| { | |
| "best_metric": 0.9, | |
| "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-1500", | |
| "epoch": 4.2, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 2.306, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 2.1606, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1e-05, | |
| "loss": 2.4268, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 2.3848, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 2.3762, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2e-05, | |
| "loss": 2.274, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 2.0968, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 2.2914, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 3e-05, | |
| "loss": 2.063, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.2059, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 2.3758, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4e-05, | |
| "loss": 2.221, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 2.268, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 2.1193, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8585, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.962962962962963e-05, | |
| "loss": 1.8749, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.925925925925926e-05, | |
| "loss": 1.8721, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 2.1232, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.851851851851852e-05, | |
| "loss": 2.2728, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 1.5833, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.7777777777777784e-05, | |
| "loss": 2.4943, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.740740740740741e-05, | |
| "loss": 1.4056, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.703703703703704e-05, | |
| "loss": 1.9793, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 2.2575, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 1.6757, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.592592592592593e-05, | |
| "loss": 2.4101, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.555555555555556e-05, | |
| "loss": 1.5145, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.518518518518519e-05, | |
| "loss": 1.7479, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.481481481481482e-05, | |
| "loss": 1.5142, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.7238, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.22857142857142856, | |
| "eval_loss": 2.0761706829071045, | |
| "eval_runtime": 19.2571, | |
| "eval_samples_per_second": 3.635, | |
| "eval_steps_per_second": 3.635, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.4074074074074076e-05, | |
| "loss": 1.7489, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.3703703703703705e-05, | |
| "loss": 1.4939, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 1.6296, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 4.296296296296296e-05, | |
| "loss": 1.3562, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 0.5818, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.222222222222222e-05, | |
| "loss": 1.1949, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.185185185185185e-05, | |
| "loss": 1.2505, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.148148148148148e-05, | |
| "loss": 1.0854, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 4.111111111111111e-05, | |
| "loss": 1.732, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 1.0014, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.0370370370370374e-05, | |
| "loss": 0.8794, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 4e-05, | |
| "loss": 1.1037, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.962962962962963e-05, | |
| "loss": 1.4254, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.925925925925926e-05, | |
| "loss": 0.7539, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 1.0575, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.851851851851852e-05, | |
| "loss": 0.9441, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.814814814814815e-05, | |
| "loss": 0.8284, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.777777777777778e-05, | |
| "loss": 1.5265, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.740740740740741e-05, | |
| "loss": 1.0127, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.9213, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 1.0182, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.62962962962963e-05, | |
| "loss": 0.9835, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.592592592592593e-05, | |
| "loss": 1.1437, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.555555555555556e-05, | |
| "loss": 0.4694, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.6354, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.481481481481482e-05, | |
| "loss": 0.2423, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.444444444444445e-05, | |
| "loss": 0.748, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.4074074074074077e-05, | |
| "loss": 1.6204, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.3703703703703706e-05, | |
| "loss": 1.1294, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.7966, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_accuracy": 0.6571428571428571, | |
| "eval_loss": 1.0164680480957031, | |
| "eval_runtime": 19.5843, | |
| "eval_samples_per_second": 3.574, | |
| "eval_steps_per_second": 3.574, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 3.2962962962962964e-05, | |
| "loss": 0.6007, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 3.25925925925926e-05, | |
| "loss": 0.158, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 3.222222222222223e-05, | |
| "loss": 0.023, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 3.185185185185185e-05, | |
| "loss": 0.527, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 0.3728, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 0.9129, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 3.074074074074074e-05, | |
| "loss": 0.2727, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 3.037037037037037e-05, | |
| "loss": 0.3488, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4387, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.9726, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.925925925925926e-05, | |
| "loss": 1.0291, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.8888888888888888e-05, | |
| "loss": 0.3092, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.851851851851852e-05, | |
| "loss": 1.0766, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.814814814814815e-05, | |
| "loss": 0.2486, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.7074, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 2.7407407407407408e-05, | |
| "loss": 0.1293, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 2.7037037037037037e-05, | |
| "loss": 0.2645, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.3538, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2.6296296296296296e-05, | |
| "loss": 0.3856, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.0705, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 2.5555555555555554e-05, | |
| "loss": 0.5857, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 2.5185185185185183e-05, | |
| "loss": 0.0951, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 2.4814814814814816e-05, | |
| "loss": 0.3052, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.4444444444444445e-05, | |
| "loss": 0.2961, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 0.2497, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 2.3703703703703707e-05, | |
| "loss": 0.6132, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.2086, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2.2962962962962965e-05, | |
| "loss": 0.0316, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2.2592592592592594e-05, | |
| "loss": 0.0949, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.4519, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_accuracy": 0.7857142857142857, | |
| "eval_loss": 0.9175742864608765, | |
| "eval_runtime": 18.8555, | |
| "eval_samples_per_second": 3.712, | |
| "eval_steps_per_second": 3.712, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 2.1851851851851852e-05, | |
| "loss": 0.353, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 2.148148148148148e-05, | |
| "loss": 0.0182, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 2.111111111111111e-05, | |
| "loss": 0.3075, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 2.074074074074074e-05, | |
| "loss": 0.0136, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 0.2276, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 2e-05, | |
| "loss": 0.011, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 1.962962962962963e-05, | |
| "loss": 0.195, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 1.925925925925926e-05, | |
| "loss": 0.0206, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 1.888888888888889e-05, | |
| "loss": 0.1989, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.0081, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 1.814814814814815e-05, | |
| "loss": 0.6501, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 1.777777777777778e-05, | |
| "loss": 0.0752, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 1.740740740740741e-05, | |
| "loss": 0.8654, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 1.7037037037037038e-05, | |
| "loss": 0.0042, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.6607, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 1.62962962962963e-05, | |
| "loss": 0.0183, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 1.5925925925925926e-05, | |
| "loss": 0.1674, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 1.5555555555555555e-05, | |
| "loss": 0.0218, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 1.5185185185185186e-05, | |
| "loss": 0.5633, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.0141, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 1.4444444444444444e-05, | |
| "loss": 0.6692, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 1.4074074074074075e-05, | |
| "loss": 0.4001, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 1.3703703703703704e-05, | |
| "loss": 0.0032, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.8661, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 0.0253, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 1.2592592592592592e-05, | |
| "loss": 0.1007, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 1.2222222222222222e-05, | |
| "loss": 0.3541, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 1.1851851851851853e-05, | |
| "loss": 0.5522, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 1.1481481481481482e-05, | |
| "loss": 0.5345, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 1.8337, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.9078142642974854, | |
| "eval_runtime": 20.2891, | |
| "eval_samples_per_second": 3.45, | |
| "eval_steps_per_second": 3.45, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 1.074074074074074e-05, | |
| "loss": 0.6171, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 1.037037037037037e-05, | |
| "loss": 0.058, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1281, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 9.62962962962963e-06, | |
| "loss": 0.1206, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.5738, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 8.88888888888889e-06, | |
| "loss": 0.005, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 8.518518518518519e-06, | |
| "loss": 0.573, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 8.14814814814815e-06, | |
| "loss": 0.4713, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 7.777777777777777e-06, | |
| "loss": 0.0032, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.0057, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 7.0370370370370375e-06, | |
| "loss": 0.0834, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.0153, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 6.296296296296296e-06, | |
| "loss": 0.0073, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 5.925925925925927e-06, | |
| "loss": 0.4686, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.5656, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 5.185185185185185e-06, | |
| "loss": 0.0061, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 4.814814814814815e-06, | |
| "loss": 0.0059, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 4.444444444444445e-06, | |
| "loss": 0.0169, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 4.074074074074075e-06, | |
| "loss": 0.1485, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.0036, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.2698, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 2.9629629629629633e-06, | |
| "loss": 0.012, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 2.5925925925925925e-06, | |
| "loss": 0.0598, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 2.2222222222222225e-06, | |
| "loss": 0.0041, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.0035, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 1.4814814814814817e-06, | |
| "loss": 0.0048, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 1.1111111111111112e-06, | |
| "loss": 0.022, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 7.407407407407408e-07, | |
| "loss": 0.4452, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 3.703703703703704e-07, | |
| "loss": 0.0023, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 0.0, | |
| "loss": 0.006, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.38240665197372437, | |
| "eval_runtime": 17.0083, | |
| "eval_samples_per_second": 4.116, | |
| "eval_steps_per_second": 4.116, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "step": 1500, | |
| "total_flos": 1.86923023515648e+18, | |
| "train_loss": 0.8117700910270214, | |
| "train_runtime": 1160.0655, | |
| "train_samples_per_second": 1.293, | |
| "train_steps_per_second": 1.293 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "eval_accuracy": 0.9161290322580645, | |
| "eval_loss": 0.2619660198688507, | |
| "eval_runtime": 42.6134, | |
| "eval_samples_per_second": 3.637, | |
| "eval_steps_per_second": 3.637, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "eval_accuracy": 0.9161290322580645, | |
| "eval_loss": 0.2619659900665283, | |
| "eval_runtime": 43.4165, | |
| "eval_samples_per_second": 3.57, | |
| "eval_steps_per_second": 3.57, | |
| "step": 1500 | |
| } | |
| ], | |
| "max_steps": 1500, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 1.86923023515648e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |