diff --git "a/checkpoint-2289600/trainer_state.json" "b/checkpoint-2289600/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2289600/trainer_state.json" @@ -0,0 +1,27091 @@ +{ + "best_metric": 3.861919403076172, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/re-irr-sv-agr/transformer/2/checkpoints/checkpoint-839520", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2289600, + "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": 10.9339, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.7961, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1583, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9557, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.7951, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.696, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.5911, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5362, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4416, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4026, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3441, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3218, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2749, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2218, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1892, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1384, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1165, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0927, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0637, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0354, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0224, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9923, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9717, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9355, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9347, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.9029, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8898, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8709, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.845, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.8283, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8102, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.8038, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7855, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7808, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7658, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7542, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969820416244367e-05, + "loss": 4.7417, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7058, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7041, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.693, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6758, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6793, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964790485618428e-05, + "loss": 4.6739, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963951890867376e-05, + "loss": 4.6516, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.6505, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6436, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6353, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6317, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.6123, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 4.5983, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958081727610012e-05, + "loss": 4.6005, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.95724313285896e-05, + "loss": 4.5863, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.587, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 4.5597, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5737, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5478, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5683, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.543, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 4.5395, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.95053765061129e-05, + "loss": 4.5312, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949699055860238e-05, + "loss": 4.5263, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948860461109186e-05, + "loss": 4.5128, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 4.5184, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947184909487455e-05, + "loss": 4.4938, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946346314736403e-05, + "loss": 4.4876, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5015, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 4.4921, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 4.4802, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942993573612568e-05, + "loss": 4.4651, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942154978861516e-05, + "loss": 4.4673, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941316384110464e-05, + "loss": 4.4738, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940477789359412e-05, + "loss": 4.468, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396408324887336e-05, + "loss": 4.4601, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388022377376816e-05, + "loss": 4.4587, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379636429866296e-05, + "loss": 4.46, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371250482355776e-05, + "loss": 4.4524, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362880913648985e-05, + "loss": 4.4301, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354494966138465e-05, + "loss": 4.4314, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346109018627945e-05, + "loss": 4.4306, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337723071117425e-05, + "loss": 4.4217, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329337123606905e-05, + "loss": 4.4218, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932095117609638e-05, + "loss": 4.4141, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931256522858586e-05, + "loss": 4.4306, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 4.4069, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.9295809712368554e-05, + "loss": 4.3908, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.9287423764858034e-05, + "loss": 4.4015, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.9279037817347514e-05, + "loss": 4.3978, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.9270651869836994e-05, + "loss": 4.4028, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.9262265922326474e-05, + "loss": 4.3857, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925389635361968e-05, + "loss": 4.3858, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924551040610916e-05, + "loss": 4.384, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923712445859864e-05, + "loss": 4.3776, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922873851108812e-05, + "loss": 4.3665, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92203525635776e-05, + "loss": 4.3688, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921196661606708e-05, + "loss": 4.3716, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920359704736029e-05, + "loss": 4.3789, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919521109984978e-05, + "loss": 4.3576, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918682515233926e-05, + "loss": 4.3496, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917843920482874e-05, + "loss": 4.3499, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917005325731822e-05, + "loss": 4.3495, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.91616673098077e-05, + "loss": 4.3549, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915328136229718e-05, + "loss": 4.3403, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914489541478666e-05, + "loss": 4.3343, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913652584607987e-05, + "loss": 4.3277, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912813989856935e-05, + "loss": 4.3382, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911975395105883e-05, + "loss": 4.3062, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911136800354831e-05, + "loss": 4.3264, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9102998434841516e-05, + "loss": 4.3179, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.9094612487330996e-05, + "loss": 4.3246, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.9086226539820476e-05, + "loss": 4.3134, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907784059230996e-05, + "loss": 4.3177, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906945464479944e-05, + "loss": 4.3067, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906106869728892e-05, + "loss": 4.3072, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905269912858213e-05, + "loss": 4.3117, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904431318107161e-05, + "loss": 4.2927, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903592723356109e-05, + "loss": 4.3113, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.9027541286050565e-05, + "loss": 4.3076, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901918809614751e-05, + "loss": 4.3007, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901080214863699e-05, + "loss": 4.2902, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900241620112647e-05, + "loss": 4.2891, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899403025361595e-05, + "loss": 4.2905, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.898564430610543e-05, + "loss": 4.2878, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.897725835859491e-05, + "loss": 4.287, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968872411084396e-05, + "loss": 4.2768, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.896048646357387e-05, + "loss": 4.2846, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.895210051606335e-05, + "loss": 4.2669, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.894371456855283e-05, + "loss": 4.2704, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893532862104231e-05, + "loss": 4.2597, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892695905233552e-05, + "loss": 4.2633, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918573104825e-05, + "loss": 4.2529, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891018715731448e-05, + "loss": 4.2745, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890180120980396e-05, + "loss": 4.2769, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889341526229344e-05, + "loss": 4.2628, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888502931478292e-05, + "loss": 4.2435, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766433672724e-05, + "loss": 4.2621, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886825741976188e-05, + "loss": 4.2561, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.8859887851055094e-05, + "loss": 4.253, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515182823483e-05, + "loss": 4.2448, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884313233483778e-05, + "loss": 4.2504, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883474638732726e-05, + "loss": 4.2454, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882636043981674e-05, + "loss": 4.241, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881797449230622e-05, + "loss": 4.2422, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88095885447957e-05, + "loss": 4.2441, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880120259728518e-05, + "loss": 4.2301, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879283302857839e-05, + "loss": 4.2319, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878444708106787e-05, + "loss": 4.2429, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877606113355735e-05, + "loss": 4.2291, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876767518604683e-05, + "loss": 4.2285, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875928923853632e-05, + "loss": 4.2395, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.87509032910258e-05, + "loss": 4.2207, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.2148919105529785, + "eval_runtime": 304.5041, + "eval_samples_per_second": 1253.155, + "eval_steps_per_second": 39.162, + "step": 76320 + }, + { + "epoch": 0.0, + "learning_rate": 4.874251734351528e-05, + "loss": 4.2011, + "step": 76800 + }, + { + "epoch": 0.0, + "learning_rate": 4.873413139600475e-05, + "loss": 4.212, + "step": 77312 + }, + { + "epoch": 0.0, + "learning_rate": 4.872574544849423e-05, + "loss": 4.2259, + "step": 77824 + }, + { + "epoch": 0.0, + "learning_rate": 4.871735950098371e-05, + "loss": 4.2144, + "step": 78336 + }, + { + "epoch": 0.0, + "learning_rate": 4.870897355347319e-05, + "loss": 4.2212, + "step": 78848 + }, + { + "epoch": 0.0, + "learning_rate": 4.870058760596267e-05, + "loss": 4.2, + "step": 79360 + }, + { + "epoch": 0.0, + "learning_rate": 4.869220165845215e-05, + "loss": 4.2117, + "step": 79872 + }, + { + "epoch": 0.0, + "learning_rate": 4.868381571094163e-05, + "loss": 4.1911, + "step": 80384 + }, + { + "epoch": 0.0, + "learning_rate": 4.867542976343111e-05, + "loss": 4.2081, + "step": 80896 + }, + { + "epoch": 0.0, + "learning_rate": 4.866704381592059e-05, + "loss": 4.192, + "step": 81408 + }, + { + "epoch": 0.0, + "learning_rate": 4.865865786841007e-05, + "loss": 4.2064, + "step": 81920 + }, + { + "epoch": 0.0, + "learning_rate": 4.865027192089955e-05, + "loss": 4.2017, + "step": 82432 + }, + { + "epoch": 0.0, + "learning_rate": 4.864190235219277e-05, + "loss": 4.1937, + "step": 82944 + }, + { + "epoch": 0.0, + "learning_rate": 4.863351640468225e-05, + "loss": 4.1842, + "step": 83456 + }, + { + "epoch": 0.0, + "learning_rate": 4.862513045717173e-05, + "loss": 4.1761, + "step": 83968 + }, + { + "epoch": 0.0, + "learning_rate": 4.861674450966121e-05, + "loss": 4.1766, + "step": 84480 + }, + { + "epoch": 0.0, + "learning_rate": 4.8608374940954416e-05, + "loss": 4.1844, + "step": 84992 + }, + { + "epoch": 0.0, + "learning_rate": 4.8599988993443896e-05, + "loss": 4.1834, + "step": 85504 + }, + { + "epoch": 0.0, + "learning_rate": 4.8591603045933376e-05, + "loss": 4.1753, + "step": 86016 + }, + { + "epoch": 0.0, + "learning_rate": 4.8583217098422856e-05, + "loss": 4.1977, + "step": 86528 + }, + { + "epoch": 0.0, + "learning_rate": 4.8574847529716065e-05, + "loss": 4.1866, + "step": 87040 + }, + { + "epoch": 0.0, + "learning_rate": 4.8566461582205545e-05, + "loss": 4.1784, + "step": 87552 + }, + { + "epoch": 0.0, + "learning_rate": 4.8558075634695025e-05, + "loss": 4.1716, + "step": 88064 + }, + { + "epoch": 0.0, + "learning_rate": 4.8549689687184505e-05, + "loss": 4.1891, + "step": 88576 + }, + { + "epoch": 0.0, + "learning_rate": 4.8541303739673985e-05, + "loss": 4.162, + "step": 89088 + }, + { + "epoch": 0.0, + "learning_rate": 4.8532917792163465e-05, + "loss": 4.175, + "step": 89600 + }, + { + "epoch": 0.0, + "learning_rate": 4.8524531844652945e-05, + "loss": 4.1718, + "step": 90112 + }, + { + "epoch": 0.0, + "learning_rate": 4.8516145897142425e-05, + "loss": 4.1649, + "step": 90624 + }, + { + "epoch": 0.0, + "learning_rate": 4.850777632843564e-05, + "loss": 4.1566, + "step": 91136 + }, + { + "epoch": 0.01, + "learning_rate": 4.8499390380925114e-05, + "loss": 4.1548, + "step": 91648 + }, + { + "epoch": 0.01, + "learning_rate": 4.849102081221833e-05, + "loss": 4.1611, + "step": 92160 + }, + { + "epoch": 0.01, + "learning_rate": 4.848263486470781e-05, + "loss": 4.1593, + "step": 92672 + }, + { + "epoch": 0.01, + "learning_rate": 4.847424891719729e-05, + "loss": 4.1606, + "step": 93184 + }, + { + "epoch": 0.01, + "learning_rate": 4.846586296968676e-05, + "loss": 4.1602, + "step": 93696 + }, + { + "epoch": 0.01, + "learning_rate": 4.845747702217624e-05, + "loss": 4.1594, + "step": 94208 + }, + { + "epoch": 0.01, + "learning_rate": 4.844909107466572e-05, + "loss": 4.1543, + "step": 94720 + }, + { + "epoch": 0.01, + "learning_rate": 4.844072150595894e-05, + "loss": 4.1362, + "step": 95232 + }, + { + "epoch": 0.01, + "learning_rate": 4.843233555844842e-05, + "loss": 4.1444, + "step": 95744 + }, + { + "epoch": 0.01, + "learning_rate": 4.84239496109379e-05, + "loss": 4.138, + "step": 96256 + }, + { + "epoch": 0.01, + "learning_rate": 4.841556366342738e-05, + "loss": 4.1334, + "step": 96768 + }, + { + "epoch": 0.01, + "learning_rate": 4.840719409472059e-05, + "loss": 4.1436, + "step": 97280 + }, + { + "epoch": 0.01, + "learning_rate": 4.839880814721007e-05, + "loss": 4.1456, + "step": 97792 + }, + { + "epoch": 0.01, + "learning_rate": 4.839042219969955e-05, + "loss": 4.1335, + "step": 98304 + }, + { + "epoch": 0.01, + "learning_rate": 4.838203625218903e-05, + "loss": 4.1326, + "step": 98816 + }, + { + "epoch": 0.01, + "learning_rate": 4.8373666683482236e-05, + "loss": 4.1365, + "step": 99328 + }, + { + "epoch": 0.01, + "learning_rate": 4.8365280735971716e-05, + "loss": 4.1362, + "step": 99840 + }, + { + "epoch": 0.01, + "learning_rate": 4.8356894788461196e-05, + "loss": 4.1386, + "step": 100352 + }, + { + "epoch": 0.01, + "learning_rate": 4.8348508840950676e-05, + "loss": 4.1276, + "step": 100864 + }, + { + "epoch": 0.01, + "learning_rate": 4.834013927224389e-05, + "loss": 4.1241, + "step": 101376 + }, + { + "epoch": 0.01, + "learning_rate": 4.833175332473337e-05, + "loss": 4.1293, + "step": 101888 + }, + { + "epoch": 0.01, + "learning_rate": 4.832336737722285e-05, + "loss": 4.1215, + "step": 102400 + }, + { + "epoch": 0.01, + "learning_rate": 4.831498142971233e-05, + "loss": 4.127, + "step": 102912 + }, + { + "epoch": 0.01, + "learning_rate": 4.830659548220181e-05, + "loss": 4.1133, + "step": 103424 + }, + { + "epoch": 0.01, + "learning_rate": 4.829822591349502e-05, + "loss": 4.1268, + "step": 103936 + }, + { + "epoch": 0.01, + "learning_rate": 4.82898399659845e-05, + "loss": 4.1025, + "step": 104448 + }, + { + "epoch": 0.01, + "learning_rate": 4.828145401847398e-05, + "loss": 4.1272, + "step": 104960 + }, + { + "epoch": 0.01, + "learning_rate": 4.827306807096346e-05, + "loss": 4.1137, + "step": 105472 + }, + { + "epoch": 0.01, + "learning_rate": 4.826469850225667e-05, + "loss": 4.1114, + "step": 105984 + }, + { + "epoch": 0.01, + "learning_rate": 4.825631255474615e-05, + "loss": 4.1201, + "step": 106496 + }, + { + "epoch": 0.01, + "learning_rate": 4.824792660723563e-05, + "loss": 4.1086, + "step": 107008 + }, + { + "epoch": 0.01, + "learning_rate": 4.823954065972511e-05, + "loss": 4.1014, + "step": 107520 + }, + { + "epoch": 0.01, + "learning_rate": 4.8231171091018326e-05, + "loss": 4.1158, + "step": 108032 + }, + { + "epoch": 0.01, + "learning_rate": 4.8222785143507806e-05, + "loss": 4.0902, + "step": 108544 + }, + { + "epoch": 0.01, + "learning_rate": 4.8214399195997286e-05, + "loss": 4.0912, + "step": 109056 + }, + { + "epoch": 0.01, + "learning_rate": 4.8206013248486766e-05, + "loss": 4.1074, + "step": 109568 + }, + { + "epoch": 0.01, + "learning_rate": 4.8197643679779975e-05, + "loss": 4.1053, + "step": 110080 + }, + { + "epoch": 0.01, + "learning_rate": 4.8189257732269455e-05, + "loss": 4.0985, + "step": 110592 + }, + { + "epoch": 0.01, + "learning_rate": 4.8180871784758935e-05, + "loss": 4.0878, + "step": 111104 + }, + { + "epoch": 0.01, + "learning_rate": 4.8172485837248415e-05, + "loss": 4.0884, + "step": 111616 + }, + { + "epoch": 0.01, + "learning_rate": 4.8164116268541624e-05, + "loss": 4.0957, + "step": 112128 + }, + { + "epoch": 0.01, + "learning_rate": 4.8155730321031104e-05, + "loss": 4.1038, + "step": 112640 + }, + { + "epoch": 0.01, + "learning_rate": 4.8147344373520584e-05, + "loss": 4.0941, + "step": 113152 + }, + { + "epoch": 0.01, + "learning_rate": 4.8138958426010064e-05, + "loss": 4.0994, + "step": 113664 + }, + { + "epoch": 0.01, + "learning_rate": 4.813057247849955e-05, + "loss": 4.1002, + "step": 114176 + }, + { + "epoch": 0.01, + "learning_rate": 4.812218653098903e-05, + "loss": 4.098, + "step": 114688 + }, + { + "epoch": 0.01, + "learning_rate": 4.811381696228224e-05, + "loss": 4.08, + "step": 115200 + }, + { + "epoch": 0.01, + "learning_rate": 4.810543101477172e-05, + "loss": 4.0841, + "step": 115712 + }, + { + "epoch": 0.01, + "learning_rate": 4.80970450672612e-05, + "loss": 4.091, + "step": 116224 + }, + { + "epoch": 0.01, + "learning_rate": 4.808865911975068e-05, + "loss": 4.0803, + "step": 116736 + }, + { + "epoch": 0.01, + "learning_rate": 4.808028955104389e-05, + "loss": 4.0854, + "step": 117248 + }, + { + "epoch": 0.01, + "learning_rate": 4.807190360353337e-05, + "loss": 4.0773, + "step": 117760 + }, + { + "epoch": 0.01, + "learning_rate": 4.806351765602285e-05, + "loss": 4.0987, + "step": 118272 + }, + { + "epoch": 0.01, + "learning_rate": 4.805513170851233e-05, + "loss": 4.0801, + "step": 118784 + }, + { + "epoch": 0.01, + "learning_rate": 4.804676213980554e-05, + "loss": 4.0679, + "step": 119296 + }, + { + "epoch": 0.01, + "learning_rate": 4.803837619229502e-05, + "loss": 4.0769, + "step": 119808 + }, + { + "epoch": 0.01, + "learning_rate": 4.8029990244784504e-05, + "loss": 4.0793, + "step": 120320 + }, + { + "epoch": 0.01, + "learning_rate": 4.8021604297273984e-05, + "loss": 4.085, + "step": 120832 + }, + { + "epoch": 0.01, + "learning_rate": 4.801323472856719e-05, + "loss": 4.0706, + "step": 121344 + }, + { + "epoch": 0.01, + "learning_rate": 4.800484878105667e-05, + "loss": 4.0712, + "step": 121856 + }, + { + "epoch": 0.02, + "learning_rate": 4.799646283354615e-05, + "loss": 4.0796, + "step": 122368 + }, + { + "epoch": 0.02, + "learning_rate": 4.798807688603563e-05, + "loss": 4.0681, + "step": 122880 + }, + { + "epoch": 0.02, + "learning_rate": 4.797970731732884e-05, + "loss": 4.0632, + "step": 123392 + }, + { + "epoch": 0.02, + "learning_rate": 4.797132136981832e-05, + "loss": 4.0679, + "step": 123904 + }, + { + "epoch": 0.02, + "learning_rate": 4.79629354223078e-05, + "loss": 4.074, + "step": 124416 + }, + { + "epoch": 0.02, + "learning_rate": 4.795456585360101e-05, + "loss": 4.0774, + "step": 124928 + }, + { + "epoch": 0.02, + "learning_rate": 4.794617990609049e-05, + "loss": 4.0706, + "step": 125440 + }, + { + "epoch": 0.02, + "learning_rate": 4.793779395857997e-05, + "loss": 4.0543, + "step": 125952 + }, + { + "epoch": 0.02, + "learning_rate": 4.792940801106946e-05, + "loss": 4.0609, + "step": 126464 + }, + { + "epoch": 0.02, + "learning_rate": 4.792102206355894e-05, + "loss": 4.0635, + "step": 126976 + }, + { + "epoch": 0.02, + "learning_rate": 4.791263611604842e-05, + "loss": 4.0654, + "step": 127488 + }, + { + "epoch": 0.02, + "learning_rate": 4.79042501685379e-05, + "loss": 4.0621, + "step": 128000 + }, + { + "epoch": 0.02, + "learning_rate": 4.789586422102737e-05, + "loss": 4.0562, + "step": 128512 + }, + { + "epoch": 0.02, + "learning_rate": 4.7887494652320587e-05, + "loss": 4.0488, + "step": 129024 + }, + { + "epoch": 0.02, + "learning_rate": 4.7879108704810067e-05, + "loss": 4.0654, + "step": 129536 + }, + { + "epoch": 0.02, + "learning_rate": 4.7870722757299546e-05, + "loss": 4.0299, + "step": 130048 + }, + { + "epoch": 0.02, + "learning_rate": 4.786233680978902e-05, + "loss": 4.0545, + "step": 130560 + }, + { + "epoch": 0.02, + "learning_rate": 4.7853967241082236e-05, + "loss": 4.0469, + "step": 131072 + }, + { + "epoch": 0.02, + "learning_rate": 4.7845581293571715e-05, + "loss": 4.0592, + "step": 131584 + }, + { + "epoch": 0.02, + "learning_rate": 4.7837195346061195e-05, + "loss": 4.044, + "step": 132096 + }, + { + "epoch": 0.02, + "learning_rate": 4.7828809398550675e-05, + "loss": 4.0537, + "step": 132608 + }, + { + "epoch": 0.02, + "learning_rate": 4.782043982984389e-05, + "loss": 4.0421, + "step": 133120 + }, + { + "epoch": 0.02, + "learning_rate": 4.781205388233337e-05, + "loss": 4.0446, + "step": 133632 + }, + { + "epoch": 0.02, + "learning_rate": 4.7803667934822844e-05, + "loss": 4.0539, + "step": 134144 + }, + { + "epoch": 0.02, + "learning_rate": 4.7795281987312324e-05, + "loss": 4.0393, + "step": 134656 + }, + { + "epoch": 0.02, + "learning_rate": 4.778691241860554e-05, + "loss": 4.0541, + "step": 135168 + }, + { + "epoch": 0.02, + "learning_rate": 4.777852647109502e-05, + "loss": 4.0553, + "step": 135680 + }, + { + "epoch": 0.02, + "learning_rate": 4.777015690238823e-05, + "loss": 4.0464, + "step": 136192 + }, + { + "epoch": 0.02, + "learning_rate": 4.776177095487771e-05, + "loss": 4.0398, + "step": 136704 + }, + { + "epoch": 0.02, + "learning_rate": 4.775338500736719e-05, + "loss": 4.0433, + "step": 137216 + }, + { + "epoch": 0.02, + "learning_rate": 4.774499905985666e-05, + "loss": 4.0452, + "step": 137728 + }, + { + "epoch": 0.02, + "learning_rate": 4.773661311234615e-05, + "loss": 4.0339, + "step": 138240 + }, + { + "epoch": 0.02, + "learning_rate": 4.772822716483563e-05, + "loss": 4.0476, + "step": 138752 + }, + { + "epoch": 0.02, + "learning_rate": 4.771984121732511e-05, + "loss": 4.0323, + "step": 139264 + }, + { + "epoch": 0.02, + "learning_rate": 4.771145526981459e-05, + "loss": 4.043, + "step": 139776 + }, + { + "epoch": 0.02, + "learning_rate": 4.77030857011078e-05, + "loss": 4.0338, + "step": 140288 + }, + { + "epoch": 0.02, + "learning_rate": 4.769469975359728e-05, + "loss": 4.0305, + "step": 140800 + }, + { + "epoch": 0.02, + "learning_rate": 4.768631380608676e-05, + "loss": 4.0214, + "step": 141312 + }, + { + "epoch": 0.02, + "learning_rate": 4.767792785857624e-05, + "loss": 4.0268, + "step": 141824 + }, + { + "epoch": 0.02, + "learning_rate": 4.766955828986945e-05, + "loss": 4.0191, + "step": 142336 + }, + { + "epoch": 0.02, + "learning_rate": 4.766117234235893e-05, + "loss": 4.042, + "step": 142848 + }, + { + "epoch": 0.02, + "learning_rate": 4.765278639484841e-05, + "loss": 4.0496, + "step": 143360 + }, + { + "epoch": 0.02, + "learning_rate": 4.764440044733789e-05, + "loss": 4.0332, + "step": 143872 + }, + { + "epoch": 0.02, + "learning_rate": 4.7636030878631096e-05, + "loss": 4.0169, + "step": 144384 + }, + { + "epoch": 0.02, + "learning_rate": 4.762764493112058e-05, + "loss": 4.0364, + "step": 144896 + }, + { + "epoch": 0.02, + "learning_rate": 4.761925898361006e-05, + "loss": 4.0267, + "step": 145408 + }, + { + "epoch": 0.02, + "learning_rate": 4.761087303609954e-05, + "loss": 4.0298, + "step": 145920 + }, + { + "epoch": 0.02, + "learning_rate": 4.760250346739275e-05, + "loss": 4.0253, + "step": 146432 + }, + { + "epoch": 0.02, + "learning_rate": 4.759411751988223e-05, + "loss": 4.0276, + "step": 146944 + }, + { + "epoch": 0.02, + "learning_rate": 4.758573157237171e-05, + "loss": 4.0225, + "step": 147456 + }, + { + "epoch": 0.02, + "learning_rate": 4.757734562486119e-05, + "loss": 4.0272, + "step": 147968 + }, + { + "epoch": 0.02, + "learning_rate": 4.75689760561544e-05, + "loss": 4.0232, + "step": 148480 + }, + { + "epoch": 0.02, + "learning_rate": 4.756059010864388e-05, + "loss": 4.0284, + "step": 148992 + }, + { + "epoch": 0.02, + "learning_rate": 4.755220416113336e-05, + "loss": 4.0222, + "step": 149504 + }, + { + "epoch": 0.02, + "learning_rate": 4.754381821362284e-05, + "loss": 4.0141, + "step": 150016 + }, + { + "epoch": 0.02, + "learning_rate": 4.753544864491605e-05, + "loss": 4.0302, + "step": 150528 + }, + { + "epoch": 0.02, + "learning_rate": 4.7527062697405536e-05, + "loss": 4.0231, + "step": 151040 + }, + { + "epoch": 0.02, + "learning_rate": 4.7518676749895016e-05, + "loss": 4.0147, + "step": 151552 + }, + { + "epoch": 0.02, + "learning_rate": 4.7510290802384496e-05, + "loss": 4.0301, + "step": 152064 + }, + { + "epoch": 0.02, + "learning_rate": 4.7501921233677705e-05, + "loss": 4.0118, + "step": 152576 + }, + { + "epoch": 0.03, + "eval_loss": 4.044399738311768, + "eval_runtime": 302.1723, + "eval_samples_per_second": 1262.826, + "eval_steps_per_second": 39.464, + "step": 152640 + }, + { + "epoch": 1.0, + "learning_rate": 4.7493535286167185e-05, + "loss": 4.003, + "step": 153088 + }, + { + "epoch": 1.0, + "learning_rate": 4.7485149338656665e-05, + "loss": 4.0051, + "step": 153600 + }, + { + "epoch": 1.0, + "learning_rate": 4.7476763391146145e-05, + "loss": 4.022, + "step": 154112 + }, + { + "epoch": 1.0, + "learning_rate": 4.7468393822439354e-05, + "loss": 4.0145, + "step": 154624 + }, + { + "epoch": 1.0, + "learning_rate": 4.7460007874928834e-05, + "loss": 4.0197, + "step": 155136 + }, + { + "epoch": 1.0, + "learning_rate": 4.7451621927418314e-05, + "loss": 4.001, + "step": 155648 + }, + { + "epoch": 1.0, + "learning_rate": 4.7443235979907794e-05, + "loss": 4.0149, + "step": 156160 + }, + { + "epoch": 1.0, + "learning_rate": 4.7434866411201e-05, + "loss": 3.9915, + "step": 156672 + }, + { + "epoch": 1.0, + "learning_rate": 4.742648046369049e-05, + "loss": 4.0149, + "step": 157184 + }, + { + "epoch": 1.0, + "learning_rate": 4.741809451617997e-05, + "loss": 3.9956, + "step": 157696 + }, + { + "epoch": 1.0, + "learning_rate": 4.740970856866945e-05, + "loss": 4.0134, + "step": 158208 + }, + { + "epoch": 1.0, + "learning_rate": 4.740133899996266e-05, + "loss": 4.0085, + "step": 158720 + }, + { + "epoch": 1.0, + "learning_rate": 4.739296943125587e-05, + "loss": 4.0023, + "step": 159232 + }, + { + "epoch": 1.0, + "learning_rate": 4.738458348374535e-05, + "loss": 3.9932, + "step": 159744 + }, + { + "epoch": 1.0, + "learning_rate": 4.737619753623483e-05, + "loss": 3.9905, + "step": 160256 + }, + { + "epoch": 1.0, + "learning_rate": 4.736781158872431e-05, + "loss": 3.9914, + "step": 160768 + }, + { + "epoch": 1.0, + "learning_rate": 4.735942564121379e-05, + "loss": 3.9955, + "step": 161280 + }, + { + "epoch": 1.0, + "learning_rate": 4.735103969370327e-05, + "loss": 3.9989, + "step": 161792 + }, + { + "epoch": 1.0, + "learning_rate": 4.734265374619275e-05, + "loss": 3.9951, + "step": 162304 + }, + { + "epoch": 1.0, + "learning_rate": 4.733426779868223e-05, + "loss": 4.011, + "step": 162816 + }, + { + "epoch": 1.0, + "learning_rate": 4.7325898229975444e-05, + "loss": 4.0051, + "step": 163328 + }, + { + "epoch": 1.0, + "learning_rate": 4.7317512282464924e-05, + "loss": 4.0008, + "step": 163840 + }, + { + "epoch": 1.0, + "learning_rate": 4.7309126334954404e-05, + "loss": 3.9946, + "step": 164352 + }, + { + "epoch": 1.0, + "learning_rate": 4.7300740387443884e-05, + "loss": 4.0035, + "step": 164864 + }, + { + "epoch": 1.0, + "learning_rate": 4.729237081873709e-05, + "loss": 3.9872, + "step": 165376 + }, + { + "epoch": 1.0, + "learning_rate": 4.728398487122657e-05, + "loss": 3.9961, + "step": 165888 + }, + { + "epoch": 1.0, + "learning_rate": 4.727559892371605e-05, + "loss": 3.9947, + "step": 166400 + }, + { + "epoch": 1.0, + "learning_rate": 4.726722935500926e-05, + "loss": 3.9909, + "step": 166912 + }, + { + "epoch": 1.0, + "learning_rate": 4.725884340749874e-05, + "loss": 3.9795, + "step": 167424 + }, + { + "epoch": 1.01, + "learning_rate": 4.725045745998822e-05, + "loss": 3.9834, + "step": 167936 + }, + { + "epoch": 1.01, + "learning_rate": 4.72420715124777e-05, + "loss": 3.9862, + "step": 168448 + }, + { + "epoch": 1.01, + "learning_rate": 4.723370194377091e-05, + "loss": 3.9909, + "step": 168960 + }, + { + "epoch": 1.01, + "learning_rate": 4.72253159962604e-05, + "loss": 3.994, + "step": 169472 + }, + { + "epoch": 1.01, + "learning_rate": 4.721693004874988e-05, + "loss": 3.9866, + "step": 169984 + }, + { + "epoch": 1.01, + "learning_rate": 4.720854410123936e-05, + "loss": 3.9871, + "step": 170496 + }, + { + "epoch": 1.01, + "learning_rate": 4.720015815372884e-05, + "loss": 3.9854, + "step": 171008 + }, + { + "epoch": 1.01, + "learning_rate": 4.719177220621832e-05, + "loss": 3.9711, + "step": 171520 + }, + { + "epoch": 1.01, + "learning_rate": 4.71833862587078e-05, + "loss": 3.9805, + "step": 172032 + }, + { + "epoch": 1.01, + "learning_rate": 4.7175016690001006e-05, + "loss": 3.9702, + "step": 172544 + }, + { + "epoch": 1.01, + "learning_rate": 4.7166630742490486e-05, + "loss": 3.9703, + "step": 173056 + }, + { + "epoch": 1.01, + "learning_rate": 4.7158244794979966e-05, + "loss": 3.976, + "step": 173568 + }, + { + "epoch": 1.01, + "learning_rate": 4.7149858847469446e-05, + "loss": 3.9855, + "step": 174080 + }, + { + "epoch": 1.01, + "learning_rate": 4.7141489278762655e-05, + "loss": 3.9736, + "step": 174592 + }, + { + "epoch": 1.01, + "learning_rate": 4.7133103331252135e-05, + "loss": 3.9691, + "step": 175104 + }, + { + "epoch": 1.01, + "learning_rate": 4.7124717383741615e-05, + "loss": 3.9826, + "step": 175616 + }, + { + "epoch": 1.01, + "learning_rate": 4.7116331436231095e-05, + "loss": 3.9718, + "step": 176128 + }, + { + "epoch": 1.01, + "learning_rate": 4.710796186752431e-05, + "loss": 3.9828, + "step": 176640 + }, + { + "epoch": 1.01, + "learning_rate": 4.709957592001379e-05, + "loss": 3.9664, + "step": 177152 + }, + { + "epoch": 1.01, + "learning_rate": 4.709118997250327e-05, + "loss": 3.9637, + "step": 177664 + }, + { + "epoch": 1.01, + "learning_rate": 4.708282040379648e-05, + "loss": 3.9772, + "step": 178176 + }, + { + "epoch": 1.01, + "learning_rate": 4.707443445628596e-05, + "loss": 3.9674, + "step": 178688 + }, + { + "epoch": 1.01, + "learning_rate": 4.706604850877544e-05, + "loss": 3.9725, + "step": 179200 + }, + { + "epoch": 1.01, + "learning_rate": 4.705766256126492e-05, + "loss": 3.9607, + "step": 179712 + }, + { + "epoch": 1.01, + "learning_rate": 4.704927661375439e-05, + "loss": 3.9682, + "step": 180224 + }, + { + "epoch": 1.01, + "learning_rate": 4.704090704504761e-05, + "loss": 3.9538, + "step": 180736 + }, + { + "epoch": 1.01, + "learning_rate": 4.703252109753709e-05, + "loss": 3.9687, + "step": 181248 + }, + { + "epoch": 1.01, + "learning_rate": 4.702413515002657e-05, + "loss": 3.9623, + "step": 181760 + }, + { + "epoch": 1.01, + "learning_rate": 4.701574920251605e-05, + "loss": 3.9639, + "step": 182272 + }, + { + "epoch": 1.01, + "learning_rate": 4.700736325500553e-05, + "loss": 3.9711, + "step": 182784 + }, + { + "epoch": 1.01, + "learning_rate": 4.699897730749501e-05, + "loss": 3.9553, + "step": 183296 + }, + { + "epoch": 1.01, + "learning_rate": 4.699059135998449e-05, + "loss": 3.9521, + "step": 183808 + }, + { + "epoch": 1.01, + "learning_rate": 4.698220541247397e-05, + "loss": 3.9717, + "step": 184320 + }, + { + "epoch": 1.01, + "learning_rate": 4.697383584376718e-05, + "loss": 3.9432, + "step": 184832 + }, + { + "epoch": 1.01, + "learning_rate": 4.696544989625666e-05, + "loss": 3.9437, + "step": 185344 + }, + { + "epoch": 1.01, + "learning_rate": 4.695706394874614e-05, + "loss": 3.9592, + "step": 185856 + }, + { + "epoch": 1.01, + "learning_rate": 4.694867800123562e-05, + "loss": 3.9651, + "step": 186368 + }, + { + "epoch": 1.01, + "learning_rate": 4.694030843252883e-05, + "loss": 3.9553, + "step": 186880 + }, + { + "epoch": 1.01, + "learning_rate": 4.6931922485018307e-05, + "loss": 3.9435, + "step": 187392 + }, + { + "epoch": 1.01, + "learning_rate": 4.6923536537507787e-05, + "loss": 3.9471, + "step": 187904 + }, + { + "epoch": 1.01, + "learning_rate": 4.6915166968801e-05, + "loss": 3.9482, + "step": 188416 + }, + { + "epoch": 1.01, + "learning_rate": 4.690678102129048e-05, + "loss": 3.9621, + "step": 188928 + }, + { + "epoch": 1.01, + "learning_rate": 4.689839507377996e-05, + "loss": 3.9537, + "step": 189440 + }, + { + "epoch": 1.01, + "learning_rate": 4.689000912626944e-05, + "loss": 3.957, + "step": 189952 + }, + { + "epoch": 1.01, + "learning_rate": 4.688163955756265e-05, + "loss": 3.9571, + "step": 190464 + }, + { + "epoch": 1.01, + "learning_rate": 4.687325361005213e-05, + "loss": 3.9608, + "step": 190976 + }, + { + "epoch": 1.01, + "learning_rate": 4.686488404134534e-05, + "loss": 3.9424, + "step": 191488 + }, + { + "epoch": 1.01, + "learning_rate": 4.685649809383482e-05, + "loss": 3.9443, + "step": 192000 + }, + { + "epoch": 1.01, + "learning_rate": 4.68481121463243e-05, + "loss": 3.9544, + "step": 192512 + }, + { + "epoch": 1.01, + "learning_rate": 4.683972619881378e-05, + "loss": 3.9399, + "step": 193024 + }, + { + "epoch": 1.01, + "learning_rate": 4.683134025130326e-05, + "loss": 3.95, + "step": 193536 + }, + { + "epoch": 1.01, + "learning_rate": 4.682295430379274e-05, + "loss": 3.9412, + "step": 194048 + }, + { + "epoch": 1.01, + "learning_rate": 4.681456835628222e-05, + "loss": 3.9586, + "step": 194560 + }, + { + "epoch": 1.01, + "learning_rate": 4.680618240877171e-05, + "loss": 3.9457, + "step": 195072 + }, + { + "epoch": 1.01, + "learning_rate": 4.6797812840064916e-05, + "loss": 3.9344, + "step": 195584 + }, + { + "epoch": 1.01, + "learning_rate": 4.6789426892554396e-05, + "loss": 3.9392, + "step": 196096 + }, + { + "epoch": 1.01, + "learning_rate": 4.6781040945043876e-05, + "loss": 3.9451, + "step": 196608 + }, + { + "epoch": 1.01, + "learning_rate": 4.6772654997533356e-05, + "loss": 3.9552, + "step": 197120 + }, + { + "epoch": 1.01, + "learning_rate": 4.6764285428826565e-05, + "loss": 3.9361, + "step": 197632 + }, + { + "epoch": 1.01, + "learning_rate": 4.6755899481316045e-05, + "loss": 3.94, + "step": 198144 + }, + { + "epoch": 1.02, + "learning_rate": 4.6747513533805525e-05, + "loss": 3.9379, + "step": 198656 + }, + { + "epoch": 1.02, + "learning_rate": 4.6739127586295005e-05, + "loss": 3.9457, + "step": 199168 + }, + { + "epoch": 1.02, + "learning_rate": 4.6730758017588214e-05, + "loss": 3.9322, + "step": 199680 + }, + { + "epoch": 1.02, + "learning_rate": 4.6722372070077694e-05, + "loss": 3.9339, + "step": 200192 + }, + { + "epoch": 1.02, + "learning_rate": 4.6713986122567174e-05, + "loss": 3.9446, + "step": 200704 + }, + { + "epoch": 1.02, + "learning_rate": 4.670561655386039e-05, + "loss": 3.9474, + "step": 201216 + }, + { + "epoch": 1.02, + "learning_rate": 4.669723060634987e-05, + "loss": 3.9439, + "step": 201728 + }, + { + "epoch": 1.02, + "learning_rate": 4.668884465883935e-05, + "loss": 3.9279, + "step": 202240 + }, + { + "epoch": 1.02, + "learning_rate": 4.668045871132883e-05, + "loss": 3.9318, + "step": 202752 + }, + { + "epoch": 1.02, + "learning_rate": 4.667207276381831e-05, + "loss": 3.9324, + "step": 203264 + }, + { + "epoch": 1.02, + "learning_rate": 4.666368681630779e-05, + "loss": 3.938, + "step": 203776 + }, + { + "epoch": 1.02, + "learning_rate": 4.665530086879727e-05, + "loss": 3.938, + "step": 204288 + }, + { + "epoch": 1.02, + "learning_rate": 4.664691492128675e-05, + "loss": 3.9294, + "step": 204800 + }, + { + "epoch": 1.02, + "learning_rate": 4.663854535257996e-05, + "loss": 3.9246, + "step": 205312 + }, + { + "epoch": 1.02, + "learning_rate": 4.663015940506944e-05, + "loss": 3.9388, + "step": 205824 + }, + { + "epoch": 1.02, + "learning_rate": 4.662177345755892e-05, + "loss": 3.9108, + "step": 206336 + }, + { + "epoch": 1.02, + "learning_rate": 4.66133875100484e-05, + "loss": 3.9271, + "step": 206848 + }, + { + "epoch": 1.02, + "learning_rate": 4.6605017941341614e-05, + "loss": 3.9219, + "step": 207360 + }, + { + "epoch": 1.02, + "learning_rate": 4.6596631993831094e-05, + "loss": 3.9357, + "step": 207872 + }, + { + "epoch": 1.02, + "learning_rate": 4.65882624251243e-05, + "loss": 3.9246, + "step": 208384 + }, + { + "epoch": 1.02, + "learning_rate": 4.657987647761378e-05, + "loss": 3.929, + "step": 208896 + }, + { + "epoch": 1.02, + "learning_rate": 4.657149053010326e-05, + "loss": 3.9196, + "step": 209408 + }, + { + "epoch": 1.02, + "learning_rate": 4.656310458259274e-05, + "loss": 3.9239, + "step": 209920 + }, + { + "epoch": 1.02, + "learning_rate": 4.655471863508222e-05, + "loss": 3.9323, + "step": 210432 + }, + { + "epoch": 1.02, + "learning_rate": 4.65463326875717e-05, + "loss": 3.9226, + "step": 210944 + }, + { + "epoch": 1.02, + "learning_rate": 4.6537946740061176e-05, + "loss": 3.9322, + "step": 211456 + }, + { + "epoch": 1.02, + "learning_rate": 4.6529560792550656e-05, + "loss": 3.9343, + "step": 211968 + }, + { + "epoch": 1.02, + "learning_rate": 4.65212076026476e-05, + "loss": 3.9302, + "step": 212480 + }, + { + "epoch": 1.02, + "learning_rate": 4.651282165513708e-05, + "loss": 3.9233, + "step": 212992 + }, + { + "epoch": 1.02, + "learning_rate": 4.650443570762657e-05, + "loss": 3.9192, + "step": 213504 + }, + { + "epoch": 1.02, + "learning_rate": 4.649604976011605e-05, + "loss": 3.9293, + "step": 214016 + }, + { + "epoch": 1.02, + "learning_rate": 4.648766381260553e-05, + "loss": 3.9148, + "step": 214528 + }, + { + "epoch": 1.02, + "learning_rate": 4.6479277865095e-05, + "loss": 3.9291, + "step": 215040 + }, + { + "epoch": 1.02, + "learning_rate": 4.647089191758448e-05, + "loss": 3.9149, + "step": 215552 + }, + { + "epoch": 1.02, + "learning_rate": 4.646250597007396e-05, + "loss": 3.9253, + "step": 216064 + }, + { + "epoch": 1.02, + "learning_rate": 4.645413640136718e-05, + "loss": 3.9191, + "step": 216576 + }, + { + "epoch": 1.02, + "learning_rate": 4.644575045385665e-05, + "loss": 3.9196, + "step": 217088 + }, + { + "epoch": 1.02, + "learning_rate": 4.643736450634613e-05, + "loss": 3.9048, + "step": 217600 + }, + { + "epoch": 1.02, + "learning_rate": 4.6428994937639346e-05, + "loss": 3.9153, + "step": 218112 + }, + { + "epoch": 1.02, + "learning_rate": 4.642060899012882e-05, + "loss": 3.908, + "step": 218624 + }, + { + "epoch": 1.02, + "learning_rate": 4.6412223042618306e-05, + "loss": 3.9208, + "step": 219136 + }, + { + "epoch": 1.02, + "learning_rate": 4.6403837095107786e-05, + "loss": 3.9345, + "step": 219648 + }, + { + "epoch": 1.02, + "learning_rate": 4.6395451147597266e-05, + "loss": 3.926, + "step": 220160 + }, + { + "epoch": 1.02, + "learning_rate": 4.6387065200086746e-05, + "loss": 3.8975, + "step": 220672 + }, + { + "epoch": 1.02, + "learning_rate": 4.6378679252576226e-05, + "loss": 3.9278, + "step": 221184 + }, + { + "epoch": 1.02, + "learning_rate": 4.6370293305065705e-05, + "loss": 3.916, + "step": 221696 + }, + { + "epoch": 1.02, + "learning_rate": 4.6361923736358915e-05, + "loss": 3.9178, + "step": 222208 + }, + { + "epoch": 1.02, + "learning_rate": 4.6353537788848395e-05, + "loss": 3.9062, + "step": 222720 + }, + { + "epoch": 1.02, + "learning_rate": 4.6345151841337874e-05, + "loss": 3.9192, + "step": 223232 + }, + { + "epoch": 1.02, + "learning_rate": 4.6336765893827354e-05, + "loss": 3.9109, + "step": 223744 + }, + { + "epoch": 1.02, + "learning_rate": 4.6328396325120564e-05, + "loss": 3.9156, + "step": 224256 + }, + { + "epoch": 1.02, + "learning_rate": 4.6320010377610043e-05, + "loss": 3.9144, + "step": 224768 + }, + { + "epoch": 1.02, + "learning_rate": 4.6311624430099523e-05, + "loss": 3.9175, + "step": 225280 + }, + { + "epoch": 1.02, + "learning_rate": 4.6303238482589003e-05, + "loss": 3.9137, + "step": 225792 + }, + { + "epoch": 1.02, + "learning_rate": 4.629486891388222e-05, + "loss": 3.9084, + "step": 226304 + }, + { + "epoch": 1.02, + "learning_rate": 4.62864829663717e-05, + "loss": 3.9175, + "step": 226816 + }, + { + "epoch": 1.02, + "learning_rate": 4.627809701886118e-05, + "loss": 3.9149, + "step": 227328 + }, + { + "epoch": 1.02, + "learning_rate": 4.626971107135066e-05, + "loss": 3.907, + "step": 227840 + }, + { + "epoch": 1.02, + "learning_rate": 4.626134150264387e-05, + "loss": 3.9194, + "step": 228352 + }, + { + "epoch": 1.02, + "learning_rate": 4.625295555513335e-05, + "loss": 3.905, + "step": 228864 + }, + { + "epoch": 1.03, + "eval_loss": 3.9699602127075195, + "eval_runtime": 302.1878, + "eval_samples_per_second": 1262.761, + "eval_steps_per_second": 39.462, + "step": 228960 + }, + { + "epoch": 0.0, + "learning_rate": 4.624456960762283e-05, + "loss": 3.8928, + "step": 229376 + }, + { + "epoch": 0.0, + "learning_rate": 4.623618366011231e-05, + "loss": 3.8991, + "step": 229888 + }, + { + "epoch": 0.0, + "learning_rate": 4.622779771260179e-05, + "loss": 3.914, + "step": 230400 + }, + { + "epoch": 0.0, + "learning_rate": 4.621941176509127e-05, + "loss": 3.9062, + "step": 230912 + }, + { + "epoch": 0.0, + "learning_rate": 4.621102581758075e-05, + "loss": 3.9192, + "step": 231424 + }, + { + "epoch": 0.0, + "learning_rate": 4.620263987007023e-05, + "loss": 3.8938, + "step": 231936 + }, + { + "epoch": 0.0, + "learning_rate": 4.619425392255971e-05, + "loss": 3.9125, + "step": 232448 + }, + { + "epoch": 0.0, + "learning_rate": 4.618586797504919e-05, + "loss": 3.8829, + "step": 232960 + }, + { + "epoch": 0.0, + "learning_rate": 4.617748202753867e-05, + "loss": 3.9144, + "step": 233472 + }, + { + "epoch": 0.0, + "learning_rate": 4.616909608002815e-05, + "loss": 3.896, + "step": 233984 + }, + { + "epoch": 0.0, + "learning_rate": 4.616071013251763e-05, + "loss": 3.9059, + "step": 234496 + }, + { + "epoch": 0.0, + "learning_rate": 4.615234056381084e-05, + "loss": 3.9047, + "step": 235008 + }, + { + "epoch": 0.0, + "learning_rate": 4.614397099510405e-05, + "loss": 3.8938, + "step": 235520 + }, + { + "epoch": 0.0, + "learning_rate": 4.613558504759353e-05, + "loss": 3.895, + "step": 236032 + }, + { + "epoch": 0.0, + "learning_rate": 4.6127199100083006e-05, + "loss": 3.8889, + "step": 236544 + }, + { + "epoch": 0.0, + "learning_rate": 4.6118813152572486e-05, + "loss": 3.8859, + "step": 237056 + }, + { + "epoch": 0.0, + "learning_rate": 4.6110427205061966e-05, + "loss": 3.8987, + "step": 237568 + }, + { + "epoch": 0.0, + "learning_rate": 4.6102041257551446e-05, + "loss": 3.8959, + "step": 238080 + }, + { + "epoch": 0.0, + "learning_rate": 4.6093655310040926e-05, + "loss": 3.8952, + "step": 238592 + }, + { + "epoch": 0.0, + "learning_rate": 4.6085269362530406e-05, + "loss": 3.909, + "step": 239104 + }, + { + "epoch": 0.0, + "learning_rate": 4.607689979382362e-05, + "loss": 3.9095, + "step": 239616 + }, + { + "epoch": 0.0, + "learning_rate": 4.60685138463131e-05, + "loss": 3.9002, + "step": 240128 + }, + { + "epoch": 0.0, + "learning_rate": 4.606012789880258e-05, + "loss": 3.8948, + "step": 240640 + }, + { + "epoch": 0.0, + "learning_rate": 4.605175833009579e-05, + "loss": 3.9029, + "step": 241152 + }, + { + "epoch": 0.0, + "learning_rate": 4.604337238258527e-05, + "loss": 3.8879, + "step": 241664 + }, + { + "epoch": 0.0, + "learning_rate": 4.603498643507475e-05, + "loss": 3.9013, + "step": 242176 + }, + { + "epoch": 0.0, + "learning_rate": 4.602660048756423e-05, + "loss": 3.8963, + "step": 242688 + }, + { + "epoch": 0.0, + "learning_rate": 4.601821454005371e-05, + "loss": 3.8889, + "step": 243200 + }, + { + "epoch": 0.0, + "learning_rate": 4.600982859254319e-05, + "loss": 3.883, + "step": 243712 + }, + { + "epoch": 0.01, + "learning_rate": 4.600144264503267e-05, + "loss": 3.8886, + "step": 244224 + }, + { + "epoch": 0.01, + "learning_rate": 4.599307307632588e-05, + "loss": 3.8879, + "step": 244736 + }, + { + "epoch": 0.01, + "learning_rate": 4.5984703507619095e-05, + "loss": 3.8957, + "step": 245248 + }, + { + "epoch": 0.01, + "learning_rate": 4.5976317560108575e-05, + "loss": 3.8975, + "step": 245760 + }, + { + "epoch": 0.01, + "learning_rate": 4.5967931612598055e-05, + "loss": 3.8908, + "step": 246272 + }, + { + "epoch": 0.01, + "learning_rate": 4.5959545665087535e-05, + "loss": 3.8931, + "step": 246784 + }, + { + "epoch": 0.01, + "learning_rate": 4.5951159717577015e-05, + "loss": 3.8903, + "step": 247296 + }, + { + "epoch": 0.01, + "learning_rate": 4.5942790148870224e-05, + "loss": 3.8761, + "step": 247808 + }, + { + "epoch": 0.01, + "learning_rate": 4.5934404201359704e-05, + "loss": 3.8841, + "step": 248320 + }, + { + "epoch": 0.01, + "learning_rate": 4.5926018253849184e-05, + "loss": 3.8758, + "step": 248832 + }, + { + "epoch": 0.01, + "learning_rate": 4.5917632306338664e-05, + "loss": 3.8799, + "step": 249344 + }, + { + "epoch": 0.01, + "learning_rate": 4.5909246358828144e-05, + "loss": 3.8819, + "step": 249856 + }, + { + "epoch": 0.01, + "learning_rate": 4.5900860411317624e-05, + "loss": 3.888, + "step": 250368 + }, + { + "epoch": 0.01, + "learning_rate": 4.5892474463807104e-05, + "loss": 3.8862, + "step": 250880 + }, + { + "epoch": 0.01, + "learning_rate": 4.5884088516296584e-05, + "loss": 3.8721, + "step": 251392 + }, + { + "epoch": 0.01, + "learning_rate": 4.58757189475898e-05, + "loss": 3.8887, + "step": 251904 + }, + { + "epoch": 0.01, + "learning_rate": 4.586733300007928e-05, + "loss": 3.8868, + "step": 252416 + }, + { + "epoch": 0.01, + "learning_rate": 4.585894705256876e-05, + "loss": 3.8857, + "step": 252928 + }, + { + "epoch": 0.01, + "learning_rate": 4.585057748386197e-05, + "loss": 3.8782, + "step": 253440 + }, + { + "epoch": 0.01, + "learning_rate": 4.584219153635145e-05, + "loss": 3.8696, + "step": 253952 + }, + { + "epoch": 0.01, + "learning_rate": 4.583382196764466e-05, + "loss": 3.8868, + "step": 254464 + }, + { + "epoch": 0.01, + "learning_rate": 4.582543602013414e-05, + "loss": 3.8738, + "step": 254976 + }, + { + "epoch": 0.01, + "learning_rate": 4.581705007262362e-05, + "loss": 3.8798, + "step": 255488 + }, + { + "epoch": 0.01, + "learning_rate": 4.58086641251131e-05, + "loss": 3.8713, + "step": 256000 + }, + { + "epoch": 0.01, + "learning_rate": 4.580027817760258e-05, + "loss": 3.8739, + "step": 256512 + }, + { + "epoch": 0.01, + "learning_rate": 4.579190860889579e-05, + "loss": 3.8664, + "step": 257024 + }, + { + "epoch": 0.01, + "learning_rate": 4.5783522661385267e-05, + "loss": 3.8759, + "step": 257536 + }, + { + "epoch": 0.01, + "learning_rate": 4.577513671387475e-05, + "loss": 3.8757, + "step": 258048 + }, + { + "epoch": 0.01, + "learning_rate": 4.576675076636423e-05, + "loss": 3.8763, + "step": 258560 + }, + { + "epoch": 0.01, + "learning_rate": 4.575836481885371e-05, + "loss": 3.8776, + "step": 259072 + }, + { + "epoch": 0.01, + "learning_rate": 4.574997887134319e-05, + "loss": 3.8664, + "step": 259584 + }, + { + "epoch": 0.01, + "learning_rate": 4.5741592923832666e-05, + "loss": 3.8664, + "step": 260096 + }, + { + "epoch": 0.01, + "learning_rate": 4.5733206976322146e-05, + "loss": 3.8857, + "step": 260608 + }, + { + "epoch": 0.01, + "learning_rate": 4.572485378641909e-05, + "loss": 3.8567, + "step": 261120 + }, + { + "epoch": 0.01, + "learning_rate": 4.571646783890857e-05, + "loss": 3.8553, + "step": 261632 + }, + { + "epoch": 0.01, + "learning_rate": 4.570808189139805e-05, + "loss": 3.8673, + "step": 262144 + }, + { + "epoch": 0.01, + "learning_rate": 4.569969594388753e-05, + "loss": 3.877, + "step": 262656 + }, + { + "epoch": 0.01, + "learning_rate": 4.569130999637701e-05, + "loss": 3.8654, + "step": 263168 + }, + { + "epoch": 0.01, + "learning_rate": 4.568292404886649e-05, + "loss": 3.8615, + "step": 263680 + }, + { + "epoch": 0.01, + "learning_rate": 4.567453810135597e-05, + "loss": 3.8559, + "step": 264192 + }, + { + "epoch": 0.01, + "learning_rate": 4.566615215384545e-05, + "loss": 3.862, + "step": 264704 + }, + { + "epoch": 0.01, + "learning_rate": 4.565778258513867e-05, + "loss": 3.8759, + "step": 265216 + }, + { + "epoch": 0.01, + "learning_rate": 4.5649413016431876e-05, + "loss": 3.8657, + "step": 265728 + }, + { + "epoch": 0.01, + "learning_rate": 4.5641027068921356e-05, + "loss": 3.8662, + "step": 266240 + }, + { + "epoch": 0.01, + "learning_rate": 4.5632641121410836e-05, + "loss": 3.8762, + "step": 266752 + }, + { + "epoch": 0.01, + "learning_rate": 4.5624255173900316e-05, + "loss": 3.8752, + "step": 267264 + }, + { + "epoch": 0.01, + "learning_rate": 4.561586922638979e-05, + "loss": 3.8578, + "step": 267776 + }, + { + "epoch": 0.01, + "learning_rate": 4.560748327887927e-05, + "loss": 3.8625, + "step": 268288 + }, + { + "epoch": 0.01, + "learning_rate": 4.559909733136875e-05, + "loss": 3.8711, + "step": 268800 + }, + { + "epoch": 0.01, + "learning_rate": 4.559071138385823e-05, + "loss": 3.8511, + "step": 269312 + }, + { + "epoch": 0.01, + "learning_rate": 4.5582358193955174e-05, + "loss": 3.8679, + "step": 269824 + }, + { + "epoch": 0.01, + "learning_rate": 4.5573972246444654e-05, + "loss": 3.8557, + "step": 270336 + }, + { + "epoch": 0.01, + "learning_rate": 4.556558629893414e-05, + "loss": 3.8773, + "step": 270848 + }, + { + "epoch": 0.01, + "learning_rate": 4.5557200351423614e-05, + "loss": 3.8612, + "step": 271360 + }, + { + "epoch": 0.01, + "learning_rate": 4.5548814403913094e-05, + "loss": 3.8528, + "step": 271872 + }, + { + "epoch": 0.01, + "learning_rate": 4.5540428456402574e-05, + "loss": 3.8508, + "step": 272384 + }, + { + "epoch": 0.01, + "learning_rate": 4.553205888769579e-05, + "loss": 3.8631, + "step": 272896 + }, + { + "epoch": 0.01, + "learning_rate": 4.552367294018526e-05, + "loss": 3.874, + "step": 273408 + }, + { + "epoch": 0.01, + "learning_rate": 4.551528699267474e-05, + "loss": 3.857, + "step": 273920 + }, + { + "epoch": 0.01, + "learning_rate": 4.550690104516422e-05, + "loss": 3.8545, + "step": 274432 + }, + { + "epoch": 0.02, + "learning_rate": 4.54985150976537e-05, + "loss": 3.8541, + "step": 274944 + }, + { + "epoch": 0.02, + "learning_rate": 4.549012915014318e-05, + "loss": 3.8651, + "step": 275456 + }, + { + "epoch": 0.02, + "learning_rate": 4.548174320263266e-05, + "loss": 3.8492, + "step": 275968 + }, + { + "epoch": 0.02, + "learning_rate": 4.547335725512214e-05, + "loss": 3.8543, + "step": 276480 + }, + { + "epoch": 0.02, + "learning_rate": 4.546500406521909e-05, + "loss": 3.8625, + "step": 276992 + }, + { + "epoch": 0.02, + "learning_rate": 4.54566344965123e-05, + "loss": 3.8668, + "step": 277504 + }, + { + "epoch": 0.02, + "learning_rate": 4.544824854900178e-05, + "loss": 3.8615, + "step": 278016 + }, + { + "epoch": 0.02, + "learning_rate": 4.543986260149126e-05, + "loss": 3.8442, + "step": 278528 + }, + { + "epoch": 0.02, + "learning_rate": 4.5431476653980736e-05, + "loss": 3.8554, + "step": 279040 + }, + { + "epoch": 0.02, + "learning_rate": 4.5423090706470216e-05, + "loss": 3.8486, + "step": 279552 + }, + { + "epoch": 0.02, + "learning_rate": 4.5414704758959696e-05, + "loss": 3.8578, + "step": 280064 + }, + { + "epoch": 0.02, + "learning_rate": 4.5406318811449176e-05, + "loss": 3.8592, + "step": 280576 + }, + { + "epoch": 0.02, + "learning_rate": 4.5397932863938656e-05, + "loss": 3.847, + "step": 281088 + }, + { + "epoch": 0.02, + "learning_rate": 4.5389546916428136e-05, + "loss": 3.8479, + "step": 281600 + }, + { + "epoch": 0.02, + "learning_rate": 4.5381160968917616e-05, + "loss": 3.856, + "step": 282112 + }, + { + "epoch": 0.02, + "learning_rate": 4.5372775021407096e-05, + "loss": 3.8341, + "step": 282624 + }, + { + "epoch": 0.02, + "learning_rate": 4.536440545270031e-05, + "loss": 3.8505, + "step": 283136 + }, + { + "epoch": 0.02, + "learning_rate": 4.535601950518979e-05, + "loss": 3.8396, + "step": 283648 + }, + { + "epoch": 0.02, + "learning_rate": 4.534763355767927e-05, + "loss": 3.8578, + "step": 284160 + }, + { + "epoch": 0.02, + "learning_rate": 4.533924761016875e-05, + "loss": 3.8473, + "step": 284672 + }, + { + "epoch": 0.02, + "learning_rate": 4.533087804146196e-05, + "loss": 3.8477, + "step": 285184 + }, + { + "epoch": 0.02, + "learning_rate": 4.532249209395144e-05, + "loss": 3.8425, + "step": 285696 + }, + { + "epoch": 0.02, + "learning_rate": 4.531410614644092e-05, + "loss": 3.8507, + "step": 286208 + }, + { + "epoch": 0.02, + "learning_rate": 4.53057201989304e-05, + "loss": 3.8543, + "step": 286720 + }, + { + "epoch": 0.02, + "learning_rate": 4.529733425141988e-05, + "loss": 3.8437, + "step": 287232 + }, + { + "epoch": 0.02, + "learning_rate": 4.528894830390936e-05, + "loss": 3.8525, + "step": 287744 + }, + { + "epoch": 0.02, + "learning_rate": 4.528057873520257e-05, + "loss": 3.857, + "step": 288256 + }, + { + "epoch": 0.02, + "learning_rate": 4.527219278769205e-05, + "loss": 3.8492, + "step": 288768 + }, + { + "epoch": 0.02, + "learning_rate": 4.526380684018153e-05, + "loss": 3.8529, + "step": 289280 + }, + { + "epoch": 0.02, + "learning_rate": 4.5255420892671017e-05, + "loss": 3.8377, + "step": 289792 + }, + { + "epoch": 0.02, + "learning_rate": 4.5247051323964226e-05, + "loss": 3.8549, + "step": 290304 + }, + { + "epoch": 0.02, + "learning_rate": 4.5238665376453706e-05, + "loss": 3.844, + "step": 290816 + }, + { + "epoch": 0.02, + "learning_rate": 4.5230279428943186e-05, + "loss": 3.8492, + "step": 291328 + }, + { + "epoch": 0.02, + "learning_rate": 4.5221893481432665e-05, + "loss": 3.8393, + "step": 291840 + }, + { + "epoch": 0.02, + "learning_rate": 4.5213523912725875e-05, + "loss": 3.8481, + "step": 292352 + }, + { + "epoch": 0.02, + "learning_rate": 4.5205137965215355e-05, + "loss": 3.8424, + "step": 292864 + }, + { + "epoch": 0.02, + "learning_rate": 4.5196752017704834e-05, + "loss": 3.8409, + "step": 293376 + }, + { + "epoch": 0.02, + "learning_rate": 4.5188366070194314e-05, + "loss": 3.8319, + "step": 293888 + }, + { + "epoch": 0.02, + "learning_rate": 4.5179996501487524e-05, + "loss": 3.8358, + "step": 294400 + }, + { + "epoch": 0.02, + "learning_rate": 4.5171610553977003e-05, + "loss": 3.8387, + "step": 294912 + }, + { + "epoch": 0.02, + "learning_rate": 4.5163224606466483e-05, + "loss": 3.8438, + "step": 295424 + }, + { + "epoch": 0.02, + "learning_rate": 4.515483865895597e-05, + "loss": 3.8574, + "step": 295936 + }, + { + "epoch": 0.02, + "learning_rate": 4.514645271144545e-05, + "loss": 3.8515, + "step": 296448 + }, + { + "epoch": 0.02, + "learning_rate": 4.513806676393492e-05, + "loss": 3.8246, + "step": 296960 + }, + { + "epoch": 0.02, + "learning_rate": 4.51296808164244e-05, + "loss": 3.854, + "step": 297472 + }, + { + "epoch": 0.02, + "learning_rate": 4.512129486891388e-05, + "loss": 3.8406, + "step": 297984 + }, + { + "epoch": 0.02, + "learning_rate": 4.51129253002071e-05, + "loss": 3.8421, + "step": 298496 + }, + { + "epoch": 0.02, + "learning_rate": 4.510453935269657e-05, + "loss": 3.8337, + "step": 299008 + }, + { + "epoch": 0.02, + "learning_rate": 4.509615340518605e-05, + "loss": 3.8452, + "step": 299520 + }, + { + "epoch": 0.02, + "learning_rate": 4.508778383647927e-05, + "loss": 3.8362, + "step": 300032 + }, + { + "epoch": 0.02, + "learning_rate": 4.507939788896874e-05, + "loss": 3.8481, + "step": 300544 + }, + { + "epoch": 0.02, + "learning_rate": 4.507101194145822e-05, + "loss": 3.8395, + "step": 301056 + }, + { + "epoch": 0.02, + "learning_rate": 4.506262599394771e-05, + "loss": 3.8411, + "step": 301568 + }, + { + "epoch": 0.02, + "learning_rate": 4.5054256425240924e-05, + "loss": 3.845, + "step": 302080 + }, + { + "epoch": 0.02, + "learning_rate": 4.50458704777304e-05, + "loss": 3.8337, + "step": 302592 + }, + { + "epoch": 0.02, + "learning_rate": 4.503748453021988e-05, + "loss": 3.8423, + "step": 303104 + }, + { + "epoch": 0.02, + "learning_rate": 4.502909858270936e-05, + "loss": 3.8473, + "step": 303616 + }, + { + "epoch": 0.02, + "learning_rate": 4.502071263519884e-05, + "loss": 3.8336, + "step": 304128 + }, + { + "epoch": 0.02, + "learning_rate": 4.501232668768832e-05, + "loss": 3.8419, + "step": 304640 + }, + { + "epoch": 0.02, + "learning_rate": 4.5003957118981526e-05, + "loss": 3.8377, + "step": 305152 + }, + { + "epoch": 0.03, + "eval_loss": 3.9284117221832275, + "eval_runtime": 330.261, + "eval_samples_per_second": 1155.422, + "eval_steps_per_second": 36.108, + "step": 305280 + }, + { + "epoch": 1.0, + "learning_rate": 4.4995571171471006e-05, + "loss": 3.8281, + "step": 305664 + }, + { + "epoch": 1.0, + "learning_rate": 4.4987185223960486e-05, + "loss": 3.8272, + "step": 306176 + }, + { + "epoch": 1.0, + "learning_rate": 4.4978799276449966e-05, + "loss": 3.8388, + "step": 306688 + }, + { + "epoch": 1.0, + "learning_rate": 4.4970413328939446e-05, + "loss": 3.8385, + "step": 307200 + }, + { + "epoch": 1.0, + "learning_rate": 4.496204376023266e-05, + "loss": 3.8515, + "step": 307712 + }, + { + "epoch": 1.0, + "learning_rate": 4.495365781272214e-05, + "loss": 3.8208, + "step": 308224 + }, + { + "epoch": 1.0, + "learning_rate": 4.494527186521162e-05, + "loss": 3.8376, + "step": 308736 + }, + { + "epoch": 1.0, + "learning_rate": 4.49368859177011e-05, + "loss": 3.8186, + "step": 309248 + }, + { + "epoch": 1.0, + "learning_rate": 4.492849997019058e-05, + "loss": 3.8393, + "step": 309760 + }, + { + "epoch": 1.0, + "learning_rate": 4.492013040148379e-05, + "loss": 3.8259, + "step": 310272 + }, + { + "epoch": 1.0, + "learning_rate": 4.491174445397327e-05, + "loss": 3.8321, + "step": 310784 + }, + { + "epoch": 1.0, + "learning_rate": 4.490335850646275e-05, + "loss": 3.8387, + "step": 311296 + }, + { + "epoch": 1.0, + "learning_rate": 4.489498893775596e-05, + "loss": 3.8213, + "step": 311808 + }, + { + "epoch": 1.0, + "learning_rate": 4.488660299024544e-05, + "loss": 3.8285, + "step": 312320 + }, + { + "epoch": 1.0, + "learning_rate": 4.487821704273492e-05, + "loss": 3.82, + "step": 312832 + }, + { + "epoch": 1.0, + "learning_rate": 4.48698310952244e-05, + "loss": 3.8174, + "step": 313344 + }, + { + "epoch": 1.0, + "learning_rate": 4.486144514771388e-05, + "loss": 3.8269, + "step": 313856 + }, + { + "epoch": 1.0, + "learning_rate": 4.485305920020336e-05, + "loss": 3.8286, + "step": 314368 + }, + { + "epoch": 1.0, + "learning_rate": 4.484467325269284e-05, + "loss": 3.8249, + "step": 314880 + }, + { + "epoch": 1.0, + "learning_rate": 4.4836287305182326e-05, + "loss": 3.8407, + "step": 315392 + }, + { + "epoch": 1.0, + "learning_rate": 4.4827901357671806e-05, + "loss": 3.8414, + "step": 315904 + }, + { + "epoch": 1.0, + "learning_rate": 4.4819531788965015e-05, + "loss": 3.8322, + "step": 316416 + }, + { + "epoch": 1.0, + "learning_rate": 4.4811145841454495e-05, + "loss": 3.8282, + "step": 316928 + }, + { + "epoch": 1.0, + "learning_rate": 4.4802759893943975e-05, + "loss": 3.8364, + "step": 317440 + }, + { + "epoch": 1.0, + "learning_rate": 4.4794373946433455e-05, + "loss": 3.8173, + "step": 317952 + }, + { + "epoch": 1.0, + "learning_rate": 4.4785987998922935e-05, + "loss": 3.8334, + "step": 318464 + }, + { + "epoch": 1.0, + "learning_rate": 4.4777618430216144e-05, + "loss": 3.8279, + "step": 318976 + }, + { + "epoch": 1.0, + "learning_rate": 4.4769232482705624e-05, + "loss": 3.8199, + "step": 319488 + }, + { + "epoch": 1.0, + "learning_rate": 4.4760846535195104e-05, + "loss": 3.817, + "step": 320000 + }, + { + "epoch": 1.0, + "learning_rate": 4.475246058768458e-05, + "loss": 3.8182, + "step": 320512 + }, + { + "epoch": 1.01, + "learning_rate": 4.4744074640174064e-05, + "loss": 3.8239, + "step": 321024 + }, + { + "epoch": 1.01, + "learning_rate": 4.473570507146728e-05, + "loss": 3.8282, + "step": 321536 + }, + { + "epoch": 1.01, + "learning_rate": 4.472731912395676e-05, + "loss": 3.8315, + "step": 322048 + }, + { + "epoch": 1.01, + "learning_rate": 4.471893317644623e-05, + "loss": 3.8252, + "step": 322560 + }, + { + "epoch": 1.01, + "learning_rate": 4.471054722893571e-05, + "loss": 3.8253, + "step": 323072 + }, + { + "epoch": 1.01, + "learning_rate": 4.470217766022893e-05, + "loss": 3.8252, + "step": 323584 + }, + { + "epoch": 1.01, + "learning_rate": 4.469379171271841e-05, + "loss": 3.8087, + "step": 324096 + }, + { + "epoch": 1.01, + "learning_rate": 4.468540576520788e-05, + "loss": 3.8215, + "step": 324608 + }, + { + "epoch": 1.01, + "learning_rate": 4.467701981769736e-05, + "loss": 3.8098, + "step": 325120 + }, + { + "epoch": 1.01, + "learning_rate": 4.466865024899058e-05, + "loss": 3.8137, + "step": 325632 + }, + { + "epoch": 1.01, + "learning_rate": 4.466026430148005e-05, + "loss": 3.8136, + "step": 326144 + }, + { + "epoch": 1.01, + "learning_rate": 4.465187835396953e-05, + "loss": 3.8276, + "step": 326656 + }, + { + "epoch": 1.01, + "learning_rate": 4.464349240645902e-05, + "loss": 3.8187, + "step": 327168 + }, + { + "epoch": 1.01, + "learning_rate": 4.463512283775223e-05, + "loss": 3.807, + "step": 327680 + }, + { + "epoch": 1.01, + "learning_rate": 4.4626736890241707e-05, + "loss": 3.8252, + "step": 328192 + }, + { + "epoch": 1.01, + "learning_rate": 4.4618350942731186e-05, + "loss": 3.82, + "step": 328704 + }, + { + "epoch": 1.01, + "learning_rate": 4.4609964995220666e-05, + "loss": 3.8192, + "step": 329216 + }, + { + "epoch": 1.01, + "learning_rate": 4.460159542651388e-05, + "loss": 3.8161, + "step": 329728 + }, + { + "epoch": 1.01, + "learning_rate": 4.4593209479003356e-05, + "loss": 3.8037, + "step": 330240 + }, + { + "epoch": 1.01, + "learning_rate": 4.4584823531492835e-05, + "loss": 3.8245, + "step": 330752 + }, + { + "epoch": 1.01, + "learning_rate": 4.4576437583982315e-05, + "loss": 3.8082, + "step": 331264 + }, + { + "epoch": 1.01, + "learning_rate": 4.4568051636471795e-05, + "loss": 3.819, + "step": 331776 + }, + { + "epoch": 1.01, + "learning_rate": 4.4559682067765004e-05, + "loss": 3.8078, + "step": 332288 + }, + { + "epoch": 1.01, + "learning_rate": 4.4551296120254484e-05, + "loss": 3.808, + "step": 332800 + }, + { + "epoch": 1.01, + "learning_rate": 4.454291017274397e-05, + "loss": 3.8047, + "step": 333312 + }, + { + "epoch": 1.01, + "learning_rate": 4.453452422523345e-05, + "loss": 3.8129, + "step": 333824 + }, + { + "epoch": 1.01, + "learning_rate": 4.452615465652666e-05, + "loss": 3.8111, + "step": 334336 + }, + { + "epoch": 1.01, + "learning_rate": 4.451776870901614e-05, + "loss": 3.8125, + "step": 334848 + }, + { + "epoch": 1.01, + "learning_rate": 4.450938276150562e-05, + "loss": 3.8176, + "step": 335360 + }, + { + "epoch": 1.01, + "learning_rate": 4.45009968139951e-05, + "loss": 3.8042, + "step": 335872 + }, + { + "epoch": 1.01, + "learning_rate": 4.449261086648458e-05, + "loss": 3.7997, + "step": 336384 + }, + { + "epoch": 1.01, + "learning_rate": 4.448424129777779e-05, + "loss": 3.8267, + "step": 336896 + }, + { + "epoch": 1.01, + "learning_rate": 4.447585535026727e-05, + "loss": 3.792, + "step": 337408 + }, + { + "epoch": 1.01, + "learning_rate": 4.446746940275675e-05, + "loss": 3.7934, + "step": 337920 + }, + { + "epoch": 1.01, + "learning_rate": 4.445908345524623e-05, + "loss": 3.8051, + "step": 338432 + }, + { + "epoch": 1.01, + "learning_rate": 4.445071388653944e-05, + "loss": 3.8193, + "step": 338944 + }, + { + "epoch": 1.01, + "learning_rate": 4.4442327939028925e-05, + "loss": 3.798, + "step": 339456 + }, + { + "epoch": 1.01, + "learning_rate": 4.4433941991518405e-05, + "loss": 3.803, + "step": 339968 + }, + { + "epoch": 1.01, + "learning_rate": 4.4425556044007885e-05, + "loss": 3.7941, + "step": 340480 + }, + { + "epoch": 1.01, + "learning_rate": 4.4417170096497365e-05, + "loss": 3.8001, + "step": 340992 + }, + { + "epoch": 1.01, + "learning_rate": 4.4408784148986845e-05, + "loss": 3.8114, + "step": 341504 + }, + { + "epoch": 1.01, + "learning_rate": 4.4400414580280054e-05, + "loss": 3.8082, + "step": 342016 + }, + { + "epoch": 1.01, + "learning_rate": 4.4392028632769534e-05, + "loss": 3.8064, + "step": 342528 + }, + { + "epoch": 1.01, + "learning_rate": 4.4383642685259014e-05, + "loss": 3.8118, + "step": 343040 + }, + { + "epoch": 1.01, + "learning_rate": 4.4375256737748494e-05, + "loss": 3.8138, + "step": 343552 + }, + { + "epoch": 1.01, + "learning_rate": 4.43668871690417e-05, + "loss": 3.8, + "step": 344064 + }, + { + "epoch": 1.01, + "learning_rate": 4.435850122153118e-05, + "loss": 3.8011, + "step": 344576 + }, + { + "epoch": 1.01, + "learning_rate": 4.435011527402066e-05, + "loss": 3.8105, + "step": 345088 + }, + { + "epoch": 1.01, + "learning_rate": 4.434172932651014e-05, + "loss": 3.7891, + "step": 345600 + }, + { + "epoch": 1.01, + "learning_rate": 4.433335975780336e-05, + "loss": 3.8061, + "step": 346112 + }, + { + "epoch": 1.01, + "learning_rate": 4.432497381029284e-05, + "loss": 3.7963, + "step": 346624 + }, + { + "epoch": 1.01, + "learning_rate": 4.431658786278232e-05, + "loss": 3.8172, + "step": 347136 + }, + { + "epoch": 1.01, + "learning_rate": 4.43082019152718e-05, + "loss": 3.801, + "step": 347648 + }, + { + "epoch": 1.01, + "learning_rate": 4.429983234656501e-05, + "loss": 3.795, + "step": 348160 + }, + { + "epoch": 1.01, + "learning_rate": 4.429144639905449e-05, + "loss": 3.7848, + "step": 348672 + }, + { + "epoch": 1.01, + "learning_rate": 4.428306045154397e-05, + "loss": 3.8071, + "step": 349184 + }, + { + "epoch": 1.01, + "learning_rate": 4.427467450403345e-05, + "loss": 3.8109, + "step": 349696 + }, + { + "epoch": 1.01, + "learning_rate": 4.4266304935326656e-05, + "loss": 3.8021, + "step": 350208 + }, + { + "epoch": 1.01, + "learning_rate": 4.4257918987816136e-05, + "loss": 3.7928, + "step": 350720 + }, + { + "epoch": 1.02, + "learning_rate": 4.4249533040305616e-05, + "loss": 3.7966, + "step": 351232 + }, + { + "epoch": 1.02, + "learning_rate": 4.4241147092795096e-05, + "loss": 3.8038, + "step": 351744 + }, + { + "epoch": 1.02, + "learning_rate": 4.423277752408831e-05, + "loss": 3.7912, + "step": 352256 + }, + { + "epoch": 1.02, + "learning_rate": 4.422439157657779e-05, + "loss": 3.7926, + "step": 352768 + }, + { + "epoch": 1.02, + "learning_rate": 4.421600562906727e-05, + "loss": 3.8046, + "step": 353280 + }, + { + "epoch": 1.02, + "learning_rate": 4.420763606036048e-05, + "loss": 3.8066, + "step": 353792 + }, + { + "epoch": 1.02, + "learning_rate": 4.419925011284996e-05, + "loss": 3.8022, + "step": 354304 + }, + { + "epoch": 1.02, + "learning_rate": 4.419086416533944e-05, + "loss": 3.7882, + "step": 354816 + }, + { + "epoch": 1.02, + "learning_rate": 4.418247821782892e-05, + "loss": 3.7973, + "step": 355328 + }, + { + "epoch": 1.02, + "learning_rate": 4.41740922703184e-05, + "loss": 3.789, + "step": 355840 + }, + { + "epoch": 1.02, + "learning_rate": 4.416570632280788e-05, + "loss": 3.7987, + "step": 356352 + }, + { + "epoch": 1.02, + "learning_rate": 4.415732037529736e-05, + "loss": 3.7984, + "step": 356864 + }, + { + "epoch": 1.02, + "learning_rate": 4.4148934427786834e-05, + "loss": 3.7934, + "step": 357376 + }, + { + "epoch": 1.02, + "learning_rate": 4.4140548480276314e-05, + "loss": 3.7899, + "step": 357888 + }, + { + "epoch": 1.02, + "learning_rate": 4.413217891156953e-05, + "loss": 3.7923, + "step": 358400 + }, + { + "epoch": 1.02, + "learning_rate": 4.412379296405901e-05, + "loss": 3.7857, + "step": 358912 + }, + { + "epoch": 1.02, + "learning_rate": 4.411540701654849e-05, + "loss": 3.7877, + "step": 359424 + }, + { + "epoch": 1.02, + "learning_rate": 4.410702106903797e-05, + "loss": 3.7818, + "step": 359936 + }, + { + "epoch": 1.02, + "learning_rate": 4.4098651500331186e-05, + "loss": 3.8003, + "step": 360448 + }, + { + "epoch": 1.02, + "learning_rate": 4.409026555282066e-05, + "loss": 3.7915, + "step": 360960 + }, + { + "epoch": 1.02, + "learning_rate": 4.408187960531014e-05, + "loss": 3.788, + "step": 361472 + }, + { + "epoch": 1.02, + "learning_rate": 4.407349365779962e-05, + "loss": 3.7835, + "step": 361984 + }, + { + "epoch": 1.02, + "learning_rate": 4.4065124089092835e-05, + "loss": 3.796, + "step": 362496 + }, + { + "epoch": 1.02, + "learning_rate": 4.405673814158231e-05, + "loss": 3.7966, + "step": 363008 + }, + { + "epoch": 1.02, + "learning_rate": 4.404835219407179e-05, + "loss": 3.7861, + "step": 363520 + }, + { + "epoch": 1.02, + "learning_rate": 4.403996624656127e-05, + "loss": 3.7961, + "step": 364032 + }, + { + "epoch": 1.02, + "learning_rate": 4.4031596677854484e-05, + "loss": 3.8009, + "step": 364544 + }, + { + "epoch": 1.02, + "learning_rate": 4.4023210730343963e-05, + "loss": 3.7927, + "step": 365056 + }, + { + "epoch": 1.02, + "learning_rate": 4.4014824782833443e-05, + "loss": 3.7975, + "step": 365568 + }, + { + "epoch": 1.02, + "learning_rate": 4.4006438835322923e-05, + "loss": 3.7829, + "step": 366080 + }, + { + "epoch": 1.02, + "learning_rate": 4.399806926661613e-05, + "loss": 3.7944, + "step": 366592 + }, + { + "epoch": 1.02, + "learning_rate": 4.398968331910561e-05, + "loss": 3.7902, + "step": 367104 + }, + { + "epoch": 1.02, + "learning_rate": 4.398129737159509e-05, + "loss": 3.7941, + "step": 367616 + }, + { + "epoch": 1.02, + "learning_rate": 4.397291142408457e-05, + "loss": 3.779, + "step": 368128 + }, + { + "epoch": 1.02, + "learning_rate": 4.396454185537778e-05, + "loss": 3.793, + "step": 368640 + }, + { + "epoch": 1.02, + "learning_rate": 4.395615590786726e-05, + "loss": 3.7872, + "step": 369152 + }, + { + "epoch": 1.02, + "learning_rate": 4.394776996035674e-05, + "loss": 3.784, + "step": 369664 + }, + { + "epoch": 1.02, + "learning_rate": 4.393938401284622e-05, + "loss": 3.7781, + "step": 370176 + }, + { + "epoch": 1.02, + "learning_rate": 4.393101444413944e-05, + "loss": 3.7809, + "step": 370688 + }, + { + "epoch": 1.02, + "learning_rate": 4.392262849662892e-05, + "loss": 3.7808, + "step": 371200 + }, + { + "epoch": 1.02, + "learning_rate": 4.39142425491184e-05, + "loss": 3.7922, + "step": 371712 + }, + { + "epoch": 1.02, + "learning_rate": 4.390585660160788e-05, + "loss": 3.7981, + "step": 372224 + }, + { + "epoch": 1.02, + "learning_rate": 4.3897487032901086e-05, + "loss": 3.8003, + "step": 372736 + }, + { + "epoch": 1.02, + "learning_rate": 4.3889101085390566e-05, + "loss": 3.7699, + "step": 373248 + }, + { + "epoch": 1.02, + "learning_rate": 4.3880715137880046e-05, + "loss": 3.7962, + "step": 373760 + }, + { + "epoch": 1.02, + "learning_rate": 4.3872329190369526e-05, + "loss": 3.7888, + "step": 374272 + }, + { + "epoch": 1.02, + "learning_rate": 4.3863959621662735e-05, + "loss": 3.7822, + "step": 374784 + }, + { + "epoch": 1.02, + "learning_rate": 4.3855573674152215e-05, + "loss": 3.7796, + "step": 375296 + }, + { + "epoch": 1.02, + "learning_rate": 4.3847187726641695e-05, + "loss": 3.7945, + "step": 375808 + }, + { + "epoch": 1.02, + "learning_rate": 4.3838801779131175e-05, + "loss": 3.7831, + "step": 376320 + }, + { + "epoch": 1.02, + "learning_rate": 4.383043221042439e-05, + "loss": 3.7914, + "step": 376832 + }, + { + "epoch": 1.02, + "learning_rate": 4.382204626291387e-05, + "loss": 3.7818, + "step": 377344 + }, + { + "epoch": 1.02, + "learning_rate": 4.381366031540335e-05, + "loss": 3.7854, + "step": 377856 + }, + { + "epoch": 1.02, + "learning_rate": 4.380527436789283e-05, + "loss": 3.7908, + "step": 378368 + }, + { + "epoch": 1.02, + "learning_rate": 4.379690479918604e-05, + "loss": 3.7814, + "step": 378880 + }, + { + "epoch": 1.02, + "learning_rate": 4.378851885167552e-05, + "loss": 3.7862, + "step": 379392 + }, + { + "epoch": 1.02, + "learning_rate": 4.3780132904165e-05, + "loss": 3.7946, + "step": 379904 + }, + { + "epoch": 1.02, + "learning_rate": 4.377174695665448e-05, + "loss": 3.7794, + "step": 380416 + }, + { + "epoch": 1.02, + "learning_rate": 4.376336100914396e-05, + "loss": 3.7829, + "step": 380928 + }, + { + "epoch": 1.02, + "learning_rate": 4.375499144043717e-05, + "loss": 3.7866, + "step": 381440 + }, + { + "epoch": 1.03, + "eval_loss": 3.9028751850128174, + "eval_runtime": 335.3025, + "eval_samples_per_second": 1138.05, + "eval_steps_per_second": 35.565, + "step": 381600 + }, + { + "epoch": 0.0, + "learning_rate": 4.374660549292665e-05, + "loss": 3.7705, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.373821954541613e-05, + "loss": 3.772, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.372983359790561e-05, + "loss": 3.7865, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.3721447650395095e-05, + "loss": 3.787, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.3713061702884575e-05, + "loss": 3.7931, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.3704675755374055e-05, + "loss": 3.7751, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.3696289807863535e-05, + "loss": 3.782, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.3687903860353015e-05, + "loss": 3.7665, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.3679534291646224e-05, + "loss": 3.7831, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.3671148344135704e-05, + "loss": 3.7775, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.3662762396625184e-05, + "loss": 3.7773, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.3654376449114664e-05, + "loss": 3.784, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.36460232592116e-05, + "loss": 3.7717, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.363763731170108e-05, + "loss": 3.7736, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.362925136419056e-05, + "loss": 3.7704, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.362086541668005e-05, + "loss": 3.7645, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.361247946916953e-05, + "loss": 3.7707, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.360409352165901e-05, + "loss": 3.7768, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.359570757414849e-05, + "loss": 3.7733, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.358732162663797e-05, + "loss": 3.7896, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357895205793118e-05, + "loss": 3.787, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.357056611042066e-05, + "loss": 3.7819, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.356218016291014e-05, + "loss": 3.777, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.355379421539962e-05, + "loss": 3.7835, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.354542464669283e-05, + "loss": 3.7672, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.353703869918231e-05, + "loss": 3.7824, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.352865275167179e-05, + "loss": 3.7757, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.352026680416127e-05, + "loss": 3.7668, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.351189723545448e-05, + "loss": 3.7659, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.350351128794396e-05, + "loss": 3.7706, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.349512534043344e-05, + "loss": 3.7723, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.3486739392922916e-05, + "loss": 3.7755, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.347836982421613e-05, + "loss": 3.7832, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.346998387670561e-05, + "loss": 3.7743, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.346159792919509e-05, + "loss": 3.7748, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.3453211981684565e-05, + "loss": 3.7754, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.344484241297778e-05, + "loss": 3.762, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.343645646546726e-05, + "loss": 3.7643, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.342807051795674e-05, + "loss": 3.7605, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.341968457044622e-05, + "loss": 3.7645, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.3411315001739436e-05, + "loss": 3.7631, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.3402929054228916e-05, + "loss": 3.7782, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.339454310671839e-05, + "loss": 3.7696, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.338615715920787e-05, + "loss": 3.7567, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.3377787590501085e-05, + "loss": 3.7776, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.3369401642990565e-05, + "loss": 3.7665, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.336101569548004e-05, + "loss": 3.7741, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.335262974796952e-05, + "loss": 3.7632, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.3344243800459e-05, + "loss": 3.754, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.333587423175221e-05, + "loss": 3.7717, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.332748828424169e-05, + "loss": 3.7624, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.3319102336731174e-05, + "loss": 3.7709, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.3310716389220654e-05, + "loss": 3.754, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.330234682051386e-05, + "loss": 3.7616, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.329396087300334e-05, + "loss": 3.7516, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.328557492549282e-05, + "loss": 3.764, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.32771889779823e-05, + "loss": 3.7653, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.326881940927551e-05, + "loss": 3.7597, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.326043346176499e-05, + "loss": 3.7706, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.325204751425447e-05, + "loss": 3.7573, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.324366156674395e-05, + "loss": 3.7496, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.323529199803716e-05, + "loss": 3.7807, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.322690605052664e-05, + "loss": 3.7441, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.321852010301613e-05, + "loss": 3.7397, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.321013415550561e-05, + "loss": 3.7573, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.320176458679882e-05, + "loss": 3.7717, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.31933786392883e-05, + "loss": 3.7456, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.318499269177778e-05, + "loss": 3.7568, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.3176623123070986e-05, + "loss": 3.7452, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.3168237175560466e-05, + "loss": 3.7513, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.3159851228049946e-05, + "loss": 3.7654, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.3151465280539426e-05, + "loss": 3.761, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.3143095711832635e-05, + "loss": 3.7599, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.3134709764322115e-05, + "loss": 3.76, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.3126323816811595e-05, + "loss": 3.7686, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.311793786930108e-05, + "loss": 3.7494, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.310956830059429e-05, + "loss": 3.7584, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.310118235308377e-05, + "loss": 3.7603, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.309279640557325e-05, + "loss": 3.7426, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.308441045806273e-05, + "loss": 3.7566, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.307604088935594e-05, + "loss": 3.7532, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.306765494184542e-05, + "loss": 3.7661, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.30592689943349e-05, + "loss": 3.756, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.305088304682438e-05, + "loss": 3.7482, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.304251347811759e-05, + "loss": 3.7393, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.303412753060707e-05, + "loss": 3.7565, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.302574158309655e-05, + "loss": 3.7626, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.3017355635586035e-05, + "loss": 3.7532, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.3008986066879244e-05, + "loss": 3.7513, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.3000600119368724e-05, + "loss": 3.7516, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.2992214171858204e-05, + "loss": 3.7558, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.2983828224347684e-05, + "loss": 3.7454, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.297545865564089e-05, + "loss": 3.7466, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.296707270813037e-05, + "loss": 3.7592, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.295870313942358e-05, + "loss": 3.7587, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.295031719191306e-05, + "loss": 3.7555, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294193124440254e-05, + "loss": 3.7411, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293354529689202e-05, + "loss": 3.7541, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.29251593493815e-05, + "loss": 3.7393, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.291677340187099e-05, + "loss": 3.7547, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.290838745436047e-05, + "loss": 3.7513, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.290000150684995e-05, + "loss": 3.7491, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.289163193814316e-05, + "loss": 3.7444, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.288324599063264e-05, + "loss": 3.7408, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.287486004312212e-05, + "loss": 3.7472, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.28664740956116e-05, + "loss": 3.7386, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.285810452690481e-05, + "loss": 3.7402, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.284971857939429e-05, + "loss": 3.7515, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.284133263188377e-05, + "loss": 3.7501, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.2832946684373247e-05, + "loss": 3.7439, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.2824577115666456e-05, + "loss": 3.7384, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.281619116815594e-05, + "loss": 3.7482, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.280780522064542e-05, + "loss": 3.7519, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.27994192731349e-05, + "loss": 3.7466, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.279104970442811e-05, + "loss": 3.7526, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.278266375691759e-05, + "loss": 3.7541, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.277427780940707e-05, + "loss": 3.7512, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.276589186189655e-05, + "loss": 3.7497, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.275752229318976e-05, + "loss": 3.7425, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.274913634567924e-05, + "loss": 3.7452, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.274075039816872e-05, + "loss": 3.7476, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.27323644506582e-05, + "loss": 3.75, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.272399488195141e-05, + "loss": 3.7368, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.2715608934440896e-05, + "loss": 3.7465, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.2707222986930376e-05, + "loss": 3.7451, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.2698837039419856e-05, + "loss": 3.741, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.2690467470713065e-05, + "loss": 3.732, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.2682081523202545e-05, + "loss": 3.7405, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.2673695575692025e-05, + "loss": 3.7357, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.2665309628181505e-05, + "loss": 3.7479, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.2656940059474714e-05, + "loss": 3.7512, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.2648554111964194e-05, + "loss": 3.7574, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.2640168164453674e-05, + "loss": 3.7271, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.2631782216943154e-05, + "loss": 3.7535, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.262341264823636e-05, + "loss": 3.7463, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.261502670072584e-05, + "loss": 3.7397, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.260664075321533e-05, + "loss": 3.735, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.259825480570481e-05, + "loss": 3.752, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.258988523699802e-05, + "loss": 3.736, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.25814992894875e-05, + "loss": 3.7511, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.257311334197698e-05, + "loss": 3.7353, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.256472739446646e-05, + "loss": 3.7457, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.255635782575967e-05, + "loss": 3.7448, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.254797187824915e-05, + "loss": 3.7379, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.253958593073863e-05, + "loss": 3.7491, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253119998322811e-05, + "loss": 3.7437, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.252283041452132e-05, + "loss": 3.7466, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.25144444670108e-05, + "loss": 3.7307, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.250605851950028e-05, + "loss": 3.7487, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 3.887489080429077, + "eval_runtime": 303.274, + "eval_samples_per_second": 1258.238, + "eval_steps_per_second": 39.321, + "step": 457920 + }, + { + "epoch": 1.0, + "learning_rate": 4.249767257198976e-05, + "loss": 3.7367, + "step": 458240 + }, + { + "epoch": 1.0, + "learning_rate": 4.248930300328297e-05, + "loss": 3.7284, + "step": 458752 + }, + { + "epoch": 1.0, + "learning_rate": 4.248091705577245e-05, + "loss": 3.7384, + "step": 459264 + }, + { + "epoch": 1.0, + "learning_rate": 4.247253110826193e-05, + "loss": 3.7478, + "step": 459776 + }, + { + "epoch": 1.0, + "learning_rate": 4.246414516075141e-05, + "loss": 3.7507, + "step": 460288 + }, + { + "epoch": 1.0, + "learning_rate": 4.245577559204462e-05, + "loss": 3.7313, + "step": 460800 + }, + { + "epoch": 1.0, + "learning_rate": 4.24473896445341e-05, + "loss": 3.7377, + "step": 461312 + }, + { + "epoch": 1.0, + "learning_rate": 4.243900369702358e-05, + "loss": 3.7249, + "step": 461824 + }, + { + "epoch": 1.0, + "learning_rate": 4.2430617749513054e-05, + "loss": 3.7424, + "step": 462336 + }, + { + "epoch": 1.0, + "learning_rate": 4.242224818080627e-05, + "loss": 3.7336, + "step": 462848 + }, + { + "epoch": 1.0, + "learning_rate": 4.241386223329575e-05, + "loss": 3.7383, + "step": 463360 + }, + { + "epoch": 1.0, + "learning_rate": 4.240547628578524e-05, + "loss": 3.7401, + "step": 463872 + }, + { + "epoch": 1.0, + "learning_rate": 4.2397106717078446e-05, + "loss": 3.7305, + "step": 464384 + }, + { + "epoch": 1.0, + "learning_rate": 4.2388720769567926e-05, + "loss": 3.7347, + "step": 464896 + }, + { + "epoch": 1.0, + "learning_rate": 4.2380334822057406e-05, + "loss": 3.7247, + "step": 465408 + }, + { + "epoch": 1.0, + "learning_rate": 4.2371948874546886e-05, + "loss": 3.7214, + "step": 465920 + }, + { + "epoch": 1.0, + "learning_rate": 4.236356292703636e-05, + "loss": 3.7296, + "step": 466432 + }, + { + "epoch": 1.0, + "learning_rate": 4.235517697952584e-05, + "loss": 3.7407, + "step": 466944 + }, + { + "epoch": 1.0, + "learning_rate": 4.234679103201532e-05, + "loss": 3.7298, + "step": 467456 + }, + { + "epoch": 1.0, + "learning_rate": 4.23384050845048e-05, + "loss": 3.7518, + "step": 467968 + }, + { + "epoch": 1.0, + "learning_rate": 4.233003551579801e-05, + "loss": 3.743, + "step": 468480 + }, + { + "epoch": 1.0, + "learning_rate": 4.232164956828749e-05, + "loss": 3.7421, + "step": 468992 + }, + { + "epoch": 1.0, + "learning_rate": 4.2313263620776975e-05, + "loss": 3.7353, + "step": 469504 + }, + { + "epoch": 1.0, + "learning_rate": 4.2304877673266455e-05, + "loss": 3.7379, + "step": 470016 + }, + { + "epoch": 1.0, + "learning_rate": 4.2296508104559664e-05, + "loss": 3.7248, + "step": 470528 + }, + { + "epoch": 1.0, + "learning_rate": 4.2288122157049144e-05, + "loss": 3.7447, + "step": 471040 + }, + { + "epoch": 1.0, + "learning_rate": 4.2279736209538624e-05, + "loss": 3.7315, + "step": 471552 + }, + { + "epoch": 1.0, + "learning_rate": 4.2271350262028104e-05, + "loss": 3.7255, + "step": 472064 + }, + { + "epoch": 1.0, + "learning_rate": 4.226298069332131e-05, + "loss": 3.7281, + "step": 472576 + }, + { + "epoch": 1.0, + "learning_rate": 4.225459474581079e-05, + "loss": 3.7296, + "step": 473088 + }, + { + "epoch": 1.01, + "learning_rate": 4.224620879830027e-05, + "loss": 3.7306, + "step": 473600 + }, + { + "epoch": 1.01, + "learning_rate": 4.223782285078975e-05, + "loss": 3.7375, + "step": 474112 + }, + { + "epoch": 1.01, + "learning_rate": 4.222945328208296e-05, + "loss": 3.7372, + "step": 474624 + }, + { + "epoch": 1.01, + "learning_rate": 4.222106733457244e-05, + "loss": 3.739, + "step": 475136 + }, + { + "epoch": 1.01, + "learning_rate": 4.221268138706193e-05, + "loss": 3.7281, + "step": 475648 + }, + { + "epoch": 1.01, + "learning_rate": 4.220431181835514e-05, + "loss": 3.7338, + "step": 476160 + }, + { + "epoch": 1.01, + "learning_rate": 4.219592587084462e-05, + "loss": 3.7286, + "step": 476672 + }, + { + "epoch": 1.01, + "learning_rate": 4.21875399233341e-05, + "loss": 3.7199, + "step": 477184 + }, + { + "epoch": 1.01, + "learning_rate": 4.217915397582358e-05, + "loss": 3.7188, + "step": 477696 + }, + { + "epoch": 1.01, + "learning_rate": 4.2170784407116787e-05, + "loss": 3.723, + "step": 478208 + }, + { + "epoch": 1.01, + "learning_rate": 4.2162398459606267e-05, + "loss": 3.7239, + "step": 478720 + }, + { + "epoch": 1.01, + "learning_rate": 4.2154012512095746e-05, + "loss": 3.7382, + "step": 479232 + }, + { + "epoch": 1.01, + "learning_rate": 4.2145626564585226e-05, + "loss": 3.7274, + "step": 479744 + }, + { + "epoch": 1.01, + "learning_rate": 4.2137256995878436e-05, + "loss": 3.7197, + "step": 480256 + }, + { + "epoch": 1.01, + "learning_rate": 4.2128871048367915e-05, + "loss": 3.7397, + "step": 480768 + }, + { + "epoch": 1.01, + "learning_rate": 4.2120485100857395e-05, + "loss": 3.724, + "step": 481280 + }, + { + "epoch": 1.01, + "learning_rate": 4.211209915334688e-05, + "loss": 3.7345, + "step": 481792 + }, + { + "epoch": 1.01, + "learning_rate": 4.210372958464009e-05, + "loss": 3.7239, + "step": 482304 + }, + { + "epoch": 1.01, + "learning_rate": 4.209534363712957e-05, + "loss": 3.7079, + "step": 482816 + }, + { + "epoch": 1.01, + "learning_rate": 4.208695768961905e-05, + "loss": 3.7386, + "step": 483328 + }, + { + "epoch": 1.01, + "learning_rate": 4.207857174210853e-05, + "loss": 3.72, + "step": 483840 + }, + { + "epoch": 1.01, + "learning_rate": 4.207020217340174e-05, + "loss": 3.7318, + "step": 484352 + }, + { + "epoch": 1.01, + "learning_rate": 4.206181622589122e-05, + "loss": 3.7197, + "step": 484864 + }, + { + "epoch": 1.01, + "learning_rate": 4.20534302783807e-05, + "loss": 3.7214, + "step": 485376 + }, + { + "epoch": 1.01, + "learning_rate": 4.204504433087018e-05, + "loss": 3.7085, + "step": 485888 + }, + { + "epoch": 1.01, + "learning_rate": 4.203667476216339e-05, + "loss": 3.721, + "step": 486400 + }, + { + "epoch": 1.01, + "learning_rate": 4.202828881465287e-05, + "loss": 3.7309, + "step": 486912 + }, + { + "epoch": 1.01, + "learning_rate": 4.201990286714235e-05, + "loss": 3.7167, + "step": 487424 + }, + { + "epoch": 1.01, + "learning_rate": 4.2011516919631836e-05, + "loss": 3.7317, + "step": 487936 + }, + { + "epoch": 1.01, + "learning_rate": 4.2003147350925045e-05, + "loss": 3.7223, + "step": 488448 + }, + { + "epoch": 1.01, + "learning_rate": 4.1994761403414525e-05, + "loss": 3.7112, + "step": 488960 + }, + { + "epoch": 1.01, + "learning_rate": 4.1986375455904005e-05, + "loss": 3.7363, + "step": 489472 + }, + { + "epoch": 1.01, + "learning_rate": 4.1977989508393485e-05, + "loss": 3.7075, + "step": 489984 + }, + { + "epoch": 1.01, + "learning_rate": 4.1969619939686694e-05, + "loss": 3.703, + "step": 490496 + }, + { + "epoch": 1.01, + "learning_rate": 4.1961233992176174e-05, + "loss": 3.7214, + "step": 491008 + }, + { + "epoch": 1.01, + "learning_rate": 4.1952848044665654e-05, + "loss": 3.7291, + "step": 491520 + }, + { + "epoch": 1.01, + "learning_rate": 4.1944462097155134e-05, + "loss": 3.7069, + "step": 492032 + }, + { + "epoch": 1.01, + "learning_rate": 4.193609252844834e-05, + "loss": 3.7217, + "step": 492544 + }, + { + "epoch": 1.01, + "learning_rate": 4.192770658093782e-05, + "loss": 3.7041, + "step": 493056 + }, + { + "epoch": 1.01, + "learning_rate": 4.19193206334273e-05, + "loss": 3.7177, + "step": 493568 + }, + { + "epoch": 1.01, + "learning_rate": 4.191093468591679e-05, + "loss": 3.7224, + "step": 494080 + }, + { + "epoch": 1.01, + "learning_rate": 4.190256511721e-05, + "loss": 3.7193, + "step": 494592 + }, + { + "epoch": 1.01, + "learning_rate": 4.189417916969948e-05, + "loss": 3.723, + "step": 495104 + }, + { + "epoch": 1.01, + "learning_rate": 4.188579322218896e-05, + "loss": 3.7185, + "step": 495616 + }, + { + "epoch": 1.01, + "learning_rate": 4.187740727467844e-05, + "loss": 3.7308, + "step": 496128 + }, + { + "epoch": 1.01, + "learning_rate": 4.186903770597165e-05, + "loss": 3.7104, + "step": 496640 + }, + { + "epoch": 1.01, + "learning_rate": 4.186065175846113e-05, + "loss": 3.7214, + "step": 497152 + }, + { + "epoch": 1.01, + "learning_rate": 4.185226581095061e-05, + "loss": 3.7173, + "step": 497664 + }, + { + "epoch": 1.01, + "learning_rate": 4.184387986344009e-05, + "loss": 3.7056, + "step": 498176 + }, + { + "epoch": 1.01, + "learning_rate": 4.1835510294733297e-05, + "loss": 3.7188, + "step": 498688 + }, + { + "epoch": 1.01, + "learning_rate": 4.1827124347222776e-05, + "loss": 3.7152, + "step": 499200 + }, + { + "epoch": 1.01, + "learning_rate": 4.1818738399712256e-05, + "loss": 3.7278, + "step": 499712 + }, + { + "epoch": 1.01, + "learning_rate": 4.181035245220174e-05, + "loss": 3.723, + "step": 500224 + }, + { + "epoch": 1.01, + "learning_rate": 4.180198288349495e-05, + "loss": 3.7051, + "step": 500736 + }, + { + "epoch": 1.01, + "learning_rate": 4.179359693598443e-05, + "loss": 3.7026, + "step": 501248 + }, + { + "epoch": 1.01, + "learning_rate": 4.178521098847391e-05, + "loss": 3.7187, + "step": 501760 + }, + { + "epoch": 1.01, + "learning_rate": 4.177682504096339e-05, + "loss": 3.7272, + "step": 502272 + }, + { + "epoch": 1.01, + "learning_rate": 4.17684554722566e-05, + "loss": 3.7165, + "step": 502784 + }, + { + "epoch": 1.01, + "learning_rate": 4.176006952474608e-05, + "loss": 3.7081, + "step": 503296 + }, + { + "epoch": 1.02, + "learning_rate": 4.175168357723556e-05, + "loss": 3.7163, + "step": 503808 + }, + { + "epoch": 1.02, + "learning_rate": 4.174329762972504e-05, + "loss": 3.7145, + "step": 504320 + }, + { + "epoch": 1.02, + "learning_rate": 4.173492806101825e-05, + "loss": 3.7107, + "step": 504832 + }, + { + "epoch": 1.02, + "learning_rate": 4.172654211350773e-05, + "loss": 3.7061, + "step": 505344 + }, + { + "epoch": 1.02, + "learning_rate": 4.171815616599721e-05, + "loss": 3.7202, + "step": 505856 + }, + { + "epoch": 1.02, + "learning_rate": 4.1709786597290426e-05, + "loss": 3.7187, + "step": 506368 + }, + { + "epoch": 1.02, + "learning_rate": 4.1701400649779906e-05, + "loss": 3.7199, + "step": 506880 + }, + { + "epoch": 1.02, + "learning_rate": 4.1693014702269386e-05, + "loss": 3.706, + "step": 507392 + }, + { + "epoch": 1.02, + "learning_rate": 4.1684628754758866e-05, + "loss": 3.7108, + "step": 507904 + }, + { + "epoch": 1.02, + "learning_rate": 4.1676242807248346e-05, + "loss": 3.7068, + "step": 508416 + }, + { + "epoch": 1.02, + "learning_rate": 4.1667856859737826e-05, + "loss": 3.7172, + "step": 508928 + }, + { + "epoch": 1.02, + "learning_rate": 4.1659470912227306e-05, + "loss": 3.7132, + "step": 509440 + }, + { + "epoch": 1.02, + "learning_rate": 4.1651084964716786e-05, + "loss": 3.7095, + "step": 509952 + }, + { + "epoch": 1.02, + "learning_rate": 4.1642715396009995e-05, + "loss": 3.7117, + "step": 510464 + }, + { + "epoch": 1.02, + "learning_rate": 4.1634329448499475e-05, + "loss": 3.7047, + "step": 510976 + }, + { + "epoch": 1.02, + "learning_rate": 4.1625943500988955e-05, + "loss": 3.7089, + "step": 511488 + }, + { + "epoch": 1.02, + "learning_rate": 4.1617557553478435e-05, + "loss": 3.7014, + "step": 512000 + }, + { + "epoch": 1.02, + "learning_rate": 4.1609187984771644e-05, + "loss": 3.7073, + "step": 512512 + }, + { + "epoch": 1.02, + "learning_rate": 4.160080203726113e-05, + "loss": 3.708, + "step": 513024 + }, + { + "epoch": 1.02, + "learning_rate": 4.159241608975061e-05, + "loss": 3.7177, + "step": 513536 + }, + { + "epoch": 1.02, + "learning_rate": 4.1584030142240084e-05, + "loss": 3.7018, + "step": 514048 + }, + { + "epoch": 1.02, + "learning_rate": 4.15756605735333e-05, + "loss": 3.7046, + "step": 514560 + }, + { + "epoch": 1.02, + "learning_rate": 4.156727462602278e-05, + "loss": 3.7068, + "step": 515072 + }, + { + "epoch": 1.02, + "learning_rate": 4.155888867851226e-05, + "loss": 3.7138, + "step": 515584 + }, + { + "epoch": 1.02, + "learning_rate": 4.155050273100173e-05, + "loss": 3.7087, + "step": 516096 + }, + { + "epoch": 1.02, + "learning_rate": 4.154213316229495e-05, + "loss": 3.719, + "step": 516608 + }, + { + "epoch": 1.02, + "learning_rate": 4.153374721478443e-05, + "loss": 3.7136, + "step": 517120 + }, + { + "epoch": 1.02, + "learning_rate": 4.152536126727391e-05, + "loss": 3.7141, + "step": 517632 + }, + { + "epoch": 1.02, + "learning_rate": 4.151697531976338e-05, + "loss": 3.7116, + "step": 518144 + }, + { + "epoch": 1.02, + "learning_rate": 4.15086057510566e-05, + "loss": 3.7095, + "step": 518656 + }, + { + "epoch": 1.02, + "learning_rate": 4.1500219803546084e-05, + "loss": 3.7083, + "step": 519168 + }, + { + "epoch": 1.02, + "learning_rate": 4.149183385603556e-05, + "loss": 3.7117, + "step": 519680 + }, + { + "epoch": 1.02, + "learning_rate": 4.148344790852504e-05, + "loss": 3.7087, + "step": 520192 + }, + { + "epoch": 1.02, + "learning_rate": 4.147507833981825e-05, + "loss": 3.7029, + "step": 520704 + }, + { + "epoch": 1.02, + "learning_rate": 4.146669239230773e-05, + "loss": 3.7128, + "step": 521216 + }, + { + "epoch": 1.02, + "learning_rate": 4.1458306444797206e-05, + "loss": 3.7083, + "step": 521728 + }, + { + "epoch": 1.02, + "learning_rate": 4.1449920497286686e-05, + "loss": 3.705, + "step": 522240 + }, + { + "epoch": 1.02, + "learning_rate": 4.14415509285799e-05, + "loss": 3.6937, + "step": 522752 + }, + { + "epoch": 1.02, + "learning_rate": 4.143316498106938e-05, + "loss": 3.7034, + "step": 523264 + }, + { + "epoch": 1.02, + "learning_rate": 4.1424779033558855e-05, + "loss": 3.7007, + "step": 523776 + }, + { + "epoch": 1.02, + "learning_rate": 4.1416393086048335e-05, + "loss": 3.7096, + "step": 524288 + }, + { + "epoch": 1.02, + "learning_rate": 4.140802351734155e-05, + "loss": 3.7159, + "step": 524800 + }, + { + "epoch": 1.02, + "learning_rate": 4.139963756983103e-05, + "loss": 3.7197, + "step": 525312 + }, + { + "epoch": 1.02, + "learning_rate": 4.139125162232051e-05, + "loss": 3.6922, + "step": 525824 + }, + { + "epoch": 1.02, + "learning_rate": 4.138286567480999e-05, + "loss": 3.7144, + "step": 526336 + }, + { + "epoch": 1.02, + "learning_rate": 4.137449610610321e-05, + "loss": 3.7079, + "step": 526848 + }, + { + "epoch": 1.02, + "learning_rate": 4.136611015859268e-05, + "loss": 3.7086, + "step": 527360 + }, + { + "epoch": 1.02, + "learning_rate": 4.135772421108216e-05, + "loss": 3.6985, + "step": 527872 + }, + { + "epoch": 1.02, + "learning_rate": 4.1349354642375376e-05, + "loss": 3.7143, + "step": 528384 + }, + { + "epoch": 1.02, + "learning_rate": 4.1340968694864856e-05, + "loss": 3.6982, + "step": 528896 + }, + { + "epoch": 1.02, + "learning_rate": 4.133258274735433e-05, + "loss": 3.7166, + "step": 529408 + }, + { + "epoch": 1.02, + "learning_rate": 4.132419679984381e-05, + "loss": 3.6974, + "step": 529920 + }, + { + "epoch": 1.02, + "learning_rate": 4.1315827231137025e-05, + "loss": 3.7093, + "step": 530432 + }, + { + "epoch": 1.02, + "learning_rate": 4.1307441283626505e-05, + "loss": 3.7093, + "step": 530944 + }, + { + "epoch": 1.02, + "learning_rate": 4.1299055336115985e-05, + "loss": 3.7061, + "step": 531456 + }, + { + "epoch": 1.02, + "learning_rate": 4.1290669388605465e-05, + "loss": 3.7105, + "step": 531968 + }, + { + "epoch": 1.02, + "learning_rate": 4.128229981989868e-05, + "loss": 3.7082, + "step": 532480 + }, + { + "epoch": 1.02, + "learning_rate": 4.1273913872388154e-05, + "loss": 3.7088, + "step": 532992 + }, + { + "epoch": 1.02, + "learning_rate": 4.1265527924877634e-05, + "loss": 3.6967, + "step": 533504 + }, + { + "epoch": 1.02, + "learning_rate": 4.1257141977367114e-05, + "loss": 3.7143, + "step": 534016 + }, + { + "epoch": 1.03, + "eval_loss": 3.877584934234619, + "eval_runtime": 302.778, + "eval_samples_per_second": 1260.3, + "eval_steps_per_second": 39.385, + "step": 534240 + }, + { + "epoch": 0.0, + "learning_rate": 4.1248756029856594e-05, + "loss": 3.6994, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.1240370082346074e-05, + "loss": 3.6918, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.1231984134835553e-05, + "loss": 3.707, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.1223598187325033e-05, + "loss": 3.7097, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.1215212239814513e-05, + "loss": 3.7138, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.120682629230399e-05, + "loss": 3.6967, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.119844034479347e-05, + "loss": 3.7052, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.119005439728296e-05, + "loss": 3.6903, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.118168482857617e-05, + "loss": 3.7045, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.117329888106565e-05, + "loss": 3.7003, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.116491293355513e-05, + "loss": 3.701, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.115652698604461e-05, + "loss": 3.7042, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.114817379614155e-05, + "loss": 3.6993, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.113978784863103e-05, + "loss": 3.6951, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.113140190112051e-05, + "loss": 3.6917, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.112301595360999e-05, + "loss": 3.6859, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111463000609947e-05, + "loss": 3.695, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110624405858895e-05, + "loss": 3.7032, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109785811107843e-05, + "loss": 3.6981, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108947216356791e-05, + "loss": 3.7095, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.108110259486112e-05, + "loss": 3.7114, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.10727166473506e-05, + "loss": 3.7097, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.106433069984008e-05, + "loss": 3.6992, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.105594475232956e-05, + "loss": 3.6994, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.104757518362277e-05, + "loss": 3.6971, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.103918923611225e-05, + "loss": 3.7069, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.103080328860173e-05, + "loss": 3.6948, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.102241734109121e-05, + "loss": 3.6959, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.101404777238442e-05, + "loss": 3.6933, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.10056618248739e-05, + "loss": 3.6934, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.099727587736338e-05, + "loss": 3.6917, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.098888992985286e-05, + "loss": 3.7044, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.0980520361146076e-05, + "loss": 3.7028, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.0972134413635556e-05, + "loss": 3.7049, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.0963748466125036e-05, + "loss": 3.6909, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.0955378897418245e-05, + "loss": 3.703, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.0946992949907725e-05, + "loss": 3.6984, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.0938607002397205e-05, + "loss": 3.6832, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.0930221054886685e-05, + "loss": 3.686, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.0921851486179894e-05, + "loss": 3.6881, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.0913465538669374e-05, + "loss": 3.694, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.0905079591158854e-05, + "loss": 3.6983, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.0896693643648334e-05, + "loss": 3.6979, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.088832407494155e-05, + "loss": 3.6836, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.087993812743103e-05, + "loss": 3.7051, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.087155217992051e-05, + "loss": 3.692, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.086316623240999e-05, + "loss": 3.7018, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.08547966637032e-05, + "loss": 3.693, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.084641071619268e-05, + "loss": 3.6696, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.083802476868216e-05, + "loss": 3.7081, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.082963882117163e-05, + "loss": 3.6851, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082126925246485e-05, + "loss": 3.6971, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081288330495433e-05, + "loss": 3.6893, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080449735744381e-05, + "loss": 3.6871, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.079611140993329e-05, + "loss": 3.6802, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.0787741841226504e-05, + "loss": 3.6846, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.0779355893715984e-05, + "loss": 3.7021, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.077098632500919e-05, + "loss": 3.6794, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.076260037749867e-05, + "loss": 3.697, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.075421442998815e-05, + "loss": 3.6938, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.074582848247763e-05, + "loss": 3.6761, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.0737442534967106e-05, + "loss": 3.7017, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.0729056587456586e-05, + "loss": 3.6787, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.0720670639946066e-05, + "loss": 3.6713, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.0712284692435546e-05, + "loss": 3.685, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.070391512372876e-05, + "loss": 3.6931, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.069552917621824e-05, + "loss": 3.6745, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.068714322870772e-05, + "loss": 3.6884, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.06787572811972e-05, + "loss": 3.6729, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.067038771249041e-05, + "loss": 3.6818, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.066200176497989e-05, + "loss": 3.6914, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.065361581746937e-05, + "loss": 3.6844, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.064522986995885e-05, + "loss": 3.6949, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.063686030125206e-05, + "loss": 3.6849, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.062847435374154e-05, + "loss": 3.6951, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.062008840623102e-05, + "loss": 3.6832, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.06117024587205e-05, + "loss": 3.6905, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.0603332890013715e-05, + "loss": 3.6794, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.0594946942503195e-05, + "loss": 3.6765, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.0586560994992675e-05, + "loss": 3.6858, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.0578175047482155e-05, + "loss": 3.6833, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.0569805478775364e-05, + "loss": 3.6929, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.0561419531264844e-05, + "loss": 3.6951, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.0553033583754324e-05, + "loss": 3.6696, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.0544647636243804e-05, + "loss": 3.6708, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.053627806753701e-05, + "loss": 3.6847, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.052789212002649e-05, + "loss": 3.6935, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.051950617251597e-05, + "loss": 3.6837, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.051112022500545e-05, + "loss": 3.6744, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.050275065629867e-05, + "loss": 3.6887, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.049436470878815e-05, + "loss": 3.6806, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.048597876127763e-05, + "loss": 3.679, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.047759281376711e-05, + "loss": 3.6733, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.046922324506032e-05, + "loss": 3.6865, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.046085367635353e-05, + "loss": 3.6903, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.045246772884301e-05, + "loss": 3.6891, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.044408178133249e-05, + "loss": 3.674, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.043569583382197e-05, + "loss": 3.6785, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.042730988631145e-05, + "loss": 3.6746, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.041892393880093e-05, + "loss": 3.6861, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.041053799129041e-05, + "loss": 3.6829, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.040215204377989e-05, + "loss": 3.677, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.03937824750731e-05, + "loss": 3.6785, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.038539652756258e-05, + "loss": 3.6739, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.037701058005206e-05, + "loss": 3.6748, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036862463254154e-05, + "loss": 3.6686, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.036025506383475e-05, + "loss": 3.6772, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.035186911632423e-05, + "loss": 3.6765, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.034348316881371e-05, + "loss": 3.684, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.033509722130319e-05, + "loss": 3.6735, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.03267276525964e-05, + "loss": 3.6666, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.031834170508588e-05, + "loss": 3.6781, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.030995575757536e-05, + "loss": 3.6807, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.030156981006484e-05, + "loss": 3.6806, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.0293200241358056e-05, + "loss": 3.6851, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.0284814293847536e-05, + "loss": 3.6816, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.0276428346337016e-05, + "loss": 3.6898, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.0268042398826496e-05, + "loss": 3.6795, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.0259672830119705e-05, + "loss": 3.6793, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.0251286882609185e-05, + "loss": 3.6744, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.0242900935098665e-05, + "loss": 3.687, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.0234514987588145e-05, + "loss": 3.6771, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.0226145418881354e-05, + "loss": 3.6701, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.0217759471370834e-05, + "loss": 3.6795, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.020938990266404e-05, + "loss": 3.6826, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.020100395515353e-05, + "loss": 3.6709, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.019261800764301e-05, + "loss": 3.6659, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.018423206013249e-05, + "loss": 3.6695, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.017584611262197e-05, + "loss": 3.6704, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.016746016511145e-05, + "loss": 3.6769, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.015907421760093e-05, + "loss": 3.6844, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.015070464889414e-05, + "loss": 3.6882, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.014231870138362e-05, + "loss": 3.6611, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.01339327538731e-05, + "loss": 3.6863, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.012554680636258e-05, + "loss": 3.677, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.011716085885206e-05, + "loss": 3.6744, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.010877491134154e-05, + "loss": 3.6682, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.010038896383101e-05, + "loss": 3.6807, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.009200301632049e-05, + "loss": 3.6701, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.008363344761371e-05, + "loss": 3.6899, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.007524750010319e-05, + "loss": 3.6672, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.006686155259267e-05, + "loss": 3.676, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.0058491983885883e-05, + "loss": 3.6788, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.0050106036375363e-05, + "loss": 3.6776, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.0041720088864837e-05, + "loss": 3.6755, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.0033334141354317e-05, + "loss": 3.6766, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.0024948193843797e-05, + "loss": 3.6827, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.0016562246333276e-05, + "loss": 3.6687, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.0008176298822756e-05, + "loss": 3.6817, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.870403528213501, + "eval_runtime": 308.5135, + "eval_samples_per_second": 1236.87, + "eval_steps_per_second": 38.653, + "step": 610560 + }, + { + "epoch": 1.0, + "learning_rate": 3.9999790351312236e-05, + "loss": 3.6671, + "step": 610816 + }, + { + "epoch": 1.0, + "learning_rate": 3.9991420782605445e-05, + "loss": 3.6626, + "step": 611328 + }, + { + "epoch": 1.0, + "learning_rate": 3.998303483509493e-05, + "loss": 3.6734, + "step": 611840 + }, + { + "epoch": 1.0, + "learning_rate": 3.997464888758441e-05, + "loss": 3.6786, + "step": 612352 + }, + { + "epoch": 1.0, + "learning_rate": 3.996626294007389e-05, + "loss": 3.6858, + "step": 612864 + }, + { + "epoch": 1.0, + "learning_rate": 3.99578933713671e-05, + "loss": 3.6667, + "step": 613376 + }, + { + "epoch": 1.0, + "learning_rate": 3.994950742385658e-05, + "loss": 3.6776, + "step": 613888 + }, + { + "epoch": 1.0, + "learning_rate": 3.994112147634606e-05, + "loss": 3.664, + "step": 614400 + }, + { + "epoch": 1.0, + "learning_rate": 3.993273552883554e-05, + "loss": 3.6707, + "step": 614912 + }, + { + "epoch": 1.0, + "learning_rate": 3.992436596012875e-05, + "loss": 3.6712, + "step": 615424 + }, + { + "epoch": 1.0, + "learning_rate": 3.991598001261823e-05, + "loss": 3.6706, + "step": 615936 + }, + { + "epoch": 1.0, + "learning_rate": 3.990759406510771e-05, + "loss": 3.6732, + "step": 616448 + }, + { + "epoch": 1.0, + "learning_rate": 3.989922449640092e-05, + "loss": 3.6735, + "step": 616960 + }, + { + "epoch": 1.0, + "learning_rate": 3.98908385488904e-05, + "loss": 3.6629, + "step": 617472 + }, + { + "epoch": 1.0, + "learning_rate": 3.9882452601379886e-05, + "loss": 3.665, + "step": 617984 + }, + { + "epoch": 1.0, + "learning_rate": 3.9874066653869366e-05, + "loss": 3.6553, + "step": 618496 + }, + { + "epoch": 1.0, + "learning_rate": 3.9865680706358846e-05, + "loss": 3.665, + "step": 619008 + }, + { + "epoch": 1.0, + "learning_rate": 3.9857294758848326e-05, + "loss": 3.6767, + "step": 619520 + }, + { + "epoch": 1.0, + "learning_rate": 3.9848925190141535e-05, + "loss": 3.6638, + "step": 620032 + }, + { + "epoch": 1.0, + "learning_rate": 3.9840539242631015e-05, + "loss": 3.6803, + "step": 620544 + }, + { + "epoch": 1.0, + "learning_rate": 3.9832153295120495e-05, + "loss": 3.6819, + "step": 621056 + }, + { + "epoch": 1.0, + "learning_rate": 3.9823767347609975e-05, + "loss": 3.6796, + "step": 621568 + }, + { + "epoch": 1.0, + "learning_rate": 3.9815381400099455e-05, + "loss": 3.6764, + "step": 622080 + }, + { + "epoch": 1.0, + "learning_rate": 3.9806995452588935e-05, + "loss": 3.6667, + "step": 622592 + }, + { + "epoch": 1.0, + "learning_rate": 3.9798609505078415e-05, + "loss": 3.6671, + "step": 623104 + }, + { + "epoch": 1.0, + "learning_rate": 3.9790223557567895e-05, + "loss": 3.6758, + "step": 623616 + }, + { + "epoch": 1.0, + "learning_rate": 3.9781853988861104e-05, + "loss": 3.6728, + "step": 624128 + }, + { + "epoch": 1.0, + "learning_rate": 3.9773468041350584e-05, + "loss": 3.6662, + "step": 624640 + }, + { + "epoch": 1.0, + "learning_rate": 3.976508209384007e-05, + "loss": 3.6662, + "step": 625152 + }, + { + "epoch": 1.0, + "learning_rate": 3.975669614632955e-05, + "loss": 3.6653, + "step": 625664 + }, + { + "epoch": 1.01, + "learning_rate": 3.974832657762276e-05, + "loss": 3.66, + "step": 626176 + }, + { + "epoch": 1.01, + "learning_rate": 3.973994063011224e-05, + "loss": 3.6741, + "step": 626688 + }, + { + "epoch": 1.01, + "learning_rate": 3.973155468260172e-05, + "loss": 3.6729, + "step": 627200 + }, + { + "epoch": 1.01, + "learning_rate": 3.97231687350912e-05, + "loss": 3.6735, + "step": 627712 + }, + { + "epoch": 1.01, + "learning_rate": 3.971479916638441e-05, + "loss": 3.6633, + "step": 628224 + }, + { + "epoch": 1.01, + "learning_rate": 3.970641321887389e-05, + "loss": 3.6724, + "step": 628736 + }, + { + "epoch": 1.01, + "learning_rate": 3.969802727136337e-05, + "loss": 3.6691, + "step": 629248 + }, + { + "epoch": 1.01, + "learning_rate": 3.968964132385284e-05, + "loss": 3.6518, + "step": 629760 + }, + { + "epoch": 1.01, + "learning_rate": 3.968127175514606e-05, + "loss": 3.6606, + "step": 630272 + }, + { + "epoch": 1.01, + "learning_rate": 3.967288580763554e-05, + "loss": 3.6544, + "step": 630784 + }, + { + "epoch": 1.01, + "learning_rate": 3.9664499860125024e-05, + "loss": 3.6634, + "step": 631296 + }, + { + "epoch": 1.01, + "learning_rate": 3.96561139126145e-05, + "loss": 3.673, + "step": 631808 + }, + { + "epoch": 1.01, + "learning_rate": 3.964774434390771e-05, + "loss": 3.6663, + "step": 632320 + }, + { + "epoch": 1.01, + "learning_rate": 3.963935839639719e-05, + "loss": 3.6596, + "step": 632832 + }, + { + "epoch": 1.01, + "learning_rate": 3.963097244888667e-05, + "loss": 3.6718, + "step": 633344 + }, + { + "epoch": 1.01, + "learning_rate": 3.9622586501376146e-05, + "loss": 3.6632, + "step": 633856 + }, + { + "epoch": 1.01, + "learning_rate": 3.961421693266936e-05, + "loss": 3.6751, + "step": 634368 + }, + { + "epoch": 1.01, + "learning_rate": 3.960583098515884e-05, + "loss": 3.6652, + "step": 634880 + }, + { + "epoch": 1.01, + "learning_rate": 3.9597445037648315e-05, + "loss": 3.6403, + "step": 635392 + }, + { + "epoch": 1.01, + "learning_rate": 3.958907546894153e-05, + "loss": 3.6792, + "step": 635904 + }, + { + "epoch": 1.01, + "learning_rate": 3.958068952143101e-05, + "loss": 3.6571, + "step": 636416 + }, + { + "epoch": 1.01, + "learning_rate": 3.957230357392049e-05, + "loss": 3.6667, + "step": 636928 + }, + { + "epoch": 1.01, + "learning_rate": 3.956391762640997e-05, + "loss": 3.6595, + "step": 637440 + }, + { + "epoch": 1.01, + "learning_rate": 3.955554805770319e-05, + "loss": 3.6585, + "step": 637952 + }, + { + "epoch": 1.01, + "learning_rate": 3.954716211019267e-05, + "loss": 3.6503, + "step": 638464 + }, + { + "epoch": 1.01, + "learning_rate": 3.953877616268215e-05, + "loss": 3.6593, + "step": 638976 + }, + { + "epoch": 1.01, + "learning_rate": 3.953039021517162e-05, + "loss": 3.6767, + "step": 639488 + }, + { + "epoch": 1.01, + "learning_rate": 3.9522020646464836e-05, + "loss": 3.6497, + "step": 640000 + }, + { + "epoch": 1.01, + "learning_rate": 3.9513634698954316e-05, + "loss": 3.6715, + "step": 640512 + }, + { + "epoch": 1.01, + "learning_rate": 3.950524875144379e-05, + "loss": 3.6627, + "step": 641024 + }, + { + "epoch": 1.01, + "learning_rate": 3.949686280393327e-05, + "loss": 3.6447, + "step": 641536 + }, + { + "epoch": 1.01, + "learning_rate": 3.948847685642275e-05, + "loss": 3.6741, + "step": 642048 + }, + { + "epoch": 1.01, + "learning_rate": 3.948009090891223e-05, + "loss": 3.6522, + "step": 642560 + }, + { + "epoch": 1.01, + "learning_rate": 3.947170496140171e-05, + "loss": 3.6408, + "step": 643072 + }, + { + "epoch": 1.01, + "learning_rate": 3.9463319013891195e-05, + "loss": 3.6573, + "step": 643584 + }, + { + "epoch": 1.01, + "learning_rate": 3.9454949445184404e-05, + "loss": 3.6653, + "step": 644096 + }, + { + "epoch": 1.01, + "learning_rate": 3.9446563497673884e-05, + "loss": 3.6492, + "step": 644608 + }, + { + "epoch": 1.01, + "learning_rate": 3.9438177550163364e-05, + "loss": 3.6597, + "step": 645120 + }, + { + "epoch": 1.01, + "learning_rate": 3.9429791602652844e-05, + "loss": 3.6456, + "step": 645632 + }, + { + "epoch": 1.01, + "learning_rate": 3.9421422033946053e-05, + "loss": 3.65, + "step": 646144 + }, + { + "epoch": 1.01, + "learning_rate": 3.9413036086435533e-05, + "loss": 3.6625, + "step": 646656 + }, + { + "epoch": 1.01, + "learning_rate": 3.940465013892501e-05, + "loss": 3.6586, + "step": 647168 + }, + { + "epoch": 1.01, + "learning_rate": 3.939626419141449e-05, + "loss": 3.6638, + "step": 647680 + }, + { + "epoch": 1.01, + "learning_rate": 3.93878946227077e-05, + "loss": 3.6584, + "step": 648192 + }, + { + "epoch": 1.01, + "learning_rate": 3.937950867519718e-05, + "loss": 3.6707, + "step": 648704 + }, + { + "epoch": 1.01, + "learning_rate": 3.937112272768666e-05, + "loss": 3.6521, + "step": 649216 + }, + { + "epoch": 1.01, + "learning_rate": 3.936273678017615e-05, + "loss": 3.6631, + "step": 649728 + }, + { + "epoch": 1.01, + "learning_rate": 3.935436721146936e-05, + "loss": 3.6509, + "step": 650240 + }, + { + "epoch": 1.01, + "learning_rate": 3.934598126395884e-05, + "loss": 3.6474, + "step": 650752 + }, + { + "epoch": 1.01, + "learning_rate": 3.933761169525205e-05, + "loss": 3.661, + "step": 651264 + }, + { + "epoch": 1.01, + "learning_rate": 3.932922574774153e-05, + "loss": 3.654, + "step": 651776 + }, + { + "epoch": 1.01, + "learning_rate": 3.932083980023101e-05, + "loss": 3.6652, + "step": 652288 + }, + { + "epoch": 1.01, + "learning_rate": 3.931245385272049e-05, + "loss": 3.6689, + "step": 652800 + }, + { + "epoch": 1.01, + "learning_rate": 3.930406790520997e-05, + "loss": 3.641, + "step": 653312 + }, + { + "epoch": 1.01, + "learning_rate": 3.929568195769945e-05, + "loss": 3.6435, + "step": 653824 + }, + { + "epoch": 1.01, + "learning_rate": 3.928729601018893e-05, + "loss": 3.6576, + "step": 654336 + }, + { + "epoch": 1.01, + "learning_rate": 3.9278926441482136e-05, + "loss": 3.6613, + "step": 654848 + }, + { + "epoch": 1.01, + "learning_rate": 3.9270540493971616e-05, + "loss": 3.6587, + "step": 655360 + }, + { + "epoch": 1.01, + "learning_rate": 3.92621545464611e-05, + "loss": 3.6494, + "step": 655872 + }, + { + "epoch": 1.02, + "learning_rate": 3.925376859895058e-05, + "loss": 3.6594, + "step": 656384 + }, + { + "epoch": 1.02, + "learning_rate": 3.924538265144006e-05, + "loss": 3.6533, + "step": 656896 + }, + { + "epoch": 1.02, + "learning_rate": 3.923699670392954e-05, + "loss": 3.651, + "step": 657408 + }, + { + "epoch": 1.02, + "learning_rate": 3.922861075641902e-05, + "loss": 3.6497, + "step": 657920 + }, + { + "epoch": 1.02, + "learning_rate": 3.92202248089085e-05, + "loss": 3.6588, + "step": 658432 + }, + { + "epoch": 1.02, + "learning_rate": 3.921187161900544e-05, + "loss": 3.6648, + "step": 658944 + }, + { + "epoch": 1.02, + "learning_rate": 3.920348567149492e-05, + "loss": 3.6611, + "step": 659456 + }, + { + "epoch": 1.02, + "learning_rate": 3.91950997239844e-05, + "loss": 3.6443, + "step": 659968 + }, + { + "epoch": 1.02, + "learning_rate": 3.918671377647388e-05, + "loss": 3.653, + "step": 660480 + }, + { + "epoch": 1.02, + "learning_rate": 3.917832782896336e-05, + "loss": 3.6473, + "step": 660992 + }, + { + "epoch": 1.02, + "learning_rate": 3.916994188145284e-05, + "loss": 3.6545, + "step": 661504 + }, + { + "epoch": 1.02, + "learning_rate": 3.916155593394232e-05, + "loss": 3.6553, + "step": 662016 + }, + { + "epoch": 1.02, + "learning_rate": 3.91531699864318e-05, + "loss": 3.6484, + "step": 662528 + }, + { + "epoch": 1.02, + "learning_rate": 3.9144800417725016e-05, + "loss": 3.6524, + "step": 663040 + }, + { + "epoch": 1.02, + "learning_rate": 3.9136414470214496e-05, + "loss": 3.6432, + "step": 663552 + }, + { + "epoch": 1.02, + "learning_rate": 3.9128028522703976e-05, + "loss": 3.6496, + "step": 664064 + }, + { + "epoch": 1.02, + "learning_rate": 3.911964257519345e-05, + "loss": 3.6399, + "step": 664576 + }, + { + "epoch": 1.02, + "learning_rate": 3.9111273006486665e-05, + "loss": 3.6513, + "step": 665088 + }, + { + "epoch": 1.02, + "learning_rate": 3.9102887058976145e-05, + "loss": 3.6501, + "step": 665600 + }, + { + "epoch": 1.02, + "learning_rate": 3.9094501111465625e-05, + "loss": 3.6566, + "step": 666112 + }, + { + "epoch": 1.02, + "learning_rate": 3.90861151639551e-05, + "loss": 3.6438, + "step": 666624 + }, + { + "epoch": 1.02, + "learning_rate": 3.9077745595248314e-05, + "loss": 3.6438, + "step": 667136 + }, + { + "epoch": 1.02, + "learning_rate": 3.9069359647737794e-05, + "loss": 3.6474, + "step": 667648 + }, + { + "epoch": 1.02, + "learning_rate": 3.9060973700227274e-05, + "loss": 3.657, + "step": 668160 + }, + { + "epoch": 1.02, + "learning_rate": 3.9052587752716754e-05, + "loss": 3.6516, + "step": 668672 + }, + { + "epoch": 1.02, + "learning_rate": 3.904421818400997e-05, + "loss": 3.653, + "step": 669184 + }, + { + "epoch": 1.02, + "learning_rate": 3.903583223649945e-05, + "loss": 3.6545, + "step": 669696 + }, + { + "epoch": 1.02, + "learning_rate": 3.902744628898892e-05, + "loss": 3.6652, + "step": 670208 + }, + { + "epoch": 1.02, + "learning_rate": 3.90190603414784e-05, + "loss": 3.651, + "step": 670720 + }, + { + "epoch": 1.02, + "learning_rate": 3.901069077277162e-05, + "loss": 3.6522, + "step": 671232 + }, + { + "epoch": 1.02, + "learning_rate": 3.90023048252611e-05, + "loss": 3.6501, + "step": 671744 + }, + { + "epoch": 1.02, + "learning_rate": 3.899391887775057e-05, + "loss": 3.6567, + "step": 672256 + }, + { + "epoch": 1.02, + "learning_rate": 3.898553293024005e-05, + "loss": 3.6502, + "step": 672768 + }, + { + "epoch": 1.02, + "learning_rate": 3.897716336153327e-05, + "loss": 3.6446, + "step": 673280 + }, + { + "epoch": 1.02, + "learning_rate": 3.896877741402275e-05, + "loss": 3.6506, + "step": 673792 + }, + { + "epoch": 1.02, + "learning_rate": 3.8960407845315964e-05, + "loss": 3.6554, + "step": 674304 + }, + { + "epoch": 1.02, + "learning_rate": 3.8952021897805444e-05, + "loss": 3.6464, + "step": 674816 + }, + { + "epoch": 1.02, + "learning_rate": 3.8943635950294924e-05, + "loss": 3.637, + "step": 675328 + }, + { + "epoch": 1.02, + "learning_rate": 3.89352500027844e-05, + "loss": 3.6426, + "step": 675840 + }, + { + "epoch": 1.02, + "learning_rate": 3.892686405527388e-05, + "loss": 3.6408, + "step": 676352 + }, + { + "epoch": 1.02, + "learning_rate": 3.891849448656709e-05, + "loss": 3.6522, + "step": 676864 + }, + { + "epoch": 1.02, + "learning_rate": 3.891010853905657e-05, + "loss": 3.6553, + "step": 677376 + }, + { + "epoch": 1.02, + "learning_rate": 3.8901722591546046e-05, + "loss": 3.662, + "step": 677888 + }, + { + "epoch": 1.02, + "learning_rate": 3.8893336644035526e-05, + "loss": 3.6354, + "step": 678400 + }, + { + "epoch": 1.02, + "learning_rate": 3.8884950696525006e-05, + "loss": 3.6591, + "step": 678912 + }, + { + "epoch": 1.02, + "learning_rate": 3.8876564749014486e-05, + "loss": 3.6515, + "step": 679424 + }, + { + "epoch": 1.02, + "learning_rate": 3.8868178801503966e-05, + "loss": 3.6493, + "step": 679936 + }, + { + "epoch": 1.02, + "learning_rate": 3.8859792853993446e-05, + "loss": 3.6431, + "step": 680448 + }, + { + "epoch": 1.02, + "learning_rate": 3.885142328528666e-05, + "loss": 3.6481, + "step": 680960 + }, + { + "epoch": 1.02, + "learning_rate": 3.884303733777614e-05, + "loss": 3.6446, + "step": 681472 + }, + { + "epoch": 1.02, + "learning_rate": 3.883465139026562e-05, + "loss": 3.6625, + "step": 681984 + }, + { + "epoch": 1.02, + "learning_rate": 3.88262654427551e-05, + "loss": 3.6395, + "step": 682496 + }, + { + "epoch": 1.02, + "learning_rate": 3.881789587404831e-05, + "loss": 3.6525, + "step": 683008 + }, + { + "epoch": 1.02, + "learning_rate": 3.880950992653779e-05, + "loss": 3.6545, + "step": 683520 + }, + { + "epoch": 1.02, + "learning_rate": 3.8801140357831e-05, + "loss": 3.6539, + "step": 684032 + }, + { + "epoch": 1.02, + "learning_rate": 3.879275441032048e-05, + "loss": 3.6431, + "step": 684544 + }, + { + "epoch": 1.02, + "learning_rate": 3.878436846280996e-05, + "loss": 3.6533, + "step": 685056 + }, + { + "epoch": 1.02, + "learning_rate": 3.877598251529944e-05, + "loss": 3.6545, + "step": 685568 + }, + { + "epoch": 1.02, + "learning_rate": 3.8767612946592655e-05, + "loss": 3.6426, + "step": 686080 + }, + { + "epoch": 1.02, + "learning_rate": 3.8759226999082135e-05, + "loss": 3.6543, + "step": 686592 + }, + { + "epoch": 1.03, + "eval_loss": 3.865609884262085, + "eval_runtime": 303.5349, + "eval_samples_per_second": 1257.157, + "eval_steps_per_second": 39.287, + "step": 686880 + }, + { + "epoch": 0.0, + "learning_rate": 3.8750841051571615e-05, + "loss": 3.6435, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.8742455104061095e-05, + "loss": 3.6321, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.8734069156550575e-05, + "loss": 3.6458, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.8725683209040055e-05, + "loss": 3.6545, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.8717297261529535e-05, + "loss": 3.6579, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.8708911314019015e-05, + "loss": 3.6422, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.8700525366508495e-05, + "loss": 3.6507, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.8692139418997975e-05, + "loss": 3.6343, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.8683769850291184e-05, + "loss": 3.6456, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.8675383902780664e-05, + "loss": 3.6445, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.8666997955270144e-05, + "loss": 3.6441, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.8658612007759624e-05, + "loss": 3.6486, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.865025881785657e-05, + "loss": 3.6534, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.864187287034605e-05, + "loss": 3.6349, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.863348692283553e-05, + "loss": 3.6374, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.862510097532501e-05, + "loss": 3.6239, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.861673140661822e-05, + "loss": 3.644, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.86083454591077e-05, + "loss": 3.6505, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.859995951159718e-05, + "loss": 3.6373, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.859157356408666e-05, + "loss": 3.6529, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.858318761657614e-05, + "loss": 3.6578, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.857480166906562e-05, + "loss": 3.6514, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.85664157215551e-05, + "loss": 3.6481, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.8558046152848307e-05, + "loss": 3.6421, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.8549660205337787e-05, + "loss": 3.6453, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.854127425782727e-05, + "loss": 3.6458, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.853288831031675e-05, + "loss": 3.6489, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.852450236280623e-05, + "loss": 3.6474, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.8516116415295706e-05, + "loss": 3.6368, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.8507730467785186e-05, + "loss": 3.6352, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.84993608990784e-05, + "loss": 3.6366, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.849097495156788e-05, + "loss": 3.6489, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.848260538286109e-05, + "loss": 3.6504, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.847421943535057e-05, + "loss": 3.6479, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.846583348784005e-05, + "loss": 3.6382, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.8457447540329524e-05, + "loss": 3.6402, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.844906159281901e-05, + "loss": 3.6471, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.844067564530849e-05, + "loss": 3.631, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.843228969779797e-05, + "loss": 3.6333, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.842390375028745e-05, + "loss": 3.6337, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.841553418158066e-05, + "loss": 3.6365, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.840714823407014e-05, + "loss": 3.6462, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.839876228655962e-05, + "loss": 3.6431, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.83903763390491e-05, + "loss": 3.6343, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.8382023149146045e-05, + "loss": 3.6464, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.8373637201635525e-05, + "loss": 3.6362, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.8365251254125e-05, + "loss": 3.6459, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.835686530661448e-05, + "loss": 3.6469, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.8348495737907694e-05, + "loss": 3.6151, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.834010979039718e-05, + "loss": 3.6481, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.8331723842886654e-05, + "loss": 3.634, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.8323337895376134e-05, + "loss": 3.6406, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.8314951947865614e-05, + "loss": 3.6363, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.830658237915883e-05, + "loss": 3.6299, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.82981964316483e-05, + "loss": 3.6284, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.828981048413778e-05, + "loss": 3.6305, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.828142453662726e-05, + "loss": 3.6513, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.827305496792047e-05, + "loss": 3.6248, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.826466902040995e-05, + "loss": 3.6473, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.825628307289943e-05, + "loss": 3.6376, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.824789712538892e-05, + "loss": 3.621, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.82395111778784e-05, + "loss": 3.6456, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.823114160917161e-05, + "loss": 3.6264, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.822275566166109e-05, + "loss": 3.6176, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.821436971415057e-05, + "loss": 3.6278, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.820598376664005e-05, + "loss": 3.643, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.819759781912953e-05, + "loss": 3.6209, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.818921187161901e-05, + "loss": 3.6392, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.818082592410849e-05, + "loss": 3.6226, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.817243997659797e-05, + "loss": 3.6232, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.8164070407891176e-05, + "loss": 3.6359, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.8155684460380656e-05, + "loss": 3.6348, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.8147298512870136e-05, + "loss": 3.639, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.8138912565359616e-05, + "loss": 3.6367, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.813054299665283e-05, + "loss": 3.6421, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.812215704914231e-05, + "loss": 3.6321, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.811377110163179e-05, + "loss": 3.6377, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.810538515412127e-05, + "loss": 3.6219, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.809701558541448e-05, + "loss": 3.6262, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.808864601670769e-05, + "loss": 3.6353, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.808026006919717e-05, + "loss": 3.6253, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.807187412168665e-05, + "loss": 3.6407, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.806348817417613e-05, + "loss": 3.6418, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.805510222666561e-05, + "loss": 3.6233, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.804671627915509e-05, + "loss": 3.6197, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.803833033164457e-05, + "loss": 3.6329, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.8029960762937786e-05, + "loss": 3.6374, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.8021574815427266e-05, + "loss": 3.6356, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.8013188867916746e-05, + "loss": 3.6229, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.8004802920406225e-05, + "loss": 3.6367, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.7996416972895705e-05, + "loss": 3.6266, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.7988047404188915e-05, + "loss": 3.6269, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.7979661456678394e-05, + "loss": 3.625, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.7971275509167874e-05, + "loss": 3.6315, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.7962889561657354e-05, + "loss": 3.6394, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.7954503614146834e-05, + "loss": 3.6379, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.794611766663631e-05, + "loss": 3.618, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.793773171912579e-05, + "loss": 3.63, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.7929345771615274e-05, + "loss": 3.62, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.792097620290849e-05, + "loss": 3.6342, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.791259025539796e-05, + "loss": 3.6311, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.790420430788744e-05, + "loss": 3.6267, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.789581836037692e-05, + "loss": 3.6296, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.788744879167013e-05, + "loss": 3.6194, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.787906284415961e-05, + "loss": 3.6247, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.787069327545283e-05, + "loss": 3.6186, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.786230732794231e-05, + "loss": 3.6264, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.785392138043178e-05, + "loss": 3.628, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.784553543292126e-05, + "loss": 3.6286, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.783714948541074e-05, + "loss": 3.6204, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.782876353790023e-05, + "loss": 3.6197, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.782039396919344e-05, + "loss": 3.6226, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.781200802168292e-05, + "loss": 3.6345, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.78036220741724e-05, + "loss": 3.6295, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.779523612666188e-05, + "loss": 3.6281, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.778685017915136e-05, + "loss": 3.6303, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.777846423164084e-05, + "loss": 3.6402, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.7770094662934046e-05, + "loss": 3.627, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.7761708715423526e-05, + "loss": 3.63, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.7753322767913006e-05, + "loss": 3.6265, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.7744936820402486e-05, + "loss": 3.6326, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.7736550872891966e-05, + "loss": 3.6307, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.7728164925381446e-05, + "loss": 3.6216, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.7719778977870926e-05, + "loss": 3.6217, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.771140940916414e-05, + "loss": 3.6318, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.770302346165362e-05, + "loss": 3.6204, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.76946375141431e-05, + "loss": 3.6161, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.768625156663258e-05, + "loss": 3.6175, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.767786561912206e-05, + "loss": 3.6146, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.766949605041527e-05, + "loss": 3.6344, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.766111010290475e-05, + "loss": 3.6258, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.765272415539423e-05, + "loss": 3.6387, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.764433820788371e-05, + "loss": 3.6156, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.763595226037319e-05, + "loss": 3.6316, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.762756631286267e-05, + "loss": 3.626, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.761918036535215e-05, + "loss": 3.627, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.761079441784163e-05, + "loss": 3.6208, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.7602424849134846e-05, + "loss": 3.6226, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.7594038901624326e-05, + "loss": 3.6199, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.75856529541138e-05, + "loss": 3.6415, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.757726700660328e-05, + "loss": 3.6156, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.7568897437896495e-05, + "loss": 3.6282, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.756051149038597e-05, + "loss": 3.6339, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.7552141921679184e-05, + "loss": 3.6256, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.7543755974168664e-05, + "loss": 3.6206, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.7535370026658144e-05, + "loss": 3.6293, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.752698407914762e-05, + "loss": 3.6311, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.751861451044083e-05, + "loss": 3.6236, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.751022856293032e-05, + "loss": 3.6302, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 3.864367723464966, + "eval_runtime": 308.893, + "eval_samples_per_second": 1235.35, + "eval_steps_per_second": 38.606, + "step": 763200 + }, + { + "epoch": 1.0, + "learning_rate": 3.750184261541979e-05, + "loss": 3.6164, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.749345666790927e-05, + "loss": 3.6101, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.748507072039875e-05, + "loss": 3.6235, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.747668477288823e-05, + "loss": 3.6305, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.746831520418144e-05, + "loss": 3.6355, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.745992925667092e-05, + "loss": 3.6186, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.74515433091604e-05, + "loss": 3.627, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.744315736164988e-05, + "loss": 3.6161, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.743477141413936e-05, + "loss": 3.6207, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.742638546662884e-05, + "loss": 3.6219, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.741799951911832e-05, + "loss": 3.6192, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.740962995041154e-05, + "loss": 3.6268, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.7401260381704747e-05, + "loss": 3.6277, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.7392874434194226e-05, + "loss": 3.6119, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.7384488486683706e-05, + "loss": 3.6154, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.7376102539173186e-05, + "loss": 3.6031, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.7367732970466395e-05, + "loss": 3.6238, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.7359347022955875e-05, + "loss": 3.6246, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.7350961075445355e-05, + "loss": 3.6135, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.7342575127934835e-05, + "loss": 3.6236, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.7334189180424315e-05, + "loss": 3.6398, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.7325819611717524e-05, + "loss": 3.6298, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.7317433664207004e-05, + "loss": 3.6247, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.730904771669649e-05, + "loss": 3.6182, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.730066176918597e-05, + "loss": 3.625, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.729227582167545e-05, + "loss": 3.6203, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.728388987416493e-05, + "loss": 3.6202, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.727550392665441e-05, + "loss": 3.6252, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.726711797914389e-05, + "loss": 3.6154, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.72587484104371e-05, + "loss": 3.6136, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.725036246292658e-05, + "loss": 3.6143, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.724197651541606e-05, + "loss": 3.6255, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.723359056790554e-05, + "loss": 3.6242, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.722522099919875e-05, + "loss": 3.6281, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.721683505168823e-05, + "loss": 3.619, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.720844910417771e-05, + "loss": 3.6173, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.720006315666719e-05, + "loss": 3.6237, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.7191677209156676e-05, + "loss": 3.6109, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.7183291261646155e-05, + "loss": 3.6113, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.7174921692939365e-05, + "loss": 3.6101, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.7166535745428845e-05, + "loss": 3.6106, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.7158149797918324e-05, + "loss": 3.6208, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.7149763850407804e-05, + "loss": 3.6194, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.714137790289728e-05, + "loss": 3.6176, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.7133008334190493e-05, + "loss": 3.6173, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.7124622386679973e-05, + "loss": 3.6171, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.7116236439169453e-05, + "loss": 3.6244, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.7107850491658927e-05, + "loss": 3.6235, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.709948092295214e-05, + "loss": 3.5919, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.709109497544163e-05, + "loss": 3.6254, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.70827090279311e-05, + "loss": 3.6113, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.707432308042058e-05, + "loss": 3.6191, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.706593713291006e-05, + "loss": 3.6172, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.705756756420328e-05, + "loss": 3.6038, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.704918161669275e-05, + "loss": 3.6087, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.704079566918223e-05, + "loss": 3.6046, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.703240972167171e-05, + "loss": 3.6253, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.702404015296493e-05, + "loss": 3.6068, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.70156542054544e-05, + "loss": 3.6213, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.700726825794388e-05, + "loss": 3.6171, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.699888231043337e-05, + "loss": 3.6037, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.699049636292285e-05, + "loss": 3.6208, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.6982126794216056e-05, + "loss": 3.6029, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.6973740846705536e-05, + "loss": 3.5991, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.6965354899195016e-05, + "loss": 3.603, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.6956968951684496e-05, + "loss": 3.6206, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.6948583004173976e-05, + "loss": 3.5985, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.6940197056663456e-05, + "loss": 3.6193, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.6931811109152936e-05, + "loss": 3.5957, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.6923441540446145e-05, + "loss": 3.6038, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.6915055592935625e-05, + "loss": 3.6129, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.6906669645425105e-05, + "loss": 3.6122, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.6898283697914585e-05, + "loss": 3.6168, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.6889897750404065e-05, + "loss": 3.6163, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.6881511802893545e-05, + "loss": 3.622, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.687314223418676e-05, + "loss": 3.6048, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.686475628667624e-05, + "loss": 3.6164, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.685637033916572e-05, + "loss": 3.6023, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.68479843916552e-05, + "loss": 3.6057, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.683961482294841e-05, + "loss": 3.6099, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.683122887543789e-05, + "loss": 3.6037, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.682284292792737e-05, + "loss": 3.6185, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.681445698041685e-05, + "loss": 3.6208, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.680607103290633e-05, + "loss": 3.6079, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.679768508539581e-05, + "loss": 3.5912, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.678931551668902e-05, + "loss": 3.613, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.67809295691785e-05, + "loss": 3.6123, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.6772543621667985e-05, + "loss": 3.6199, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.6764157674157465e-05, + "loss": 3.5967, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.675577172664694e-05, + "loss": 3.6148, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.674738577913642e-05, + "loss": 3.6068, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.6739016210429634e-05, + "loss": 3.6037, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.6730630262919114e-05, + "loss": 3.6019, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.672224431540859e-05, + "loss": 3.6115, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.671385836789807e-05, + "loss": 3.6136, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.670548879919128e-05, + "loss": 3.6177, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.6697102851680756e-05, + "loss": 3.5987, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.6688716904170236e-05, + "loss": 3.6073, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.668033095665972e-05, + "loss": 3.6007, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.66719450091492e-05, + "loss": 3.6112, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.666357544044241e-05, + "loss": 3.6074, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.665518949293189e-05, + "loss": 3.6056, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.664680354542137e-05, + "loss": 3.6038, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.663841759791085e-05, + "loss": 3.5973, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.663003165040033e-05, + "loss": 3.6074, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.662166208169354e-05, + "loss": 3.5917, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.661327613418302e-05, + "loss": 3.6029, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.66048901866725e-05, + "loss": 3.6036, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.659650423916198e-05, + "loss": 3.6132, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.658811829165146e-05, + "loss": 3.597, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.657973234414094e-05, + "loss": 3.601, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.6571362775434156e-05, + "loss": 3.6008, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.6562976827923636e-05, + "loss": 3.6132, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.6554590880413116e-05, + "loss": 3.6087, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.6546204932902596e-05, + "loss": 3.6068, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.6537835364195805e-05, + "loss": 3.6111, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.6529449416685285e-05, + "loss": 3.617, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.6521063469174765e-05, + "loss": 3.605, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.6512677521664245e-05, + "loss": 3.609, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.6504291574153725e-05, + "loss": 3.6057, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.6495922005446934e-05, + "loss": 3.6113, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.6487536057936414e-05, + "loss": 3.6058, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.6479150110425894e-05, + "loss": 3.6003, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.6470764162915374e-05, + "loss": 3.6012, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.646239459420859e-05, + "loss": 3.6108, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.645400864669807e-05, + "loss": 3.5979, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.644562269918755e-05, + "loss": 3.5996, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.643723675167703e-05, + "loss": 3.5896, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.642886718297024e-05, + "loss": 3.5976, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.642048123545972e-05, + "loss": 3.6099, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.64120952879492e-05, + "loss": 3.6081, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.640370934043868e-05, + "loss": 3.6212, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.639532339292816e-05, + "loss": 3.5925, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.638693744541764e-05, + "loss": 3.6111, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.637855149790712e-05, + "loss": 3.6034, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.637018192920033e-05, + "loss": 3.6068, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.6361795981689815e-05, + "loss": 3.5976, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.6353410034179295e-05, + "loss": 3.5999, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.6345024086668775e-05, + "loss": 3.6031, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.6336654517961984e-05, + "loss": 3.6196, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.6328268570451464e-05, + "loss": 3.5925, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.6319882622940944e-05, + "loss": 3.6084, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.631149667543042e-05, + "loss": 3.6097, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.630312710672363e-05, + "loss": 3.6045, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.629474115921311e-05, + "loss": 3.6011, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.628635521170259e-05, + "loss": 3.6092, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.6277969264192066e-05, + "loss": 3.6064, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.626959969548528e-05, + "loss": 3.6053, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.626121374797477e-05, + "loss": 3.6039, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 3.861919403076172, + "eval_runtime": 301.9684, + "eval_samples_per_second": 1263.679, + "eval_steps_per_second": 39.491, + "step": 839520 + }, + { + "epoch": 0.0, + "learning_rate": 3.625282780046425e-05, + "loss": 3.5901, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.624444185295372e-05, + "loss": 3.5908, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.62360559054432e-05, + "loss": 3.6035, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.622766995793268e-05, + "loss": 3.6075, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.621930038922589e-05, + "loss": 3.6155, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.621091444171537e-05, + "loss": 3.5981, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.620252849420485e-05, + "loss": 3.6088, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.619414254669433e-05, + "loss": 3.5954, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.618577297798754e-05, + "loss": 3.5972, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.617738703047702e-05, + "loss": 3.5974, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.6169001082966506e-05, + "loss": 3.6019, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.6160615135455986e-05, + "loss": 3.6033, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.6152245566749195e-05, + "loss": 3.6087, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.6143859619238675e-05, + "loss": 3.592, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.6135473671728155e-05, + "loss": 3.593, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.6127087724217635e-05, + "loss": 3.5814, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.6118701776707115e-05, + "loss": 3.6012, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.6110315829196595e-05, + "loss": 3.6034, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.6101929881686075e-05, + "loss": 3.5914, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.6093543934175555e-05, + "loss": 3.6051, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.6085157986665035e-05, + "loss": 3.6191, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.6076788417958244e-05, + "loss": 3.6077, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.6068402470447724e-05, + "loss": 3.6031, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.6060016522937204e-05, + "loss": 3.5989, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.6051630575426684e-05, + "loss": 3.6044, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.604324462791617e-05, + "loss": 3.6032, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.603485868040565e-05, + "loss": 3.5992, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.602647273289513e-05, + "loss": 3.601, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.601810316418834e-05, + "loss": 3.5972, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.600973359548155e-05, + "loss": 3.5917, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.600134764797103e-05, + "loss": 3.5996, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.599296170046051e-05, + "loss": 3.598, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.598457575294999e-05, + "loss": 3.6041, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.597618980543947e-05, + "loss": 3.6079, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.596782023673268e-05, + "loss": 3.5977, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.595943428922216e-05, + "loss": 3.5955, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.595104834171164e-05, + "loss": 3.6052, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.5942662394201124e-05, + "loss": 3.5894, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.5934276446690604e-05, + "loss": 3.5926, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.592590687798381e-05, + "loss": 3.5877, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.591752093047329e-05, + "loss": 3.5947, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.590913498296277e-05, + "loss": 3.5954, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.590074903545225e-05, + "loss": 3.599, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.589237946674546e-05, + "loss": 3.6006, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.588399351923494e-05, + "loss": 3.5956, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.587560757172442e-05, + "loss": 3.601, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.58672216242139e-05, + "loss": 3.6017, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.585885205550711e-05, + "loss": 3.605, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.585046610799659e-05, + "loss": 3.5737, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.584208016048608e-05, + "loss": 3.6053, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.583369421297556e-05, + "loss": 3.5885, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.582530826546503e-05, + "loss": 3.5976, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.581692231795451e-05, + "loss": 3.5941, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.580855274924773e-05, + "loss": 3.5884, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.58001668017372e-05, + "loss": 3.5842, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.579178085422668e-05, + "loss": 3.5829, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.578339490671616e-05, + "loss": 3.6107, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.5775025338009376e-05, + "loss": 3.5829, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.576663939049885e-05, + "loss": 3.6023, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.575825344298833e-05, + "loss": 3.5937, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.5749867495477816e-05, + "loss": 3.5843, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.5741481547967296e-05, + "loss": 3.6008, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.5733111979260505e-05, + "loss": 3.5863, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.5724726031749985e-05, + "loss": 3.576, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.5716340084239465e-05, + "loss": 3.5848, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.5707954136728944e-05, + "loss": 3.6015, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.5699584568022154e-05, + "loss": 3.5807, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.5691198620511634e-05, + "loss": 3.6005, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.5682812673001114e-05, + "loss": 3.5731, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.5674426725490593e-05, + "loss": 3.5854, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.56660571567838e-05, + "loss": 3.5935, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.565767120927328e-05, + "loss": 3.5935, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.564928526176277e-05, + "loss": 3.5933, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.564089931425225e-05, + "loss": 3.5964, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.563251336674173e-05, + "loss": 3.6008, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.562414379803494e-05, + "loss": 3.5869, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.561575785052442e-05, + "loss": 3.5936, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.56073719030139e-05, + "loss": 3.5856, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.559898595550338e-05, + "loss": 3.5881, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.559060000799286e-05, + "loss": 3.5873, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.558223043928607e-05, + "loss": 3.5869, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.557384449177555e-05, + "loss": 3.5973, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.556545854426503e-05, + "loss": 3.5994, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.555707259675451e-05, + "loss": 3.5897, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.554868664924399e-05, + "loss": 3.5696, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.554030070173347e-05, + "loss": 3.5927, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.553193113302668e-05, + "loss": 3.5946, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.552354518551616e-05, + "loss": 3.601, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.551515923800564e-05, + "loss": 3.5779, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.550677329049512e-05, + "loss": 3.5904, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.54983873429846e-05, + "loss": 3.5944, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.549001777427781e-05, + "loss": 3.5812, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.548163182676729e-05, + "loss": 3.5803, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.547324587925677e-05, + "loss": 3.5937, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.546485993174625e-05, + "loss": 3.5917, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.545649036303946e-05, + "loss": 3.6, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.544810441552894e-05, + "loss": 3.5819, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.543971846801842e-05, + "loss": 3.584, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.54313325205079e-05, + "loss": 3.5805, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.542294657299739e-05, + "loss": 3.5933, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.5414577004290596e-05, + "loss": 3.5913, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.5406191056780076e-05, + "loss": 3.5849, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.5397805109269556e-05, + "loss": 3.583, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.5389419161759036e-05, + "loss": 3.5807, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.538103321424851e-05, + "loss": 3.587, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.5372663645541725e-05, + "loss": 3.5726, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.5364277698031205e-05, + "loss": 3.5853, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.5355891750520685e-05, + "loss": 3.5813, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.534750580301016e-05, + "loss": 3.5907, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.533911985549964e-05, + "loss": 3.5812, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.5330750286792854e-05, + "loss": 3.5888, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.5322364339282334e-05, + "loss": 3.5774, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.5313978391771814e-05, + "loss": 3.5948, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.5305592444261294e-05, + "loss": 3.5861, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.529722287555451e-05, + "loss": 3.5891, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.528883692804398e-05, + "loss": 3.587, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.528045098053346e-05, + "loss": 3.6031, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.527206503302294e-05, + "loss": 3.5837, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.526369546431616e-05, + "loss": 3.5895, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.525530951680563e-05, + "loss": 3.5882, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.524692356929511e-05, + "loss": 3.5898, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.523853762178459e-05, + "loss": 3.5848, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.523015167427408e-05, + "loss": 3.5852, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.522176572676356e-05, + "loss": 3.581, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.521339615805677e-05, + "loss": 3.589, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.520501021054625e-05, + "loss": 3.5766, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.519662426303573e-05, + "loss": 3.5802, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.518823831552521e-05, + "loss": 3.5728, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.517986874681842e-05, + "loss": 3.5836, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.51714827993079e-05, + "loss": 3.5889, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.516309685179738e-05, + "loss": 3.5873, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.515471090428686e-05, + "loss": 3.6011, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.5146341335580066e-05, + "loss": 3.5767, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.5137955388069546e-05, + "loss": 3.5866, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.512956944055903e-05, + "loss": 3.5899, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.512118349304851e-05, + "loss": 3.5873, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.511279754553799e-05, + "loss": 3.5789, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.510441159802747e-05, + "loss": 3.5763, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.509602565051695e-05, + "loss": 3.5872, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.508765608181016e-05, + "loss": 3.594, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.507927013429964e-05, + "loss": 3.5801, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.507088418678912e-05, + "loss": 3.5885, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.50624982392786e-05, + "loss": 3.5904, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.505412867057181e-05, + "loss": 3.5852, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.504574272306129e-05, + "loss": 3.5843, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.503735677555077e-05, + "loss": 3.5881, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.502897082804025e-05, + "loss": 3.587, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.5020601259333466e-05, + "loss": 3.5846, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.5012215311822946e-05, + "loss": 3.5885, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 3.862126350402832, + "eval_runtime": 304.3076, + "eval_samples_per_second": 1253.965, + "eval_steps_per_second": 39.187, + "step": 915840 + }, + { + "epoch": 1.0, + "learning_rate": 3.5003829364312426e-05, + "loss": 3.5815, + "step": 915968 + }, + { + "epoch": 1.0, + "learning_rate": 3.4995443416801906e-05, + "loss": 3.5677, + "step": 916480 + }, + { + "epoch": 1.0, + "learning_rate": 3.4987057469291386e-05, + "loss": 3.5849, + "step": 916992 + }, + { + "epoch": 1.0, + "learning_rate": 3.4978687900584595e-05, + "loss": 3.5898, + "step": 917504 + }, + { + "epoch": 1.0, + "learning_rate": 3.4970301953074075e-05, + "loss": 3.5919, + "step": 918016 + }, + { + "epoch": 1.0, + "learning_rate": 3.4961916005563555e-05, + "loss": 3.5819, + "step": 918528 + }, + { + "epoch": 1.0, + "learning_rate": 3.4953530058053035e-05, + "loss": 3.5853, + "step": 919040 + }, + { + "epoch": 1.0, + "learning_rate": 3.4945144110542515e-05, + "loss": 3.5789, + "step": 919552 + }, + { + "epoch": 1.0, + "learning_rate": 3.4936774541835724e-05, + "loss": 3.5774, + "step": 920064 + }, + { + "epoch": 1.0, + "learning_rate": 3.4928388594325204e-05, + "loss": 3.5794, + "step": 920576 + }, + { + "epoch": 1.0, + "learning_rate": 3.4920002646814684e-05, + "loss": 3.5844, + "step": 921088 + }, + { + "epoch": 1.0, + "learning_rate": 3.4911616699304164e-05, + "loss": 3.582, + "step": 921600 + }, + { + "epoch": 1.0, + "learning_rate": 3.4903230751793644e-05, + "loss": 3.5919, + "step": 922112 + }, + { + "epoch": 1.0, + "learning_rate": 3.489486118308686e-05, + "loss": 3.57, + "step": 922624 + }, + { + "epoch": 1.0, + "learning_rate": 3.488647523557634e-05, + "loss": 3.5752, + "step": 923136 + }, + { + "epoch": 1.0, + "learning_rate": 3.487808928806582e-05, + "loss": 3.5664, + "step": 923648 + }, + { + "epoch": 1.0, + "learning_rate": 3.486970334055529e-05, + "loss": 3.5835, + "step": 924160 + }, + { + "epoch": 1.0, + "learning_rate": 3.486131739304477e-05, + "loss": 3.5812, + "step": 924672 + }, + { + "epoch": 1.0, + "learning_rate": 3.485294782433799e-05, + "loss": 3.5798, + "step": 925184 + }, + { + "epoch": 1.0, + "learning_rate": 3.484456187682746e-05, + "loss": 3.581, + "step": 925696 + }, + { + "epoch": 1.0, + "learning_rate": 3.483617592931694e-05, + "loss": 3.598, + "step": 926208 + }, + { + "epoch": 1.0, + "learning_rate": 3.482778998180642e-05, + "loss": 3.5879, + "step": 926720 + }, + { + "epoch": 1.0, + "learning_rate": 3.48194040342959e-05, + "loss": 3.584, + "step": 927232 + }, + { + "epoch": 1.0, + "learning_rate": 3.481103446558912e-05, + "loss": 3.5774, + "step": 927744 + }, + { + "epoch": 1.0, + "learning_rate": 3.48026485180786e-05, + "loss": 3.5911, + "step": 928256 + }, + { + "epoch": 1.0, + "learning_rate": 3.479426257056808e-05, + "loss": 3.5822, + "step": 928768 + }, + { + "epoch": 1.0, + "learning_rate": 3.478587662305756e-05, + "loss": 3.5779, + "step": 929280 + }, + { + "epoch": 1.0, + "learning_rate": 3.4777507054350766e-05, + "loss": 3.5882, + "step": 929792 + }, + { + "epoch": 1.0, + "learning_rate": 3.4769121106840246e-05, + "loss": 3.5704, + "step": 930304 + }, + { + "epoch": 1.0, + "learning_rate": 3.4760735159329726e-05, + "loss": 3.575, + "step": 930816 + }, + { + "epoch": 1.01, + "learning_rate": 3.4752349211819206e-05, + "loss": 3.5806, + "step": 931328 + }, + { + "epoch": 1.01, + "learning_rate": 3.4743979643112415e-05, + "loss": 3.5773, + "step": 931840 + }, + { + "epoch": 1.01, + "learning_rate": 3.4735593695601895e-05, + "loss": 3.5869, + "step": 932352 + }, + { + "epoch": 1.01, + "learning_rate": 3.4727207748091375e-05, + "loss": 3.5883, + "step": 932864 + }, + { + "epoch": 1.01, + "learning_rate": 3.4718821800580855e-05, + "loss": 3.5767, + "step": 933376 + }, + { + "epoch": 1.01, + "learning_rate": 3.471045223187407e-05, + "loss": 3.5794, + "step": 933888 + }, + { + "epoch": 1.01, + "learning_rate": 3.470206628436355e-05, + "loss": 3.586, + "step": 934400 + }, + { + "epoch": 1.01, + "learning_rate": 3.469368033685303e-05, + "loss": 3.5703, + "step": 934912 + }, + { + "epoch": 1.01, + "learning_rate": 3.468529438934251e-05, + "loss": 3.5741, + "step": 935424 + }, + { + "epoch": 1.01, + "learning_rate": 3.467690844183199e-05, + "loss": 3.5726, + "step": 935936 + }, + { + "epoch": 1.01, + "learning_rate": 3.46685388731252e-05, + "loss": 3.5728, + "step": 936448 + }, + { + "epoch": 1.01, + "learning_rate": 3.466015292561468e-05, + "loss": 3.5747, + "step": 936960 + }, + { + "epoch": 1.01, + "learning_rate": 3.465176697810416e-05, + "loss": 3.5819, + "step": 937472 + }, + { + "epoch": 1.01, + "learning_rate": 3.464338103059364e-05, + "loss": 3.5817, + "step": 937984 + }, + { + "epoch": 1.01, + "learning_rate": 3.463499508308312e-05, + "loss": 3.5768, + "step": 938496 + }, + { + "epoch": 1.01, + "learning_rate": 3.462662551437633e-05, + "loss": 3.5802, + "step": 939008 + }, + { + "epoch": 1.01, + "learning_rate": 3.461823956686581e-05, + "loss": 3.5839, + "step": 939520 + }, + { + "epoch": 1.01, + "learning_rate": 3.4609853619355296e-05, + "loss": 3.5842, + "step": 940032 + }, + { + "epoch": 1.01, + "learning_rate": 3.4601467671844776e-05, + "loss": 3.5612, + "step": 940544 + }, + { + "epoch": 1.01, + "learning_rate": 3.4593098103137985e-05, + "loss": 3.5821, + "step": 941056 + }, + { + "epoch": 1.01, + "learning_rate": 3.4584712155627465e-05, + "loss": 3.57, + "step": 941568 + }, + { + "epoch": 1.01, + "learning_rate": 3.4576326208116945e-05, + "loss": 3.5762, + "step": 942080 + }, + { + "epoch": 1.01, + "learning_rate": 3.4567940260606425e-05, + "loss": 3.5787, + "step": 942592 + }, + { + "epoch": 1.01, + "learning_rate": 3.4559570691899634e-05, + "loss": 3.5688, + "step": 943104 + }, + { + "epoch": 1.01, + "learning_rate": 3.4551184744389114e-05, + "loss": 3.5667, + "step": 943616 + }, + { + "epoch": 1.01, + "learning_rate": 3.4542798796878594e-05, + "loss": 3.5621, + "step": 944128 + }, + { + "epoch": 1.01, + "learning_rate": 3.4534412849368073e-05, + "loss": 3.593, + "step": 944640 + }, + { + "epoch": 1.01, + "learning_rate": 3.452604328066128e-05, + "loss": 3.5675, + "step": 945152 + }, + { + "epoch": 1.01, + "learning_rate": 3.451765733315076e-05, + "loss": 3.5816, + "step": 945664 + }, + { + "epoch": 1.01, + "learning_rate": 3.450927138564025e-05, + "loss": 3.5747, + "step": 946176 + }, + { + "epoch": 1.01, + "learning_rate": 3.450088543812973e-05, + "loss": 3.5664, + "step": 946688 + }, + { + "epoch": 1.01, + "learning_rate": 3.449251586942294e-05, + "loss": 3.5782, + "step": 947200 + }, + { + "epoch": 1.01, + "learning_rate": 3.448412992191242e-05, + "loss": 3.5707, + "step": 947712 + }, + { + "epoch": 1.01, + "learning_rate": 3.44757439744019e-05, + "loss": 3.5614, + "step": 948224 + }, + { + "epoch": 1.01, + "learning_rate": 3.446735802689138e-05, + "loss": 3.5594, + "step": 948736 + }, + { + "epoch": 1.01, + "learning_rate": 3.445897207938086e-05, + "loss": 3.5872, + "step": 949248 + }, + { + "epoch": 1.01, + "learning_rate": 3.445060251067407e-05, + "loss": 3.5646, + "step": 949760 + }, + { + "epoch": 1.01, + "learning_rate": 3.444221656316355e-05, + "loss": 3.5751, + "step": 950272 + }, + { + "epoch": 1.01, + "learning_rate": 3.443383061565303e-05, + "loss": 3.557, + "step": 950784 + }, + { + "epoch": 1.01, + "learning_rate": 3.442544466814251e-05, + "loss": 3.5703, + "step": 951296 + }, + { + "epoch": 1.01, + "learning_rate": 3.4417075099435716e-05, + "loss": 3.5693, + "step": 951808 + }, + { + "epoch": 1.01, + "learning_rate": 3.44086891519252e-05, + "loss": 3.5776, + "step": 952320 + }, + { + "epoch": 1.01, + "learning_rate": 3.440030320441468e-05, + "loss": 3.5768, + "step": 952832 + }, + { + "epoch": 1.01, + "learning_rate": 3.439191725690416e-05, + "loss": 3.5762, + "step": 953344 + }, + { + "epoch": 1.01, + "learning_rate": 3.438353130939364e-05, + "loss": 3.5809, + "step": 953856 + }, + { + "epoch": 1.01, + "learning_rate": 3.437516174068685e-05, + "loss": 3.5686, + "step": 954368 + }, + { + "epoch": 1.01, + "learning_rate": 3.436677579317633e-05, + "loss": 3.5742, + "step": 954880 + }, + { + "epoch": 1.01, + "learning_rate": 3.435838984566581e-05, + "loss": 3.5666, + "step": 955392 + }, + { + "epoch": 1.01, + "learning_rate": 3.435000389815529e-05, + "loss": 3.57, + "step": 955904 + }, + { + "epoch": 1.01, + "learning_rate": 3.43416343294485e-05, + "loss": 3.5735, + "step": 956416 + }, + { + "epoch": 1.01, + "learning_rate": 3.433324838193798e-05, + "loss": 3.5648, + "step": 956928 + }, + { + "epoch": 1.01, + "learning_rate": 3.432486243442746e-05, + "loss": 3.5812, + "step": 957440 + }, + { + "epoch": 1.01, + "learning_rate": 3.431647648691694e-05, + "loss": 3.5819, + "step": 957952 + }, + { + "epoch": 1.01, + "learning_rate": 3.430810691821016e-05, + "loss": 3.573, + "step": 958464 + }, + { + "epoch": 1.01, + "learning_rate": 3.4299720970699637e-05, + "loss": 3.5492, + "step": 958976 + }, + { + "epoch": 1.01, + "learning_rate": 3.4291335023189117e-05, + "loss": 3.57, + "step": 959488 + }, + { + "epoch": 1.01, + "learning_rate": 3.4282949075678596e-05, + "loss": 3.5782, + "step": 960000 + }, + { + "epoch": 1.01, + "learning_rate": 3.427456312816807e-05, + "loss": 3.5816, + "step": 960512 + }, + { + "epoch": 1.01, + "learning_rate": 3.4266193559461286e-05, + "loss": 3.5668, + "step": 961024 + }, + { + "epoch": 1.01, + "learning_rate": 3.4257807611950765e-05, + "loss": 3.5695, + "step": 961536 + }, + { + "epoch": 1.02, + "learning_rate": 3.4249421664440245e-05, + "loss": 3.5756, + "step": 962048 + }, + { + "epoch": 1.02, + "learning_rate": 3.424103571692972e-05, + "loss": 3.5634, + "step": 962560 + }, + { + "epoch": 1.02, + "learning_rate": 3.42326497694192e-05, + "loss": 3.5634, + "step": 963072 + }, + { + "epoch": 1.02, + "learning_rate": 3.4224280200712414e-05, + "loss": 3.5738, + "step": 963584 + }, + { + "epoch": 1.02, + "learning_rate": 3.4215894253201894e-05, + "loss": 3.5715, + "step": 964096 + }, + { + "epoch": 1.02, + "learning_rate": 3.4207508305691374e-05, + "loss": 3.5824, + "step": 964608 + }, + { + "epoch": 1.02, + "learning_rate": 3.4199122358180854e-05, + "loss": 3.5674, + "step": 965120 + }, + { + "epoch": 1.02, + "learning_rate": 3.4190736410670334e-05, + "loss": 3.5651, + "step": 965632 + }, + { + "epoch": 1.02, + "learning_rate": 3.4182350463159814e-05, + "loss": 3.5619, + "step": 966144 + }, + { + "epoch": 1.02, + "learning_rate": 3.417398089445302e-05, + "loss": 3.5751, + "step": 966656 + }, + { + "epoch": 1.02, + "learning_rate": 3.41655949469425e-05, + "loss": 3.5724, + "step": 967168 + }, + { + "epoch": 1.02, + "learning_rate": 3.415720899943198e-05, + "loss": 3.5662, + "step": 967680 + }, + { + "epoch": 1.02, + "learning_rate": 3.414882305192146e-05, + "loss": 3.566, + "step": 968192 + }, + { + "epoch": 1.02, + "learning_rate": 3.414045348321467e-05, + "loss": 3.5596, + "step": 968704 + }, + { + "epoch": 1.02, + "learning_rate": 3.413206753570415e-05, + "loss": 3.5723, + "step": 969216 + }, + { + "epoch": 1.02, + "learning_rate": 3.412368158819363e-05, + "loss": 3.5505, + "step": 969728 + }, + { + "epoch": 1.02, + "learning_rate": 3.411529564068311e-05, + "loss": 3.5644, + "step": 970240 + }, + { + "epoch": 1.02, + "learning_rate": 3.410692607197633e-05, + "loss": 3.5676, + "step": 970752 + }, + { + "epoch": 1.02, + "learning_rate": 3.409854012446581e-05, + "loss": 3.5713, + "step": 971264 + }, + { + "epoch": 1.02, + "learning_rate": 3.409015417695529e-05, + "loss": 3.5589, + "step": 971776 + }, + { + "epoch": 1.02, + "learning_rate": 3.408176822944477e-05, + "loss": 3.5708, + "step": 972288 + }, + { + "epoch": 1.02, + "learning_rate": 3.407338228193425e-05, + "loss": 3.5615, + "step": 972800 + }, + { + "epoch": 1.02, + "learning_rate": 3.406501271322746e-05, + "loss": 3.5731, + "step": 973312 + }, + { + "epoch": 1.02, + "learning_rate": 3.405662676571694e-05, + "loss": 3.5695, + "step": 973824 + }, + { + "epoch": 1.02, + "learning_rate": 3.404824081820642e-05, + "loss": 3.57, + "step": 974336 + }, + { + "epoch": 1.02, + "learning_rate": 3.40398548706959e-05, + "loss": 3.5692, + "step": 974848 + }, + { + "epoch": 1.02, + "learning_rate": 3.403146892318538e-05, + "loss": 3.5857, + "step": 975360 + }, + { + "epoch": 1.02, + "learning_rate": 3.4023099354478586e-05, + "loss": 3.5645, + "step": 975872 + }, + { + "epoch": 1.02, + "learning_rate": 3.4014713406968066e-05, + "loss": 3.5696, + "step": 976384 + }, + { + "epoch": 1.02, + "learning_rate": 3.4006327459457546e-05, + "loss": 3.5752, + "step": 976896 + }, + { + "epoch": 1.02, + "learning_rate": 3.3997941511947026e-05, + "loss": 3.5691, + "step": 977408 + }, + { + "epoch": 1.02, + "learning_rate": 3.398955556443651e-05, + "loss": 3.5674, + "step": 977920 + }, + { + "epoch": 1.02, + "learning_rate": 3.398118599572972e-05, + "loss": 3.566, + "step": 978432 + }, + { + "epoch": 1.02, + "learning_rate": 3.39728000482192e-05, + "loss": 3.564, + "step": 978944 + }, + { + "epoch": 1.02, + "learning_rate": 3.396441410070868e-05, + "loss": 3.5706, + "step": 979456 + }, + { + "epoch": 1.02, + "learning_rate": 3.395602815319816e-05, + "loss": 3.5556, + "step": 979968 + }, + { + "epoch": 1.02, + "learning_rate": 3.394764220568764e-05, + "loss": 3.5676, + "step": 980480 + }, + { + "epoch": 1.02, + "learning_rate": 3.393925625817712e-05, + "loss": 3.5572, + "step": 980992 + }, + { + "epoch": 1.02, + "learning_rate": 3.393088668947033e-05, + "loss": 3.5665, + "step": 981504 + }, + { + "epoch": 1.02, + "learning_rate": 3.392250074195981e-05, + "loss": 3.5625, + "step": 982016 + }, + { + "epoch": 1.02, + "learning_rate": 3.391411479444929e-05, + "loss": 3.5705, + "step": 982528 + }, + { + "epoch": 1.02, + "learning_rate": 3.390572884693877e-05, + "loss": 3.5818, + "step": 983040 + }, + { + "epoch": 1.02, + "learning_rate": 3.389735927823198e-05, + "loss": 3.5606, + "step": 983552 + }, + { + "epoch": 1.02, + "learning_rate": 3.3888973330721466e-05, + "loss": 3.57, + "step": 984064 + }, + { + "epoch": 1.02, + "learning_rate": 3.3880587383210946e-05, + "loss": 3.5696, + "step": 984576 + }, + { + "epoch": 1.02, + "learning_rate": 3.3872201435700426e-05, + "loss": 3.5676, + "step": 985088 + }, + { + "epoch": 1.02, + "learning_rate": 3.3863815488189906e-05, + "loss": 3.5647, + "step": 985600 + }, + { + "epoch": 1.02, + "learning_rate": 3.3855445919483115e-05, + "loss": 3.5567, + "step": 986112 + }, + { + "epoch": 1.02, + "learning_rate": 3.3847059971972595e-05, + "loss": 3.5725, + "step": 986624 + }, + { + "epoch": 1.02, + "learning_rate": 3.3838674024462075e-05, + "loss": 3.577, + "step": 987136 + }, + { + "epoch": 1.02, + "learning_rate": 3.3830288076951555e-05, + "loss": 3.5636, + "step": 987648 + }, + { + "epoch": 1.02, + "learning_rate": 3.382190212944103e-05, + "loss": 3.569, + "step": 988160 + }, + { + "epoch": 1.02, + "learning_rate": 3.381351618193051e-05, + "loss": 3.573, + "step": 988672 + }, + { + "epoch": 1.02, + "learning_rate": 3.3805146613223724e-05, + "loss": 3.5652, + "step": 989184 + }, + { + "epoch": 1.02, + "learning_rate": 3.3796760665713204e-05, + "loss": 3.5646, + "step": 989696 + }, + { + "epoch": 1.02, + "learning_rate": 3.3788374718202684e-05, + "loss": 3.5742, + "step": 990208 + }, + { + "epoch": 1.02, + "learning_rate": 3.3779988770692164e-05, + "loss": 3.5665, + "step": 990720 + }, + { + "epoch": 1.02, + "learning_rate": 3.377161920198538e-05, + "loss": 3.5661, + "step": 991232 + }, + { + "epoch": 1.02, + "learning_rate": 3.376323325447485e-05, + "loss": 3.5743, + "step": 991744 + }, + { + "epoch": 1.03, + "eval_loss": 3.862633466720581, + "eval_runtime": 305.3094, + "eval_samples_per_second": 1249.85, + "eval_steps_per_second": 39.059, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.375484730696433e-05, + "loss": 3.5708, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.374646135945381e-05, + "loss": 3.5473, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.373807541194329e-05, + "loss": 3.5651, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.372968946443277e-05, + "loss": 3.5753, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.372130351692225e-05, + "loss": 3.5738, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.371293394821546e-05, + "loss": 3.5666, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.370454800070494e-05, + "loss": 3.5655, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.369616205319442e-05, + "loss": 3.5638, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.36877761056839e-05, + "loss": 3.558, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.367940653697712e-05, + "loss": 3.5652, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.36710205894666e-05, + "loss": 3.5644, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.366263464195608e-05, + "loss": 3.5654, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.3654265073249287e-05, + "loss": 3.5764, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.3645879125738766e-05, + "loss": 3.5548, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.3637493178228246e-05, + "loss": 3.5546, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.3629107230717726e-05, + "loss": 3.5464, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.3620721283207206e-05, + "loss": 3.5669, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.3612335335696686e-05, + "loss": 3.5637, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.3603949388186166e-05, + "loss": 3.5649, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.3595563440675646e-05, + "loss": 3.5624, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.3587193871968855e-05, + "loss": 3.5796, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.357880792445834e-05, + "loss": 3.5702, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.357042197694782e-05, + "loss": 3.5665, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.35620360294373e-05, + "loss": 3.5615, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.355366646073051e-05, + "loss": 3.5771, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.354528051321999e-05, + "loss": 3.5593, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.353689456570947e-05, + "loss": 3.5639, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.352850861819895e-05, + "loss": 3.5723, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.352012267068843e-05, + "loss": 3.5542, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.351175310198164e-05, + "loss": 3.5587, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350336715447112e-05, + "loss": 3.5612, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.34949812069606e-05, + "loss": 3.5592, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348659525945008e-05, + "loss": 3.5697, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.347820931193956e-05, + "loss": 3.5712, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.346982336442904e-05, + "loss": 3.5626, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.3461453795722256e-05, + "loss": 3.5616, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.3453067848211736e-05, + "loss": 3.5728, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.3444681900701216e-05, + "loss": 3.5464, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.343629595319069e-05, + "loss": 3.56, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.3427926384483905e-05, + "loss": 3.5577, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.3419540436973385e-05, + "loss": 3.5525, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.3411154489462864e-05, + "loss": 3.5586, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.340276854195234e-05, + "loss": 3.568, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.3394398973245554e-05, + "loss": 3.5642, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.3386013025735033e-05, + "loss": 3.5583, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.3377627078224513e-05, + "loss": 3.561, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.3369241130713993e-05, + "loss": 3.5631, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.336087156200721e-05, + "loss": 3.5689, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.335248561449669e-05, + "loss": 3.5466, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.334409966698616e-05, + "loss": 3.5669, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.333571371947564e-05, + "loss": 3.5576, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.332732777196512e-05, + "loss": 3.5572, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.331895820325834e-05, + "loss": 3.5626, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.331057225574781e-05, + "loss": 3.546, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.330218630823729e-05, + "loss": 3.5557, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329381673953051e-05, + "loss": 3.5434, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.328543079201998e-05, + "loss": 3.5757, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.327704484450947e-05, + "loss": 3.5493, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.326865889699895e-05, + "loss": 3.5671, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.326027294948843e-05, + "loss": 3.5538, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.3251903380781636e-05, + "loss": 3.552, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.3243517433271116e-05, + "loss": 3.5582, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.3235131485760596e-05, + "loss": 3.5556, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.3226745538250076e-05, + "loss": 3.5476, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.3218359590739556e-05, + "loss": 3.5396, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.3209990022032765e-05, + "loss": 3.5642, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.3201604074522245e-05, + "loss": 3.5518, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.3193218127011725e-05, + "loss": 3.5544, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.3184832179501205e-05, + "loss": 3.543, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.3176446231990685e-05, + "loss": 3.5471, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.31680766632839e-05, + "loss": 3.5556, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.315969071577338e-05, + "loss": 3.5607, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.315130476826286e-05, + "loss": 3.5569, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314291882075234e-05, + "loss": 3.5594, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.313454925204555e-05, + "loss": 3.5628, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.312616330453503e-05, + "loss": 3.5516, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.311777735702451e-05, + "loss": 3.5571, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.310939140951399e-05, + "loss": 3.5508, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.31010218408072e-05, + "loss": 3.554, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.309263589329668e-05, + "loss": 3.557, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.308424994578616e-05, + "loss": 3.5479, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.307586399827564e-05, + "loss": 3.5652, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.3067494429568854e-05, + "loss": 3.5648, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.3059108482058334e-05, + "loss": 3.551, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.3050722534547814e-05, + "loss": 3.5378, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.3042336587037294e-05, + "loss": 3.5561, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.30339670183305e-05, + "loss": 3.5593, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.302558107081998e-05, + "loss": 3.5617, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.301719512330946e-05, + "loss": 3.5474, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.300880917579894e-05, + "loss": 3.5536, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.300043960709215e-05, + "loss": 3.5595, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.299205365958163e-05, + "loss": 3.5452, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.298366771207111e-05, + "loss": 3.5474, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.297528176456059e-05, + "loss": 3.5561, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.296691219585381e-05, + "loss": 3.5539, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.295852624834329e-05, + "loss": 3.5665, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.295014030083277e-05, + "loss": 3.5551, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.294175435332225e-05, + "loss": 3.5436, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.293338478461546e-05, + "loss": 3.5484, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292499883710494e-05, + "loss": 3.5548, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291661288959442e-05, + "loss": 3.5606, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.29082269420839e-05, + "loss": 3.552, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.289984099457338e-05, + "loss": 3.5465, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.2891471425866586e-05, + "loss": 3.5409, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.2883085478356066e-05, + "loss": 3.5591, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.2874699530845546e-05, + "loss": 3.5342, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.2866313583335026e-05, + "loss": 3.5452, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285794401462824e-05, + "loss": 3.5536, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.284955806711772e-05, + "loss": 3.5555, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.28411721196072e-05, + "loss": 3.5414, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.283278617209668e-05, + "loss": 3.5539, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.282441660338989e-05, + "loss": 3.5458, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.281603065587937e-05, + "loss": 3.555, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.280764470836885e-05, + "loss": 3.5552, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.279925876085833e-05, + "loss": 3.5492, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.279088919215154e-05, + "loss": 3.5537, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.278250324464102e-05, + "loss": 3.5679, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.27741172971305e-05, + "loss": 3.5487, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.276573134961998e-05, + "loss": 3.5556, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.2757361780913195e-05, + "loss": 3.554, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.2748975833402675e-05, + "loss": 3.5506, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.2740589885892155e-05, + "loss": 3.5517, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.2732203938381635e-05, + "loss": 3.548, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.2723834369674844e-05, + "loss": 3.5476, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.2715448422164324e-05, + "loss": 3.5541, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.2707062474653804e-05, + "loss": 3.5437, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.2698676527143284e-05, + "loss": 3.5485, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.2690290579632764e-05, + "loss": 3.5418, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.268192101092597e-05, + "loss": 3.5492, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.267353506341545e-05, + "loss": 3.5425, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.266514911590493e-05, + "loss": 3.5602, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.265676316839441e-05, + "loss": 3.564, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.264839359968763e-05, + "loss": 3.5407, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.264000765217711e-05, + "loss": 3.5517, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.263162170466659e-05, + "loss": 3.5553, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.262323575715606e-05, + "loss": 3.554, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.261486618844928e-05, + "loss": 3.5417, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260648024093876e-05, + "loss": 3.5439, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.259809429342824e-05, + "loss": 3.5579, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.258970834591771e-05, + "loss": 3.5595, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.258133877721093e-05, + "loss": 3.5429, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.257295282970041e-05, + "loss": 3.5544, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.256456688218989e-05, + "loss": 3.5584, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.255618093467937e-05, + "loss": 3.5511, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254781136597258e-05, + "loss": 3.5456, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.253942541846206e-05, + "loss": 3.5565, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.2531039470951536e-05, + "loss": 3.55, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.2522653523441016e-05, + "loss": 3.5554, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.251428395473423e-05, + "loss": 3.5508, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.8622679710388184, + "eval_runtime": 302.265, + "eval_samples_per_second": 1262.438, + "eval_steps_per_second": 39.452, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250589800722371e-05, + "loss": 3.5613, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.2497512059713185e-05, + "loss": 3.5332, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.2489126112202665e-05, + "loss": 3.5473, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.2480740164692145e-05, + "loss": 3.5627, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.2472354217181625e-05, + "loss": 3.556, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246398464847484e-05, + "loss": 3.5516, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245559870096432e-05, + "loss": 3.5464, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.24472127534538e-05, + "loss": 3.5466, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243882680594328e-05, + "loss": 3.5436, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243045723723649e-05, + "loss": 3.5497, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242207128972597e-05, + "loss": 3.544, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241368534221545e-05, + "loss": 3.5536, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240531577350866e-05, + "loss": 3.5571, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239692982599814e-05, + "loss": 3.539, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238854387848762e-05, + "loss": 3.542, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.23801579309771e-05, + "loss": 3.5282, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237177198346658e-05, + "loss": 3.5492, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236338603595606e-05, + "loss": 3.5485, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2355000088445545e-05, + "loss": 3.5488, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2346614140935025e-05, + "loss": 3.5431, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2338228193424505e-05, + "loss": 3.5676, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2329858624717714e-05, + "loss": 3.5563, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2321472677207194e-05, + "loss": 3.5484, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2313086729696674e-05, + "loss": 3.5476, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2304700782186154e-05, + "loss": 3.5603, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229633121347936e-05, + "loss": 3.5426, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228794526596884e-05, + "loss": 3.5455, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227955931845832e-05, + "loss": 3.5571, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.22711733709478e-05, + "loss": 3.537, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226280380224101e-05, + "loss": 3.5395, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.22544178547305e-05, + "loss": 3.5424, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224603190721998e-05, + "loss": 3.5445, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223764595970946e-05, + "loss": 3.5536, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222926001219894e-05, + "loss": 3.5557, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222089044349215e-05, + "loss": 3.543, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221250449598163e-05, + "loss": 3.5531, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220411854847111e-05, + "loss": 3.551, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219573260096059e-05, + "loss": 3.533, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.2187363032253797e-05, + "loss": 3.542, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.2178977084743277e-05, + "loss": 3.544, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.2170591137232756e-05, + "loss": 3.5329, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.2162205189722236e-05, + "loss": 3.5451, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215383562101545e-05, + "loss": 3.5504, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214544967350493e-05, + "loss": 3.5445, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213706372599441e-05, + "loss": 3.5427, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212867777848389e-05, + "loss": 3.5498, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.21203082097771e-05, + "loss": 3.5445, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211192226226658e-05, + "loss": 3.5547, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210353631475606e-05, + "loss": 3.5273, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209515036724554e-05, + "loss": 3.5479, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208676441973502e-05, + "loss": 3.5473, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207839485102823e-05, + "loss": 3.5411, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207000890351771e-05, + "loss": 3.5449, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206162295600719e-05, + "loss": 3.5278, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205323700849667e-05, + "loss": 3.544, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.2044867439789886e-05, + "loss": 3.5243, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.2036481492279366e-05, + "loss": 3.5611, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.2028095544768846e-05, + "loss": 3.5322, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201970959725832e-05, + "loss": 3.5492, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.2011340028551535e-05, + "loss": 3.5404, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.2002954081041015e-05, + "loss": 3.5367, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.1994568133530495e-05, + "loss": 3.54, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198618218601997e-05, + "loss": 3.5431, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.1977812617313184e-05, + "loss": 3.5281, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.1969426669802664e-05, + "loss": 3.5243, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.1961040722292144e-05, + "loss": 3.5492, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.1952654774781624e-05, + "loss": 3.5383, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194428520607484e-05, + "loss": 3.5359, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193589925856432e-05, + "loss": 3.5251, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192751331105379e-05, + "loss": 3.5347, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191912736354327e-05, + "loss": 3.5394, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191074141603275e-05, + "loss": 3.5426, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190237184732596e-05, + "loss": 3.5434, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189398589981544e-05, + "loss": 3.5453, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188559995230492e-05, + "loss": 3.5443, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.18772140047944e-05, + "loss": 3.5383, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186884443608761e-05, + "loss": 3.5392, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186045848857709e-05, + "loss": 3.5339, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185207254106658e-05, + "loss": 3.5399, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184368659355606e-05, + "loss": 3.54, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1835317024849266e-05, + "loss": 3.5325, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.1826931077338746e-05, + "loss": 3.5434, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1818545129828226e-05, + "loss": 3.5465, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.1810159182317706e-05, + "loss": 3.5375, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1801789613610915e-05, + "loss": 3.5269, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1793403666100395e-05, + "loss": 3.5328, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.1785017718589875e-05, + "loss": 3.5419, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.1776631771079355e-05, + "loss": 3.5494, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.1768262202372564e-05, + "loss": 3.5333, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.1759876254862044e-05, + "loss": 3.5356, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175149030735153e-05, + "loss": 3.5393, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174310435984101e-05, + "loss": 3.5337, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173471841233049e-05, + "loss": 3.5291, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172633246481997e-05, + "loss": 3.5374, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171796289611318e-05, + "loss": 3.5402, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170957694860266e-05, + "loss": 3.5458, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170119100109214e-05, + "loss": 3.5408, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169280505358162e-05, + "loss": 3.5259, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168443548487483e-05, + "loss": 3.5345, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167604953736431e-05, + "loss": 3.5356, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166766358985379e-05, + "loss": 3.5443, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165927764234327e-05, + "loss": 3.5355, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.1650908073636485e-05, + "loss": 3.5306, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1642522126125965e-05, + "loss": 3.5275, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1634136178615445e-05, + "loss": 3.5405, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.1625750231104925e-05, + "loss": 3.5199, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.1617380662398134e-05, + "loss": 3.5319, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.1608994714887614e-05, + "loss": 3.5381, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.1600608767377094e-05, + "loss": 3.5368, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.1592222819866574e-05, + "loss": 3.5282, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158385325115978e-05, + "loss": 3.5385, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157546730364926e-05, + "loss": 3.5282, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156708135613874e-05, + "loss": 3.5346, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155869540862822e-05, + "loss": 3.5404, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155032583992144e-05, + "loss": 3.5324, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154193989241092e-05, + "loss": 3.5414, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.15335539449004e-05, + "loss": 3.5481, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152516799738988e-05, + "loss": 3.5377, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151679842868309e-05, + "loss": 3.5321, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150841248117257e-05, + "loss": 3.5434, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.150002653366205e-05, + "loss": 3.536, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149164058615153e-05, + "loss": 3.5323, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.1483271017444736e-05, + "loss": 3.5359, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.1474885069934216e-05, + "loss": 3.5303, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.1466499122423696e-05, + "loss": 3.5392, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1458113174913176e-05, + "loss": 3.5285, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.144974360620639e-05, + "loss": 3.5328, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144135765869587e-05, + "loss": 3.5253, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143297171118535e-05, + "loss": 3.5299, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142458576367483e-05, + "loss": 3.524, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141621619496804e-05, + "loss": 3.5447, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140783024745752e-05, + "loss": 3.5492, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.1399444299947e-05, + "loss": 3.5317, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139105835243648e-05, + "loss": 3.5312, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138268878372969e-05, + "loss": 3.543, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137430283621917e-05, + "loss": 3.5362, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136591688870865e-05, + "loss": 3.5291, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135753094119813e-05, + "loss": 3.5283, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1349161372491346e-05, + "loss": 3.542, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.1340775424980826e-05, + "loss": 3.5423, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.1332389477470306e-05, + "loss": 3.5321, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.1324003529959786e-05, + "loss": 3.5354, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1315633961252995e-05, + "loss": 3.5432, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1307248013742475e-05, + "loss": 3.5315, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1298862066231955e-05, + "loss": 3.5315, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1290476118721435e-05, + "loss": 3.544, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.1282106550014644e-05, + "loss": 3.5334, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.1273720602504124e-05, + "loss": 3.5403, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.1265334654993604e-05, + "loss": 3.5341, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.863744020462036, + "eval_runtime": 302.668, + "eval_samples_per_second": 1260.758, + "eval_steps_per_second": 39.4, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.1256948707483084e-05, + "loss": 3.5319, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.12485791387763e-05, + "loss": 3.5209, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.124019319126578e-05, + "loss": 3.5305, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123180724375526e-05, + "loss": 3.5441, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122342129624474e-05, + "loss": 3.5393, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121505172753795e-05, + "loss": 3.54, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120666578002743e-05, + "loss": 3.5276, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119827983251691e-05, + "loss": 3.5363, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.118989388500639e-05, + "loss": 3.5254, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.11815243162996e-05, + "loss": 3.537, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117313836878908e-05, + "loss": 3.5266, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116475242127856e-05, + "loss": 3.5397, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115636647376804e-05, + "loss": 3.5429, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114799690506125e-05, + "loss": 3.5232, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113961095755073e-05, + "loss": 3.5251, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113122501004021e-05, + "loss": 3.5169, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112283906252969e-05, + "loss": 3.5259, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.11144694938229e-05, + "loss": 3.5321, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110608354631238e-05, + "loss": 3.5351, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109769759880186e-05, + "loss": 3.5258, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108931165129134e-05, + "loss": 3.5551, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108094208258455e-05, + "loss": 3.539, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107255613507403e-05, + "loss": 3.5363, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106417018756351e-05, + "loss": 3.5325, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105578424005299e-05, + "loss": 3.5444, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.10474146713462e-05, + "loss": 3.5277, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103902872383569e-05, + "loss": 3.5305, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103064277632517e-05, + "loss": 3.5393, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102225682881464e-05, + "loss": 3.5186, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.1013887260107856e-05, + "loss": 3.5293, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.1005501312597336e-05, + "loss": 3.5246, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.0997115365086816e-05, + "loss": 3.5319, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098872941757629e-05, + "loss": 3.5353, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0980359848869505e-05, + "loss": 3.5386, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0971973901358985e-05, + "loss": 3.5289, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096358795384846e-05, + "loss": 3.5373, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095520200633794e-05, + "loss": 3.5367, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.0946816058827424e-05, + "loss": 3.5145, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093844649012064e-05, + "loss": 3.5303, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0930060542610114e-05, + "loss": 3.5263, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0921674595099593e-05, + "loss": 3.5163, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.0913288647589073e-05, + "loss": 3.5312, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090491907888229e-05, + "loss": 3.5347, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089653313137176e-05, + "loss": 3.5332, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088814718386124e-05, + "loss": 3.5203, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087976123635072e-05, + "loss": 3.5364, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087139166764393e-05, + "loss": 3.5292, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086300572013341e-05, + "loss": 3.5389, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085461977262289e-05, + "loss": 3.5127, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084623382511238e-05, + "loss": 3.5286, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083786425640559e-05, + "loss": 3.5358, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082947830889507e-05, + "loss": 3.5249, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082109236138455e-05, + "loss": 3.5339, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081272279267776e-05, + "loss": 3.5113, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.0804336845167236e-05, + "loss": 3.5308, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0795950897656716e-05, + "loss": 3.5096, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.0787564950146196e-05, + "loss": 3.5416, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.0779195381439405e-05, + "loss": 3.5206, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.0770809433928885e-05, + "loss": 3.5314, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.0762423486418365e-05, + "loss": 3.5273, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.0754037538907845e-05, + "loss": 3.5214, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074565159139733e-05, + "loss": 3.524, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073728202269054e-05, + "loss": 3.529, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072889607518002e-05, + "loss": 3.5129, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.07205101276695e-05, + "loss": 3.5091, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071212418015898e-05, + "loss": 3.532, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070375461145219e-05, + "loss": 3.5242, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069536866394167e-05, + "loss": 3.5253, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068698271643115e-05, + "loss": 3.5106, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067859676892063e-05, + "loss": 3.5176, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067022720021384e-05, + "loss": 3.5251, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066184125270332e-05, + "loss": 3.5274, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.06534553051928e-05, + "loss": 3.5299, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0645069357682285e-05, + "loss": 3.5284, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.0636699788975495e-05, + "loss": 3.5303, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.0628313841464975e-05, + "loss": 3.5245, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0619927893954454e-05, + "loss": 3.5218, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.0611541946443934e-05, + "loss": 3.5214, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.0603172377737144e-05, + "loss": 3.5221, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.0594786430226623e-05, + "loss": 3.5258, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0586400482716103e-05, + "loss": 3.5206, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0578014535205583e-05, + "loss": 3.5238, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056964496649879e-05, + "loss": 3.5373, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056125901898827e-05, + "loss": 3.5204, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055287307147775e-05, + "loss": 3.5129, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054448712396724e-05, + "loss": 3.5198, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053611755526045e-05, + "loss": 3.526, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052773160774993e-05, + "loss": 3.5327, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051934566023941e-05, + "loss": 3.5201, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0510959712728888e-05, + "loss": 3.5188, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502590144022097e-05, + "loss": 3.5276, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494204196511577e-05, + "loss": 3.5209, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0485818249001057e-05, + "loss": 3.5134, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477432301490537e-05, + "loss": 3.5215, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.046906273278375e-05, + "loss": 3.5254, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.046067678527323e-05, + "loss": 3.5312, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.045229083776271e-05, + "loss": 3.525, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.044390489025219e-05, + "loss": 3.514, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.04355353215454e-05, + "loss": 3.5183, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.042714937403488e-05, + "loss": 3.5195, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0418763426524362e-05, + "loss": 3.5324, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410377479013842e-05, + "loss": 3.517, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0401991531503322e-05, + "loss": 3.5169, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.039362196279653e-05, + "loss": 3.5141, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.038523601528601e-05, + "loss": 3.5216, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037685006777549e-05, + "loss": 3.5076, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.036846412026497e-05, + "loss": 3.5197, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0360094551558183e-05, + "loss": 3.5179, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0351708604047663e-05, + "loss": 3.5223, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0343322656537143e-05, + "loss": 3.5127, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0334936709026623e-05, + "loss": 3.5257, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326567140319832e-05, + "loss": 3.5131, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318181192809315e-05, + "loss": 3.5218, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0309795245298795e-05, + "loss": 3.5282, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301409297788275e-05, + "loss": 3.5157, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0293039729081484e-05, + "loss": 3.5273, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284653781570964e-05, + "loss": 3.5339, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276267834060444e-05, + "loss": 3.524, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0267881886549924e-05, + "loss": 3.522, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259512317843137e-05, + "loss": 3.5216, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251126370332617e-05, + "loss": 3.522, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0242740422822097e-05, + "loss": 3.5159, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234354475311577e-05, + "loss": 3.524, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0225984906604786e-05, + "loss": 3.5151, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.021759895909427e-05, + "loss": 3.5251, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.020921301158375e-05, + "loss": 3.5122, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.020082706407323e-05, + "loss": 3.5186, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.019244111656271e-05, + "loss": 3.5099, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0184071547855918e-05, + "loss": 3.5161, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0175685600345398e-05, + "loss": 3.5083, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167299652834878e-05, + "loss": 3.5267, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.015891370532436e-05, + "loss": 3.5357, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.015054413661757e-05, + "loss": 3.5193, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.014215818910705e-05, + "loss": 3.5118, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.013377224159653e-05, + "loss": 3.5286, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.012538629408601e-05, + "loss": 3.5236, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0117016725379223e-05, + "loss": 3.5174, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108630777868703e-05, + "loss": 3.5104, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0100244830358183e-05, + "loss": 3.5304, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0091858882847663e-05, + "loss": 3.5217, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083489314140872e-05, + "loss": 3.5196, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075103366630352e-05, + "loss": 3.5193, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.006671741911983e-05, + "loss": 3.5261, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058331471609315e-05, + "loss": 3.5157, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0049961902902524e-05, + "loss": 3.517, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041575955392004e-05, + "loss": 3.5289, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033190007881484e-05, + "loss": 3.5174, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.002480406037096e-05, + "loss": 3.524, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016434491664176e-05, + "loss": 3.5212, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0008048544153656e-05, + "loss": 3.5187, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.8642308712005615, + "eval_runtime": 302.7097, + "eval_samples_per_second": 1260.584, + "eval_steps_per_second": 39.394, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999662596643136e-05, + "loss": 3.5053, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.999127664913261e-05, + "loss": 3.5154, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.998289070162209e-05, + "loss": 3.5265, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.997450475411157e-05, + "loss": 3.5262, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966135185404782e-05, + "loss": 3.5238, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9957749237894262e-05, + "loss": 3.5116, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949363290383742e-05, + "loss": 3.5213, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9940977342873222e-05, + "loss": 3.5064, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.993260777416643e-05, + "loss": 3.5279, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924221826655914e-05, + "loss": 3.509, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9915835879145394e-05, + "loss": 3.5288, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9907449931634874e-05, + "loss": 3.5256, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9899080362928083e-05, + "loss": 3.5105, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9890694415417563e-05, + "loss": 3.5107, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882308467907043e-05, + "loss": 3.5056, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9873922520396523e-05, + "loss": 3.5064, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865552951689736e-05, + "loss": 3.5193, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9857167004179216e-05, + "loss": 3.5197, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9848781056668696e-05, + "loss": 3.5138, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840395109158176e-05, + "loss": 3.538, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9832025540451385e-05, + "loss": 3.5237, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823639592940868e-05, + "loss": 3.5239, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815253645430348e-05, + "loss": 3.5157, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9806867697919828e-05, + "loss": 3.5278, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798498129213037e-05, + "loss": 3.5097, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790112181702517e-05, + "loss": 3.5228, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9781726234191997e-05, + "loss": 3.5232, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773340286681477e-05, + "loss": 3.5103, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.976497071797469e-05, + "loss": 3.5095, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.975658477046417e-05, + "loss": 3.5087, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.974819882295365e-05, + "loss": 3.519, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.973981287544313e-05, + "loss": 3.5199, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731443306736338e-05, + "loss": 3.5236, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9723057359225818e-05, + "loss": 3.5185, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.97146714117153e-05, + "loss": 3.5218, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.970628546420478e-05, + "loss": 3.5207, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.969791589549799e-05, + "loss": 3.5051, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.968952994798747e-05, + "loss": 3.5155, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.968114400047695e-05, + "loss": 3.51, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.967275805296643e-05, + "loss": 3.5051, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664388484259643e-05, + "loss": 3.5143, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9656002536749123e-05, + "loss": 3.5225, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647616589238603e-05, + "loss": 3.5152, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9639230641728083e-05, + "loss": 3.5103, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9630861073021292e-05, + "loss": 3.5212, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622475125510772e-05, + "loss": 3.5207, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9614089178000255e-05, + "loss": 3.5199, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9605703230489735e-05, + "loss": 3.5047, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597333661782944e-05, + "loss": 3.511, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9588947714272424e-05, + "loss": 3.5191, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580561766761904e-05, + "loss": 3.5133, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572175819251384e-05, + "loss": 3.5153, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9563806250544597e-05, + "loss": 3.5005, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555420303034077e-05, + "loss": 3.5165, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9547034355523557e-05, + "loss": 3.4965, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538648408013037e-05, + "loss": 3.5241, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530278839306246e-05, + "loss": 3.5106, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9521892891795726e-05, + "loss": 3.5163, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.951350694428521e-05, + "loss": 3.5113, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.950512099677469e-05, + "loss": 3.5101, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9496751428067898e-05, + "loss": 3.5061, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488365480557378e-05, + "loss": 3.5159, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9479979533046858e-05, + "loss": 3.5008, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471593585536338e-05, + "loss": 3.4962, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.946322401682955e-05, + "loss": 3.5137, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.945483806931903e-05, + "loss": 3.513, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944645212180851e-05, + "loss": 3.5088, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.943806617429799e-05, + "loss": 3.495, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.94296966055912e-05, + "loss": 3.5034, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.942131065808068e-05, + "loss": 3.5133, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9412924710570163e-05, + "loss": 3.5145, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9404538763059643e-05, + "loss": 3.5111, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.939616919435285e-05, + "loss": 3.5149, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.938778324684233e-05, + "loss": 3.5182, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.937939729933181e-05, + "loss": 3.5153, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.937101135182129e-05, + "loss": 3.5012, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9362641783114504e-05, + "loss": 3.5063, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9354255835603984e-05, + "loss": 3.5131, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9345869888093464e-05, + "loss": 3.5081, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337483940582944e-05, + "loss": 3.51, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329114371876153e-05, + "loss": 3.5093, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9320728424365633e-05, + "loss": 3.5249, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312342476855116e-05, + "loss": 3.5039, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9303956529344596e-05, + "loss": 3.4962, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295586960637805e-05, + "loss": 3.5069, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287201013127285e-05, + "loss": 3.5109, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9278815065616765e-05, + "loss": 3.5177, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270429118106245e-05, + "loss": 3.504, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9262059549399458e-05, + "loss": 3.5062, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253673601888938e-05, + "loss": 3.5144, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245287654378418e-05, + "loss": 3.509, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9236901706867898e-05, + "loss": 3.4972, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228532138161107e-05, + "loss": 3.5073, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220146190650587e-05, + "loss": 3.5154, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.921176024314007e-05, + "loss": 3.523, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.920337429562955e-05, + "loss": 3.505, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.919500472692276e-05, + "loss": 3.4989, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.918661877941224e-05, + "loss": 3.5094, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.917823283190172e-05, + "loss": 3.5009, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.91698468843912e-05, + "loss": 3.5163, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.916147731568441e-05, + "loss": 3.5058, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.915309136817389e-05, + "loss": 3.5036, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.914470542066337e-05, + "loss": 3.5013, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.913631947315285e-05, + "loss": 3.513, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.912793352564233e-05, + "loss": 3.4882, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.911956395693554e-05, + "loss": 3.5082, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111178009425024e-05, + "loss": 3.5025, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9102792061914504e-05, + "loss": 3.5109, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094406114403983e-05, + "loss": 3.5017, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9086036545697193e-05, + "loss": 3.5097, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9077650598186673e-05, + "loss": 3.5019, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069264650676152e-05, + "loss": 3.5053, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9060878703165632e-05, + "loss": 3.511, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052509134458845e-05, + "loss": 3.5032, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044123186948325e-05, + "loss": 3.5156, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9035737239437805e-05, + "loss": 3.5217, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027351291927278e-05, + "loss": 3.5087, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9018981723220494e-05, + "loss": 3.5083, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010595775709977e-05, + "loss": 3.5061, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002209828199457e-05, + "loss": 3.5067, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.899382388068893e-05, + "loss": 3.5051, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985454311982146e-05, + "loss": 3.5095, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8977068364471626e-05, + "loss": 3.5044, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968682416961106e-05, + "loss": 3.5109, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960296469450583e-05, + "loss": 3.4989, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.89519269007438e-05, + "loss": 3.5053, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.894354095323328e-05, + "loss": 3.4975, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8935155005722752e-05, + "loss": 3.4988, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.892676905821223e-05, + "loss": 3.4956, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918399489505448e-05, + "loss": 3.5144, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8910013541994928e-05, + "loss": 3.5228, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901627594484404e-05, + "loss": 3.5117, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893241646973884e-05, + "loss": 3.4915, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.88848720782671e-05, + "loss": 3.5156, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.887648613075658e-05, + "loss": 3.5092, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8868100183246056e-05, + "loss": 3.5021, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859714235735536e-05, + "loss": 3.4984, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8851328288225016e-05, + "loss": 3.5163, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8842958719518225e-05, + "loss": 3.5065, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834572772007705e-05, + "loss": 3.5051, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826186824497185e-05, + "loss": 3.5083, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8817800876986665e-05, + "loss": 3.5102, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809431308279878e-05, + "loss": 3.5025, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801045360769358e-05, + "loss": 3.5033, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792659413258838e-05, + "loss": 3.5183, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784273465748318e-05, + "loss": 3.506, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8775903897041527e-05, + "loss": 3.5094, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.876751794953101e-05, + "loss": 3.5105, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.875913200202049e-05, + "loss": 3.5007, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.865279197692871, + "eval_runtime": 304.0509, + "eval_samples_per_second": 1255.023, + "eval_steps_per_second": 39.22, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.875074605450997e-05, + "loss": 3.4942, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.874237648580318e-05, + "loss": 3.5038, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.873399053829266e-05, + "loss": 3.5126, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.872560459078214e-05, + "loss": 3.5086, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.871721864327162e-05, + "loss": 3.5144, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.870884907456483e-05, + "loss": 3.4967, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.870046312705431e-05, + "loss": 3.5067, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.869207717954379e-05, + "loss": 3.4938, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.868369123203327e-05, + "loss": 3.5144, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.867532166332648e-05, + "loss": 3.4983, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.8666935715815964e-05, + "loss": 3.5109, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8658549768305444e-05, + "loss": 3.5084, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8650180199598653e-05, + "loss": 3.5028, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8641794252088133e-05, + "loss": 3.4966, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8633408304577613e-05, + "loss": 3.4932, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8625022357067093e-05, + "loss": 3.4918, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8616652788360305e-05, + "loss": 3.5029, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8608266840849785e-05, + "loss": 3.5063, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8599880893339265e-05, + "loss": 3.5001, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591494945828745e-05, + "loss": 3.5237, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8583125377121954e-05, + "loss": 3.514, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8574739429611434e-05, + "loss": 3.5068, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566353482100917e-05, + "loss": 3.5011, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8557967534590397e-05, + "loss": 3.5172, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549597965883606e-05, + "loss": 3.4937, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541212018373086e-05, + "loss": 3.5078, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8532826070862566e-05, + "loss": 3.5066, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524440123352046e-05, + "loss": 3.5018, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.851607055464526e-05, + "loss": 3.4932, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.850768460713474e-05, + "loss": 3.4977, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.849929865962422e-05, + "loss": 3.5042, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.84909127121137e-05, + "loss": 3.5057, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482543143406908e-05, + "loss": 3.5063, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8474157195896388e-05, + "loss": 3.5076, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.846577124838587e-05, + "loss": 3.5084, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.845738530087535e-05, + "loss": 3.5045, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.844901573216856e-05, + "loss": 3.4905, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.844062978465804e-05, + "loss": 3.5037, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.843224383714752e-05, + "loss": 3.4945, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8423857889637e-05, + "loss": 3.4913, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8415488320930213e-05, + "loss": 3.503, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8407102373419692e-05, + "loss": 3.5078, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8398716425909172e-05, + "loss": 3.5001, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390330478398652e-05, + "loss": 3.4979, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8381944530888132e-05, + "loss": 3.5039, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.837357496218134e-05, + "loss": 3.507, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8365189014670825e-05, + "loss": 3.5049, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8356803067160305e-05, + "loss": 3.4938, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8348417119649785e-05, + "loss": 3.4988, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8340047550942994e-05, + "loss": 3.5026, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8331661603432474e-05, + "loss": 3.4983, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8323275655921954e-05, + "loss": 3.4988, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8314889708411434e-05, + "loss": 3.4923, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306520139704646e-05, + "loss": 3.5051, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8298134192194126e-05, + "loss": 3.4811, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8289748244683606e-05, + "loss": 3.5059, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281362297173086e-05, + "loss": 3.4998, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8272992728466295e-05, + "loss": 3.4976, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.826460678095578e-05, + "loss": 3.506, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.825622083344526e-05, + "loss": 3.4969, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.824783488593474e-05, + "loss": 3.4913, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239465317227947e-05, + "loss": 3.5053, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8231079369717427e-05, + "loss": 3.4822, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8222693422206907e-05, + "loss": 3.4834, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8214307474696387e-05, + "loss": 3.4997, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.82059379059896e-05, + "loss": 3.5, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.819755195847908e-05, + "loss": 3.4961, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.818916601096856e-05, + "loss": 3.4848, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.818078006345804e-05, + "loss": 3.489, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.817241049475125e-05, + "loss": 3.4955, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8164024547240732e-05, + "loss": 3.5029, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8155638599730212e-05, + "loss": 3.495, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8147252652219692e-05, + "loss": 3.5031, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.81388830835129e-05, + "loss": 3.5019, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.813049713600238e-05, + "loss": 3.5048, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.812211118849186e-05, + "loss": 3.4885, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.811372524098134e-05, + "loss": 3.4931, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105355672274553e-05, + "loss": 3.5025, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8096969724764033e-05, + "loss": 3.4921, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8088583777253513e-05, + "loss": 3.497, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8080197829742993e-05, + "loss": 3.4931, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8071828261036202e-05, + "loss": 3.5108, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063442313525686e-05, + "loss": 3.492, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8055056366015166e-05, + "loss": 3.4844, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8046670418504646e-05, + "loss": 3.4918, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8038300849797855e-05, + "loss": 3.5002, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8029914902287335e-05, + "loss": 3.5058, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8021528954776815e-05, + "loss": 3.4904, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8013143007266295e-05, + "loss": 3.4909, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8004773438559507e-05, + "loss": 3.5018, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996387491048987e-05, + "loss": 3.4925, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7988001543538467e-05, + "loss": 3.4862, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7979615596027947e-05, + "loss": 3.4937, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7971246027321156e-05, + "loss": 3.5018, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7962860079810636e-05, + "loss": 3.5036, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.795447413230012e-05, + "loss": 3.4994, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.79460881847896e-05, + "loss": 3.4854, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.793771861608281e-05, + "loss": 3.496, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.792933266857229e-05, + "loss": 3.4927, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.792094672106177e-05, + "loss": 3.4984, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.791256077355125e-05, + "loss": 3.4934, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.790419120484446e-05, + "loss": 3.4926, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.789580525733394e-05, + "loss": 3.4869, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.788741930982342e-05, + "loss": 3.498, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.78790333623129e-05, + "loss": 3.4727, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.787066379360611e-05, + "loss": 3.4946, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.786227784609559e-05, + "loss": 3.4867, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7853891898585073e-05, + "loss": 3.4986, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7845505951074546e-05, + "loss": 3.4848, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7837136382367762e-05, + "loss": 3.4971, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7828750434857242e-05, + "loss": 3.4891, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7820364487346722e-05, + "loss": 3.4927, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.78119785398362e-05, + "loss": 3.4994, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.780359259232568e-05, + "loss": 3.4908, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7795223023618894e-05, + "loss": 3.5008, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7786837076108374e-05, + "loss": 3.5079, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7778451128597848e-05, + "loss": 3.4944, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7770065181087328e-05, + "loss": 3.4933, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7761695612380543e-05, + "loss": 3.4965, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.775330966487002e-05, + "loss": 3.4962, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.77449237173595e-05, + "loss": 3.484, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.773653776984898e-05, + "loss": 3.4996, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7728168201142196e-05, + "loss": 3.4889, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7719782253631672e-05, + "loss": 3.4966, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7711396306121152e-05, + "loss": 3.4891, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7703010358610632e-05, + "loss": 3.4918, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694640789903848e-05, + "loss": 3.4803, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.768625484239332e-05, + "loss": 3.4851, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.76778688948828e-05, + "loss": 3.4818, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.766948294737228e-05, + "loss": 3.5003, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7661113378665494e-05, + "loss": 3.5121, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7652727431154974e-05, + "loss": 3.4969, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7644341483644454e-05, + "loss": 3.4804, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7635955536133934e-05, + "loss": 3.5002, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7627585967427143e-05, + "loss": 3.4929, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7619200019916626e-05, + "loss": 3.491, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7610814072406106e-05, + "loss": 3.4871, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7602428124895586e-05, + "loss": 3.4989, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7594058556188795e-05, + "loss": 3.4885, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7585672608678275e-05, + "loss": 3.4945, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577286661167755e-05, + "loss": 3.4924, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7568900713657235e-05, + "loss": 3.4974, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560531144950447e-05, + "loss": 3.4954, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7552145197439927e-05, + "loss": 3.484, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7543759249929407e-05, + "loss": 3.5047, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535373302418887e-05, + "loss": 3.4968, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7527003733712096e-05, + "loss": 3.4919, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.751861778620158e-05, + "loss": 3.499, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.751023183869106e-05, + "loss": 3.4857, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.8662986755371094, + "eval_runtime": 303.6558, + "eval_samples_per_second": 1256.656, + "eval_steps_per_second": 39.271, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.750184589118054e-05, + "loss": 3.4795, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.749345994367002e-05, + "loss": 3.4897, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.74850739961595e-05, + "loss": 3.5005, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.747668804864898e-05, + "loss": 3.4975, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.746831847994219e-05, + "loss": 3.4996, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7459932532431672e-05, + "loss": 3.4842, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451546584921152e-05, + "loss": 3.494, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443160637410632e-05, + "loss": 3.4765, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.743479106870384e-05, + "loss": 3.5019, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.742640512119332e-05, + "loss": 3.4834, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.74180191736828e-05, + "loss": 3.4971, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.740963322617228e-05, + "loss": 3.4924, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7401263657465493e-05, + "loss": 3.4913, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7392877709954973e-05, + "loss": 3.4821, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384491762444453e-05, + "loss": 3.4829, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7376105814933933e-05, + "loss": 3.481, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7367736246227142e-05, + "loss": 3.4889, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7359350298716626e-05, + "loss": 3.4907, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7350964351206105e-05, + "loss": 3.4926, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7342578403695585e-05, + "loss": 3.5077, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7334208834988795e-05, + "loss": 3.4998, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7325822887478274e-05, + "loss": 3.4955, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317436939967754e-05, + "loss": 3.49, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7309050992457234e-05, + "loss": 3.5001, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7300681423750447e-05, + "loss": 3.484, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292295476239927e-05, + "loss": 3.4952, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7283909528729407e-05, + "loss": 3.4946, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275523581218887e-05, + "loss": 3.49, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7267154012512096e-05, + "loss": 3.4789, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.725876806500158e-05, + "loss": 3.4825, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.725038211749106e-05, + "loss": 3.491, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.724199616998054e-05, + "loss": 3.4936, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233626601273748e-05, + "loss": 3.4974, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225240653763228e-05, + "loss": 3.4937, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7216854706252708e-05, + "loss": 3.4929, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7208468758742188e-05, + "loss": 3.4902, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.72000991900354e-05, + "loss": 3.4797, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.719171324252488e-05, + "loss": 3.4942, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.718332729501436e-05, + "loss": 3.48, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.717494134750384e-05, + "loss": 3.4814, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.716657177879705e-05, + "loss": 3.4867, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.715818583128653e-05, + "loss": 3.4963, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7149799883776013e-05, + "loss": 3.4855, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141413936265493e-05, + "loss": 3.4821, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7133044367558702e-05, + "loss": 3.4959, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7124658420048182e-05, + "loss": 3.4894, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116272472537662e-05, + "loss": 3.4943, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7107886525027142e-05, + "loss": 3.4805, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099516956320354e-05, + "loss": 3.48, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7091131008809834e-05, + "loss": 3.4929, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7082745061299314e-05, + "loss": 3.4849, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074359113788794e-05, + "loss": 3.4876, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7065989545082003e-05, + "loss": 3.4805, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057603597571483e-05, + "loss": 3.4861, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049217650060966e-05, + "loss": 3.4753, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7040831702550446e-05, + "loss": 3.4885, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032462133843656e-05, + "loss": 3.4847, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7024076186333135e-05, + "loss": 3.4859, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7015690238822615e-05, + "loss": 3.4926, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007304291312095e-05, + "loss": 3.4811, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6998934722605308e-05, + "loss": 3.4766, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990548775094788e-05, + "loss": 3.4979, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6982162827584268e-05, + "loss": 3.4718, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6973776880073748e-05, + "loss": 3.4695, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6965407311366957e-05, + "loss": 3.4852, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6957021363856437e-05, + "loss": 3.491, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.694863541634592e-05, + "loss": 3.4827, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.69402494688354e-05, + "loss": 3.4739, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.693187990012861e-05, + "loss": 3.4767, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.692349395261809e-05, + "loss": 3.4773, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.691510800510757e-05, + "loss": 3.4899, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6906722057597046e-05, + "loss": 3.4825, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.689835248889026e-05, + "loss": 3.4892, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.688996654137974e-05, + "loss": 3.4859, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.688158059386922e-05, + "loss": 3.4953, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873194646358695e-05, + "loss": 3.4765, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.686482507765191e-05, + "loss": 3.4811, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.685643913014139e-05, + "loss": 3.487, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6848053182630874e-05, + "loss": 3.4756, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6839667235120347e-05, + "loss": 3.487, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6831297666413563e-05, + "loss": 3.4806, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6822911718903043e-05, + "loss": 3.4959, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.681452577139252e-05, + "loss": 3.4815, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6806139823882e-05, + "loss": 3.4716, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797770255175215e-05, + "loss": 3.4766, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789384307664695e-05, + "loss": 3.4856, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.678099836015417e-05, + "loss": 3.4968, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772612412643648e-05, + "loss": 3.479, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764242843936864e-05, + "loss": 3.482, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.675585689642634e-05, + "loss": 3.478, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.674747094891582e-05, + "loss": 3.4883, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.67390850014053e-05, + "loss": 3.475, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730715432698517e-05, + "loss": 3.4761, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.672232948518799e-05, + "loss": 3.4893, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6713943537677473e-05, + "loss": 3.49, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6705557590166953e-05, + "loss": 3.4871, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.669718802146017e-05, + "loss": 3.4729, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6688802073949642e-05, + "loss": 3.4817, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6680416126439122e-05, + "loss": 3.4773, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6672030178928602e-05, + "loss": 3.4846, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6663660610221814e-05, + "loss": 3.4835, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6655274662711294e-05, + "loss": 3.4776, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6646888715200774e-05, + "loss": 3.4745, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6638502767690254e-05, + "loss": 3.4842, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6630133198983463e-05, + "loss": 3.4642, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6621747251472943e-05, + "loss": 3.4778, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6613361303962427e-05, + "loss": 3.4719, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6604975356451907e-05, + "loss": 3.4876, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6596605787745116e-05, + "loss": 3.476, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6588219840234596e-05, + "loss": 3.4822, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6579833892724076e-05, + "loss": 3.476, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571447945213556e-05, + "loss": 3.4805, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6563078376506768e-05, + "loss": 3.4864, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554692428996248e-05, + "loss": 3.4803, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546306481485728e-05, + "loss": 3.4891, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6537920533975208e-05, + "loss": 3.4928, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529550965268417e-05, + "loss": 3.4838, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521165017757897e-05, + "loss": 3.4803, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.651277907024738e-05, + "loss": 3.4767, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.650439312273686e-05, + "loss": 3.4869, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.649602355403007e-05, + "loss": 3.4726, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.648763760651955e-05, + "loss": 3.4852, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.647925165900903e-05, + "loss": 3.4745, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.647086571149851e-05, + "loss": 3.4834, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462496142791722e-05, + "loss": 3.4785, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454110195281202e-05, + "loss": 3.4805, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6445724247770682e-05, + "loss": 3.4644, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.643733830026016e-05, + "loss": 3.4763, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.642896873155337e-05, + "loss": 3.4731, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.642058278404285e-05, + "loss": 3.4813, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6412196836532334e-05, + "loss": 3.4959, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6403827267825543e-05, + "loss": 3.4891, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395441320315023e-05, + "loss": 3.4646, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6387055372804503e-05, + "loss": 3.4924, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6378669425293983e-05, + "loss": 3.4797, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370299856587196e-05, + "loss": 3.4792, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6361913909076675e-05, + "loss": 3.4686, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6353527961566155e-05, + "loss": 3.4873, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6345142014055635e-05, + "loss": 3.4778, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6336772445348844e-05, + "loss": 3.4821, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328386497838324e-05, + "loss": 3.4811, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6320000550327804e-05, + "loss": 3.4833, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311614602817288e-05, + "loss": 3.4831, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303245034110497e-05, + "loss": 3.4744, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6294859086599977e-05, + "loss": 3.4884, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286473139089457e-05, + "loss": 3.4851, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6278087191578937e-05, + "loss": 3.4808, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.626971762287215e-05, + "loss": 3.4863, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.626133167536163e-05, + "loss": 3.4733, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.8688669204711914, + "eval_runtime": 310.6141, + "eval_samples_per_second": 1228.505, + "eval_steps_per_second": 38.392, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.625294572785111e-05, + "loss": 3.4694, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.624455978034059e-05, + "loss": 3.478, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6236190211633798e-05, + "loss": 3.4851, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6227804264123278e-05, + "loss": 3.4822, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6219418316612758e-05, + "loss": 3.4926, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.621103236910224e-05, + "loss": 3.4694, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.620266280039545e-05, + "loss": 3.4825, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.619427685288493e-05, + "loss": 3.4601, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.618589090537441e-05, + "loss": 3.4916, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.617750495786389e-05, + "loss": 3.4724, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.616911901035337e-05, + "loss": 3.4826, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6160749441646583e-05, + "loss": 3.4824, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6152363494136063e-05, + "loss": 3.471, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6143977546625543e-05, + "loss": 3.474, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6135591599115023e-05, + "loss": 3.4702, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6127222030408232e-05, + "loss": 3.4663, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6118836082897712e-05, + "loss": 3.4793, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.611045013538719e-05, + "loss": 3.4768, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6102064187876675e-05, + "loss": 3.4784, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6093694619169884e-05, + "loss": 3.4934, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085308671659364e-05, + "loss": 3.4902, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6076922724148844e-05, + "loss": 3.4804, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6068536776638324e-05, + "loss": 3.4796, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6060167207931536e-05, + "loss": 3.4845, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6051781260421016e-05, + "loss": 3.4704, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6043395312910496e-05, + "loss": 3.4873, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6035009365399976e-05, + "loss": 3.4807, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6026639796693185e-05, + "loss": 3.4726, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6018253849182665e-05, + "loss": 3.4667, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6009867901672145e-05, + "loss": 3.4725, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.600148195416163e-05, + "loss": 3.4767, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5993112385454838e-05, + "loss": 3.4835, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5984726437944318e-05, + "loss": 3.4838, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5976340490433798e-05, + "loss": 3.4818, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5967954542923278e-05, + "loss": 3.4811, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.595958497421649e-05, + "loss": 3.4807, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.595119902670597e-05, + "loss": 3.4674, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.594281307919545e-05, + "loss": 3.4783, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.593442713168493e-05, + "loss": 3.4661, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.592605756297814e-05, + "loss": 3.4717, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.591767161546762e-05, + "loss": 3.4738, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.59092856679571e-05, + "loss": 3.4807, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5900899720446582e-05, + "loss": 3.4766, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.589253015173979e-05, + "loss": 3.4663, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.588414420422927e-05, + "loss": 3.4838, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.587575825671875e-05, + "loss": 3.483, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.586737230920823e-05, + "loss": 3.4785, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5859002740501444e-05, + "loss": 3.4711, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5850616792990924e-05, + "loss": 3.4637, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5842230845480404e-05, + "loss": 3.4831, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5833844897969884e-05, + "loss": 3.4716, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5825475329263093e-05, + "loss": 3.476, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5817089381752573e-05, + "loss": 3.4699, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5808703434242053e-05, + "loss": 3.4692, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5800317486731536e-05, + "loss": 3.463, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5791947918024745e-05, + "loss": 3.4742, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5783561970514225e-05, + "loss": 3.4745, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5775176023003705e-05, + "loss": 3.4761, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5766790075493185e-05, + "loss": 3.4763, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5758420506786397e-05, + "loss": 3.4662, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5750034559275877e-05, + "loss": 3.466, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5741648611765357e-05, + "loss": 3.4861, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5733262664254837e-05, + "loss": 3.4594, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5724893095548046e-05, + "loss": 3.454, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5716507148037526e-05, + "loss": 3.468, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5708121200527006e-05, + "loss": 3.4771, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.569975163182022e-05, + "loss": 3.4674, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.56913656843097e-05, + "loss": 3.4633, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.568297973679918e-05, + "loss": 3.4594, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.567459378928866e-05, + "loss": 3.4641, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5666224220581868e-05, + "loss": 3.4775, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.565783827307135e-05, + "loss": 3.4719, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.564945232556083e-05, + "loss": 3.4722, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.564106637805031e-05, + "loss": 3.4799, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.563269680934352e-05, + "loss": 3.4825, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5624310861833e-05, + "loss": 3.4662, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.561592491432248e-05, + "loss": 3.4691, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.560753896681196e-05, + "loss": 3.4761, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5599169398105172e-05, + "loss": 3.4598, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5590783450594652e-05, + "loss": 3.4745, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5582397503084132e-05, + "loss": 3.4679, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5574011555573612e-05, + "loss": 3.4849, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.556562560806309e-05, + "loss": 3.4675, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5557256039356305e-05, + "loss": 3.4615, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5548870091845785e-05, + "loss": 3.4618, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5540484144335258e-05, + "loss": 3.4731, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5532098196824738e-05, + "loss": 3.4844, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.5523728628117954e-05, + "loss": 3.4702, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5515342680607434e-05, + "loss": 3.4649, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.550695673309691e-05, + "loss": 3.4648, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5498587164390126e-05, + "loss": 3.4776, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5490201216879606e-05, + "loss": 3.4631, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5481815269369086e-05, + "loss": 3.4649, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.547342932185856e-05, + "loss": 3.476, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5465059753151775e-05, + "loss": 3.4794, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.545667380564126e-05, + "loss": 3.4738, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.544828785813073e-05, + "loss": 3.4589, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.543990191062021e-05, + "loss": 3.4732, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5431532341913427e-05, + "loss": 3.4631, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5423146394402907e-05, + "loss": 3.4732, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5414760446892384e-05, + "loss": 3.4711, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406374499381864e-05, + "loss": 3.4638, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.539800493067508e-05, + "loss": 3.4647, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5389618983164553e-05, + "loss": 3.4691, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5381233035654033e-05, + "loss": 3.4565, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5372847088143513e-05, + "loss": 3.469, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.536447751943673e-05, + "loss": 3.4557, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5356091571926205e-05, + "loss": 3.4758, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5347705624415685e-05, + "loss": 3.466, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5339319676905165e-05, + "loss": 3.4667, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.533095010819838e-05, + "loss": 3.464, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5322564160687858e-05, + "loss": 3.4693, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5314178213177338e-05, + "loss": 3.475, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5305792265666818e-05, + "loss": 3.4649, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5297422696960027e-05, + "loss": 3.4741, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5289036749449507e-05, + "loss": 3.4785, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5280650801938987e-05, + "loss": 3.4709, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5272264854428467e-05, + "loss": 3.4752, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.526389528572168e-05, + "loss": 3.4613, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.525550933821116e-05, + "loss": 3.4775, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.524712339070064e-05, + "loss": 3.464, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.523873744319012e-05, + "loss": 3.4685, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5230367874483328e-05, + "loss": 3.4622, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.522198192697281e-05, + "loss": 3.4724, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.521359597946229e-05, + "loss": 3.4647, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.520521003195177e-05, + "loss": 3.4651, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.519684046324498e-05, + "loss": 3.4561, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.518845451573446e-05, + "loss": 3.4603, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.518006856822394e-05, + "loss": 3.4655, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.517168262071342e-05, + "loss": 3.4667, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163313052006633e-05, + "loss": 3.4808, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5154927104496113e-05, + "loss": 3.4777, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146541156985593e-05, + "loss": 3.4534, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5138155209475073e-05, + "loss": 3.4809, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.512978564076828e-05, + "loss": 3.4645, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.512139969325776e-05, + "loss": 3.4671, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5113013745747245e-05, + "loss": 3.4597, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5104627798236725e-05, + "loss": 3.4708, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5096258229529934e-05, + "loss": 3.4636, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5087872282019414e-05, + "loss": 3.4759, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5079486334508894e-05, + "loss": 3.4658, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5071100386998374e-05, + "loss": 3.4687, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5062730818291586e-05, + "loss": 3.4755, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5054344870781066e-05, + "loss": 3.4596, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.5045958923270546e-05, + "loss": 3.4717, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5037572975760026e-05, + "loss": 3.4774, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5029203407053235e-05, + "loss": 3.4675, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5020817459542715e-05, + "loss": 3.4678, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.50124315120322e-05, + "loss": 3.4644, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.869727611541748, + "eval_runtime": 311.4466, + "eval_samples_per_second": 1225.221, + "eval_steps_per_second": 38.289, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500404556452168e-05, + "loss": 3.4561, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499565961701116e-05, + "loss": 3.4649, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498727366950064e-05, + "loss": 3.4704, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.497888772199012e-05, + "loss": 3.4729, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970518153283328e-05, + "loss": 3.4826, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4962132205772808e-05, + "loss": 3.4575, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.495374625826229e-05, + "loss": 3.4653, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494536031075177e-05, + "loss": 3.4534, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.493699074204498e-05, + "loss": 3.4757, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.492860479453446e-05, + "loss": 3.4624, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.492021884702394e-05, + "loss": 3.466, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.491183289951342e-05, + "loss": 3.4753, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903463330806632e-05, + "loss": 3.4577, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895077383296112e-05, + "loss": 3.4672, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886691435785592e-05, + "loss": 3.4579, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878305488275072e-05, + "loss": 3.4556, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.486993591956828e-05, + "loss": 3.4628, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.486154997205776e-05, + "loss": 3.4671, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4853164024547245e-05, + "loss": 3.4657, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844794455840454e-05, + "loss": 3.4781, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836408508329934e-05, + "loss": 3.4792, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4828022560819414e-05, + "loss": 3.4694, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819636613308894e-05, + "loss": 3.4702, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811267044602106e-05, + "loss": 3.4742, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802881097091586e-05, + "loss": 3.4565, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794495149581066e-05, + "loss": 3.474, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786109202070542e-05, + "loss": 3.4702, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4777739633363755e-05, + "loss": 3.459, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4769353685853235e-05, + "loss": 3.4553, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4760967738342715e-05, + "loss": 3.4578, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752581790832195e-05, + "loss": 3.4646, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744212222125407e-05, + "loss": 3.4705, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4735826274614887e-05, + "loss": 3.4733, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727440327104367e-05, + "loss": 3.4699, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4719054379593844e-05, + "loss": 3.4679, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.471068481088706e-05, + "loss": 3.4689, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.470229886337654e-05, + "loss": 3.4528, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4693912915866016e-05, + "loss": 3.4688, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685526968355496e-05, + "loss": 3.4514, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.467715739964871e-05, + "loss": 3.458, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.466877145213819e-05, + "loss": 3.4605, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.466038550462767e-05, + "loss": 3.4731, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.465199955711715e-05, + "loss": 3.4645, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.464361360960663e-05, + "loss": 3.4539, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.463524404089984e-05, + "loss": 3.4723, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4626858093389317e-05, + "loss": 3.4677, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4618472145878797e-05, + "loss": 3.4687, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610086198368277e-05, + "loss": 3.4591, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.460171662966149e-05, + "loss": 3.4512, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.459333068215097e-05, + "loss": 3.4715, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.458494473464045e-05, + "loss": 3.4588, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.457655878712993e-05, + "loss": 3.4646, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.456818921842314e-05, + "loss": 3.4571, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559803270912622e-05, + "loss": 3.4536, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551417323402102e-05, + "loss": 3.4545, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4543031375891582e-05, + "loss": 3.4623, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.453466180718479e-05, + "loss": 3.4613, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.452627585967427e-05, + "loss": 3.4631, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.451788991216375e-05, + "loss": 3.4689, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.450950396465323e-05, + "loss": 3.4555, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4501134395946444e-05, + "loss": 3.4512, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492748448435924e-05, + "loss": 3.4769, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484362500925403e-05, + "loss": 3.446, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4475976553414883e-05, + "loss": 3.4425, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467606984708093e-05, + "loss": 3.4576, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459221037197576e-05, + "loss": 3.4684, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450835089687056e-05, + "loss": 3.4518, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442449142176536e-05, + "loss": 3.4545, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434079573469745e-05, + "loss": 3.4475, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4425693625959225e-05, + "loss": 3.4534, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4417307678448705e-05, + "loss": 3.4634, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4408921730938185e-05, + "loss": 3.462, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4400552162231397e-05, + "loss": 3.4615, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4392166214720877e-05, + "loss": 3.4669, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4383780267210357e-05, + "loss": 3.4672, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375394319699837e-05, + "loss": 3.4579, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4367024750993046e-05, + "loss": 3.4592, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.435863880348253e-05, + "loss": 3.466, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.435025285597201e-05, + "loss": 3.4457, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.434186690846149e-05, + "loss": 3.4612, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.43334973397547e-05, + "loss": 3.4539, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.432511139224418e-05, + "loss": 3.4732, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.431672544473366e-05, + "loss": 3.4572, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.430833949722314e-05, + "loss": 3.4508, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.429996992851635e-05, + "loss": 3.4445, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.429158398100583e-05, + "loss": 3.4648, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.428319803349531e-05, + "loss": 3.4684, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.427481208598479e-05, + "loss": 3.4615, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266442517278e-05, + "loss": 3.4511, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4258056569767483e-05, + "loss": 3.4557, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249670622256963e-05, + "loss": 3.4632, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241284674746443e-05, + "loss": 3.4509, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4232915106039652e-05, + "loss": 3.4529, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4224529158529132e-05, + "loss": 3.4652, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4216143211018612e-05, + "loss": 3.4642, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207757263508092e-05, + "loss": 3.4617, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199387694801305e-05, + "loss": 3.448, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4191001747290785e-05, + "loss": 3.4596, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182615799780264e-05, + "loss": 3.4504, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.417422985226974e-05, + "loss": 3.4602, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4165860283562954e-05, + "loss": 3.4571, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4157474336052437e-05, + "loss": 3.456, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4149088388541917e-05, + "loss": 3.4519, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140702441031393e-05, + "loss": 3.4534, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132332872324606e-05, + "loss": 3.451, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4123946924814086e-05, + "loss": 3.4525, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115560977303562e-05, + "loss": 3.4452, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4107175029793046e-05, + "loss": 3.4623, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4098805461086258e-05, + "loss": 3.4547, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090419513575738e-05, + "loss": 3.453, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4082033566065215e-05, + "loss": 3.4524, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073647618554695e-05, + "loss": 3.4617, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065278049847907e-05, + "loss": 3.462, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4056892102337387e-05, + "loss": 3.4529, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4048506154826867e-05, + "loss": 3.4629, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4040120207316347e-05, + "loss": 3.467, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.403175063860956e-05, + "loss": 3.459, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023364691099036e-05, + "loss": 3.4624, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4014978743588516e-05, + "loss": 3.4494, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006592796078e-05, + "loss": 3.4625, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998223227371212e-05, + "loss": 3.4551, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.398983727986069e-05, + "loss": 3.4591, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.398145133235017e-05, + "loss": 3.4454, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.397306538483965e-05, + "loss": 3.4622, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.396469581613286e-05, + "loss": 3.4556, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.395630986862234e-05, + "loss": 3.4528, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.394792392111182e-05, + "loss": 3.4456, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.39395379736013e-05, + "loss": 3.4486, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.393116840489451e-05, + "loss": 3.4508, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.392278245738399e-05, + "loss": 3.4583, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.391439650987347e-05, + "loss": 3.4624, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3906010562362953e-05, + "loss": 3.4691, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897640993656162e-05, + "loss": 3.4415, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889255046145642e-05, + "loss": 3.4676, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3880869098635122e-05, + "loss": 3.4586, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3872483151124602e-05, + "loss": 3.4521, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3864113582417815e-05, + "loss": 3.448, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3855727634907294e-05, + "loss": 3.4625, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847341687396774e-05, + "loss": 3.4521, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3838972118689984e-05, + "loss": 3.4609, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830586171179463e-05, + "loss": 3.4521, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3822200223668943e-05, + "loss": 3.4556, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3813814276158423e-05, + "loss": 3.4615, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.3805444707451636e-05, + "loss": 3.4494, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3797058759941116e-05, + "loss": 3.4586, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3788672812430596e-05, + "loss": 3.4665, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780286864920076e-05, + "loss": 3.4578, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3771917296213285e-05, + "loss": 3.4545, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763531348702768e-05, + "loss": 3.4563, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8720314502716064, + "eval_runtime": 303.1928, + "eval_samples_per_second": 1258.575, + "eval_steps_per_second": 39.331, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.3755145401192248e-05, + "loss": 3.4487, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.3746759453681728e-05, + "loss": 3.4522, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3738389884974937e-05, + "loss": 3.4568, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3730003937464417e-05, + "loss": 3.464, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.3721617989953897e-05, + "loss": 3.4664, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3713232042443377e-05, + "loss": 3.4495, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.370486247373659e-05, + "loss": 3.454, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.369647652622607e-05, + "loss": 3.4448, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.368809057871555e-05, + "loss": 3.4605, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.367970463120503e-05, + "loss": 3.4529, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.367133506249824e-05, + "loss": 3.4532, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3662949114987722e-05, + "loss": 3.462, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3654563167477202e-05, + "loss": 3.4501, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.3646177219966682e-05, + "loss": 3.4525, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.363780765125989e-05, + "loss": 3.4494, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.362942170374937e-05, + "loss": 3.4418, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.362103575623885e-05, + "loss": 3.4485, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.361264980872833e-05, + "loss": 3.4548, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604280240021543e-05, + "loss": 3.4553, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3595894292511023e-05, + "loss": 3.4681, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3587508345000503e-05, + "loss": 3.4663, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.3579122397489983e-05, + "loss": 3.4573, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.3570752828783192e-05, + "loss": 3.459, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3562366881272676e-05, + "loss": 3.4595, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3553980933762155e-05, + "loss": 3.4457, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545594986251635e-05, + "loss": 3.4634, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3537225417544845e-05, + "loss": 3.4537, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3528839470034324e-05, + "loss": 3.4481, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.3520453522523804e-05, + "loss": 3.4451, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.3512067575013284e-05, + "loss": 3.4506, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3503698006306497e-05, + "loss": 3.4558, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3495312058795977e-05, + "loss": 3.4565, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3486926111285457e-05, + "loss": 3.4625, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3478540163774933e-05, + "loss": 3.456, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3470170595068146e-05, + "loss": 3.4552, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.346178464755763e-05, + "loss": 3.4572, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.345339870004711e-05, + "loss": 3.4487, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.3445012752536586e-05, + "loss": 3.4498, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3436643183829798e-05, + "loss": 3.4412, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3428257236319278e-05, + "loss": 3.4458, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3419871288808755e-05, + "loss": 3.447, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.3411485341298238e-05, + "loss": 3.4621, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.340311577259145e-05, + "loss": 3.4542, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.339472982508093e-05, + "loss": 3.4411, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.3386343877570407e-05, + "loss": 3.4638, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.3377957930059887e-05, + "loss": 3.4511, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.33695883613531e-05, + "loss": 3.4594, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.336120241384258e-05, + "loss": 3.4472, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.335281646633206e-05, + "loss": 3.4385, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.334443051882154e-05, + "loss": 3.4594, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.3336060950114752e-05, + "loss": 3.4494, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.332767500260423e-05, + "loss": 3.454, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.331928905509371e-05, + "loss": 3.4437, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.3310903107583192e-05, + "loss": 3.4437, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.3302533538876404e-05, + "loss": 3.4383, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.329414759136588e-05, + "loss": 3.4505, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.328576164385536e-05, + "loss": 3.4543, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.327737569634484e-05, + "loss": 3.4476, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3269006127638053e-05, + "loss": 3.4577, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3260620180127533e-05, + "loss": 3.4474, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252234232617013e-05, + "loss": 3.439, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3243848285106493e-05, + "loss": 3.4665, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.3235478716399702e-05, + "loss": 3.4323, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.3227092768889182e-05, + "loss": 3.4276, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.3218706821378662e-05, + "loss": 3.4469, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.3210320873868145e-05, + "loss": 3.4595, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3201951305161355e-05, + "loss": 3.4366, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3193565357650834e-05, + "loss": 3.4473, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.3185179410140314e-05, + "loss": 3.4359, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.3176793462629794e-05, + "loss": 3.4413, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.3168423893923007e-05, + "loss": 3.454, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.3160037946412487e-05, + "loss": 3.4502, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.3151651998901967e-05, + "loss": 3.4511, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3143266051391447e-05, + "loss": 3.4512, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3134896482684656e-05, + "loss": 3.4578, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3126510535174136e-05, + "loss": 3.4421, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.3118124587663616e-05, + "loss": 3.4493, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.31097386401531e-05, + "loss": 3.4496, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.3101369071446308e-05, + "loss": 3.4348, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.3092983123935788e-05, + "loss": 3.4483, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.3084597176425268e-05, + "loss": 3.4474, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076211228914748e-05, + "loss": 3.4559, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.306784166020796e-05, + "loss": 3.4512, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.305945571269744e-05, + "loss": 3.44, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.305106976518692e-05, + "loss": 3.4346, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.30426838176764e-05, + "loss": 3.4493, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.303431424896961e-05, + "loss": 3.4582, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.302592830145909e-05, + "loss": 3.4458, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.301754235394857e-05, + "loss": 3.4454, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.300915640643805e-05, + "loss": 3.4442, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3000786837731262e-05, + "loss": 3.4521, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.2992400890220742e-05, + "loss": 3.4428, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.2984014942710222e-05, + "loss": 3.4391, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.2975628995199702e-05, + "loss": 3.4553, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.2967259426492914e-05, + "loss": 3.4522, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2958873478982394e-05, + "loss": 3.4508, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2950487531471874e-05, + "loss": 3.4356, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2942101583961354e-05, + "loss": 3.4517, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.2933732015254563e-05, + "loss": 3.4371, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.2925346067744043e-05, + "loss": 3.45, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.2916960120233523e-05, + "loss": 3.4459, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908574172723003e-05, + "loss": 3.446, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2900204604016216e-05, + "loss": 3.4409, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2891818656505695e-05, + "loss": 3.4384, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883432708995175e-05, + "loss": 3.4453, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2875046761484655e-05, + "loss": 3.4385, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.2866677192777864e-05, + "loss": 3.4358, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2858291245267348e-05, + "loss": 3.4479, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2849905297756828e-05, + "loss": 3.4447, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2841519350246304e-05, + "loss": 3.4406, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.2833149781539517e-05, + "loss": 3.4361, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2824763834028997e-05, + "loss": 3.4459, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.2816377886518477e-05, + "loss": 3.4524, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.2807991939007957e-05, + "loss": 3.4423, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.279962237030117e-05, + "loss": 3.4514, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.279123642279065e-05, + "loss": 3.4543, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2782850475280126e-05, + "loss": 3.449, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.2774480906573338e-05, + "loss": 3.4486, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.2766094959062818e-05, + "loss": 3.441, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.27577090115523e-05, + "loss": 3.4481, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.2749323064041778e-05, + "loss": 3.4455, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.274095349533499e-05, + "loss": 3.4484, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.273256754782447e-05, + "loss": 3.4357, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.272418160031395e-05, + "loss": 3.4473, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.271579565280343e-05, + "loss": 3.4449, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2707426084096643e-05, + "loss": 3.442, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.2699040136586123e-05, + "loss": 3.4328, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.26906541890756e-05, + "loss": 3.4399, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.268226824156508e-05, + "loss": 3.438, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2673898672858292e-05, + "loss": 3.4464, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665512725347772e-05, + "loss": 3.449, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2657126777837252e-05, + "loss": 3.4575, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.2648740830326732e-05, + "loss": 3.4323, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.2640371261619944e-05, + "loss": 3.4567, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.2631985314109424e-05, + "loss": 3.4474, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.26235993665989e-05, + "loss": 3.4404, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.2615213419088384e-05, + "loss": 3.436, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2606843850381597e-05, + "loss": 3.4537, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2598457902871073e-05, + "loss": 3.436, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2590071955360553e-05, + "loss": 3.453, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.2581686007850033e-05, + "loss": 3.4379, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.2573316439143246e-05, + "loss": 3.4486, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.2564930491632725e-05, + "loss": 3.4483, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.2556544544122205e-05, + "loss": 3.441, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2548158596611685e-05, + "loss": 3.4542, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2539789027904898e-05, + "loss": 3.4486, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2531403080394374e-05, + "loss": 3.4513, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.2523017132883854e-05, + "loss": 3.4356, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.2514631185373338e-05, + "loss": 3.4494, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.872992992401123, + "eval_runtime": 303.7721, + "eval_samples_per_second": 1256.175, + "eval_steps_per_second": 39.256, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2506245237862818e-05, + "loss": 3.4407, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2497859290352298e-05, + "loss": 3.4382, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2489473342841778e-05, + "loss": 3.4424, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2481087395331254e-05, + "loss": 3.4532, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2472717826624467e-05, + "loss": 3.4563, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464331879113947e-05, + "loss": 3.4362, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.2455945931603427e-05, + "loss": 3.4432, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.2447559984092907e-05, + "loss": 3.4322, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.243919041538612e-05, + "loss": 3.4499, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.24308044678756e-05, + "loss": 3.439, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.242241852036508e-05, + "loss": 3.4461, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2414032572854555e-05, + "loss": 3.4472, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.240566300414777e-05, + "loss": 3.4393, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.239727705663725e-05, + "loss": 3.4447, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2388891109126728e-05, + "loss": 3.4357, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2380505161616208e-05, + "loss": 3.4307, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.237213559290942e-05, + "loss": 3.4356, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.23637496453989e-05, + "loss": 3.4478, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.235536369788838e-05, + "loss": 3.4415, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.234697775037786e-05, + "loss": 3.4586, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338608181671073e-05, + "loss": 3.4508, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2330222234160553e-05, + "loss": 3.4499, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.232183628665003e-05, + "loss": 3.4457, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.231345033913951e-05, + "loss": 3.4477, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2305080770432725e-05, + "loss": 3.4343, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.22966948229222e-05, + "loss": 3.4547, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.228830887541168e-05, + "loss": 3.4418, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.227992292790116e-05, + "loss": 3.4363, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2271553359194374e-05, + "loss": 3.4368, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2263167411683854e-05, + "loss": 3.4406, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2254781464173334e-05, + "loss": 3.4415, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2246395516662814e-05, + "loss": 3.4492, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2238025947956026e-05, + "loss": 3.4481, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2229640000445503e-05, + "loss": 3.4507, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2221254052934983e-05, + "loss": 3.4381, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2212868105424463e-05, + "loss": 3.4453, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2204498536717675e-05, + "loss": 3.4402, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2196112589207155e-05, + "loss": 3.4338, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2187726641696635e-05, + "loss": 3.4295, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2179340694186115e-05, + "loss": 3.4334, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2170971125479324e-05, + "loss": 3.4376, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2162585177968808e-05, + "loss": 3.4514, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2154199230458288e-05, + "loss": 3.4405, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.2145829661751497e-05, + "loss": 3.4292, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2137443714240977e-05, + "loss": 3.4543, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2129057766730457e-05, + "loss": 3.4385, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2120671819219937e-05, + "loss": 3.448, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.211230225051315e-05, + "loss": 3.4357, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.210391630300263e-05, + "loss": 3.4224, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.209553035549211e-05, + "loss": 3.4522, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.208714440798159e-05, + "loss": 3.4352, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2078774839274798e-05, + "loss": 3.4445, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2070388891764278e-05, + "loss": 3.4355, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2062002944253758e-05, + "loss": 3.4353, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.205361699674324e-05, + "loss": 3.4247, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.204524742803645e-05, + "loss": 3.435, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.203686148052593e-05, + "loss": 3.4482, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2028491911819143e-05, + "loss": 3.433, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2020105964308623e-05, + "loss": 3.4467, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011720016798103e-05, + "loss": 3.4393, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003334069287583e-05, + "loss": 3.4289, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1994948121777063e-05, + "loss": 3.4517, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1986562174266543e-05, + "loss": 3.4239, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1978176226756022e-05, + "loss": 3.4166, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1969790279245502e-05, + "loss": 3.4394, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.196142071053871e-05, + "loss": 3.4436, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1953034763028195e-05, + "loss": 3.4247, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944648815517675e-05, + "loss": 3.4379, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.193626286800715e-05, + "loss": 3.4227, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1927893299300364e-05, + "loss": 3.4363, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.1919507351789844e-05, + "loss": 3.4416, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.1911121404279324e-05, + "loss": 3.4352, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.1902735456768804e-05, + "loss": 3.4424, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1894365888062016e-05, + "loss": 3.4368, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1885979940551496e-05, + "loss": 3.4479, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1877593993040976e-05, + "loss": 3.4298, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1869208045530453e-05, + "loss": 3.4416, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1860838476823665e-05, + "loss": 3.4353, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.185245252931315e-05, + "loss": 3.4254, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1844066581802625e-05, + "loss": 3.4371, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1835680634292105e-05, + "loss": 3.4368, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827311065585318e-05, + "loss": 3.4466, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1818925118074798e-05, + "loss": 3.4445, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.1810539170564277e-05, + "loss": 3.4234, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.1802153223053757e-05, + "loss": 3.4235, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.179378365434697e-05, + "loss": 3.4389, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.178539770683645e-05, + "loss": 3.4467, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1777011759325926e-05, + "loss": 3.4362, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1768625811815406e-05, + "loss": 3.4305, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.176025624310862e-05, + "loss": 3.4364, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.17518702955981e-05, + "loss": 3.4362, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.174348434808758e-05, + "loss": 3.4336, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173509840057706e-05, + "loss": 3.4286, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.172672883187027e-05, + "loss": 3.4423, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1718342884359748e-05, + "loss": 3.441, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.170995693684923e-05, + "loss": 3.4395, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.170157098933871e-05, + "loss": 3.4267, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1693201420631924e-05, + "loss": 3.4342, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.16848154731214e-05, + "loss": 3.4298, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.167642952561088e-05, + "loss": 3.4392, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.166804357810036e-05, + "loss": 3.4338, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1659674009393573e-05, + "loss": 3.4333, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1651288061883053e-05, + "loss": 3.4338, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1642902114372532e-05, + "loss": 3.4266, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634516166862012e-05, + "loss": 3.4335, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.162614659815522e-05, + "loss": 3.4273, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.16177606506447e-05, + "loss": 3.4285, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.160937470313418e-05, + "loss": 3.4313, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1600988755623665e-05, + "loss": 3.4389, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592619186916874e-05, + "loss": 3.4252, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584233239406354e-05, + "loss": 3.4318, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1575847291895834e-05, + "loss": 3.4315, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.1567461344385314e-05, + "loss": 3.44, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.1559091775678526e-05, + "loss": 3.4314, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.1550705828168006e-05, + "loss": 3.4447, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1542319880657486e-05, + "loss": 3.4386, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1533933933146966e-05, + "loss": 3.44, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1525564364440175e-05, + "loss": 3.4348, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1517178416929655e-05, + "loss": 3.4341, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1508792469419135e-05, + "loss": 3.4331, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.150040652190862e-05, + "loss": 3.4364, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.1492036953201828e-05, + "loss": 3.4301, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1483651005691307e-05, + "loss": 3.4285, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1475265058180787e-05, + "loss": 3.439, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1466879110670267e-05, + "loss": 3.4358, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.145850954196348e-05, + "loss": 3.4308, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.145012359445296e-05, + "loss": 3.4183, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.144173764694244e-05, + "loss": 3.428, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.143335169943192e-05, + "loss": 3.4274, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.142498213072513e-05, + "loss": 3.4348, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.141659618321461e-05, + "loss": 3.4405, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.140821023570409e-05, + "loss": 3.4471, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.13998406669973e-05, + "loss": 3.4182, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.139145471948678e-05, + "loss": 3.4429, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.138306877197626e-05, + "loss": 3.4336, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.137468282446574e-05, + "loss": 3.4346, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.136631325575895e-05, + "loss": 3.425, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1357927308248434e-05, + "loss": 3.4391, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349541360737914e-05, + "loss": 3.4264, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1341155413227393e-05, + "loss": 3.4454, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1332785844520603e-05, + "loss": 3.4244, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1324399897010083e-05, + "loss": 3.4362, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1316013949499562e-05, + "loss": 3.4352, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1307628001989042e-05, + "loss": 3.4324, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299258433282255e-05, + "loss": 3.4382, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1290872485771735e-05, + "loss": 3.4368, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282486538261215e-05, + "loss": 3.4387, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1274100590750695e-05, + "loss": 3.4258, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1265731022043904e-05, + "loss": 3.4406, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.8751070499420166, + "eval_runtime": 302.7923, + "eval_samples_per_second": 1260.24, + "eval_steps_per_second": 39.383, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.1257345074533387e-05, + "loss": 3.4273, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1248959127022867e-05, + "loss": 3.4239, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.1240573179512347e-05, + "loss": 3.4344, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.1232203610805556e-05, + "loss": 3.4401, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.1223817663295036e-05, + "loss": 3.4432, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.1215431715784516e-05, + "loss": 3.4258, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.1207045768273996e-05, + "loss": 3.4319, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.119867619956721e-05, + "loss": 3.4206, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.119029025205669e-05, + "loss": 3.4384, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.118190430454617e-05, + "loss": 3.4303, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.1173518357035645e-05, + "loss": 3.4322, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.1165148788328858e-05, + "loss": 3.4371, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.115676284081834e-05, + "loss": 3.4295, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.114837689330782e-05, + "loss": 3.426, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.1139990945797297e-05, + "loss": 3.4259, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.113162137709051e-05, + "loss": 3.4183, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.112323542957999e-05, + "loss": 3.4277, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.111484948206947e-05, + "loss": 3.4355, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.110646353455895e-05, + "loss": 3.4316, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.1098093965852162e-05, + "loss": 3.4431, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.1089708018341642e-05, + "loss": 3.4438, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.108132207083112e-05, + "loss": 3.4402, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.10729361233206e-05, + "loss": 3.4339, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.106456655461381e-05, + "loss": 3.4345, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.1056180607103295e-05, + "loss": 3.4304, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.104779465959277e-05, + "loss": 3.4426, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.103940871208225e-05, + "loss": 3.4283, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.1031039143375464e-05, + "loss": 3.4296, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.102265319586494e-05, + "loss": 3.4247, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.101426724835442e-05, + "loss": 3.4243, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1005881300843903e-05, + "loss": 3.4268, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.0997511732137116e-05, + "loss": 3.4356, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0989125784626592e-05, + "loss": 3.4369, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.0980739837116072e-05, + "loss": 3.4373, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.0972353889605552e-05, + "loss": 3.4247, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0963984320898765e-05, + "loss": 3.4377, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0955598373388245e-05, + "loss": 3.4339, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0947212425877725e-05, + "loss": 3.4204, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.0938826478367205e-05, + "loss": 3.4206, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.0930456909660414e-05, + "loss": 3.4211, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.0922070962149894e-05, + "loss": 3.429, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.0913685014639374e-05, + "loss": 3.4333, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.0905299067128857e-05, + "loss": 3.4316, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.0896929498422066e-05, + "loss": 3.4195, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.0888543550911546e-05, + "loss": 3.4438, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.0880157603401026e-05, + "loss": 3.4289, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.0871771655890506e-05, + "loss": 3.438, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.086340208718372e-05, + "loss": 3.4287, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.08550161396732e-05, + "loss": 3.4052, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.084663019216268e-05, + "loss": 3.4441, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.083824424465216e-05, + "loss": 3.4235, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.0829874675945368e-05, + "loss": 3.4329, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.0821488728434847e-05, + "loss": 3.4255, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.0813102780924327e-05, + "loss": 3.4223, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.080471683341381e-05, + "loss": 3.4178, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.079634726470702e-05, + "loss": 3.4233, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.07879613171965e-05, + "loss": 3.4412, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.077959174848971e-05, + "loss": 3.4185, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.077120580097919e-05, + "loss": 3.435, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.0762819853468672e-05, + "loss": 3.4308, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.0754433905958152e-05, + "loss": 3.4142, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.0746047958447632e-05, + "loss": 3.4365, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.0737662010937112e-05, + "loss": 3.4186, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.0729276063426592e-05, + "loss": 3.4081, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.072089011591607e-05, + "loss": 3.4235, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.071252054720928e-05, + "loss": 3.43, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0704134599698764e-05, + "loss": 3.4161, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0695748652188244e-05, + "loss": 3.4264, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.068736270467772e-05, + "loss": 3.413, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.0678993135970933e-05, + "loss": 3.4216, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.0670607188460413e-05, + "loss": 3.4298, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.066222124094989e-05, + "loss": 3.4235, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0653835293439373e-05, + "loss": 3.4342, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0645465724732586e-05, + "loss": 3.4243, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0637079777222066e-05, + "loss": 3.435, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.0628693829711542e-05, + "loss": 3.4245, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.0620307882201022e-05, + "loss": 3.4311, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.0611938313494235e-05, + "loss": 3.4193, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0603552365983718e-05, + "loss": 3.4163, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0595166418473195e-05, + "loss": 3.4246, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0586780470962675e-05, + "loss": 3.429, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0578410902255887e-05, + "loss": 3.4334, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.0570024954745364e-05, + "loss": 3.4349, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.0561639007234844e-05, + "loss": 3.4092, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.0553253059724327e-05, + "loss": 3.4143, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.054488349101754e-05, + "loss": 3.428, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.0536497543507016e-05, + "loss": 3.4348, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0528111595996496e-05, + "loss": 3.4289, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0519725648485976e-05, + "loss": 3.4159, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.051135607977919e-05, + "loss": 3.4288, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.050297013226867e-05, + "loss": 3.424, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.049458418475815e-05, + "loss": 3.4239, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.0486198237247628e-05, + "loss": 3.416, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.0477828668540837e-05, + "loss": 3.4279, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.0469442721030317e-05, + "loss": 3.4325, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0461056773519797e-05, + "loss": 3.43, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.045267082600928e-05, + "loss": 3.4192, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.044430125730249e-05, + "loss": 3.4198, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.043591530979197e-05, + "loss": 3.4177, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.042752936228145e-05, + "loss": 3.4294, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.041914341477093e-05, + "loss": 3.4235, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.0410773846064142e-05, + "loss": 3.4212, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.0402387898553622e-05, + "loss": 3.421, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.0394001951043102e-05, + "loss": 3.4185, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.0385616003532582e-05, + "loss": 3.4198, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.037724643482579e-05, + "loss": 3.4141, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.036886048731527e-05, + "loss": 3.4195, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.036047453980475e-05, + "loss": 3.419, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.0352088592294234e-05, + "loss": 3.4263, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.0343719023587443e-05, + "loss": 3.4149, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.0335333076076923e-05, + "loss": 3.4123, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.0326947128566403e-05, + "loss": 3.4239, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.0318561181055883e-05, + "loss": 3.4266, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.0310191612349096e-05, + "loss": 3.423, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0301805664838576e-05, + "loss": 3.4286, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.0293419717328056e-05, + "loss": 3.4281, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.0285033769817536e-05, + "loss": 3.4331, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.0276664201110745e-05, + "loss": 3.4213, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.0268278253600225e-05, + "loss": 3.4214, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.0259892306089705e-05, + "loss": 3.4197, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.0251506358579188e-05, + "loss": 3.4311, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.0243136789872397e-05, + "loss": 3.4192, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.0234750842361877e-05, + "loss": 3.4162, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.0226364894851357e-05, + "loss": 3.4245, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.0217978947340837e-05, + "loss": 3.4302, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.020960937863405e-05, + "loss": 3.4157, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.020122343112353e-05, + "loss": 3.4104, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.019283748361301e-05, + "loss": 3.4149, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.018445153610249e-05, + "loss": 3.4186, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.01760819673957e-05, + "loss": 3.4234, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.016769601988518e-05, + "loss": 3.4285, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.0159310072374658e-05, + "loss": 3.4343, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.015092412486414e-05, + "loss": 3.4093, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.014255455615735e-05, + "loss": 3.4362, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.013416860864683e-05, + "loss": 3.4219, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.012578266113631e-05, + "loss": 3.4201, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.011741309242952e-05, + "loss": 3.4133, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0109027144919003e-05, + "loss": 3.4272, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0100641197408483e-05, + "loss": 3.4158, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.0092255249897963e-05, + "loss": 3.4357, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.0083885681191172e-05, + "loss": 3.4135, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.0075499733680652e-05, + "loss": 3.4239, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.0067113786170132e-05, + "loss": 3.4246, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.0058727838659612e-05, + "loss": 3.4262, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0050358269952824e-05, + "loss": 3.4223, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0041972322442304e-05, + "loss": 3.4239, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.0033586374931784e-05, + "loss": 3.4313, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.0025216806224993e-05, + "loss": 3.4156, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.0016830858714473e-05, + "loss": 3.4292, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.8765103816986084, + "eval_runtime": 301.818, + "eval_samples_per_second": 1264.308, + "eval_steps_per_second": 39.511, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.0008444911203957e-05, + "loss": 3.4166, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 2.0000058963693437e-05, + "loss": 3.4166, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.9991673016182913e-05, + "loss": 3.4216, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.9983287068672393e-05, + "loss": 3.429, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.9974917499965606e-05, + "loss": 3.4343, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.9966531552455086e-05, + "loss": 3.4139, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.9958145604944566e-05, + "loss": 3.4245, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.9949759657434046e-05, + "loss": 3.4127, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.9941390088727258e-05, + "loss": 3.4217, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9933004141216735e-05, + "loss": 3.42, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9924618193706215e-05, + "loss": 3.4216, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.9916232246195695e-05, + "loss": 3.4252, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.990786267748891e-05, + "loss": 3.4211, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.9899476729978387e-05, + "loss": 3.4133, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9891090782467867e-05, + "loss": 3.4165, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9882704834957347e-05, + "loss": 3.4064, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.987433526625056e-05, + "loss": 3.4151, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9865949318740036e-05, + "loss": 3.4279, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.985756337122952e-05, + "loss": 3.4176, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.9849177423719e-05, + "loss": 3.4328, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.984080785501221e-05, + "loss": 3.4308, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9832421907501688e-05, + "loss": 3.4279, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9824035959991168e-05, + "loss": 3.4283, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9815650012480648e-05, + "loss": 3.417, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.980728044377386e-05, + "loss": 3.4168, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.979889449626334e-05, + "loss": 3.4293, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.979050854875282e-05, + "loss": 3.4232, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.97821226012423e-05, + "loss": 3.4203, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.977375303253551e-05, + "loss": 3.4158, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.976536708502499e-05, + "loss": 3.4155, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9756981137514473e-05, + "loss": 3.4118, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9748595190003953e-05, + "loss": 3.4269, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.9740225621297162e-05, + "loss": 3.4251, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.9731839673786642e-05, + "loss": 3.4267, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.9723453726276122e-05, + "loss": 3.4175, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.9715067778765602e-05, + "loss": 3.4261, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.9706698210058814e-05, + "loss": 3.4232, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.9698312262548294e-05, + "loss": 3.4102, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.9689926315037774e-05, + "loss": 3.4163, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.9681540367527254e-05, + "loss": 3.4091, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.9673170798820463e-05, + "loss": 3.4164, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.9664784851309943e-05, + "loss": 3.4256, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.9656398903799427e-05, + "loss": 3.4196, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.9648012956288907e-05, + "loss": 3.4126, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9639643387582116e-05, + "loss": 3.4264, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.9631257440071596e-05, + "loss": 3.4168, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.9622871492561076e-05, + "loss": 3.4288, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.9614485545050556e-05, + "loss": 3.4199, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.9606115976343768e-05, + "loss": 3.3937, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.9597730028833248e-05, + "loss": 3.4336, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.9589344081322728e-05, + "loss": 3.4135, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.9580958133812208e-05, + "loss": 3.4203, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.9572588565105417e-05, + "loss": 3.415, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.9564202617594897e-05, + "loss": 3.4109, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.955581667008438e-05, + "loss": 3.4051, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.954743072257386e-05, + "loss": 3.4136, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.953906115386707e-05, + "loss": 3.4326, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.953069158516028e-05, + "loss": 3.4051, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.952230563764976e-05, + "loss": 3.4274, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.9513919690139242e-05, + "loss": 3.4181, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.9505533742628722e-05, + "loss": 3.4, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.94971477951182e-05, + "loss": 3.4295, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.948876184760768e-05, + "loss": 3.4077, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.9480375900097158e-05, + "loss": 3.3956, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9471989952586638e-05, + "loss": 3.4128, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.946362038387985e-05, + "loss": 3.4197, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9455234436369334e-05, + "loss": 3.4059, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.944684848885881e-05, + "loss": 3.4164, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.943846254134829e-05, + "loss": 3.4024, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.9430092972641503e-05, + "loss": 3.4068, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9421707025130983e-05, + "loss": 3.4196, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.941332107762046e-05, + "loss": 3.4163, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9404935130109943e-05, + "loss": 3.4199, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9396565561403155e-05, + "loss": 3.416, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9388179613892632e-05, + "loss": 3.4265, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.9379793666382112e-05, + "loss": 3.4101, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.9371407718871592e-05, + "loss": 3.4205, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.9363038150164804e-05, + "loss": 3.4078, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.9354652202654284e-05, + "loss": 3.4076, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.9346266255143764e-05, + "loss": 3.417, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9337880307633244e-05, + "loss": 3.4117, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.9329510738926457e-05, + "loss": 3.4227, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.9321124791415933e-05, + "loss": 3.426, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.9312738843905413e-05, + "loss": 3.3972, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.9304352896394897e-05, + "loss": 3.4043, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.9295983327688106e-05, + "loss": 3.4159, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9287597380177586e-05, + "loss": 3.4198, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9279211432667066e-05, + "loss": 3.4192, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.9270825485156545e-05, + "loss": 3.4098, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.9262455916449758e-05, + "loss": 3.4157, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.9254069968939238e-05, + "loss": 3.4124, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.9245684021428718e-05, + "loss": 3.4108, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.9237298073918198e-05, + "loss": 3.4083, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.9228928505211407e-05, + "loss": 3.4175, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.9220542557700887e-05, + "loss": 3.4239, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.9212156610190367e-05, + "loss": 3.4191, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.920377066267985e-05, + "loss": 3.4029, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.919540109397306e-05, + "loss": 3.4107, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.918701514646254e-05, + "loss": 3.4064, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.917862919895202e-05, + "loss": 3.418, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.91702432514415e-05, + "loss": 3.4141, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.916187368273471e-05, + "loss": 3.412, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.915348773522419e-05, + "loss": 3.4125, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.914510178771367e-05, + "loss": 3.4039, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.913671584020315e-05, + "loss": 3.4103, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.912834627149636e-05, + "loss": 3.4042, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.911996032398584e-05, + "loss": 3.4109, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.911157437647532e-05, + "loss": 3.4089, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.9103188428964804e-05, + "loss": 3.4163, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.9094818860258013e-05, + "loss": 3.4048, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.9086432912747493e-05, + "loss": 3.4063, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9078046965236973e-05, + "loss": 3.4084, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.9069661017726453e-05, + "loss": 3.4197, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9061291449019665e-05, + "loss": 3.4118, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9052905501509145e-05, + "loss": 3.4148, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9044519553998625e-05, + "loss": 3.4143, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9036149985291834e-05, + "loss": 3.428, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.9027764037781314e-05, + "loss": 3.4131, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.9019378090270794e-05, + "loss": 3.4117, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.9010992142760274e-05, + "loss": 3.4134, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.9002622574053487e-05, + "loss": 3.4186, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.8994236626542967e-05, + "loss": 3.4094, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8985850679032447e-05, + "loss": 3.4051, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8977464731521927e-05, + "loss": 3.4117, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.8969095162815136e-05, + "loss": 3.4181, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.896070921530462e-05, + "loss": 3.4083, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.89523232677941e-05, + "loss": 3.4013, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.894393732028358e-05, + "loss": 3.4046, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8935567751576788e-05, + "loss": 3.4053, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8927181804066268e-05, + "loss": 3.4149, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8918795856555748e-05, + "loss": 3.4165, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.8910409909045228e-05, + "loss": 3.4219, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.890204034033844e-05, + "loss": 3.3996, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.889365439282792e-05, + "loss": 3.4238, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.88852684453174e-05, + "loss": 3.4126, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.887688249780688e-05, + "loss": 3.4118, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.886851292910009e-05, + "loss": 3.4044, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.886012698158957e-05, + "loss": 3.4068, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.8851741034079053e-05, + "loss": 3.4063, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.884335508656853e-05, + "loss": 3.426, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.883498551786174e-05, + "loss": 3.4017, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.882659957035122e-05, + "loss": 3.4144, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.88182136228407e-05, + "loss": 3.4163, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.880982767533018e-05, + "loss": 3.4164, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8801458106623394e-05, + "loss": 3.4072, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8793072159112874e-05, + "loss": 3.4163, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8784686211602354e-05, + "loss": 3.4182, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.877630026409183e-05, + "loss": 3.4062, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.8767930695385043e-05, + "loss": 3.417, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.8777248859405518, + "eval_runtime": 305.2216, + "eval_samples_per_second": 1250.21, + "eval_steps_per_second": 39.07, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8759544747874523e-05, + "loss": 3.4083, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8751158800364003e-05, + "loss": 3.4031, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8742772852853483e-05, + "loss": 3.4093, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8734386905342963e-05, + "loss": 3.4199, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8726017336636175e-05, + "loss": 3.4236, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8717631389125652e-05, + "loss": 3.4041, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8709245441615135e-05, + "loss": 3.4139, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8700859494104615e-05, + "loss": 3.3994, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8692489925397828e-05, + "loss": 3.4125, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8684103977887304e-05, + "loss": 3.4103, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8675718030376784e-05, + "loss": 3.4104, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8667332082866264e-05, + "loss": 3.4141, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.8658962514159477e-05, + "loss": 3.4172, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.8650576566648957e-05, + "loss": 3.401, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.8642190619138436e-05, + "loss": 3.4032, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.8633804671627916e-05, + "loss": 3.393, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8625435102921126e-05, + "loss": 3.4085, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8617049155410605e-05, + "loss": 3.419, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.860866320790009e-05, + "loss": 3.4052, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.860027726038957e-05, + "loss": 3.4188, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8591907691682778e-05, + "loss": 3.425, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.8583521744172258e-05, + "loss": 3.4185, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.8575135796661738e-05, + "loss": 3.4139, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8566749849151218e-05, + "loss": 3.4079, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.855838028044443e-05, + "loss": 3.4091, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.854999433293391e-05, + "loss": 3.4139, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.854160838542339e-05, + "loss": 3.4146, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.853322243791287e-05, + "loss": 3.4151, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.852485286920608e-05, + "loss": 3.4028, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.851646692169556e-05, + "loss": 3.4005, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.8508080974185042e-05, + "loss": 3.4032, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.8499695026674522e-05, + "loss": 3.4169, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.849132545796773e-05, + "loss": 3.4187, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.848293951045721e-05, + "loss": 3.4147, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.847455356294669e-05, + "loss": 3.4074, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.846616761543617e-05, + "loss": 3.4099, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.8457798046729384e-05, + "loss": 3.4145, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8449412099218864e-05, + "loss": 3.4021, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8441026151708344e-05, + "loss": 3.4021, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8432640204197824e-05, + "loss": 3.3995, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8424270635491033e-05, + "loss": 3.4049, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8415884687980513e-05, + "loss": 3.4152, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8407498740469993e-05, + "loss": 3.4078, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8399129171763205e-05, + "loss": 3.4029, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8390743224252685e-05, + "loss": 3.417, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8382357276742165e-05, + "loss": 3.4053, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8373971329231645e-05, + "loss": 3.4145, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8365601760524858e-05, + "loss": 3.4187, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.8357215813014338e-05, + "loss": 3.3845, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.8348829865503818e-05, + "loss": 3.4155, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.8340443917993297e-05, + "loss": 3.4059, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8332074349286507e-05, + "loss": 3.4093, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.8323688401775987e-05, + "loss": 3.406, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.8315302454265466e-05, + "loss": 3.3985, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.8306916506754946e-05, + "loss": 3.3972, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.829854693804816e-05, + "loss": 3.4018, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.829016099053764e-05, + "loss": 3.4214, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8281791421830848e-05, + "loss": 3.3962, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.8273405474320328e-05, + "loss": 3.4168, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.8265019526809808e-05, + "loss": 3.4085, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.825663357929929e-05, + "loss": 3.3907, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.824824763178877e-05, + "loss": 3.4158, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.823986168427825e-05, + "loss": 3.3985, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8231475736767728e-05, + "loss": 3.3878, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8223089789257208e-05, + "loss": 3.3973, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.821472022055042e-05, + "loss": 3.4124, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.82063342730399e-05, + "loss": 3.3907, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.819794832552938e-05, + "loss": 3.4093, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.818956237801886e-05, + "loss": 3.3938, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8181192809312073e-05, + "loss": 3.394, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.817280686180155e-05, + "loss": 3.4086, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.816442091429103e-05, + "loss": 3.4078, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8156034966780512e-05, + "loss": 3.4081, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8147665398073725e-05, + "loss": 3.4062, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.81392794505632e-05, + "loss": 3.4132, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.813089350305268e-05, + "loss": 3.4059, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.812250755554216e-05, + "loss": 3.4104, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8114137986835374e-05, + "loss": 3.3936, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8105752039324854e-05, + "loss": 3.3984, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8097366091814334e-05, + "loss": 3.4059, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8088980144303814e-05, + "loss": 3.3997, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8080610575597023e-05, + "loss": 3.412, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8072224628086503e-05, + "loss": 3.4137, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8063838680575983e-05, + "loss": 3.3948, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8055452733065466e-05, + "loss": 3.3915, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8047083164358675e-05, + "loss": 3.408, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8038697216848155e-05, + "loss": 3.4089, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8030311269337635e-05, + "loss": 3.4084, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8021925321827115e-05, + "loss": 3.3957, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.8013555753120327e-05, + "loss": 3.4104, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8005169805609807e-05, + "loss": 3.4019, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7996783858099287e-05, + "loss": 3.4009, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7988397910588767e-05, + "loss": 3.3982, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.7980028341881976e-05, + "loss": 3.406, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7971642394371456e-05, + "loss": 3.4093, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.7963256446860936e-05, + "loss": 3.409, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.7954870499350416e-05, + "loss": 3.3906, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.794650093064363e-05, + "loss": 3.4047, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.793811498313311e-05, + "loss": 3.3952, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.792972903562259e-05, + "loss": 3.4082, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.792134308811207e-05, + "loss": 3.4024, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7912973519405278e-05, + "loss": 3.4026, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.790458757189476e-05, + "loss": 3.4026, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.789620162438424e-05, + "loss": 3.3914, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.788781567687372e-05, + "loss": 3.3985, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.787944610816693e-05, + "loss": 3.3948, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.787106016065641e-05, + "loss": 3.4009, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.786267421314589e-05, + "loss": 3.4008, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.785428826563537e-05, + "loss": 3.4041, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7845918696928582e-05, + "loss": 3.3932, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.7837532749418062e-05, + "loss": 3.3961, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.7829146801907542e-05, + "loss": 3.3992, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.7820760854397022e-05, + "loss": 3.4092, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.781239128569023e-05, + "loss": 3.4027, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.7804005338179715e-05, + "loss": 3.4044, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7795619390669195e-05, + "loss": 3.4047, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7787233443158675e-05, + "loss": 3.4153, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7778863874451884e-05, + "loss": 3.4011, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7770477926941364e-05, + "loss": 3.4036, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7762091979430844e-05, + "loss": 3.401, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7753706031920324e-05, + "loss": 3.4056, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7745336463213536e-05, + "loss": 3.4018, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7736950515703016e-05, + "loss": 3.3961, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7728564568192496e-05, + "loss": 3.3998, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7720178620681973e-05, + "loss": 3.409, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7711809051975185e-05, + "loss": 3.3953, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.770342310446467e-05, + "loss": 3.3919, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.769503715695415e-05, + "loss": 3.3926, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7686651209443625e-05, + "loss": 3.3926, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7678281640736837e-05, + "loss": 3.4112, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7669895693226317e-05, + "loss": 3.4013, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7661509745715797e-05, + "loss": 3.4164, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7653123798205277e-05, + "loss": 3.3943, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.764475422949849e-05, + "loss": 3.4095, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.763636828198797e-05, + "loss": 3.402, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.7627982334477446e-05, + "loss": 3.4017, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7619596386966926e-05, + "loss": 3.3954, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.761122681826014e-05, + "loss": 3.3993, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7602840870749622e-05, + "loss": 3.3948, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.75944549232391e-05, + "loss": 3.417, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.758606897572858e-05, + "loss": 3.3912, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.757769940702179e-05, + "loss": 3.4055, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7569313459511268e-05, + "loss": 3.4096, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.756092751200075e-05, + "loss": 3.4023, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7552557943293964e-05, + "loss": 3.3983, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7544171995783443e-05, + "loss": 3.4051, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.753578604827292e-05, + "loss": 3.4078, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7527416479566133e-05, + "loss": 3.3993, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7519030532055612e-05, + "loss": 3.4052, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.8788576126098633, + "eval_runtime": 306.1617, + "eval_samples_per_second": 1246.371, + "eval_steps_per_second": 38.95, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.7510644584545092e-05, + "loss": 3.3922, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.7502258637034572e-05, + "loss": 3.3921, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7493872689524052e-05, + "loss": 3.3998, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7485486742013532e-05, + "loss": 3.4084, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7477100794503012e-05, + "loss": 3.4153, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.7468714846992492e-05, + "loss": 3.3946, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.74603452782857e-05, + "loss": 3.4039, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.7451959330775185e-05, + "loss": 3.391, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.7443573383264665e-05, + "loss": 3.4012, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.7435187435754145e-05, + "loss": 3.4004, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.7426817867047354e-05, + "loss": 3.3977, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.7418431919536834e-05, + "loss": 3.4058, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.7410045972026314e-05, + "loss": 3.4054, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.7401660024515794e-05, + "loss": 3.3934, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.7393290455809006e-05, + "loss": 3.3931, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.7384904508298486e-05, + "loss": 3.3832, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.7376518560787966e-05, + "loss": 3.3988, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.7368132613277446e-05, + "loss": 3.4039, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.7359763044570655e-05, + "loss": 3.394, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.735137709706014e-05, + "loss": 3.4045, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.7342991149549618e-05, + "loss": 3.4182, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.7334605202039098e-05, + "loss": 3.4084, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.7326235633332307e-05, + "loss": 3.4046, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.7317849685821787e-05, + "loss": 3.3978, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.7309463738311267e-05, + "loss": 3.4039, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.7301077790800747e-05, + "loss": 3.401, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.729270822209396e-05, + "loss": 3.3986, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.728432227458344e-05, + "loss": 3.4047, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.727593632707292e-05, + "loss": 3.3947, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.7267550379562396e-05, + "loss": 3.391, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.725918081085561e-05, + "loss": 3.3951, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.7250794863345092e-05, + "loss": 3.403, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.7242408915834572e-05, + "loss": 3.4029, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.723402296832405e-05, + "loss": 3.4061, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.722565339961726e-05, + "loss": 3.3979, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.721726745210674e-05, + "loss": 3.3971, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.720888150459622e-05, + "loss": 3.4028, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.72004955570857e-05, + "loss": 3.3931, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.7192125988378913e-05, + "loss": 3.3918, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.7183740040868393e-05, + "loss": 3.3906, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.717535409335787e-05, + "loss": 3.392, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.716696814584735e-05, + "loss": 3.4007, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.7158598577140562e-05, + "loss": 3.3992, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.7150212629630046e-05, + "loss": 3.3979, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7141826682119522e-05, + "loss": 3.3983, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7133440734609002e-05, + "loss": 3.3992, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7125071165902215e-05, + "loss": 3.4059, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.7116685218391695e-05, + "loss": 3.4031, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.7108299270881175e-05, + "loss": 3.3718, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.7099913323370655e-05, + "loss": 3.4071, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.7091543754663867e-05, + "loss": 3.3934, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.7083157807153344e-05, + "loss": 3.4011, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.7074771859642824e-05, + "loss": 3.3994, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.7066385912132303e-05, + "loss": 3.3852, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.7058016343425516e-05, + "loss": 3.3912, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.7049630395914996e-05, + "loss": 3.3875, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.7041244448404476e-05, + "loss": 3.4068, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.703287487969769e-05, + "loss": 3.3895, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.702448893218717e-05, + "loss": 3.405, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7016102984676645e-05, + "loss": 3.398, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.7007717037166125e-05, + "loss": 3.3862, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.6999331089655608e-05, + "loss": 3.4043, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.6990945142145088e-05, + "loss": 3.385, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.6982559194634568e-05, + "loss": 3.3823, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.6974173247124048e-05, + "loss": 3.3847, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.6965803678417257e-05, + "loss": 3.4008, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.6957417730906737e-05, + "loss": 3.383, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.6949031783396217e-05, + "loss": 3.4008, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.69406458358857e-05, + "loss": 3.38, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.693227626717891e-05, + "loss": 3.3885, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.692389031966839e-05, + "loss": 3.3955, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.691550437215787e-05, + "loss": 3.3937, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.6907118424647346e-05, + "loss": 3.4, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.6898748855940562e-05, + "loss": 3.3989, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.6890362908430042e-05, + "loss": 3.4036, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.6881976960919522e-05, + "loss": 3.39, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.6873591013409e-05, + "loss": 3.4014, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.686522144470221e-05, + "loss": 3.3855, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.685683549719169e-05, + "loss": 3.3876, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.684844954968117e-05, + "loss": 3.3929, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.684006360217065e-05, + "loss": 3.3869, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.6831694033463863e-05, + "loss": 3.4001, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.6823308085953343e-05, + "loss": 3.4029, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.681492213844282e-05, + "loss": 3.3905, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.68065361909323e-05, + "loss": 3.3749, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.6798166622225516e-05, + "loss": 3.3973, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.6789780674714995e-05, + "loss": 3.3955, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.6781394727204472e-05, + "loss": 3.4037, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.6773008779693952e-05, + "loss": 3.3818, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.6764639210987164e-05, + "loss": 3.3987, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.6756253263476644e-05, + "loss": 3.3911, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.6747867315966124e-05, + "loss": 3.3903, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.6739481368455604e-05, + "loss": 3.3859, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.6731111799748817e-05, + "loss": 3.3972, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.6722725852238293e-05, + "loss": 3.4001, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.6714339904727773e-05, + "loss": 3.3987, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.6705953957217253e-05, + "loss": 3.3822, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.669758438851047e-05, + "loss": 3.393, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.6689198440999946e-05, + "loss": 3.3854, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.6680812493489426e-05, + "loss": 3.3955, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.6672426545978906e-05, + "loss": 3.3921, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.6664056977272118e-05, + "loss": 3.3947, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.6655671029761598e-05, + "loss": 3.3886, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.6647285082251078e-05, + "loss": 3.3831, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.6638899134740558e-05, + "loss": 3.3945, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.6630529566033767e-05, + "loss": 3.3824, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.6622143618523247e-05, + "loss": 3.3885, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.6613757671012727e-05, + "loss": 3.3857, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.6605371723502207e-05, + "loss": 3.3984, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.659700215479542e-05, + "loss": 3.3821, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.65886162072849e-05, + "loss": 3.3855, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.658023025977438e-05, + "loss": 3.3873, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.657184431226386e-05, + "loss": 3.3999, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.656347474355707e-05, + "loss": 3.3947, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.655508879604655e-05, + "loss": 3.3923, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.6546702848536032e-05, + "loss": 3.3945, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.6538316901025512e-05, + "loss": 3.4054, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.652994733231872e-05, + "loss": 3.389, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.65215613848082e-05, + "loss": 3.3944, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.651317543729768e-05, + "loss": 3.3919, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.650478948978716e-05, + "loss": 3.3958, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6496419921080373e-05, + "loss": 3.3888, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6488033973569853e-05, + "loss": 3.3856, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6479648026059333e-05, + "loss": 3.3898, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.6471262078548813e-05, + "loss": 3.3979, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.6462892509842022e-05, + "loss": 3.3846, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.6454506562331502e-05, + "loss": 3.3862, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.6446120614820985e-05, + "loss": 3.3757, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.6437734667310465e-05, + "loss": 3.3873, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.6429365098603674e-05, + "loss": 3.3959, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.6420979151093154e-05, + "loss": 3.3928, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.6412593203582634e-05, + "loss": 3.4077, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.6404207256072114e-05, + "loss": 3.3806, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.6395837687365327e-05, + "loss": 3.3991, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.6387451739854807e-05, + "loss": 3.3904, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.6379065792344287e-05, + "loss": 3.3948, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.6370679844833767e-05, + "loss": 3.3845, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.6362310276126976e-05, + "loss": 3.3841, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.6353924328616456e-05, + "loss": 3.3904, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.634553838110594e-05, + "loss": 3.4047, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.6337168812399148e-05, + "loss": 3.3782, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.6328782864888628e-05, + "loss": 3.3956, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.6320396917378108e-05, + "loss": 3.3965, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.6312010969867588e-05, + "loss": 3.3903, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.63036414011608e-05, + "loss": 3.3896, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.629525545365028e-05, + "loss": 3.397, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.628686950613976e-05, + "loss": 3.3945, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.627849993743297e-05, + "loss": 3.3955, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.627011398992245e-05, + "loss": 3.3902, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.880368947982788, + "eval_runtime": 305.7831, + "eval_samples_per_second": 1247.914, + "eval_steps_per_second": 38.998, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.626172804241193e-05, + "loss": 3.3776, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.625334209490141e-05, + "loss": 3.3825, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6244956147390893e-05, + "loss": 3.3918, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.623657019988037e-05, + "loss": 3.3954, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.6228200631173582e-05, + "loss": 3.4051, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.6219814683663062e-05, + "loss": 3.385, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.6211428736152542e-05, + "loss": 3.3962, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.6203042788642018e-05, + "loss": 3.3841, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6194673219935234e-05, + "loss": 3.389, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.6186287272424714e-05, + "loss": 3.3851, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.617790132491419e-05, + "loss": 3.391, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.616951537740367e-05, + "loss": 3.3935, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.6161145808696883e-05, + "loss": 3.3967, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.6152759861186363e-05, + "loss": 3.3814, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.6144373913675843e-05, + "loss": 3.3831, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.6135987966165323e-05, + "loss": 3.3712, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.6127618397458535e-05, + "loss": 3.3893, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6119232449948015e-05, + "loss": 3.3935, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6110846502437492e-05, + "loss": 3.3841, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6102460554926972e-05, + "loss": 3.3956, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.6094090986220188e-05, + "loss": 3.4078, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.6085705038709664e-05, + "loss": 3.3969, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6077319091199144e-05, + "loss": 3.3934, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6068933143688624e-05, + "loss": 3.3864, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.6060563574981837e-05, + "loss": 3.3949, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6052177627471317e-05, + "loss": 3.3905, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.6043791679960797e-05, + "loss": 3.391, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.6035405732450277e-05, + "loss": 3.391, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.602703616374349e-05, + "loss": 3.3867, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.6018650216232966e-05, + "loss": 3.3802, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6010264268722446e-05, + "loss": 3.3888, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.6001878321211926e-05, + "loss": 3.3894, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5993508752505138e-05, + "loss": 3.3928, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.5985122804994618e-05, + "loss": 3.3985, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.5976736857484098e-05, + "loss": 3.389, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.5968350909973578e-05, + "loss": 3.3858, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.5959981341266787e-05, + "loss": 3.3949, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.595159539375627e-05, + "loss": 3.3812, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.594320944624575e-05, + "loss": 3.3844, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.593482349873523e-05, + "loss": 3.376, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.592645393002844e-05, + "loss": 3.3846, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.591806798251792e-05, + "loss": 3.3856, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.59096820350074e-05, + "loss": 3.3899, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.590129608749688e-05, + "loss": 3.3919, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5892942897593824e-05, + "loss": 3.3873, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5884556950083304e-05, + "loss": 3.3916, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.5876171002572784e-05, + "loss": 3.3919, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.586778505506226e-05, + "loss": 3.3958, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.585939910755174e-05, + "loss": 3.3651, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5851013160041224e-05, + "loss": 3.3961, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5842627212530704e-05, + "loss": 3.3801, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5834241265020184e-05, + "loss": 3.3892, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5825871696313393e-05, + "loss": 3.3885, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.5817485748802873e-05, + "loss": 3.3801, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.5809099801292353e-05, + "loss": 3.3749, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.5800713853781833e-05, + "loss": 3.377, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5792344285075045e-05, + "loss": 3.4004, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.5783958337564525e-05, + "loss": 3.3776, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.5775588768857734e-05, + "loss": 3.3961, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.5767202821347214e-05, + "loss": 3.3835, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.5758816873836694e-05, + "loss": 3.3776, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.5750430926326178e-05, + "loss": 3.3939, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.5742044978815658e-05, + "loss": 3.3769, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5733659031305138e-05, + "loss": 3.3703, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5725273083794618e-05, + "loss": 3.3757, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5716903515087827e-05, + "loss": 3.392, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5708517567577307e-05, + "loss": 3.3726, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5700131620066787e-05, + "loss": 3.391, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.5691745672556267e-05, + "loss": 3.3679, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.568337610384948e-05, + "loss": 3.3796, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.567499015633896e-05, + "loss": 3.3861, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.566660420882844e-05, + "loss": 3.3856, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.5658218261317916e-05, + "loss": 3.3879, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.564984869261113e-05, + "loss": 3.3875, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.564146274510061e-05, + "loss": 3.3929, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.5633076797590088e-05, + "loss": 3.3793, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.5624690850079568e-05, + "loss": 3.3869, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.561632128137278e-05, + "loss": 3.3778, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.560793533386226e-05, + "loss": 3.3801, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.559954938635174e-05, + "loss": 3.3796, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.559116343884122e-05, + "loss": 3.3792, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.5582793870134433e-05, + "loss": 3.39, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.5574407922623913e-05, + "loss": 3.391, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.556602197511339e-05, + "loss": 3.3816, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.555763602760287e-05, + "loss": 3.3649, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5549266458896085e-05, + "loss": 3.3864, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.554088051138556e-05, + "loss": 3.3858, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.553249456387504e-05, + "loss": 3.3943, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.552410861636452e-05, + "loss": 3.3752, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.5515739047657734e-05, + "loss": 3.3861, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.550735310014721e-05, + "loss": 3.388, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.5498967152636694e-05, + "loss": 3.3751, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.5490581205126174e-05, + "loss": 3.3756, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.5482211636419386e-05, + "loss": 3.3894, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.5473825688908863e-05, + "loss": 3.3861, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5465439741398343e-05, + "loss": 3.3919, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.5457053793887823e-05, + "loss": 3.3736, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.5448684225181035e-05, + "loss": 3.38, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.5440298277670515e-05, + "loss": 3.377, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5431912330159995e-05, + "loss": 3.3853, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.5423526382649475e-05, + "loss": 3.3837, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.5415156813942684e-05, + "loss": 3.3802, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5406770866432164e-05, + "loss": 3.3798, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.5398384918921648e-05, + "loss": 3.377, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.5389998971411128e-05, + "loss": 3.3817, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5381629402704337e-05, + "loss": 3.3696, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.5373243455193817e-05, + "loss": 3.3794, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.5364857507683297e-05, + "loss": 3.3755, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5356471560172777e-05, + "loss": 3.3852, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.534810199146599e-05, + "loss": 3.3744, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.533971604395547e-05, + "loss": 3.3829, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.533133009644495e-05, + "loss": 3.3742, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.532294414893443e-05, + "loss": 3.389, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.5314574580227638e-05, + "loss": 3.381, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.5306188632717118e-05, + "loss": 3.383, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.52978026852066e-05, + "loss": 3.3817, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.528941673769608e-05, + "loss": 3.4007, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.528104716898929e-05, + "loss": 3.3759, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.527266122147877e-05, + "loss": 3.3821, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.526427527396825e-05, + "loss": 3.3817, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5255905705261461e-05, + "loss": 3.3853, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5247519757750941e-05, + "loss": 3.3788, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5239133810240423e-05, + "loss": 3.3776, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5230747862729903e-05, + "loss": 3.3779, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5222378294023112e-05, + "loss": 3.3852, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5213992346512593e-05, + "loss": 3.3719, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5205606399002073e-05, + "loss": 3.3762, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5197220451491553e-05, + "loss": 3.3679, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5188850882784764e-05, + "loss": 3.3802, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5180464935274244e-05, + "loss": 3.3845, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5172078987763724e-05, + "loss": 3.3817, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5163693040253204e-05, + "loss": 3.396, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5155323471546415e-05, + "loss": 3.3735, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5146937524035895e-05, + "loss": 3.3851, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5138551576525376e-05, + "loss": 3.3862, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5130165629014856e-05, + "loss": 3.3819, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5121796060308065e-05, + "loss": 3.3751, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5113410112797547e-05, + "loss": 3.3713, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5105024165287027e-05, + "loss": 3.3832, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5096638217776507e-05, + "loss": 3.3892, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5088268649069718e-05, + "loss": 3.3764, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5079882701559198e-05, + "loss": 3.3854, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5071496754048678e-05, + "loss": 3.3858, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5063110806538158e-05, + "loss": 3.3808, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5054757616635101e-05, + "loss": 3.3804, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.504637166912458e-05, + "loss": 3.3843, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5037985721614059e-05, + "loss": 3.3838, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5029599774103539e-05, + "loss": 3.3819, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5021213826593019e-05, + "loss": 3.3852, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.8813884258270264, + "eval_runtime": 302.9442, + "eval_samples_per_second": 1259.608, + "eval_steps_per_second": 39.364, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.50128278790825e-05, + "loss": 3.376, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.500444193157198e-05, + "loss": 3.3688, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.499605598406146e-05, + "loss": 3.3823, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4987686415354671e-05, + "loss": 3.3862, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4979300467844151e-05, + "loss": 3.3923, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4970914520333631e-05, + "loss": 3.3768, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.496252857282311e-05, + "loss": 3.3843, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4954159004116322e-05, + "loss": 3.3751, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4945773056605802e-05, + "loss": 3.3771, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4937387109095282e-05, + "loss": 3.3785, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.492900116158476e-05, + "loss": 3.3838, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4920631592877973e-05, + "loss": 3.382, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.4912245645367454e-05, + "loss": 3.389, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4903859697856931e-05, + "loss": 3.3699, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4895473750346411e-05, + "loss": 3.3724, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4887104181639625e-05, + "loss": 3.3638, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4878718234129105e-05, + "loss": 3.3825, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4870332286618582e-05, + "loss": 3.3798, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4861946339108063e-05, + "loss": 3.3796, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4853576770401276e-05, + "loss": 3.3808, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4845190822890756e-05, + "loss": 3.3965, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4836804875380234e-05, + "loss": 3.3863, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4828418927869714e-05, + "loss": 3.3836, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4820049359162926e-05, + "loss": 3.378, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4811663411652405e-05, + "loss": 3.3902, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4803277464141885e-05, + "loss": 3.3811, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4794891516631365e-05, + "loss": 3.3757, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4786521947924579e-05, + "loss": 3.3885, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4778136000414055e-05, + "loss": 3.3696, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4769750052903535e-05, + "loss": 3.3724, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4761364105393017e-05, + "loss": 3.38, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.475299453668623e-05, + "loss": 3.3773, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4744608589175708e-05, + "loss": 3.3851, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4736222641665188e-05, + "loss": 3.3883, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4727836694154668e-05, + "loss": 3.3762, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.4719467125447878e-05, + "loss": 3.3781, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4711081177937358e-05, + "loss": 3.3866, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4702695230426838e-05, + "loss": 3.3718, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4694309282916318e-05, + "loss": 3.3741, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4685939714209529e-05, + "loss": 3.3699, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4677553766699009e-05, + "loss": 3.3737, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4669167819188489e-05, + "loss": 3.3728, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.466078187167797e-05, + "loss": 3.382, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.465241230297118e-05, + "loss": 3.38, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4644026355460661e-05, + "loss": 3.3779, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4635640407950141e-05, + "loss": 3.3791, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.462727083924335e-05, + "loss": 3.3827, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4618884891732832e-05, + "loss": 3.3857, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4610498944222312e-05, + "loss": 3.36, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4602112996711792e-05, + "loss": 3.3824, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4593743428005003e-05, + "loss": 3.3711, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.4585357480494483e-05, + "loss": 3.3772, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.4576971532983963e-05, + "loss": 3.3785, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4568601964277175e-05, + "loss": 3.369, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4560216016766653e-05, + "loss": 3.3688, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4551830069256133e-05, + "loss": 3.3626, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4543444121745613e-05, + "loss": 3.3938, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4535058174235095e-05, + "loss": 3.3679, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4526688605528304e-05, + "loss": 3.383, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4518302658017786e-05, + "loss": 3.3758, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4509916710507266e-05, + "loss": 3.369, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4501530762996746e-05, + "loss": 3.378, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4493144815486226e-05, + "loss": 3.3709, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4484758867975705e-05, + "loss": 3.3646, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4476372920465184e-05, + "loss": 3.3577, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4468003351758396e-05, + "loss": 3.3861, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4459617404247878e-05, + "loss": 3.3647, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4451231456737358e-05, + "loss": 3.3742, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4442845509226834e-05, + "loss": 3.3606, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4434475940520049e-05, + "loss": 3.372, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4426089993009529e-05, + "loss": 3.3702, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.4417704045499005e-05, + "loss": 3.378, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4409318097988487e-05, + "loss": 3.3794, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.44009485292817e-05, + "loss": 3.378, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.439256258177118e-05, + "loss": 3.3801, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4384176634260657e-05, + "loss": 3.3715, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4375790686750137e-05, + "loss": 3.3765, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.436742111804335e-05, + "loss": 3.3676, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4359035170532832e-05, + "loss": 3.3717, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4350649223022308e-05, + "loss": 3.3729, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4342263275511788e-05, + "loss": 3.3653, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4333893706805002e-05, + "loss": 3.3825, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4325507759294479e-05, + "loss": 3.3819, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4317121811783959e-05, + "loss": 3.3716, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.430873586427344e-05, + "loss": 3.3519, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4300366295566653e-05, + "loss": 3.3733, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4291980348056131e-05, + "loss": 3.3786, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4283594400545611e-05, + "loss": 3.3839, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4275208453035091e-05, + "loss": 3.3693, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4266838884328302e-05, + "loss": 3.3721, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.4258452936817782e-05, + "loss": 3.3775, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4250066989307262e-05, + "loss": 3.3655, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.4241681041796742e-05, + "loss": 3.3659, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4233311473089953e-05, + "loss": 3.3784, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4224925525579432e-05, + "loss": 3.3735, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.4216539578068912e-05, + "loss": 3.3812, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.4208153630558394e-05, + "loss": 3.3682, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4199784061851603e-05, + "loss": 3.3681, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4191398114341085e-05, + "loss": 3.366, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.4183012166830565e-05, + "loss": 3.3747, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.4174626219320045e-05, + "loss": 3.3748, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4166256650613256e-05, + "loss": 3.3719, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4157870703102735e-05, + "loss": 3.3702, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4149484755592215e-05, + "loss": 3.3637, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4141098808081695e-05, + "loss": 3.3771, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4132729239374906e-05, + "loss": 3.3556, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4124343291864386e-05, + "loss": 3.368, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4115957344353866e-05, + "loss": 3.3707, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4107571396843348e-05, + "loss": 3.3759, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4099201828136557e-05, + "loss": 3.3627, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4090815880626037e-05, + "loss": 3.3743, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4082429933115518e-05, + "loss": 3.3658, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4074043985604998e-05, + "loss": 3.3787, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.406567441689821e-05, + "loss": 3.372, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.405728846938769e-05, + "loss": 3.3727, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4048902521877169e-05, + "loss": 3.3722, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4040516574366649e-05, + "loss": 3.3891, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.403214700565986e-05, + "loss": 3.3687, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.402376105814934e-05, + "loss": 3.3748, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.401537511063882e-05, + "loss": 3.3761, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.4006989163128301e-05, + "loss": 3.3698, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.399861959442151e-05, + "loss": 3.3691, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.399023364691099e-05, + "loss": 3.3686, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3981847699400472e-05, + "loss": 3.3676, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3973461751889952e-05, + "loss": 3.3762, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3965092183183163e-05, + "loss": 3.3611, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3956706235672643e-05, + "loss": 3.3704, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3948320288162123e-05, + "loss": 3.3594, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3939934340651603e-05, + "loss": 3.3703, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3931564771944814e-05, + "loss": 3.3686, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3923178824434293e-05, + "loss": 3.3737, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3914792876923773e-05, + "loss": 3.3867, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3906423308216984e-05, + "loss": 3.364, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3898037360706464e-05, + "loss": 3.3734, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3889651413195944e-05, + "loss": 3.3718, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3881265465685426e-05, + "loss": 3.3702, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3872895896978635e-05, + "loss": 3.3698, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3864509949468117e-05, + "loss": 3.3571, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3856124001957596e-05, + "loss": 3.3747, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3847738054447076e-05, + "loss": 3.3795, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3839368485740287e-05, + "loss": 3.365, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3830982538229767e-05, + "loss": 3.3729, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3822596590719247e-05, + "loss": 3.3796, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3814210643208727e-05, + "loss": 3.3682, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3805841074501938e-05, + "loss": 3.3695, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3797455126991418e-05, + "loss": 3.3791, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3789069179480898e-05, + "loss": 3.3722, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3780683231970376e-05, + "loss": 3.372, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3772313663263589e-05, + "loss": 3.3769, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.883070468902588, + "eval_runtime": 302.0947, + "eval_samples_per_second": 1263.15, + "eval_steps_per_second": 39.474, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.376392771575307e-05, + "loss": 3.3742, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.375554176824255e-05, + "loss": 3.3569, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3747155820732027e-05, + "loss": 3.371, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3738769873221508e-05, + "loss": 3.3808, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3730400304514721e-05, + "loss": 3.3782, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.37220143570042e-05, + "loss": 3.3701, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3713628409493679e-05, + "loss": 3.371, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3705242461983159e-05, + "loss": 3.367, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3696872893276372e-05, + "loss": 3.3651, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.368848694576585e-05, + "loss": 3.3694, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.368010099825533e-05, + "loss": 3.37, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.367171505074481e-05, + "loss": 3.3715, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3663345482038022e-05, + "loss": 3.3801, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.36549595345275e-05, + "loss": 3.3598, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.364657358701698e-05, + "loss": 3.3622, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.363818763950646e-05, + "loss": 3.3527, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3629818070799671e-05, + "loss": 3.3724, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3621432123289151e-05, + "loss": 3.3703, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3613046175778633e-05, + "loss": 3.373, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3604660228268113e-05, + "loss": 3.37, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3596290659561322e-05, + "loss": 3.3862, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3587904712050803e-05, + "loss": 3.3756, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3579518764540283e-05, + "loss": 3.3729, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3571132817029763e-05, + "loss": 3.3672, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3562763248322974e-05, + "loss": 3.3825, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3554377300812454e-05, + "loss": 3.3667, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3545991353301934e-05, + "loss": 3.3704, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3537605405791414e-05, + "loss": 3.3778, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3529235837084625e-05, + "loss": 3.3608, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3520849889574105e-05, + "loss": 3.3629, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3512463942063586e-05, + "loss": 3.3661, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3504077994553066e-05, + "loss": 3.3656, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3495708425846275e-05, + "loss": 3.3755, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3487322478335757e-05, + "loss": 3.3783, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3478936530825237e-05, + "loss": 3.3671, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3470550583314717e-05, + "loss": 3.3692, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3462181014607928e-05, + "loss": 3.3798, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3453795067097408e-05, + "loss": 3.3551, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3445409119586888e-05, + "loss": 3.3688, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3437023172076368e-05, + "loss": 3.3638, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3428653603369578e-05, + "loss": 3.3598, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3420267655859058e-05, + "loss": 3.3653, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.341188170834854e-05, + "loss": 3.3769, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.340349576083802e-05, + "loss": 3.3708, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3395126192131229e-05, + "loss": 3.3674, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.338674024462071e-05, + "loss": 3.3685, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.337835429711019e-05, + "loss": 3.3708, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.336996834959967e-05, + "loss": 3.3755, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3361598780892881e-05, + "loss": 3.3512, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3353212833382361e-05, + "loss": 3.3745, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3344826885871841e-05, + "loss": 3.3671, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3336440938361321e-05, + "loss": 3.3659, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3328071369654532e-05, + "loss": 3.3691, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3319685422144012e-05, + "loss": 3.3552, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3311299474633494e-05, + "loss": 3.3633, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3302913527122974e-05, + "loss": 3.3515, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3294543958416183e-05, + "loss": 3.3849, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3286158010905664e-05, + "loss": 3.3572, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3277788442198874e-05, + "loss": 3.3745, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3269402494688355e-05, + "loss": 3.3625, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3261016547177835e-05, + "loss": 3.3589, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3252630599667315e-05, + "loss": 3.3652, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3244244652156795e-05, + "loss": 3.3632, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3235858704646273e-05, + "loss": 3.3582, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3227472757135753e-05, + "loss": 3.3468, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3219086809625233e-05, + "loss": 3.3726, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3210717240918446e-05, + "loss": 3.3608, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3202331293407924e-05, + "loss": 3.3647, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3193945345897404e-05, + "loss": 3.3511, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3185575777190618e-05, + "loss": 3.3583, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3177189829680098e-05, + "loss": 3.3656, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.3168803882169575e-05, + "loss": 3.3683, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3160417934659056e-05, + "loss": 3.3672, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3152048365952269e-05, + "loss": 3.3683, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3143662418441745e-05, + "loss": 3.3696, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3135276470931227e-05, + "loss": 3.3596, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.3126890523420707e-05, + "loss": 3.3666, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.311852095471392e-05, + "loss": 3.3594, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3110135007203398e-05, + "loss": 3.3597, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3101749059692878e-05, + "loss": 3.3649, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3093363112182358e-05, + "loss": 3.3556, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3084993543475572e-05, + "loss": 3.3708, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3076607595965048e-05, + "loss": 3.3734, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3068221648454528e-05, + "loss": 3.3581, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.305983570094401e-05, + "loss": 3.3478, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3051466132237219e-05, + "loss": 3.3662, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3043080184726699e-05, + "loss": 3.368, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.303469423721618e-05, + "loss": 3.3703, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.302630828970566e-05, + "loss": 3.3582, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3017938720998871e-05, + "loss": 3.3634, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3009552773488351e-05, + "loss": 3.3711, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.3001166825977831e-05, + "loss": 3.3542, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2992780878467311e-05, + "loss": 3.3565, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2984411309760522e-05, + "loss": 3.3661, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2976025362250002e-05, + "loss": 3.3636, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2967639414739482e-05, + "loss": 3.3741, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2959253467228964e-05, + "loss": 3.3646, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2950883898522173e-05, + "loss": 3.3541, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2942497951011653e-05, + "loss": 3.3589, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2934112003501134e-05, + "loss": 3.3656, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2925726055990614e-05, + "loss": 3.3666, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2917356487283825e-05, + "loss": 3.3609, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2908970539773305e-05, + "loss": 3.357, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2900584592262785e-05, + "loss": 3.3514, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2892198644752265e-05, + "loss": 3.3694, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2883829076045476e-05, + "loss": 3.3476, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2875443128534956e-05, + "loss": 3.3577, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2867057181024436e-05, + "loss": 3.3609, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2858671233513917e-05, + "loss": 3.3669, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2850301664807126e-05, + "loss": 3.3523, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2841915717296606e-05, + "loss": 3.363, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2833529769786088e-05, + "loss": 3.356, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2825143822275568e-05, + "loss": 3.3643, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2816774253568779e-05, + "loss": 3.3669, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2808388306058259e-05, + "loss": 3.3583, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2800002358547739e-05, + "loss": 3.3637, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2791616411037219e-05, + "loss": 3.3784, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.278324684233043e-05, + "loss": 3.359, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.277486089481991e-05, + "loss": 3.3647, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.276647494730939e-05, + "loss": 3.3635, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.275808899979887e-05, + "loss": 3.3589, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.274971943109208e-05, + "loss": 3.3622, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.274133348358156e-05, + "loss": 3.3568, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2732947536071042e-05, + "loss": 3.3594, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2724561588560522e-05, + "loss": 3.3657, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.271619201985373e-05, + "loss": 3.3549, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2707806072343212e-05, + "loss": 3.3593, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2699420124832692e-05, + "loss": 3.3505, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2691050556125903e-05, + "loss": 3.3604, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2682664608615383e-05, + "loss": 3.3538, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2674278661104863e-05, + "loss": 3.3679, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2665892713594343e-05, + "loss": 3.3757, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2657523144887554e-05, + "loss": 3.3532, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2649137197377034e-05, + "loss": 3.3642, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2640751249866514e-05, + "loss": 3.3646, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2632365302355995e-05, + "loss": 3.3639, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2623995733649204e-05, + "loss": 3.3546, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2615609786138684e-05, + "loss": 3.3505, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2607223838628166e-05, + "loss": 3.3674, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2598837891117643e-05, + "loss": 3.3684, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2590468322410857e-05, + "loss": 3.354, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2582082374900337e-05, + "loss": 3.3642, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2573696427389817e-05, + "loss": 3.3685, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2565310479879295e-05, + "loss": 3.3628, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2556957289976237e-05, + "loss": 3.3569, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2548571342465718e-05, + "loss": 3.3678, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2540185394955198e-05, + "loss": 3.3616, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2531799447444678e-05, + "loss": 3.3658, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2523413499934158e-05, + "loss": 3.3628, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.8842740058898926, + "eval_runtime": 303.2398, + "eval_samples_per_second": 1258.38, + "eval_steps_per_second": 39.325, + "step": 2289600 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.5444074027470234e+18, + "trial_name": null, + "trial_params": null +}