + "epoch": 0.02, + "learning_rate": 9.241740005490176e-06, + "loss": 3.844, + "step": 2489344 + }, + { + "epoch": 0.02, + "learning_rate": 9.233354057979656e-06, + "loss": 3.8576, + "step": 2489856 + }, + { + "epoch": 0.02, + "learning_rate": 9.224984489272866e-06, + "loss": 3.845, + "step": 2490368 + }, + { + "epoch": 0.02, + "learning_rate": 9.216598541762346e-06, + "loss": 3.8593, + "step": 2490880 + }, + { + "epoch": 0.02, + "learning_rate": 9.208212594251826e-06, + "loss": 3.8532, + "step": 2491392 + }, + { + "epoch": 0.02, + "learning_rate": 9.199826646741306e-06, + "loss": 3.8384, + "step": 2491904 + }, + { + "epoch": 0.02, + "learning_rate": 9.191457078034519e-06, + "loss": 3.8523, + "step": 2492416 + }, + { + "epoch": 0.02, + "learning_rate": 9.183071130523997e-06, + "loss": 3.8569, + "step": 2492928 + }, + { + "epoch": 0.02, + "learning_rate": 9.174685183013477e-06, + "loss": 3.8592, + "step": 2493440 + }, + { + "epoch": 0.02, + "learning_rate": 9.166299235502959e-06, + "loss": 3.8513, + "step": 2493952 + }, + { + "epoch": 0.02, + "learning_rate": 9.157913287992437e-06, + "loss": 3.8506, + "step": 2494464 + }, + { + "epoch": 0.02, + "learning_rate": 9.149527340481917e-06, + "loss": 3.8448, + "step": 2494976 + }, + { + "epoch": 0.02, + "learning_rate": 9.141141392971397e-06, + "loss": 3.8548, + "step": 2495488 + }, + { + "epoch": 0.02, + "learning_rate": 9.132755445460878e-06, + "loss": 3.8404, + "step": 2496000 + }, + { + "epoch": 0.02, + "learning_rate": 9.124385876754087e-06, + "loss": 3.8473, + "step": 2496512 + }, + { + "epoch": 0.02, + "learning_rate": 9.115999929243569e-06, + "loss": 3.8523, + "step": 2497024 + }, + { + "epoch": 0.02, + "learning_rate": 9.107613981733049e-06, + "loss": 3.8514, + "step": 2497536 + }, + { + "epoch": 0.02, + "learning_rate": 9.099228034222527e-06, + "loss": 3.8389, + "step": 2498048 + }, + { + "epoch": 0.02, + "learning_rate": 9.090842086712007e-06, + "loss": 3.8492, + "step": 2498560 + }, + { + "epoch": 0.02, + "learning_rate": 9.08247251800522e-06, + "loss": 3.8441, + "step": 2499072 + }, + { + "epoch": 0.02, + "learning_rate": 9.0740865704947e-06, + "loss": 3.8539, + "step": 2499584 + }, + { + "epoch": 0.02, + "learning_rate": 9.065700622984178e-06, + "loss": 3.8485, + "step": 2500096 + }, + { + "epoch": 0.02, + "learning_rate": 9.05731467547366e-06, + "loss": 3.8496, + "step": 2500608 + }, + { + "epoch": 0.02, + "learning_rate": 9.04894510676687e-06, + "loss": 3.8621, + "step": 2501120 + }, + { + "epoch": 0.02, + "learning_rate": 9.04055915925635e-06, + "loss": 3.858, + "step": 2501632 + }, + { + "epoch": 0.02, + "learning_rate": 9.03217321174583e-06, + "loss": 3.8527, + "step": 2502144 + }, + { + "epoch": 0.02, + "learning_rate": 9.02378726423531e-06, + "loss": 3.8457, + "step": 2502656 + }, + { + "epoch": 0.02, + "learning_rate": 9.015417695528521e-06, + "loss": 3.8523, + "step": 2503168 + }, + { + "epoch": 0.02, + "learning_rate": 9.007031748018001e-06, + "loss": 3.8474, + "step": 2503680 + }, + { + "epoch": 0.02, + "learning_rate": 8.998645800507481e-06, + "loss": 3.8473, + "step": 2504192 + }, + { + "epoch": 0.02, + "learning_rate": 8.990259852996961e-06, + "loss": 3.8623, + "step": 2504704 + }, + { + "epoch": 0.02, + "learning_rate": 8.981873905486443e-06, + "loss": 3.8451, + "step": 2505216 + }, + { + "epoch": 0.02, + "learning_rate": 8.97348795797592e-06, + "loss": 3.855, + "step": 2505728 + }, + { + "epoch": 0.02, + "learning_rate": 8.9651020104654e-06, + "loss": 3.841, + "step": 2506240 + }, + { + "epoch": 0.02, + "learning_rate": 8.95671606295488e-06, + "loss": 3.8453, + "step": 2506752 + }, + { + "epoch": 0.02, + "learning_rate": 8.948346494248092e-06, + "loss": 3.8547, + "step": 2507264 + }, + { + "epoch": 0.02, + "learning_rate": 8.939976925541304e-06, + "loss": 3.8471, + "step": 2507776 + }, + { + "epoch": 0.02, + "learning_rate": 8.931590978030784e-06, + "loss": 3.8413, + "step": 2508288 + }, + { + "epoch": 0.02, + "learning_rate": 8.923205030520264e-06, + "loss": 3.8687, + "step": 2508800 + }, + { + "epoch": 0.02, + "learning_rate": 8.914819083009742e-06, + "loss": 3.8545, + "step": 2509312 + }, + { + "epoch": 0.02, + "learning_rate": 8.906433135499224e-06, + "loss": 3.852, + "step": 2509824 + }, + { + "epoch": 0.02, + "learning_rate": 8.898047187988704e-06, + "loss": 3.8513, + "step": 2510336 + }, + { + "epoch": 0.02, + "learning_rate": 8.889661240478182e-06, + "loss": 3.852, + "step": 2510848 + }, + { + "epoch": 0.02, + "learning_rate": 8.881275292967662e-06, + "loss": 3.8588, + "step": 2511360 + }, + { + "epoch": 0.02, + "learning_rate": 8.872889345457144e-06, + "loss": 3.8529, + "step": 2511872 + }, + { + "epoch": 0.02, + "learning_rate": 8.864519776750354e-06, + "loss": 3.8489, + "step": 2512384 + }, + { + "epoch": 0.02, + "learning_rate": 8.856150208043565e-06, + "loss": 3.8625, + "step": 2512896 + }, + { + "epoch": 0.02, + "learning_rate": 8.847764260533045e-06, + "loss": 3.8605, + "step": 2513408 + }, + { + "epoch": 0.02, + "learning_rate": 8.839378313022525e-06, + "loss": 3.855, + "step": 2513920 + }, + { + "epoch": 0.02, + "learning_rate": 8.830992365512005e-06, + "loss": 3.8536, + "step": 2514432 + }, + { + "epoch": 0.02, + "learning_rate": 8.822622796805216e-06, + "loss": 3.8576, + "step": 2514944 + }, + { + "epoch": 0.02, + "learning_rate": 8.814253228098428e-06, + "loss": 3.8567, + "step": 2515456 + }, + { + "epoch": 0.02, + "learning_rate": 8.805867280587908e-06, + "loss": 3.8563, + "step": 2515968 + }, + { + "epoch": 0.02, + "learning_rate": 8.797481333077387e-06, + "loss": 3.8524, + "step": 2516480 + }, + { + "epoch": 0.02, + "learning_rate": 8.789095385566867e-06, + "loss": 3.853, + "step": 2516992 + }, + { + "epoch": 0.02, + "learning_rate": 8.780709438056348e-06, + "loss": 3.8591, + "step": 2517504 + }, + { + "epoch": 0.02, + "learning_rate": 8.772323490545828e-06, + "loss": 3.8454, + "step": 2518016 + }, + { + "epoch": 0.02, + "learning_rate": 8.763937543035306e-06, + "loss": 3.8493, + "step": 2518528 + }, + { + "epoch": 0.03, + "eval_loss": 3.9814047813415527, + "eval_runtime": 290.5338, + "eval_samples_per_second": 1313.414, + "eval_steps_per_second": 41.045, + "step": 2518560 + }, + { + "epoch": 1.0, + "learning_rate": 8.755551595524786e-06, + "loss": 3.8442, + "step": 2519040 + }, + { + "epoch": 1.0, + "learning_rate": 8.747165648014268e-06, + "loss": 3.846, + "step": 2519552 + }, + { + "epoch": 1.0, + "learning_rate": 8.738779700503746e-06, + "loss": 3.8668, + "step": 2520064 + }, + { + "epoch": 1.0, + "learning_rate": 8.730393752993226e-06, + "loss": 3.8603, + "step": 2520576 + }, + { + "epoch": 1.0, + "learning_rate": 8.722024184286439e-06, + "loss": 3.8568, + "step": 2521088 + }, + { + "epoch": 1.0, + "learning_rate": 8.713638236775919e-06, + "loss": 3.8527, + "step": 2521600 + }, + { + "epoch": 1.0, + "learning_rate": 8.705252289265397e-06, + "loss": 3.8529, + "step": 2522112 + }, + { + "epoch": 1.0, + "learning_rate": 8.696866341754879e-06, + "loss": 3.8444, + "step": 2522624 + }, + { + "epoch": 1.0, + "learning_rate": 8.688480394244359e-06, + "loss": 3.8605, + "step": 2523136 + }, + { + "epoch": 1.0, + "learning_rate": 8.680094446733837e-06, + "loss": 3.8562, + "step": 2523648 + }, + { + "epoch": 1.0, + "learning_rate": 8.671708499223317e-06, + "loss": 3.8581, + "step": 2524160 + }, + { + "epoch": 1.0, + "learning_rate": 8.663322551712798e-06, + "loss": 3.863, + "step": 2524672 + }, + { + "epoch": 1.0, + "learning_rate": 8.65495298300601e-06, + "loss": 3.8487, + "step": 2525184 + }, + { + "epoch": 1.0, + "learning_rate": 8.64656703549549e-06, + "loss": 3.8455, + "step": 2525696 + }, + { + "epoch": 1.0, + "learning_rate": 8.638181087984969e-06, + "loss": 3.8402, + "step": 2526208 + }, + { + "epoch": 1.0, + "learning_rate": 8.629795140474449e-06, + "loss": 3.8421, + "step": 2526720 + }, + { + "epoch": 1.0, + "learning_rate": 8.621409192963927e-06, + "loss": 3.8536, + "step": 2527232 + }, + { + "epoch": 1.0, + "learning_rate": 8.613023245453409e-06, + "loss": 3.8434, + "step": 2527744 + }, + { + "epoch": 1.0, + "learning_rate": 8.604637297942889e-06, + "loss": 3.8517, + "step": 2528256 + }, + { + "epoch": 1.0, + "learning_rate": 8.596251350432367e-06, + "loss": 3.8731, + "step": 2528768 + }, + { + "epoch": 1.0, + "learning_rate": 8.58788178172558e-06, + "loss": 3.8541, + "step": 2529280 + }, + { + "epoch": 1.0, + "learning_rate": 8.57951221301879e-06, + "loss": 3.8586, + "step": 2529792 + }, + { + "epoch": 1.0, + "learning_rate": 8.57112626550827e-06, + "loss": 3.8516, + "step": 2530304 + }, + { + "epoch": 1.0, + "learning_rate": 8.56274031799775e-06, + "loss": 3.8653, + "step": 2530816 + }, + { + "epoch": 1.0, + "learning_rate": 8.55435437048723e-06, + "loss": 3.8475, + "step": 2531328 + }, + { + "epoch": 1.0, + "learning_rate": 8.54596842297671e-06, + "loss": 3.8512, + "step": 2531840 + }, + { + "epoch": 1.0, + "learning_rate": 8.53758247546619e-06, + "loss": 3.845, + "step": 2532352 + }, + { + "epoch": 1.0, + "learning_rate": 8.529212906759401e-06, + "loss": 3.8536, + "step": 2532864 + }, + { + "epoch": 1.0, + "learning_rate": 8.520826959248881e-06, + "loss": 3.8461, + "step": 2533376 + }, + { + "epoch": 1.01, + "learning_rate": 8.512441011738363e-06, + "loss": 3.8473, + "step": 2533888 + }, + { + "epoch": 1.01, + "learning_rate": 8.504055064227841e-06, + "loss": 3.8528, + "step": 2534400 + }, + { + "epoch": 1.01, + "learning_rate": 8.495669116717321e-06, + "loss": 3.8616, + "step": 2534912 + }, + { + "epoch": 1.01, + "learning_rate": 8.487299548010533e-06, + "loss": 3.8498, + "step": 2535424 + }, + { + "epoch": 1.01, + "learning_rate": 8.478913600500013e-06, + "loss": 3.8578, + "step": 2535936 + }, + { + "epoch": 1.01, + "learning_rate": 8.470544031793224e-06, + "loss": 3.851, + "step": 2536448 + }, + { + "epoch": 1.01, + "learning_rate": 8.462158084282704e-06, + "loss": 3.862, + "step": 2536960 + }, + { + "epoch": 1.01, + "learning_rate": 8.453772136772184e-06, + "loss": 3.8382, + "step": 2537472 + }, + { + "epoch": 1.01, + "learning_rate": 8.445386189261664e-06, + "loss": 3.8543, + "step": 2537984 + }, + { + "epoch": 1.01, + "learning_rate": 8.437016620554875e-06, + "loss": 3.835, + "step": 2538496 + }, + { + "epoch": 1.01, + "learning_rate": 8.428630673044355e-06, + "loss": 3.8567, + "step": 2539008 + }, + { + "epoch": 1.01, + "learning_rate": 8.420244725533835e-06, + "loss": 3.8467, + "step": 2539520 + }, + { + "epoch": 1.01, + "learning_rate": 8.411858778023315e-06, + "loss": 3.8607, + "step": 2540032 + }, + { + "epoch": 1.01, + "learning_rate": 8.403472830512795e-06, + "loss": 3.8419, + "step": 2540544 + }, + { + "epoch": 1.01, + "learning_rate": 8.395086883002275e-06, + "loss": 3.8579, + "step": 2541056 + }, + { + "epoch": 1.01, + "learning_rate": 8.386700935491755e-06, + "loss": 3.8579, + "step": 2541568 + }, + { + "epoch": 1.01, + "learning_rate": 8.378314987981234e-06, + "loss": 3.8568, + "step": 2542080 + }, + { + "epoch": 1.01, + "learning_rate": 8.369929040470714e-06, + "loss": 3.8591, + "step": 2542592 + }, + { + "epoch": 1.01, + "learning_rate": 8.361543092960194e-06, + "loss": 3.8332, + "step": 2543104 + }, + { + "epoch": 1.01, + "learning_rate": 8.353173524253405e-06, + "loss": 3.8457, + "step": 2543616 + }, + { + "epoch": 1.01, + "learning_rate": 8.344787576742885e-06, + "loss": 3.8579, + "step": 2544128 + }, + { + "epoch": 1.01, + "learning_rate": 8.336401629232365e-06, + "loss": 3.8557, + "step": 2544640 + }, + { + "epoch": 1.01, + "learning_rate": 8.328015681721845e-06, + "loss": 3.8485, + "step": 2545152 + }, + { + "epoch": 1.01, + "learning_rate": 8.319629734211325e-06, + "loss": 3.8474, + "step": 2545664 + }, + { + "epoch": 1.01, + "learning_rate": 8.311243786700805e-06, + "loss": 3.8447, + "step": 2546176 + }, + { + "epoch": 1.01, + "learning_rate": 8.302857839190285e-06, + "loss": 3.8362, + "step": 2546688 + }, + { + "epoch": 1.01, + "learning_rate": 8.294471891679765e-06, + "loss": 3.8531, + "step": 2547200 + }, + { + "epoch": 1.01, + "learning_rate": 8.286085944169245e-06, + "loss": 3.838, + "step": 2547712 + }, + { + "epoch": 1.01, + "learning_rate": 8.277699996658725e-06, + "loss": 3.8494, + "step": 2548224 + }, + { + "epoch": 1.01, + "learning_rate": 8.269314049148203e-06, + "loss": 3.8586, + "step": 2548736 + }, + { + "epoch": 1.01, + "learning_rate": 8.260928101637685e-06, + "loss": 3.8419, + "step": 2549248 + }, + { + "epoch": 1.01, + "learning_rate": 8.252574911734626e-06, + "loss": 3.8419, + "step": 2549760 + }, + { + "epoch": 1.01, + "learning_rate": 8.244188964224108e-06, + "loss": 3.8445, + "step": 2550272 + }, + { + "epoch": 1.01, + "learning_rate": 8.235803016713586e-06, + "loss": 3.8367, + "step": 2550784 + }, + { + "epoch": 1.01, + "learning_rate": 8.227417069203066e-06, + "loss": 3.8391, + "step": 2551296 + }, + { + "epoch": 1.01, + "learning_rate": 8.219031121692546e-06, + "loss": 3.858, + "step": 2551808 + }, + { + "epoch": 1.01, + "learning_rate": 8.210645174182026e-06, + "loss": 3.846, + "step": 2552320 + }, + { + "epoch": 1.01, + "learning_rate": 8.202275605475237e-06, + "loss": 3.844, + "step": 2552832 + }, + { + "epoch": 1.01, + "learning_rate": 8.193889657964719e-06, + "loss": 3.8408, + "step": 2553344 + }, + { + "epoch": 1.01, + "learning_rate": 8.185503710454198e-06, + "loss": 3.8426, + "step": 2553856 + }, + { + "epoch": 1.01, + "learning_rate": 8.177117762943677e-06, + "loss": 3.8546, + "step": 2554368 + }, + { + "epoch": 1.01, + "learning_rate": 8.168731815433157e-06, + "loss": 3.8511, + "step": 2554880 + }, + { + "epoch": 1.01, + "learning_rate": 8.16036224672637e-06, + "loss": 3.845, + "step": 2555392 + }, + { + "epoch": 1.01, + "learning_rate": 8.151976299215849e-06, + "loss": 3.8568, + "step": 2555904 + }, + { + "epoch": 1.01, + "learning_rate": 8.143590351705329e-06, + "loss": 3.8592, + "step": 2556416 + }, + { + "epoch": 1.01, + "learning_rate": 8.135204404194809e-06, + "loss": 3.8414, + "step": 2556928 + }, + { + "epoch": 1.01, + "learning_rate": 8.126818456684289e-06, + "loss": 3.8514, + "step": 2557440 + }, + { + "epoch": 1.01, + "learning_rate": 8.1184488879775e-06, + "loss": 3.8503, + "step": 2557952 + }, + { + "epoch": 1.01, + "learning_rate": 8.11006294046698e-06, + "loss": 3.8502, + "step": 2558464 + }, + { + "epoch": 1.01, + "learning_rate": 8.10167699295646e-06, + "loss": 3.8444, + "step": 2558976 + }, + { + "epoch": 1.01, + "learning_rate": 8.09329104544594e-06, + "loss": 3.8443, + "step": 2559488 + }, + { + "epoch": 1.01, + "learning_rate": 8.08490509793542e-06, + "loss": 3.8615, + "step": 2560000 + }, + { + "epoch": 1.01, + "learning_rate": 8.0765191504249e-06, + "loss": 3.8565, + "step": 2560512 + }, + { + "epoch": 1.01, + "learning_rate": 8.06813320291438e-06, + "loss": 3.8484, + "step": 2561024 + }, + { + "epoch": 1.01, + "learning_rate": 8.05976363420759e-06, + "loss": 3.826, + "step": 2561536 + }, + { + "epoch": 1.01, + "learning_rate": 8.05137768669707e-06, + "loss": 3.8428, + "step": 2562048 + }, + { + "epoch": 1.01, + "learning_rate": 8.04299173918655e-06, + "loss": 3.852, + "step": 2562560 + }, + { + "epoch": 1.01, + "learning_rate": 8.03460579167603e-06, + "loss": 3.8502, + "step": 2563072 + }, + { + "epoch": 1.01, + "learning_rate": 8.02621984416551e-06, + "loss": 3.8463, + "step": 2563584 + }, + { + "epoch": 1.01, + "learning_rate": 8.017850275458721e-06, + "loss": 3.847, + "step": 2564096 + }, + { + "epoch": 1.02, + "learning_rate": 8.009464327948203e-06, + "loss": 3.8506, + "step": 2564608 + }, + { + "epoch": 1.02, + "learning_rate": 8.001094759241413e-06, + "loss": 3.8462, + "step": 2565120 + }, + { + "epoch": 1.02, + "learning_rate": 7.992708811730892e-06, + "loss": 3.8406, + "step": 2565632 + }, + { + "epoch": 1.02, + "learning_rate": 7.984322864220373e-06, + "loss": 3.857, + "step": 2566144 + }, + { + "epoch": 1.02, + "learning_rate": 7.975936916709853e-06, + "loss": 3.839, + "step": 2566656 + }, + { + "epoch": 1.02, + "learning_rate": 7.967550969199331e-06, + "loss": 3.8604, + "step": 2567168 + }, + { + "epoch": 1.02, + "learning_rate": 7.959165021688811e-06, + "loss": 3.8534, + "step": 2567680 + }, + { + "epoch": 1.02, + "learning_rate": 7.950779074178293e-06, + "loss": 3.8356, + "step": 2568192 + }, + { + "epoch": 1.02, + "learning_rate": 7.942393126667771e-06, + "loss": 3.8499, + "step": 2568704 + }, + { + "epoch": 1.02, + "learning_rate": 7.934007179157251e-06, + "loss": 3.8493, + "step": 2569216 + }, + { + "epoch": 1.02, + "learning_rate": 7.925621231646731e-06, + "loss": 3.8567, + "step": 2569728 + }, + { + "epoch": 1.02, + "learning_rate": 7.917251662939944e-06, + "loss": 3.8495, + "step": 2570240 + }, + { + "epoch": 1.02, + "learning_rate": 7.908865715429422e-06, + "loss": 3.8473, + "step": 2570752 + }, + { + "epoch": 1.02, + "learning_rate": 7.900479767918904e-06, + "loss": 3.8412, + "step": 2571264 + }, + { + "epoch": 1.02, + "learning_rate": 7.892093820408384e-06, + "loss": 3.8551, + "step": 2571776 + }, + { + "epoch": 1.02, + "learning_rate": 7.883707872897862e-06, + "loss": 3.8377, + "step": 2572288 + }, + { + "epoch": 1.02, + "learning_rate": 7.875321925387342e-06, + "loss": 3.8441, + "step": 2572800 + }, + { + "epoch": 1.02, + "learning_rate": 7.866935977876823e-06, + "loss": 3.8508, + "step": 2573312 + }, + { + "epoch": 1.02, + "learning_rate": 7.858566409170034e-06, + "loss": 3.8482, + "step": 2573824 + }, + { + "epoch": 1.02, + "learning_rate": 7.850180461659514e-06, + "loss": 3.8354, + "step": 2574336 + }, + { + "epoch": 1.02, + "learning_rate": 7.841794514148994e-06, + "loss": 3.849, + "step": 2574848 + }, + { + "epoch": 1.02, + "learning_rate": 7.833408566638474e-06, + "loss": 3.8421, + "step": 2575360 + }, + { + "epoch": 1.02, + "learning_rate": 7.825038997931685e-06, + "loss": 3.8477, + "step": 2575872 + }, + { + "epoch": 1.02, + "learning_rate": 7.816653050421165e-06, + "loss": 3.8482, + "step": 2576384 + }, + { + "epoch": 1.02, + "learning_rate": 7.808267102910645e-06, + "loss": 3.8422, + "step": 2576896 + }, + { + "epoch": 1.02, + "learning_rate": 7.799881155400125e-06, + "loss": 3.8648, + "step": 2577408 + }, + { + "epoch": 1.02, + "learning_rate": 7.791495207889605e-06, + "loss": 3.8563, + "step": 2577920 + }, + { + "epoch": 1.02, + "learning_rate": 7.783125639182816e-06, + "loss": 3.852, + "step": 2578432 + }, + { + "epoch": 1.02, + "learning_rate": 7.774739691672296e-06, + "loss": 3.842, + "step": 2578944 + }, + { + "epoch": 1.02, + "learning_rate": 7.766353744161777e-06, + "loss": 3.8498, + "step": 2579456 + }, + { + "epoch": 1.02, + "learning_rate": 7.757967796651255e-06, + "loss": 3.8461, + "step": 2579968 + }, + { + "epoch": 1.02, + "learning_rate": 7.749581849140735e-06, + "loss": 3.8402, + "step": 2580480 + }, + { + "epoch": 1.02, + "learning_rate": 7.741195901630215e-06, + "loss": 3.8596, + "step": 2580992 + }, + { + "epoch": 1.02, + "learning_rate": 7.732809954119695e-06, + "loss": 3.8457, + "step": 2581504 + }, + { + "epoch": 1.02, + "learning_rate": 7.724424006609175e-06, + "loss": 3.8461, + "step": 2582016 + }, + { + "epoch": 1.02, + "learning_rate": 7.716038059098655e-06, + "loss": 3.8436, + "step": 2582528 + }, + { + "epoch": 1.02, + "learning_rate": 7.707668490391866e-06, + "loss": 3.8425, + "step": 2583040 + }, + { + "epoch": 1.02, + "learning_rate": 7.699282542881346e-06, + "loss": 3.8466, + "step": 2583552 + }, + { + "epoch": 1.02, + "learning_rate": 7.690912974174558e-06, + "loss": 3.8465, + "step": 2584064 + }, + { + "epoch": 1.02, + "learning_rate": 7.682527026664038e-06, + "loss": 3.8363, + "step": 2584576 + }, + { + "epoch": 1.02, + "learning_rate": 7.674141079153517e-06, + "loss": 3.8668, + "step": 2585088 + }, + { + "epoch": 1.02, + "learning_rate": 7.665755131642997e-06, + "loss": 3.8572, + "step": 2585600 + }, + { + "epoch": 1.02, + "learning_rate": 7.657369184132478e-06, + "loss": 3.8493, + "step": 2586112 + }, + { + "epoch": 1.02, + "learning_rate": 7.648983236621957e-06, + "loss": 3.848, + "step": 2586624 + }, + { + "epoch": 1.02, + "learning_rate": 7.640597289111436e-06, + "loss": 3.8443, + "step": 2587136 + }, + { + "epoch": 1.02, + "learning_rate": 7.632211341600916e-06, + "loss": 3.8587, + "step": 2587648 + }, + { + "epoch": 1.02, + "learning_rate": 7.623825394090397e-06, + "loss": 3.8519, + "step": 2588160 + }, + { + "epoch": 1.02, + "learning_rate": 7.615455825383608e-06, + "loss": 3.8454, + "step": 2588672 + }, + { + "epoch": 1.02, + "learning_rate": 7.60708625667682e-06, + "loss": 3.8623, + "step": 2589184 + }, + { + "epoch": 1.02, + "learning_rate": 7.5987003091663e-06, + "loss": 3.8524, + "step": 2589696 + }, + { + "epoch": 1.02, + "learning_rate": 7.590330740459511e-06, + "loss": 3.8559, + "step": 2590208 + }, + { + "epoch": 1.02, + "learning_rate": 7.58194479294899e-06, + "loss": 3.8493, + "step": 2590720 + }, + { + "epoch": 1.02, + "learning_rate": 7.57355884543847e-06, + "loss": 3.857, + "step": 2591232 + }, + { + "epoch": 1.02, + "learning_rate": 7.565172897927951e-06, + "loss": 3.8522, + "step": 2591744 + }, + { + "epoch": 1.02, + "learning_rate": 7.55678695041743e-06, + "loss": 3.8513, + "step": 2592256 + }, + { + "epoch": 1.02, + "learning_rate": 7.54840100290691e-06, + "loss": 3.8511, + "step": 2592768 + }, + { + "epoch": 1.02, + "learning_rate": 7.54001505539639e-06, + "loss": 3.8511, + "step": 2593280 + }, + { + "epoch": 1.02, + "learning_rate": 7.531629107885871e-06, + "loss": 3.8543, + "step": 2593792 + }, + { + "epoch": 1.02, + "learning_rate": 7.523259539179081e-06, + "loss": 3.8433, + "step": 2594304 + }, + { + "epoch": 1.02, + "learning_rate": 7.514873591668562e-06, + "loss": 3.8468, + "step": 2594816 + }, + { + "epoch": 1.03, + "eval_loss": 3.9806466102600098, + "eval_runtime": 289.4514, + "eval_samples_per_second": 1318.325, + "eval_steps_per_second": 41.199, + "step": 2594880 + }, + { + "epoch": 0.0, + "learning_rate": 7.506487644158042e-06, + "loss": 3.839, + "step": 2595328 + }, + { + "epoch": 0.0, + "learning_rate": 7.498101696647521e-06, + "loss": 3.844, + "step": 2595840 + }, + { + "epoch": 0.0, + "learning_rate": 7.489715749137001e-06, + "loss": 3.8618, + "step": 2596352 + }, + { + "epoch": 0.0, + "learning_rate": 7.4813298016264815e-06, + "loss": 3.8594, + "step": 2596864 + }, + { + "epoch": 0.0, + "learning_rate": 7.4729438541159615e-06, + "loss": 3.854, + "step": 2597376 + }, + { + "epoch": 0.0, + "learning_rate": 7.4645579066054406e-06, + "loss": 3.8485, + "step": 2597888 + }, + { + "epoch": 0.0, + "learning_rate": 7.4561719590949205e-06, + "loss": 3.8511, + "step": 2598400 + }, + { + "epoch": 0.0, + "learning_rate": 7.447786011584401e-06, + "loss": 3.8395, + "step": 2598912 + }, + { + "epoch": 0.0, + "learning_rate": 7.4394000640738804e-06, + "loss": 3.8594, + "step": 2599424 + }, + { + "epoch": 0.0, + "learning_rate": 7.43101411656336e-06, + "loss": 3.8519, + "step": 2599936 + }, + { + "epoch": 0.0, + "learning_rate": 7.42262816905284e-06, + "loss": 3.8535, + "step": 2600448 + }, + { + "epoch": 0.0, + "learning_rate": 7.4142422215423195e-06, + "loss": 3.858, + "step": 2600960 + }, + { + "epoch": 0.0, + "learning_rate": 7.405872652835531e-06, + "loss": 3.8441, + "step": 2601472 + }, + { + "epoch": 0.0, + "learning_rate": 7.397486705325012e-06, + "loss": 3.8457, + "step": 2601984 + }, + { + "epoch": 0.0, + "learning_rate": 7.389100757814492e-06, + "loss": 3.8413, + "step": 2602496 + }, + { + "epoch": 0.0, + "learning_rate": 7.380714810303971e-06, + "loss": 3.8415, + "step": 2603008 + }, + { + "epoch": 0.0, + "learning_rate": 7.372328862793451e-06, + "loss": 3.8473, + "step": 2603520 + }, + { + "epoch": 0.0, + "learning_rate": 7.363942915282932e-06, + "loss": 3.8419, + "step": 2604032 + }, + { + "epoch": 0.0, + "learning_rate": 7.355573346576143e-06, + "loss": 3.8483, + "step": 2604544 + }, + { + "epoch": 0.0, + "learning_rate": 7.347187399065622e-06, + "loss": 3.8727, + "step": 2605056 + }, + { + "epoch": 0.0, + "learning_rate": 7.338801451555102e-06, + "loss": 3.8498, + "step": 2605568 + }, + { + "epoch": 0.0, + "learning_rate": 7.330415504044582e-06, + "loss": 3.8521, + "step": 2606080 + }, + { + "epoch": 0.0, + "learning_rate": 7.3220295565340615e-06, + "loss": 3.8543, + "step": 2606592 + }, + { + "epoch": 0.0, + "learning_rate": 7.313643609023542e-06, + "loss": 3.8582, + "step": 2607104 + }, + { + "epoch": 0.0, + "learning_rate": 7.305257661513022e-06, + "loss": 3.844, + "step": 2607616 + }, + { + "epoch": 0.0, + "learning_rate": 7.296871714002501e-06, + "loss": 3.8527, + "step": 2608128 + }, + { + "epoch": 0.0, + "learning_rate": 7.288485766491981e-06, + "loss": 3.8427, + "step": 2608640 + }, + { + "epoch": 0.0, + "learning_rate": 7.280116197785193e-06, + "loss": 3.8466, + "step": 2609152 + }, + { + "epoch": 0.0, + "learning_rate": 7.271730250274674e-06, + "loss": 3.8413, + "step": 2609664 + }, + { + "epoch": 0.01, + "learning_rate": 7.263344302764152e-06, + "loss": 3.8451, + "step": 2610176 + }, + { + "epoch": 0.01, + "learning_rate": 7.254958355253633e-06, + "loss": 3.8486, + "step": 2610688 + }, + { + "epoch": 0.01, + "learning_rate": 7.246572407743113e-06, + "loss": 3.8572, + "step": 2611200 + }, + { + "epoch": 0.01, + "learning_rate": 7.238186460232592e-06, + "loss": 3.8488, + "step": 2611712 + }, + { + "epoch": 0.01, + "learning_rate": 7.229800512722072e-06, + "loss": 3.8573, + "step": 2612224 + }, + { + "epoch": 0.01, + "learning_rate": 7.2214309440152835e-06, + "loss": 3.8423, + "step": 2612736 + }, + { + "epoch": 0.01, + "learning_rate": 7.213044996504764e-06, + "loss": 3.8623, + "step": 2613248 + }, + { + "epoch": 0.01, + "learning_rate": 7.204675427797974e-06, + "loss": 3.8335, + "step": 2613760 + }, + { + "epoch": 0.01, + "learning_rate": 7.196289480287455e-06, + "loss": 3.8545, + "step": 2614272 + }, + { + "epoch": 0.01, + "learning_rate": 7.187903532776935e-06, + "loss": 3.832, + "step": 2614784 + }, + { + "epoch": 0.01, + "learning_rate": 7.179517585266416e-06, + "loss": 3.855, + "step": 2615296 + }, + { + "epoch": 0.01, + "learning_rate": 7.171131637755894e-06, + "loss": 3.8435, + "step": 2615808 + }, + { + "epoch": 0.01, + "learning_rate": 7.162745690245375e-06, + "loss": 3.8602, + "step": 2616320 + }, + { + "epoch": 0.01, + "learning_rate": 7.154359742734855e-06, + "loss": 3.8414, + "step": 2616832 + }, + { + "epoch": 0.01, + "learning_rate": 7.145973795224334e-06, + "loss": 3.8535, + "step": 2617344 + }, + { + "epoch": 0.01, + "learning_rate": 7.137587847713814e-06, + "loss": 3.8551, + "step": 2617856 + }, + { + "epoch": 0.01, + "learning_rate": 7.129201900203295e-06, + "loss": 3.8555, + "step": 2618368 + }, + { + "epoch": 0.01, + "learning_rate": 7.120832331496505e-06, + "loss": 3.8544, + "step": 2618880 + }, + { + "epoch": 0.01, + "learning_rate": 7.112446383985985e-06, + "loss": 3.8354, + "step": 2619392 + }, + { + "epoch": 0.01, + "learning_rate": 7.104060436475465e-06, + "loss": 3.8388, + "step": 2619904 + }, + { + "epoch": 0.01, + "learning_rate": 7.095674488964945e-06, + "loss": 3.8573, + "step": 2620416 + }, + { + "epoch": 0.01, + "learning_rate": 7.0872885414544244e-06, + "loss": 3.8523, + "step": 2620928 + }, + { + "epoch": 0.01, + "learning_rate": 7.078902593943905e-06, + "loss": 3.8453, + "step": 2621440 + }, + { + "epoch": 0.01, + "learning_rate": 7.070516646433385e-06, + "loss": 3.8454, + "step": 2621952 + }, + { + "epoch": 0.01, + "learning_rate": 7.062147077726595e-06, + "loss": 3.8435, + "step": 2622464 + }, + { + "epoch": 0.01, + "learning_rate": 7.053761130216076e-06, + "loss": 3.8329, + "step": 2622976 + }, + { + "epoch": 0.01, + "learning_rate": 7.045375182705556e-06, + "loss": 3.8456, + "step": 2623488 + }, + { + "epoch": 0.01, + "learning_rate": 7.036989235195037e-06, + "loss": 3.8356, + "step": 2624000 + }, + { + "epoch": 0.01, + "learning_rate": 7.028603287684515e-06, + "loss": 3.8461, + "step": 2624512 + }, + { + "epoch": 0.01, + "learning_rate": 7.020217340173996e-06, + "loss": 3.8558, + "step": 2625024 + }, + { + "epoch": 0.01, + "learning_rate": 7.011831392663476e-06, + "loss": 3.8389, + "step": 2625536 + }, + { + "epoch": 0.01, + "learning_rate": 7.003445445152955e-06, + "loss": 3.84, + "step": 2626048 + }, + { + "epoch": 0.01, + "learning_rate": 6.9950758764461665e-06, + "loss": 3.8452, + "step": 2626560 + }, + { + "epoch": 0.01, + "learning_rate": 6.986689928935647e-06, + "loss": 3.8319, + "step": 2627072 + }, + { + "epoch": 0.01, + "learning_rate": 6.978303981425127e-06, + "loss": 3.8325, + "step": 2627584 + }, + { + "epoch": 0.01, + "learning_rate": 6.969918033914606e-06, + "loss": 3.8555, + "step": 2628096 + }, + { + "epoch": 0.01, + "learning_rate": 6.961548465207818e-06, + "loss": 3.8455, + "step": 2628608 + }, + { + "epoch": 0.01, + "learning_rate": 6.953162517697298e-06, + "loss": 3.8394, + "step": 2629120 + }, + { + "epoch": 0.01, + "learning_rate": 6.944776570186777e-06, + "loss": 3.8376, + "step": 2629632 + }, + { + "epoch": 0.01, + "learning_rate": 6.936390622676257e-06, + "loss": 3.8444, + "step": 2630144 + }, + { + "epoch": 0.01, + "learning_rate": 6.928021053969469e-06, + "loss": 3.8512, + "step": 2630656 + }, + { + "epoch": 0.01, + "learning_rate": 6.919635106458949e-06, + "loss": 3.8521, + "step": 2631168 + }, + { + "epoch": 0.01, + "learning_rate": 6.9112491589484285e-06, + "loss": 3.842, + "step": 2631680 + }, + { + "epoch": 0.01, + "learning_rate": 6.9028632114379085e-06, + "loss": 3.8528, + "step": 2632192 + }, + { + "epoch": 0.01, + "learning_rate": 6.8944772639273884e-06, + "loss": 3.8521, + "step": 2632704 + }, + { + "epoch": 0.01, + "learning_rate": 6.886107695220601e-06, + "loss": 3.8415, + "step": 2633216 + }, + { + "epoch": 0.01, + "learning_rate": 6.877721747710079e-06, + "loss": 3.8452, + "step": 2633728 + }, + { + "epoch": 0.01, + "learning_rate": 6.86933580019956e-06, + "loss": 3.8501, + "step": 2634240 + }, + { + "epoch": 0.01, + "learning_rate": 6.86094985268904e-06, + "loss": 3.8465, + "step": 2634752 + }, + { + "epoch": 0.01, + "learning_rate": 6.852563905178519e-06, + "loss": 3.843, + "step": 2635264 + }, + { + "epoch": 0.01, + "learning_rate": 6.844177957667999e-06, + "loss": 3.8416, + "step": 2635776 + }, + { + "epoch": 0.01, + "learning_rate": 6.835808388961211e-06, + "loss": 3.8554, + "step": 2636288 + }, + { + "epoch": 0.01, + "learning_rate": 6.8274224414506914e-06, + "loss": 3.8565, + "step": 2636800 + }, + { + "epoch": 0.01, + "learning_rate": 6.8190364939401706e-06, + "loss": 3.8438, + "step": 2637312 + }, + { + "epoch": 0.01, + "learning_rate": 6.810666925233382e-06, + "loss": 3.8287, + "step": 2637824 + }, + { + "epoch": 0.01, + "learning_rate": 6.802280977722862e-06, + "loss": 3.8375, + "step": 2638336 + }, + { + "epoch": 0.01, + "learning_rate": 6.793895030212341e-06, + "loss": 3.8467, + "step": 2638848 + }, + { + "epoch": 0.01, + "learning_rate": 6.785509082701821e-06, + "loss": 3.8495, + "step": 2639360 + }, + { + "epoch": 0.01, + "learning_rate": 6.777123135191302e-06, + "loss": 3.8418, + "step": 2639872 + }, + { + "epoch": 0.01, + "learning_rate": 6.768737187680782e-06, + "loss": 3.8415, + "step": 2640384 + }, + { + "epoch": 0.02, + "learning_rate": 6.760351240170261e-06, + "loss": 3.8512, + "step": 2640896 + }, + { + "epoch": 0.02, + "learning_rate": 6.751965292659741e-06, + "loss": 3.8387, + "step": 2641408 + }, + { + "epoch": 0.02, + "learning_rate": 6.743579345149222e-06, + "loss": 3.8391, + "step": 2641920 + }, + { + "epoch": 0.02, + "learning_rate": 6.7351933976387e-06, + "loss": 3.8489, + "step": 2642432 + }, + { + "epoch": 0.02, + "learning_rate": 6.726807450128181e-06, + "loss": 3.8395, + "step": 2642944 + }, + { + "epoch": 0.02, + "learning_rate": 6.7184378814213925e-06, + "loss": 3.8559, + "step": 2643456 + }, + { + "epoch": 0.02, + "learning_rate": 6.7100519339108725e-06, + "loss": 3.8467, + "step": 2643968 + }, + { + "epoch": 0.02, + "learning_rate": 6.701665986400352e-06, + "loss": 3.8336, + "step": 2644480 + }, + { + "epoch": 0.02, + "learning_rate": 6.693280038889832e-06, + "loss": 3.8466, + "step": 2644992 + }, + { + "epoch": 0.02, + "learning_rate": 6.684894091379312e-06, + "loss": 3.8431, + "step": 2645504 + }, + { + "epoch": 0.02, + "learning_rate": 6.676524522672522e-06, + "loss": 3.8583, + "step": 2646016 + }, + { + "epoch": 0.02, + "learning_rate": 6.668138575162003e-06, + "loss": 3.8505, + "step": 2646528 + }, + { + "epoch": 0.02, + "learning_rate": 6.659752627651483e-06, + "loss": 3.8426, + "step": 2647040 + }, + { + "epoch": 0.02, + "learning_rate": 6.651366680140964e-06, + "loss": 3.835, + "step": 2647552 + }, + { + "epoch": 0.02, + "learning_rate": 6.642980732630442e-06, + "loss": 3.8516, + "step": 2648064 + }, + { + "epoch": 0.02, + "learning_rate": 6.634594785119923e-06, + "loss": 3.8337, + "step": 2648576 + }, + { + "epoch": 0.02, + "learning_rate": 6.626208837609403e-06, + "loss": 3.8444, + "step": 2649088 + }, + { + "epoch": 0.02, + "learning_rate": 6.617839268902614e-06, + "loss": 3.8457, + "step": 2649600 + }, + { + "epoch": 0.02, + "learning_rate": 6.609453321392094e-06, + "loss": 3.8443, + "step": 2650112 + }, + { + "epoch": 0.02, + "learning_rate": 6.601067373881574e-06, + "loss": 3.8306, + "step": 2650624 + }, + { + "epoch": 0.02, + "learning_rate": 6.592681426371053e-06, + "loss": 3.8527, + "step": 2651136 + }, + { + "epoch": 0.02, + "learning_rate": 6.5842954788605335e-06, + "loss": 3.8385, + "step": 2651648 + }, + { + "epoch": 0.02, + "learning_rate": 6.5759095313500135e-06, + "loss": 3.8397, + "step": 2652160 + }, + { + "epoch": 0.02, + "learning_rate": 6.567523583839494e-06, + "loss": 3.8475, + "step": 2652672 + }, + { + "epoch": 0.02, + "learning_rate": 6.5591376363289725e-06, + "loss": 3.8383, + "step": 2653184 + }, + { + "epoch": 0.02, + "learning_rate": 6.550768067622184e-06, + "loss": 3.8591, + "step": 2653696 + }, + { + "epoch": 0.02, + "learning_rate": 6.542398498915396e-06, + "loss": 3.8496, + "step": 2654208 + }, + { + "epoch": 0.02, + "learning_rate": 6.534012551404877e-06, + "loss": 3.8504, + "step": 2654720 + }, + { + "epoch": 0.02, + "learning_rate": 6.5256429826980865e-06, + "loss": 3.8384, + "step": 2655232 + }, + { + "epoch": 0.02, + "learning_rate": 6.517273413991298e-06, + "loss": 3.8487, + "step": 2655744 + }, + { + "epoch": 0.02, + "learning_rate": 6.508887466480779e-06, + "loss": 3.8485, + "step": 2656256 + }, + { + "epoch": 0.02, + "learning_rate": 6.500501518970259e-06, + "loss": 3.8344, + "step": 2656768 + }, + { + "epoch": 0.02, + "learning_rate": 6.492115571459738e-06, + "loss": 3.8541, + "step": 2657280 + }, + { + "epoch": 0.02, + "learning_rate": 6.483729623949218e-06, + "loss": 3.8441, + "step": 2657792 + }, + { + "epoch": 0.02, + "learning_rate": 6.475343676438699e-06, + "loss": 3.8439, + "step": 2658304 + }, + { + "epoch": 0.02, + "learning_rate": 6.466957728928177e-06, + "loss": 3.8455, + "step": 2658816 + }, + { + "epoch": 0.02, + "learning_rate": 6.458571781417658e-06, + "loss": 3.843, + "step": 2659328 + }, + { + "epoch": 0.02, + "learning_rate": 6.450185833907138e-06, + "loss": 3.8367, + "step": 2659840 + }, + { + "epoch": 0.02, + "learning_rate": 6.441799886396617e-06, + "loss": 3.8498, + "step": 2660352 + }, + { + "epoch": 0.02, + "learning_rate": 6.433413938886097e-06, + "loss": 3.8367, + "step": 2660864 + }, + { + "epoch": 0.02, + "learning_rate": 6.425027991375578e-06, + "loss": 3.8611, + "step": 2661376 + }, + { + "epoch": 0.02, + "learning_rate": 6.416642043865058e-06, + "loss": 3.8594, + "step": 2661888 + }, + { + "epoch": 0.02, + "learning_rate": 6.408256096354537e-06, + "loss": 3.8432, + "step": 2662400 + }, + { + "epoch": 0.02, + "learning_rate": 6.3998701488440176e-06, + "loss": 3.8424, + "step": 2662912 + }, + { + "epoch": 0.02, + "learning_rate": 6.3914842013334975e-06, + "loss": 3.8449, + "step": 2663424 + }, + { + "epoch": 0.02, + "learning_rate": 6.3831146326267075e-06, + "loss": 3.8521, + "step": 2663936 + }, + { + "epoch": 0.02, + "learning_rate": 6.374728685116188e-06, + "loss": 3.8503, + "step": 2664448 + }, + { + "epoch": 0.02, + "learning_rate": 6.366342737605668e-06, + "loss": 3.8455, + "step": 2664960 + }, + { + "epoch": 0.02, + "learning_rate": 6.357956790095149e-06, + "loss": 3.8562, + "step": 2665472 + }, + { + "epoch": 0.02, + "learning_rate": 6.349587221388359e-06, + "loss": 3.8503, + "step": 2665984 + }, + { + "epoch": 0.02, + "learning_rate": 6.341201273877839e-06, + "loss": 3.8544, + "step": 2666496 + }, + { + "epoch": 0.02, + "learning_rate": 6.33281532636732e-06, + "loss": 3.8455, + "step": 2667008 + }, + { + "epoch": 0.02, + "learning_rate": 6.324429378856799e-06, + "loss": 3.8582, + "step": 2667520 + }, + { + "epoch": 0.02, + "learning_rate": 6.3160598101500105e-06, + "loss": 3.8522, + "step": 2668032 + }, + { + "epoch": 0.02, + "learning_rate": 6.30767386263949e-06, + "loss": 3.845, + "step": 2668544 + }, + { + "epoch": 0.02, + "learning_rate": 6.29928791512897e-06, + "loss": 3.8509, + "step": 2669056 + }, + { + "epoch": 0.02, + "learning_rate": 6.2909019676184495e-06, + "loss": 3.8534, + "step": 2669568 + }, + { + "epoch": 0.02, + "learning_rate": 6.28251602010793e-06, + "loss": 3.848, + "step": 2670080 + }, + { + "epoch": 0.02, + "learning_rate": 6.274146451401142e-06, + "loss": 3.8371, + "step": 2670592 + }, + { + "epoch": 0.02, + "learning_rate": 6.265760503890622e-06, + "loss": 3.8419, + "step": 2671104 + }, + { + "epoch": 0.03, + "eval_loss": 3.97987961769104, + "eval_runtime": 287.9652, + "eval_samples_per_second": 1325.129, + "eval_steps_per_second": 41.411, + "step": 2671200 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.1037451129954456e+18, + "trial_name": null, + "trial_params": null +}