| { | |
| "best_metric": 0.9857142857142858, | |
| "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-975", | |
| "epoch": 15.0625, | |
| "global_step": 1200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 2.4162, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 2.3905, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.25e-05, | |
| "loss": 2.3538, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 2.3149, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 2.2402, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.1902, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.916666666666667e-05, | |
| "loss": 2.1382, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.2571428571428571, | |
| "eval_loss": 2.105558156967163, | |
| "eval_runtime": 6.8406, | |
| "eval_samples_per_second": 10.233, | |
| "eval_steps_per_second": 2.631, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.1216, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 1.8205, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.7791, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 1.4561, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3894, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.9537037037037035e-05, | |
| "loss": 0.9883, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.9074074074074075e-05, | |
| "loss": 0.9602, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 0.8185, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.6269657611846924, | |
| "eval_runtime": 6.7548, | |
| "eval_samples_per_second": 10.363, | |
| "eval_steps_per_second": 2.665, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.6751, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 4.768518518518519e-05, | |
| "loss": 0.8774, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.5025, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 4.675925925925926e-05, | |
| "loss": 0.7617, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.5016, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 0.7137, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 4.5370370370370374e-05, | |
| "loss": 0.5221, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.4340825378894806, | |
| "eval_runtime": 6.8255, | |
| "eval_samples_per_second": 10.256, | |
| "eval_steps_per_second": 2.637, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.490740740740741e-05, | |
| "loss": 0.2861, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.3487, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 4.3981481481481486e-05, | |
| "loss": 0.41, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 4.351851851851852e-05, | |
| "loss": 0.2375, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 4.305555555555556e-05, | |
| "loss": 0.3549, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 0.338, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 4.212962962962963e-05, | |
| "loss": 0.4893, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.1069, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.4389760196208954, | |
| "eval_runtime": 6.8626, | |
| "eval_samples_per_second": 10.2, | |
| "eval_steps_per_second": 2.623, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.1203703703703705e-05, | |
| "loss": 0.3017, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.2006, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 4.027777777777778e-05, | |
| "loss": 0.8863, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 3.981481481481482e-05, | |
| "loss": 0.0937, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 3.935185185185186e-05, | |
| "loss": 0.1638, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.1285, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 3.8425925925925924e-05, | |
| "loss": 0.0195, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.29379311203956604, | |
| "eval_runtime": 6.6946, | |
| "eval_samples_per_second": 10.456, | |
| "eval_steps_per_second": 2.689, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.7962962962962964e-05, | |
| "loss": 0.1345, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.0226, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.0097, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 3.6574074074074076e-05, | |
| "loss": 0.3541, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.2285, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 3.564814814814815e-05, | |
| "loss": 0.2023, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.0792, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.0097, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.21138475835323334, | |
| "eval_runtime": 6.7377, | |
| "eval_samples_per_second": 10.389, | |
| "eval_steps_per_second": 2.672, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 3.425925925925926e-05, | |
| "loss": 0.2802, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 3.3796296296296295e-05, | |
| "loss": 0.2688, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0271, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 3.2870370370370375e-05, | |
| "loss": 0.0278, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.0655, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 3.194444444444444e-05, | |
| "loss": 0.063, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 0.0076, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "eval_accuracy": 0.9428571428571428, | |
| "eval_loss": 0.1508892923593521, | |
| "eval_runtime": 6.6721, | |
| "eval_samples_per_second": 10.491, | |
| "eval_steps_per_second": 2.698, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.101851851851852e-05, | |
| "loss": 0.157, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.0048, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 3.0092592592592593e-05, | |
| "loss": 0.0622, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.0213, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 2.916666666666667e-05, | |
| "loss": 0.0034, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 2.8703703703703706e-05, | |
| "loss": 0.0495, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 2.824074074074074e-05, | |
| "loss": 0.0037, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.1686, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.2527245581150055, | |
| "eval_runtime": 6.9358, | |
| "eval_samples_per_second": 10.093, | |
| "eval_steps_per_second": 2.595, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 2.7314814814814816e-05, | |
| "loss": 0.0044, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 2.6851851851851855e-05, | |
| "loss": 0.0034, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 2.6388888888888892e-05, | |
| "loss": 0.0038, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.0055, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 2.5462962962962965e-05, | |
| "loss": 0.2185, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.1292, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 2.4537037037037038e-05, | |
| "loss": 0.0679, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "eval_accuracy": 0.9714285714285714, | |
| "eval_loss": 0.061473362147808075, | |
| "eval_runtime": 6.7398, | |
| "eval_samples_per_second": 10.386, | |
| "eval_steps_per_second": 2.671, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 0.0031, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 2.361111111111111e-05, | |
| "loss": 0.008, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.0656, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 2.2685185185185187e-05, | |
| "loss": 0.0026, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0029, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 2.175925925925926e-05, | |
| "loss": 0.0035, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 2.1296296296296296e-05, | |
| "loss": 0.0029, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.0024, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "eval_accuracy": 0.9428571428571428, | |
| "eval_loss": 0.15893925726413727, | |
| "eval_runtime": 6.754, | |
| "eval_samples_per_second": 10.364, | |
| "eval_steps_per_second": 2.665, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 0.0027, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 1.990740740740741e-05, | |
| "loss": 0.0024, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 10.03, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.0025, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 10.03, | |
| "learning_rate": 1.8981481481481482e-05, | |
| "loss": 0.0023, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.0873, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 1.8055555555555555e-05, | |
| "loss": 0.1121, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 10.06, | |
| "learning_rate": 1.7592592592592595e-05, | |
| "loss": 0.1946, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 10.06, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.40144404768943787, | |
| "eval_runtime": 6.6936, | |
| "eval_samples_per_second": 10.458, | |
| "eval_steps_per_second": 2.689, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 1.712962962962963e-05, | |
| "loss": 0.1594, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.003, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 1.6203703703703704e-05, | |
| "loss": 0.0025, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 1.574074074074074e-05, | |
| "loss": 0.0093, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 1.527777777777778e-05, | |
| "loss": 0.0034, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.0251, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "learning_rate": 1.4351851851851853e-05, | |
| "loss": 0.1587, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.154, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "eval_accuracy": 0.9428571428571428, | |
| "eval_loss": 0.1862240433692932, | |
| "eval_runtime": 6.664, | |
| "eval_samples_per_second": 10.504, | |
| "eval_steps_per_second": 2.701, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 1.3425925925925928e-05, | |
| "loss": 0.0023, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 0.0025, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.0027, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "learning_rate": 1.2037037037037037e-05, | |
| "loss": 0.002, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 12.04, | |
| "learning_rate": 1.1574074074074075e-05, | |
| "loss": 0.002, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0025, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 12.06, | |
| "learning_rate": 1.0648148148148148e-05, | |
| "loss": 0.0021, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 12.06, | |
| "eval_accuracy": 0.9857142857142858, | |
| "eval_loss": 0.06825670599937439, | |
| "eval_runtime": 6.9976, | |
| "eval_samples_per_second": 10.003, | |
| "eval_steps_per_second": 2.572, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 1.0185185185185185e-05, | |
| "loss": 0.002, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 9.722222222222223e-06, | |
| "loss": 0.0018, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.002, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 13.03, | |
| "learning_rate": 8.796296296296297e-06, | |
| "loss": 0.0022, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.0021, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "learning_rate": 7.87037037037037e-06, | |
| "loss": 0.0019, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.0021, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.0019, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "eval_accuracy": 0.9857142857142858, | |
| "eval_loss": 0.05410011112689972, | |
| "eval_runtime": 6.8574, | |
| "eval_samples_per_second": 10.208, | |
| "eval_steps_per_second": 2.625, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 6.481481481481481e-06, | |
| "loss": 0.0019, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 6.0185185185185185e-06, | |
| "loss": 0.0019, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.002, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 5.092592592592592e-06, | |
| "loss": 0.0019, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.002, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 14.05, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.0018, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.002, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "eval_accuracy": 0.9857142857142858, | |
| "eval_loss": 0.04728488251566887, | |
| "eval_runtime": 7.0728, | |
| "eval_samples_per_second": 9.897, | |
| "eval_steps_per_second": 2.545, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 3.2407407407407406e-06, | |
| "loss": 0.0022, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 0.002, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 2.3148148148148148e-06, | |
| "loss": 0.0019, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.002, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 1.388888888888889e-06, | |
| "loss": 0.0019, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "learning_rate": 9.259259259259259e-07, | |
| "loss": 0.0018, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "learning_rate": 4.6296296296296297e-07, | |
| "loss": 0.0019, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 15.06, | |
| "learning_rate": 0.0, | |
| "loss": 0.0018, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 15.06, | |
| "eval_accuracy": 0.9857142857142858, | |
| "eval_loss": 0.047529980540275574, | |
| "eval_runtime": 6.8222, | |
| "eval_samples_per_second": 10.261, | |
| "eval_steps_per_second": 2.638, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 15.06, | |
| "step": 1200, | |
| "total_flos": 5.981536752500736e+18, | |
| "train_loss": 0.3337698955554515, | |
| "train_runtime": 902.4336, | |
| "train_samples_per_second": 5.319, | |
| "train_steps_per_second": 1.33 | |
| }, | |
| { | |
| "epoch": 15.06, | |
| "eval_accuracy": 0.896774193548387, | |
| "eval_loss": 0.3229670226573944, | |
| "eval_runtime": 15.168, | |
| "eval_samples_per_second": 10.219, | |
| "eval_steps_per_second": 2.571, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 15.06, | |
| "eval_accuracy": 0.896774193548387, | |
| "eval_loss": 0.3229670226573944, | |
| "eval_runtime": 15.21, | |
| "eval_samples_per_second": 10.191, | |
| "eval_steps_per_second": 2.564, | |
| "step": 1200 | |
| } | |
| ], | |
| "max_steps": 1200, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 5.981536752500736e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |