| { | |
| "best_metric": 0.93125, | |
| "best_model_checkpoint": "mvit_v2_rwf-2000/checkpoint-570", | |
| "epoch": 5.125, | |
| "eval_steps": 500, | |
| "global_step": 1140, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006578947368421052, | |
| "grad_norm": 36.64044189453125, | |
| "learning_rate": 1.986842105263158e-05, | |
| "loss": 6.5592, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013157894736842105, | |
| "grad_norm": 43.76960372924805, | |
| "learning_rate": 1.9736842105263158e-05, | |
| "loss": 5.0333, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.019736842105263157, | |
| "grad_norm": 29.054157257080078, | |
| "learning_rate": 1.960526315789474e-05, | |
| "loss": 3.3536, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02631578947368421, | |
| "grad_norm": 26.586713790893555, | |
| "learning_rate": 1.9473684210526318e-05, | |
| "loss": 2.0178, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03289473684210526, | |
| "grad_norm": 13.628296852111816, | |
| "learning_rate": 1.9342105263157896e-05, | |
| "loss": 1.4669, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.039473684210526314, | |
| "grad_norm": 12.267337799072266, | |
| "learning_rate": 1.9210526315789474e-05, | |
| "loss": 0.9024, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.046052631578947366, | |
| "grad_norm": 13.692243576049805, | |
| "learning_rate": 1.9078947368421056e-05, | |
| "loss": 0.676, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 15.4345064163208, | |
| "learning_rate": 1.894736842105263e-05, | |
| "loss": 0.8188, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.05921052631578947, | |
| "grad_norm": 18.368070602416992, | |
| "learning_rate": 1.8815789473684213e-05, | |
| "loss": 0.6296, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.06578947368421052, | |
| "grad_norm": 12.882184982299805, | |
| "learning_rate": 1.868421052631579e-05, | |
| "loss": 0.6014, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07236842105263158, | |
| "grad_norm": 13.11134147644043, | |
| "learning_rate": 1.8552631578947373e-05, | |
| "loss": 0.6352, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.07894736842105263, | |
| "grad_norm": 8.479208946228027, | |
| "learning_rate": 1.8421052631578947e-05, | |
| "loss": 0.6688, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.08552631578947369, | |
| "grad_norm": 9.394298553466797, | |
| "learning_rate": 1.828947368421053e-05, | |
| "loss": 0.5578, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.09210526315789473, | |
| "grad_norm": 13.005159378051758, | |
| "learning_rate": 1.8157894736842107e-05, | |
| "loss": 0.5352, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.09868421052631579, | |
| "grad_norm": 21.03794288635254, | |
| "learning_rate": 1.8026315789473685e-05, | |
| "loss": 0.3291, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 20.376361846923828, | |
| "learning_rate": 1.7894736842105264e-05, | |
| "loss": 0.3126, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.1118421052631579, | |
| "grad_norm": 9.78145694732666, | |
| "learning_rate": 1.7763157894736845e-05, | |
| "loss": 0.4688, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.11842105263157894, | |
| "grad_norm": 10.771368026733398, | |
| "learning_rate": 1.763157894736842e-05, | |
| "loss": 0.3389, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 1.7945446968078613, | |
| "learning_rate": 1.7500000000000002e-05, | |
| "loss": 0.4242, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "eval_accuracy": 0.8375, | |
| "eval_f1": 0.8365807668133248, | |
| "eval_loss": 0.42270001769065857, | |
| "eval_precision": 0.8452685421994885, | |
| "eval_runtime": 69.4902, | |
| "eval_samples_per_second": 2.302, | |
| "eval_steps_per_second": 0.288, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.006578947368421, | |
| "grad_norm": 26.072763442993164, | |
| "learning_rate": 1.736842105263158e-05, | |
| "loss": 0.2755, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.013157894736842, | |
| "grad_norm": 16.94261932373047, | |
| "learning_rate": 1.723684210526316e-05, | |
| "loss": 0.4916, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.019736842105263, | |
| "grad_norm": 11.323436737060547, | |
| "learning_rate": 1.7105263157894737e-05, | |
| "loss": 0.2864, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.0263157894736843, | |
| "grad_norm": 5.436691761016846, | |
| "learning_rate": 1.6973684210526318e-05, | |
| "loss": 0.3343, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.0328947368421053, | |
| "grad_norm": 19.71637725830078, | |
| "learning_rate": 1.6842105263157896e-05, | |
| "loss": 0.3933, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.0394736842105263, | |
| "grad_norm": 7.336604595184326, | |
| "learning_rate": 1.6710526315789475e-05, | |
| "loss": 0.3754, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.0460526315789473, | |
| "grad_norm": 23.727394104003906, | |
| "learning_rate": 1.6578947368421053e-05, | |
| "loss": 0.2446, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 21.048952102661133, | |
| "learning_rate": 1.644736842105263e-05, | |
| "loss": 0.3691, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.0592105263157894, | |
| "grad_norm": 1.7281363010406494, | |
| "learning_rate": 1.6315789473684213e-05, | |
| "loss": 0.363, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.0657894736842106, | |
| "grad_norm": 17.512372970581055, | |
| "learning_rate": 1.618421052631579e-05, | |
| "loss": 0.365, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.0723684210526316, | |
| "grad_norm": 4.898046016693115, | |
| "learning_rate": 1.605263157894737e-05, | |
| "loss": 0.1919, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.0789473684210527, | |
| "grad_norm": 23.86078643798828, | |
| "learning_rate": 1.5921052631578948e-05, | |
| "loss": 0.3222, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.0855263157894737, | |
| "grad_norm": 14.71253490447998, | |
| "learning_rate": 1.578947368421053e-05, | |
| "loss": 0.3996, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.0921052631578947, | |
| "grad_norm": 15.617661476135254, | |
| "learning_rate": 1.5657894736842107e-05, | |
| "loss": 0.2916, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.0986842105263157, | |
| "grad_norm": 16.566120147705078, | |
| "learning_rate": 1.5526315789473686e-05, | |
| "loss": 0.2138, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.1052631578947367, | |
| "grad_norm": 19.48283576965332, | |
| "learning_rate": 1.5394736842105264e-05, | |
| "loss": 0.3296, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.111842105263158, | |
| "grad_norm": 25.25094223022461, | |
| "learning_rate": 1.5263157894736846e-05, | |
| "loss": 0.5412, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.118421052631579, | |
| "grad_norm": 2.2683284282684326, | |
| "learning_rate": 1.5131578947368422e-05, | |
| "loss": 0.2906, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.125, | |
| "grad_norm": 31.231639862060547, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.3906, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.125, | |
| "eval_accuracy": 0.9, | |
| "eval_f1": 0.8999374609130708, | |
| "eval_loss": 0.2932564616203308, | |
| "eval_precision": 0.9010025062656641, | |
| "eval_runtime": 73.6902, | |
| "eval_samples_per_second": 2.171, | |
| "eval_steps_per_second": 0.271, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.0065789473684212, | |
| "grad_norm": 0.302801251411438, | |
| "learning_rate": 1.486842105263158e-05, | |
| "loss": 0.148, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.013157894736842, | |
| "grad_norm": 2.899660587310791, | |
| "learning_rate": 1.4736842105263159e-05, | |
| "loss": 0.3116, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.0197368421052633, | |
| "grad_norm": 0.4640880227088928, | |
| "learning_rate": 1.4605263157894739e-05, | |
| "loss": 0.131, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.026315789473684, | |
| "grad_norm": 28.330896377563477, | |
| "learning_rate": 1.4473684210526317e-05, | |
| "loss": 0.1221, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.0328947368421053, | |
| "grad_norm": 0.6787762641906738, | |
| "learning_rate": 1.4342105263157895e-05, | |
| "loss": 0.1547, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.039473684210526, | |
| "grad_norm": 27.384422302246094, | |
| "learning_rate": 1.4210526315789475e-05, | |
| "loss": 0.2902, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.0460526315789473, | |
| "grad_norm": 18.884803771972656, | |
| "learning_rate": 1.4078947368421055e-05, | |
| "loss": 0.2381, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.0526315789473686, | |
| "grad_norm": 2.0699939727783203, | |
| "learning_rate": 1.3947368421052631e-05, | |
| "loss": 0.1437, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.0592105263157894, | |
| "grad_norm": 0.6573389768600464, | |
| "learning_rate": 1.3815789473684211e-05, | |
| "loss": 0.54, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.0657894736842106, | |
| "grad_norm": 24.888164520263672, | |
| "learning_rate": 1.3684210526315791e-05, | |
| "loss": 0.2222, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.0723684210526314, | |
| "grad_norm": 5.3757643699646, | |
| "learning_rate": 1.3552631578947371e-05, | |
| "loss": 0.3766, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.0789473684210527, | |
| "grad_norm": 8.543233871459961, | |
| "learning_rate": 1.3421052631578948e-05, | |
| "loss": 0.2016, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.085526315789474, | |
| "grad_norm": 24.547653198242188, | |
| "learning_rate": 1.3289473684210528e-05, | |
| "loss": 0.1867, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.0921052631578947, | |
| "grad_norm": 9.149017333984375, | |
| "learning_rate": 1.3157894736842108e-05, | |
| "loss": 0.1007, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.098684210526316, | |
| "grad_norm": 0.6297352313995361, | |
| "learning_rate": 1.3026315789473684e-05, | |
| "loss": 0.0951, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 17.117029190063477, | |
| "learning_rate": 1.2894736842105264e-05, | |
| "loss": 0.405, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.111842105263158, | |
| "grad_norm": 1.1509796380996704, | |
| "learning_rate": 1.2763157894736844e-05, | |
| "loss": 0.3637, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.1184210526315788, | |
| "grad_norm": 13.600915908813477, | |
| "learning_rate": 1.263157894736842e-05, | |
| "loss": 0.2626, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.125, | |
| "grad_norm": 3.0041847229003906, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.3199, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.125, | |
| "eval_accuracy": 0.93125, | |
| "eval_f1": 0.931247314348217, | |
| "eval_loss": 0.30343881249427795, | |
| "eval_precision": 0.9313173933427098, | |
| "eval_runtime": 65.8695, | |
| "eval_samples_per_second": 2.429, | |
| "eval_steps_per_second": 0.304, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.0065789473684212, | |
| "grad_norm": 3.123574733734131, | |
| "learning_rate": 1.236842105263158e-05, | |
| "loss": 0.1695, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.013157894736842, | |
| "grad_norm": 30.406293869018555, | |
| "learning_rate": 1.2236842105263159e-05, | |
| "loss": 0.2813, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.0197368421052633, | |
| "grad_norm": 14.729782104492188, | |
| "learning_rate": 1.2105263157894737e-05, | |
| "loss": 0.2084, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.026315789473684, | |
| "grad_norm": 6.453456401824951, | |
| "learning_rate": 1.1973684210526317e-05, | |
| "loss": 0.3726, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 3.0328947368421053, | |
| "grad_norm": 0.5487316846847534, | |
| "learning_rate": 1.1842105263157895e-05, | |
| "loss": 0.3515, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.039473684210526, | |
| "grad_norm": 2.270763635635376, | |
| "learning_rate": 1.1710526315789475e-05, | |
| "loss": 0.0221, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 3.0460526315789473, | |
| "grad_norm": 13.998810768127441, | |
| "learning_rate": 1.1578947368421053e-05, | |
| "loss": 0.33, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 3.0526315789473686, | |
| "grad_norm": 8.822827339172363, | |
| "learning_rate": 1.1447368421052632e-05, | |
| "loss": 0.161, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.0592105263157894, | |
| "grad_norm": 29.708253860473633, | |
| "learning_rate": 1.1315789473684212e-05, | |
| "loss": 0.2569, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.0657894736842106, | |
| "grad_norm": 23.062585830688477, | |
| "learning_rate": 1.1184210526315792e-05, | |
| "loss": 0.2207, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.0723684210526314, | |
| "grad_norm": 10.31871509552002, | |
| "learning_rate": 1.105263157894737e-05, | |
| "loss": 0.3339, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 3.0789473684210527, | |
| "grad_norm": 2.75856351852417, | |
| "learning_rate": 1.0921052631578948e-05, | |
| "loss": 0.0798, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 3.085526315789474, | |
| "grad_norm": 1.439271330833435, | |
| "learning_rate": 1.0789473684210528e-05, | |
| "loss": 0.107, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.0921052631578947, | |
| "grad_norm": 0.4239494502544403, | |
| "learning_rate": 1.0657894736842108e-05, | |
| "loss": 0.1158, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 3.098684210526316, | |
| "grad_norm": 16.95366859436035, | |
| "learning_rate": 1.0526315789473684e-05, | |
| "loss": 0.2155, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 3.1052631578947367, | |
| "grad_norm": 20.484813690185547, | |
| "learning_rate": 1.0394736842105264e-05, | |
| "loss": 0.2505, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 3.111842105263158, | |
| "grad_norm": 31.08599853515625, | |
| "learning_rate": 1.0263157894736844e-05, | |
| "loss": 0.4975, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 3.1184210526315788, | |
| "grad_norm": 22.264848709106445, | |
| "learning_rate": 1.0131578947368421e-05, | |
| "loss": 0.2602, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.125, | |
| "grad_norm": 20.796369552612305, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2239, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 3.125, | |
| "eval_accuracy": 0.9125, | |
| "eval_f1": 0.912445278298937, | |
| "eval_loss": 0.3610968291759491, | |
| "eval_precision": 0.9135338345864662, | |
| "eval_runtime": 68.362, | |
| "eval_samples_per_second": 2.34, | |
| "eval_steps_per_second": 0.293, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 4.006578947368421, | |
| "grad_norm": 0.06610066443681717, | |
| "learning_rate": 9.868421052631579e-06, | |
| "loss": 0.2882, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 4.0131578947368425, | |
| "grad_norm": 3.3229968547821045, | |
| "learning_rate": 9.736842105263159e-06, | |
| "loss": 0.148, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 4.019736842105263, | |
| "grad_norm": 18.369155883789062, | |
| "learning_rate": 9.605263157894737e-06, | |
| "loss": 0.2034, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 4.026315789473684, | |
| "grad_norm": 0.4686603844165802, | |
| "learning_rate": 9.473684210526315e-06, | |
| "loss": 0.1949, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.032894736842105, | |
| "grad_norm": 0.3468804359436035, | |
| "learning_rate": 9.342105263157895e-06, | |
| "loss": 0.1468, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 4.0394736842105265, | |
| "grad_norm": 5.2816243171691895, | |
| "learning_rate": 9.210526315789474e-06, | |
| "loss": 0.1253, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 4.046052631578948, | |
| "grad_norm": 3.5091466903686523, | |
| "learning_rate": 9.078947368421054e-06, | |
| "loss": 0.0314, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 4.052631578947368, | |
| "grad_norm": 38.08211135864258, | |
| "learning_rate": 8.947368421052632e-06, | |
| "loss": 0.3176, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 4.059210526315789, | |
| "grad_norm": 0.1611049771308899, | |
| "learning_rate": 8.81578947368421e-06, | |
| "loss": 0.1931, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 4.065789473684211, | |
| "grad_norm": 0.5490935444831848, | |
| "learning_rate": 8.68421052631579e-06, | |
| "loss": 0.4194, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 4.072368421052632, | |
| "grad_norm": 4.411422252655029, | |
| "learning_rate": 8.552631578947368e-06, | |
| "loss": 0.1544, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 4.078947368421052, | |
| "grad_norm": 0.4949572682380676, | |
| "learning_rate": 8.421052631578948e-06, | |
| "loss": 0.3998, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 4.0855263157894735, | |
| "grad_norm": 30.750051498413086, | |
| "learning_rate": 8.289473684210526e-06, | |
| "loss": 0.1656, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 4.092105263157895, | |
| "grad_norm": 16.065580368041992, | |
| "learning_rate": 8.157894736842106e-06, | |
| "loss": 0.0652, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.098684210526316, | |
| "grad_norm": 21.529672622680664, | |
| "learning_rate": 8.026315789473685e-06, | |
| "loss": 0.1112, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 4.105263157894737, | |
| "grad_norm": 1.2219691276550293, | |
| "learning_rate": 7.894736842105265e-06, | |
| "loss": 0.2536, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 4.1118421052631575, | |
| "grad_norm": 1.4607069492340088, | |
| "learning_rate": 7.763157894736843e-06, | |
| "loss": 0.0822, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 4.118421052631579, | |
| "grad_norm": 35.09339904785156, | |
| "learning_rate": 7.631578947368423e-06, | |
| "loss": 0.3982, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 4.125, | |
| "grad_norm": 4.976933479309082, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.1747, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 4.125, | |
| "eval_accuracy": 0.93125, | |
| "eval_f1": 0.931247314348217, | |
| "eval_loss": 0.34753698110580444, | |
| "eval_precision": 0.9313173933427098, | |
| "eval_runtime": 73.1814, | |
| "eval_samples_per_second": 2.186, | |
| "eval_steps_per_second": 0.273, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 5.006578947368421, | |
| "grad_norm": 0.45159298181533813, | |
| "learning_rate": 7.368421052631579e-06, | |
| "loss": 0.1255, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 5.0131578947368425, | |
| "grad_norm": 29.889768600463867, | |
| "learning_rate": 7.236842105263158e-06, | |
| "loss": 0.1549, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 5.019736842105263, | |
| "grad_norm": 6.2291412353515625, | |
| "learning_rate": 7.1052631578947375e-06, | |
| "loss": 0.1345, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 5.026315789473684, | |
| "grad_norm": 17.853551864624023, | |
| "learning_rate": 6.973684210526316e-06, | |
| "loss": 0.0786, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 5.032894736842105, | |
| "grad_norm": 0.2519562244415283, | |
| "learning_rate": 6.842105263157896e-06, | |
| "loss": 0.1226, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.0394736842105265, | |
| "grad_norm": 17.962093353271484, | |
| "learning_rate": 6.710526315789474e-06, | |
| "loss": 0.2208, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 5.046052631578948, | |
| "grad_norm": 0.25263816118240356, | |
| "learning_rate": 6.578947368421054e-06, | |
| "loss": 0.0662, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 5.052631578947368, | |
| "grad_norm": 0.3767828345298767, | |
| "learning_rate": 6.447368421052632e-06, | |
| "loss": 0.1212, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 5.059210526315789, | |
| "grad_norm": 31.959402084350586, | |
| "learning_rate": 6.31578947368421e-06, | |
| "loss": 0.4038, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 5.065789473684211, | |
| "grad_norm": 28.180463790893555, | |
| "learning_rate": 6.18421052631579e-06, | |
| "loss": 0.1677, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 5.072368421052632, | |
| "grad_norm": 0.06592092663049698, | |
| "learning_rate": 6.0526315789473685e-06, | |
| "loss": 0.1123, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 5.078947368421052, | |
| "grad_norm": 19.177854537963867, | |
| "learning_rate": 5.921052631578948e-06, | |
| "loss": 0.4745, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 5.0855263157894735, | |
| "grad_norm": 39.3027458190918, | |
| "learning_rate": 5.789473684210527e-06, | |
| "loss": 0.2614, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 5.092105263157895, | |
| "grad_norm": 12.32589054107666, | |
| "learning_rate": 5.657894736842106e-06, | |
| "loss": 0.0943, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 5.098684210526316, | |
| "grad_norm": 17.65743064880371, | |
| "learning_rate": 5.526315789473685e-06, | |
| "loss": 0.1302, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 5.105263157894737, | |
| "grad_norm": 0.037535008043050766, | |
| "learning_rate": 5.394736842105264e-06, | |
| "loss": 0.1401, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 5.1118421052631575, | |
| "grad_norm": 1.1971192359924316, | |
| "learning_rate": 5.263157894736842e-06, | |
| "loss": 0.1045, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 5.118421052631579, | |
| "grad_norm": 0.809428334236145, | |
| "learning_rate": 5.131578947368422e-06, | |
| "loss": 0.2402, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 5.125, | |
| "grad_norm": 0.5052193999290466, | |
| "learning_rate": 5e-06, | |
| "loss": 0.1702, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 5.125, | |
| "eval_accuracy": 0.93125, | |
| "eval_f1": 0.931247314348217, | |
| "eval_loss": 0.36672312021255493, | |
| "eval_precision": 0.9313173933427098, | |
| "eval_runtime": 73.77, | |
| "eval_samples_per_second": 2.169, | |
| "eval_steps_per_second": 0.271, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 5.125, | |
| "step": 1140, | |
| "total_flos": 0.0, | |
| "train_loss": 0.43041260364024264, | |
| "train_runtime": 5887.2517, | |
| "train_samples_per_second": 2.065, | |
| "train_steps_per_second": 0.258 | |
| }, | |
| { | |
| "epoch": 5.125, | |
| "eval_accuracy": 0.8876404494382022, | |
| "eval_f1": 0.887419371456348, | |
| "eval_loss": 0.37810325622558594, | |
| "eval_precision": 0.8908100139372724, | |
| "eval_runtime": 376.8406, | |
| "eval_samples_per_second": 2.126, | |
| "eval_steps_per_second": 0.268, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 5.125, | |
| "eval_accuracy": 0.8875, | |
| "eval_f1": 0.8872717252436183, | |
| "eval_loss": 0.37857261300086975, | |
| "eval_precision": 0.8906643814900695, | |
| "eval_runtime": 371.215, | |
| "eval_samples_per_second": 2.155, | |
| "eval_steps_per_second": 0.269, | |
| "step": 1140 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1520, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |