{ "best_metric": 0.8351063829787234, "best_model_checkpoint": "videomae-base-finetuned-kinetics-finetuned-movienet/checkpoint-744", "epoch": 4.100540540540541, "global_step": 930, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 1.3513513513513515e-06, "loss": 1.6108, "step": 10 }, { "epoch": 0.01, "learning_rate": 2.702702702702703e-06, "loss": 1.6587, "step": 20 }, { "epoch": 0.02, "learning_rate": 4.0540540540540545e-06, "loss": 1.6075, "step": 30 }, { "epoch": 0.02, "learning_rate": 5.405405405405406e-06, "loss": 1.603, "step": 40 }, { "epoch": 0.03, "learning_rate": 6.7567567567567575e-06, "loss": 1.5604, "step": 50 }, { "epoch": 0.03, "learning_rate": 8.108108108108109e-06, "loss": 1.494, "step": 60 }, { "epoch": 0.04, "learning_rate": 9.45945945945946e-06, "loss": 1.4524, "step": 70 }, { "epoch": 0.04, "learning_rate": 1.0810810810810812e-05, "loss": 1.4549, "step": 80 }, { "epoch": 0.05, "learning_rate": 1.2162162162162164e-05, "loss": 1.3249, "step": 90 }, { "epoch": 0.05, "learning_rate": 1.3513513513513515e-05, "loss": 1.2482, "step": 100 }, { "epoch": 0.06, "learning_rate": 1.4864864864864867e-05, "loss": 1.187, "step": 110 }, { "epoch": 0.06, "learning_rate": 1.6216216216216218e-05, "loss": 1.0783, "step": 120 }, { "epoch": 0.07, "learning_rate": 1.756756756756757e-05, "loss": 0.9135, "step": 130 }, { "epoch": 0.08, "learning_rate": 1.891891891891892e-05, "loss": 0.76, "step": 140 }, { "epoch": 0.08, "learning_rate": 2.0270270270270273e-05, "loss": 0.7138, "step": 150 }, { "epoch": 0.09, "learning_rate": 2.1621621621621624e-05, "loss": 0.5681, "step": 160 }, { "epoch": 0.09, "learning_rate": 2.2972972972972976e-05, "loss": 0.6388, "step": 170 }, { "epoch": 0.1, "learning_rate": 2.4324324324324327e-05, "loss": 0.7666, "step": 180 }, { "epoch": 0.1, "eval_accuracy": 0.7021276595744681, "eval_loss": 0.683621346950531, "eval_runtime": 338.0924, "eval_samples_per_second": 0.556, "eval_steps_per_second": 0.071, "step": 186 }, { "epoch": 1.0, "learning_rate": 2.5675675675675675e-05, "loss": 0.5934, "step": 190 }, { "epoch": 1.01, "learning_rate": 2.702702702702703e-05, "loss": 0.5488, "step": 200 }, { "epoch": 1.01, "learning_rate": 2.8378378378378378e-05, "loss": 0.3927, "step": 210 }, { "epoch": 1.02, "learning_rate": 2.9729729729729733e-05, "loss": 0.4944, "step": 220 }, { "epoch": 1.02, "learning_rate": 3.108108108108108e-05, "loss": 0.5078, "step": 230 }, { "epoch": 1.03, "learning_rate": 3.2432432432432436e-05, "loss": 0.5674, "step": 240 }, { "epoch": 1.03, "learning_rate": 3.3783783783783784e-05, "loss": 0.4871, "step": 250 }, { "epoch": 1.04, "learning_rate": 3.513513513513514e-05, "loss": 0.6036, "step": 260 }, { "epoch": 1.05, "learning_rate": 3.648648648648649e-05, "loss": 0.447, "step": 270 }, { "epoch": 1.05, "learning_rate": 3.783783783783784e-05, "loss": 0.4363, "step": 280 }, { "epoch": 1.06, "learning_rate": 3.918918918918919e-05, "loss": 0.472, "step": 290 }, { "epoch": 1.06, "learning_rate": 4.0540540540540545e-05, "loss": 0.3898, "step": 300 }, { "epoch": 1.07, "learning_rate": 4.189189189189189e-05, "loss": 0.3694, "step": 310 }, { "epoch": 1.07, "learning_rate": 4.324324324324325e-05, "loss": 0.5361, "step": 320 }, { "epoch": 1.08, "learning_rate": 4.4594594594594596e-05, "loss": 0.4282, "step": 330 }, { "epoch": 1.08, "learning_rate": 4.594594594594595e-05, "loss": 0.4951, "step": 340 }, { "epoch": 1.09, "learning_rate": 4.72972972972973e-05, "loss": 0.4869, "step": 350 }, { "epoch": 1.09, "learning_rate": 4.8648648648648654e-05, "loss": 0.5659, "step": 360 }, { "epoch": 1.1, "learning_rate": 5e-05, "loss": 0.5221, "step": 370 }, { "epoch": 1.1, "eval_accuracy": 0.8191489361702128, "eval_loss": 0.45883435010910034, "eval_runtime": 177.7151, "eval_samples_per_second": 1.058, "eval_steps_per_second": 0.135, "step": 372 }, { "epoch": 2.0, "learning_rate": 4.9662162162162164e-05, "loss": 0.4096, "step": 380 }, { "epoch": 2.01, "learning_rate": 4.9324324324324325e-05, "loss": 0.2432, "step": 390 }, { "epoch": 2.02, "learning_rate": 4.8986486486486486e-05, "loss": 0.3223, "step": 400 }, { "epoch": 2.02, "learning_rate": 4.8648648648648654e-05, "loss": 0.2595, "step": 410 }, { "epoch": 2.03, "learning_rate": 4.8310810810810816e-05, "loss": 0.2677, "step": 420 }, { "epoch": 2.03, "learning_rate": 4.797297297297298e-05, "loss": 0.1923, "step": 430 }, { "epoch": 2.04, "learning_rate": 4.763513513513514e-05, "loss": 0.2242, "step": 440 }, { "epoch": 2.04, "learning_rate": 4.72972972972973e-05, "loss": 0.2813, "step": 450 }, { "epoch": 2.05, "learning_rate": 4.695945945945946e-05, "loss": 0.1839, "step": 460 }, { "epoch": 2.05, "learning_rate": 4.662162162162162e-05, "loss": 0.1759, "step": 470 }, { "epoch": 2.06, "learning_rate": 4.628378378378378e-05, "loss": 0.3216, "step": 480 }, { "epoch": 2.06, "learning_rate": 4.594594594594595e-05, "loss": 0.4189, "step": 490 }, { "epoch": 2.07, "learning_rate": 4.560810810810811e-05, "loss": 0.3461, "step": 500 }, { "epoch": 2.07, "learning_rate": 4.5270270270270274e-05, "loss": 0.3762, "step": 510 }, { "epoch": 2.08, "learning_rate": 4.4932432432432435e-05, "loss": 0.274, "step": 520 }, { "epoch": 2.09, "learning_rate": 4.4594594594594596e-05, "loss": 0.2273, "step": 530 }, { "epoch": 2.09, "learning_rate": 4.425675675675676e-05, "loss": 0.3088, "step": 540 }, { "epoch": 2.1, "learning_rate": 4.391891891891892e-05, "loss": 0.2842, "step": 550 }, { "epoch": 2.1, "eval_accuracy": 0.7872340425531915, "eval_loss": 0.7170040011405945, "eval_runtime": 129.3008, "eval_samples_per_second": 1.454, "eval_steps_per_second": 0.186, "step": 558 }, { "epoch": 3.0, "learning_rate": 4.358108108108108e-05, "loss": 0.4734, "step": 560 }, { "epoch": 3.01, "learning_rate": 4.324324324324325e-05, "loss": 0.1211, "step": 570 }, { "epoch": 3.01, "learning_rate": 4.290540540540541e-05, "loss": 0.2635, "step": 580 }, { "epoch": 3.02, "learning_rate": 4.256756756756757e-05, "loss": 0.1709, "step": 590 }, { "epoch": 3.02, "learning_rate": 4.222972972972973e-05, "loss": 0.1331, "step": 600 }, { "epoch": 3.03, "learning_rate": 4.189189189189189e-05, "loss": 0.2039, "step": 610 }, { "epoch": 3.03, "learning_rate": 4.1554054054054055e-05, "loss": 0.1331, "step": 620 }, { "epoch": 3.04, "learning_rate": 4.1216216216216216e-05, "loss": 0.0862, "step": 630 }, { "epoch": 3.04, "learning_rate": 4.087837837837838e-05, "loss": 0.0994, "step": 640 }, { "epoch": 3.05, "learning_rate": 4.0540540540540545e-05, "loss": 0.0995, "step": 650 }, { "epoch": 3.06, "learning_rate": 4.0202702702702707e-05, "loss": 0.1932, "step": 660 }, { "epoch": 3.06, "learning_rate": 3.986486486486487e-05, "loss": 0.1393, "step": 670 }, { "epoch": 3.07, "learning_rate": 3.952702702702703e-05, "loss": 0.2566, "step": 680 }, { "epoch": 3.07, "learning_rate": 3.918918918918919e-05, "loss": 0.1237, "step": 690 }, { "epoch": 3.08, "learning_rate": 3.885135135135135e-05, "loss": 0.3312, "step": 700 }, { "epoch": 3.08, "learning_rate": 3.851351351351351e-05, "loss": 0.1597, "step": 710 }, { "epoch": 3.09, "learning_rate": 3.8175675675675674e-05, "loss": 0.2005, "step": 720 }, { "epoch": 3.09, "learning_rate": 3.783783783783784e-05, "loss": 0.1036, "step": 730 }, { "epoch": 3.1, "learning_rate": 3.7500000000000003e-05, "loss": 0.2556, "step": 740 }, { "epoch": 3.1, "eval_accuracy": 0.8351063829787234, "eval_loss": 0.5215957164764404, "eval_runtime": 162.9032, "eval_samples_per_second": 1.154, "eval_steps_per_second": 0.147, "step": 744 }, { "epoch": 4.0, "learning_rate": 3.7162162162162165e-05, "loss": 0.0293, "step": 750 }, { "epoch": 4.01, "learning_rate": 3.6824324324324326e-05, "loss": 0.0963, "step": 760 }, { "epoch": 4.01, "learning_rate": 3.648648648648649e-05, "loss": 0.0378, "step": 770 }, { "epoch": 4.02, "learning_rate": 3.6148648648648655e-05, "loss": 0.0574, "step": 780 }, { "epoch": 4.02, "learning_rate": 3.581081081081081e-05, "loss": 0.0259, "step": 790 }, { "epoch": 4.03, "learning_rate": 3.547297297297297e-05, "loss": 0.1403, "step": 800 }, { "epoch": 4.04, "learning_rate": 3.513513513513514e-05, "loss": 0.0184, "step": 810 }, { "epoch": 4.04, "learning_rate": 3.47972972972973e-05, "loss": 0.18, "step": 820 }, { "epoch": 4.05, "learning_rate": 3.445945945945946e-05, "loss": 0.0206, "step": 830 }, { "epoch": 4.05, "learning_rate": 3.412162162162162e-05, "loss": 0.0274, "step": 840 }, { "epoch": 4.06, "learning_rate": 3.3783783783783784e-05, "loss": 0.0834, "step": 850 }, { "epoch": 4.06, "learning_rate": 3.344594594594595e-05, "loss": 0.1082, "step": 860 }, { "epoch": 4.07, "learning_rate": 3.310810810810811e-05, "loss": 0.0765, "step": 870 }, { "epoch": 4.07, "learning_rate": 3.277027027027027e-05, "loss": 0.0635, "step": 880 }, { "epoch": 4.08, "learning_rate": 3.2432432432432436e-05, "loss": 0.0918, "step": 890 }, { "epoch": 4.08, "learning_rate": 3.20945945945946e-05, "loss": 0.1317, "step": 900 }, { "epoch": 4.09, "learning_rate": 3.175675675675676e-05, "loss": 0.0651, "step": 910 }, { "epoch": 4.1, "learning_rate": 3.141891891891892e-05, "loss": 0.0477, "step": 920 }, { "epoch": 4.1, "learning_rate": 3.108108108108108e-05, "loss": 0.0356, "step": 930 }, { "epoch": 4.1, "eval_accuracy": 0.7864583333333334, "eval_loss": 0.8737158179283142, "eval_runtime": 287.7784, "eval_samples_per_second": 0.667, "eval_steps_per_second": 0.083, "step": 930 }, { "epoch": 4.1, "eval_accuracy": 0.7864583333333334, "eval_loss": 0.8737158179283142, "eval_runtime": 124.9385, "eval_samples_per_second": 1.537, "eval_steps_per_second": 0.192, "step": 930 } ], "max_steps": 1850, "num_train_epochs": 9223372036854775807, "total_flos": 9.227355150982349e+18, "trial_name": null, "trial_params": null }