{ "best_metric": 0.8351063829787234, "best_model_checkpoint": "videomae-base-finetuned-kinetics-finetuned-movienet-2-2/checkpoint-372", "epoch": 6.00054054054054, "global_step": 1117, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 5.405405405405406e-07, "loss": 0.0001, "step": 10 }, { "epoch": 0.01, "learning_rate": 1.0810810810810812e-06, "loss": 0.0009, "step": 20 }, { "epoch": 0.02, "learning_rate": 1.6216216216216219e-06, "loss": 0.0003, "step": 30 }, { "epoch": 0.02, "learning_rate": 2.1621621621621623e-06, "loss": 0.0002, "step": 40 }, { "epoch": 0.03, "learning_rate": 2.702702702702703e-06, "loss": 0.0001, "step": 50 }, { "epoch": 0.03, "learning_rate": 3.2432432432432437e-06, "loss": 0.0001, "step": 60 }, { "epoch": 0.04, "learning_rate": 3.783783783783784e-06, "loss": 0.0033, "step": 70 }, { "epoch": 0.04, "learning_rate": 4.324324324324325e-06, "loss": 0.0003, "step": 80 }, { "epoch": 0.05, "learning_rate": 4.864864864864866e-06, "loss": 0.0001, "step": 90 }, { "epoch": 0.05, "learning_rate": 5.405405405405406e-06, "loss": 0.0001, "step": 100 }, { "epoch": 0.06, "learning_rate": 5.945945945945946e-06, "loss": 0.0001, "step": 110 }, { "epoch": 0.06, "learning_rate": 6.486486486486487e-06, "loss": 0.0001, "step": 120 }, { "epoch": 0.07, "learning_rate": 7.027027027027028e-06, "loss": 0.0, "step": 130 }, { "epoch": 0.08, "learning_rate": 7.567567567567568e-06, "loss": 0.0001, "step": 140 }, { "epoch": 0.08, "learning_rate": 8.108108108108109e-06, "loss": 0.0001, "step": 150 }, { "epoch": 0.09, "learning_rate": 8.64864864864865e-06, "loss": 0.0, "step": 160 }, { "epoch": 0.09, "learning_rate": 9.18918918918919e-06, "loss": 0.0007, "step": 170 }, { "epoch": 0.1, "learning_rate": 9.729729729729732e-06, "loss": 0.0006, "step": 180 }, { "epoch": 0.1, "eval_accuracy": 0.7978723404255319, "eval_loss": 1.0443280935287476, "eval_runtime": 333.5702, "eval_samples_per_second": 0.564, "eval_steps_per_second": 0.072, "step": 186 }, { "epoch": 1.0, "learning_rate": 1.0270270270270272e-05, "loss": 0.0001, "step": 190 }, { "epoch": 1.01, "learning_rate": 1.0810810810810812e-05, "loss": 0.0003, "step": 200 }, { "epoch": 1.01, "learning_rate": 1.1351351351351352e-05, "loss": 0.0, "step": 210 }, { "epoch": 1.02, "learning_rate": 1.1891891891891893e-05, "loss": 0.0001, "step": 220 }, { "epoch": 1.02, "learning_rate": 1.2432432432432435e-05, "loss": 0.0001, "step": 230 }, { "epoch": 1.03, "learning_rate": 1.2972972972972975e-05, "loss": 0.0001, "step": 240 }, { "epoch": 1.03, "learning_rate": 1.3513513513513515e-05, "loss": 0.0, "step": 250 }, { "epoch": 1.04, "learning_rate": 1.4054054054054055e-05, "loss": 0.0, "step": 260 }, { "epoch": 1.05, "learning_rate": 1.4594594594594596e-05, "loss": 0.0, "step": 270 }, { "epoch": 1.05, "learning_rate": 1.5135135135135136e-05, "loss": 0.0001, "step": 280 }, { "epoch": 1.06, "learning_rate": 1.5675675675675676e-05, "loss": 0.0, "step": 290 }, { "epoch": 1.06, "learning_rate": 1.6216216216216218e-05, "loss": 0.0, "step": 300 }, { "epoch": 1.07, "learning_rate": 1.675675675675676e-05, "loss": 0.0, "step": 310 }, { "epoch": 1.07, "learning_rate": 1.72972972972973e-05, "loss": 0.0, "step": 320 }, { "epoch": 1.08, "learning_rate": 1.783783783783784e-05, "loss": 0.0, "step": 330 }, { "epoch": 1.08, "learning_rate": 1.837837837837838e-05, "loss": 0.0, "step": 340 }, { "epoch": 1.09, "learning_rate": 1.891891891891892e-05, "loss": 0.0, "step": 350 }, { "epoch": 1.09, "learning_rate": 1.9459459459459463e-05, "loss": 0.0001, "step": 360 }, { "epoch": 1.1, "learning_rate": 2e-05, "loss": 0.0, "step": 370 }, { "epoch": 1.1, "eval_accuracy": 0.8351063829787234, "eval_loss": 1.0924887657165527, "eval_runtime": 177.4121, "eval_samples_per_second": 1.06, "eval_steps_per_second": 0.135, "step": 372 }, { "epoch": 2.0, "learning_rate": 2.0540540540540544e-05, "loss": 0.0001, "step": 380 }, { "epoch": 2.01, "learning_rate": 2.1081081081081082e-05, "loss": 0.0, "step": 390 }, { "epoch": 2.02, "learning_rate": 2.1621621621621624e-05, "loss": 0.0, "step": 400 }, { "epoch": 2.02, "learning_rate": 2.2162162162162166e-05, "loss": 0.0, "step": 410 }, { "epoch": 2.03, "learning_rate": 2.2702702702702705e-05, "loss": 0.0, "step": 420 }, { "epoch": 2.03, "learning_rate": 2.3243243243243247e-05, "loss": 0.0, "step": 430 }, { "epoch": 2.04, "learning_rate": 2.3783783783783785e-05, "loss": 0.0, "step": 440 }, { "epoch": 2.04, "learning_rate": 2.4324324324324327e-05, "loss": 0.0, "step": 450 }, { "epoch": 2.05, "learning_rate": 2.486486486486487e-05, "loss": 0.0, "step": 460 }, { "epoch": 2.05, "learning_rate": 2.5405405405405408e-05, "loss": 0.0, "step": 470 }, { "epoch": 2.06, "learning_rate": 2.594594594594595e-05, "loss": 0.0, "step": 480 }, { "epoch": 2.06, "learning_rate": 2.6486486486486488e-05, "loss": 0.0, "step": 490 }, { "epoch": 2.07, "learning_rate": 2.702702702702703e-05, "loss": 0.0, "step": 500 }, { "epoch": 2.07, "learning_rate": 2.7567567567567572e-05, "loss": 0.0, "step": 510 }, { "epoch": 2.08, "learning_rate": 2.810810810810811e-05, "loss": 0.0, "step": 520 }, { "epoch": 2.09, "learning_rate": 2.8648648648648653e-05, "loss": 0.0, "step": 530 }, { "epoch": 2.09, "learning_rate": 2.918918918918919e-05, "loss": 0.0332, "step": 540 }, { "epoch": 2.1, "learning_rate": 2.9729729729729733e-05, "loss": 0.0005, "step": 550 }, { "epoch": 2.1, "eval_accuracy": 0.7925531914893617, "eval_loss": 1.8252729177474976, "eval_runtime": 119.7198, "eval_samples_per_second": 1.57, "eval_steps_per_second": 0.2, "step": 558 }, { "epoch": 3.0, "learning_rate": 3.0270270270270272e-05, "loss": 0.2088, "step": 560 }, { "epoch": 3.01, "learning_rate": 3.081081081081082e-05, "loss": 0.3743, "step": 570 }, { "epoch": 3.01, "learning_rate": 3.135135135135135e-05, "loss": 0.5181, "step": 580 }, { "epoch": 3.02, "learning_rate": 3.1891891891891894e-05, "loss": 0.694, "step": 590 }, { "epoch": 3.02, "learning_rate": 3.2432432432432436e-05, "loss": 0.0207, "step": 600 }, { "epoch": 3.03, "learning_rate": 3.297297297297298e-05, "loss": 0.0749, "step": 610 }, { "epoch": 3.03, "learning_rate": 3.351351351351352e-05, "loss": 0.0858, "step": 620 }, { "epoch": 3.04, "learning_rate": 3.4054054054054055e-05, "loss": 0.2189, "step": 630 }, { "epoch": 3.04, "learning_rate": 3.45945945945946e-05, "loss": 0.0966, "step": 640 }, { "epoch": 3.05, "learning_rate": 3.513513513513514e-05, "loss": 0.0286, "step": 650 }, { "epoch": 3.06, "learning_rate": 3.567567567567568e-05, "loss": 0.1632, "step": 660 }, { "epoch": 3.06, "learning_rate": 3.621621621621622e-05, "loss": 0.1709, "step": 670 }, { "epoch": 3.07, "learning_rate": 3.675675675675676e-05, "loss": 0.1024, "step": 680 }, { "epoch": 3.07, "learning_rate": 3.72972972972973e-05, "loss": 0.0277, "step": 690 }, { "epoch": 3.08, "learning_rate": 3.783783783783784e-05, "loss": 0.1365, "step": 700 }, { "epoch": 3.08, "learning_rate": 3.8378378378378384e-05, "loss": 0.0059, "step": 710 }, { "epoch": 3.09, "learning_rate": 3.8918918918918926e-05, "loss": 0.1678, "step": 720 }, { "epoch": 3.09, "learning_rate": 3.945945945945946e-05, "loss": 0.0807, "step": 730 }, { "epoch": 3.1, "learning_rate": 4e-05, "loss": 0.1005, "step": 740 }, { "epoch": 3.1, "eval_accuracy": 0.776595744680851, "eval_loss": 1.4864708185195923, "eval_runtime": 144.0436, "eval_samples_per_second": 1.305, "eval_steps_per_second": 0.167, "step": 744 }, { "epoch": 4.0, "learning_rate": 4.0540540540540545e-05, "loss": 0.0011, "step": 750 }, { "epoch": 4.01, "learning_rate": 4.108108108108109e-05, "loss": 0.0026, "step": 760 }, { "epoch": 4.01, "learning_rate": 4.162162162162163e-05, "loss": 0.0969, "step": 770 }, { "epoch": 4.02, "learning_rate": 4.2162162162162164e-05, "loss": 0.0021, "step": 780 }, { "epoch": 4.02, "learning_rate": 4.2702702702702706e-05, "loss": 0.1575, "step": 790 }, { "epoch": 4.03, "learning_rate": 4.324324324324325e-05, "loss": 0.1013, "step": 800 }, { "epoch": 4.04, "learning_rate": 4.378378378378379e-05, "loss": 0.107, "step": 810 }, { "epoch": 4.04, "learning_rate": 4.432432432432433e-05, "loss": 0.1215, "step": 820 }, { "epoch": 4.05, "learning_rate": 4.486486486486487e-05, "loss": 0.1436, "step": 830 }, { "epoch": 4.05, "learning_rate": 4.540540540540541e-05, "loss": 0.1396, "step": 840 }, { "epoch": 4.06, "learning_rate": 4.594594594594595e-05, "loss": 0.1465, "step": 850 }, { "epoch": 4.06, "learning_rate": 4.648648648648649e-05, "loss": 0.1406, "step": 860 }, { "epoch": 4.07, "learning_rate": 4.7027027027027035e-05, "loss": 0.0622, "step": 870 }, { "epoch": 4.07, "learning_rate": 4.756756756756757e-05, "loss": 0.1626, "step": 880 }, { "epoch": 4.08, "learning_rate": 4.810810810810811e-05, "loss": 0.0762, "step": 890 }, { "epoch": 4.08, "learning_rate": 4.8648648648648654e-05, "loss": 0.3711, "step": 900 }, { "epoch": 4.09, "learning_rate": 4.9189189189189196e-05, "loss": 0.0856, "step": 910 }, { "epoch": 4.1, "learning_rate": 4.972972972972974e-05, "loss": 0.1893, "step": 920 }, { "epoch": 4.1, "learning_rate": 4.972972972972974e-05, "loss": 0.0775, "step": 930 }, { "epoch": 4.1, "eval_accuracy": 0.7819148936170213, "eval_loss": 1.3223650455474854, "eval_runtime": 128.5188, "eval_samples_per_second": 1.463, "eval_steps_per_second": 0.187, "step": 930 }, { "epoch": 5.01, "learning_rate": 4.9189189189189196e-05, "loss": 0.0432, "step": 940 }, { "epoch": 5.01, "learning_rate": 4.8648648648648654e-05, "loss": 0.0816, "step": 950 }, { "epoch": 5.02, "learning_rate": 4.810810810810811e-05, "loss": 0.1708, "step": 960 }, { "epoch": 5.02, "learning_rate": 4.756756756756757e-05, "loss": 0.239, "step": 970 }, { "epoch": 5.03, "learning_rate": 4.7027027027027035e-05, "loss": 0.3324, "step": 980 }, { "epoch": 5.03, "learning_rate": 4.648648648648649e-05, "loss": 0.0658, "step": 990 }, { "epoch": 5.04, "learning_rate": 4.594594594594595e-05, "loss": 0.1028, "step": 1000 }, { "epoch": 5.04, "learning_rate": 4.540540540540541e-05, "loss": 0.0007, "step": 1010 }, { "epoch": 5.05, "learning_rate": 4.486486486486487e-05, "loss": 0.0467, "step": 1020 }, { "epoch": 5.05, "learning_rate": 4.432432432432433e-05, "loss": 0.1297, "step": 1030 }, { "epoch": 5.06, "learning_rate": 4.378378378378379e-05, "loss": 0.1153, "step": 1040 }, { "epoch": 5.06, "learning_rate": 4.324324324324325e-05, "loss": 0.0932, "step": 1050 }, { "epoch": 5.07, "learning_rate": 4.2702702702702706e-05, "loss": 0.0055, "step": 1060 }, { "epoch": 5.08, "learning_rate": 4.2162162162162164e-05, "loss": 0.0069, "step": 1070 }, { "epoch": 5.08, "learning_rate": 4.162162162162163e-05, "loss": 0.2046, "step": 1080 }, { "epoch": 5.09, "learning_rate": 4.108108108108109e-05, "loss": 0.0671, "step": 1090 }, { "epoch": 5.09, "learning_rate": 4.0540540540540545e-05, "loss": 0.0448, "step": 1100 }, { "epoch": 5.1, "learning_rate": 4e-05, "loss": 0.224, "step": 1110 }, { "epoch": 5.1, "eval_accuracy": 0.75, "eval_loss": 1.1644213199615479, "eval_runtime": 165.0141, "eval_samples_per_second": 1.139, "eval_steps_per_second": 0.145, "step": 1116 }, { "epoch": 6.0, "eval_accuracy": 0.7552083333333334, "eval_loss": 1.4970475435256958, "eval_runtime": 328.5593, "eval_samples_per_second": 0.584, "eval_steps_per_second": 0.073, "step": 1117 }, { "epoch": 6.0, "eval_accuracy": 0.7552083333333334, "eval_loss": 1.4970475435256958, "eval_runtime": 166.7089, "eval_samples_per_second": 1.152, "eval_steps_per_second": 0.144, "step": 1117 } ], "max_steps": 1850, "num_train_epochs": 9223372036854775807, "total_flos": 1.1072826181178819e+19, "trial_name": null, "trial_params": null }