| { | |
| "best_metric": 0.7694382022471911, | |
| "best_model_checkpoint": "videomae-base-finetuned-ucf_crime2/checkpoint-1350", | |
| "epoch": 19.05, | |
| "global_step": 2700, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 1.161, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.9572, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.7833, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.6751, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.6776, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.7582, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 0.9072, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 1.083, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.6728, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.8973, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 0.7393, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 1.0236, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 0.475, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.6004424778761062, | |
| "eval_loss": 0.9934607148170471, | |
| "eval_runtime": 459.4529, | |
| "eval_samples_per_second": 4.919, | |
| "eval_steps_per_second": 2.459, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.4687, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 1.2807, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 1.0942, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 0.7793, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.2889, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 1.5235, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 1.301, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.8914, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 1.0077, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 0.7204, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.994, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 1.0282, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.5885, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5e-05, | |
| "loss": 1.44, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_accuracy": 0.42741573033707864, | |
| "eval_loss": 1.419556736946106, | |
| "eval_runtime": 453.7779, | |
| "eval_samples_per_second": 4.903, | |
| "eval_steps_per_second": 2.453, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.9794238683127575e-05, | |
| "loss": 1.2216, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 4.958847736625515e-05, | |
| "loss": 1.0898, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 0.7468, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 4.9176954732510286e-05, | |
| "loss": 0.9055, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 4.8971193415637865e-05, | |
| "loss": 1.0255, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 4.876543209876544e-05, | |
| "loss": 0.4722, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 4.855967078189301e-05, | |
| "loss": 1.4331, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 4.835390946502058e-05, | |
| "loss": 0.7642, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.8817, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 4.794238683127572e-05, | |
| "loss": 1.1087, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 4.773662551440329e-05, | |
| "loss": 0.8529, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 4.7530864197530866e-05, | |
| "loss": 1.0228, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 4.732510288065844e-05, | |
| "loss": 1.1084, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "eval_accuracy": 0.6737078651685393, | |
| "eval_loss": 0.9134577512741089, | |
| "eval_runtime": 453.5744, | |
| "eval_samples_per_second": 4.905, | |
| "eval_steps_per_second": 2.454, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.711934156378601e-05, | |
| "loss": 0.7187, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 4.691358024691358e-05, | |
| "loss": 0.6336, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 4.6707818930041156e-05, | |
| "loss": 1.158, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 4.650205761316873e-05, | |
| "loss": 1.1985, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 1.0297, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 4.609053497942387e-05, | |
| "loss": 0.7153, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 4.5884773662551446e-05, | |
| "loss": 1.5667, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 4.567901234567901e-05, | |
| "loss": 1.0087, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 4.5473251028806584e-05, | |
| "loss": 1.3097, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 4.5267489711934157e-05, | |
| "loss": 0.5826, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 4.506172839506173e-05, | |
| "loss": 1.5182, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 4.48559670781893e-05, | |
| "loss": 1.2051, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 4.4650205761316874e-05, | |
| "loss": 0.8987, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.8732, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "eval_accuracy": 0.5478651685393259, | |
| "eval_loss": 1.198416829109192, | |
| "eval_runtime": 453.9361, | |
| "eval_samples_per_second": 4.902, | |
| "eval_steps_per_second": 2.452, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.423868312757202e-05, | |
| "loss": 1.1824, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.403292181069959e-05, | |
| "loss": 1.154, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.3827160493827164e-05, | |
| "loss": 0.719, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.3621399176954737e-05, | |
| "loss": 1.1264, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 4.341563786008231e-05, | |
| "loss": 0.6353, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 4.3209876543209875e-05, | |
| "loss": 0.844, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 4.300411522633745e-05, | |
| "loss": 0.4229, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 4.279835390946502e-05, | |
| "loss": 1.0073, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 1.0208, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 4.2386831275720165e-05, | |
| "loss": 1.0574, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 4.2181069958847744e-05, | |
| "loss": 0.8135, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 4.197530864197531e-05, | |
| "loss": 0.7802, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 4.176954732510288e-05, | |
| "loss": 1.4184, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "eval_accuracy": 0.49258426966292135, | |
| "eval_loss": 1.3372939825057983, | |
| "eval_runtime": 451.1457, | |
| "eval_samples_per_second": 4.932, | |
| "eval_steps_per_second": 2.467, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.1563786008230455e-05, | |
| "loss": 1.6902, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 4.135802469135803e-05, | |
| "loss": 0.9522, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 4.11522633744856e-05, | |
| "loss": 0.9839, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 4.094650205761317e-05, | |
| "loss": 1.1898, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.9646, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 4.053497942386831e-05, | |
| "loss": 0.5725, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 4.032921810699588e-05, | |
| "loss": 0.7269, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 4.012345679012346e-05, | |
| "loss": 0.4925, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 3.9917695473251035e-05, | |
| "loss": 0.8769, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 3.971193415637861e-05, | |
| "loss": 1.2494, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 3.950617283950617e-05, | |
| "loss": 1.4721, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 3.9300411522633746e-05, | |
| "loss": 0.7253, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 3.909465020576132e-05, | |
| "loss": 0.9903, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 1.1355, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "eval_accuracy": 0.6148314606741573, | |
| "eval_loss": 0.9887858629226685, | |
| "eval_runtime": 451.8846, | |
| "eval_samples_per_second": 4.924, | |
| "eval_steps_per_second": 2.463, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 3.868312757201646e-05, | |
| "loss": 1.0351, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 3.8477366255144036e-05, | |
| "loss": 0.9506, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 3.82716049382716e-05, | |
| "loss": 0.6972, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 3.806584362139918e-05, | |
| "loss": 1.11, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 3.786008230452675e-05, | |
| "loss": 0.6072, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 3.7654320987654326e-05, | |
| "loss": 1.2918, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 3.74485596707819e-05, | |
| "loss": 1.5236, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 3.724279835390947e-05, | |
| "loss": 1.1904, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.8145, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 3.683127572016461e-05, | |
| "loss": 0.9992, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 3.662551440329218e-05, | |
| "loss": 0.6562, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 3.6419753086419754e-05, | |
| "loss": 0.6701, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 3.6213991769547327e-05, | |
| "loss": 0.4522, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "eval_accuracy": 0.569438202247191, | |
| "eval_loss": 1.074515700340271, | |
| "eval_runtime": 453.9477, | |
| "eval_samples_per_second": 4.901, | |
| "eval_steps_per_second": 2.452, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.60082304526749e-05, | |
| "loss": 0.5866, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 3.580246913580247e-05, | |
| "loss": 0.9363, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 3.5596707818930044e-05, | |
| "loss": 0.9, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 3.539094650205762e-05, | |
| "loss": 1.1666, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.919, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 3.497942386831276e-05, | |
| "loss": 0.7928, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 3.4773662551440334e-05, | |
| "loss": 1.0973, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 3.45679012345679e-05, | |
| "loss": 0.8628, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 3.436213991769547e-05, | |
| "loss": 1.0555, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 3.4156378600823045e-05, | |
| "loss": 0.4659, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 3.395061728395062e-05, | |
| "loss": 1.1641, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 3.374485596707819e-05, | |
| "loss": 0.7964, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 3.353909465020576e-05, | |
| "loss": 0.9106, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.7754, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "eval_accuracy": 0.5330337078651686, | |
| "eval_loss": 1.5848411321640015, | |
| "eval_runtime": 455.0314, | |
| "eval_samples_per_second": 4.89, | |
| "eval_steps_per_second": 2.446, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 3.312757201646091e-05, | |
| "loss": 0.6768, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 3.292181069958848e-05, | |
| "loss": 1.2231, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 3.271604938271605e-05, | |
| "loss": 0.823, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 3.2510288065843625e-05, | |
| "loss": 0.7431, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 3.230452674897119e-05, | |
| "loss": 1.5209, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 3.209876543209876e-05, | |
| "loss": 0.9587, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 3.1893004115226336e-05, | |
| "loss": 0.7317, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 3.168724279835391e-05, | |
| "loss": 0.5452, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 0.7977, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 3.127572016460906e-05, | |
| "loss": 0.6247, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 3.1069958847736626e-05, | |
| "loss": 1.2815, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 3.08641975308642e-05, | |
| "loss": 1.487, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 3.065843621399177e-05, | |
| "loss": 1.1235, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "eval_accuracy": 0.5752808988764045, | |
| "eval_loss": 1.3688323497772217, | |
| "eval_runtime": 455.1649, | |
| "eval_samples_per_second": 4.888, | |
| "eval_steps_per_second": 2.445, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 3.0452674897119343e-05, | |
| "loss": 0.7969, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 3.0246913580246916e-05, | |
| "loss": 1.3205, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 3.0041152263374488e-05, | |
| "loss": 0.6858, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 2.9835390946502057e-05, | |
| "loss": 0.6296, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.3671, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 2.9423868312757202e-05, | |
| "loss": 1.118, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 2.9218106995884775e-05, | |
| "loss": 1.138, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 2.9012345679012347e-05, | |
| "loss": 0.7986, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 2.880658436213992e-05, | |
| "loss": 0.939, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 2.860082304526749e-05, | |
| "loss": 0.9008, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 2.839506172839506e-05, | |
| "loss": 0.4685, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 2.8189300411522634e-05, | |
| "loss": 0.4786, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 2.7983539094650207e-05, | |
| "loss": 1.3754, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 1.611, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "eval_accuracy": 0.7694382022471911, | |
| "eval_loss": 0.6958285570144653, | |
| "eval_runtime": 451.5196, | |
| "eval_samples_per_second": 4.928, | |
| "eval_steps_per_second": 2.465, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 2.757201646090535e-05, | |
| "loss": 0.4512, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 2.736625514403292e-05, | |
| "loss": 1.2525, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 2.7160493827160493e-05, | |
| "loss": 0.8525, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 2.6954732510288066e-05, | |
| "loss": 0.5316, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 2.6748971193415638e-05, | |
| "loss": 0.7157, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 2.654320987654321e-05, | |
| "loss": 0.5926, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 10.03, | |
| "learning_rate": 2.6337448559670787e-05, | |
| "loss": 0.5692, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 10.03, | |
| "learning_rate": 2.6131687242798352e-05, | |
| "loss": 1.0166, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 10.03, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.3822, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "learning_rate": 2.5720164609053497e-05, | |
| "loss": 0.7237, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "learning_rate": 2.551440329218107e-05, | |
| "loss": 0.273, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "learning_rate": 2.5308641975308646e-05, | |
| "loss": 1.3527, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 2.510288065843622e-05, | |
| "loss": 0.5714, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "eval_accuracy": 0.7541573033707866, | |
| "eval_loss": 0.8026723861694336, | |
| "eval_runtime": 451.0424, | |
| "eval_samples_per_second": 4.933, | |
| "eval_steps_per_second": 2.468, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 2.4897119341563787e-05, | |
| "loss": 0.7973, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 2.4691358024691357e-05, | |
| "loss": 0.6256, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 2.4485596707818932e-05, | |
| "loss": 0.5342, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 2.4279835390946505e-05, | |
| "loss": 0.7312, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 0.6744, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 2.3868312757201647e-05, | |
| "loss": 1.1513, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 2.366255144032922e-05, | |
| "loss": 0.7242, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 2.345679012345679e-05, | |
| "loss": 1.1095, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 2.3251028806584364e-05, | |
| "loss": 1.0725, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 2.3045267489711937e-05, | |
| "loss": 0.3324, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 2.2839506172839506e-05, | |
| "loss": 0.3455, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 2.2633744855967078e-05, | |
| "loss": 0.617, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "learning_rate": 2.242798353909465e-05, | |
| "loss": 0.8421, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.716, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "eval_accuracy": 0.6782022471910112, | |
| "eval_loss": 1.350299596786499, | |
| "eval_runtime": 452.7002, | |
| "eval_samples_per_second": 4.915, | |
| "eval_steps_per_second": 2.459, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 2.2016460905349796e-05, | |
| "loss": 0.4089, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 2.1810699588477368e-05, | |
| "loss": 0.4587, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 2.1604938271604937e-05, | |
| "loss": 0.6623, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 2.139917695473251e-05, | |
| "loss": 1.1919, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 2.1193415637860082e-05, | |
| "loss": 1.3429, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 2.0987654320987655e-05, | |
| "loss": 0.7212, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "learning_rate": 2.0781893004115227e-05, | |
| "loss": 1.2803, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "learning_rate": 2.05761316872428e-05, | |
| "loss": 1.0035, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 0.7179, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 12.04, | |
| "learning_rate": 2.016460905349794e-05, | |
| "loss": 0.5513, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 12.04, | |
| "learning_rate": 1.9958847736625517e-05, | |
| "loss": 1.147, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 12.04, | |
| "learning_rate": 1.9753086419753087e-05, | |
| "loss": 0.1456, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "learning_rate": 1.954732510288066e-05, | |
| "loss": 0.6642, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "eval_accuracy": 0.6957303370786517, | |
| "eval_loss": 1.0797581672668457, | |
| "eval_runtime": 455.6582, | |
| "eval_samples_per_second": 4.883, | |
| "eval_steps_per_second": 2.443, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 1.934156378600823e-05, | |
| "loss": 0.2892, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 1.91358024691358e-05, | |
| "loss": 0.7764, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 1.8930041152263377e-05, | |
| "loss": 0.7818, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 1.872427983539095e-05, | |
| "loss": 0.5361, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.6236, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 1.831275720164609e-05, | |
| "loss": 0.4748, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 1.8106995884773663e-05, | |
| "loss": 0.4336, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 13.03, | |
| "learning_rate": 1.7901234567901236e-05, | |
| "loss": 0.2829, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 13.03, | |
| "learning_rate": 1.769547325102881e-05, | |
| "loss": 1.1384, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "learning_rate": 1.748971193415638e-05, | |
| "loss": 0.312, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "learning_rate": 1.728395061728395e-05, | |
| "loss": 0.1352, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "learning_rate": 1.7078189300411522e-05, | |
| "loss": 0.3037, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "learning_rate": 1.6872427983539095e-05, | |
| "loss": 1.5336, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.8451, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "eval_accuracy": 0.7478651685393258, | |
| "eval_loss": 1.2327640056610107, | |
| "eval_runtime": 454.752, | |
| "eval_samples_per_second": 4.893, | |
| "eval_steps_per_second": 2.447, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 1.646090534979424e-05, | |
| "loss": 0.3734, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 1.6255144032921812e-05, | |
| "loss": 0.9384, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 1.604938271604938e-05, | |
| "loss": 0.3985, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 1.5843621399176954e-05, | |
| "loss": 0.3549, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 1.563786008230453e-05, | |
| "loss": 0.5028, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 1.54320987654321e-05, | |
| "loss": 0.7132, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 1.5226337448559672e-05, | |
| "loss": 0.497, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 1.5020576131687244e-05, | |
| "loss": 0.4788, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 1.0759, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "learning_rate": 1.4609053497942387e-05, | |
| "loss": 0.3888, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "learning_rate": 1.440329218106996e-05, | |
| "loss": 0.4838, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "learning_rate": 1.419753086419753e-05, | |
| "loss": 0.5042, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 14.05, | |
| "learning_rate": 1.3991769547325103e-05, | |
| "loss": 0.6157, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 14.05, | |
| "eval_accuracy": 0.5761797752808989, | |
| "eval_loss": 1.9402521848678589, | |
| "eval_runtime": 453.7626, | |
| "eval_samples_per_second": 4.903, | |
| "eval_steps_per_second": 2.453, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 1.3786008230452676e-05, | |
| "loss": 0.5696, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 1.3580246913580247e-05, | |
| "loss": 0.5913, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 1.3374485596707819e-05, | |
| "loss": 0.6535, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 1.3168724279835393e-05, | |
| "loss": 0.0899, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 0.5375, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 1.2757201646090535e-05, | |
| "loss": 0.17, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 1.255144032921811e-05, | |
| "loss": 0.9722, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.6784, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 1.2139917695473252e-05, | |
| "loss": 1.101, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 1.1934156378600823e-05, | |
| "loss": 0.9849, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 1.1728395061728396e-05, | |
| "loss": 0.5966, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 1.1522633744855968e-05, | |
| "loss": 0.5226, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "learning_rate": 1.1316872427983539e-05, | |
| "loss": 0.853, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.3358, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "eval_accuracy": 0.6939325842696629, | |
| "eval_loss": 1.343485951423645, | |
| "eval_runtime": 450.914, | |
| "eval_samples_per_second": 4.934, | |
| "eval_steps_per_second": 2.468, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 1.0905349794238684e-05, | |
| "loss": 0.2757, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 1.0699588477366255e-05, | |
| "loss": 1.0079, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 1.0493827160493827e-05, | |
| "loss": 0.2953, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 1.02880658436214e-05, | |
| "loss": 0.0277, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 1.008230452674897e-05, | |
| "loss": 0.8641, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 9.876543209876543e-06, | |
| "loss": 1.6375, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 9.670781893004116e-06, | |
| "loss": 0.4548, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 9.465020576131688e-06, | |
| "loss": 1.2109, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 1.1418, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 16.04, | |
| "learning_rate": 9.053497942386832e-06, | |
| "loss": 0.1765, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 16.04, | |
| "learning_rate": 8.847736625514404e-06, | |
| "loss": 0.6366, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 16.04, | |
| "learning_rate": 8.641975308641975e-06, | |
| "loss": 0.3775, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 16.05, | |
| "learning_rate": 8.436213991769547e-06, | |
| "loss": 0.5394, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 16.05, | |
| "eval_accuracy": 0.7056179775280899, | |
| "eval_loss": 1.2524322271347046, | |
| "eval_runtime": 451.5141, | |
| "eval_samples_per_second": 4.928, | |
| "eval_steps_per_second": 2.465, | |
| "step": 2295 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 8.23045267489712e-06, | |
| "loss": 0.4007, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 8.02469135802469e-06, | |
| "loss": 0.0099, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 7.818930041152265e-06, | |
| "loss": 0.7945, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 7.613168724279836e-06, | |
| "loss": 0.9694, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.543, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 7.20164609053498e-06, | |
| "loss": 0.3373, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 6.995884773662552e-06, | |
| "loss": 0.1535, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 17.03, | |
| "learning_rate": 6.790123456790123e-06, | |
| "loss": 1.0903, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 17.03, | |
| "learning_rate": 6.584362139917697e-06, | |
| "loss": 1.1557, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 17.04, | |
| "learning_rate": 6.3786008230452675e-06, | |
| "loss": 0.4063, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 17.04, | |
| "learning_rate": 6.172839506172839e-06, | |
| "loss": 0.3571, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 17.04, | |
| "learning_rate": 5.967078189300412e-06, | |
| "loss": 0.2122, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 17.05, | |
| "learning_rate": 5.761316872427984e-06, | |
| "loss": 0.6792, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 17.05, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.3334, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 17.05, | |
| "eval_accuracy": 0.7644943820224719, | |
| "eval_loss": 1.1189634799957275, | |
| "eval_runtime": 451.7673, | |
| "eval_samples_per_second": 4.925, | |
| "eval_steps_per_second": 2.464, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 5.3497942386831275e-06, | |
| "loss": 0.1849, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 5.1440329218107e-06, | |
| "loss": 0.4635, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 4.938271604938272e-06, | |
| "loss": 0.3219, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 4.732510288065844e-06, | |
| "loss": 0.4388, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 4.526748971193416e-06, | |
| "loss": 0.0534, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 4.3209876543209875e-06, | |
| "loss": 0.9314, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 18.03, | |
| "learning_rate": 4.11522633744856e-06, | |
| "loss": 0.2579, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 18.03, | |
| "learning_rate": 3.9094650205761325e-06, | |
| "loss": 1.321, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 18.03, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.5764, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 18.04, | |
| "learning_rate": 3.497942386831276e-06, | |
| "loss": 0.4099, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 18.04, | |
| "learning_rate": 3.2921810699588483e-06, | |
| "loss": 0.1749, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 18.04, | |
| "learning_rate": 3.0864197530864196e-06, | |
| "loss": 0.008, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 18.05, | |
| "learning_rate": 2.880658436213992e-06, | |
| "loss": 0.3513, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 18.05, | |
| "eval_accuracy": 0.7460674157303371, | |
| "eval_loss": 1.213651418685913, | |
| "eval_runtime": 453.0911, | |
| "eval_samples_per_second": 4.911, | |
| "eval_steps_per_second": 2.456, | |
| "step": 2565 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 2.6748971193415637e-06, | |
| "loss": 0.3758, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 2.469135802469136e-06, | |
| "loss": 1.1312, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 2.263374485596708e-06, | |
| "loss": 0.2969, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 2.05761316872428e-06, | |
| "loss": 0.1413, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 1.0703, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 1.6460905349794242e-06, | |
| "loss": 0.5428, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 1.440329218106996e-06, | |
| "loss": 0.0521, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "learning_rate": 1.234567901234568e-06, | |
| "loss": 0.3258, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "learning_rate": 1.02880658436214e-06, | |
| "loss": 0.8149, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 8.230452674897121e-07, | |
| "loss": 0.4027, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 6.17283950617284e-07, | |
| "loss": 0.4456, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 4.1152263374485604e-07, | |
| "loss": 0.1438, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 19.05, | |
| "learning_rate": 2.0576131687242802e-07, | |
| "loss": 0.0089, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 19.05, | |
| "learning_rate": 0.0, | |
| "loss": 0.2531, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 19.05, | |
| "eval_accuracy": 0.7361797752808988, | |
| "eval_loss": 1.2130513191223145, | |
| "eval_runtime": 450.9469, | |
| "eval_samples_per_second": 4.934, | |
| "eval_steps_per_second": 2.468, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 19.05, | |
| "step": 2700, | |
| "total_flos": 6.728808791074406e+18, | |
| "train_loss": 0.7812991208555522, | |
| "train_runtime": 12592.4173, | |
| "train_samples_per_second": 0.429, | |
| "train_steps_per_second": 0.214 | |
| }, | |
| { | |
| "epoch": 19.05, | |
| "eval_accuracy": 0.5199748348537276, | |
| "eval_loss": 1.8463083505630493, | |
| "eval_runtime": 631.3319, | |
| "eval_samples_per_second": 5.035, | |
| "eval_steps_per_second": 2.518, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 19.05, | |
| "eval_accuracy": 0.5199748348537276, | |
| "eval_loss": 1.8463084697723389, | |
| "eval_runtime": 626.062, | |
| "eval_samples_per_second": 5.078, | |
| "eval_steps_per_second": 2.54, | |
| "step": 2700 | |
| } | |
| ], | |
| "max_steps": 2700, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 6.728808791074406e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |