| { | |
| "best_metric": 0.9428571428571428, | |
| "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-228", | |
| "epoch": 7.113333333333333, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.6438, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.6929, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7999, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.7967767715454102, | |
| "eval_runtime": 16.581, | |
| "eval_samples_per_second": 4.222, | |
| "eval_steps_per_second": 0.543, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.5279, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.4039, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.3795, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 0.3574, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_accuracy": 0.7571428571428571, | |
| "eval_loss": 0.6632290482521057, | |
| "eval_runtime": 16.8693, | |
| "eval_samples_per_second": 4.15, | |
| "eval_steps_per_second": 0.534, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.3809, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.3093, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2716, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.1651, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_accuracy": 0.8428571428571429, | |
| "eval_loss": 0.3925662040710449, | |
| "eval_runtime": 13.1445, | |
| "eval_samples_per_second": 5.325, | |
| "eval_steps_per_second": 0.685, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.1444, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 0.2528, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.0722, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0843, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "eval_accuracy": 0.8714285714285714, | |
| "eval_loss": 0.375051349401474, | |
| "eval_runtime": 12.7881, | |
| "eval_samples_per_second": 5.474, | |
| "eval_steps_per_second": 0.704, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.1844, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 0.103, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.1064, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 0.1116, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "eval_accuracy": 0.9285714285714286, | |
| "eval_loss": 0.32321324944496155, | |
| "eval_runtime": 16.6139, | |
| "eval_samples_per_second": 4.213, | |
| "eval_steps_per_second": 0.542, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.1736, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.087, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.0123, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "eval_accuracy": 0.9428571428571428, | |
| "eval_loss": 0.14982175827026367, | |
| "eval_runtime": 17.2395, | |
| "eval_samples_per_second": 4.06, | |
| "eval_steps_per_second": 0.522, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 0.0702, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0106, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.0152, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.0188, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.42830967903137207, | |
| "eval_runtime": 17.0875, | |
| "eval_samples_per_second": 4.097, | |
| "eval_steps_per_second": 0.527, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0077, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.0079, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.0092, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 0.0, | |
| "loss": 0.0146, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.4196590185165405, | |
| "eval_runtime": 16.8156, | |
| "eval_samples_per_second": 4.163, | |
| "eval_steps_per_second": 0.535, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "step": 300, | |
| "total_flos": 2.955876078527447e+18, | |
| "train_loss": 0.21394788240393003, | |
| "train_runtime": 1232.6567, | |
| "train_samples_per_second": 1.947, | |
| "train_steps_per_second": 0.243 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "eval_accuracy": 0.9032258064516129, | |
| "eval_loss": 0.2630390524864197, | |
| "eval_runtime": 38.8311, | |
| "eval_samples_per_second": 3.992, | |
| "eval_steps_per_second": 0.515, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "eval_accuracy": 0.9032258064516129, | |
| "eval_loss": 0.2707708775997162, | |
| "eval_runtime": 38.8958, | |
| "eval_samples_per_second": 3.985, | |
| "eval_steps_per_second": 0.514, | |
| "step": 300 | |
| } | |
| ], | |
| "max_steps": 300, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 2.955876078527447e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |