| { | |
| "best_metric": 0.9857142857142858, | |
| "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-600", | |
| "epoch": 3.25, | |
| "eval_steps": 500, | |
| "global_step": 600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 2.3171, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 2.252, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.1918, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.2038, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 2.1914, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2023, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.9074074074074075e-05, | |
| "loss": 2.206, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 1.8991, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 2.0264, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 1.8314, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.5370370370370374e-05, | |
| "loss": 1.7088, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.6541, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.351851851851852e-05, | |
| "loss": 1.6237, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 1.3924, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.2544, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.44285714285714284, | |
| "eval_loss": 1.370309829711914, | |
| "eval_runtime": 19.2054, | |
| "eval_samples_per_second": 3.645, | |
| "eval_steps_per_second": 1.822, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 1.1833, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.981481481481482e-05, | |
| "loss": 1.1287, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.9832, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.7962962962962964e-05, | |
| "loss": 0.9388, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 1.2162, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.826, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.9838, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.425925925925926e-05, | |
| "loss": 0.8888, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.6393, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.5864, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 0.5376, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.8571, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.3683, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.8703703703703706e-05, | |
| "loss": 1.1622, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 1.0825, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_accuracy": 0.7428571428571429, | |
| "eval_loss": 0.6761045455932617, | |
| "eval_runtime": 19.331, | |
| "eval_samples_per_second": 3.621, | |
| "eval_steps_per_second": 1.811, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.6851851851851855e-05, | |
| "loss": 0.478, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.2416, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.333, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 0.2037, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.34, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.669, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 2.1296296296296296e-05, | |
| "loss": 0.3737, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 0.1322, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.2662, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.318, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.7592592592592595e-05, | |
| "loss": 0.1596, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0874, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.574074074074074e-05, | |
| "loss": 0.2727, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.0459, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.2885, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_accuracy": 0.8285714285714286, | |
| "eval_loss": 0.6104217767715454, | |
| "eval_runtime": 20.1055, | |
| "eval_samples_per_second": 3.482, | |
| "eval_steps_per_second": 1.741, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 0.2173, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 1.2037037037037037e-05, | |
| "loss": 0.1313, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0252, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 1.0185185185185185e-05, | |
| "loss": 0.035, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.025, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.1221, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.1264, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 6.481481481481481e-06, | |
| "loss": 0.036, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0544, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.2549, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.2963, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 0.1269, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.1344, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 9.259259259259259e-07, | |
| "loss": 0.4507, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 0.0, | |
| "loss": 0.262, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_accuracy": 0.9857142857142858, | |
| "eval_loss": 0.093513622879982, | |
| "eval_runtime": 20.2313, | |
| "eval_samples_per_second": 3.46, | |
| "eval_steps_per_second": 1.73, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "step": 600, | |
| "total_flos": 1.495384188125184e+18, | |
| "train_loss": 0.8140682246039311, | |
| "train_runtime": 787.3727, | |
| "train_samples_per_second": 1.524, | |
| "train_steps_per_second": 0.762 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_accuracy": 0.8838709677419355, | |
| "eval_loss": 0.39101719856262207, | |
| "eval_runtime": 43.7237, | |
| "eval_samples_per_second": 3.545, | |
| "eval_steps_per_second": 1.784, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_accuracy": 0.8838709677419355, | |
| "eval_loss": 0.39101719856262207, | |
| "eval_runtime": 43.5539, | |
| "eval_samples_per_second": 3.559, | |
| "eval_steps_per_second": 1.791, | |
| "step": 600 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 600, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 1.495384188125184e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |