| { | |
| "best_metric": 0.8212643678160919, | |
| "best_model_checkpoint": "videomae-base-finetuned-ucf_crime/checkpoint-2280", | |
| "epoch": 49.02, | |
| "global_step": 6000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 8.333333333333333e-07, | |
| "loss": 0.7241, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 0.7076, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.763, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.7228, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.6616, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7404, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.833333333333334e-06, | |
| "loss": 0.7135, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.6836, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.5e-06, | |
| "loss": 0.6721, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.6418, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.166666666666666e-06, | |
| "loss": 0.5405, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6487, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.6988505747126437, | |
| "eval_loss": 0.6812763810157776, | |
| "eval_runtime": 356.8448, | |
| "eval_samples_per_second": 4.876, | |
| "eval_steps_per_second": 2.438, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.0833333333333334e-05, | |
| "loss": 0.6362, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.1666666666666668e-05, | |
| "loss": 0.8027, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.6654, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.7161, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.4166666666666668e-05, | |
| "loss": 0.6356, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.5828, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.5833333333333333e-05, | |
| "loss": 0.6804, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.6067, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.75e-05, | |
| "loss": 0.9103, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.8333333333333333e-05, | |
| "loss": 0.779, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.9166666666666667e-05, | |
| "loss": 0.9004, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4529, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_accuracy": 0.5678160919540229, | |
| "eval_loss": 0.746660590171814, | |
| "eval_runtime": 362.9202, | |
| "eval_samples_per_second": 4.794, | |
| "eval_steps_per_second": 2.397, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.7456, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.1666666666666667e-05, | |
| "loss": 0.7377, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.25e-05, | |
| "loss": 0.9795, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 1.3186, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.4166666666666667e-05, | |
| "loss": 0.7593, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.7627, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.5833333333333336e-05, | |
| "loss": 0.832, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.5974, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.7500000000000004e-05, | |
| "loss": 0.4035, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.8333333333333335e-05, | |
| "loss": 1.1156, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.916666666666667e-05, | |
| "loss": 0.8433, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 3e-05, | |
| "loss": 0.5165, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_accuracy": 0.7264367816091954, | |
| "eval_loss": 0.7599618434906006, | |
| "eval_runtime": 363.2632, | |
| "eval_samples_per_second": 4.79, | |
| "eval_steps_per_second": 2.395, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.0833333333333335e-05, | |
| "loss": 0.6962, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.1666666666666666e-05, | |
| "loss": 0.9465, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.2500000000000004e-05, | |
| "loss": 0.9085, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.2004, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.4166666666666666e-05, | |
| "loss": 0.5015, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.5292, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.5833333333333335e-05, | |
| "loss": 1.0356, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 0.4709, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 1.0485, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.8333333333333334e-05, | |
| "loss": 1.2158, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.9166666666666665e-05, | |
| "loss": 1.6987, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 4e-05, | |
| "loss": 0.9203, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "eval_accuracy": 0.6517241379310345, | |
| "eval_loss": 0.6189371943473816, | |
| "eval_runtime": 360.5738, | |
| "eval_samples_per_second": 4.826, | |
| "eval_steps_per_second": 2.413, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.0833333333333334e-05, | |
| "loss": 0.3345, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.161, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.25e-05, | |
| "loss": 1.7037, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 1.1513, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.4166666666666665e-05, | |
| "loss": 0.8115, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.636, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 0.6967, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 1.0099, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.75e-05, | |
| "loss": 0.8856, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 4.8333333333333334e-05, | |
| "loss": 0.4968, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 4.9166666666666665e-05, | |
| "loss": 0.9492, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2667, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "eval_accuracy": 0.6511494252873563, | |
| "eval_loss": 0.6701719164848328, | |
| "eval_runtime": 360.4153, | |
| "eval_samples_per_second": 4.828, | |
| "eval_steps_per_second": 2.414, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.9907407407407406e-05, | |
| "loss": 0.4786, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.981481481481482e-05, | |
| "loss": 0.6767, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.972222222222223e-05, | |
| "loss": 0.9659, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 4.962962962962963e-05, | |
| "loss": 1.4623, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 4.9537037037037035e-05, | |
| "loss": 0.6624, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 4.9444444444444446e-05, | |
| "loss": 0.8057, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 4.935185185185186e-05, | |
| "loss": 0.8291, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 4.925925925925926e-05, | |
| "loss": 0.6476, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 4.9166666666666665e-05, | |
| "loss": 1.1142, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 4.9074074074074075e-05, | |
| "loss": 1.0131, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 4.8981481481481486e-05, | |
| "loss": 0.7027, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 1.0452, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "eval_accuracy": 0.7591954022988506, | |
| "eval_loss": 0.5703285932540894, | |
| "eval_runtime": 357.4022, | |
| "eval_samples_per_second": 4.868, | |
| "eval_steps_per_second": 2.434, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.87962962962963e-05, | |
| "loss": 0.6886, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.8703703703703704e-05, | |
| "loss": 0.6544, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 0.8136, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 4.851851851851852e-05, | |
| "loss": 0.5133, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 4.842592592592593e-05, | |
| "loss": 0.5336, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 4.8333333333333334e-05, | |
| "loss": 0.9107, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 4.8240740740740744e-05, | |
| "loss": 0.7703, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 1.2991, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 4.805555555555556e-05, | |
| "loss": 0.6108, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 4.796296296296296e-05, | |
| "loss": 0.8556, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 4.7870370370370373e-05, | |
| "loss": 1.1234, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 4.7777777777777784e-05, | |
| "loss": 0.3893, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "eval_accuracy": 0.7396551724137931, | |
| "eval_loss": 0.5523963570594788, | |
| "eval_runtime": 356.1273, | |
| "eval_samples_per_second": 4.886, | |
| "eval_steps_per_second": 2.443, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 4.768518518518519e-05, | |
| "loss": 0.3443, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 4.759259259259259e-05, | |
| "loss": 0.6966, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 4.75e-05, | |
| "loss": 1.2216, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 4.740740740740741e-05, | |
| "loss": 0.3746, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 4.731481481481482e-05, | |
| "loss": 0.8805, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.6962, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 4.712962962962963e-05, | |
| "loss": 1.3004, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 4.703703703703704e-05, | |
| "loss": 1.1392, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 4.6944444444444446e-05, | |
| "loss": 0.9222, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 4.685185185185185e-05, | |
| "loss": 0.7862, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 4.675925925925926e-05, | |
| "loss": 0.8084, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 1.2013, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "eval_accuracy": 0.610919540229885, | |
| "eval_loss": 0.7469594478607178, | |
| "eval_runtime": 353.1759, | |
| "eval_samples_per_second": 4.927, | |
| "eval_steps_per_second": 2.463, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.6574074074074076e-05, | |
| "loss": 0.8368, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.648148148148148e-05, | |
| "loss": 0.564, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 4.638888888888889e-05, | |
| "loss": 0.8657, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.8194, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 4.6203703703703705e-05, | |
| "loss": 0.4039, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 4.6111111111111115e-05, | |
| "loss": 0.8453, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 4.601851851851852e-05, | |
| "loss": 1.0273, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 4.592592592592593e-05, | |
| "loss": 1.2728, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 0.5125, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 4.5740740740740745e-05, | |
| "loss": 0.8747, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 4.564814814814815e-05, | |
| "loss": 0.6782, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 4.555555555555556e-05, | |
| "loss": 1.4903, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "eval_accuracy": 0.5695402298850575, | |
| "eval_loss": 1.0093830823898315, | |
| "eval_runtime": 355.0274, | |
| "eval_samples_per_second": 4.901, | |
| "eval_steps_per_second": 2.451, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.546296296296296e-05, | |
| "loss": 0.3923, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.5370370370370374e-05, | |
| "loss": 0.7116, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 4.527777777777778e-05, | |
| "loss": 0.3186, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 4.518518518518519e-05, | |
| "loss": 0.9053, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 4.50925925925926e-05, | |
| "loss": 1.272, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.4022, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 4.490740740740741e-05, | |
| "loss": 0.9156, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 4.481481481481482e-05, | |
| "loss": 0.87, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 4.472222222222223e-05, | |
| "loss": 1.2737, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 4.462962962962963e-05, | |
| "loss": 0.5527, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 4.4537037037037036e-05, | |
| "loss": 0.558, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.5434, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "eval_accuracy": 0.7586206896551724, | |
| "eval_loss": 0.5188660025596619, | |
| "eval_runtime": 355.6201, | |
| "eval_samples_per_second": 4.893, | |
| "eval_steps_per_second": 2.446, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.435185185185186e-05, | |
| "loss": 0.3802, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.425925925925926e-05, | |
| "loss": 0.8603, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 4.4166666666666665e-05, | |
| "loss": 0.8157, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 4.4074074074074076e-05, | |
| "loss": 0.5727, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 4.3981481481481486e-05, | |
| "loss": 0.8289, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 4.388888888888889e-05, | |
| "loss": 0.8628, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 4.3796296296296294e-05, | |
| "loss": 0.9309, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 4.3703703703703705e-05, | |
| "loss": 0.4891, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 4.3611111111111116e-05, | |
| "loss": 1.0905, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 4.351851851851852e-05, | |
| "loss": 0.8349, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 4.342592592592592e-05, | |
| "loss": 0.8802, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 0.8344, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "eval_accuracy": 0.5551724137931034, | |
| "eval_loss": 0.7673728466033936, | |
| "eval_runtime": 364.5203, | |
| "eval_samples_per_second": 4.773, | |
| "eval_steps_per_second": 2.387, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.3240740740740745e-05, | |
| "loss": 0.9388, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.314814814814815e-05, | |
| "loss": 0.6321, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 4.305555555555556e-05, | |
| "loss": 0.785, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 4.296296296296296e-05, | |
| "loss": 0.8641, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 4.2870370370370374e-05, | |
| "loss": 0.582, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 4.277777777777778e-05, | |
| "loss": 0.5381, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 4.268518518518519e-05, | |
| "loss": 0.3799, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 1.1579, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 4.25e-05, | |
| "loss": 0.7256, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 4.240740740740741e-05, | |
| "loss": 0.4198, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 4.231481481481482e-05, | |
| "loss": 0.9882, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 4.222222222222222e-05, | |
| "loss": 1.1621, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "eval_accuracy": 0.5873563218390805, | |
| "eval_loss": 0.9610044360160828, | |
| "eval_runtime": 355.0886, | |
| "eval_samples_per_second": 4.9, | |
| "eval_steps_per_second": 2.45, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.212962962962963e-05, | |
| "loss": 0.8105, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.203703703703704e-05, | |
| "loss": 0.5899, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 4.194444444444445e-05, | |
| "loss": 0.6743, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 4.185185185185185e-05, | |
| "loss": 1.4275, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 4.175925925925926e-05, | |
| "loss": 0.6946, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.7746, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 4.1574074074074076e-05, | |
| "loss": 0.6887, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 4.148148148148148e-05, | |
| "loss": 0.9869, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 4.138888888888889e-05, | |
| "loss": 0.6283, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 4.12962962962963e-05, | |
| "loss": 0.2219, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 4.1203703703703705e-05, | |
| "loss": 0.5915, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 4.111111111111111e-05, | |
| "loss": 0.8743, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "eval_accuracy": 0.6448275862068965, | |
| "eval_loss": 0.8160411715507507, | |
| "eval_runtime": 355.8367, | |
| "eval_samples_per_second": 4.89, | |
| "eval_steps_per_second": 2.445, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 4.101851851851852e-05, | |
| "loss": 0.7112, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 4.092592592592593e-05, | |
| "loss": 1.2422, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 4.0833333333333334e-05, | |
| "loss": 1.365, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.5083, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 4.064814814814815e-05, | |
| "loss": 0.7632, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 4.055555555555556e-05, | |
| "loss": 0.8477, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 4.0462962962962963e-05, | |
| "loss": 0.3935, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 4.0370370370370374e-05, | |
| "loss": 1.2253, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 4.027777777777778e-05, | |
| "loss": 1.5369, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 4.018518518518519e-05, | |
| "loss": 0.8792, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 4.009259259259259e-05, | |
| "loss": 0.8461, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7118, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "eval_accuracy": 0.6591954022988505, | |
| "eval_loss": 0.6014773845672607, | |
| "eval_runtime": 354.7515, | |
| "eval_samples_per_second": 4.905, | |
| "eval_steps_per_second": 2.452, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 3.990740740740741e-05, | |
| "loss": 0.7558, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 3.981481481481482e-05, | |
| "loss": 0.7457, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 3.972222222222222e-05, | |
| "loss": 0.5081, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 3.962962962962963e-05, | |
| "loss": 0.781, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 3.9537037037037036e-05, | |
| "loss": 0.5625, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 3.944444444444445e-05, | |
| "loss": 0.7814, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 3.935185185185186e-05, | |
| "loss": 0.7786, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 3.925925925925926e-05, | |
| "loss": 0.426, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 3.9166666666666665e-05, | |
| "loss": 0.7625, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 3.9074074074074076e-05, | |
| "loss": 1.0261, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 3.898148148148149e-05, | |
| "loss": 1.0153, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.8404, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "eval_accuracy": 0.7660919540229885, | |
| "eval_loss": 0.7148768901824951, | |
| "eval_runtime": 354.5439, | |
| "eval_samples_per_second": 4.908, | |
| "eval_steps_per_second": 2.454, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 3.8796296296296295e-05, | |
| "loss": 0.4245, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 3.8703703703703705e-05, | |
| "loss": 0.9398, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 3.8611111111111116e-05, | |
| "loss": 0.4956, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 3.851851851851852e-05, | |
| "loss": 0.3703, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 3.8425925925925924e-05, | |
| "loss": 1.2318, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 3.8333333333333334e-05, | |
| "loss": 0.8561, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 3.8240740740740745e-05, | |
| "loss": 0.9777, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 3.814814814814815e-05, | |
| "loss": 0.8541, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 3.805555555555555e-05, | |
| "loss": 0.6224, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 3.7962962962962964e-05, | |
| "loss": 1.0637, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 3.7870370370370374e-05, | |
| "loss": 1.0431, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 3.777777777777778e-05, | |
| "loss": 1.0397, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "eval_accuracy": 0.7770114942528735, | |
| "eval_loss": 0.6360009908676147, | |
| "eval_runtime": 354.5339, | |
| "eval_samples_per_second": 4.908, | |
| "eval_steps_per_second": 2.454, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 3.768518518518518e-05, | |
| "loss": 0.3126, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 3.759259259259259e-05, | |
| "loss": 0.7058, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.3957, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 3.740740740740741e-05, | |
| "loss": 1.4855, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 3.731481481481482e-05, | |
| "loss": 1.0118, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 3.722222222222222e-05, | |
| "loss": 1.1027, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 3.712962962962963e-05, | |
| "loss": 1.2266, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.6825, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 3.694444444444445e-05, | |
| "loss": 0.568, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 3.685185185185185e-05, | |
| "loss": 0.4856, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 3.675925925925926e-05, | |
| "loss": 0.8751, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 1.3511, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "eval_accuracy": 0.6522988505747126, | |
| "eval_loss": 0.9110041260719299, | |
| "eval_runtime": 356.131, | |
| "eval_samples_per_second": 4.886, | |
| "eval_steps_per_second": 2.443, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 3.6574074074074076e-05, | |
| "loss": 0.3147, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 3.648148148148148e-05, | |
| "loss": 1.0829, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 3.638888888888889e-05, | |
| "loss": 0.8333, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 3.62962962962963e-05, | |
| "loss": 0.8554, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 3.6203703703703706e-05, | |
| "loss": 0.9251, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 1.1388, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 3.601851851851852e-05, | |
| "loss": 0.519, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 3.592592592592593e-05, | |
| "loss": 0.6697, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 3.5833333333333335e-05, | |
| "loss": 0.4289, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 3.574074074074074e-05, | |
| "loss": 0.819, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 3.564814814814815e-05, | |
| "loss": 1.1293, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 3.555555555555556e-05, | |
| "loss": 1.0257, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "eval_accuracy": 0.5890804597701149, | |
| "eval_loss": 1.0642170906066895, | |
| "eval_runtime": 355.6816, | |
| "eval_samples_per_second": 4.892, | |
| "eval_steps_per_second": 2.446, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 3.5462962962962964e-05, | |
| "loss": 0.4082, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 3.537037037037037e-05, | |
| "loss": 0.6808, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 3.527777777777778e-05, | |
| "loss": 0.4721, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.6651, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 3.509259259259259e-05, | |
| "loss": 0.5115, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.5868, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 3.490740740740741e-05, | |
| "loss": 0.6031, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 3.481481481481482e-05, | |
| "loss": 0.7139, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.7654, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 3.4629629629629626e-05, | |
| "loss": 0.2731, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 3.453703703703704e-05, | |
| "loss": 1.1167, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 3.444444444444445e-05, | |
| "loss": 1.0726, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "eval_accuracy": 0.8212643678160919, | |
| "eval_loss": 0.7299070954322815, | |
| "eval_runtime": 356.169, | |
| "eval_samples_per_second": 4.885, | |
| "eval_steps_per_second": 2.443, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 3.435185185185185e-05, | |
| "loss": 0.3174, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 3.425925925925926e-05, | |
| "loss": 0.5826, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 3.4166666666666666e-05, | |
| "loss": 0.9714, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 3.4074074074074077e-05, | |
| "loss": 0.4854, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 3.398148148148148e-05, | |
| "loss": 1.1501, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 3.388888888888889e-05, | |
| "loss": 0.7365, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 3.3796296296296295e-05, | |
| "loss": 0.7153, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 3.3703703703703706e-05, | |
| "loss": 0.9818, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 3.3611111111111116e-05, | |
| "loss": 0.9492, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 3.351851851851852e-05, | |
| "loss": 1.0675, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 3.3425925925925924e-05, | |
| "loss": 0.3415, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.5609, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "eval_accuracy": 0.6408045977011494, | |
| "eval_loss": 0.8921392560005188, | |
| "eval_runtime": 355.1169, | |
| "eval_samples_per_second": 4.9, | |
| "eval_steps_per_second": 2.45, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.3240740740740746e-05, | |
| "loss": 1.036, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.314814814814815e-05, | |
| "loss": 0.5695, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.3055555555555553e-05, | |
| "loss": 0.5739, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 3.2962962962962964e-05, | |
| "loss": 0.5152, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 3.2870370370370375e-05, | |
| "loss": 1.0498, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 3.277777777777778e-05, | |
| "loss": 0.5446, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 3.268518518518518e-05, | |
| "loss": 0.1624, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 3.25925925925926e-05, | |
| "loss": 1.5474, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "learning_rate": 3.2500000000000004e-05, | |
| "loss": 1.507, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.371, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "learning_rate": 3.231481481481481e-05, | |
| "loss": 0.443, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "learning_rate": 3.222222222222223e-05, | |
| "loss": 0.495, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "eval_accuracy": 0.7632183908045977, | |
| "eval_loss": 0.7762243747711182, | |
| "eval_runtime": 355.6167, | |
| "eval_samples_per_second": 4.893, | |
| "eval_steps_per_second": 2.446, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 3.212962962962963e-05, | |
| "loss": 0.4073, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 3.203703703703704e-05, | |
| "loss": 1.5583, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 3.194444444444444e-05, | |
| "loss": 0.5917, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 3.185185185185185e-05, | |
| "loss": 0.4646, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 3.175925925925926e-05, | |
| "loss": 0.5858, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 3.1666666666666666e-05, | |
| "loss": 0.5061, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 3.157407407407408e-05, | |
| "loss": 0.4264, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 0.2457, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "learning_rate": 3.138888888888889e-05, | |
| "loss": 0.7008, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "learning_rate": 3.1296296296296295e-05, | |
| "loss": 0.616, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "learning_rate": 3.1203703703703706e-05, | |
| "loss": 0.8168, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 1.6306, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "eval_accuracy": 0.7091954022988506, | |
| "eval_loss": 0.9975525736808777, | |
| "eval_runtime": 354.7554, | |
| "eval_samples_per_second": 4.905, | |
| "eval_steps_per_second": 2.452, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 3.101851851851852e-05, | |
| "loss": 0.416, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 3.0925925925925924e-05, | |
| "loss": 0.7102, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 3.0833333333333335e-05, | |
| "loss": 0.7875, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 3.074074074074074e-05, | |
| "loss": 0.0282, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 3.064814814814815e-05, | |
| "loss": 0.7786, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.6717, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 3.0462962962962964e-05, | |
| "loss": 0.5418, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 3.037037037037037e-05, | |
| "loss": 0.4978, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "learning_rate": 3.0277777777777776e-05, | |
| "loss": 1.2388, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "learning_rate": 3.018518518518519e-05, | |
| "loss": 0.6185, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "learning_rate": 3.0092592592592593e-05, | |
| "loss": 0.7501, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0072, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "eval_accuracy": 0.8028735632183908, | |
| "eval_loss": 0.5696666240692139, | |
| "eval_runtime": 354.9525, | |
| "eval_samples_per_second": 4.902, | |
| "eval_steps_per_second": 2.451, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 2.9907407407407405e-05, | |
| "loss": 0.666, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 2.981481481481482e-05, | |
| "loss": 0.507, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 2.9722222222222223e-05, | |
| "loss": 0.6905, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.5331, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 2.953703703703704e-05, | |
| "loss": 0.7063, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 2.9444444444444448e-05, | |
| "loss": 0.8265, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 2.9351851851851852e-05, | |
| "loss": 0.5169, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 2.925925925925926e-05, | |
| "loss": 0.5814, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "learning_rate": 2.916666666666667e-05, | |
| "loss": 0.9736, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "learning_rate": 2.9074074074074077e-05, | |
| "loss": 0.8377, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "learning_rate": 2.898148148148148e-05, | |
| "loss": 0.9445, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "learning_rate": 2.8888888888888888e-05, | |
| "loss": 0.4503, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "eval_accuracy": 0.6913793103448276, | |
| "eval_loss": 0.8447661995887756, | |
| "eval_runtime": 354.9507, | |
| "eval_samples_per_second": 4.902, | |
| "eval_steps_per_second": 2.451, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 2.87962962962963e-05, | |
| "loss": 0.2364, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 2.8703703703703706e-05, | |
| "loss": 0.6677, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 2.861111111111111e-05, | |
| "loss": 0.5877, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 2.851851851851852e-05, | |
| "loss": 0.4619, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 2.8425925925925928e-05, | |
| "loss": 0.3709, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 2.8333333333333335e-05, | |
| "loss": 0.254, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 2.824074074074074e-05, | |
| "loss": 1.4855, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 2.814814814814815e-05, | |
| "loss": 0.7073, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "learning_rate": 2.8055555555555557e-05, | |
| "loss": 0.9287, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "learning_rate": 2.7962962962962965e-05, | |
| "loss": 0.0098, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "learning_rate": 2.7870370370370375e-05, | |
| "loss": 0.8322, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.8306, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "eval_accuracy": 0.7350574712643678, | |
| "eval_loss": 0.961682915687561, | |
| "eval_runtime": 355.3327, | |
| "eval_samples_per_second": 4.897, | |
| "eval_steps_per_second": 2.448, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 2.7685185185185186e-05, | |
| "loss": 0.3266, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 2.7592592592592594e-05, | |
| "loss": 0.6064, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 2.7500000000000004e-05, | |
| "loss": 0.8877, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "learning_rate": 2.7407407407407408e-05, | |
| "loss": 0.2949, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "learning_rate": 2.7314814814814816e-05, | |
| "loss": 0.8731, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "learning_rate": 2.7222222222222223e-05, | |
| "loss": 0.1076, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "learning_rate": 2.7129629629629634e-05, | |
| "loss": 0.2606, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "learning_rate": 2.7037037037037037e-05, | |
| "loss": 0.9969, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "learning_rate": 2.6944444444444445e-05, | |
| "loss": 0.4266, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "learning_rate": 2.6851851851851855e-05, | |
| "loss": 0.454, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "learning_rate": 2.6759259259259263e-05, | |
| "loss": 0.6279, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.8824, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "eval_accuracy": 0.6758620689655173, | |
| "eval_loss": 1.183898687362671, | |
| "eval_runtime": 354.9739, | |
| "eval_samples_per_second": 4.902, | |
| "eval_steps_per_second": 2.451, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 2.6574074074074074e-05, | |
| "loss": 0.7845, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 2.6481481481481485e-05, | |
| "loss": 0.3211, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 2.6388888888888892e-05, | |
| "loss": 0.4379, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 2.6296296296296296e-05, | |
| "loss": 0.8879, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 2.6203703703703703e-05, | |
| "loss": 0.4217, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 2.6111111111111114e-05, | |
| "loss": 0.4884, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 2.601851851851852e-05, | |
| "loss": 0.658, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.3958, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "learning_rate": 2.5833333333333336e-05, | |
| "loss": 0.0735, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "learning_rate": 2.5740740740740743e-05, | |
| "loss": 0.5385, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "learning_rate": 2.564814814814815e-05, | |
| "loss": 0.2616, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "learning_rate": 2.5555555555555554e-05, | |
| "loss": 0.837, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "eval_accuracy": 0.6074712643678161, | |
| "eval_loss": 1.640615701675415, | |
| "eval_runtime": 358.9161, | |
| "eval_samples_per_second": 4.848, | |
| "eval_steps_per_second": 2.424, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 2.5462962962962965e-05, | |
| "loss": 0.6176, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 2.5370370370370372e-05, | |
| "loss": 0.4121, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 2.527777777777778e-05, | |
| "loss": 0.7788, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 2.5185185185185183e-05, | |
| "loss": 0.7417, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 2.5092592592592594e-05, | |
| "loss": 0.6805, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.4876, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 2.490740740740741e-05, | |
| "loss": 0.6502, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 2.4814814814814816e-05, | |
| "loss": 0.7487, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 2.4722222222222223e-05, | |
| "loss": 1.0194, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 2.462962962962963e-05, | |
| "loss": 0.3909, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 2.4537037037037038e-05, | |
| "loss": 0.7057, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 2.4444444444444445e-05, | |
| "loss": 0.4214, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "eval_accuracy": 0.6919540229885057, | |
| "eval_loss": 1.1276469230651855, | |
| "eval_runtime": 368.278, | |
| "eval_samples_per_second": 4.725, | |
| "eval_steps_per_second": 2.362, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 2.4351851851851852e-05, | |
| "loss": 0.5698, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 2.425925925925926e-05, | |
| "loss": 0.6112, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 2.4166666666666667e-05, | |
| "loss": 0.1946, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 0.6828, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "learning_rate": 2.398148148148148e-05, | |
| "loss": 0.4324, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "learning_rate": 2.3888888888888892e-05, | |
| "loss": 0.2255, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "learning_rate": 2.3796296296296296e-05, | |
| "loss": 0.3095, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "learning_rate": 2.3703703703703707e-05, | |
| "loss": 0.6489, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "learning_rate": 2.361111111111111e-05, | |
| "loss": 0.5608, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "learning_rate": 2.351851851851852e-05, | |
| "loss": 0.3346, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "learning_rate": 2.3425925925925925e-05, | |
| "loss": 0.8548, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.5166, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "eval_accuracy": 0.7626436781609195, | |
| "eval_loss": 1.081528663635254, | |
| "eval_runtime": 366.7196, | |
| "eval_samples_per_second": 4.745, | |
| "eval_steps_per_second": 2.372, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 2.324074074074074e-05, | |
| "loss": 0.184, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.9068, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 2.3055555555555558e-05, | |
| "loss": 0.4148, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 2.2962962962962965e-05, | |
| "loss": 0.308, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 2.2870370370370372e-05, | |
| "loss": 0.4313, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 2.277777777777778e-05, | |
| "loss": 0.0049, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 2.2685185185185187e-05, | |
| "loss": 0.8774, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 2.2592592592592594e-05, | |
| "loss": 1.244, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "learning_rate": 2.25e-05, | |
| "loss": 0.5034, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "learning_rate": 2.240740740740741e-05, | |
| "loss": 0.2402, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "learning_rate": 2.2314814814814816e-05, | |
| "loss": 0.0161, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.6925, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "eval_accuracy": 0.7086206896551724, | |
| "eval_loss": 1.1491729021072388, | |
| "eval_runtime": 364.1723, | |
| "eval_samples_per_second": 4.778, | |
| "eval_steps_per_second": 2.389, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 2.212962962962963e-05, | |
| "loss": 0.2812, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 2.2037037037037038e-05, | |
| "loss": 0.5704, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 2.1944444444444445e-05, | |
| "loss": 0.638, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "learning_rate": 2.1851851851851852e-05, | |
| "loss": 0.6747, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "learning_rate": 2.175925925925926e-05, | |
| "loss": 0.1777, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "learning_rate": 2.1666666666666667e-05, | |
| "loss": 0.0085, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "learning_rate": 2.1574074074074074e-05, | |
| "loss": 0.4212, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "learning_rate": 2.148148148148148e-05, | |
| "loss": 0.2663, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 30.02, | |
| "learning_rate": 2.138888888888889e-05, | |
| "loss": 0.7677, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 30.02, | |
| "learning_rate": 2.1296296296296296e-05, | |
| "loss": 0.6289, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 30.02, | |
| "learning_rate": 2.1203703703703703e-05, | |
| "loss": 0.565, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 30.02, | |
| "learning_rate": 2.111111111111111e-05, | |
| "loss": 0.2864, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 30.02, | |
| "eval_accuracy": 0.7344827586206897, | |
| "eval_loss": 1.1919379234313965, | |
| "eval_runtime": 367.8385, | |
| "eval_samples_per_second": 4.73, | |
| "eval_steps_per_second": 2.365, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "learning_rate": 2.101851851851852e-05, | |
| "loss": 0.7583, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "learning_rate": 2.0925925925925925e-05, | |
| "loss": 1.0015, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.65, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 2.074074074074074e-05, | |
| "loss": 0.4765, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 2.064814814814815e-05, | |
| "loss": 0.0245, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 2.0555555555555555e-05, | |
| "loss": 0.3426, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 2.0462962962962965e-05, | |
| "loss": 0.3368, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 0.4659, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 31.02, | |
| "learning_rate": 2.027777777777778e-05, | |
| "loss": 0.005, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 31.02, | |
| "learning_rate": 2.0185185185185187e-05, | |
| "loss": 0.6972, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 31.02, | |
| "learning_rate": 2.0092592592592594e-05, | |
| "loss": 1.1985, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 31.02, | |
| "learning_rate": 2e-05, | |
| "loss": 0.463, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 31.02, | |
| "eval_accuracy": 0.6936781609195403, | |
| "eval_loss": 1.3523625135421753, | |
| "eval_runtime": 368.5262, | |
| "eval_samples_per_second": 4.722, | |
| "eval_steps_per_second": 2.361, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 1.990740740740741e-05, | |
| "loss": 0.2083, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 1.9814814814814816e-05, | |
| "loss": 0.245, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 1.9722222222222224e-05, | |
| "loss": 0.8645, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 1.962962962962963e-05, | |
| "loss": 0.273, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 1.9537037037037038e-05, | |
| "loss": 0.4796, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.5766, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 1.9351851851851853e-05, | |
| "loss": 0.2411, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 1.925925925925926e-05, | |
| "loss": 0.2637, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 32.02, | |
| "learning_rate": 1.9166666666666667e-05, | |
| "loss": 0.2752, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 32.02, | |
| "learning_rate": 1.9074074074074075e-05, | |
| "loss": 0.4028, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 32.02, | |
| "learning_rate": 1.8981481481481482e-05, | |
| "loss": 0.7273, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 32.02, | |
| "learning_rate": 1.888888888888889e-05, | |
| "loss": 1.1162, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 32.02, | |
| "eval_accuracy": 0.582183908045977, | |
| "eval_loss": 1.830126166343689, | |
| "eval_runtime": 366.2978, | |
| "eval_samples_per_second": 4.75, | |
| "eval_steps_per_second": 2.375, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 1.8796296296296296e-05, | |
| "loss": 0.2229, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 1.8703703703703704e-05, | |
| "loss": 0.3904, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "learning_rate": 1.861111111111111e-05, | |
| "loss": 0.047, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.482, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "learning_rate": 1.8425925925925926e-05, | |
| "loss": 0.2528, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "learning_rate": 1.8333333333333333e-05, | |
| "loss": 0.782, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "learning_rate": 1.824074074074074e-05, | |
| "loss": 0.4598, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "learning_rate": 1.814814814814815e-05, | |
| "loss": 0.532, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 33.02, | |
| "learning_rate": 1.8055555555555555e-05, | |
| "loss": 0.4071, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 33.02, | |
| "learning_rate": 1.7962962962962965e-05, | |
| "loss": 0.0044, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 33.02, | |
| "learning_rate": 1.787037037037037e-05, | |
| "loss": 0.5293, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 33.02, | |
| "learning_rate": 1.777777777777778e-05, | |
| "loss": 0.0033, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 33.02, | |
| "eval_accuracy": 0.6890804597701149, | |
| "eval_loss": 1.4447053670883179, | |
| "eval_runtime": 368.5359, | |
| "eval_samples_per_second": 4.721, | |
| "eval_steps_per_second": 2.361, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 1.7685185185185184e-05, | |
| "loss": 0.0077, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 1.7592592592592595e-05, | |
| "loss": 0.5462, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 1.75e-05, | |
| "loss": 0.0031, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 1.740740740740741e-05, | |
| "loss": 0.2755, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 1.7314814814814813e-05, | |
| "loss": 0.0031, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 1.7222222222222224e-05, | |
| "loss": 0.4803, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 1.712962962962963e-05, | |
| "loss": 0.5753, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 1.7037037037037038e-05, | |
| "loss": 0.004, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 34.02, | |
| "learning_rate": 1.6944444444444446e-05, | |
| "loss": 0.1565, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 34.02, | |
| "learning_rate": 1.6851851851851853e-05, | |
| "loss": 0.3328, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 34.02, | |
| "learning_rate": 1.675925925925926e-05, | |
| "loss": 0.0359, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 34.02, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.002, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 34.02, | |
| "eval_accuracy": 0.6959770114942528, | |
| "eval_loss": 1.6565355062484741, | |
| "eval_runtime": 367.1701, | |
| "eval_samples_per_second": 4.739, | |
| "eval_steps_per_second": 2.369, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 1.6574074074074075e-05, | |
| "loss": 0.002, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 1.6481481481481482e-05, | |
| "loss": 0.0023, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "learning_rate": 1.638888888888889e-05, | |
| "loss": 0.3309, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "learning_rate": 1.62962962962963e-05, | |
| "loss": 0.0013, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "learning_rate": 1.6203703703703704e-05, | |
| "loss": 0.2573, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "learning_rate": 1.6111111111111115e-05, | |
| "loss": 0.3305, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "learning_rate": 1.601851851851852e-05, | |
| "loss": 0.5151, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "learning_rate": 1.5925925925925926e-05, | |
| "loss": 0.2275, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 35.02, | |
| "learning_rate": 1.5833333333333333e-05, | |
| "loss": 0.2553, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 35.02, | |
| "learning_rate": 1.574074074074074e-05, | |
| "loss": 1.3411, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 35.02, | |
| "learning_rate": 1.5648148148148148e-05, | |
| "loss": 0.2521, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 35.02, | |
| "learning_rate": 1.5555555555555555e-05, | |
| "loss": 0.0017, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 35.02, | |
| "eval_accuracy": 0.7281609195402299, | |
| "eval_loss": 1.5356777906417847, | |
| "eval_runtime": 366.7166, | |
| "eval_samples_per_second": 4.745, | |
| "eval_steps_per_second": 2.372, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 1.5462962962962962e-05, | |
| "loss": 0.0068, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 1.537037037037037e-05, | |
| "loss": 0.3627, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 1.527777777777778e-05, | |
| "loss": 0.1035, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 1.5185185185185186e-05, | |
| "loss": 0.002, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 1.5092592592592595e-05, | |
| "loss": 0.3503, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.7162, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 1.490740740740741e-05, | |
| "loss": 0.8599, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.0376, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 36.02, | |
| "learning_rate": 1.4722222222222224e-05, | |
| "loss": 0.4794, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 36.02, | |
| "learning_rate": 1.462962962962963e-05, | |
| "loss": 0.002, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 36.02, | |
| "learning_rate": 1.4537037037037039e-05, | |
| "loss": 0.2838, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 36.02, | |
| "learning_rate": 1.4444444444444444e-05, | |
| "loss": 0.2289, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 36.02, | |
| "eval_accuracy": 0.6396551724137931, | |
| "eval_loss": 1.9812363386154175, | |
| "eval_runtime": 368.0404, | |
| "eval_samples_per_second": 4.728, | |
| "eval_steps_per_second": 2.364, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "learning_rate": 1.4351851851851853e-05, | |
| "loss": 0.0018, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "learning_rate": 1.425925925925926e-05, | |
| "loss": 0.0082, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 1.4166666666666668e-05, | |
| "loss": 0.8398, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 1.4074074074074075e-05, | |
| "loss": 0.002, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 1.3981481481481482e-05, | |
| "loss": 0.5404, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.0074, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 1.3796296296296297e-05, | |
| "loss": 0.2944, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 1.3703703703703704e-05, | |
| "loss": 0.0018, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 37.02, | |
| "learning_rate": 1.3611111111111111e-05, | |
| "loss": 0.0025, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 37.02, | |
| "learning_rate": 1.3518518518518519e-05, | |
| "loss": 0.218, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 37.02, | |
| "learning_rate": 1.3425925925925928e-05, | |
| "loss": 0.0021, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 37.02, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.4801, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 37.02, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_loss": 2.2316389083862305, | |
| "eval_runtime": 367.6533, | |
| "eval_samples_per_second": 4.733, | |
| "eval_steps_per_second": 2.366, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 1.3240740740740742e-05, | |
| "loss": 0.0016, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 1.3148148148148148e-05, | |
| "loss": 0.279, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "learning_rate": 1.3055555555555557e-05, | |
| "loss": 0.0178, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 0.7231, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "learning_rate": 1.2870370370370371e-05, | |
| "loss": 0.9815, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "learning_rate": 1.2777777777777777e-05, | |
| "loss": 0.5828, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "learning_rate": 1.2685185185185186e-05, | |
| "loss": 0.0037, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "learning_rate": 1.2592592592592592e-05, | |
| "loss": 0.3147, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.0017, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "learning_rate": 1.2407407407407408e-05, | |
| "loss": 0.0022, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "learning_rate": 1.2314814814814815e-05, | |
| "loss": 0.5569, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "learning_rate": 1.2222222222222222e-05, | |
| "loss": 1.0323, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "eval_accuracy": 0.582183908045977, | |
| "eval_loss": 2.1379587650299072, | |
| "eval_runtime": 368.1572, | |
| "eval_samples_per_second": 4.726, | |
| "eval_steps_per_second": 2.363, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "learning_rate": 1.212962962962963e-05, | |
| "loss": 0.2515, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "learning_rate": 1.2037037037037037e-05, | |
| "loss": 0.0031, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 1.1944444444444446e-05, | |
| "loss": 0.0826, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 1.1851851851851853e-05, | |
| "loss": 0.2209, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 1.175925925925926e-05, | |
| "loss": 0.2841, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 1.1666666666666668e-05, | |
| "loss": 0.3254, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 1.1574074074074075e-05, | |
| "loss": 0.1848, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 1.1481481481481482e-05, | |
| "loss": 0.0076, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 39.02, | |
| "learning_rate": 1.138888888888889e-05, | |
| "loss": 0.5761, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 39.02, | |
| "learning_rate": 1.1296296296296297e-05, | |
| "loss": 0.2621, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 39.02, | |
| "learning_rate": 1.1203703703703704e-05, | |
| "loss": 0.0054, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 39.02, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0715, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 39.02, | |
| "eval_accuracy": 0.6344827586206897, | |
| "eval_loss": 1.9264222383499146, | |
| "eval_runtime": 369.3263, | |
| "eval_samples_per_second": 4.711, | |
| "eval_steps_per_second": 2.356, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 1.1018518518518519e-05, | |
| "loss": 0.3268, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 1.0925925925925926e-05, | |
| "loss": 0.1513, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "learning_rate": 1.0833333333333334e-05, | |
| "loss": 0.6202, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "learning_rate": 1.074074074074074e-05, | |
| "loss": 0.0015, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "learning_rate": 1.0648148148148148e-05, | |
| "loss": 0.2299, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "learning_rate": 1.0555555555555555e-05, | |
| "loss": 0.3157, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "learning_rate": 1.0462962962962963e-05, | |
| "loss": 0.5713, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "learning_rate": 1.037037037037037e-05, | |
| "loss": 0.0017, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 40.02, | |
| "learning_rate": 1.0277777777777777e-05, | |
| "loss": 0.3048, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 40.02, | |
| "learning_rate": 1.0185185185185185e-05, | |
| "loss": 0.2808, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 40.02, | |
| "learning_rate": 1.0092592592592594e-05, | |
| "loss": 0.0042, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 40.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0024, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 40.02, | |
| "eval_accuracy": 0.5022988505747127, | |
| "eval_loss": 2.625736951828003, | |
| "eval_runtime": 369.4977, | |
| "eval_samples_per_second": 4.709, | |
| "eval_steps_per_second": 2.355, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "learning_rate": 9.907407407407408e-06, | |
| "loss": 0.0013, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "learning_rate": 9.814814814814815e-06, | |
| "loss": 0.7708, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "learning_rate": 9.722222222222223e-06, | |
| "loss": 0.4907, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "learning_rate": 9.62962962962963e-06, | |
| "loss": 0.001, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "learning_rate": 9.537037037037037e-06, | |
| "loss": 0.3011, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "learning_rate": 9.444444444444445e-06, | |
| "loss": 0.1026, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "learning_rate": 9.351851851851852e-06, | |
| "loss": 0.4189, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.5392, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 41.02, | |
| "learning_rate": 9.166666666666666e-06, | |
| "loss": 0.4442, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 41.02, | |
| "learning_rate": 9.074074074074075e-06, | |
| "loss": 0.2831, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 41.02, | |
| "learning_rate": 8.981481481481483e-06, | |
| "loss": 0.0059, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 41.02, | |
| "learning_rate": 8.88888888888889e-06, | |
| "loss": 0.4734, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 41.02, | |
| "eval_accuracy": 0.6316091954022989, | |
| "eval_loss": 1.8665626049041748, | |
| "eval_runtime": 366.3463, | |
| "eval_samples_per_second": 4.75, | |
| "eval_steps_per_second": 2.375, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "learning_rate": 8.796296296296297e-06, | |
| "loss": 0.0236, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "learning_rate": 8.703703703703705e-06, | |
| "loss": 0.0025, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "learning_rate": 8.611111111111112e-06, | |
| "loss": 0.6772, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "learning_rate": 8.518518518518519e-06, | |
| "loss": 0.426, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "learning_rate": 8.425925925925926e-06, | |
| "loss": 0.0012, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.2111, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "learning_rate": 8.240740740740741e-06, | |
| "loss": 0.486, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "learning_rate": 8.14814814814815e-06, | |
| "loss": 0.2354, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 42.02, | |
| "learning_rate": 8.055555555555557e-06, | |
| "loss": 0.0016, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 42.02, | |
| "learning_rate": 7.962962962962963e-06, | |
| "loss": 0.0016, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 42.02, | |
| "learning_rate": 7.87037037037037e-06, | |
| "loss": 0.2763, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 42.02, | |
| "learning_rate": 7.777777777777777e-06, | |
| "loss": 0.3108, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 42.02, | |
| "eval_accuracy": 0.7298850574712644, | |
| "eval_loss": 1.5492610931396484, | |
| "eval_runtime": 368.3644, | |
| "eval_samples_per_second": 4.724, | |
| "eval_steps_per_second": 2.362, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "learning_rate": 7.685185185185185e-06, | |
| "loss": 0.0018, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "learning_rate": 7.592592592592593e-06, | |
| "loss": 0.001, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "learning_rate": 7.5e-06, | |
| "loss": 0.291, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.0006, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "learning_rate": 7.314814814814815e-06, | |
| "loss": 0.2717, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "learning_rate": 7.222222222222222e-06, | |
| "loss": 0.0038, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "learning_rate": 7.12962962962963e-06, | |
| "loss": 0.001, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "learning_rate": 7.0370370370370375e-06, | |
| "loss": 0.3122, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 43.02, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.3125, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 43.02, | |
| "learning_rate": 6.851851851851852e-06, | |
| "loss": 0.488, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 43.02, | |
| "learning_rate": 6.759259259259259e-06, | |
| "loss": 0.0019, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 43.02, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.2318, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 43.02, | |
| "eval_accuracy": 0.6333333333333333, | |
| "eval_loss": 2.083085536956787, | |
| "eval_runtime": 369.1574, | |
| "eval_samples_per_second": 4.713, | |
| "eval_steps_per_second": 2.357, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 6.574074074074074e-06, | |
| "loss": 0.2911, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 6.481481481481481e-06, | |
| "loss": 0.1259, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "learning_rate": 6.3888888888888885e-06, | |
| "loss": 0.0012, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "learning_rate": 6.296296296296296e-06, | |
| "loss": 0.11, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "learning_rate": 6.203703703703704e-06, | |
| "loss": 0.0012, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "learning_rate": 6.111111111111111e-06, | |
| "loss": 0.0015, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "learning_rate": 6.0185185185185185e-06, | |
| "loss": 0.0014, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "learning_rate": 5.925925925925927e-06, | |
| "loss": 0.0008, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 44.02, | |
| "learning_rate": 5.833333333333334e-06, | |
| "loss": 0.1953, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 44.02, | |
| "learning_rate": 5.740740740740741e-06, | |
| "loss": 0.2241, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 44.02, | |
| "learning_rate": 5.6481481481481485e-06, | |
| "loss": 0.2815, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 44.02, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.6623, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 44.02, | |
| "eval_accuracy": 0.6028735632183908, | |
| "eval_loss": 2.327577829360962, | |
| "eval_runtime": 367.4776, | |
| "eval_samples_per_second": 4.735, | |
| "eval_steps_per_second": 2.367, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 5.462962962962963e-06, | |
| "loss": 0.0018, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 5.37037037037037e-06, | |
| "loss": 0.0014, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "learning_rate": 5.277777777777778e-06, | |
| "loss": 0.0008, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "learning_rate": 5.185185185185185e-06, | |
| "loss": 0.001, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "learning_rate": 5.092592592592592e-06, | |
| "loss": 0.1921, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "learning_rate": 5e-06, | |
| "loss": 0.167, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "learning_rate": 4.907407407407408e-06, | |
| "loss": 0.2255, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "learning_rate": 4.814814814814815e-06, | |
| "loss": 0.0013, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 45.02, | |
| "learning_rate": 4.722222222222222e-06, | |
| "loss": 0.1237, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 45.02, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.0008, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 45.02, | |
| "learning_rate": 4.537037037037038e-06, | |
| "loss": 0.2072, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 45.02, | |
| "learning_rate": 4.444444444444445e-06, | |
| "loss": 0.0011, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 45.02, | |
| "eval_accuracy": 0.6683908045977012, | |
| "eval_loss": 2.046869993209839, | |
| "eval_runtime": 367.6951, | |
| "eval_samples_per_second": 4.732, | |
| "eval_steps_per_second": 2.366, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "learning_rate": 4.351851851851852e-06, | |
| "loss": 0.0005, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "learning_rate": 4.2592592592592596e-06, | |
| "loss": 0.2675, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.0012, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "learning_rate": 4.074074074074075e-06, | |
| "loss": 0.0006, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "learning_rate": 3.9814814814814814e-06, | |
| "loss": 0.0008, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "learning_rate": 3.888888888888889e-06, | |
| "loss": 0.4061, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "learning_rate": 3.7962962962962964e-06, | |
| "loss": 0.2902, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.0018, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 46.02, | |
| "learning_rate": 3.611111111111111e-06, | |
| "loss": 0.0097, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 46.02, | |
| "learning_rate": 3.5185185185185187e-06, | |
| "loss": 0.3332, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 46.02, | |
| "learning_rate": 3.425925925925926e-06, | |
| "loss": 0.0009, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 46.02, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.32, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 46.02, | |
| "eval_accuracy": 0.6137931034482759, | |
| "eval_loss": 2.464597463607788, | |
| "eval_runtime": 368.3259, | |
| "eval_samples_per_second": 4.724, | |
| "eval_steps_per_second": 2.362, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "learning_rate": 3.2407407407407406e-06, | |
| "loss": 0.2132, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "learning_rate": 3.148148148148148e-06, | |
| "loss": 0.001, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "learning_rate": 3.0555555555555556e-06, | |
| "loss": 0.2829, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "learning_rate": 2.9629629629629633e-06, | |
| "loss": 0.7263, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "learning_rate": 2.8703703703703706e-06, | |
| "loss": 0.2271, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 0.0007, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "learning_rate": 2.685185185185185e-06, | |
| "loss": 0.0009, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "learning_rate": 2.5925925925925925e-06, | |
| "loss": 0.1367, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 47.02, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0005, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 47.02, | |
| "learning_rate": 2.4074074074074075e-06, | |
| "loss": 0.001, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 47.02, | |
| "learning_rate": 2.3148148148148148e-06, | |
| "loss": 0.0006, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 47.02, | |
| "learning_rate": 2.2222222222222225e-06, | |
| "loss": 0.0054, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 47.02, | |
| "eval_accuracy": 0.5896551724137931, | |
| "eval_loss": 2.5998167991638184, | |
| "eval_runtime": 367.3132, | |
| "eval_samples_per_second": 4.737, | |
| "eval_steps_per_second": 2.369, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 2.1296296296296298e-06, | |
| "loss": 0.2378, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 2.0370370370370375e-06, | |
| "loss": 0.0005, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "learning_rate": 1.9444444444444444e-06, | |
| "loss": 0.084, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.0009, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "learning_rate": 1.7592592592592594e-06, | |
| "loss": 0.2661, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 0.0378, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "learning_rate": 1.574074074074074e-06, | |
| "loss": 0.0015, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "learning_rate": 1.4814814814814817e-06, | |
| "loss": 0.1867, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "learning_rate": 1.388888888888889e-06, | |
| "loss": 0.0017, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "learning_rate": 1.2962962962962962e-06, | |
| "loss": 0.1657, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "learning_rate": 1.2037037037037037e-06, | |
| "loss": 0.0006, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "learning_rate": 1.1111111111111112e-06, | |
| "loss": 0.2733, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "eval_accuracy": 0.5637931034482758, | |
| "eval_loss": 2.759432792663574, | |
| "eval_runtime": 368.2879, | |
| "eval_samples_per_second": 4.725, | |
| "eval_steps_per_second": 2.362, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "learning_rate": 1.0185185185185188e-06, | |
| "loss": 0.0015, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "learning_rate": 9.259259259259259e-07, | |
| "loss": 0.001, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 49.01, | |
| "learning_rate": 8.333333333333333e-07, | |
| "loss": 0.0008, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 49.01, | |
| "learning_rate": 7.407407407407408e-07, | |
| "loss": 0.2271, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 49.01, | |
| "learning_rate": 6.481481481481481e-07, | |
| "loss": 0.2413, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 49.01, | |
| "learning_rate": 5.555555555555556e-07, | |
| "loss": 0.0006, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 49.01, | |
| "learning_rate": 4.6296296296296297e-07, | |
| "loss": 1.1137, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 49.01, | |
| "learning_rate": 3.703703703703704e-07, | |
| "loss": 0.2621, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 49.02, | |
| "learning_rate": 2.777777777777778e-07, | |
| "loss": 0.2838, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 49.02, | |
| "learning_rate": 1.851851851851852e-07, | |
| "loss": 0.5229, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 49.02, | |
| "learning_rate": 9.25925925925926e-08, | |
| "loss": 0.2068, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 49.02, | |
| "learning_rate": 0.0, | |
| "loss": 0.0005, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 49.02, | |
| "eval_accuracy": 0.55, | |
| "eval_loss": 2.8624658584594727, | |
| "eval_runtime": 368.643, | |
| "eval_samples_per_second": 4.72, | |
| "eval_steps_per_second": 2.36, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 49.02, | |
| "step": 6000, | |
| "total_flos": 1.4952775073660928e+19, | |
| "train_loss": 0.5452439992037447, | |
| "train_runtime": 27845.188, | |
| "train_samples_per_second": 0.431, | |
| "train_steps_per_second": 0.215 | |
| }, | |
| { | |
| "epoch": 49.02, | |
| "eval_accuracy": 0.5058339052848319, | |
| "eval_loss": 2.0870985984802246, | |
| "eval_runtime": 603.5268, | |
| "eval_samples_per_second": 4.828, | |
| "eval_steps_per_second": 2.414, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 49.02, | |
| "eval_accuracy": 0.5058339052848319, | |
| "eval_loss": 2.0870985984802246, | |
| "eval_runtime": 598.9066, | |
| "eval_samples_per_second": 4.866, | |
| "eval_steps_per_second": 2.433, | |
| "step": 6000 | |
| } | |
| ], | |
| "max_steps": 6000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 1.4952775073660928e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |