| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "videomae-base-OKN-Test-V27\\checkpoint-328", | |
| "epoch": 9.0775, | |
| "eval_steps": 500, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.7255, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.5251, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.6081, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3018, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.8421052631578947, | |
| "eval_loss": 0.2653438150882721, | |
| "eval_runtime": 16.9042, | |
| "eval_samples_per_second": 1.124, | |
| "eval_steps_per_second": 0.296, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 0.537, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.3357, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 0.2755, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.4595, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_accuracy": 0.7894736842105263, | |
| "eval_loss": 0.3112753927707672, | |
| "eval_runtime": 16.8432, | |
| "eval_samples_per_second": 1.128, | |
| "eval_steps_per_second": 0.297, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 4.305555555555556e-05, | |
| "loss": 0.2786, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.2892, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 4.027777777777778e-05, | |
| "loss": 0.3056, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.4487, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_accuracy": 0.8421052631578947, | |
| "eval_loss": 0.3188110291957855, | |
| "eval_runtime": 16.124, | |
| "eval_samples_per_second": 1.178, | |
| "eval_steps_per_second": 0.31, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.361, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.1396, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.238, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.1211, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "eval_accuracy": 0.8421052631578947, | |
| "eval_loss": 0.8331090211868286, | |
| "eval_runtime": 16.4908, | |
| "eval_samples_per_second": 1.152, | |
| "eval_steps_per_second": 0.303, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 3.194444444444444e-05, | |
| "loss": 0.5472, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.332, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 2.916666666666667e-05, | |
| "loss": 0.2465, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.309, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "eval_accuracy": 0.8947368421052632, | |
| "eval_loss": 0.29101037979125977, | |
| "eval_runtime": 16.4706, | |
| "eval_samples_per_second": 1.154, | |
| "eval_steps_per_second": 0.304, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 2.6388888888888892e-05, | |
| "loss": 0.1975, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0963, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 2.361111111111111e-05, | |
| "loss": 0.366, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.1185, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "eval_accuracy": 0.8421052631578947, | |
| "eval_loss": 0.20961391925811768, | |
| "eval_runtime": 17.1194, | |
| "eval_samples_per_second": 1.11, | |
| "eval_steps_per_second": 0.292, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.616, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.0551, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 1.8055555555555555e-05, | |
| "loss": 0.2922, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.2193, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "eval_accuracy": 0.8947368421052632, | |
| "eval_loss": 0.31129229068756104, | |
| "eval_runtime": 16.4386, | |
| "eval_samples_per_second": 1.156, | |
| "eval_steps_per_second": 0.304, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 1.527777777777778e-05, | |
| "loss": 0.1423, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.0269, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.0218, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.056, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.000889659917447716, | |
| "eval_runtime": 15.8787, | |
| "eval_samples_per_second": 1.197, | |
| "eval_steps_per_second": 0.315, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 9.722222222222223e-06, | |
| "loss": 0.0011, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.0007, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.001, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.002, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0006986224907450378, | |
| "eval_runtime": 16.4309, | |
| "eval_samples_per_second": 1.156, | |
| "eval_steps_per_second": 0.304, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.0005, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 0.0005, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 1.388888888888889e-06, | |
| "loss": 0.0005, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "learning_rate": 0.0, | |
| "loss": 0.0005, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0006409377092495561, | |
| "eval_runtime": 17.0698, | |
| "eval_samples_per_second": 1.113, | |
| "eval_steps_per_second": 0.293, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "step": 400, | |
| "total_flos": 1.9824887618495447e+18, | |
| "train_loss": 0.23998755085049198, | |
| "train_runtime": 4577.1455, | |
| "train_samples_per_second": 0.35, | |
| "train_steps_per_second": 0.087 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0008896598010323942, | |
| "eval_runtime": 17.4007, | |
| "eval_samples_per_second": 1.092, | |
| "eval_steps_per_second": 0.287, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0007012621499598026, | |
| "eval_runtime": 18.6184, | |
| "eval_samples_per_second": 1.02, | |
| "eval_steps_per_second": 0.269, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 400, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 1.9824887618495447e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |