|
{ |
|
"best_metric": 0.8683385579937304, |
|
"best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned-FER2013/checkpoint-1616", |
|
"epoch": 10.0, |
|
"eval_steps": 500, |
|
"global_step": 2020, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 2.4752475247524753e-06, |
|
"loss": 0.7062, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 4.950495049504951e-06, |
|
"loss": 0.6984, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 7.4257425742574256e-06, |
|
"loss": 0.6891, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 9.900990099009901e-06, |
|
"loss": 0.6814, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 1.2376237623762377e-05, |
|
"loss": 0.6688, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 1.4851485148514851e-05, |
|
"loss": 0.6468, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 1.7326732673267325e-05, |
|
"loss": 0.6276, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 1.9801980198019803e-05, |
|
"loss": 0.6003, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 2.227722772277228e-05, |
|
"loss": 0.5689, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 2.4752475247524754e-05, |
|
"loss": 0.5499, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 2.722772277227723e-05, |
|
"loss": 0.5432, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 2.9702970297029702e-05, |
|
"loss": 0.5408, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 3.217821782178218e-05, |
|
"loss": 0.535, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 3.465346534653465e-05, |
|
"loss": 0.5331, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 3.712871287128713e-05, |
|
"loss": 0.4929, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 3.9603960396039605e-05, |
|
"loss": 0.5054, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 4.207920792079208e-05, |
|
"loss": 0.4882, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 4.455445544554456e-05, |
|
"loss": 0.4844, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 4.702970297029703e-05, |
|
"loss": 0.5134, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 4.950495049504951e-05, |
|
"loss": 0.495, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.7739463601532567, |
|
"eval_loss": 0.46603715419769287, |
|
"eval_runtime": 15.7268, |
|
"eval_samples_per_second": 182.555, |
|
"eval_steps_per_second": 5.723, |
|
"step": 202 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 4.977997799779978e-05, |
|
"loss": 0.5214, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 4.950495049504951e-05, |
|
"loss": 0.5009, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 4.9229922992299234e-05, |
|
"loss": 0.4632, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 4.895489548954896e-05, |
|
"loss": 0.4585, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 4.867986798679868e-05, |
|
"loss": 0.4339, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 4.8404840484048406e-05, |
|
"loss": 0.4703, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 4.812981298129813e-05, |
|
"loss": 0.4748, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 4.785478547854786e-05, |
|
"loss": 0.4688, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 4.7579757975797585e-05, |
|
"loss": 0.4613, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 4.730473047304731e-05, |
|
"loss": 0.4633, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.53, |
|
"learning_rate": 4.702970297029703e-05, |
|
"loss": 0.4661, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 4.675467546754676e-05, |
|
"loss": 0.4476, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 1.63, |
|
"learning_rate": 4.647964796479648e-05, |
|
"loss": 0.458, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 4.62046204620462e-05, |
|
"loss": 0.4606, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 4.592959295929593e-05, |
|
"loss": 0.4433, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 4.5654565456545655e-05, |
|
"loss": 0.4568, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 1.83, |
|
"learning_rate": 4.537953795379538e-05, |
|
"loss": 0.4395, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 4.510451045104511e-05, |
|
"loss": 0.448, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 1.93, |
|
"learning_rate": 4.4829482948294834e-05, |
|
"loss": 0.4722, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 4.455445544554456e-05, |
|
"loss": 0.4632, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.8286311389759665, |
|
"eval_loss": 0.3819791376590729, |
|
"eval_runtime": 15.8456, |
|
"eval_samples_per_second": 181.185, |
|
"eval_steps_per_second": 5.68, |
|
"step": 404 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"learning_rate": 4.427942794279428e-05, |
|
"loss": 0.4614, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 4.4004400440044006e-05, |
|
"loss": 0.4644, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 4.372937293729373e-05, |
|
"loss": 0.4325, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 2.18, |
|
"learning_rate": 4.345434543454346e-05, |
|
"loss": 0.4297, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 2.23, |
|
"learning_rate": 4.3179317931793185e-05, |
|
"loss": 0.456, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 2.28, |
|
"learning_rate": 4.2904290429042904e-05, |
|
"loss": 0.4119, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 2.33, |
|
"learning_rate": 4.262926292629263e-05, |
|
"loss": 0.4101, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 2.38, |
|
"learning_rate": 4.2354235423542356e-05, |
|
"loss": 0.3827, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 2.43, |
|
"learning_rate": 4.207920792079208e-05, |
|
"loss": 0.4177, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 2.48, |
|
"learning_rate": 4.18041804180418e-05, |
|
"loss": 0.4286, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.52, |
|
"learning_rate": 4.152915291529153e-05, |
|
"loss": 0.4471, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 2.57, |
|
"learning_rate": 4.1254125412541255e-05, |
|
"loss": 0.4304, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 2.62, |
|
"learning_rate": 4.097909790979098e-05, |
|
"loss": 0.4043, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"learning_rate": 4.070407040704071e-05, |
|
"loss": 0.4277, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 2.72, |
|
"learning_rate": 4.042904290429043e-05, |
|
"loss": 0.403, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 2.77, |
|
"learning_rate": 4.015401540154016e-05, |
|
"loss": 0.4138, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 2.82, |
|
"learning_rate": 3.987898789878988e-05, |
|
"loss": 0.4005, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 2.87, |
|
"learning_rate": 3.9603960396039605e-05, |
|
"loss": 0.407, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 2.92, |
|
"learning_rate": 3.932893289328933e-05, |
|
"loss": 0.4124, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 2.97, |
|
"learning_rate": 3.905390539053906e-05, |
|
"loss": 0.4013, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.8446534308603274, |
|
"eval_loss": 0.35617050528526306, |
|
"eval_runtime": 16.2713, |
|
"eval_samples_per_second": 176.445, |
|
"eval_steps_per_second": 5.531, |
|
"step": 606 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"learning_rate": 3.877887788778878e-05, |
|
"loss": 0.3881, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 3.07, |
|
"learning_rate": 3.8503850385038503e-05, |
|
"loss": 0.3761, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 3.12, |
|
"learning_rate": 3.822882288228823e-05, |
|
"loss": 0.4161, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 3.17, |
|
"learning_rate": 3.7953795379537956e-05, |
|
"loss": 0.3975, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 3.22, |
|
"learning_rate": 3.767876787678768e-05, |
|
"loss": 0.4224, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 3.27, |
|
"learning_rate": 3.74037403740374e-05, |
|
"loss": 0.3849, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 3.32, |
|
"learning_rate": 3.712871287128713e-05, |
|
"loss": 0.4178, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 3.37, |
|
"learning_rate": 3.6853685368536854e-05, |
|
"loss": 0.3966, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 3.42, |
|
"learning_rate": 3.657865786578658e-05, |
|
"loss": 0.3886, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 3.47, |
|
"learning_rate": 3.6303630363036307e-05, |
|
"loss": 0.4021, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 3.51, |
|
"learning_rate": 3.602860286028603e-05, |
|
"loss": 0.3913, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 3.56, |
|
"learning_rate": 3.575357535753576e-05, |
|
"loss": 0.3886, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 3.61, |
|
"learning_rate": 3.5478547854785485e-05, |
|
"loss": 0.4066, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 3.66, |
|
"learning_rate": 3.5203520352035205e-05, |
|
"loss": 0.401, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 3.71, |
|
"learning_rate": 3.492849284928493e-05, |
|
"loss": 0.4002, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 3.76, |
|
"learning_rate": 3.465346534653465e-05, |
|
"loss": 0.3738, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 3.81, |
|
"learning_rate": 3.4378437843784377e-05, |
|
"loss": 0.4218, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 3.86, |
|
"learning_rate": 3.41034103410341e-05, |
|
"loss": 0.368, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 3.91, |
|
"learning_rate": 3.382838283828383e-05, |
|
"loss": 0.3969, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 3.96, |
|
"learning_rate": 3.3553355335533555e-05, |
|
"loss": 0.3883, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_accuracy": 0.851619644723093, |
|
"eval_loss": 0.3426118791103363, |
|
"eval_runtime": 15.7929, |
|
"eval_samples_per_second": 181.79, |
|
"eval_steps_per_second": 5.699, |
|
"step": 808 |
|
}, |
|
{ |
|
"epoch": 4.01, |
|
"learning_rate": 3.327832783278328e-05, |
|
"loss": 0.3605, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 4.06, |
|
"learning_rate": 3.300330033003301e-05, |
|
"loss": 0.3797, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 4.11, |
|
"learning_rate": 3.272827282728273e-05, |
|
"loss": 0.3701, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 4.16, |
|
"learning_rate": 3.2453245324532453e-05, |
|
"loss": 0.3968, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 4.21, |
|
"learning_rate": 3.217821782178218e-05, |
|
"loss": 0.3754, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 4.26, |
|
"learning_rate": 3.1903190319031906e-05, |
|
"loss": 0.3962, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 4.31, |
|
"learning_rate": 3.162816281628163e-05, |
|
"loss": 0.3723, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 4.36, |
|
"learning_rate": 3.135313531353136e-05, |
|
"loss": 0.3743, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 4.41, |
|
"learning_rate": 3.1078107810781085e-05, |
|
"loss": 0.4, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 4.46, |
|
"learning_rate": 3.0803080308030804e-05, |
|
"loss": 0.3827, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 4.5, |
|
"learning_rate": 3.052805280528053e-05, |
|
"loss": 0.3488, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 4.55, |
|
"learning_rate": 3.0253025302530253e-05, |
|
"loss": 0.3755, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 4.6, |
|
"learning_rate": 2.9977997799779976e-05, |
|
"loss": 0.3695, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 4.65, |
|
"learning_rate": 2.9702970297029702e-05, |
|
"loss": 0.3803, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 4.7, |
|
"learning_rate": 2.942794279427943e-05, |
|
"loss": 0.404, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 4.75, |
|
"learning_rate": 2.9152915291529155e-05, |
|
"loss": 0.3711, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 4.8, |
|
"learning_rate": 2.8877887788778878e-05, |
|
"loss": 0.3495, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 4.85, |
|
"learning_rate": 2.8602860286028604e-05, |
|
"loss": 0.3644, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 4.9, |
|
"learning_rate": 2.832783278327833e-05, |
|
"loss": 0.3673, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 4.95, |
|
"learning_rate": 2.8052805280528056e-05, |
|
"loss": 0.3597, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 2.777777777777778e-05, |
|
"loss": 0.3801, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_accuracy": 0.8561476837338906, |
|
"eval_loss": 0.33033424615859985, |
|
"eval_runtime": 16.0262, |
|
"eval_samples_per_second": 179.144, |
|
"eval_steps_per_second": 5.616, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 5.05, |
|
"learning_rate": 2.7502750275027505e-05, |
|
"loss": 0.3717, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 5.1, |
|
"learning_rate": 2.722772277227723e-05, |
|
"loss": 0.3409, |
|
"step": 1030 |
|
}, |
|
{ |
|
"epoch": 5.15, |
|
"learning_rate": 2.6952695269526958e-05, |
|
"loss": 0.3647, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 5.2, |
|
"learning_rate": 2.667766776677668e-05, |
|
"loss": 0.3454, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 5.25, |
|
"learning_rate": 2.64026402640264e-05, |
|
"loss": 0.3592, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 5.3, |
|
"learning_rate": 2.6127612761276126e-05, |
|
"loss": 0.3529, |
|
"step": 1070 |
|
}, |
|
{ |
|
"epoch": 5.35, |
|
"learning_rate": 2.5852585258525853e-05, |
|
"loss": 0.3598, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 5.4, |
|
"learning_rate": 2.557755775577558e-05, |
|
"loss": 0.3922, |
|
"step": 1090 |
|
}, |
|
{ |
|
"epoch": 5.45, |
|
"learning_rate": 2.53025302530253e-05, |
|
"loss": 0.3547, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 5.5, |
|
"learning_rate": 2.5027502750275028e-05, |
|
"loss": 0.3432, |
|
"step": 1110 |
|
}, |
|
{ |
|
"epoch": 5.54, |
|
"learning_rate": 2.4752475247524754e-05, |
|
"loss": 0.3542, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 5.59, |
|
"learning_rate": 2.447744774477448e-05, |
|
"loss": 0.3541, |
|
"step": 1130 |
|
}, |
|
{ |
|
"epoch": 5.64, |
|
"learning_rate": 2.4202420242024203e-05, |
|
"loss": 0.3475, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 5.69, |
|
"learning_rate": 2.392739273927393e-05, |
|
"loss": 0.3528, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 5.74, |
|
"learning_rate": 2.3652365236523656e-05, |
|
"loss": 0.3446, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 5.79, |
|
"learning_rate": 2.337733773377338e-05, |
|
"loss": 0.3264, |
|
"step": 1170 |
|
}, |
|
{ |
|
"epoch": 5.84, |
|
"learning_rate": 2.31023102310231e-05, |
|
"loss": 0.3327, |
|
"step": 1180 |
|
}, |
|
{ |
|
"epoch": 5.89, |
|
"learning_rate": 2.2827282728272828e-05, |
|
"loss": 0.3529, |
|
"step": 1190 |
|
}, |
|
{ |
|
"epoch": 5.94, |
|
"learning_rate": 2.2552255225522554e-05, |
|
"loss": 0.3473, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 5.99, |
|
"learning_rate": 2.227722772277228e-05, |
|
"loss": 0.3612, |
|
"step": 1210 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_accuracy": 0.8557993730407524, |
|
"eval_loss": 0.3362487852573395, |
|
"eval_runtime": 15.9082, |
|
"eval_samples_per_second": 180.474, |
|
"eval_steps_per_second": 5.657, |
|
"step": 1212 |
|
}, |
|
{ |
|
"epoch": 6.04, |
|
"learning_rate": 2.2002200220022003e-05, |
|
"loss": 0.3324, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 6.09, |
|
"learning_rate": 2.172717271727173e-05, |
|
"loss": 0.3365, |
|
"step": 1230 |
|
}, |
|
{ |
|
"epoch": 6.14, |
|
"learning_rate": 2.1452145214521452e-05, |
|
"loss": 0.3212, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 6.19, |
|
"learning_rate": 2.1177117711771178e-05, |
|
"loss": 0.33, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 6.24, |
|
"learning_rate": 2.09020902090209e-05, |
|
"loss": 0.3627, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 6.29, |
|
"learning_rate": 2.0627062706270627e-05, |
|
"loss": 0.3322, |
|
"step": 1270 |
|
}, |
|
{ |
|
"epoch": 6.34, |
|
"learning_rate": 2.0352035203520354e-05, |
|
"loss": 0.3236, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 6.39, |
|
"learning_rate": 2.007700770077008e-05, |
|
"loss": 0.3398, |
|
"step": 1290 |
|
}, |
|
{ |
|
"epoch": 6.44, |
|
"learning_rate": 1.9801980198019803e-05, |
|
"loss": 0.3481, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 6.49, |
|
"learning_rate": 1.952695269526953e-05, |
|
"loss": 0.3421, |
|
"step": 1310 |
|
}, |
|
{ |
|
"epoch": 6.53, |
|
"learning_rate": 1.9251925192519252e-05, |
|
"loss": 0.3136, |
|
"step": 1320 |
|
}, |
|
{ |
|
"epoch": 6.58, |
|
"learning_rate": 1.8976897689768978e-05, |
|
"loss": 0.3432, |
|
"step": 1330 |
|
}, |
|
{ |
|
"epoch": 6.63, |
|
"learning_rate": 1.87018701870187e-05, |
|
"loss": 0.3277, |
|
"step": 1340 |
|
}, |
|
{ |
|
"epoch": 6.68, |
|
"learning_rate": 1.8426842684268427e-05, |
|
"loss": 0.3285, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 6.73, |
|
"learning_rate": 1.8151815181518153e-05, |
|
"loss": 0.3449, |
|
"step": 1360 |
|
}, |
|
{ |
|
"epoch": 6.78, |
|
"learning_rate": 1.787678767876788e-05, |
|
"loss": 0.3433, |
|
"step": 1370 |
|
}, |
|
{ |
|
"epoch": 6.83, |
|
"learning_rate": 1.7601760176017602e-05, |
|
"loss": 0.3275, |
|
"step": 1380 |
|
}, |
|
{ |
|
"epoch": 6.88, |
|
"learning_rate": 1.7326732673267325e-05, |
|
"loss": 0.3351, |
|
"step": 1390 |
|
}, |
|
{ |
|
"epoch": 6.93, |
|
"learning_rate": 1.705170517051705e-05, |
|
"loss": 0.2946, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 6.98, |
|
"learning_rate": 1.6776677667766778e-05, |
|
"loss": 0.3504, |
|
"step": 1410 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_accuracy": 0.8652037617554859, |
|
"eval_loss": 0.330201655626297, |
|
"eval_runtime": 15.6907, |
|
"eval_samples_per_second": 182.974, |
|
"eval_steps_per_second": 5.736, |
|
"step": 1414 |
|
}, |
|
{ |
|
"epoch": 7.03, |
|
"learning_rate": 1.6501650165016504e-05, |
|
"loss": 0.3424, |
|
"step": 1420 |
|
}, |
|
{ |
|
"epoch": 7.08, |
|
"learning_rate": 1.6226622662266227e-05, |
|
"loss": 0.3244, |
|
"step": 1430 |
|
}, |
|
{ |
|
"epoch": 7.13, |
|
"learning_rate": 1.5951595159515953e-05, |
|
"loss": 0.3208, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 7.18, |
|
"learning_rate": 1.567656765676568e-05, |
|
"loss": 0.3002, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 7.23, |
|
"learning_rate": 1.5401540154015402e-05, |
|
"loss": 0.3007, |
|
"step": 1460 |
|
}, |
|
{ |
|
"epoch": 7.28, |
|
"learning_rate": 1.5126512651265127e-05, |
|
"loss": 0.3443, |
|
"step": 1470 |
|
}, |
|
{ |
|
"epoch": 7.33, |
|
"learning_rate": 1.4851485148514851e-05, |
|
"loss": 0.3192, |
|
"step": 1480 |
|
}, |
|
{ |
|
"epoch": 7.38, |
|
"learning_rate": 1.4576457645764577e-05, |
|
"loss": 0.3146, |
|
"step": 1490 |
|
}, |
|
{ |
|
"epoch": 7.43, |
|
"learning_rate": 1.4301430143014302e-05, |
|
"loss": 0.3147, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 7.48, |
|
"learning_rate": 1.4026402640264028e-05, |
|
"loss": 0.3041, |
|
"step": 1510 |
|
}, |
|
{ |
|
"epoch": 7.52, |
|
"learning_rate": 1.3751375137513753e-05, |
|
"loss": 0.2958, |
|
"step": 1520 |
|
}, |
|
{ |
|
"epoch": 7.57, |
|
"learning_rate": 1.3476347634763479e-05, |
|
"loss": 0.3235, |
|
"step": 1530 |
|
}, |
|
{ |
|
"epoch": 7.62, |
|
"learning_rate": 1.32013201320132e-05, |
|
"loss": 0.3137, |
|
"step": 1540 |
|
}, |
|
{ |
|
"epoch": 7.67, |
|
"learning_rate": 1.2926292629262926e-05, |
|
"loss": 0.3222, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 7.72, |
|
"learning_rate": 1.265126512651265e-05, |
|
"loss": 0.3087, |
|
"step": 1560 |
|
}, |
|
{ |
|
"epoch": 7.77, |
|
"learning_rate": 1.2376237623762377e-05, |
|
"loss": 0.2969, |
|
"step": 1570 |
|
}, |
|
{ |
|
"epoch": 7.82, |
|
"learning_rate": 1.2101210121012102e-05, |
|
"loss": 0.3091, |
|
"step": 1580 |
|
}, |
|
{ |
|
"epoch": 7.87, |
|
"learning_rate": 1.1826182618261828e-05, |
|
"loss": 0.3356, |
|
"step": 1590 |
|
}, |
|
{ |
|
"epoch": 7.92, |
|
"learning_rate": 1.155115511551155e-05, |
|
"loss": 0.2903, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 7.97, |
|
"learning_rate": 1.1276127612761277e-05, |
|
"loss": 0.3366, |
|
"step": 1610 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_accuracy": 0.8683385579937304, |
|
"eval_loss": 0.3320719301700592, |
|
"eval_runtime": 15.9857, |
|
"eval_samples_per_second": 179.598, |
|
"eval_steps_per_second": 5.63, |
|
"step": 1616 |
|
}, |
|
{ |
|
"epoch": 8.02, |
|
"learning_rate": 1.1001100110011001e-05, |
|
"loss": 0.2956, |
|
"step": 1620 |
|
}, |
|
{ |
|
"epoch": 8.07, |
|
"learning_rate": 1.0726072607260726e-05, |
|
"loss": 0.2987, |
|
"step": 1630 |
|
}, |
|
{ |
|
"epoch": 8.12, |
|
"learning_rate": 1.045104510451045e-05, |
|
"loss": 0.2965, |
|
"step": 1640 |
|
}, |
|
{ |
|
"epoch": 8.17, |
|
"learning_rate": 1.0176017601760177e-05, |
|
"loss": 0.3014, |
|
"step": 1650 |
|
}, |
|
{ |
|
"epoch": 8.22, |
|
"learning_rate": 9.900990099009901e-06, |
|
"loss": 0.3267, |
|
"step": 1660 |
|
}, |
|
{ |
|
"epoch": 8.27, |
|
"learning_rate": 9.625962596259626e-06, |
|
"loss": 0.3243, |
|
"step": 1670 |
|
}, |
|
{ |
|
"epoch": 8.32, |
|
"learning_rate": 9.35093509350935e-06, |
|
"loss": 0.2841, |
|
"step": 1680 |
|
}, |
|
{ |
|
"epoch": 8.37, |
|
"learning_rate": 9.075907590759077e-06, |
|
"loss": 0.2949, |
|
"step": 1690 |
|
}, |
|
{ |
|
"epoch": 8.42, |
|
"learning_rate": 8.800880088008801e-06, |
|
"loss": 0.2944, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 8.47, |
|
"learning_rate": 8.525852585258526e-06, |
|
"loss": 0.3137, |
|
"step": 1710 |
|
}, |
|
{ |
|
"epoch": 8.51, |
|
"learning_rate": 8.250825082508252e-06, |
|
"loss": 0.2825, |
|
"step": 1720 |
|
}, |
|
{ |
|
"epoch": 8.56, |
|
"learning_rate": 7.975797579757976e-06, |
|
"loss": 0.3012, |
|
"step": 1730 |
|
}, |
|
{ |
|
"epoch": 8.61, |
|
"learning_rate": 7.700770077007701e-06, |
|
"loss": 0.3221, |
|
"step": 1740 |
|
}, |
|
{ |
|
"epoch": 8.66, |
|
"learning_rate": 7.4257425742574256e-06, |
|
"loss": 0.2977, |
|
"step": 1750 |
|
}, |
|
{ |
|
"epoch": 8.71, |
|
"learning_rate": 7.150715071507151e-06, |
|
"loss": 0.316, |
|
"step": 1760 |
|
}, |
|
{ |
|
"epoch": 8.76, |
|
"learning_rate": 6.875687568756876e-06, |
|
"loss": 0.3023, |
|
"step": 1770 |
|
}, |
|
{ |
|
"epoch": 8.81, |
|
"learning_rate": 6.6006600660066e-06, |
|
"loss": 0.2937, |
|
"step": 1780 |
|
}, |
|
{ |
|
"epoch": 8.86, |
|
"learning_rate": 6.325632563256325e-06, |
|
"loss": 0.2825, |
|
"step": 1790 |
|
}, |
|
{ |
|
"epoch": 8.91, |
|
"learning_rate": 6.050605060506051e-06, |
|
"loss": 0.2907, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 8.96, |
|
"learning_rate": 5.775577557755775e-06, |
|
"loss": 0.3007, |
|
"step": 1810 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"eval_accuracy": 0.866597004528039, |
|
"eval_loss": 0.33304381370544434, |
|
"eval_runtime": 16.241, |
|
"eval_samples_per_second": 176.775, |
|
"eval_steps_per_second": 5.542, |
|
"step": 1818 |
|
}, |
|
{ |
|
"epoch": 9.01, |
|
"learning_rate": 5.500550055005501e-06, |
|
"loss": 0.297, |
|
"step": 1820 |
|
}, |
|
{ |
|
"epoch": 9.06, |
|
"learning_rate": 5.225522552255225e-06, |
|
"loss": 0.2894, |
|
"step": 1830 |
|
}, |
|
{ |
|
"epoch": 9.11, |
|
"learning_rate": 4.950495049504951e-06, |
|
"loss": 0.2927, |
|
"step": 1840 |
|
}, |
|
{ |
|
"epoch": 9.16, |
|
"learning_rate": 4.675467546754675e-06, |
|
"loss": 0.2884, |
|
"step": 1850 |
|
}, |
|
{ |
|
"epoch": 9.21, |
|
"learning_rate": 4.400440044004401e-06, |
|
"loss": 0.3217, |
|
"step": 1860 |
|
}, |
|
{ |
|
"epoch": 9.26, |
|
"learning_rate": 4.125412541254126e-06, |
|
"loss": 0.3278, |
|
"step": 1870 |
|
}, |
|
{ |
|
"epoch": 9.31, |
|
"learning_rate": 3.8503850385038505e-06, |
|
"loss": 0.3126, |
|
"step": 1880 |
|
}, |
|
{ |
|
"epoch": 9.36, |
|
"learning_rate": 3.5753575357535755e-06, |
|
"loss": 0.2997, |
|
"step": 1890 |
|
}, |
|
{ |
|
"epoch": 9.41, |
|
"learning_rate": 3.3003300330033e-06, |
|
"loss": 0.279, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 9.46, |
|
"learning_rate": 3.0253025302530254e-06, |
|
"loss": 0.2686, |
|
"step": 1910 |
|
}, |
|
{ |
|
"epoch": 9.5, |
|
"learning_rate": 2.7502750275027504e-06, |
|
"loss": 0.2811, |
|
"step": 1920 |
|
}, |
|
{ |
|
"epoch": 9.55, |
|
"learning_rate": 2.4752475247524753e-06, |
|
"loss": 0.2866, |
|
"step": 1930 |
|
}, |
|
{ |
|
"epoch": 9.6, |
|
"learning_rate": 2.2002200220022003e-06, |
|
"loss": 0.2746, |
|
"step": 1940 |
|
}, |
|
{ |
|
"epoch": 9.65, |
|
"learning_rate": 1.9251925192519253e-06, |
|
"loss": 0.2565, |
|
"step": 1950 |
|
}, |
|
{ |
|
"epoch": 9.7, |
|
"learning_rate": 1.65016501650165e-06, |
|
"loss": 0.3004, |
|
"step": 1960 |
|
}, |
|
{ |
|
"epoch": 9.75, |
|
"learning_rate": 1.3751375137513752e-06, |
|
"loss": 0.3053, |
|
"step": 1970 |
|
}, |
|
{ |
|
"epoch": 9.8, |
|
"learning_rate": 1.1001100110011001e-06, |
|
"loss": 0.2805, |
|
"step": 1980 |
|
}, |
|
{ |
|
"epoch": 9.85, |
|
"learning_rate": 8.25082508250825e-07, |
|
"loss": 0.2817, |
|
"step": 1990 |
|
}, |
|
{ |
|
"epoch": 9.9, |
|
"learning_rate": 5.500550055005501e-07, |
|
"loss": 0.3138, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 9.95, |
|
"learning_rate": 2.7502750275027504e-07, |
|
"loss": 0.2733, |
|
"step": 2010 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 0.0, |
|
"loss": 0.3089, |
|
"step": 2020 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"eval_accuracy": 0.8655520724486242, |
|
"eval_loss": 0.3326851427555084, |
|
"eval_runtime": 15.8375, |
|
"eval_samples_per_second": 181.279, |
|
"eval_steps_per_second": 5.683, |
|
"step": 2020 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"step": 2020, |
|
"total_flos": 2.0021605356722135e+19, |
|
"train_loss": 0.3826778081384036, |
|
"train_runtime": 3330.0466, |
|
"train_samples_per_second": 77.588, |
|
"train_steps_per_second": 0.607 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 2020, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 10, |
|
"save_steps": 500, |
|
"total_flos": 2.0021605356722135e+19, |
|
"train_batch_size": 32, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|