| { | |
| "best_metric": 0.9625668449197861, | |
| "best_model_checkpoint": "videomae-base-finetuned-RealLifeViolenceSituations-subset/checkpoint-801", | |
| "epoch": 1.00125, | |
| "global_step": 801, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.7083333333333332e-05, | |
| "loss": 0.1898, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.6388888888888892e-05, | |
| "loss": 0.0711, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.5694444444444445e-05, | |
| "loss": 0.2212, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.007, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.4305555555555558e-05, | |
| "loss": 0.0788, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.361111111111111e-05, | |
| "loss": 0.0797, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 2.2916666666666667e-05, | |
| "loss": 0.1241, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0802, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2.152777777777778e-05, | |
| "loss": 0.1921, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.0206, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.013888888888889e-05, | |
| "loss": 0.0651, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.0225, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 0.0067, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.8055555555555555e-05, | |
| "loss": 0.0726, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.736111111111111e-05, | |
| "loss": 0.1615, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0143, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.597222222222222e-05, | |
| "loss": 0.1015, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.527777777777778e-05, | |
| "loss": 0.0444, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.4583333333333335e-05, | |
| "loss": 0.0842, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.1065, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.9597855227882037, | |
| "eval_loss": 0.1469525396823883, | |
| "eval_runtime": 797.6638, | |
| "eval_samples_per_second": 0.468, | |
| "eval_steps_per_second": 0.059, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.3194444444444446e-05, | |
| "loss": 0.15, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.0802, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 1.1805555555555555e-05, | |
| "loss": 0.0472, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0397, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 0.2298, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 9.722222222222223e-06, | |
| "loss": 0.207, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 9.027777777777777e-06, | |
| "loss": 0.0975, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.1434, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 7.63888888888889e-06, | |
| "loss": 0.0511, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.0115, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 6.25e-06, | |
| "loss": 0.0294, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.2199, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.861111111111111e-06, | |
| "loss": 0.1026, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.1386, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.4722222222222224e-06, | |
| "loss": 0.0015, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 0.0329, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.0833333333333334e-06, | |
| "loss": 0.1884, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.388888888888889e-06, | |
| "loss": 0.063, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 6.944444444444445e-07, | |
| "loss": 0.0044, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0, | |
| "loss": 0.067, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_accuracy": 0.9624664879356568, | |
| "eval_loss": 0.1415206491947174, | |
| "eval_runtime": 805.592, | |
| "eval_samples_per_second": 0.463, | |
| "eval_steps_per_second": 0.058, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.0, | |
| "loss": 0.0037, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0, | |
| "loss": 0.0683, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0, | |
| "loss": 0.0159, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.0, | |
| "loss": 0.0406, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.0, | |
| "loss": 0.0719, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.0, | |
| "loss": 0.2585, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.0, | |
| "loss": 0.0222, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.0, | |
| "loss": 0.0742, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.0, | |
| "loss": 0.0088, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.0, | |
| "loss": 0.0085, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0, | |
| "loss": 0.0046, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.0, | |
| "loss": 0.0205, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.0, | |
| "loss": 0.0954, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.0, | |
| "loss": 0.1016, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.0, | |
| "loss": 0.0768, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.0, | |
| "loss": 0.0799, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.0, | |
| "loss": 0.0762, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.0, | |
| "loss": 0.0028, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.0, | |
| "loss": 0.1537, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.0, | |
| "loss": 0.0058, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_accuracy": 0.9624664879356568, | |
| "eval_loss": 0.1415206491947174, | |
| "eval_runtime": 825.0942, | |
| "eval_samples_per_second": 0.452, | |
| "eval_steps_per_second": 0.057, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.0, | |
| "loss": 0.0106, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.0, | |
| "loss": 0.0877, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 0.0, | |
| "loss": 0.0056, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 0.0, | |
| "loss": 0.0712, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.0, | |
| "loss": 0.0045, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 0.0, | |
| "loss": 0.051, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 0.0, | |
| "loss": 0.0953, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 0.0, | |
| "loss": 0.0815, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 0.0, | |
| "loss": 0.1176, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.0, | |
| "loss": 0.1597, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 0.0, | |
| "loss": 0.0417, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 0.0, | |
| "loss": 0.0023, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 0.0, | |
| "loss": 0.0292, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 0.0, | |
| "loss": 0.0133, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 0.0, | |
| "loss": 0.0347, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 0.0, | |
| "loss": 0.0022, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 0.0, | |
| "loss": 0.0083, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 0.0, | |
| "loss": 0.0046, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 0.0, | |
| "loss": 0.0067, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 0.0, | |
| "loss": 0.0274, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_accuracy": 0.9624664879356568, | |
| "eval_loss": 0.1415206491947174, | |
| "eval_runtime": 788.2208, | |
| "eval_samples_per_second": 0.473, | |
| "eval_steps_per_second": 0.06, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9625668449197861, | |
| "eval_loss": 0.14114385843276978, | |
| "eval_runtime": 846.6552, | |
| "eval_samples_per_second": 0.442, | |
| "eval_steps_per_second": 0.056, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 801, | |
| "total_flos": 7.99475040605071e+18, | |
| "train_loss": 2.0883763476406293e-06, | |
| "train_runtime": 900.3937, | |
| "train_samples_per_second": 7.108, | |
| "train_steps_per_second": 0.889 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9585687382297552, | |
| "eval_loss": 0.14402535557746887, | |
| "eval_runtime": 1042.5133, | |
| "eval_samples_per_second": 0.509, | |
| "eval_steps_per_second": 0.064, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9532908704883227, | |
| "eval_loss": 0.16175416111946106, | |
| "eval_runtime": 971.1712, | |
| "eval_samples_per_second": 0.485, | |
| "eval_steps_per_second": 0.061, | |
| "step": 801 | |
| } | |
| ], | |
| "max_steps": 800, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 7.99475040605071e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |