diff --git "a/checkpoint-1755360/trainer_state.json" "b/checkpoint-1755360/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1755360/trainer_state.json" @@ -0,0 +1,20777 @@ +{ + "best_metric": 3.9915289878845215, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/det-noun/lstm/1/checkpoints/checkpoint-1755360", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 1755360, + "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": 10.8218, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5559, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0623, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.9945, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.9491, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.9228, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.7544, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994131474623009e-05, + "loss": 6.6386, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993292879871958e-05, + "loss": 6.5403, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992454285120906e-05, + "loss": 6.4647, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.991615690369854e-05, + "loss": 6.4038, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990777095618801e-05, + "loss": 6.3434, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 6.2793, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 6.2147, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 6.1649, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 6.0996, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 6.0694, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 6.0129, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.9691, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.9354, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.8995, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 5.8604, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 5.8316, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.980713958606178e-05, + "loss": 5.7974, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798786396158716e-05, + "loss": 5.7765, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 5.7421, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 5.7218, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 5.6898, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 5.6659, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 5.6491, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 5.6283, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 5.6119, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 5.5908, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 5.574, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 5.5583, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.9706557352346724e-05, + "loss": 5.5421, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.9698171404836204e-05, + "loss": 5.5269, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.9689785457325684e-05, + "loss": 5.4978, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.9681399509815164e-05, + "loss": 5.4933, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 5.4545, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 5.4558, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965625804608733e-05, + "loss": 5.445, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 5.4419, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 5.4048, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 5.4049, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962273063484898e-05, + "loss": 5.3946, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 5.3861, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 5.3844, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 5.3497, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 5.3443, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958081727610012e-05, + "loss": 5.3484, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.95724313285896e-05, + "loss": 5.3376, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 5.3186, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 5.2987, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954728986486177e-05, + "loss": 5.3032, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953890391735125e-05, + "loss": 5.2832, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530517969840727e-05, + "loss": 5.3044, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 5.2538, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 5.2642, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.95053765061129e-05, + "loss": 5.253, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949699055860238e-05, + "loss": 5.2493, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948860461109186e-05, + "loss": 5.2461, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948021866358134e-05, + "loss": 5.2242, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947183271607082e-05, + "loss": 5.2066, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.94634467685603e-05, + "loss": 5.2112, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945506082104978e-05, + "loss": 5.2224, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944669125234299e-05, + "loss": 5.1926, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943830530483247e-05, + "loss": 5.1914, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942991935732195e-05, + "loss": 5.1679, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942153340981143e-05, + "loss": 5.1679, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941316384110464e-05, + "loss": 5.1796, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940477789359412e-05, + "loss": 5.1781, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.93963919460836e-05, + "loss": 5.1515, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.938800599857309e-05, + "loss": 5.1636, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379636429866296e-05, + "loss": 5.1613, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 5.1499, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362880913648985e-05, + "loss": 5.121, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354494966138465e-05, + "loss": 5.1278, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346109018627945e-05, + "loss": 5.1168, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337723071117425e-05, + "loss": 5.1111, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329337123606905e-05, + "loss": 5.109, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 5.1038, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 5.1043, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 5.0934, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.9295809712368554e-05, + "loss": 5.0764, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.9287423764858034e-05, + "loss": 5.0762, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.9279037817347514e-05, + "loss": 5.077, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.9270651869836994e-05, + "loss": 5.0674, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.9262265922326474e-05, + "loss": 5.0644, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.9253879974815954e-05, + "loss": 5.047, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.9245494027305433e-05, + "loss": 5.049, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923712445859864e-05, + "loss": 5.0377, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922873851108812e-05, + "loss": 5.0459, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92203525635776e-05, + "loss": 5.0333, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921196661606708e-05, + "loss": 5.0326, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920359704736029e-05, + "loss": 5.0295, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919521109984978e-05, + "loss": 5.0158, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918682515233926e-05, + "loss": 5.0114, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917843920482874e-05, + "loss": 5.004, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917005325731822e-05, + "loss": 4.9997, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916168368861143e-05, + "loss": 5.0019, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915329774110091e-05, + "loss": 4.9841, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914491179359039e-05, + "loss": 4.9896, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913652584607987e-05, + "loss": 4.9849, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912813989856935e-05, + "loss": 4.9712, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119770329862556e-05, + "loss": 4.9678, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111400761155765e-05, + "loss": 4.9627, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9103014813645245e-05, + "loss": 4.9615, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909462886613473e-05, + "loss": 4.953, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908624291862421e-05, + "loss": 4.9556, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907785697111369e-05, + "loss": 4.9472, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906947102360317e-05, + "loss": 4.9346, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906108507609265e-05, + "loss": 4.9471, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905269912858213e-05, + "loss": 4.9293, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904431318107161e-05, + "loss": 4.9351, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903592723356109e-05, + "loss": 4.9294, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.90275576648543e-05, + "loss": 4.9237, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901918809614751e-05, + "loss": 4.9188, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901080214863699e-05, + "loss": 4.9147, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900241620112647e-05, + "loss": 4.9282, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899403025361595e-05, + "loss": 4.9155, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.898564430610543e-05, + "loss": 4.8993, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.897725835859491e-05, + "loss": 4.8952, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968872411084396e-05, + "loss": 4.893, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.896048646357387e-05, + "loss": 4.8866, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952116894867085e-05, + "loss": 4.8806, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943730947356565e-05, + "loss": 4.8835, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.8701, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926975431139254e-05, + "loss": 4.8704, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918589483628734e-05, + "loss": 4.8653, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910203536118214e-05, + "loss": 4.8835, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890181758860769e-05, + "loss": 4.8765, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889343164109717e-05, + "loss": 4.8585, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888504569358665e-05, + "loss": 4.8557, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.8876659746076134e-05, + "loss": 4.8507, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886829017736934e-05, + "loss": 4.8606, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885990422985882e-05, + "loss": 4.8516, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515182823483e-05, + "loss": 4.8508, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884313233483778e-05, + "loss": 4.8454, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883474638732726e-05, + "loss": 4.8408, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882637681862047e-05, + "loss": 4.8373, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881799087110995e-05, + "loss": 4.8266, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880960492359943e-05, + "loss": 4.8327, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880121897608891e-05, + "loss": 4.8233, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879284940738212e-05, + "loss": 4.8119, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.87844634598716e-05, + "loss": 4.8241, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877607751236109e-05, + "loss": 4.8191, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876769156485057e-05, + "loss": 4.8206, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875930561734005e-05, + "loss": 4.8077, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875091966982953e-05, + "loss": 4.8048, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.769217491149902, + "eval_runtime": 294.8081, + "eval_samples_per_second": 1294.371, + "eval_steps_per_second": 40.45, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874255010112274e-05, + "loss": 4.8008, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873416415361222e-05, + "loss": 4.7957, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.87257782061017e-05, + "loss": 4.8091, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871739225859118e-05, + "loss": 4.7935, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709022689884386e-05, + "loss": 4.7987, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700636742373866e-05, + "loss": 4.7799, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692250794863346e-05, + "loss": 4.7946, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683864847352826e-05, + "loss": 4.777, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867549527864604e-05, + "loss": 4.7792, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866710933113552e-05, + "loss": 4.7773, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658723383625e-05, + "loss": 4.7844, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865033743611448e-05, + "loss": 4.778, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864196786740769e-05, + "loss": 4.7601, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.863358191989717e-05, + "loss": 4.7635, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862519597238665e-05, + "loss": 4.755, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861681002487613e-05, + "loss": 4.7554, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860842407736561e-05, + "loss": 4.757, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860003812985509e-05, + "loss": 4.7495, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.859165218234457e-05, + "loss": 4.7524, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858326623483405e-05, + "loss": 4.7629, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857488028732352e-05, + "loss": 4.749, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856649433981301e-05, + "loss": 4.747, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.855810839230249e-05, + "loss": 4.741, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.85497388235957e-05, + "loss": 4.7554, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541369254888915e-05, + "loss": 4.7237, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532983307378395e-05, + "loss": 4.7378, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524597359867875e-05, + "loss": 4.7252, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851621141235735e-05, + "loss": 4.7271, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850782546484683e-05, + "loss": 4.7218, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849943951733631e-05, + "loss": 4.7151, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.8491069948629524e-05, + "loss": 4.7219, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848270037992273e-05, + "loss": 4.729, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847431443241221e-05, + "loss": 4.7163, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846592848490169e-05, + "loss": 4.7204, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845754253739117e-05, + "loss": 4.7054, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844915658988065e-05, + "loss": 4.7144, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844077064237013e-05, + "loss": 4.6999, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843238469485961e-05, + "loss": 4.7091, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842399874734909e-05, + "loss": 4.6844, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841561279983857e-05, + "loss": 4.6963, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840722685232805e-05, + "loss": 4.6912, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839884090481753e-05, + "loss": 4.7056, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839045495730701e-05, + "loss": 4.6776, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838208538860022e-05, + "loss": 4.6938, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.83736994410897e-05, + "loss": 4.6894, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836531349357918e-05, + "loss": 4.6822, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835692754606866e-05, + "loss": 4.6928, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834855797736188e-05, + "loss": 4.6675, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.8340188408655086e-05, + "loss": 4.6694, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331802461144566e-05, + "loss": 4.685, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323416513634046e-05, + "loss": 4.6719, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315030566123526e-05, + "loss": 4.6686, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.8306644618613006e-05, + "loss": 4.6622, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298258671102486e-05, + "loss": 4.6671, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289889102395695e-05, + "loss": 4.6565, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281503154885175e-05, + "loss": 4.6766, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273117207374655e-05, + "loss": 4.6456, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264731259864135e-05, + "loss": 4.6555, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256345312353615e-05, + "loss": 4.6529, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8247959364843095e-05, + "loss": 4.653, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823957341733258e-05, + "loss": 4.6605, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823118746982206e-05, + "loss": 4.6484, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822281790111527e-05, + "loss": 4.6284, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821443195360475e-05, + "loss": 4.6356, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820604600609423e-05, + "loss": 4.6593, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819766005858371e-05, + "loss": 4.633, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818929048987692e-05, + "loss": 4.634, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818092092117013e-05, + "loss": 4.626, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817253497365961e-05, + "loss": 4.627, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816416540495282e-05, + "loss": 4.6428, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155779457442305e-05, + "loss": 4.6425, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147393509931785e-05, + "loss": 4.6273, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8139007562421265e-05, + "loss": 4.6378, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.8130621614910745e-05, + "loss": 4.6419, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.8122235667400224e-05, + "loss": 4.6384, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113849719889704e-05, + "loss": 4.612, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.8105463772379184e-05, + "loss": 4.6269, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809707782486866e-05, + "loss": 4.6184, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808869187735814e-05, + "loss": 4.6192, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808032230865135e-05, + "loss": 4.6158, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.8071936361140827e-05, + "loss": 4.6171, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.8063550413630307e-05, + "loss": 4.6241, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.8055164466119786e-05, + "loss": 4.6164, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804677851860927e-05, + "loss": 4.6002, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803839257109875e-05, + "loss": 4.6036, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803002300239196e-05, + "loss": 4.6063, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802163705488144e-05, + "loss": 4.609, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801325110737092e-05, + "loss": 4.6084, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.80048651598604e-05, + "loss": 4.5947, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799649559115361e-05, + "loss": 4.6027, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798810964364309e-05, + "loss": 4.5868, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797972369613257e-05, + "loss": 4.6027, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797133774862205e-05, + "loss": 4.5969, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796295180111153e-05, + "loss": 4.5919, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795456585360101e-05, + "loss": 4.5989, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794619628489423e-05, + "loss": 4.5896, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793781033738371e-05, + "loss": 4.5859, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792942438987319e-05, + "loss": 4.5872, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792103844236267e-05, + "loss": 4.5894, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791265249485215e-05, + "loss": 4.5834, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790426654734163e-05, + "loss": 4.5766, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895880599831107e-05, + "loss": 4.5792, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887494652320587e-05, + "loss": 4.5813, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879125083613796e-05, + "loss": 4.578, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870739136103276e-05, + "loss": 4.5621, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862369567396485e-05, + "loss": 4.5738, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7853983619885965e-05, + "loss": 4.5753, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845597672375445e-05, + "loss": 4.5678, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837211724864925e-05, + "loss": 4.5664, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782882577735441e-05, + "loss": 4.5666, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782045620864762e-05, + "loss": 4.5549, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.78120702611371e-05, + "loss": 4.5741, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780368431362658e-05, + "loss": 4.5594, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779529836611606e-05, + "loss": 4.563, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778692879740927e-05, + "loss": 4.5595, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777854284989875e-05, + "loss": 4.5659, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777015690238823e-05, + "loss": 4.557, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776177095487771e-05, + "loss": 4.5579, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775338500736719e-05, + "loss": 4.569, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.77450154386604e-05, + "loss": 4.5598, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773662949114988e-05, + "loss": 4.5484, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772824354363936e-05, + "loss": 4.5491, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.7719857596128845e-05, + "loss": 4.5439, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771147164861832e-05, + "loss": 4.5418, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.77030857011078e-05, + "loss": 4.5452, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769469975359728e-05, + "loss": 4.5427, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.7686330184890494e-05, + "loss": 4.5332, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767794423737997e-05, + "loss": 4.5382, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766955828986945e-05, + "loss": 4.5341, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766117234235893e-05, + "loss": 4.5505, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765278639484841e-05, + "loss": 4.5539, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764440044733789e-05, + "loss": 4.5389, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763601449982737e-05, + "loss": 4.5285, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762762855231685e-05, + "loss": 4.5356, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761924260480633e-05, + "loss": 4.5409, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.7610856657295813e-05, + "loss": 4.5396, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760248708858902e-05, + "loss": 4.5331, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.75941011410785e-05, + "loss": 4.538, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758571519356798e-05, + "loss": 4.5285, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757734562486119e-05, + "loss": 4.53, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756895967735067e-05, + "loss": 4.5254, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756057372984015e-05, + "loss": 4.5282, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755218778232963e-05, + "loss": 4.5226, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.754380183481911e-05, + "loss": 4.517, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753541588730859e-05, + "loss": 4.5241, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752702993979807e-05, + "loss": 4.5262, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751864399228755e-05, + "loss": 4.5277, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751025804477703e-05, + "loss": 4.5153, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750188847607025e-05, + "loss": 4.5159, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.485238552093506, + "eval_runtime": 295.8472, + "eval_samples_per_second": 1289.824, + "eval_steps_per_second": 40.308, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749350252855973e-05, + "loss": 4.5114, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748511658104921e-05, + "loss": 4.5072, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747673063353868e-05, + "loss": 4.5231, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746834468602816e-05, + "loss": 4.5127, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.745995873851764e-05, + "loss": 4.5197, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745157279100712e-05, + "loss": 4.5012, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.74431868434966e-05, + "loss": 4.5153, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743480089598608e-05, + "loss": 4.5023, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742641494847556e-05, + "loss": 4.51, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741802900096504e-05, + "loss": 4.5053, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740964305345452e-05, + "loss": 4.5141, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401257105944e-05, + "loss": 4.5086, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.7392887537237216e-05, + "loss": 4.4931, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384501589726696e-05, + "loss": 4.5, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.7376115642216176e-05, + "loss": 4.4925, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.7367729694705656e-05, + "loss": 4.4959, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.7359343747195135e-05, + "loss": 4.4969, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.7350957799684615e-05, + "loss": 4.4887, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.7342571852174095e-05, + "loss": 4.4943, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733418590466357e-05, + "loss": 4.5106, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.7325816335956784e-05, + "loss": 4.4974, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.7317430388446264e-05, + "loss": 4.4922, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730904444093574e-05, + "loss": 4.4926, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730065849342522e-05, + "loss": 4.5003, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292288924718433e-05, + "loss": 4.475, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728390297720791e-05, + "loss": 4.4862, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727551702969739e-05, + "loss": 4.485, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726713108218687e-05, + "loss": 4.4796, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725876151348009e-05, + "loss": 4.4768, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725037556596957e-05, + "loss": 4.4731, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724198961845904e-05, + "loss": 4.4822, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723360367094852e-05, + "loss": 4.4904, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225217723438e-05, + "loss": 4.4805, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721686453353495e-05, + "loss": 4.4798, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720847858602443e-05, + "loss": 4.4744, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720010901731764e-05, + "loss": 4.477, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719172306980712e-05, + "loss": 4.4647, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.71833371222966e-05, + "loss": 4.482, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717495117478608e-05, + "loss": 4.455, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716656522727556e-05, + "loss": 4.4683, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715817927976504e-05, + "loss": 4.4615, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149793332254516e-05, + "loss": 4.4768, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141407384743996e-05, + "loss": 4.4552, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713303781603721e-05, + "loss": 4.4681, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.7124651868526685e-05, + "loss": 4.468, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116265921016165e-05, + "loss": 4.4602, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7107879973505645e-05, + "loss": 4.4695, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099494025995125e-05, + "loss": 4.451, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091108078484605e-05, + "loss": 4.4501, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708273850977782e-05, + "loss": 4.469, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.70743525622673e-05, + "loss": 4.4542, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706596661475678e-05, + "loss": 4.4531, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705758066724626e-05, + "loss": 4.449, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704919471973574e-05, + "loss": 4.457, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704082515102895e-05, + "loss": 4.4426, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703243920351843e-05, + "loss": 4.4617, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702405325600791e-05, + "loss": 4.4342, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701566730849739e-05, + "loss": 4.4487, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700728136098687e-05, + "loss": 4.4505, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699889541347635e-05, + "loss": 4.443, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699050946596583e-05, + "loss": 4.4503, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698212351845531e-05, + "loss": 4.4493, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697373757094479e-05, + "loss": 4.4246, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.6965351623434276e-05, + "loss": 4.4359, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.6956982054727485e-05, + "loss": 4.447, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.6948596107216965e-05, + "loss": 4.4374, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.6940226538510174e-05, + "loss": 4.4374, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.6931840590999654e-05, + "loss": 4.4222, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.6923454643489134e-05, + "loss": 4.4285, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915068695978614e-05, + "loss": 4.4465, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.6906682748468094e-05, + "loss": 4.4452, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898296800957574e-05, + "loss": 4.4287, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688991085344705e-05, + "loss": 4.4451, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688152490593653e-05, + "loss": 4.4489, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687315533722974e-05, + "loss": 4.4491, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686476938971923e-05, + "loss": 4.4159, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.68563834422087e-05, + "loss": 4.4372, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684799749469818e-05, + "loss": 4.4303, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683961154718766e-05, + "loss": 4.4256, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683122559967714e-05, + "loss": 4.4309, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682283965216662e-05, + "loss": 4.4301, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.68144537046561e-05, + "loss": 4.4337, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680608413594931e-05, + "loss": 4.4351, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679769818843879e-05, + "loss": 4.412, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.6789328619732e-05, + "loss": 4.4225, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678094267222148e-05, + "loss": 4.4206, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677255672471097e-05, + "loss": 4.4266, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676417077720045e-05, + "loss": 4.4275, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675578482968993e-05, + "loss": 4.4115, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674739888217941e-05, + "loss": 4.4213, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673901293466889e-05, + "loss": 4.4092, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673062698715837e-05, + "loss": 4.4219, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672224103964785e-05, + "loss": 4.4164, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671385509213733e-05, + "loss": 4.4146, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670546914462681e-05, + "loss": 4.4213, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669708319711629e-05, + "loss": 4.4185, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688713628409496e-05, + "loss": 4.4086, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680327680898976e-05, + "loss": 4.4127, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6671941733388456e-05, + "loss": 4.4164, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663555785877936e-05, + "loss": 4.4123, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.6655186217171145e-05, + "loss": 4.3996, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664680026966063e-05, + "loss": 4.4086, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663841432215011e-05, + "loss": 4.4121, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663002837463959e-05, + "loss": 4.4089, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.66216588059328e-05, + "loss": 4.3892, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661328923722601e-05, + "loss": 4.4035, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660490328971549e-05, + "loss": 4.4095, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659651734220497e-05, + "loss": 4.3995, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658813139469445e-05, + "loss": 4.3989, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657976182598766e-05, + "loss": 4.4009, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657137587847714e-05, + "loss": 4.3904, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656298993096662e-05, + "loss": 4.4076, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.65546039834561e-05, + "loss": 4.3927, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546218035945586e-05, + "loss": 4.4025, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6537848467238795e-05, + "loss": 4.4008, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529462519728275e-05, + "loss": 4.4032, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521076572217755e-05, + "loss": 4.3935, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512690624707234e-05, + "loss": 4.401, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.6504321056000444e-05, + "loss": 4.4071, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6495935108489924e-05, + "loss": 4.3996, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487549160979403e-05, + "loss": 4.3871, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479163213468883e-05, + "loss": 4.3897, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647077726595836e-05, + "loss": 4.3848, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462391318447837e-05, + "loss": 4.3889, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645400537093732e-05, + "loss": 4.3862, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.64456194234268e-05, + "loss": 4.3889, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643723347591628e-05, + "loss": 4.376, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642886390720949e-05, + "loss": 4.3844, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642047795969897e-05, + "loss": 4.3782, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641209201218845e-05, + "loss": 4.3963, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640370606467793e-05, + "loss": 4.3968, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639533649597114e-05, + "loss": 4.3893, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638695054846062e-05, + "loss": 4.375, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.63785646009501e-05, + "loss": 4.3828, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637017865343958e-05, + "loss": 4.3908, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636179270592906e-05, + "loss": 4.3861, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635342313722228e-05, + "loss": 4.3824, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634503718971176e-05, + "loss": 4.3872, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633665124220124e-05, + "loss": 4.3806, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632826529469072e-05, + "loss": 4.3864, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6319895725983926e-05, + "loss": 4.3705, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311509778473406e-05, + "loss": 4.3837, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303123830962886e-05, + "loss": 4.376, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294737883452366e-05, + "loss": 4.3682, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286351935941846e-05, + "loss": 4.3768, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6277998746038784e-05, + "loss": 4.3823, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.6269612798528264e-05, + "loss": 4.3782, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.6261226851017744e-05, + "loss": 4.3716, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625284090350723e-05, + "loss": 4.3691, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.347572326660156, + "eval_runtime": 302.0433, + "eval_samples_per_second": 1263.365, + "eval_steps_per_second": 39.481, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624445495599671e-05, + "loss": 4.3777, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623606900848619e-05, + "loss": 4.3627, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622768306097567e-05, + "loss": 4.3802, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621929711346515e-05, + "loss": 4.3679, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621091116595463e-05, + "loss": 4.3822, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620254159724784e-05, + "loss": 4.3581, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619415564973732e-05, + "loss": 4.3771, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.61857697022268e-05, + "loss": 4.3603, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617738375471628e-05, + "loss": 4.373, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616901418600949e-05, + "loss": 4.3677, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616062823849897e-05, + "loss": 4.3688, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.6152258669792184e-05, + "loss": 4.3756, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.6143872722281664e-05, + "loss": 4.3546, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.6135486774771144e-05, + "loss": 4.3623, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6127100827260624e-05, + "loss": 4.3562, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.6118714879750104e-05, + "loss": 4.3609, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110328932239584e-05, + "loss": 4.3581, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.6101942984729064e-05, + "loss": 4.3566, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.6093557037218544e-05, + "loss": 4.3594, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608517108970802e-05, + "loss": 4.3765, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.60767851421975e-05, + "loss": 4.3611, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606841557349071e-05, + "loss": 4.3596, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606002962598019e-05, + "loss": 4.3621, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051643678469666e-05, + "loss": 4.365, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604325773095915e-05, + "loss": 4.3449, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603488816225236e-05, + "loss": 4.3619, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602650221474184e-05, + "loss": 4.3474, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601811626723132e-05, + "loss": 4.3484, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.60097303197208e-05, + "loss": 4.3439, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600136075101402e-05, + "loss": 4.3509, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599297480350349e-05, + "loss": 4.3489, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598458885599297e-05, + "loss": 4.3627, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597620290848245e-05, + "loss": 4.3531, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596781696097193e-05, + "loss": 4.3517, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595943101346141e-05, + "loss": 4.3425, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595104506595089e-05, + "loss": 4.3526, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594265911844037e-05, + "loss": 4.3362, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593427317092985e-05, + "loss": 4.3572, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5925903602223066e-05, + "loss": 4.3293, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.5917517654712546e-05, + "loss": 4.3408, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.5909131707202026e-05, + "loss": 4.3397, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.5900745759691506e-05, + "loss": 4.3519, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.5892359812180986e-05, + "loss": 4.3334, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5883973864670466e-05, + "loss": 4.34, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.5875604295963675e-05, + "loss": 4.3423, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.5867218348453155e-05, + "loss": 4.3382, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.5858848779746364e-05, + "loss": 4.3461, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.5850462832235844e-05, + "loss": 4.3303, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.5842076884725324e-05, + "loss": 4.3246, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.5833690937214804e-05, + "loss": 4.3451, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.5825304989704284e-05, + "loss": 4.3344, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581691904219377e-05, + "loss": 4.3311, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580853309468325e-05, + "loss": 4.3316, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580014714717273e-05, + "loss": 4.3343, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.5791761199662204e-05, + "loss": 4.3208, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578340800975915e-05, + "loss": 4.3426, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577502206224863e-05, + "loss": 4.315, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576663611473811e-05, + "loss": 4.3303, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575825016722759e-05, + "loss": 4.3278, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.574986421971707e-05, + "loss": 4.3327, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574147827220655e-05, + "loss": 4.3265, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573310870349976e-05, + "loss": 4.3316, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572472275598924e-05, + "loss": 4.3066, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716336808478725e-05, + "loss": 4.3248, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5707950860968205e-05, + "loss": 4.3286, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569956491345768e-05, + "loss": 4.3243, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569117896594716e-05, + "loss": 4.3168, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682809397240374e-05, + "loss": 4.3133, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.5674423449729854e-05, + "loss": 4.3124, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566603750221933e-05, + "loss": 4.3274, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565765155470881e-05, + "loss": 4.3325, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564928198600202e-05, + "loss": 4.3165, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.5640896038491496e-05, + "loss": 4.3293, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632510090980976e-05, + "loss": 4.3346, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562412414347046e-05, + "loss": 4.3399, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561573819595994e-05, + "loss": 4.3016, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560735224844942e-05, + "loss": 4.3222, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.55989663009389e-05, + "loss": 4.3216, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559058035342838e-05, + "loss": 4.3112, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558221078472159e-05, + "loss": 4.3204, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557382483721107e-05, + "loss": 4.3235, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556543888970055e-05, + "loss": 4.3259, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555705294219003e-05, + "loss": 4.3166, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554866699467951e-05, + "loss": 4.3096, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554028104716899e-05, + "loss": 4.3111, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553189509965847e-05, + "loss": 4.3111, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552352553095168e-05, + "loss": 4.3185, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551513958344116e-05, + "loss": 4.3209, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.5506770014734376e-05, + "loss": 4.3046, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.5498384067223856e-05, + "loss": 4.3112, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.5489998119713336e-05, + "loss": 4.301, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.5481612172202816e-05, + "loss": 4.3111, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.5473226224692296e-05, + "loss": 4.3116, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.5464840277181776e-05, + "loss": 4.307, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.5456454329671256e-05, + "loss": 4.3165, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.5448068382160736e-05, + "loss": 4.3108, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.5439682434650216e-05, + "loss": 4.3044, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431312865943425e-05, + "loss": 4.307, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.5422926918432905e-05, + "loss": 4.3097, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.5414540970922385e-05, + "loss": 4.3121, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.5406155023411865e-05, + "loss": 4.2929, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.5397769075901345e-05, + "loss": 4.3045, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538939950719456e-05, + "loss": 4.3087, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538101355968404e-05, + "loss": 4.3079, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372627612173514e-05, + "loss": 4.2902, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364241664662994e-05, + "loss": 4.2948, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5355855717152473e-05, + "loss": 4.3077, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347469769641953e-05, + "loss": 4.2987, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533908382213143e-05, + "loss": 4.2957, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533069787462091e-05, + "loss": 4.2957, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532232830591412e-05, + "loss": 4.2967, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.53139423584036e-05, + "loss": 4.2992, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530557278969682e-05, + "loss": 4.2945, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297203220990034e-05, + "loss": 4.2939, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5288817273479514e-05, + "loss": 4.3022, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528043132596899e-05, + "loss": 4.3041, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527204537845847e-05, + "loss": 4.3016, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526365943094795e-05, + "loss": 4.2927, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525527348343743e-05, + "loss": 4.3092, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524688753592691e-05, + "loss": 4.3008, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523850158841639e-05, + "loss": 4.2868, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523011564090587e-05, + "loss": 4.2937, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522172969339535e-05, + "loss": 4.2882, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521334374588483e-05, + "loss": 4.2926, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.5204974177178036e-05, + "loss": 4.2834, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519660460847125e-05, + "loss": 4.2938, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518821866096073e-05, + "loss": 4.2786, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517983271345021e-05, + "loss": 4.2875, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517144676593969e-05, + "loss": 4.28, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516306081842917e-05, + "loss": 4.3015, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515467487091865e-05, + "loss": 4.2962, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514628892340813e-05, + "loss": 4.2948, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513790297589761e-05, + "loss": 4.2787, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512953340719082e-05, + "loss": 4.2903, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512116383848403e-05, + "loss": 4.2985, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511277789097351e-05, + "loss": 4.2879, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510439194346299e-05, + "loss": 4.286, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509600599595247e-05, + "loss": 4.295, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087620048441956e-05, + "loss": 4.2867, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079234100931436e-05, + "loss": 4.2931, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.5070864532224645e-05, + "loss": 4.2739, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.5062478584714125e-05, + "loss": 4.2905, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5054092637203605e-05, + "loss": 4.28, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.5045706689693085e-05, + "loss": 4.2803, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.5037320742182565e-05, + "loss": 4.2824, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.5028934794672045e-05, + "loss": 4.2913, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502054884716152e-05, + "loss": 4.2823, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012162899651e-05, + "loss": 4.278, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.5003793330944214e-05, + "loss": 4.2797, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 4.263718605041504, + "eval_runtime": 296.8429, + "eval_samples_per_second": 1285.498, + "eval_steps_per_second": 40.173, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995407383433694e-05, + "loss": 4.2779, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987021435923174e-05, + "loss": 4.2736, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978635488412654e-05, + "loss": 4.2848, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970249540902134e-05, + "loss": 4.2781, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4961863593391614e-05, + "loss": 4.2911, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953477645881094e-05, + "loss": 4.2747, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945091698370574e-05, + "loss": 4.2807, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936705750860054e-05, + "loss": 4.2703, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492833618215326e-05, + "loss": 4.2795, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.491995023464274e-05, + "loss": 4.2818, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491156428713222e-05, + "loss": 4.2783, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.49031783396217e-05, + "loss": 4.2818, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489479239211118e-05, + "loss": 4.2669, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488640644460066e-05, + "loss": 4.2747, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487802049709014e-05, + "loss": 4.2698, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486963454957962e-05, + "loss": 4.2684, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.48612486020691e-05, + "loss": 4.2714, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485286265455859e-05, + "loss": 4.2699, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484447670704806e-05, + "loss": 4.2699, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483609075953754e-05, + "loss": 4.2834, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482772119083076e-05, + "loss": 4.2779, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481933524332024e-05, + "loss": 4.2717, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481094929580971e-05, + "loss": 4.2755, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480257972710293e-05, + "loss": 4.28, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479419377959241e-05, + "loss": 4.2569, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478580783208188e-05, + "loss": 4.2741, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477742188457136e-05, + "loss": 4.2626, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476903593706084e-05, + "loss": 4.2591, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476064998955033e-05, + "loss": 4.2581, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475226404203981e-05, + "loss": 4.2669, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474387809452929e-05, + "loss": 4.2638, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473549214701877e-05, + "loss": 4.276, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.4727122578311976e-05, + "loss": 4.2677, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4718736630801456e-05, + "loss": 4.2655, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710350683290936e-05, + "loss": 4.2592, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4701964735780416e-05, + "loss": 4.2671, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693578788269896e-05, + "loss": 4.2594, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.4685209219563105e-05, + "loss": 4.2679, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4676823272052585e-05, + "loss": 4.2461, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668437324542065e-05, + "loss": 4.2561, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466006775583528e-05, + "loss": 4.2555, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465168180832476e-05, + "loss": 4.2692, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464329586081424e-05, + "loss": 4.2558, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463490991330372e-05, + "loss": 4.2575, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.46265239657932e-05, + "loss": 4.2594, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461813801828268e-05, + "loss": 4.2555, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460976844957589e-05, + "loss": 4.2633, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.46013988808691e-05, + "loss": 4.2509, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459301293335858e-05, + "loss": 4.2423, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458462698584806e-05, + "loss": 4.2632, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457624103833754e-05, + "loss": 4.2523, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456785509082702e-05, + "loss": 4.2511, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.45594691433165e-05, + "loss": 4.2486, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455108319580598e-05, + "loss": 4.257, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542697248295465e-05, + "loss": 4.2415, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534311300784945e-05, + "loss": 4.2555, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4525925353274425e-05, + "loss": 4.2397, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.45175394057639e-05, + "loss": 4.2475, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450915345825338e-05, + "loss": 4.2522, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450076751074286e-05, + "loss": 4.2505, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449238156323234e-05, + "loss": 4.2468, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448401199452555e-05, + "loss": 4.2573, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447562604701503e-05, + "loss": 4.2294, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446725647830824e-05, + "loss": 4.2407, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.4458870530797716e-05, + "loss": 4.2513, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.44504845832872e-05, + "loss": 4.2434, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444209863577668e-05, + "loss": 4.2439, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443371268826616e-05, + "loss": 4.2352, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442532674075564e-05, + "loss": 4.2327, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441694079324512e-05, + "loss": 4.2477, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.44085548457346e-05, + "loss": 4.2545, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440016889822408e-05, + "loss": 4.2441, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439178295071356e-05, + "loss": 4.2508, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438339700320304e-05, + "loss": 4.2572, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437502743449625e-05, + "loss": 4.2663, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436664148698573e-05, + "loss": 4.2298, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435825553947521e-05, + "loss": 4.242, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.434986959196469e-05, + "loss": 4.2526, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434148364445417e-05, + "loss": 4.2301, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433311407574738e-05, + "loss": 4.2469, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432472812823687e-05, + "loss": 4.2449, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431634218072635e-05, + "loss": 4.2495, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430795623321583e-05, + "loss": 4.245, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429957028570531e-05, + "loss": 4.2306, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291200716998516e-05, + "loss": 4.2375, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4282814769487996e-05, + "loss": 4.2343, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274428821977476e-05, + "loss": 4.2422, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266042874466956e-05, + "loss": 4.2469, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257673305760165e-05, + "loss": 4.2287, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249287358249645e-05, + "loss": 4.2374, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4240901410739125e-05, + "loss": 4.228, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232515463228605e-05, + "loss": 4.2358, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224129515718085e-05, + "loss": 4.2379, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4215743568207565e-05, + "loss": 4.2362, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207357620697045e-05, + "loss": 4.2445, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4198971673186525e-05, + "loss": 4.2336, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190585725676005e-05, + "loss": 4.2346, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418223253577295e-05, + "loss": 4.2322, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417386296706616e-05, + "loss": 4.2346, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416547701955564e-05, + "loss": 4.2421, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415709107204512e-05, + "loss": 4.222, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.41487051245346e-05, + "loss": 4.2333, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414031917702408e-05, + "loss": 4.235, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413193322951356e-05, + "loss": 4.2357, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412354728200304e-05, + "loss": 4.2178, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411516133449252e-05, + "loss": 4.2248, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4106775386982e-05, + "loss": 4.2355, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409838943947148e-05, + "loss": 4.2293, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409000349196096e-05, + "loss": 4.2219, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408161754445044e-05, + "loss": 4.2294, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407324797574365e-05, + "loss": 4.2205, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406486202823313e-05, + "loss": 4.2339, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405647608072261e-05, + "loss": 4.2241, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404809013321209e-05, + "loss": 4.2198, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.40397205645053e-05, + "loss": 4.233, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031334616994777e-05, + "loss": 4.2377, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402296504828799e-05, + "loss": 4.2289, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401457910077747e-05, + "loss": 4.2257, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400619315326695e-05, + "loss": 4.2311, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399782358456016e-05, + "loss": 4.2311, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398943763704964e-05, + "loss": 4.2208, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398105168953912e-05, + "loss": 4.2304, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.39726657420286e-05, + "loss": 4.2178, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396427979451808e-05, + "loss": 4.2224, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395589384700756e-05, + "loss": 4.2167, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394750789949704e-05, + "loss": 4.2243, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393912195198652e-05, + "loss": 4.2112, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3930736004476e-05, + "loss": 4.2153, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392235005696548e-05, + "loss": 4.2174, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391396410945496e-05, + "loss": 4.2291, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390557816194444e-05, + "loss": 4.231, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389719221443392e-05, + "loss": 4.2271, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.38888062669234e-05, + "loss": 4.2098, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388043669821662e-05, + "loss": 4.227, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387205075070609e-05, + "loss": 4.2295, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3863681181999306e-05, + "loss": 4.2231, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855295234488786e-05, + "loss": 4.2186, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3846909286978266e-05, + "loss": 4.2316, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383852333946774e-05, + "loss": 4.2171, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383013739195722e-05, + "loss": 4.2276, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.38217514444467e-05, + "loss": 4.204, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381336549693618e-05, + "loss": 4.2286, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380497954942566e-05, + "loss": 4.2104, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796593601915145e-05, + "loss": 4.2137, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788207654404625e-05, + "loss": 4.219, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3779821706894105e-05, + "loss": 4.2194, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771435759383585e-05, + "loss": 4.2214, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763066190676794e-05, + "loss": 4.2069, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3754680243166274e-05, + "loss": 4.2204, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 4.206528663635254, + "eval_runtime": 291.1655, + "eval_samples_per_second": 1310.564, + "eval_steps_per_second": 40.956, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.3746294295655754e-05, + "loss": 4.2172, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.3737908348145234e-05, + "loss": 4.2081, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.3729538779438443e-05, + "loss": 4.2217, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372115283192792e-05, + "loss": 4.2132, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.37127668844174e-05, + "loss": 4.2244, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370438093690688e-05, + "loss": 4.2099, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369599498939636e-05, + "loss": 4.2097, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368760904188584e-05, + "loss": 4.2119, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367923947317906e-05, + "loss": 4.2135, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367085352566854e-05, + "loss": 4.2177, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366246757815802e-05, + "loss": 4.2123, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.36540816306475e-05, + "loss": 4.2209, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364571206194071e-05, + "loss": 4.2045, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363732611443019e-05, + "loss": 4.2087, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362894016691967e-05, + "loss": 4.2092, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362055421940915e-05, + "loss": 4.2011, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361216827189863e-05, + "loss": 4.2092, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.36037823243881e-05, + "loss": 4.2032, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359539637687758e-05, + "loss": 4.2046, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358701042936707e-05, + "loss": 4.2247, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.3578640860660284e-05, + "loss": 4.2152, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357025491314976e-05, + "loss": 4.2157, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356186896563924e-05, + "loss": 4.2107, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355348301812872e-05, + "loss": 4.2153, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.35450970706182e-05, + "loss": 4.1955, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.3536711123107677e-05, + "loss": 4.2131, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.3528341554400886e-05, + "loss": 4.2034, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.35199719856941e-05, + "loss": 4.1929, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.3511586038183575e-05, + "loss": 4.1974, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.3503200090673055e-05, + "loss": 4.2024, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.3494814143162535e-05, + "loss": 4.2027, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348642819565202e-05, + "loss": 4.2134, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.34780422481415e-05, + "loss": 4.2103, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.346965630063098e-05, + "loss": 4.2033, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346127035312046e-05, + "loss": 4.2013, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345288440560994e-05, + "loss": 4.2032, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344449845809942e-05, + "loss": 4.1991, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343612888939263e-05, + "loss": 4.2057, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342774294188211e-05, + "loss": 4.1918, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341935699437159e-05, + "loss": 4.192, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341097104686107e-05, + "loss": 4.1979, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340258509935055e-05, + "loss": 4.2074, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339419915184003e-05, + "loss": 4.1982, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338581320432951e-05, + "loss": 4.1959, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337742725681899e-05, + "loss": 4.2015, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336904130930847e-05, + "loss": 4.1949, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3360671740601686e-05, + "loss": 4.2048, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.3352285793091166e-05, + "loss": 4.1904, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.3343916224384375e-05, + "loss": 4.1826, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.3335530276873855e-05, + "loss": 4.2017, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.3327144329363335e-05, + "loss": 4.1969, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.3318758381852815e-05, + "loss": 4.1911, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331037243434229e-05, + "loss": 4.1957, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330198648683177e-05, + "loss": 4.193, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329360053932125e-05, + "loss": 4.1872, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.3285230970614464e-05, + "loss": 4.1922, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327684502310394e-05, + "loss": 4.1847, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.3268459075593424e-05, + "loss": 4.1872, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326008950688664e-05, + "loss": 4.1974, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325170355937611e-05, + "loss": 4.188, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324331761186559e-05, + "loss": 4.1905, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323493166435507e-05, + "loss": 4.1987, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322654571684455e-05, + "loss": 4.1757, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321815976933403e-05, + "loss": 4.1826, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.320977382182351e-05, + "loss": 4.1891, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320138787431299e-05, + "loss": 4.1918, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319303468440994e-05, + "loss": 4.1826, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318464873689941e-05, + "loss": 4.1814, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317626278938889e-05, + "loss": 4.1731, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316787684187838e-05, + "loss": 4.192, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315949089436786e-05, + "loss": 4.1963, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315110494685734e-05, + "loss": 4.1888, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314271899934682e-05, + "loss": 4.1923, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.31343330518363e-05, + "loss": 4.1937, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312594710432578e-05, + "loss": 4.215, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311756115681526e-05, + "loss": 4.1758, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109191588108466e-05, + "loss": 4.1839, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.3100805640597946e-05, + "loss": 4.197, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.3092419693087426e-05, + "loss": 4.1719, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.3084050124380635e-05, + "loss": 4.1907, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.3075664176870115e-05, + "loss": 4.1886, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.3067278229359595e-05, + "loss": 4.1914, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.3058892281849075e-05, + "loss": 4.189, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305050633433856e-05, + "loss": 4.174, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304212038682804e-05, + "loss": 4.1885, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303373443931752e-05, + "loss": 4.1734, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025348491807e-05, + "loss": 4.1893, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3016962544296475e-05, + "loss": 4.1916, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300859297558969e-05, + "loss": 4.1695, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300020702807917e-05, + "loss": 4.1844, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299182108056865e-05, + "loss": 4.1757, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.2983435133058124e-05, + "loss": 4.1776, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.2975049185547604e-05, + "loss": 4.1787, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.2966663238037084e-05, + "loss": 4.1903, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.2958277290526564e-05, + "loss": 4.1921, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.2949891343016043e-05, + "loss": 4.1754, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294150539550553e-05, + "loss": 4.1774, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293311944799501e-05, + "loss": 4.1816, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292473350048449e-05, + "loss": 4.1764, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.29163639317777e-05, + "loss": 4.1899, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290797798426718e-05, + "loss": 4.1699, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.289959203675666e-05, + "loss": 4.1761, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289120608924614e-05, + "loss": 4.1809, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288282014173562e-05, + "loss": 4.1836, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287445057302883e-05, + "loss": 4.1642, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286606462551831e-05, + "loss": 4.1718, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285767867800779e-05, + "loss": 4.1795, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284929273049727e-05, + "loss": 4.1777, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284090678298675e-05, + "loss": 4.1651, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283252083547623e-05, + "loss": 4.1833, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282413488796571e-05, + "loss": 4.1657, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281574894045519e-05, + "loss": 4.1765, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807379371748404e-05, + "loss": 4.1731, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2798993424237884e-05, + "loss": 4.1675, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279062385553109e-05, + "loss": 4.1779, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278223790802057e-05, + "loss": 4.1886, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277385196051005e-05, + "loss": 4.176, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276546601299953e-05, + "loss": 4.1752, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275708006548901e-05, + "loss": 4.1802, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2748694117978486e-05, + "loss": 4.18, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.2740308170467966e-05, + "loss": 4.1678, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273193860176118e-05, + "loss": 4.1738, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272355265425066e-05, + "loss": 4.167, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271516670674014e-05, + "loss": 4.1689, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270678075922962e-05, + "loss": 4.17, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.26983948117191e-05, + "loss": 4.169, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269000886420858e-05, + "loss": 4.1647, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268162291669806e-05, + "loss": 4.1614, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267323696918754e-05, + "loss": 4.1687, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266486740048075e-05, + "loss": 4.1781, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265648145297023e-05, + "loss": 4.176, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264809550545971e-05, + "loss": 4.1761, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.263970955794919e-05, + "loss": 4.1566, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263132361043867e-05, + "loss": 4.1798, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2622954041731886e-05, + "loss": 4.1777, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2614568094221366e-05, + "loss": 4.1705, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.2606182146710846e-05, + "loss": 4.1699, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2597796199200326e-05, + "loss": 4.1752, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.2589410251689806e-05, + "loss": 4.1662, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.2581024304179286e-05, + "loss": 4.1825, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.2572638356668766e-05, + "loss": 4.1517, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.2564252409158246e-05, + "loss": 4.1756, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.2555882840451455e-05, + "loss": 4.1595, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.2547496892940935e-05, + "loss": 4.1643, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.2539110945430415e-05, + "loss": 4.1692, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.2530741376723624e-05, + "loss": 4.1652, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.2522355429213104e-05, + "loss": 4.1766, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251398586050632e-05, + "loss": 4.1524, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.25055999129958e-05, + "loss": 4.1733, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 4.164845943450928, + "eval_runtime": 293.5672, + "eval_samples_per_second": 1299.842, + "eval_steps_per_second": 40.621, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249721396548528e-05, + "loss": 4.1687, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248882801797476e-05, + "loss": 4.1568, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248044207046424e-05, + "loss": 4.1714, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247205612295372e-05, + "loss": 4.1658, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.24636701754432e-05, + "loss": 4.1714, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245528422793267e-05, + "loss": 4.1603, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244689828042215e-05, + "loss": 4.1595, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243851233291163e-05, + "loss": 4.1642, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243012638540111e-05, + "loss": 4.1638, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242174043789059e-05, + "loss": 4.1679, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241335449038007e-05, + "loss": 4.1663, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240496854286955e-05, + "loss": 4.1675, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239659897416277e-05, + "loss": 4.1611, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238821302665225e-05, + "loss": 4.1602, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.237982707914173e-05, + "loss": 4.1615, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237144113163121e-05, + "loss": 4.1522, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236305518412069e-05, + "loss": 4.1609, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235466923661017e-05, + "loss": 4.1542, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234628328909965e-05, + "loss": 4.1579, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233789734158913e-05, + "loss": 4.1724, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.232951139407861e-05, + "loss": 4.169, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232112544656809e-05, + "loss": 4.1682, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231273949905756e-05, + "loss": 4.162, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230435355154704e-05, + "loss": 4.1684, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229598398284026e-05, + "loss": 4.1465, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228761441413347e-05, + "loss": 4.1675, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227922846662295e-05, + "loss": 4.155, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227084251911243e-05, + "loss": 4.1473, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226245657160191e-05, + "loss": 4.1506, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225408700289512e-05, + "loss": 4.1555, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.22457010553846e-05, + "loss": 4.1554, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223731510787408e-05, + "loss": 4.1656, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222892916036356e-05, + "loss": 4.1617, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2220543212853035e-05, + "loss": 4.1594, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212157265342515e-05, + "loss": 4.1484, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2203771317831995e-05, + "loss": 4.1587, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219540174912521e-05, + "loss": 4.1576, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187032180418426e-05, + "loss": 4.1514, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2178646232907906e-05, + "loss": 4.1487, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170260285397386e-05, + "loss": 4.1418, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216187433788686e-05, + "loss": 4.1525, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215348839037634e-05, + "loss": 4.1592, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214510244286582e-05, + "loss": 4.1521, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.21367164953553e-05, + "loss": 4.1496, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212833054784478e-05, + "loss": 4.1567, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.211994460033426e-05, + "loss": 4.1475, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211157503162747e-05, + "loss": 4.1598, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210318908411695e-05, + "loss": 4.1458, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209480313660643e-05, + "loss": 4.1339, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208641718909591e-05, + "loss": 4.1574, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.2078031241585395e-05, + "loss": 4.1528, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2069645294074875e-05, + "loss": 4.1482, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061259346564355e-05, + "loss": 4.1472, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2052873399053835e-05, + "loss": 4.1437, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2044487451543315e-05, + "loss": 4.1441, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036117882836524e-05, + "loss": 4.1447, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2027731935326004e-05, + "loss": 4.1416, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2019345987815484e-05, + "loss": 4.1472, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2010960040304964e-05, + "loss": 4.1486, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200259047159817e-05, + "loss": 4.1442, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199420452408765e-05, + "loss": 4.1419, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198581857657713e-05, + "loss": 4.1606, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197743262906661e-05, + "loss": 4.1271, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196906306035983e-05, + "loss": 4.135, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196067711284931e-05, + "loss": 4.1462, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195230754414252e-05, + "loss": 4.1507, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.1943921596632e-05, + "loss": 4.1384, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193553564912148e-05, + "loss": 4.1364, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192714970161096e-05, + "loss": 4.1283, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1918780132904167e-05, + "loss": 4.1444, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910394185393647e-05, + "loss": 4.1542, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902008237883126e-05, + "loss": 4.1459, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1893622290372606e-05, + "loss": 4.1433, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885236342862086e-05, + "loss": 4.1523, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1876850395351566e-05, + "loss": 4.1681, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186848082664478e-05, + "loss": 4.1337, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186009487913426e-05, + "loss": 4.1409, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185170893162374e-05, + "loss": 4.151, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184332298411322e-05, + "loss": 4.129, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183495341540643e-05, + "loss": 4.1462, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182656746789591e-05, + "loss": 4.1457, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181818152038539e-05, + "loss": 4.1478, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.180979557287487e-05, + "loss": 4.1474, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.1801409625364344e-05, + "loss": 4.1302, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179304005665756e-05, + "loss": 4.1426, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178465410914704e-05, + "loss": 4.1336, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177626816163652e-05, + "loss": 4.1408, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1767882214126e-05, + "loss": 4.1478, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1759512645419216e-05, + "loss": 4.1288, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751126697908696e-05, + "loss": 4.1399, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174274075039817e-05, + "loss": 4.1332, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173435480288765e-05, + "loss": 4.1296, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172596885537713e-05, + "loss": 4.1405, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171758290786661e-05, + "loss": 4.1427, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170919696035609e-05, + "loss": 4.1499, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170081101284557e-05, + "loss": 4.1354, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169242506533505e-05, + "loss": 4.1358, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168407187543199e-05, + "loss": 4.1375, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1675685927921474e-05, + "loss": 4.1364, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1667299980410954e-05, + "loss": 4.144, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1658914032900434e-05, + "loss": 4.1317, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1650528085389914e-05, + "loss": 4.1339, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642142137879393e-05, + "loss": 4.1369, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1633756190368873e-05, + "loss": 4.1458, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625370242858353e-05, + "loss": 4.1177, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161698429534783e-05, + "loss": 4.1344, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160861472664104e-05, + "loss": 4.1353, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160022877913052e-05, + "loss": 4.1375, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159184283162e-05, + "loss": 4.1235, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158345688410948e-05, + "loss": 4.1391, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157507093659896e-05, + "loss": 4.1316, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156670136789217e-05, + "loss": 4.1289, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155831542038166e-05, + "loss": 4.1357, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.154992947287114e-05, + "loss": 4.1276, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154154352536062e-05, + "loss": 4.1331, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.15331575778501e-05, + "loss": 4.1491, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152478800914331e-05, + "loss": 4.136, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151640206163279e-05, + "loss": 4.1297, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150801611412227e-05, + "loss": 4.1409, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.149963016661175e-05, + "loss": 4.1376, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149124421910123e-05, + "loss": 4.123, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1482874650394436e-05, + "loss": 4.1376, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1474488702883916e-05, + "loss": 4.1264, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466102755373396e-05, + "loss": 4.125, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1457716807862876e-05, + "loss": 4.1291, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449330860352356e-05, + "loss": 4.1268, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144096129164557e-05, + "loss": 4.1269, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143257534413505e-05, + "loss": 4.1248, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142418939662453e-05, + "loss": 4.1235, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1415803449114005e-05, + "loss": 4.1403, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1407417501603485e-05, + "loss": 4.1314, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.13990479328967e-05, + "loss": 4.1353, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139067836418991e-05, + "loss": 4.1151, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138229241667939e-05, + "loss": 4.1428, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137390646916887e-05, + "loss": 4.1333, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136552052165835e-05, + "loss": 4.132, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135713457414783e-05, + "loss": 4.1327, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134874862663731e-05, + "loss": 4.1344, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134036267912679e-05, + "loss": 4.1247, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133197673161627e-05, + "loss": 4.1457, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132359078410575e-05, + "loss": 4.1135, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131520483659523e-05, + "loss": 4.1323, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130683526788844e-05, + "loss": 4.1243, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129844932037792e-05, + "loss": 4.1245, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.12900633728674e-05, + "loss": 4.1262, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128167742535688e-05, + "loss": 4.1229, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127329147784636e-05, + "loss": 4.1383, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126492190913957e-05, + "loss": 4.1165, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125653596162905e-05, + "loss": 4.1326, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.133554458618164, + "eval_runtime": 350.8156, + "eval_samples_per_second": 1087.725, + "eval_steps_per_second": 33.992, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.1248150014118534e-05, + "loss": 4.1273, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.1239764066608014e-05, + "loss": 4.1168, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.1231378119097494e-05, + "loss": 4.1312, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.1222992171586974e-05, + "loss": 4.1256, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.1214606224076454e-05, + "loss": 4.1297, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.1206220276565934e-05, + "loss": 4.122, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119785070785914e-05, + "loss": 4.1247, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.118946476034862e-05, + "loss": 4.121, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.11810788128381e-05, + "loss": 4.128, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117270924413131e-05, + "loss": 4.1311, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116432329662079e-05, + "loss": 4.1278, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115593734911027e-05, + "loss": 4.1254, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114756778040348e-05, + "loss": 4.1212, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113918183289297e-05, + "loss": 4.1212, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113079588538245e-05, + "loss": 4.1236, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112240993787193e-05, + "loss": 4.1151, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111402399036141e-05, + "loss": 4.1207, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110563804285089e-05, + "loss": 4.118, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109725209534036e-05, + "loss": 4.1183, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108886614782984e-05, + "loss": 4.1293, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108048020031932e-05, + "loss": 4.1344, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.10720942528088e-05, + "loss": 4.1285, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106370830529828e-05, + "loss": 4.123, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105532235778776e-05, + "loss": 4.1277, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104695278908097e-05, + "loss": 4.111, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103856684157045e-05, + "loss": 4.1284, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.1030197272863665e-05, + "loss": 4.1165, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.1021811325353145e-05, + "loss": 4.1103, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.1013425377842625e-05, + "loss": 4.115, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005039430332105e-05, + "loss": 4.1192, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0996653482821585e-05, + "loss": 4.1181, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988267535311065e-05, + "loss": 4.1278, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0979881587800545e-05, + "loss": 4.1251, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0971512019093754e-05, + "loss": 4.1167, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963126071583234e-05, + "loss": 4.1155, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0954740124072714e-05, + "loss": 4.1228, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0946354176562194e-05, + "loss": 4.1203, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0937968229051674e-05, + "loss": 4.1133, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0929582281541154e-05, + "loss": 4.1143, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092121271283437e-05, + "loss": 4.1032, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091282676532385e-05, + "loss": 4.1122, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090444081781333e-05, + "loss": 4.1252, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089605487030281e-05, + "loss": 4.1159, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088768530159602e-05, + "loss": 4.1113, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.08792993540855e-05, + "loss": 4.1196, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087091340657498e-05, + "loss": 4.1098, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086252745906446e-05, + "loss": 4.1217, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085414151155394e-05, + "loss": 4.1117, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084575556404342e-05, + "loss": 4.0926, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.08373696165329e-05, + "loss": 4.1206, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082898366902237e-05, + "loss": 4.1153, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082061410031559e-05, + "loss": 4.1143, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.0812228152805074e-05, + "loss": 4.1085, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.0803842205294554e-05, + "loss": 4.1071, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079545625778403e-05, + "loss": 4.108, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078708668907724e-05, + "loss": 4.1051, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077870074156672e-05, + "loss": 4.1076, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0770314794056196e-05, + "loss": 4.107, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076194522534941e-05, + "loss": 4.1185, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075355927783889e-05, + "loss": 4.1028, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074517333032837e-05, + "loss": 4.109, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0736787382817845e-05, + "loss": 4.1229, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.0728401435307325e-05, + "loss": 4.0923, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072003186660054e-05, + "loss": 4.0975, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071164591909002e-05, + "loss": 4.1132, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.07032599715795e-05, + "loss": 4.1118, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069487402406898e-05, + "loss": 4.1013, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.06865044553622e-05, + "loss": 4.1043, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067811850785167e-05, + "loss": 4.0905, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.066973256034115e-05, + "loss": 4.1118, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066134661283063e-05, + "loss": 4.1136, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0652977044123846e-05, + "loss": 4.1106, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064459109661332e-05, + "loss": 4.1064, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.06362051491028e-05, + "loss": 4.1184, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062781920159228e-05, + "loss": 4.1301, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0619433254081766e-05, + "loss": 4.0991, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611047306571246e-05, + "loss": 4.1045, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0602661359060726e-05, + "loss": 4.1167, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0594275411550206e-05, + "loss": 4.0967, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0585889464039686e-05, + "loss": 4.1072, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0577503516529166e-05, + "loss": 4.1099, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569117569018645e-05, + "loss": 4.1135, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0560748000311855e-05, + "loss": 4.116, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0552362052801335e-05, + "loss": 4.0964, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0543976105290814e-05, + "loss": 4.104, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.0535606536584024e-05, + "loss": 4.0987, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.0527220589073504e-05, + "loss": 4.1063, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.0518834641562984e-05, + "loss": 4.1088, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.0510448694052463e-05, + "loss": 4.0964, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.0502062746541943e-05, + "loss": 4.1031, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049367679903143e-05, + "loss": 4.0993, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048529085152091e-05, + "loss": 4.0979, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047692128281412e-05, + "loss": 4.1052, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.04685353353036e-05, + "loss": 4.1083, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046014938779308e-05, + "loss": 4.1131, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045176344028256e-05, + "loss": 4.1042, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044337749277203e-05, + "loss": 4.0966, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043500792406525e-05, + "loss": 4.1054, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042662197655473e-05, + "loss": 4.1028, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041823602904421e-05, + "loss": 4.1045, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.040985008153368e-05, + "loss": 4.1002, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040146413402317e-05, + "loss": 4.0991, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039307818651265e-05, + "loss": 4.1007, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038469223900213e-05, + "loss": 4.1131, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037630629149161e-05, + "loss": 4.0857, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036792034398109e-05, + "loss": 4.0994, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.03595507752743e-05, + "loss": 4.0968, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035116482776378e-05, + "loss": 4.1031, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034277888025326e-05, + "loss": 4.0933, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033439293274274e-05, + "loss": 4.1055, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.0326023364035946e-05, + "loss": 4.0912, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.0317637416525426e-05, + "loss": 4.1003, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.0309251469014906e-05, + "loss": 4.1043, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.0300865521504386e-05, + "loss": 4.0899, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.0292479573993866e-05, + "loss": 4.1001, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028409362648335e-05, + "loss": 4.114, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027570767897283e-05, + "loss": 4.1022, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026732173146231e-05, + "loss": 4.0966, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025895216275552e-05, + "loss": 4.1004, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.0250566215245e-05, + "loss": 4.1078, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024219664653821e-05, + "loss": 4.0919, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023381069902769e-05, + "loss": 4.1024, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022542475151717e-05, + "loss": 4.0877, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021703880400665e-05, + "loss": 4.0948, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020865285649613e-05, + "loss": 4.0918, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020028328778934e-05, + "loss": 4.0957, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019189734027882e-05, + "loss": 4.0939, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0183511392768306e-05, + "loss": 4.0916, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175125445257786e-05, + "loss": 4.0879, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0166739497747266e-05, + "loss": 4.106, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0158353550236746e-05, + "loss": 4.1019, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.0149983981529955e-05, + "loss": 4.1, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.0141598034019435e-05, + "loss": 4.0824, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.0133212086508915e-05, + "loss": 4.1108, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.0124826138998395e-05, + "loss": 4.0956, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011644019148787e-05, + "loss": 4.0992, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.0108070622781084e-05, + "loss": 4.1026, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.0099684675270564e-05, + "loss": 4.0962, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.0091298727760044e-05, + "loss": 4.0926, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.0082912780249524e-05, + "loss": 4.1111, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.0074526832739004e-05, + "loss": 4.085, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.0066140885228484e-05, + "loss": 4.1005, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.0057754937717964e-05, + "loss": 4.0911, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.0049368990207444e-05, + "loss": 4.0937, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.0040983042696924e-05, + "loss": 4.0924, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003261347399013e-05, + "loss": 4.0911, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002422752647961e-05, + "loss": 4.1021, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001585795777282e-05, + "loss": 4.0906, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.00074720102623e-05, + "loss": 4.0967, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 4.10824728012085, + "eval_runtime": 337.266, + "eval_samples_per_second": 1131.425, + "eval_steps_per_second": 35.358, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999908606275178e-05, + "loss": 4.0937, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999070011524126e-05, + "loss": 4.0885, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998231416773074e-05, + "loss": 4.0936, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997392822022022e-05, + "loss": 4.0914, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996554227270971e-05, + "loss": 4.1015, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995715632519919e-05, + "loss": 4.0868, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994877037768867e-05, + "loss": 4.0965, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994038443017815e-05, + "loss": 4.0886, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993199848266763e-05, + "loss": 4.0925, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992361253515711e-05, + "loss": 4.1007, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991522658764658e-05, + "loss": 4.0932, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990684064013606e-05, + "loss": 4.0919, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989847107142928e-05, + "loss": 4.0974, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989008512391876e-05, + "loss": 4.0829, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988169917640823e-05, + "loss": 4.0883, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987331322889771e-05, + "loss": 4.0829, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986492728138719e-05, + "loss": 4.0917, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985654133387668e-05, + "loss": 4.0854, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984815538636616e-05, + "loss": 4.0837, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.983976943885564e-05, + "loss": 4.0982, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983138349134512e-05, + "loss": 4.1054, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9822997543834597e-05, + "loss": 4.0998, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9814611596324077e-05, + "loss": 4.088, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.9806225648813557e-05, + "loss": 4.0924, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.9797872458910495e-05, + "loss": 4.0838, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9789486511399975e-05, + "loss": 4.0939, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.9781100563889455e-05, + "loss": 4.0885, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9772714616378935e-05, + "loss": 4.085, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9764328668868415e-05, + "loss": 4.0803, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9755942721357895e-05, + "loss": 4.0852, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9747556773847374e-05, + "loss": 4.0808, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973917082633686e-05, + "loss": 4.0976, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973078487882634e-05, + "loss": 4.0927, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972241531011955e-05, + "loss": 4.0875, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971402936260903e-05, + "loss": 4.083, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970565979390224e-05, + "loss": 4.0884, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969727384639172e-05, + "loss": 4.0886, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.96888878988812e-05, + "loss": 4.085, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968050195137068e-05, + "loss": 4.0841, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967211600386016e-05, + "loss": 4.072, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966373005634964e-05, + "loss": 4.0789, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965534410883912e-05, + "loss": 4.0934, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964697454013233e-05, + "loss": 4.0891, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963858859262181e-05, + "loss": 4.078, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9630202645111295e-05, + "loss": 4.0881, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962181669760077e-05, + "loss": 4.0792, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.9613447128893984e-05, + "loss": 4.0895, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.9605061181383464e-05, + "loss": 4.0829, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.9596675233872944e-05, + "loss": 4.0577, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958828928636242e-05, + "loss": 4.0927, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.95799033388519e-05, + "loss": 4.0833, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957153377014511e-05, + "loss": 4.0853, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956314782263459e-05, + "loss": 4.0796, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.9554761875124066e-05, + "loss": 4.0769, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954639230641728e-05, + "loss": 4.0747, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953800635890676e-05, + "loss": 4.076, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.952962041139624e-05, + "loss": 4.0787, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952123446388572e-05, + "loss": 4.0741, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.95128485163752e-05, + "loss": 4.0891, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950446256886468e-05, + "loss": 4.0718, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949607662135416e-05, + "loss": 4.0778, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948769067384364e-05, + "loss": 4.0916, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.947930472633312e-05, + "loss": 4.0623, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.94709187788226e-05, + "loss": 4.0676, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946253283131208e-05, + "loss": 4.0828, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945414688380156e-05, + "loss": 4.0808, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944577731509477e-05, + "loss": 4.0706, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943739136758425e-05, + "loss": 4.0739, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942900542007373e-05, + "loss": 4.0644, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942061947256322e-05, + "loss": 4.0786, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.94122335250527e-05, + "loss": 4.0833, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940384757754218e-05, + "loss": 4.0771, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939546163003166e-05, + "loss": 4.0813, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387092061324866e-05, + "loss": 4.086, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.9378706113814346e-05, + "loss": 4.1007, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.9370320166303826e-05, + "loss": 4.0668, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.9361934218793306e-05, + "loss": 4.079, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935354827128278e-05, + "loss": 4.0837, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934516232377226e-05, + "loss": 4.0688, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933677637626174e-05, + "loss": 4.0719, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9328406807554955e-05, + "loss": 4.0855, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9320020860044435e-05, + "loss": 4.0823, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.9311634912533915e-05, + "loss": 4.0879, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9303248965023395e-05, + "loss": 4.0652, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9294863017512875e-05, + "loss": 4.0721, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9286477070002355e-05, + "loss": 4.0709, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.9278091122491835e-05, + "loss": 4.0782, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.9269721553785044e-05, + "loss": 4.0797, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.9261335606274524e-05, + "loss": 4.0706, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.9252949658764004e-05, + "loss": 4.0658, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.9244563711253484e-05, + "loss": 4.0734, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.9236177763742964e-05, + "loss": 4.0673, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.9227791816232443e-05, + "loss": 4.0746, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.9219405868721923e-05, + "loss": 4.0821, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211019921211403e-05, + "loss": 4.0826, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920265035250462e-05, + "loss": 4.0719, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919428078379783e-05, + "loss": 4.0689, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918589483628731e-05, + "loss": 4.0759, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917750888877679e-05, + "loss": 4.0708, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916912294126627e-05, + "loss": 4.0792, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916075337255948e-05, + "loss": 4.0729, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915236742504896e-05, + "loss": 4.064, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914398147753844e-05, + "loss": 4.0806, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913559553002792e-05, + "loss": 4.0789, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.91272095825174e-05, + "loss": 4.057, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911882363500688e-05, + "loss": 4.0706, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.9110454066300086e-05, + "loss": 4.0632, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910206811878957e-05, + "loss": 4.0815, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909369855008278e-05, + "loss": 4.0619, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908531260257226e-05, + "loss": 4.0786, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907692665506174e-05, + "loss": 4.0622, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906854070755122e-05, + "loss": 4.0707, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.90601547600407e-05, + "loss": 4.0723, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905176881253018e-05, + "loss": 4.0652, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904338286501966e-05, + "loss": 4.069, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903499691750914e-05, + "loss": 4.0858, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902662734880235e-05, + "loss": 4.0712, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901824140129183e-05, + "loss": 4.0723, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.900985545378131e-05, + "loss": 4.0716, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900146950627079e-05, + "loss": 4.0753, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899308355876027e-05, + "loss": 4.071, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8984713990053487e-05, + "loss": 4.0706, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8976328042542966e-05, + "loss": 4.0576, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896794209503244e-05, + "loss": 4.0674, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.895955614752192e-05, + "loss": 4.063, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.89511702000114e-05, + "loss": 4.0672, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894278425250088e-05, + "loss": 4.0622, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893439830499036e-05, + "loss": 4.0667, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892602873628357e-05, + "loss": 4.0585, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891764278877305e-05, + "loss": 4.0813, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.890925684126253e-05, + "loss": 4.0685, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890087089375201e-05, + "loss": 4.0781, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.8892501325045224e-05, + "loss": 4.0507, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.8884115377534704e-05, + "loss": 4.0839, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.8875729430024184e-05, + "loss": 4.067, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.8867343482513664e-05, + "loss": 4.0719, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.8858957535003144e-05, + "loss": 4.0735, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.8850571587492624e-05, + "loss": 4.0681, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.8842185639982104e-05, + "loss": 4.0677, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.8833799692471584e-05, + "loss": 4.083, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882543012376479e-05, + "loss": 4.0525, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881704417625427e-05, + "loss": 4.0753, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880865822874375e-05, + "loss": 4.0673, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880027228123323e-05, + "loss": 4.0584, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879190271252645e-05, + "loss": 4.0653, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878351676501593e-05, + "loss": 4.0637, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877513081750541e-05, + "loss": 4.0776, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876674486999489e-05, + "loss": 4.0641, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.87583753012881e-05, + "loss": 4.0679, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 4.087896347045898, + "eval_runtime": 295.9934, + "eval_samples_per_second": 1289.188, + "eval_steps_per_second": 40.288, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.874998935377758e-05, + "loss": 4.0626, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874160340626706e-05, + "loss": 4.063, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873321745875654e-05, + "loss": 4.0629, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872483151124602e-05, + "loss": 4.0686, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.87164455637355e-05, + "loss": 4.0757, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870805961622497e-05, + "loss": 4.0572, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.869967366871445e-05, + "loss": 4.0672, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.8691304100007667e-05, + "loss": 4.0622, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.8682918152497147e-05, + "loss": 4.067, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.8674532204986626e-05, + "loss": 4.0739, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.8666146257476106e-05, + "loss": 4.0641, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.8657760309965586e-05, + "loss": 4.0669, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.86493907412588e-05, + "loss": 4.0742, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.8641004793748275e-05, + "loss": 4.0543, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8632618846237755e-05, + "loss": 4.0612, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8624232898727235e-05, + "loss": 4.0542, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8615863330020444e-05, + "loss": 4.0649, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8607477382509924e-05, + "loss": 4.0596, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8599091434999404e-05, + "loss": 4.0594, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8590705487488884e-05, + "loss": 4.0704, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858231953997837e-05, + "loss": 4.0758, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857394997127158e-05, + "loss": 4.0748, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856556402376106e-05, + "loss": 4.0655, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855717807625054e-05, + "loss": 4.0619, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854880850754375e-05, + "loss": 4.0568, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854042256003323e-05, + "loss": 4.0679, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853203661252271e-05, + "loss": 4.0632, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852365066501219e-05, + "loss": 4.0596, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851526471750167e-05, + "loss": 4.0546, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850687876999115e-05, + "loss": 4.0585, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849849282248063e-05, + "loss": 4.0543, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849010687497011e-05, + "loss": 4.0707, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848173730626332e-05, + "loss": 4.0692, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.8473351358752805e-05, + "loss": 4.0627, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.8464965411242285e-05, + "loss": 4.0579, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.8456595842535494e-05, + "loss": 4.0595, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.8448209895024974e-05, + "loss": 4.0645, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.8439823947514454e-05, + "loss": 4.0604, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.8431438000003934e-05, + "loss": 4.0588, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842306843129714e-05, + "loss": 4.0457, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841468248378662e-05, + "loss": 4.0551, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.84062965362761e-05, + "loss": 4.0617, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839792696756931e-05, + "loss": 4.0611, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.838954102005879e-05, + "loss": 4.0583, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838115507254827e-05, + "loss": 4.0591, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837276912503776e-05, + "loss": 4.058, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836438317752724e-05, + "loss": 4.06, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835599723001672e-05, + "loss": 4.0579, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.83476112825062e-05, + "loss": 4.0313, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.833922533499568e-05, + "loss": 4.0678, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833083938748516e-05, + "loss": 4.0582, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832245343997464e-05, + "loss": 4.0614, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831408387126785e-05, + "loss": 4.0534, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830569792375733e-05, + "loss": 4.0513, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829731197624681e-05, + "loss": 4.0497, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828892602873628e-05, + "loss": 4.0492, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828054008122576e-05, + "loss": 4.0565, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.8272170512518976e-05, + "loss": 4.041, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.8263784565008456e-05, + "loss": 4.0627, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.8255398617497936e-05, + "loss": 4.0516, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.8247012669987416e-05, + "loss": 4.0493, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.8238626722476896e-05, + "loss": 4.0691, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.8230240774966376e-05, + "loss": 4.0404, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.8221854827455856e-05, + "loss": 4.0391, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.8213468879945336e-05, + "loss": 4.0586, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.8205099311238545e-05, + "loss": 4.0568, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8196713363728025e-05, + "loss": 4.0463, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8188327416217505e-05, + "loss": 4.0497, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8179941468706985e-05, + "loss": 4.0331, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8171555521196465e-05, + "loss": 4.0553, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816318595248968e-05, + "loss": 4.0571, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815480000497916e-05, + "loss": 4.0572, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814641405746864e-05, + "loss": 4.0516, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813802810995812e-05, + "loss": 4.0603, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.812965854125133e-05, + "loss": 4.0754, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812127259374081e-05, + "loss": 4.0471, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811288664623029e-05, + "loss": 4.0572, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810450069871977e-05, + "loss": 4.0529, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809613113001298e-05, + "loss": 4.0494, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808774518250246e-05, + "loss": 4.0445, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.807935923499194e-05, + "loss": 4.0625, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807097328748142e-05, + "loss": 4.0566, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.8062603718774634e-05, + "loss": 4.0616, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805423415006784e-05, + "loss": 4.0437, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804584820255732e-05, + "loss": 4.0479, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.80374622550468e-05, + "loss": 4.0483, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.802907630753628e-05, + "loss": 4.0526, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802069036002576e-05, + "loss": 4.0552, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801232079131897e-05, + "loss": 4.048, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800395122261218e-05, + "loss": 4.0379, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799556527510166e-05, + "loss": 4.0531, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798717932759114e-05, + "loss": 4.0444, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797879338008062e-05, + "loss": 4.0473, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.79704074325701e-05, + "loss": 4.0564, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796203786386332e-05, + "loss": 4.0581, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.79536519163528e-05, + "loss": 4.0507, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794526596884228e-05, + "loss": 4.0459, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793688002133176e-05, + "loss": 4.0474, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792849407382124e-05, + "loss": 4.0475, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792010812631072e-05, + "loss": 4.0568, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.79117221788002e-05, + "loss": 4.0483, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790333623128968e-05, + "loss": 4.0449, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789495028377916e-05, + "loss": 4.0522, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.7886580715072366e-05, + "loss": 4.0557, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.7878194767561846e-05, + "loss": 4.0327, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.7869808820051326e-05, + "loss": 4.0475, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.7861422872540806e-05, + "loss": 4.0387, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785305330383402e-05, + "loss": 4.0554, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.78446673563235e-05, + "loss": 4.039, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783628140881298e-05, + "loss": 4.0537, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782789546130246e-05, + "loss": 4.0383, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.781950951379194e-05, + "loss": 4.0523, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.7811123566281415e-05, + "loss": 4.047, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780275399757463e-05, + "loss": 4.0405, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779436805006411e-05, + "loss": 4.0475, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778598210255359e-05, + "loss": 4.0612, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.7777596155043063e-05, + "loss": 4.0465, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.7769210207532543e-05, + "loss": 4.0528, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.7760824260022023e-05, + "loss": 4.0438, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.77524383125115e-05, + "loss": 4.0506, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774405236500099e-05, + "loss": 4.0521, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.77356827962942e-05, + "loss": 4.0441, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772729684878368e-05, + "loss": 4.0385, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771892728007689e-05, + "loss": 4.0434, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771054133256637e-05, + "loss": 4.0435, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770215538505585e-05, + "loss": 4.0426, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769376943754533e-05, + "loss": 4.0419, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768539986883854e-05, + "loss": 4.041, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767701392132802e-05, + "loss": 4.0354, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.76686279738175e-05, + "loss": 4.0553, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766024202630698e-05, + "loss": 4.0444, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765187245760019e-05, + "loss": 4.0542, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764348651008967e-05, + "loss": 4.0284, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763510056257915e-05, + "loss": 4.0574, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762671461506863e-05, + "loss": 4.0481, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761832866755811e-05, + "loss": 4.0484, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.760994272004759e-05, + "loss": 4.0465, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760155677253707e-05, + "loss": 4.0444, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759317082502655e-05, + "loss": 4.0475, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758478487751603e-05, + "loss": 4.0595, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757643168761297e-05, + "loss": 4.0313, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756804574010245e-05, + "loss": 4.0493, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.755965979259193e-05, + "loss": 4.042, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755127384508141e-05, + "loss": 4.0402, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.75428878975709e-05, + "loss": 4.0444, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753450195006038e-05, + "loss": 4.0398, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752611600254986e-05, + "loss": 4.0484, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751773005503934e-05, + "loss": 4.0474, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.7509360486332546e-05, + "loss": 4.0421, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 4.072147846221924, + "eval_runtime": 292.5316, + "eval_samples_per_second": 1304.443, + "eval_steps_per_second": 40.765, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.7500974538822026e-05, + "loss": 4.0414, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.7492588591311506e-05, + "loss": 4.0414, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7484202643800986e-05, + "loss": 4.0397, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7475816696290466e-05, + "loss": 4.047, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.7467430748779946e-05, + "loss": 4.0511, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459044801269426e-05, + "loss": 4.0362, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.74506588537589e-05, + "loss": 4.0439, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744227290624838e-05, + "loss": 4.043, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.7433886958737866e-05, + "loss": 4.042, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.7425501011227346e-05, + "loss": 4.0481, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7417115063716826e-05, + "loss": 4.0415, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.7408729116206306e-05, + "loss": 4.0461, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.7400359547499515e-05, + "loss": 4.051, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.7391973599988995e-05, + "loss": 4.0326, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.7383587652478475e-05, + "loss": 4.0387, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.7375201704967955e-05, + "loss": 4.0284, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.7366815757457435e-05, + "loss": 4.0442, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.7358429809946915e-05, + "loss": 4.0379, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.7350043862436395e-05, + "loss": 4.0344, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7341657914925875e-05, + "loss": 4.0461, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7333271967415355e-05, + "loss": 4.0507, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7324902398708564e-05, + "loss": 4.0495, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7316516451198044e-05, + "loss": 4.0452, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730813050368753e-05, + "loss": 4.0409, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.729974455617701e-05, + "loss": 4.0381, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729135860866649e-05, + "loss": 4.0413, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7282972661155963e-05, + "loss": 4.039, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.7274586713645443e-05, + "loss": 4.0396, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726620076613492e-05, + "loss": 4.0334, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725783119742814e-05, + "loss": 4.0346, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.724946162872135e-05, + "loss": 4.0333, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724107568121083e-05, + "loss": 4.0408, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723268973370031e-05, + "loss": 4.0494, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722430378618979e-05, + "loss": 4.0408, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721591783867927e-05, + "loss": 4.037, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.7207548269972484e-05, + "loss": 4.0344, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7199162322461964e-05, + "loss": 4.0457, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719077637495144e-05, + "loss": 4.0374, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718239042744092e-05, + "loss": 4.0351, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717402085873413e-05, + "loss": 4.0228, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716563491122361e-05, + "loss": 4.0358, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.7157248963713086e-05, + "loss": 4.0372, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7148863016202566e-05, + "loss": 4.0398, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.7140477068692046e-05, + "loss": 4.0369, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.7132091121181526e-05, + "loss": 4.0359, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.7123705173671006e-05, + "loss": 4.0325, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7115319226160486e-05, + "loss": 4.0389, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.7106933278649966e-05, + "loss": 4.0372, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709856370994318e-05, + "loss": 4.0101, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709017776243266e-05, + "loss": 4.0435, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708179181492214e-05, + "loss": 4.0356, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707342224621535e-05, + "loss": 4.0405, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706503629870483e-05, + "loss": 4.032, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705665035119431e-05, + "loss": 4.0296, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704826440368379e-05, + "loss": 4.0262, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.703987845617327e-05, + "loss": 4.0262, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703149250866275e-05, + "loss": 4.0405, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702310656115223e-05, + "loss": 4.0152, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701473699244544e-05, + "loss": 4.0433, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700635104493492e-05, + "loss": 4.0265, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6997965097424406e-05, + "loss": 4.0261, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6989579149913886e-05, + "loss": 4.0498, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6981209581207095e-05, + "loss": 4.0223, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6972823633696575e-05, + "loss": 4.018, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.6964437686186055e-05, + "loss": 4.0358, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.6956051738675535e-05, + "loss": 4.0361, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.6947665791165015e-05, + "loss": 4.0227, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.6939279843654495e-05, + "loss": 4.0296, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.6930893896143975e-05, + "loss": 4.0145, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692250794863345e-05, + "loss": 4.0289, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691415475873039e-05, + "loss": 4.0381, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690576881121987e-05, + "loss": 4.0346, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689738286370936e-05, + "loss": 4.0305, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688899691619884e-05, + "loss": 4.0376, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688061096868832e-05, + "loss": 4.052, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.68722250211778e-05, + "loss": 4.0289, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686383907366727e-05, + "loss": 4.0326, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685546950496049e-05, + "loss": 4.0298, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684708355744997e-05, + "loss": 4.0303, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683869760993945e-05, + "loss": 4.022, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683031166242892e-05, + "loss": 4.0429, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.68219257149184e-05, + "loss": 4.0335, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681353976740788e-05, + "loss": 4.0423, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680515381989736e-05, + "loss": 4.0175, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679678425119058e-05, + "loss": 4.0285, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678839830368006e-05, + "loss": 4.0282, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678001235616954e-05, + "loss": 4.0298, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677162640865902e-05, + "loss": 4.0323, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.67632404611485e-05, + "loss": 4.0307, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675485451363798e-05, + "loss": 4.0166, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6746484944931187e-05, + "loss": 4.0295, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6738098997420667e-05, + "loss": 4.0263, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.6729713049910146e-05, + "loss": 4.0234, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.6721327102399626e-05, + "loss": 4.0351, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6712941154889106e-05, + "loss": 4.0415, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.6704555207378586e-05, + "loss": 4.0259, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.6696169259868066e-05, + "loss": 4.0277, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.6687783312357546e-05, + "loss": 4.0281, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.667941374365076e-05, + "loss": 4.0221, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667104417494397e-05, + "loss": 4.0371, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666265822743345e-05, + "loss": 4.0264, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665427227992293e-05, + "loss": 4.026, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664588633241241e-05, + "loss": 4.0307, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663750038490189e-05, + "loss": 4.0276, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.662911443739137e-05, + "loss": 4.0215, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662074486868458e-05, + "loss": 4.0234, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661235892117406e-05, + "loss": 4.0164, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660397297366354e-05, + "loss": 4.0326, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659558702615302e-05, + "loss": 4.0256, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.65872010786425e-05, + "loss": 4.0262, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657881513113198e-05, + "loss": 4.0105, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657042918362146e-05, + "loss": 4.0275, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656204323611094e-05, + "loss": 4.0308, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.6553673667404156e-05, + "loss": 4.0198, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.6545287719893636e-05, + "loss": 4.0304, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653690177238311e-05, + "loss": 4.0388, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652851582487259e-05, + "loss": 4.0237, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652012987736207e-05, + "loss": 4.0334, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651174392985155e-05, + "loss": 4.0241, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650335798234103e-05, + "loss": 4.0299, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649497203483051e-05, + "loss": 4.031, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648660246612372e-05, + "loss": 4.0198, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.64782165186132e-05, + "loss": 4.019, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6469846949906414e-05, + "loss": 4.0235, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6461461002395893e-05, + "loss": 4.0256, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6453075054885373e-05, + "loss": 4.025, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644468910737485e-05, + "loss": 4.0158, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643630315986433e-05, + "loss": 4.0224, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642793359115754e-05, + "loss": 4.0125, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.641954764364702e-05, + "loss": 4.0349, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.64111616961365e-05, + "loss": 4.0233, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640277574862598e-05, + "loss": 4.0334, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639438980111546e-05, + "loss": 4.0144, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638602023240867e-05, + "loss": 4.0323, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637763428489815e-05, + "loss": 4.0275, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.636924833738764e-05, + "loss": 4.0267, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636086238987712e-05, + "loss": 4.0285, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.63524764423666e-05, + "loss": 4.0244, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634410687365981e-05, + "loss": 4.0251, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633572092614929e-05, + "loss": 4.0395, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632733497863877e-05, + "loss": 4.0115, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631894903112825e-05, + "loss": 4.0293, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631056308361773e-05, + "loss": 4.0188, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630217713610721e-05, + "loss": 4.0204, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629379118859669e-05, + "loss": 4.0229, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628540524108617e-05, + "loss": 4.0184, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627701929357564e-05, + "loss": 4.0303, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6268649724868856e-05, + "loss": 4.0279, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6260263777358336e-05, + "loss": 4.0218, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 4.057968616485596, + "eval_runtime": 295.9943, + "eval_samples_per_second": 1289.183, + "eval_steps_per_second": 40.288, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.6251877829847816e-05, + "loss": 4.017, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.6243491882337296e-05, + "loss": 4.0208, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623512231363051e-05, + "loss": 4.0214, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622673636611999e-05, + "loss": 4.0259, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621835041860947e-05, + "loss": 4.0312, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.6209964471098945e-05, + "loss": 4.017, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620159490239216e-05, + "loss": 4.0256, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619320895488164e-05, + "loss": 4.0244, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.6184823007371114e-05, + "loss": 4.0201, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617645343866433e-05, + "loss": 4.0226, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616806749115381e-05, + "loss": 4.0276, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.615968154364329e-05, + "loss": 4.0218, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6151311974936505e-05, + "loss": 4.0309, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.6142926027425985e-05, + "loss": 4.0127, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.6134540079915465e-05, + "loss": 4.0192, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6126154132404945e-05, + "loss": 4.0057, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611776818489442e-05, + "loss": 4.0294, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.61093822373839e-05, + "loss": 4.0174, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610099628987338e-05, + "loss": 4.0146, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609261034236286e-05, + "loss": 4.0249, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608422439485234e-05, + "loss": 4.0295, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607585482614555e-05, + "loss": 4.0273, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606746887863503e-05, + "loss": 4.0278, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.605908293112451e-05, + "loss": 4.0215, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6050696983613994e-05, + "loss": 4.0214, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.60423274149072e-05, + "loss": 4.0252, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603394146739668e-05, + "loss": 4.0122, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602555551988616e-05, + "loss": 4.0218, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601716957237564e-05, + "loss": 4.0165, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600878362486512e-05, + "loss": 4.0148, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.60003976773546e-05, + "loss": 4.0165, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599201172984408e-05, + "loss": 4.0229, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598364216113729e-05, + "loss": 4.0239, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597525621362677e-05, + "loss": 4.0291, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596687026611625e-05, + "loss": 4.0138, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595848431860573e-05, + "loss": 4.0136, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595009837109521e-05, + "loss": 4.0263, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594171242358469e-05, + "loss": 4.015, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593332647607418e-05, + "loss": 4.0206, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592495690736739e-05, + "loss": 4.0067, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591657095985687e-05, + "loss": 4.0123, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590818501234635e-05, + "loss": 4.018, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.589979906483583e-05, + "loss": 4.0206, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589141311732531e-05, + "loss": 4.018, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588302716981478e-05, + "loss": 4.0152, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587464122230426e-05, + "loss": 4.0167, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586625527479374e-05, + "loss": 4.0164, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.585788570608695e-05, + "loss": 4.0206, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.584949975857643e-05, + "loss": 3.9938, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5841130189869645e-05, + "loss": 4.0202, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583274424235913e-05, + "loss": 4.0128, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.5824358294848605e-05, + "loss": 4.0224, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.5815972347338085e-05, + "loss": 4.0124, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.5807586399827565e-05, + "loss": 4.0081, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.5799200452317045e-05, + "loss": 4.0085, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5790830883610254e-05, + "loss": 4.0075, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.5782444936099734e-05, + "loss": 4.0195, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.5774058988589214e-05, + "loss": 3.9959, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.5765673041078694e-05, + "loss": 4.0271, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.5757287093568174e-05, + "loss": 4.0112, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.5748901146057654e-05, + "loss": 4.0049, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.5740515198547134e-05, + "loss": 4.0283, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.5732129251036614e-05, + "loss": 4.0039, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572375968232983e-05, + "loss": 4.0006, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571539011362304e-05, + "loss": 4.0178, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570700416611252e-05, + "loss": 4.0162, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.5698618218602e-05, + "loss": 4.002, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569023227109148e-05, + "loss": 4.0132, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568184632358096e-05, + "loss": 3.994, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567347675487417e-05, + "loss": 4.0102, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566509080736365e-05, + "loss": 4.0218, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565670485985313e-05, + "loss": 4.0154, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564831891234261e-05, + "loss": 4.0141, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.563993296483209e-05, + "loss": 4.0182, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563154701732157e-05, + "loss": 4.0327, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562316106981105e-05, + "loss": 4.0119, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.5614775122300534e-05, + "loss": 4.0174, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560642193239747e-05, + "loss": 4.0084, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559803598488695e-05, + "loss": 4.011, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.558965003737643e-05, + "loss": 4.0073, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558126408986591e-05, + "loss": 4.0201, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557287814235539e-05, + "loss": 4.0195, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556449219484487e-05, + "loss": 4.0225, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555612262613808e-05, + "loss": 4.0039, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554773667862756e-05, + "loss": 4.0098, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.553935073111704e-05, + "loss": 4.008, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553096478360652e-05, + "loss": 4.0091, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5522578836096e-05, + "loss": 4.0137, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551420926738922e-05, + "loss": 4.0141, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.55058233198787e-05, + "loss": 4.001, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549743737236818e-05, + "loss": 4.0095, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.548905142485766e-05, + "loss": 4.0085, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548066547734714e-05, + "loss": 4.0034, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.547227952983661e-05, + "loss": 4.0191, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546389358232609e-05, + "loss": 4.0244, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545550763481557e-05, + "loss": 4.011, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5447138066108786e-05, + "loss": 4.0051, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543875211859826e-05, + "loss": 4.011, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.5430382549891475e-05, + "loss": 4.0039, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542201298118469e-05, + "loss": 4.0162, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541362703367417e-05, + "loss": 4.0143, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540524108616365e-05, + "loss": 4.0036, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539685513865313e-05, + "loss": 4.015, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538846919114261e-05, + "loss": 4.0053, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.5380083243632084e-05, + "loss": 4.0053, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.5371697296121564e-05, + "loss": 4.0028, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.5363311348611044e-05, + "loss": 4.0018, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535494177990426e-05, + "loss": 4.0121, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534655583239373e-05, + "loss": 4.0122, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533816988488321e-05, + "loss": 4.0065, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.532978393737269e-05, + "loss": 3.9954, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532139798986218e-05, + "loss": 4.0082, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531301204235166e-05, + "loss": 4.0133, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530462609484114e-05, + "loss": 4.0014, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529624014733062e-05, + "loss": 4.0141, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528787057862383e-05, + "loss": 4.0186, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.527948463111331e-05, + "loss": 4.0114, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527109868360279e-05, + "loss": 4.0111, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526271273609227e-05, + "loss": 4.0102, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525432678858175e-05, + "loss": 4.0132, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524594084107123e-05, + "loss": 4.0131, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523757127236444e-05, + "loss": 4.0021, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.522918532485392e-05, + "loss": 4.0028, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.52207993773434e-05, + "loss": 4.0066, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521241342983288e-05, + "loss": 4.0071, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.5204027482322364e-05, + "loss": 4.0055, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519565791361557e-05, + "loss": 4.0037, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518727196610505e-05, + "loss": 4.0006, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517888601859453e-05, + "loss": 3.9978, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517050007108401e-05, + "loss": 4.0202, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516211412357349e-05, + "loss": 4.0048, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.51537445548667e-05, + "loss": 4.0178, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514535860735618e-05, + "loss": 3.9955, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513697265984566e-05, + "loss": 4.0164, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512858671233514e-05, + "loss": 4.0125, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512020076482462e-05, + "loss": 4.0098, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511183119611783e-05, + "loss": 4.0061, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510344524860731e-05, + "loss": 4.0101, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.50950593010968e-05, + "loss": 4.0099, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508667335358627e-05, + "loss": 4.0177, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507828740607575e-05, + "loss": 4.0012, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.506990145856523e-05, + "loss": 4.0062, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.5061531889858446e-05, + "loss": 4.0065, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505314594234792e-05, + "loss": 4.0046, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.50447599948374e-05, + "loss": 4.0034, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503637404732688e-05, + "loss": 4.006, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502798809981636e-05, + "loss": 4.01, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.501960215230584e-05, + "loss": 4.0096, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501123258359905e-05, + "loss": 4.0062, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 4.047466278076172, + "eval_runtime": 296.3913, + "eval_samples_per_second": 1287.457, + "eval_steps_per_second": 40.234, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.5002846636088535e-05, + "loss": 4.0085, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.4994460688578015e-05, + "loss": 4.0006, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.4986074741067495e-05, + "loss": 4.0069, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.4977688793556975e-05, + "loss": 4.0097, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4969302846046455e-05, + "loss": 4.0084, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.4960916898535935e-05, + "loss": 4.0057, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4952530951025415e-05, + "loss": 4.0086, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.4944145003514895e-05, + "loss": 4.0061, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.4935759056004375e-05, + "loss": 4.0, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.4927373108493855e-05, + "loss": 4.0088, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.4918987160983335e-05, + "loss": 4.0127, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.491060121347281e-05, + "loss": 4.0047, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4902231644766024e-05, + "loss": 4.0199, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4893845697255504e-05, + "loss": 3.991, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4885459749744984e-05, + "loss": 4.0009, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.4877073802234464e-05, + "loss": 3.9913, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4868687854723944e-05, + "loss": 4.0144, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.4860301907213424e-05, + "loss": 3.9992, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485193233850663e-05, + "loss": 3.9987, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484354639099611e-05, + "loss": 4.0056, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483516044348559e-05, + "loss": 4.0149, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482677449597507e-05, + "loss": 4.0129, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481838854846455e-05, + "loss": 4.0085, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481000260095403e-05, + "loss": 4.0054, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480161665344351e-05, + "loss": 4.0074, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479323070593299e-05, + "loss": 4.0052, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478484475842247e-05, + "loss": 3.995, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477645881091195e-05, + "loss": 4.0035, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476807286340143e-05, + "loss": 4.0005, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.475968691589092e-05, + "loss": 3.9966, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475131734718413e-05, + "loss": 4.001, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474293139967361e-05, + "loss": 4.0035, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473456183096682e-05, + "loss": 4.0088, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.47261758834563e-05, + "loss": 4.0131, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471778993594578e-05, + "loss": 3.9984, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.470940398843526e-05, + "loss": 3.9968, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.4701034419728466e-05, + "loss": 4.0124, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.4692648472217946e-05, + "loss": 3.994, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.4684262524707426e-05, + "loss": 4.0041, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467589295600064e-05, + "loss": 3.9946, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466750700849012e-05, + "loss": 3.9945, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.46591210609796e-05, + "loss": 4.0019, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465073511346908e-05, + "loss": 4.0054, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464234916595856e-05, + "loss": 3.9994, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463396321844804e-05, + "loss": 4.0001, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462557727093752e-05, + "loss": 3.9998, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.4617191323426995e-05, + "loss": 3.9994, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4608805375916475e-05, + "loss": 4.0042, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460043580720969e-05, + "loss": 3.981, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459204985969917e-05, + "loss": 4.006, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4583663912188644e-05, + "loss": 3.9969, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.4575277964678124e-05, + "loss": 4.0077, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.4566892017167604e-05, + "loss": 3.9937, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455852244846082e-05, + "loss": 3.9966, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.45501365009503e-05, + "loss": 3.9913, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454175055343978e-05, + "loss": 3.9915, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453336460592926e-05, + "loss": 4.0031, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452497865841874e-05, + "loss": 3.9783, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451659271090822e-05, + "loss": 4.0107, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.45082067633977e-05, + "loss": 3.9948, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.449982081588718e-05, + "loss": 3.9872, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449145124718039e-05, + "loss": 4.0146, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448306529966987e-05, + "loss": 3.9835, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447467935215935e-05, + "loss": 3.9844, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446630978345256e-05, + "loss": 3.998, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4457923835942044e-05, + "loss": 4.0008, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4449537888431524e-05, + "loss": 3.9897, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.4441151940921004e-05, + "loss": 3.9983, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.4432765993410484e-05, + "loss": 3.9772, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442439642470369e-05, + "loss": 3.9945, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441601047719317e-05, + "loss": 4.0042, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440762452968265e-05, + "loss": 4.0016, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.439923858217213e-05, + "loss": 3.9945, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439085263466161e-05, + "loss": 4.0019, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438248306595482e-05, + "loss": 4.0169, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.43740971184443e-05, + "loss": 3.9951, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436571117093378e-05, + "loss": 4.0041, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435732522342326e-05, + "loss": 3.9893, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.434893927591274e-05, + "loss": 3.9967, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434055332840223e-05, + "loss": 3.9891, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433216738089171e-05, + "loss": 4.0049, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432378143338118e-05, + "loss": 4.0012, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431539548587066e-05, + "loss": 4.0081, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430702591716388e-05, + "loss": 3.9918, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429863996965336e-05, + "loss": 3.9909, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4290270400946566e-05, + "loss": 3.9888, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4281884453436046e-05, + "loss": 4.0006, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.4273498505925526e-05, + "loss": 3.9928, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.4265112558415006e-05, + "loss": 3.9982, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425672661090448e-05, + "loss": 3.9866, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.4248340663393966e-05, + "loss": 3.9943, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.4239954715883446e-05, + "loss": 3.9906, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.4231568768372926e-05, + "loss": 3.9879, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.4223199199666135e-05, + "loss": 3.999, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.4214813252155615e-05, + "loss": 4.0094, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.4206427304645095e-05, + "loss": 3.9973, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.4198041357134575e-05, + "loss": 3.9907, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.4189655409624055e-05, + "loss": 3.9916, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.4181285840917264e-05, + "loss": 3.9918, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.4172899893406744e-05, + "loss": 4.0012, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.4164513945896224e-05, + "loss": 3.9958, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.4156127998385704e-05, + "loss": 3.9865, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4147742050875184e-05, + "loss": 4.0003, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.41393724821684e-05, + "loss": 3.9941, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413100291346161e-05, + "loss": 3.9909, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412261696595109e-05, + "loss": 3.9882, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411423101844057e-05, + "loss": 3.9886, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410584507093005e-05, + "loss": 3.9924, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409745912341953e-05, + "loss": 3.9957, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.408907317590901e-05, + "loss": 3.9901, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408068722839849e-05, + "loss": 3.9802, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.40723176596917e-05, + "loss": 3.9915, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406393171218118e-05, + "loss": 3.9989, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405554576467066e-05, + "loss": 3.9897, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404715981716014e-05, + "loss": 3.9948, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403877386964962e-05, + "loss": 4.0026, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.4030404300942833e-05, + "loss": 3.9956, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.4022018353432313e-05, + "loss": 3.9961, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401363240592179e-05, + "loss": 3.9946, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400524645841127e-05, + "loss": 3.9971, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399687688970448e-05, + "loss": 4.0039, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398849094219396e-05, + "loss": 3.9824, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398010499468344e-05, + "loss": 3.991, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397171904717292e-05, + "loss": 3.9864, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.39633330996624e-05, + "loss": 3.9926, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395494715215188e-05, + "loss": 3.9899, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394656120464136e-05, + "loss": 3.9881, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393819163593457e-05, + "loss": 3.9802, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.392982206722779e-05, + "loss": 3.9857, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392143611971727e-05, + "loss": 4.0018, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391305017220675e-05, + "loss": 3.9937, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390466422469623e-05, + "loss": 3.9987, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389627827718571e-05, + "loss": 3.9848, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388789232967519e-05, + "loss": 3.9982, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.387950638216467e-05, + "loss": 3.9991, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387112043465414e-05, + "loss": 3.9945, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386273448714362e-05, + "loss": 3.989, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.38543485396331e-05, + "loss": 3.9953, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384596259212258e-05, + "loss": 3.9981, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383757664461206e-05, + "loss": 4.0021, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.3829207075905276e-05, + "loss": 3.9873, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.3820821128394756e-05, + "loss": 3.9892, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3812435180884236e-05, + "loss": 3.9906, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.3804049233373716e-05, + "loss": 3.9907, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.3795663285863196e-05, + "loss": 3.987, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.3787277338352676e-05, + "loss": 3.993, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3778907769645885e-05, + "loss": 3.9886, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.3770521822135365e-05, + "loss": 3.9989, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.3762135874624845e-05, + "loss": 3.9891, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 4.038130760192871, + "eval_runtime": 375.9291, + "eval_samples_per_second": 1015.061, + "eval_steps_per_second": 31.721, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.3753749927114324e-05, + "loss": 4.0002, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.3745363979603804e-05, + "loss": 3.9847, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.3736978032093284e-05, + "loss": 3.9893, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.3728592084582764e-05, + "loss": 3.9976, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.3720206137072244e-05, + "loss": 3.9926, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.3711820189561724e-05, + "loss": 3.9937, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.3703434242051204e-05, + "loss": 3.9891, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.3695048294540684e-05, + "loss": 3.9906, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.3686662347030164e-05, + "loss": 3.9834, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.3678276399519644e-05, + "loss": 3.999, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.3669890452009124e-05, + "loss": 3.9901, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.3661504504498604e-05, + "loss": 3.9946, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.365313493579181e-05, + "loss": 4.003, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.364474898828129e-05, + "loss": 3.9763, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.363636304077077e-05, + "loss": 3.9872, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.362797709326025e-05, + "loss": 3.9751, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.361959114574973e-05, + "loss": 3.9985, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361120519823921e-05, + "loss": 3.984, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360281925072869e-05, + "loss": 3.9859, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.359444968202191e-05, + "loss": 3.9859, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.358606373451139e-05, + "loss": 4.0018, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.357767778700087e-05, + "loss": 3.9948, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.356929183949035e-05, + "loss": 3.9954, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.356090589197983e-05, + "loss": 3.99, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.355251994446931e-05, + "loss": 3.9975, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.354413399695879e-05, + "loss": 3.9867, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.353574804944827e-05, + "loss": 3.9839, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.352736210193774e-05, + "loss": 3.9852, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.351899253323096e-05, + "loss": 3.9856, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.351060658572044e-05, + "loss": 3.9794, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350222063820991e-05, + "loss": 3.9857, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.349383469069939e-05, + "loss": 3.9897, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348544874318888e-05, + "loss": 3.9956, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.347706279567836e-05, + "loss": 3.9957, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.346867684816784e-05, + "loss": 3.9836, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346032365826478e-05, + "loss": 3.9822, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.345193771075426e-05, + "loss": 4.0007, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.344355176324374e-05, + "loss": 3.973, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.3435165815733215e-05, + "loss": 3.9916, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.3426779868222695e-05, + "loss": 3.9804, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.3418393920712175e-05, + "loss": 3.9746, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.3410007973201655e-05, + "loss": 3.9872, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.3401622025691135e-05, + "loss": 3.9911, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.3393236078180615e-05, + "loss": 3.9845, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.3384850130670095e-05, + "loss": 3.9871, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.3376464183159575e-05, + "loss": 3.9857, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.336809461445279e-05, + "loss": 3.984, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.3359725045746e-05, + "loss": 3.9902, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.335133909823548e-05, + "loss": 3.966, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.334295315072496e-05, + "loss": 3.9851, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.333456720321444e-05, + "loss": 3.9856, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.332618125570392e-05, + "loss": 3.9961, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.331781168699713e-05, + "loss": 3.9777, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.330942573948661e-05, + "loss": 3.9835, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.330103979197609e-05, + "loss": 3.9684, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329265384446557e-05, + "loss": 3.9794, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.328426789695505e-05, + "loss": 3.9914, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.327588194944453e-05, + "loss": 3.9642, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.3267496001934015e-05, + "loss": 3.994, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.3259110054423495e-05, + "loss": 3.9824, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.3250724106912975e-05, + "loss": 3.9776, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.3242338159402455e-05, + "loss": 3.9966, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.323395221189193e-05, + "loss": 3.9676, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.322556626438141e-05, + "loss": 3.9698, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.3217196695674624e-05, + "loss": 3.9795, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.3208810748164104e-05, + "loss": 3.9918, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.320042480065358e-05, + "loss": 3.9734, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.319203885314306e-05, + "loss": 3.9806, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.318366928443627e-05, + "loss": 3.9626, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.317528333692575e-05, + "loss": 3.9798, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.316689738941523e-05, + "loss": 3.9888, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.315851144190471e-05, + "loss": 3.9913, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.315012549439419e-05, + "loss": 3.9788, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314173954688367e-05, + "loss": 3.9903, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.313335359937315e-05, + "loss": 3.9994, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.312496765186263e-05, + "loss": 3.9825, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.311659808315584e-05, + "loss": 3.9831, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.310821213564532e-05, + "loss": 3.9809, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.30998261881348e-05, + "loss": 3.9836, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.309144024062428e-05, + "loss": 3.9757, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.308307067191749e-05, + "loss": 3.9869, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.307468472440697e-05, + "loss": 3.9843, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.306629877689645e-05, + "loss": 3.9959, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.305791282938593e-05, + "loss": 3.9834, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.304952688187542e-05, + "loss": 3.9721, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.3041173691972356e-05, + "loss": 3.9727, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.3032787744461836e-05, + "loss": 3.9867, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.3024401796951316e-05, + "loss": 3.9741, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.3016015849440796e-05, + "loss": 3.984, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.3007646280734005e-05, + "loss": 3.9764, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.2999260333223485e-05, + "loss": 3.9753, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.2990874385712965e-05, + "loss": 3.9803, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.2982488438202445e-05, + "loss": 3.9744, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.2974102490691925e-05, + "loss": 3.9829, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.2965716543181405e-05, + "loss": 3.9914, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.295734697447462e-05, + "loss": 3.9861, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.29489610269641e-05, + "loss": 3.9712, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.294057507945358e-05, + "loss": 3.9806, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.293218913194306e-05, + "loss": 3.9741, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292380318443254e-05, + "loss": 3.9852, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291541723692202e-05, + "loss": 3.9852, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.29070312894115e-05, + "loss": 3.9693, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.289864534190098e-05, + "loss": 3.9866, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.289025939439046e-05, + "loss": 3.9779, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.288188982568367e-05, + "loss": 3.977, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.287350387817315e-05, + "loss": 3.9742, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.286511793066263e-05, + "loss": 3.9725, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285673198315211e-05, + "loss": 3.9789, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.2848362414445325e-05, + "loss": 3.9831, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.2839976466934805e-05, + "loss": 3.9744, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.2831590519424285e-05, + "loss": 3.9662, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.2823204571913765e-05, + "loss": 3.9728, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.2814835003206974e-05, + "loss": 3.9867, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.2806449055696454e-05, + "loss": 3.9736, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.2798063108185934e-05, + "loss": 3.9809, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.278967716067541e-05, + "loss": 3.9826, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.278129121316489e-05, + "loss": 3.9869, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.277293802326183e-05, + "loss": 3.9815, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.276455207575131e-05, + "loss": 3.9778, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275616612824079e-05, + "loss": 3.9869, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.274778018073028e-05, + "loss": 3.9864, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.273941061202349e-05, + "loss": 3.972, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.273102466451297e-05, + "loss": 3.979, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.272263871700245e-05, + "loss": 3.9652, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.271425276949193e-05, + "loss": 3.9808, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.270586682198141e-05, + "loss": 3.9764, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.269748087447088e-05, + "loss": 3.97, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.2689111305764097e-05, + "loss": 3.9656, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.2680725358253576e-05, + "loss": 3.9738, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.2672339410743056e-05, + "loss": 3.9849, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.266395346323253e-05, + "loss": 3.9822, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.2655567515722016e-05, + "loss": 3.9805, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.2647181568211496e-05, + "loss": 3.9724, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.2638795620700976e-05, + "loss": 3.9853, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.2630426051994185e-05, + "loss": 3.9852, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.26220564832874e-05, + "loss": 3.9803, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.261367053577688e-05, + "loss": 3.9749, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.2605284588266354e-05, + "loss": 3.98, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.2596898640755834e-05, + "loss": 3.984, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.2588512693245314e-05, + "loss": 3.9865, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.2580126745734794e-05, + "loss": 3.9739, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.2571740798224274e-05, + "loss": 3.9707, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.2563354850713754e-05, + "loss": 3.9793, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.2554968903203234e-05, + "loss": 3.9761, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.2546582955692714e-05, + "loss": 3.9698, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.25381970081822e-05, + "loss": 3.9835, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.252981106067168e-05, + "loss": 3.9722, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.252142511316116e-05, + "loss": 3.9878, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.251305554445437e-05, + "loss": 3.9682, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 4.029884338378906, + "eval_runtime": 296.0242, + "eval_samples_per_second": 1289.053, + "eval_steps_per_second": 40.284, + "step": 1068480 + }, + { + "epoch": 1.0, + "learning_rate": 3.250466959694385e-05, + "loss": 3.9775, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.249628364943333e-05, + "loss": 3.9728, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.248789770192281e-05, + "loss": 3.9738, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.247952813321602e-05, + "loss": 3.9825, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.24711421857055e-05, + "loss": 3.9779, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.246275623819498e-05, + "loss": 3.9795, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.245437029068446e-05, + "loss": 3.9736, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.244598434317394e-05, + "loss": 3.9775, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.243761477446715e-05, + "loss": 3.9718, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.2429228826956634e-05, + "loss": 3.9811, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.2420842879446114e-05, + "loss": 3.9787, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.2412473310739323e-05, + "loss": 3.9815, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.240410374203253e-05, + "loss": 3.987, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.239571779452201e-05, + "loss": 3.9641, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.238733184701149e-05, + "loss": 3.9727, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.237894589950097e-05, + "loss": 3.9603, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.237055995199045e-05, + "loss": 3.9871, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.236217400447993e-05, + "loss": 3.9677, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.235378805696941e-05, + "loss": 3.9713, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.234541848826262e-05, + "loss": 3.9766, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.23370325407521e-05, + "loss": 3.9861, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.232864659324159e-05, + "loss": 3.981, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.232026064573107e-05, + "loss": 3.9766, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.231187469822054e-05, + "loss": 3.978, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.230348875071002e-05, + "loss": 3.9822, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.22951028031995e-05, + "loss": 3.9689, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.228671685568898e-05, + "loss": 3.9718, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.227833090817846e-05, + "loss": 3.9746, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.226996133947167e-05, + "loss": 3.9692, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.226157539196115e-05, + "loss": 3.9649, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.225318944445063e-05, + "loss": 3.9707, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.224480349694011e-05, + "loss": 3.9705, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.223641754942959e-05, + "loss": 3.9852, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.222803160191907e-05, + "loss": 3.9836, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.221964565440856e-05, + "loss": 3.9684, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.2211276085701766e-05, + "loss": 3.9725, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.2202890138191246e-05, + "loss": 3.9843, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.2194504190680726e-05, + "loss": 3.9591, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.2186118243170206e-05, + "loss": 3.9805, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.2177732295659686e-05, + "loss": 3.9619, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.2169346348149166e-05, + "loss": 3.9623, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.2160960400638645e-05, + "loss": 3.9723, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.2152590831931855e-05, + "loss": 3.9836, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.2144204884421335e-05, + "loss": 3.9654, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.2135818936910814e-05, + "loss": 3.9716, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.2127432989400294e-05, + "loss": 3.9722, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.2119047041889774e-05, + "loss": 3.9705, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.2110661094379254e-05, + "loss": 3.9754, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.2102275146868734e-05, + "loss": 3.9553, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.2093889199358214e-05, + "loss": 3.9727, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.208553600945516e-05, + "loss": 3.9737, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.207715006194464e-05, + "loss": 3.9773, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.206876411443412e-05, + "loss": 3.961, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.20603781669236e-05, + "loss": 3.9647, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.205199221941308e-05, + "loss": 3.9641, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.204362265070629e-05, + "loss": 3.9567, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.203523670319577e-05, + "loss": 3.9812, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.202685075568525e-05, + "loss": 3.9492, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.201846480817473e-05, + "loss": 3.977, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.201007886066421e-05, + "loss": 3.97, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.200169291315369e-05, + "loss": 3.9667, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.199330696564317e-05, + "loss": 3.9819, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.198492101813265e-05, + "loss": 3.9569, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.197655144942586e-05, + "loss": 3.9575, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.19681982595228e-05, + "loss": 3.9611, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.195981231201228e-05, + "loss": 3.9813, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.195142636450176e-05, + "loss": 3.9633, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.194304041699124e-05, + "loss": 3.9609, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.193465446948072e-05, + "loss": 3.9535, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.19262685219702e-05, + "loss": 3.9625, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.191788257445968e-05, + "loss": 3.9752, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.190949662694916e-05, + "loss": 3.9786, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.190111067943864e-05, + "loss": 3.962, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.189272473192812e-05, + "loss": 3.9779, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.18843387844176e-05, + "loss": 3.9843, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.187595283690708e-05, + "loss": 3.9708, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.186758326820029e-05, + "loss": 3.9708, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.185919732068977e-05, + "loss": 3.9672, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.185081137317925e-05, + "loss": 3.9714, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.184244180447246e-05, + "loss": 3.9624, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.183405585696194e-05, + "loss": 3.9721, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.182566990945142e-05, + "loss": 3.9718, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.18172839619409e-05, + "loss": 3.9802, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.180889801443038e-05, + "loss": 3.9701, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.1800512066919866e-05, + "loss": 3.9552, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.1792126119409346e-05, + "loss": 3.9596, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.1783740171898826e-05, + "loss": 3.9728, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.1775354224388306e-05, + "loss": 3.9598, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.1766984655681515e-05, + "loss": 3.9717, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.1758598708170995e-05, + "loss": 3.9633, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.1750212760660475e-05, + "loss": 3.9599, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.1741826813149955e-05, + "loss": 3.9615, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.1733440865639435e-05, + "loss": 3.9653, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.1725071296932644e-05, + "loss": 3.97, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.1716685349422124e-05, + "loss": 3.9768, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.1708299401911604e-05, + "loss": 3.9715, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.1699913454401084e-05, + "loss": 3.9592, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.1691527506890564e-05, + "loss": 3.9674, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.1683141559380044e-05, + "loss": 3.9651, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.1674755611869524e-05, + "loss": 3.9708, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.1666369664359004e-05, + "loss": 3.9717, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.1657983716848484e-05, + "loss": 3.9547, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.164961414814169e-05, + "loss": 3.9721, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.164122820063117e-05, + "loss": 3.9671, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.163284225312065e-05, + "loss": 3.9634, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.162445630561013e-05, + "loss": 3.9601, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.161608673690334e-05, + "loss": 3.9613, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.160771716819656e-05, + "loss": 3.9671, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.159933122068604e-05, + "loss": 3.9716, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.159094527317552e-05, + "loss": 3.9601, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.1582559325665e-05, + "loss": 3.9526, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.157418975695821e-05, + "loss": 3.9586, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.1565803809447687e-05, + "loss": 3.9732, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.1557417861937166e-05, + "loss": 3.9622, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.1549031914426646e-05, + "loss": 3.9643, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.1540645966916126e-05, + "loss": 3.9709, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.1532276398209335e-05, + "loss": 3.972, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.152390682950255e-05, + "loss": 3.9661, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.151552088199203e-05, + "loss": 3.9672, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.150713493448151e-05, + "loss": 3.9731, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.149874898697099e-05, + "loss": 3.9712, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.149036303946047e-05, + "loss": 3.9561, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.148197709194995e-05, + "loss": 3.9655, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.147359114443943e-05, + "loss": 3.9607, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.146520519692891e-05, + "loss": 3.9624, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.145681924941839e-05, + "loss": 3.961, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.14484496807116e-05, + "loss": 3.9577, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.144006373320108e-05, + "loss": 3.9566, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.143167778569056e-05, + "loss": 3.9639, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.142329183818004e-05, + "loss": 3.9632, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.141490589066952e-05, + "loss": 3.9724, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.140653632196273e-05, + "loss": 3.971, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.139815037445221e-05, + "loss": 3.957, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.1389764426941696e-05, + "loss": 3.9689, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.1381378479431176e-05, + "loss": 3.9679, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.1373008910724385e-05, + "loss": 3.9715, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.1364622963213865e-05, + "loss": 3.9625, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.1356237015703345e-05, + "loss": 3.9705, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.1347851068192825e-05, + "loss": 3.9709, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.1339465120682305e-05, + "loss": 3.972, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.1331079173171785e-05, + "loss": 3.9614, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.1322693225661264e-05, + "loss": 3.9609, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.1314307278150744e-05, + "loss": 3.9655, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.1305921330640224e-05, + "loss": 3.9604, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.12975353831297e-05, + "loss": 3.9566, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.128914943561918e-05, + "loss": 3.97, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.128076348810866e-05, + "loss": 3.9603, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.1272377540598144e-05, + "loss": 3.9748, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.126400797189135e-05, + "loss": 3.9583, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 4.022413730621338, + "eval_runtime": 295.7682, + "eval_samples_per_second": 1290.169, + "eval_steps_per_second": 40.319, + "step": 1144800 + }, + { + "epoch": 0.0, + "learning_rate": 3.125562202438083e-05, + "loss": 3.9475, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.124723607687031e-05, + "loss": 3.9643, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.123885012935979e-05, + "loss": 3.9606, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.123046418184927e-05, + "loss": 3.9709, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.122207823433875e-05, + "loss": 3.9619, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.121369228682823e-05, + "loss": 3.9683, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.120530633931771e-05, + "loss": 3.9592, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.119692039180719e-05, + "loss": 3.9626, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.118853444429667e-05, + "loss": 3.9629, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.118014849678615e-05, + "loss": 3.9667, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.117176254927563e-05, + "loss": 3.9634, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.116337660176511e-05, + "loss": 3.9733, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.115500703305833e-05, + "loss": 3.9751, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.114662108554781e-05, + "loss": 3.9523, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.113823513803729e-05, + "loss": 3.9564, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.112984919052676e-05, + "loss": 3.9506, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.112146324301624e-05, + "loss": 3.969, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.111307729550572e-05, + "loss": 3.9629, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.11046913479952e-05, + "loss": 3.9566, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.109630540048468e-05, + "loss": 3.9607, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.108791945297416e-05, + "loss": 3.9727, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.107953350546364e-05, + "loss": 3.9697, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.107114755795312e-05, + "loss": 3.9656, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.10627616104426e-05, + "loss": 3.9659, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.105439204173581e-05, + "loss": 3.9778, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.10460060942253e-05, + "loss": 3.9556, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.1037636525518506e-05, + "loss": 3.9599, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.1029250578007986e-05, + "loss": 3.9673, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.1020864630497466e-05, + "loss": 3.9529, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.1012478682986946e-05, + "loss": 3.9562, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.1004092735476426e-05, + "loss": 3.9561, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.0995706787965906e-05, + "loss": 3.9616, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.0987320840455386e-05, + "loss": 3.9722, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.0978951271748595e-05, + "loss": 3.9658, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.0970565324238075e-05, + "loss": 3.9615, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.0962195755531284e-05, + "loss": 3.9573, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.0953809808020764e-05, + "loss": 3.9719, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.094542386051025e-05, + "loss": 3.9505, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.093703791299973e-05, + "loss": 3.9687, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.092865196548921e-05, + "loss": 3.9514, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.092028239678242e-05, + "loss": 3.9524, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.09118964492719e-05, + "loss": 3.9595, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.090351050176138e-05, + "loss": 3.9742, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.089512455425086e-05, + "loss": 3.9464, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.088673860674034e-05, + "loss": 3.9641, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.087835265922982e-05, + "loss": 3.9625, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.08699667117193e-05, + "loss": 3.958, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.086158076420877e-05, + "loss": 3.9625, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.085321119550199e-05, + "loss": 3.9412, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.084482524799147e-05, + "loss": 3.9599, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.083643930048095e-05, + "loss": 3.9667, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.082805335297043e-05, + "loss": 3.964, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.081966740545991e-05, + "loss": 3.9513, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.081128145794939e-05, + "loss": 3.9504, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.080289551043887e-05, + "loss": 3.9563, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.079450956292835e-05, + "loss": 3.9445, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.078613999422156e-05, + "loss": 3.9728, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.077775404671104e-05, + "loss": 3.9383, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.076936809920052e-05, + "loss": 3.9622, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.076098215169e-05, + "loss": 3.9574, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.075259620417948e-05, + "loss": 3.954, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.074424301427642e-05, + "loss": 3.9653, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.07358570667659e-05, + "loss": 3.9515, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.072747111925538e-05, + "loss": 3.9437, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.071908517174486e-05, + "loss": 3.948, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.071069922423434e-05, + "loss": 3.972, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.070231327672382e-05, + "loss": 3.9503, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.06939273292133e-05, + "loss": 3.9492, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.068554138170278e-05, + "loss": 3.9419, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.067715543419226e-05, + "loss": 3.9525, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.06688022442892e-05, + "loss": 3.9637, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.066041629677868e-05, + "loss": 3.9665, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.065203034926816e-05, + "loss": 3.9476, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.064364440175764e-05, + "loss": 3.966, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.063525845424712e-05, + "loss": 3.9725, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.062687250673661e-05, + "loss": 3.9609, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.0618502938029816e-05, + "loss": 3.9526, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.0610116990519296e-05, + "loss": 3.9573, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.0601747421812505e-05, + "loss": 3.9585, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.0593361474301985e-05, + "loss": 3.9555, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.0584975526791465e-05, + "loss": 3.9542, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.0576589579280945e-05, + "loss": 3.9669, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.0568203631770425e-05, + "loss": 3.9691, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.0559817684259905e-05, + "loss": 3.9631, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.0551431736749385e-05, + "loss": 3.9444, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.0543045789238865e-05, + "loss": 3.9486, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.0534659841728345e-05, + "loss": 3.9604, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.0526273894217824e-05, + "loss": 3.949, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.051790432551104e-05, + "loss": 3.9602, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.0509518378000517e-05, + "loss": 3.9495, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.0501132430489997e-05, + "loss": 3.95, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.0492746482979477e-05, + "loss": 3.9482, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.048436053546896e-05, + "loss": 3.9561, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.0475974587958433e-05, + "loss": 3.9563, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.0467588640447913e-05, + "loss": 3.963, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.0459202692937393e-05, + "loss": 3.9636, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.0450816745426873e-05, + "loss": 3.9439, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.044246355552382e-05, + "loss": 3.9591, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.04340776080133e-05, + "loss": 3.9537, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.042569166050278e-05, + "loss": 3.9595, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.0417305712992255e-05, + "loss": 3.9612, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.0408919765481735e-05, + "loss": 3.9448, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.0400533817971215e-05, + "loss": 3.9581, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.0392147870460698e-05, + "loss": 3.9567, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.0383778301753907e-05, + "loss": 3.9544, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.0375392354243387e-05, + "loss": 3.9467, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.0367006406732867e-05, + "loss": 3.9511, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.0358620459222347e-05, + "loss": 3.9573, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.035025089051556e-05, + "loss": 3.9597, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.034186494300504e-05, + "loss": 3.9469, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.033347899549452e-05, + "loss": 3.947, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.0325093047984e-05, + "loss": 3.9448, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.031670710047348e-05, + "loss": 3.9624, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.030832115296296e-05, + "loss": 3.9494, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.029993520545244e-05, + "loss": 3.9541, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.029154925794192e-05, + "loss": 3.9623, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.02831633104314e-05, + "loss": 3.9647, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.027479374172461e-05, + "loss": 3.9549, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.026640779421409e-05, + "loss": 3.9548, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.025802184670357e-05, + "loss": 3.9654, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.024963589919305e-05, + "loss": 3.9586, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.024124995168253e-05, + "loss": 3.9471, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.0232880382975744e-05, + "loss": 3.9573, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.0224510814268953e-05, + "loss": 3.9462, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.0216124866758433e-05, + "loss": 3.9513, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.0207738919247913e-05, + "loss": 3.9468, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.0199369350541122e-05, + "loss": 3.9514, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.0190983403030605e-05, + "loss": 3.9475, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.0182597455520085e-05, + "loss": 3.9499, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.0174211508009565e-05, + "loss": 3.9508, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.0165825560499045e-05, + "loss": 3.9622, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.0157455991792254e-05, + "loss": 3.9618, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.0149070044281734e-05, + "loss": 3.9532, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.0140700475574947e-05, + "loss": 3.9532, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.0132314528064427e-05, + "loss": 3.9553, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.0123928580553907e-05, + "loss": 3.9606, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.0115542633043387e-05, + "loss": 3.9561, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.0107156685532867e-05, + "loss": 3.958, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.0098770738022347e-05, + "loss": 3.9606, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.0090384790511826e-05, + "loss": 3.9584, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.0081998843001306e-05, + "loss": 3.9523, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.007361289549079e-05, + "loss": 3.9493, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.006522694798027e-05, + "loss": 3.9533, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.0056841000469743e-05, + "loss": 3.9511, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.0048455052959223e-05, + "loss": 3.9456, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.0040069105448703e-05, + "loss": 3.9601, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.0031683157938183e-05, + "loss": 3.9532, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.0023313589231395e-05, + "loss": 3.9586, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.0014927641720875e-05, + "loss": 3.9471, + "step": 1220608 + }, + { + "epoch": 0.03, + "learning_rate": 3.0006541694210355e-05, + "loss": 3.9536, + "step": 1221120 + }, + { + "epoch": 0.03, + "eval_loss": 4.017250061035156, + "eval_runtime": 286.9429, + "eval_samples_per_second": 1329.85, + "eval_steps_per_second": 41.559, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 2.9998155746699835e-05, + "loss": 3.9536, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.9989786177993044e-05, + "loss": 3.9462, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.9981400230482528e-05, + "loss": 3.9628, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.9973014282972008e-05, + "loss": 3.954, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.9964628335461487e-05, + "loss": 3.9578, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.9956258766754697e-05, + "loss": 3.9483, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.9947872819244177e-05, + "loss": 3.9547, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.9939486871733656e-05, + "loss": 3.9468, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.9931100924223136e-05, + "loss": 3.9604, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.9922714976712616e-05, + "loss": 3.9515, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.99143290292021e-05, + "loss": 3.9645, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.990594308169158e-05, + "loss": 3.9597, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.989757351298479e-05, + "loss": 3.9467, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.988918756547427e-05, + "loss": 3.948, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.988080161796375e-05, + "loss": 3.9367, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.987241567045323e-05, + "loss": 3.9548, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.986402972294271e-05, + "loss": 3.9502, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.9855643775432192e-05, + "loss": 3.9498, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.9847257827921672e-05, + "loss": 3.9476, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.983888825921488e-05, + "loss": 3.9664, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.983050231170436e-05, + "loss": 3.9547, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.982211636419384e-05, + "loss": 3.9567, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.981373041668332e-05, + "loss": 3.9581, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.98053444691728e-05, + "loss": 3.9625, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.9796958521662277e-05, + "loss": 3.9451, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.9788572574151757e-05, + "loss": 3.9531, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.9780186626641237e-05, + "loss": 3.9495, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.9771800679130717e-05, + "loss": 3.9452, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.976343111042393e-05, + "loss": 3.9473, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.975504516291341e-05, + "loss": 3.9452, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.9746675594206626e-05, + "loss": 3.9516, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.97382896466961e-05, + "loss": 3.9611, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.972990369918558e-05, + "loss": 3.9565, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.972151775167506e-05, + "loss": 3.9498, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.9713148182968275e-05, + "loss": 3.9511, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.970476223545775e-05, + "loss": 3.9551, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.969637628794723e-05, + "loss": 3.9419, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.968799034043671e-05, + "loss": 3.9577, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.967960439292619e-05, + "loss": 3.9399, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.967121844541567e-05, + "loss": 3.9452, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.966283249790515e-05, + "loss": 3.9492, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.965444655039463e-05, + "loss": 3.9595, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.9646060602884114e-05, + "loss": 3.9408, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.9637691034177323e-05, + "loss": 3.9527, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.9629321465470532e-05, + "loss": 3.9508, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.9620935517960012e-05, + "loss": 3.9465, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.9612549570449492e-05, + "loss": 3.9575, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.9604163622938976e-05, + "loss": 3.9284, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.9595777675428456e-05, + "loss": 3.9474, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.9587391727917936e-05, + "loss": 3.9561, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.9579005780407415e-05, + "loss": 3.9565, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.9570619832896895e-05, + "loss": 3.9443, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.9562233885386375e-05, + "loss": 3.9363, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.9553847937875855e-05, + "loss": 3.9469, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.9545478369169068e-05, + "loss": 3.9322, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.9537092421658548e-05, + "loss": 3.9629, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.9528706474148028e-05, + "loss": 3.9277, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.9520320526637508e-05, + "loss": 3.954, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.9511950957930717e-05, + "loss": 3.9451, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.9503565010420197e-05, + "loss": 3.9448, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.949519544171341e-05, + "loss": 3.9534, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.948680949420289e-05, + "loss": 3.94, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.947842354669237e-05, + "loss": 3.9341, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.947003759918185e-05, + "loss": 3.9379, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.946165165167133e-05, + "loss": 3.9594, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.945326570416081e-05, + "loss": 3.9435, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.944487975665029e-05, + "loss": 3.9431, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.9436493809139766e-05, + "loss": 3.9304, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.9428107861629245e-05, + "loss": 3.9392, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.9419721914118725e-05, + "loss": 3.9567, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.9411335966608205e-05, + "loss": 3.9576, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.9402950019097685e-05, + "loss": 3.9387, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.9394564071587165e-05, + "loss": 3.9545, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.9386194502880378e-05, + "loss": 3.965, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.9377808555369858e-05, + "loss": 3.9517, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.9369422607859338e-05, + "loss": 3.9411, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.9361036660348818e-05, + "loss": 3.9486, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.9352667091642027e-05, + "loss": 3.9485, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.9344281144131507e-05, + "loss": 3.9468, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.9335895196620987e-05, + "loss": 3.9453, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.932750924911047e-05, + "loss": 3.9498, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.931912330159995e-05, + "loss": 3.9584, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.9310770111696888e-05, + "loss": 3.9528, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.9302384164186368e-05, + "loss": 3.9332, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.9293998216675848e-05, + "loss": 3.9425, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.928561226916533e-05, + "loss": 3.9463, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.927722632165481e-05, + "loss": 3.947, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.926885675294802e-05, + "loss": 3.9478, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.92604708054375e-05, + "loss": 3.9439, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.925210123673071e-05, + "loss": 3.9435, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.9243715289220193e-05, + "loss": 3.9355, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.9235329341709673e-05, + "loss": 3.9466, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.9226943394199153e-05, + "loss": 3.9467, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.9218557446688633e-05, + "loss": 3.9505, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.9210171499178113e-05, + "loss": 3.9541, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.9201785551667593e-05, + "loss": 3.938, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.9193399604157073e-05, + "loss": 3.9452, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.9185013656646553e-05, + "loss": 3.9466, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.9176627709136033e-05, + "loss": 3.9484, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.9168241761625516e-05, + "loss": 3.9521, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.9159872192918725e-05, + "loss": 3.9367, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.9151486245408205e-05, + "loss": 3.9447, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.9143100297897685e-05, + "loss": 3.9467, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.9134714350387165e-05, + "loss": 3.9449, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.9126328402876645e-05, + "loss": 3.9361, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.911794245536612e-05, + "loss": 3.9398, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.91095565078556e-05, + "loss": 3.9497, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.910117056034508e-05, + "loss": 3.944, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.909278461283456e-05, + "loss": 3.9409, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.908441504412777e-05, + "loss": 3.9356, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.9076045475420986e-05, + "loss": 3.9347, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.906765952791047e-05, + "loss": 3.955, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.905927358039995e-05, + "loss": 3.9391, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.9050887632889423e-05, + "loss": 3.9467, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.9042501685378903e-05, + "loss": 3.9493, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.903413211667212e-05, + "loss": 3.9549, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.9025746169161595e-05, + "loss": 3.941, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.9017360221651075e-05, + "loss": 3.9426, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.9008974274140555e-05, + "loss": 3.9563, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.9000588326630035e-05, + "loss": 3.9483, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.8992202379119515e-05, + "loss": 3.9353, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.8983832810412724e-05, + "loss": 3.9439, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.8975446862902207e-05, + "loss": 3.9387, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.8967060915391687e-05, + "loss": 3.9411, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.8958674967881167e-05, + "loss": 3.9379, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.8950289020370647e-05, + "loss": 3.9431, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.8941919451663856e-05, + "loss": 3.9344, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.8933533504153336e-05, + "loss": 3.9378, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.8925147556642816e-05, + "loss": 3.9371, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.89167616091323e-05, + "loss": 3.9588, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.890837566162178e-05, + "loss": 3.9548, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.889998971411126e-05, + "loss": 3.9411, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.889160376660074e-05, + "loss": 3.9413, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.888323419789395e-05, + "loss": 3.9432, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.887486462918716e-05, + "loss": 3.9523, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.886647868167664e-05, + "loss": 3.9478, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.885809273416612e-05, + "loss": 3.9458, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.88497067866556e-05, + "loss": 3.9506, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.884133721794881e-05, + "loss": 3.9464, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.883295127043829e-05, + "loss": 3.9443, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.882456532292777e-05, + "loss": 3.9401, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.881617937541725e-05, + "loss": 3.9484, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.8807793427906733e-05, + "loss": 3.9422, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.8799407480396213e-05, + "loss": 3.9324, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.8791021532885693e-05, + "loss": 3.9495, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.8782635585375173e-05, + "loss": 3.9441, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.8774249637864653e-05, + "loss": 3.9509, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.8765863690354133e-05, + "loss": 3.9382, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.875747774284361e-05, + "loss": 3.9398, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 4.011906623840332, + "eval_runtime": 287.3432, + "eval_samples_per_second": 1327.997, + "eval_steps_per_second": 41.501, + "step": 1297440 + }, + { + "epoch": 0.0, + "learning_rate": 2.874909179533309e-05, + "loss": 3.9408, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.874070584782257e-05, + "loss": 3.9393, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.873231990031205e-05, + "loss": 3.9531, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.872393395280153e-05, + "loss": 3.9398, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.871554800529101e-05, + "loss": 3.9494, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.870716205778049e-05, + "loss": 3.9379, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.869877611026997e-05, + "loss": 3.9462, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.869039016275945e-05, + "loss": 3.9361, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.8682004215248933e-05, + "loss": 3.9492, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.8673618267738412e-05, + "loss": 3.9449, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.8665232320227892e-05, + "loss": 3.9529, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.8656846372717372e-05, + "loss": 3.9487, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.864847680401058e-05, + "loss": 3.936, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.864009085650006e-05, + "loss": 3.9403, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.863170490898954e-05, + "loss": 3.9343, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.8623318961479025e-05, + "loss": 3.9351, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.8614933013968498e-05, + "loss": 3.9431, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.8606547066457978e-05, + "loss": 3.939, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.8598161118947458e-05, + "loss": 3.9393, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.8589775171436938e-05, + "loss": 3.9587, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.8581389223926418e-05, + "loss": 3.946, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.85730032764159e-05, + "loss": 3.9474, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.856461732890538e-05, + "loss": 3.9442, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.855624776019859e-05, + "loss": 3.9569, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.854786181268807e-05, + "loss": 3.9282, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.853947586517755e-05, + "loss": 3.9473, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.853108991766703e-05, + "loss": 3.9368, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.852270397015651e-05, + "loss": 3.9372, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.8514334401449722e-05, + "loss": 3.9359, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.8505948453939202e-05, + "loss": 3.9318, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.8497562506428682e-05, + "loss": 3.9425, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.848919293772189e-05, + "loss": 3.9526, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.848080699021137e-05, + "loss": 3.941, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.8472421042700855e-05, + "loss": 3.9473, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8464051473994064e-05, + "loss": 3.9357, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.8455665526483544e-05, + "loss": 3.9434, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8447279578973024e-05, + "loss": 3.9336, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.8438893631462504e-05, + "loss": 3.9472, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.8430507683951984e-05, + "loss": 3.9304, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.8422121736441464e-05, + "loss": 3.9365, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.8413735788930944e-05, + "loss": 3.9379, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.8405349841420427e-05, + "loss": 3.9515, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.8396963893909907e-05, + "loss": 3.9297, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.8388577946399387e-05, + "loss": 3.9421, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8380208377692596e-05, + "loss": 3.9435, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.8371822430182076e-05, + "loss": 3.9353, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.8363436482671556e-05, + "loss": 3.9456, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.8355050535161032e-05, + "loss": 3.9242, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.8346680966454248e-05, + "loss": 3.9346, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.8338295018943728e-05, + "loss": 3.9475, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.8329909071433208e-05, + "loss": 3.9406, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.832152312392268e-05, + "loss": 3.9322, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.8313137176412165e-05, + "loss": 3.9327, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.8304751228901645e-05, + "loss": 3.9363, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.8296365281391125e-05, + "loss": 3.9244, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.8287979333880605e-05, + "loss": 3.9462, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.8279593386370085e-05, + "loss": 3.9231, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.827124019646703e-05, + "loss": 3.9384, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.8262870627760242e-05, + "loss": 3.9365, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.8254484680249722e-05, + "loss": 3.9358, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.8246098732739202e-05, + "loss": 3.942, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.8237712785228682e-05, + "loss": 3.9355, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8229326837718155e-05, + "loss": 3.9219, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8220940890207635e-05, + "loss": 3.9249, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.821255494269712e-05, + "loss": 3.9517, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.8204185373990328e-05, + "loss": 3.9325, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.8195799426479807e-05, + "loss": 3.9298, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.8187413478969287e-05, + "loss": 3.9227, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.8179027531458767e-05, + "loss": 3.9311, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.8170641583948247e-05, + "loss": 3.9426, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.8162255636437727e-05, + "loss": 3.9468, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.815386968892721e-05, + "loss": 3.9324, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.814548374141669e-05, + "loss": 3.9456, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.813709779390617e-05, + "loss": 3.9496, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.812872822519938e-05, + "loss": 3.946, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.812034227768886e-05, + "loss": 3.9261, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.811195633017834e-05, + "loss": 3.942, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.8103586761471552e-05, + "loss": 3.9371, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.8095200813961032e-05, + "loss": 3.9379, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.8086814866450512e-05, + "loss": 3.9338, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.8078428918939992e-05, + "loss": 3.9406, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.8070042971429472e-05, + "loss": 3.9499, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.8061657023918952e-05, + "loss": 3.9433, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8053271076408432e-05, + "loss": 3.9243, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.8044885128897912e-05, + "loss": 3.9321, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.8036499181387395e-05, + "loss": 3.9349, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.8028113233876868e-05, + "loss": 3.9398, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.8019727286366348e-05, + "loss": 3.9389, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8011341338855828e-05, + "loss": 3.9303, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8002971770149044e-05, + "loss": 3.9384, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.799458582263852e-05, + "loss": 3.9214, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.7986199875128e-05, + "loss": 3.9354, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.797781392761748e-05, + "loss": 3.938, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.796942798010696e-05, + "loss": 3.9361, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.796104203259644e-05, + "loss": 3.9442, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.795265608508592e-05, + "loss": 3.9326, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.79442701375754e-05, + "loss": 3.9331, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.793588419006488e-05, + "loss": 3.9373, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7927514621358093e-05, + "loss": 3.9409, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7919145052651302e-05, + "loss": 3.9354, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.7910759105140782e-05, + "loss": 3.9301, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.7902373157630262e-05, + "loss": 3.9341, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.7893987210119742e-05, + "loss": 3.9377, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.788560126260922e-05, + "loss": 3.9387, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.7877215315098705e-05, + "loss": 3.9189, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.7868845746391914e-05, + "loss": 3.9337, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.7860459798881394e-05, + "loss": 3.9408, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.7852073851370874e-05, + "loss": 3.9365, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.7843687903860354e-05, + "loss": 3.9279, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.7835301956349834e-05, + "loss": 3.9308, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.7826916008839314e-05, + "loss": 3.9224, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.7818530061328797e-05, + "loss": 3.9449, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.7810144113818277e-05, + "loss": 3.9295, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7801758166307757e-05, + "loss": 3.9369, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.7793388597600966e-05, + "loss": 3.9347, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.7785019028894175e-05, + "loss": 3.9482, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.777663308138366e-05, + "loss": 3.9312, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.776824713387314e-05, + "loss": 3.9372, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.775986118636262e-05, + "loss": 3.9445, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.77514752388521e-05, + "loss": 3.9354, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.774308929134158e-05, + "loss": 3.9305, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.773470334383105e-05, + "loss": 3.9368, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.7726333775124268e-05, + "loss": 3.9269, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.771794782761375e-05, + "loss": 3.9309, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.770956188010323e-05, + "loss": 3.9325, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7701175932592704e-05, + "loss": 3.9324, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7692789985082184e-05, + "loss": 3.9253, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.768443679517913e-05, + "loss": 3.9301, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.7676050847668612e-05, + "loss": 3.9292, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.7667664900158092e-05, + "loss": 3.9448, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.7659278952647572e-05, + "loss": 3.9472, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.7650893005137052e-05, + "loss": 3.9343, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.7642507057626525e-05, + "loss": 3.926, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.7634121110116005e-05, + "loss": 3.9374, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.762573516260549e-05, + "loss": 3.9394, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.761734921509497e-05, + "loss": 3.9385, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.760896326758445e-05, + "loss": 3.9334, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.760057732007393e-05, + "loss": 3.9415, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.759219137256341e-05, + "loss": 3.9353, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.758380542505289e-05, + "loss": 3.9364, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.7575435856346098e-05, + "loss": 3.9331, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.756704990883558e-05, + "loss": 3.9367, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.755866396132506e-05, + "loss": 3.9303, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.755027801381454e-05, + "loss": 3.9271, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.754190844510775e-05, + "loss": 3.9372, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.753352249759723e-05, + "loss": 3.9363, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7525152928890442e-05, + "loss": 3.9404, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.7516766981379922e-05, + "loss": 3.9273, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.7508381033869402e-05, + "loss": 3.9296, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 4.007091999053955, + "eval_runtime": 302.0163, + "eval_samples_per_second": 1263.478, + "eval_steps_per_second": 39.485, + "step": 1373760 + }, + { + "epoch": 1.0, + "learning_rate": 2.7499995086358882e-05, + "loss": 3.9343, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.7491609138848362e-05, + "loss": 3.9306, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.748323957014157e-05, + "loss": 3.9415, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.747485362263105e-05, + "loss": 3.9305, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.7466467675120535e-05, + "loss": 3.9426, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.7458081727610015e-05, + "loss": 3.9259, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.7449695780099494e-05, + "loss": 3.9368, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.7441309832588974e-05, + "loss": 3.9255, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.7432923885078454e-05, + "loss": 3.9396, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.7424537937567934e-05, + "loss": 3.9327, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.7416151990057414e-05, + "loss": 3.9436, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.7407782421350627e-05, + "loss": 3.9381, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.7399429231447565e-05, + "loss": 3.9262, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.7391043283937045e-05, + "loss": 3.9314, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.7382657336426525e-05, + "loss": 3.926, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.7374271388916005e-05, + "loss": 3.9302, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.7365885441405488e-05, + "loss": 3.9315, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.7357499493894968e-05, + "loss": 3.927, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.7349113546384448e-05, + "loss": 3.9312, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.7340727598873928e-05, + "loss": 3.9493, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.7332341651363408e-05, + "loss": 3.9382, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.7323955703852888e-05, + "loss": 3.9367, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7315569756342365e-05, + "loss": 3.9371, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.7307183808831845e-05, + "loss": 3.9425, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.7298797861321325e-05, + "loss": 3.9184, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.729042829261454e-05, + "loss": 3.9348, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.7282042345104014e-05, + "loss": 3.9331, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.727367277639723e-05, + "loss": 3.928, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.726528682888671e-05, + "loss": 3.924, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.7256900881376186e-05, + "loss": 3.9233, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.7248514933865666e-05, + "loss": 3.9325, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.7240128986355146e-05, + "loss": 3.9424, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.7231743038844626e-05, + "loss": 3.9327, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.7223373470137835e-05, + "loss": 3.9365, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.721500390143105e-05, + "loss": 3.9283, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.720661795392053e-05, + "loss": 3.9328, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.7198232006410014e-05, + "loss": 3.9231, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.7189846058899487e-05, + "loss": 3.9419, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.7181460111388967e-05, + "loss": 3.9184, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.7173074163878447e-05, + "loss": 3.9281, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.7164688216367927e-05, + "loss": 3.9264, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.7156302268857407e-05, + "loss": 3.9422, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.714791632134689e-05, + "loss": 3.9227, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.713953037383637e-05, + "loss": 3.9302, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.713114442632585e-05, + "loss": 3.935, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.712275847881533e-05, + "loss": 3.9288, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.711438891010854e-05, + "loss": 3.9343, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.7106019341401752e-05, + "loss": 3.9154, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.7097633393891232e-05, + "loss": 3.9255, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.7089247446380712e-05, + "loss": 3.9389, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.7080861498870192e-05, + "loss": 3.9291, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.7072475551359672e-05, + "loss": 3.9244, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.706408960384915e-05, + "loss": 3.925, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.705572003514236e-05, + "loss": 3.9312, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.7047334087631844e-05, + "loss": 3.9146, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.7038948140121324e-05, + "loss": 3.934, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.7030562192610804e-05, + "loss": 3.9144, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.7022176245100284e-05, + "loss": 3.9308, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.7013806676393493e-05, + "loss": 3.9319, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.7005420728882973e-05, + "loss": 3.9246, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.6997034781372453e-05, + "loss": 3.9294, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.6988648833861936e-05, + "loss": 3.9324, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.6980262886351416e-05, + "loss": 3.9097, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.6971893317644625e-05, + "loss": 3.9218, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.6963507370134105e-05, + "loss": 3.9346, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.6955121422623585e-05, + "loss": 3.9282, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.6946735475113065e-05, + "loss": 3.9232, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.6938365906406278e-05, + "loss": 3.9108, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.6929979958895758e-05, + "loss": 3.9209, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.6921594011385238e-05, + "loss": 3.9356, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.6913208063874718e-05, + "loss": 3.937, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.6904822116364198e-05, + "loss": 3.9211, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.6896436168853674e-05, + "loss": 3.9383, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.6888050221343154e-05, + "loss": 3.9402, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.6879664273832634e-05, + "loss": 3.9426, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.6871278326322114e-05, + "loss": 3.9112, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.6862908757615323e-05, + "loss": 3.9357, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.6854522810104803e-05, + "loss": 3.9271, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.684615324139802e-05, + "loss": 3.9278, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.6837767293887495e-05, + "loss": 3.9297, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.6829381346376975e-05, + "loss": 3.9307, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.6820995398866455e-05, + "loss": 3.935, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.681262583015967e-05, + "loss": 3.9379, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.6804239882649144e-05, + "loss": 3.9129, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.679587031394236e-05, + "loss": 3.9233, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.6787484366431844e-05, + "loss": 3.9244, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.6779098418921317e-05, + "loss": 3.9305, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.6770712471410797e-05, + "loss": 3.9342, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.6762326523900277e-05, + "loss": 3.92, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.6753940576389757e-05, + "loss": 3.9293, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.6745554628879237e-05, + "loss": 3.9153, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.673716868136872e-05, + "loss": 3.9274, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.67287827338582e-05, + "loss": 3.927, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.672039678634768e-05, + "loss": 3.927, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.671202721764089e-05, + "loss": 3.9335, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.670364127013037e-05, + "loss": 3.93, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.669525532261985e-05, + "loss": 3.9205, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.668686937510933e-05, + "loss": 3.9303, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.667848342759881e-05, + "loss": 3.9322, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.6670097480088292e-05, + "loss": 3.9308, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.66617279113815e-05, + "loss": 3.9184, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.665334196387098e-05, + "loss": 3.9265, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.664495601636046e-05, + "loss": 3.9289, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.663657006884994e-05, + "loss": 3.9301, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.662818412133942e-05, + "loss": 3.907, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.66197981738289e-05, + "loss": 3.9223, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.6611412226318384e-05, + "loss": 3.934, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.6603042657611593e-05, + "loss": 3.9262, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.6594673088904803e-05, + "loss": 3.9181, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.6586287141394283e-05, + "loss": 3.9226, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.6577901193883763e-05, + "loss": 3.916, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.6569515246373246e-05, + "loss": 3.9327, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.6561129298862726e-05, + "loss": 3.9189, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.6552743351352206e-05, + "loss": 3.9292, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.654435740384168e-05, + "loss": 3.928, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.653597145633116e-05, + "loss": 3.935, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.6527601887624375e-05, + "loss": 3.9216, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.6519215940113855e-05, + "loss": 3.9309, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.651082999260333e-05, + "loss": 3.9346, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.650244404509281e-05, + "loss": 3.9294, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.649405809758229e-05, + "loss": 3.9182, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.648567215007177e-05, + "loss": 3.9248, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.6477302581364984e-05, + "loss": 3.9199, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.6468916633854464e-05, + "loss": 3.9268, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.6460530686343944e-05, + "loss": 3.9218, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.6452144738833424e-05, + "loss": 3.9267, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.6443758791322903e-05, + "loss": 3.9157, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.6435389222616113e-05, + "loss": 3.9205, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.6427003275105593e-05, + "loss": 3.9188, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.6418617327595076e-05, + "loss": 3.9374, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.6410231380084556e-05, + "loss": 3.937, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.6401861811377765e-05, + "loss": 3.9312, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.6393475863867245e-05, + "loss": 3.9174, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.6385089916356725e-05, + "loss": 3.9269, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.6376703968846205e-05, + "loss": 3.9331, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.6368318021335685e-05, + "loss": 3.9275, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.6359932073825168e-05, + "loss": 3.9254, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.6351546126314648e-05, + "loss": 3.9315, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.6343176557607857e-05, + "loss": 3.9273, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.6334790610097337e-05, + "loss": 3.9332, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.6326404662586817e-05, + "loss": 3.9195, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.6318018715076297e-05, + "loss": 3.93, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.6309632767565777e-05, + "loss": 3.9221, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.630124682005526e-05, + "loss": 3.917, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.629286087254474e-05, + "loss": 3.9291, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.628447492503422e-05, + "loss": 3.9309, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.627610535632743e-05, + "loss": 3.9284, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.626771940881691e-05, + "loss": 3.9225, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.6259349840110122e-05, + "loss": 3.9182, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 4.0035552978515625, + "eval_runtime": 301.617, + "eval_samples_per_second": 1265.151, + "eval_steps_per_second": 39.537, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6250963892599602e-05, + "loss": 3.9278, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.624257794508908e-05, + "loss": 3.9218, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.623419199757856e-05, + "loss": 3.9315, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.622580605006804e-05, + "loss": 3.9207, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6217420102557515e-05, + "loss": 3.939, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6209034155046998e-05, + "loss": 3.9141, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.6200648207536478e-05, + "loss": 3.9301, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.6192262260025958e-05, + "loss": 3.9172, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6183876312515438e-05, + "loss": 3.9318, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.6175490365004918e-05, + "loss": 3.9262, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.6167104417494398e-05, + "loss": 3.9276, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.6158718469983878e-05, + "loss": 3.9339, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6150348901277087e-05, + "loss": 3.9162, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.614196295376657e-05, + "loss": 3.9242, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.613357700625605e-05, + "loss": 3.9178, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.612519105874553e-05, + "loss": 3.9228, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.611680511123501e-05, + "loss": 3.92, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.610841916372449e-05, + "loss": 3.9207, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.610003321621397e-05, + "loss": 3.9218, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.609164726870345e-05, + "loss": 3.94, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.608326132119293e-05, + "loss": 3.9283, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.6074875373682407e-05, + "loss": 3.9272, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6066489426171886e-05, + "loss": 3.9308, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.6058103478661366e-05, + "loss": 3.9316, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.6049733909954582e-05, + "loss": 3.9124, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.6041347962444055e-05, + "loss": 3.9332, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.603296201493354e-05, + "loss": 3.919, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6024592446226755e-05, + "loss": 3.921, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.6016206498716228e-05, + "loss": 3.9141, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.6007820551205708e-05, + "loss": 3.9199, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.5999434603695188e-05, + "loss": 3.9215, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.5991048656184668e-05, + "loss": 3.9347, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.5982662708674148e-05, + "loss": 3.9278, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.597429313996736e-05, + "loss": 3.9276, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.5965923571260576e-05, + "loss": 3.9157, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5957537623750056e-05, + "loss": 3.9284, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.594915167623953e-05, + "loss": 3.9112, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.594076572872901e-05, + "loss": 3.9363, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5932379781218492e-05, + "loss": 3.9093, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5923993833707972e-05, + "loss": 3.9186, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.5915607886197452e-05, + "loss": 3.9217, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.5907221938686932e-05, + "loss": 3.9323, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.5898835991176412e-05, + "loss": 3.9159, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.589046642246962e-05, + "loss": 3.9213, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.58820804749591e-05, + "loss": 3.9239, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.5873694527448585e-05, + "loss": 3.9221, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5865308579938065e-05, + "loss": 3.9258, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5856922632427545e-05, + "loss": 3.915, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5848536684917025e-05, + "loss": 3.9115, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5840167116210234e-05, + "loss": 3.9297, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.5831781168699714e-05, + "loss": 3.9213, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.5823395221189194e-05, + "loss": 3.9167, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.5815009273678677e-05, + "loss": 3.919, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5806623326168157e-05, + "loss": 3.9214, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.5798253757461366e-05, + "loss": 3.9062, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.5789867809950846e-05, + "loss": 3.9274, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5781481862440326e-05, + "loss": 3.9054, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5773095914929806e-05, + "loss": 3.9219, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5764709967419286e-05, + "loss": 3.9203, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5756340398712498e-05, + "loss": 3.9234, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.5747954451201978e-05, + "loss": 3.9171, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.5739568503691458e-05, + "loss": 3.9231, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.5731182556180938e-05, + "loss": 3.8991, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5722812987474147e-05, + "loss": 3.9175, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5714427039963627e-05, + "loss": 3.926, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.570604109245311e-05, + "loss": 3.9234, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.569765514494259e-05, + "loss": 3.911, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.5689269197432064e-05, + "loss": 3.9085, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.568089962872528e-05, + "loss": 3.9102, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.567251368121476e-05, + "loss": 3.9235, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.566412773370424e-05, + "loss": 3.9278, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.5655741786193716e-05, + "loss": 3.9154, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.5647355838683196e-05, + "loss": 3.9298, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.5638969891172676e-05, + "loss": 3.9326, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.5630600322465885e-05, + "loss": 3.9385, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.562221437495537e-05, + "loss": 3.902, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.561382842744485e-05, + "loss": 3.9256, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.5605442479934328e-05, + "loss": 3.9249, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.5597056532423808e-05, + "loss": 3.9134, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5588686963717017e-05, + "loss": 3.9219, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.5580301016206497e-05, + "loss": 3.9251, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5571915068695977e-05, + "loss": 3.9301, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5563529121185457e-05, + "loss": 3.9216, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.555514317367494e-05, + "loss": 3.9126, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.554675722616442e-05, + "loss": 3.9123, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.55383712786539e-05, + "loss": 3.9142, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.552998533114338e-05, + "loss": 3.9242, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.552161576243659e-05, + "loss": 3.9284, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.551322981492607e-05, + "loss": 3.913, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5504860246219282e-05, + "loss": 3.9188, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5496474298708762e-05, + "loss": 3.9086, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5488088351198242e-05, + "loss": 3.9178, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5479702403687722e-05, + "loss": 3.9193, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5471316456177202e-05, + "loss": 3.9158, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5462930508666682e-05, + "loss": 3.9284, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5454560939959894e-05, + "loss": 3.9232, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5446174992449374e-05, + "loss": 3.9125, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.5437789044938854e-05, + "loss": 3.9204, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.5429403097428334e-05, + "loss": 3.9238, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.5421017149917814e-05, + "loss": 3.9237, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.5412631202407294e-05, + "loss": 3.9087, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.5404245254896774e-05, + "loss": 3.9188, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.539585930738625e-05, + "loss": 3.9221, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.538747335987573e-05, + "loss": 3.9252, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.5379103791168946e-05, + "loss": 3.904, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.5370717843658426e-05, + "loss": 3.9109, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.53623318961479e-05, + "loss": 3.9267, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.5353962327441115e-05, + "loss": 3.9185, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.5345576379930595e-05, + "loss": 3.9083, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.533719043242008e-05, + "loss": 3.9124, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.5328804484909552e-05, + "loss": 3.9172, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.5320418537399032e-05, + "loss": 3.9201, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5312032589888512e-05, + "loss": 3.9144, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5303663021181724e-05, + "loss": 3.9146, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.5295277073671204e-05, + "loss": 3.9223, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.5286891126160684e-05, + "loss": 3.9306, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5278505178650164e-05, + "loss": 3.9235, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5270119231139644e-05, + "loss": 3.9145, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.5261733283629124e-05, + "loss": 3.9289, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.5253347336118604e-05, + "loss": 3.9197, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.5244961388608084e-05, + "loss": 3.9072, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.5236591819901296e-05, + "loss": 3.9208, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.5228205872390776e-05, + "loss": 3.9136, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.5219819924880256e-05, + "loss": 3.9186, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5211433977369736e-05, + "loss": 3.9101, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5203064408662945e-05, + "loss": 3.9218, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5194694839956158e-05, + "loss": 3.9071, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5186308892445638e-05, + "loss": 3.9132, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.5177922944935118e-05, + "loss": 3.9087, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.5169536997424598e-05, + "loss": 3.9307, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.5161151049914078e-05, + "loss": 3.9245, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.5152781481207287e-05, + "loss": 3.9247, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.514439553369677e-05, + "loss": 3.9098, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.513602596498998e-05, + "loss": 3.9206, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.512764001747946e-05, + "loss": 3.9263, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.511925406996894e-05, + "loss": 3.9176, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.511086812245842e-05, + "loss": 3.9164, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.51024821749479e-05, + "loss": 3.9243, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.509409622743738e-05, + "loss": 3.92, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.508571027992686e-05, + "loss": 3.9262, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5077324332416342e-05, + "loss": 3.9099, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5068938384905822e-05, + "loss": 3.9225, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.506056881619903e-05, + "loss": 3.9119, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.505218286868851e-05, + "loss": 3.9151, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.504379692117799e-05, + "loss": 3.9191, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.503541097366747e-05, + "loss": 3.9249, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.502702502615695e-05, + "loss": 3.9191, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5018639078646435e-05, + "loss": 3.911, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.5010253131135908e-05, + "loss": 3.9138, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 4.000204086303711, + "eval_runtime": 289.3201, + "eval_samples_per_second": 1318.923, + "eval_steps_per_second": 41.217, + "step": 1526400 + }, + { + "epoch": 1.0, + "learning_rate": 2.5001883562429124e-05, + "loss": 3.9221, + "step": 1526784 + }, + { + "epoch": 1.0, + "learning_rate": 2.49934976149186e-05, + "loss": 3.9159, + "step": 1527296 + }, + { + "epoch": 1.0, + "learning_rate": 2.4985128046211813e-05, + "loss": 3.9218, + "step": 1527808 + }, + { + "epoch": 1.0, + "learning_rate": 2.4976742098701293e-05, + "loss": 3.9147, + "step": 1528320 + }, + { + "epoch": 1.0, + "learning_rate": 2.4968356151190773e-05, + "loss": 3.9294, + "step": 1528832 + }, + { + "epoch": 1.0, + "learning_rate": 2.4959970203680252e-05, + "loss": 3.9142, + "step": 1529344 + }, + { + "epoch": 1.0, + "learning_rate": 2.4951584256169732e-05, + "loss": 3.919, + "step": 1529856 + }, + { + "epoch": 1.0, + "learning_rate": 2.494321468746294e-05, + "loss": 3.9094, + "step": 1530368 + }, + { + "epoch": 1.0, + "learning_rate": 2.4934828739952425e-05, + "loss": 3.9221, + "step": 1530880 + }, + { + "epoch": 1.0, + "learning_rate": 2.4926442792441905e-05, + "loss": 3.9234, + "step": 1531392 + }, + { + "epoch": 1.0, + "learning_rate": 2.4918056844931385e-05, + "loss": 3.9201, + "step": 1531904 + }, + { + "epoch": 1.0, + "learning_rate": 2.4909670897420865e-05, + "loss": 3.9218, + "step": 1532416 + }, + { + "epoch": 1.0, + "learning_rate": 2.4901301328714074e-05, + "loss": 3.9099, + "step": 1532928 + }, + { + "epoch": 1.0, + "learning_rate": 2.4892915381203554e-05, + "loss": 3.9153, + "step": 1533440 + }, + { + "epoch": 1.0, + "learning_rate": 2.4884529433693034e-05, + "loss": 3.9122, + "step": 1533952 + }, + { + "epoch": 1.0, + "learning_rate": 2.4876143486182517e-05, + "loss": 3.9141, + "step": 1534464 + }, + { + "epoch": 1.0, + "learning_rate": 2.4867757538671997e-05, + "loss": 3.9162, + "step": 1534976 + }, + { + "epoch": 1.0, + "learning_rate": 2.4859371591161474e-05, + "loss": 3.9141, + "step": 1535488 + }, + { + "epoch": 1.0, + "learning_rate": 2.4850985643650954e-05, + "loss": 3.9146, + "step": 1536000 + }, + { + "epoch": 1.0, + "learning_rate": 2.4842599696140434e-05, + "loss": 3.9276, + "step": 1536512 + }, + { + "epoch": 1.0, + "learning_rate": 2.4834213748629913e-05, + "loss": 3.9237, + "step": 1537024 + }, + { + "epoch": 1.0, + "learning_rate": 2.4825827801119393e-05, + "loss": 3.9194, + "step": 1537536 + }, + { + "epoch": 1.0, + "learning_rate": 2.4817458232412606e-05, + "loss": 3.9229, + "step": 1538048 + }, + { + "epoch": 1.0, + "learning_rate": 2.4809072284902086e-05, + "loss": 3.9265, + "step": 1538560 + }, + { + "epoch": 1.0, + "learning_rate": 2.4800686337391566e-05, + "loss": 3.9059, + "step": 1539072 + }, + { + "epoch": 1.0, + "learning_rate": 2.4792300389881046e-05, + "loss": 3.9227, + "step": 1539584 + }, + { + "epoch": 1.0, + "learning_rate": 2.4783914442370526e-05, + "loss": 3.9122, + "step": 1540096 + }, + { + "epoch": 1.0, + "learning_rate": 2.4775528494860006e-05, + "loss": 3.9096, + "step": 1540608 + }, + { + "epoch": 1.0, + "learning_rate": 2.4767158926153218e-05, + "loss": 3.9061, + "step": 1541120 + }, + { + "epoch": 1.0, + "learning_rate": 2.4758772978642698e-05, + "loss": 3.9155, + "step": 1541632 + }, + { + "epoch": 1.01, + "learning_rate": 2.4750387031132178e-05, + "loss": 3.9129, + "step": 1542144 + }, + { + "epoch": 1.01, + "learning_rate": 2.4742001083621655e-05, + "loss": 3.9268, + "step": 1542656 + }, + { + "epoch": 1.01, + "learning_rate": 2.4733615136111135e-05, + "loss": 3.9191, + "step": 1543168 + }, + { + "epoch": 1.01, + "learning_rate": 2.4725245567404347e-05, + "loss": 3.9181, + "step": 1543680 + }, + { + "epoch": 1.01, + "learning_rate": 2.471687599869756e-05, + "loss": 3.9103, + "step": 1544192 + }, + { + "epoch": 1.01, + "learning_rate": 2.470849005118704e-05, + "loss": 3.9175, + "step": 1544704 + }, + { + "epoch": 1.01, + "learning_rate": 2.470010410367652e-05, + "loss": 3.9104, + "step": 1545216 + }, + { + "epoch": 1.01, + "learning_rate": 2.4691718156166e-05, + "loss": 3.9231, + "step": 1545728 + }, + { + "epoch": 1.01, + "learning_rate": 2.4683332208655476e-05, + "loss": 3.9043, + "step": 1546240 + }, + { + "epoch": 1.01, + "learning_rate": 2.467496263994869e-05, + "loss": 3.9091, + "step": 1546752 + }, + { + "epoch": 1.01, + "learning_rate": 2.4666576692438172e-05, + "loss": 3.9144, + "step": 1547264 + }, + { + "epoch": 1.01, + "learning_rate": 2.4658190744927652e-05, + "loss": 3.9253, + "step": 1547776 + }, + { + "epoch": 1.01, + "learning_rate": 2.464980479741713e-05, + "loss": 3.9128, + "step": 1548288 + }, + { + "epoch": 1.01, + "learning_rate": 2.464141884990661e-05, + "loss": 3.9133, + "step": 1548800 + }, + { + "epoch": 1.01, + "learning_rate": 2.4633032902396088e-05, + "loss": 3.9178, + "step": 1549312 + }, + { + "epoch": 1.01, + "learning_rate": 2.46246633336893e-05, + "loss": 3.9127, + "step": 1549824 + }, + { + "epoch": 1.01, + "learning_rate": 2.461627738617878e-05, + "loss": 3.919, + "step": 1550336 + }, + { + "epoch": 1.01, + "learning_rate": 2.460789143866826e-05, + "loss": 3.9076, + "step": 1550848 + }, + { + "epoch": 1.01, + "learning_rate": 2.459950549115774e-05, + "loss": 3.9016, + "step": 1551360 + }, + { + "epoch": 1.01, + "learning_rate": 2.459113592245095e-05, + "loss": 3.9208, + "step": 1551872 + }, + { + "epoch": 1.01, + "learning_rate": 2.458274997494043e-05, + "loss": 3.9129, + "step": 1552384 + }, + { + "epoch": 1.01, + "learning_rate": 2.457436402742991e-05, + "loss": 3.9121, + "step": 1552896 + }, + { + "epoch": 1.01, + "learning_rate": 2.456597807991939e-05, + "loss": 3.9091, + "step": 1553408 + }, + { + "epoch": 1.01, + "learning_rate": 2.4557592132408873e-05, + "loss": 3.9143, + "step": 1553920 + }, + { + "epoch": 1.01, + "learning_rate": 2.4549222563702082e-05, + "loss": 3.9005, + "step": 1554432 + }, + { + "epoch": 1.01, + "learning_rate": 2.4540836616191562e-05, + "loss": 3.9151, + "step": 1554944 + }, + { + "epoch": 1.01, + "learning_rate": 2.4532450668681042e-05, + "loss": 3.9013, + "step": 1555456 + }, + { + "epoch": 1.01, + "learning_rate": 2.4524064721170522e-05, + "loss": 3.9108, + "step": 1555968 + }, + { + "epoch": 1.01, + "learning_rate": 2.4515678773660002e-05, + "loss": 3.9151, + "step": 1556480 + }, + { + "epoch": 1.01, + "learning_rate": 2.4507292826149482e-05, + "loss": 3.9137, + "step": 1556992 + }, + { + "epoch": 1.01, + "learning_rate": 2.4498906878638962e-05, + "loss": 3.9092, + "step": 1557504 + }, + { + "epoch": 1.01, + "learning_rate": 2.4490520931128442e-05, + "loss": 3.9221, + "step": 1558016 + }, + { + "epoch": 1.01, + "learning_rate": 2.448213498361792e-05, + "loss": 3.893, + "step": 1558528 + }, + { + "epoch": 1.01, + "learning_rate": 2.44737490361074e-05, + "loss": 3.9022, + "step": 1559040 + }, + { + "epoch": 1.01, + "learning_rate": 2.446536308859688e-05, + "loss": 3.9192, + "step": 1559552 + }, + { + "epoch": 1.01, + "learning_rate": 2.445697714108636e-05, + "loss": 3.9124, + "step": 1560064 + }, + { + "epoch": 1.01, + "learning_rate": 2.4448607572379574e-05, + "loss": 3.9085, + "step": 1560576 + }, + { + "epoch": 1.01, + "learning_rate": 2.4440221624869054e-05, + "loss": 3.9, + "step": 1561088 + }, + { + "epoch": 1.01, + "learning_rate": 2.4431835677358534e-05, + "loss": 3.9014, + "step": 1561600 + }, + { + "epoch": 1.01, + "learning_rate": 2.4423449729848014e-05, + "loss": 3.9131, + "step": 1562112 + }, + { + "epoch": 1.01, + "learning_rate": 2.441506378233749e-05, + "loss": 3.9209, + "step": 1562624 + }, + { + "epoch": 1.01, + "learning_rate": 2.4406694213630703e-05, + "loss": 3.9087, + "step": 1563136 + }, + { + "epoch": 1.01, + "learning_rate": 2.4398308266120183e-05, + "loss": 3.9187, + "step": 1563648 + }, + { + "epoch": 1.01, + "learning_rate": 2.4389922318609666e-05, + "loss": 3.922, + "step": 1564160 + }, + { + "epoch": 1.01, + "learning_rate": 2.4381536371099143e-05, + "loss": 3.9334, + "step": 1564672 + }, + { + "epoch": 1.01, + "learning_rate": 2.4373150423588623e-05, + "loss": 3.898, + "step": 1565184 + }, + { + "epoch": 1.01, + "learning_rate": 2.4364780854881835e-05, + "loss": 3.9118, + "step": 1565696 + }, + { + "epoch": 1.01, + "learning_rate": 2.4356394907371312e-05, + "loss": 3.921, + "step": 1566208 + }, + { + "epoch": 1.01, + "learning_rate": 2.4348008959860795e-05, + "loss": 3.9008, + "step": 1566720 + }, + { + "epoch": 1.01, + "learning_rate": 2.4339639391154008e-05, + "loss": 3.9179, + "step": 1567232 + }, + { + "epoch": 1.01, + "learning_rate": 2.4331253443643488e-05, + "loss": 3.916, + "step": 1567744 + }, + { + "epoch": 1.01, + "learning_rate": 2.4322867496132964e-05, + "loss": 3.92, + "step": 1568256 + }, + { + "epoch": 1.01, + "learning_rate": 2.4314481548622444e-05, + "loss": 3.9162, + "step": 1568768 + }, + { + "epoch": 1.01, + "learning_rate": 2.4306095601111924e-05, + "loss": 3.9028, + "step": 1569280 + }, + { + "epoch": 1.01, + "learning_rate": 2.4297709653601404e-05, + "loss": 3.9073, + "step": 1569792 + }, + { + "epoch": 1.01, + "learning_rate": 2.4289323706090884e-05, + "loss": 3.9063, + "step": 1570304 + }, + { + "epoch": 1.01, + "learning_rate": 2.4280937758580367e-05, + "loss": 3.9132, + "step": 1570816 + }, + { + "epoch": 1.01, + "learning_rate": 2.4272551811069847e-05, + "loss": 3.9204, + "step": 1571328 + }, + { + "epoch": 1.01, + "learning_rate": 2.4264165863559324e-05, + "loss": 3.9031, + "step": 1571840 + }, + { + "epoch": 1.02, + "learning_rate": 2.4255779916048804e-05, + "loss": 3.911, + "step": 1572352 + }, + { + "epoch": 1.02, + "learning_rate": 2.4247393968538284e-05, + "loss": 3.9012, + "step": 1572864 + }, + { + "epoch": 1.02, + "learning_rate": 2.4239024399831496e-05, + "loss": 3.9079, + "step": 1573376 + }, + { + "epoch": 1.02, + "learning_rate": 2.423065483112471e-05, + "loss": 3.9114, + "step": 1573888 + }, + { + "epoch": 1.02, + "learning_rate": 2.4222285262417918e-05, + "loss": 3.9128, + "step": 1574400 + }, + { + "epoch": 1.02, + "learning_rate": 2.4213899314907398e-05, + "loss": 3.9228, + "step": 1574912 + }, + { + "epoch": 1.02, + "learning_rate": 2.4205513367396878e-05, + "loss": 3.9111, + "step": 1575424 + }, + { + "epoch": 1.02, + "learning_rate": 2.4197127419886358e-05, + "loss": 3.9091, + "step": 1575936 + }, + { + "epoch": 1.02, + "learning_rate": 2.4188741472375838e-05, + "loss": 3.9105, + "step": 1576448 + }, + { + "epoch": 1.02, + "learning_rate": 2.418035552486532e-05, + "loss": 3.9134, + "step": 1576960 + }, + { + "epoch": 1.02, + "learning_rate": 2.4171969577354798e-05, + "loss": 3.9184, + "step": 1577472 + }, + { + "epoch": 1.02, + "learning_rate": 2.4163583629844278e-05, + "loss": 3.9022, + "step": 1577984 + }, + { + "epoch": 1.02, + "learning_rate": 2.4155197682333757e-05, + "loss": 3.91, + "step": 1578496 + }, + { + "epoch": 1.02, + "learning_rate": 2.4146828113626967e-05, + "loss": 3.914, + "step": 1579008 + }, + { + "epoch": 1.02, + "learning_rate": 2.413844216611645e-05, + "loss": 3.9177, + "step": 1579520 + }, + { + "epoch": 1.02, + "learning_rate": 2.413005621860593e-05, + "loss": 3.8973, + "step": 1580032 + }, + { + "epoch": 1.02, + "learning_rate": 2.412167027109541e-05, + "loss": 3.9044, + "step": 1580544 + }, + { + "epoch": 1.02, + "learning_rate": 2.411328432358489e-05, + "loss": 3.9175, + "step": 1581056 + }, + { + "epoch": 1.02, + "learning_rate": 2.410489837607437e-05, + "loss": 3.9121, + "step": 1581568 + }, + { + "epoch": 1.02, + "learning_rate": 2.409651242856385e-05, + "loss": 3.8987, + "step": 1582080 + }, + { + "epoch": 1.02, + "learning_rate": 2.4088126481053326e-05, + "loss": 3.9108, + "step": 1582592 + }, + { + "epoch": 1.02, + "learning_rate": 2.4079756912346542e-05, + "loss": 3.9037, + "step": 1583104 + }, + { + "epoch": 1.02, + "learning_rate": 2.4071370964836022e-05, + "loss": 3.9169, + "step": 1583616 + }, + { + "epoch": 1.02, + "learning_rate": 2.40629850173255e-05, + "loss": 3.9073, + "step": 1584128 + }, + { + "epoch": 1.02, + "learning_rate": 2.405459906981498e-05, + "loss": 3.9029, + "step": 1584640 + }, + { + "epoch": 1.02, + "learning_rate": 2.404622950110819e-05, + "loss": 3.9178, + "step": 1585152 + }, + { + "epoch": 1.02, + "learning_rate": 2.403784355359767e-05, + "loss": 3.9254, + "step": 1585664 + }, + { + "epoch": 1.02, + "learning_rate": 2.4029473984890884e-05, + "loss": 3.9127, + "step": 1586176 + }, + { + "epoch": 1.02, + "learning_rate": 2.4021088037380364e-05, + "loss": 3.9098, + "step": 1586688 + }, + { + "epoch": 1.02, + "learning_rate": 2.4012702089869843e-05, + "loss": 3.9154, + "step": 1587200 + }, + { + "epoch": 1.02, + "learning_rate": 2.4004316142359323e-05, + "loss": 3.9156, + "step": 1587712 + }, + { + "epoch": 1.02, + "learning_rate": 2.3995946573652533e-05, + "loss": 3.9038, + "step": 1588224 + }, + { + "epoch": 1.02, + "learning_rate": 2.3987560626142012e-05, + "loss": 3.9175, + "step": 1588736 + }, + { + "epoch": 1.02, + "learning_rate": 2.3979174678631496e-05, + "loss": 3.9047, + "step": 1589248 + }, + { + "epoch": 1.02, + "learning_rate": 2.3970788731120972e-05, + "loss": 3.9084, + "step": 1589760 + }, + { + "epoch": 1.02, + "learning_rate": 2.3962402783610452e-05, + "loss": 3.9035, + "step": 1590272 + }, + { + "epoch": 1.02, + "learning_rate": 2.3954016836099932e-05, + "loss": 3.9108, + "step": 1590784 + }, + { + "epoch": 1.02, + "learning_rate": 2.3945630888589412e-05, + "loss": 3.902, + "step": 1591296 + }, + { + "epoch": 1.02, + "learning_rate": 2.393726131988262e-05, + "loss": 3.9033, + "step": 1591808 + }, + { + "epoch": 1.02, + "learning_rate": 2.3928875372372105e-05, + "loss": 3.9059, + "step": 1592320 + }, + { + "epoch": 1.02, + "learning_rate": 2.3920489424861585e-05, + "loss": 3.9194, + "step": 1592832 + }, + { + "epoch": 1.02, + "learning_rate": 2.3912103477351065e-05, + "loss": 3.9187, + "step": 1593344 + }, + { + "epoch": 1.02, + "learning_rate": 2.3903733908644274e-05, + "loss": 3.9187, + "step": 1593856 + }, + { + "epoch": 1.02, + "learning_rate": 2.3895347961133754e-05, + "loss": 3.9001, + "step": 1594368 + }, + { + "epoch": 1.02, + "learning_rate": 2.3886978392426966e-05, + "loss": 3.916, + "step": 1594880 + }, + { + "epoch": 1.02, + "learning_rate": 2.3878592444916446e-05, + "loss": 3.9175, + "step": 1595392 + }, + { + "epoch": 1.02, + "learning_rate": 2.3870206497405926e-05, + "loss": 3.9123, + "step": 1595904 + }, + { + "epoch": 1.02, + "learning_rate": 2.3861820549895406e-05, + "loss": 3.9077, + "step": 1596416 + }, + { + "epoch": 1.02, + "learning_rate": 2.3853434602384886e-05, + "loss": 3.92, + "step": 1596928 + }, + { + "epoch": 1.02, + "learning_rate": 2.3845048654874366e-05, + "loss": 3.9111, + "step": 1597440 + }, + { + "epoch": 1.02, + "learning_rate": 2.3836662707363846e-05, + "loss": 3.92, + "step": 1597952 + }, + { + "epoch": 1.02, + "learning_rate": 2.3828276759853326e-05, + "loss": 3.8983, + "step": 1598464 + }, + { + "epoch": 1.02, + "learning_rate": 2.3819890812342806e-05, + "loss": 3.92, + "step": 1598976 + }, + { + "epoch": 1.02, + "learning_rate": 2.3811504864832286e-05, + "loss": 3.9015, + "step": 1599488 + }, + { + "epoch": 1.02, + "learning_rate": 2.3803118917321766e-05, + "loss": 3.9079, + "step": 1600000 + }, + { + "epoch": 1.02, + "learning_rate": 2.3794732969811246e-05, + "loss": 3.9135, + "step": 1600512 + }, + { + "epoch": 1.02, + "learning_rate": 2.3786363401104455e-05, + "loss": 3.9137, + "step": 1601024 + }, + { + "epoch": 1.02, + "learning_rate": 2.3777977453593935e-05, + "loss": 3.9135, + "step": 1601536 + }, + { + "epoch": 1.02, + "learning_rate": 2.3769591506083415e-05, + "loss": 3.8995, + "step": 1602048 + }, + { + "epoch": 1.02, + "learning_rate": 2.3761205558572898e-05, + "loss": 3.9124, + "step": 1602560 + }, + { + "epoch": 1.03, + "eval_loss": 3.996628761291504, + "eval_runtime": 283.9803, + "eval_samples_per_second": 1343.723, + "eval_steps_per_second": 41.992, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.3752819611062378e-05, + "loss": 3.9109, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.3744433663551858e-05, + "loss": 3.9101, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.3736047716041334e-05, + "loss": 3.9142, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3727661768530814e-05, + "loss": 3.9085, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3719275821020294e-05, + "loss": 3.9204, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3710889873509774e-05, + "loss": 3.906, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3702503925999254e-05, + "loss": 3.9058, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.3694117978488738e-05, + "loss": 3.9068, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.3685732030978218e-05, + "loss": 3.9104, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3677346083467694e-05, + "loss": 3.9161, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3668960135957174e-05, + "loss": 3.911, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3660574188446654e-05, + "loss": 3.9169, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3652204619739867e-05, + "loss": 3.9047, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3643818672229347e-05, + "loss": 3.9086, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3635432724718826e-05, + "loss": 3.9068, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3627046777208306e-05, + "loss": 3.9021, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3618660829697786e-05, + "loss": 3.9098, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3610274882187266e-05, + "loss": 3.9043, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3601888934676746e-05, + "loss": 3.9045, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3593502987166223e-05, + "loss": 3.9233, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3585117039655706e-05, + "loss": 3.914, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.357674747094892e-05, + "loss": 3.9181, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.35683615234384e-05, + "loss": 3.9128, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3559975575927875e-05, + "loss": 3.9183, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3551589628417355e-05, + "loss": 3.9002, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3543203680906835e-05, + "loss": 3.9162, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3534817733396315e-05, + "loss": 3.906, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.35264317858858e-05, + "loss": 3.8976, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.3518062217179008e-05, + "loss": 3.902, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.3509676269668487e-05, + "loss": 3.9061, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.3501290322157967e-05, + "loss": 3.9091, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3492904374647447e-05, + "loss": 3.918, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.348453480594066e-05, + "loss": 3.916, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.347614885843014e-05, + "loss": 3.9108, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.346777928972335e-05, + "loss": 3.9049, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.345939334221283e-05, + "loss": 3.9078, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.345100739470231e-05, + "loss": 3.9042, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.344262144719179e-05, + "loss": 3.9135, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.343423549968127e-05, + "loss": 3.8992, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3425849552170752e-05, + "loss": 3.8984, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.341746360466023e-05, + "loss": 3.9066, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.340907765714971e-05, + "loss": 3.9179, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.340069170963919e-05, + "loss": 3.9082, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.339230576212867e-05, + "loss": 3.9051, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.338391981461815e-05, + "loss": 3.9117, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.337553386710763e-05, + "loss": 3.9044, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.336716429840084e-05, + "loss": 3.9138, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.335877835089032e-05, + "loss": 3.8997, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.33503924033798e-05, + "loss": 3.8935, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.334200645586928e-05, + "loss": 3.9137, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.333362050835876e-05, + "loss": 3.9062, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3325234560848237e-05, + "loss": 3.9033, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3316864992141453e-05, + "loss": 3.9065, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3308479044630933e-05, + "loss": 3.9027, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.330009309712041e-05, + "loss": 3.8959, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.329170714960989e-05, + "loss": 3.9033, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.328332120209937e-05, + "loss": 3.8963, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.3274951633392582e-05, + "loss": 3.9034, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.3266582064685795e-05, + "loss": 3.9116, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3258196117175275e-05, + "loss": 3.9021, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3249810169664755e-05, + "loss": 3.9041, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3241424222154234e-05, + "loss": 3.9127, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.323303827464371e-05, + "loss": 3.8896, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.322465232713319e-05, + "loss": 3.8958, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.321626637962267e-05, + "loss": 3.9064, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.3207880432112154e-05, + "loss": 3.9082, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3199494484601634e-05, + "loss": 3.8981, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3191108537091114e-05, + "loss": 3.8971, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.318272258958059e-05, + "loss": 3.8916, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.317433664207007e-05, + "loss": 3.9067, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.316595069455955e-05, + "loss": 3.9121, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.3157581125852763e-05, + "loss": 3.9045, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3149195178342243e-05, + "loss": 3.9127, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.3140809230831723e-05, + "loss": 3.9091, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3132423283321203e-05, + "loss": 3.9333, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3124053714614416e-05, + "loss": 3.8935, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3115667767103892e-05, + "loss": 3.9029, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3107298198397108e-05, + "loss": 3.9155, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3098912250886588e-05, + "loss": 3.8938, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3090526303376064e-05, + "loss": 3.9114, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3082140355865544e-05, + "loss": 3.9089, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3073754408355024e-05, + "loss": 3.9121, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3065368460844504e-05, + "loss": 3.9092, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3056998892137717e-05, + "loss": 3.8964, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3048612944627197e-05, + "loss": 3.9062, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.3040226997116677e-05, + "loss": 3.8923, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3031841049606157e-05, + "loss": 3.9096, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3023455102095637e-05, + "loss": 3.9125, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3015069154585117e-05, + "loss": 3.8943, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.300669958587833e-05, + "loss": 3.9061, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.299831363836781e-05, + "loss": 3.8957, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.298992769085729e-05, + "loss": 3.897, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.298154174334677e-05, + "loss": 3.9006, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.297318855344371e-05, + "loss": 3.9138, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.296480260593319e-05, + "loss": 3.9168, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.295641665842267e-05, + "loss": 3.8999, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.294803071091215e-05, + "loss": 3.8991, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.293964476340163e-05, + "loss": 3.9068, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.293125881589111e-05, + "loss": 3.9014, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.292287286838059e-05, + "loss": 3.9161, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2914486920870067e-05, + "loss": 3.8968, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2906100973359547e-05, + "loss": 3.9028, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.289771502584903e-05, + "loss": 3.9067, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.288932907833851e-05, + "loss": 3.9124, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.288094313082799e-05, + "loss": 3.889, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.287255718331747e-05, + "loss": 3.8986, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.286418761461068e-05, + "loss": 3.904, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.285580166710016e-05, + "loss": 3.9082, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.284741571958964e-05, + "loss": 3.89, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2839029772079122e-05, + "loss": 3.9104, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2830643824568602e-05, + "loss": 3.8919, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.282227425586181e-05, + "loss": 3.905, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.281388830835129e-05, + "loss": 3.9015, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.280550236084077e-05, + "loss": 3.8965, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.2797116413330248e-05, + "loss": 3.9079, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.2788763223427193e-05, + "loss": 3.9193, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2780377275916673e-05, + "loss": 3.9054, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.2771991328406153e-05, + "loss": 3.9023, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2763605380895633e-05, + "loss": 3.9091, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2755219433385113e-05, + "loss": 3.9086, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.2746833485874593e-05, + "loss": 3.8974, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.2738447538364076e-05, + "loss": 3.9045, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.2730077969657285e-05, + "loss": 3.8993, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2721692022146765e-05, + "loss": 3.9009, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2713306074636245e-05, + "loss": 3.9023, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.270492012712572e-05, + "loss": 3.9014, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.26965341796152e-05, + "loss": 3.8993, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.2688148232104685e-05, + "loss": 3.8934, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2679778663397897e-05, + "loss": 3.9007, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.2671392715887374e-05, + "loss": 3.9089, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2663006768376854e-05, + "loss": 3.9097, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2654620820866334e-05, + "loss": 3.9113, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2646234873355814e-05, + "loss": 3.8912, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2637865304649026e-05, + "loss": 3.914, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.2629479357138506e-05, + "loss": 3.9104, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.2621093409627986e-05, + "loss": 3.9056, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.2612707462117466e-05, + "loss": 3.9047, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2604321514606946e-05, + "loss": 3.9068, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2595951945900155e-05, + "loss": 3.9032, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.258756599838964e-05, + "loss": 3.9184, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.257918005087912e-05, + "loss": 3.8902, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.25707941033686e-05, + "loss": 3.911, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.256240815585808e-05, + "loss": 3.8954, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.2554022208347555e-05, + "loss": 3.9033, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2545636260837035e-05, + "loss": 3.9067, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2537250313326515e-05, + "loss": 3.9013, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.252888074461973e-05, + "loss": 3.9144, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2520494797109207e-05, + "loss": 3.8876, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.251214160720615e-05, + "loss": 3.9072, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.9940643310546875, + "eval_runtime": 320.1187, + "eval_samples_per_second": 1192.03, + "eval_steps_per_second": 37.252, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.250375565969563e-05, + "loss": 3.9078, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.249536971218511e-05, + "loss": 3.9, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.2486983764674592e-05, + "loss": 3.9092, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2478597817164072e-05, + "loss": 3.9023, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.2470211869653552e-05, + "loss": 3.9094, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.246182592214303e-05, + "loss": 3.9012, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.245343997463251e-05, + "loss": 3.8989, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.244507040592572e-05, + "loss": 3.9024, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.24366844584152e-05, + "loss": 3.9038, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2428314889708414e-05, + "loss": 3.9081, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2419928942197894e-05, + "loss": 3.9074, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.2411542994687374e-05, + "loss": 3.9056, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2403173425980583e-05, + "loss": 3.9016, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.2394787478470063e-05, + "loss": 3.9013, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.2386401530959546e-05, + "loss": 3.9008, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.2378015583449026e-05, + "loss": 3.8955, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2369629635938502e-05, + "loss": 3.9022, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.2361243688427982e-05, + "loss": 3.8953, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.2352857740917462e-05, + "loss": 3.8997, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.2344471793406942e-05, + "loss": 3.9142, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.2336085845896422e-05, + "loss": 3.9106, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2327699898385902e-05, + "loss": 3.9091, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.2319313950875382e-05, + "loss": 3.9053, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.2310928003364862e-05, + "loss": 3.9115, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2302558434658075e-05, + "loss": 3.8936, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2294172487147555e-05, + "loss": 3.9106, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.228578653963703e-05, + "loss": 3.899, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.227740059212651e-05, + "loss": 3.8921, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.2269014644615994e-05, + "loss": 3.8961, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.2260628697105474e-05, + "loss": 3.8985, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2252259128398684e-05, + "loss": 3.9021, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2243873180888163e-05, + "loss": 3.9108, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2235487233377643e-05, + "loss": 3.9086, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.2227101285867123e-05, + "loss": 3.9044, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.2218731717160336e-05, + "loss": 3.8958, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.2210345769649816e-05, + "loss": 3.9039, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.2201959822139296e-05, + "loss": 3.902, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2193573874628776e-05, + "loss": 3.8994, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.2185187927118256e-05, + "loss": 3.8966, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.2176801979607736e-05, + "loss": 3.8887, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2168416032097216e-05, + "loss": 3.9012, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.2160046463390428e-05, + "loss": 3.9083, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.2151660515879908e-05, + "loss": 3.9009, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.2143274568369388e-05, + "loss": 3.8981, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.2134888620858865e-05, + "loss": 3.9059, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.2126502673348345e-05, + "loss": 3.8968, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.2118116725837824e-05, + "loss": 3.909, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.2109730778327304e-05, + "loss": 3.8943, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.2101361209620517e-05, + "loss": 3.8832, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.2092975262109997e-05, + "loss": 3.9069, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.2084589314599477e-05, + "loss": 3.9021, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.2076203367088957e-05, + "loss": 3.8996, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.2067817419578437e-05, + "loss": 3.8957, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.2059431472067917e-05, + "loss": 3.8938, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.205106190336113e-05, + "loss": 3.8912, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.204267595585061e-05, + "loss": 3.8949, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.203429000834009e-05, + "loss": 3.8911, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.202590406082957e-05, + "loss": 3.8997, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.2017518113319046e-05, + "loss": 3.9035, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.2009132165808526e-05, + "loss": 3.8974, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.200074621829801e-05, + "loss": 3.8944, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.199236027078749e-05, + "loss": 3.9109, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.198397432327697e-05, + "loss": 3.8799, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.1975604754570178e-05, + "loss": 3.8856, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.196723518586339e-05, + "loss": 3.9018, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1958865617156603e-05, + "loss": 3.9058, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1950479669646083e-05, + "loss": 3.8914, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.1942093722135563e-05, + "loss": 3.891, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.1933707774625043e-05, + "loss": 3.8858, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.192532182711452e-05, + "loss": 3.8974, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.1916935879604e-05, + "loss": 3.9084, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.190854993209348e-05, + "loss": 3.897, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1900163984582963e-05, + "loss": 3.8999, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1891778037072443e-05, + "loss": 3.9076, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.188340846836565e-05, + "loss": 3.9235, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1875038899658864e-05, + "loss": 3.8891, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.186665295214834e-05, + "loss": 3.8986, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.1858267004637824e-05, + "loss": 3.905, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1849881057127304e-05, + "loss": 3.8881, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1841495109616784e-05, + "loss": 3.9038, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1833125540909993e-05, + "loss": 3.9045, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1824739593399473e-05, + "loss": 3.9047, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1816353645888953e-05, + "loss": 3.905, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1807967698378433e-05, + "loss": 3.8889, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.1799581750867913e-05, + "loss": 3.897, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.1791195803357396e-05, + "loss": 3.891, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.1782809855846873e-05, + "loss": 3.8994, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.1774423908336353e-05, + "loss": 3.9063, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.1766037960825833e-05, + "loss": 3.8877, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.1757652013315313e-05, + "loss": 3.8999, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.1749266065804793e-05, + "loss": 3.8924, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.1740880118294273e-05, + "loss": 3.8893, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.1732510549587485e-05, + "loss": 3.8978, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.1724140980880694e-05, + "loss": 3.9043, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.1715755033370174e-05, + "loss": 3.9089, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.1707369085859654e-05, + "loss": 3.8972, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1698983138349134e-05, + "loss": 3.8934, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.1690597190838617e-05, + "loss": 3.9, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.1682211243328097e-05, + "loss": 3.8978, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.1673841674621306e-05, + "loss": 3.9047, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.1665455727110786e-05, + "loss": 3.8933, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.1657086158403995e-05, + "loss": 3.8936, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.164870021089348e-05, + "loss": 3.8991, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.164031426338296e-05, + "loss": 3.9082, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.163192831587244e-05, + "loss": 3.8791, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.162354236836192e-05, + "loss": 3.897, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.16151564208514e-05, + "loss": 3.8966, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.1606770473340875e-05, + "loss": 3.9027, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.1598384525830355e-05, + "loss": 3.8851, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.159001495712357e-05, + "loss": 3.901, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.158162900961305e-05, + "loss": 3.8933, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.1573243062102528e-05, + "loss": 3.8938, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.1564857114592007e-05, + "loss": 3.8988, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.155648754588522e-05, + "loss": 3.8908, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.15481015983747e-05, + "loss": 3.8975, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.153971565086418e-05, + "loss": 3.9146, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.153132970335366e-05, + "loss": 3.9006, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.152294375584314e-05, + "loss": 3.8934, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.151455780833262e-05, + "loss": 3.9038, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.15061718608221e-05, + "loss": 3.9033, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.149778591331158e-05, + "loss": 3.8865, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.148941634460479e-05, + "loss": 3.9035, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1481030397094272e-05, + "loss": 3.8921, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.147266082838748e-05, + "loss": 3.8918, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.146427488087696e-05, + "loss": 3.894, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.1455905312170174e-05, + "loss": 3.894, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.144751936465965e-05, + "loss": 3.892, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.1439133417149134e-05, + "loss": 3.8903, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.1430747469638613e-05, + "loss": 3.8924, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.1422361522128093e-05, + "loss": 3.906, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1413975574617573e-05, + "loss": 3.9002, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.1405589627107053e-05, + "loss": 3.9041, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.139720367959653e-05, + "loss": 3.885, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.138881773208601e-05, + "loss": 3.9101, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.138043178457549e-05, + "loss": 3.9004, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.1372045837064973e-05, + "loss": 3.9004, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.1363676268358182e-05, + "loss": 3.8995, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.1355290320847662e-05, + "loss": 3.9014, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1346904373337142e-05, + "loss": 3.8951, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.1338518425826622e-05, + "loss": 3.9146, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.1330132478316102e-05, + "loss": 3.8855, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.1321746530805582e-05, + "loss": 3.9024, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.1313360583295065e-05, + "loss": 3.892, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.1304974635784542e-05, + "loss": 3.8967, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.1296605067077754e-05, + "loss": 3.8968, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.1288219119567234e-05, + "loss": 3.8942, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.127983317205671e-05, + "loss": 3.9091, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.1271447224546194e-05, + "loss": 3.8869, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.1263077655839407e-05, + "loss": 3.9015, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.9915289878845215, + "eval_runtime": 323.55, + "eval_samples_per_second": 1179.388, + "eval_steps_per_second": 36.857, + "step": 1755360 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 7.254390356620689e+17, + "trial_name": null, + "trial_params": null +}