| { | |
| "best_metric": 0.9, | |
| "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-300", | |
| "epoch": 3.25, | |
| "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": 2.359, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.2786, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2906, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 2.0457, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 2.0903, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.9531, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 1.8073, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 1.399868130683899, | |
| "eval_runtime": 20.1581, | |
| "eval_samples_per_second": 3.473, | |
| "eval_steps_per_second": 0.893, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 1.3983, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 1.2218, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 1.0969, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.8963, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.9137, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 0.6036, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.611, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.9688, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_accuracy": 0.7285714285714285, | |
| "eval_loss": 0.6959248781204224, | |
| "eval_runtime": 19.7738, | |
| "eval_samples_per_second": 3.54, | |
| "eval_steps_per_second": 0.91, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.395, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 0.4499, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.5235, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 0.3547, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.3817, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.2556, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.266, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_accuracy": 0.7714285714285715, | |
| "eval_loss": 0.45454928278923035, | |
| "eval_runtime": 20.1463, | |
| "eval_samples_per_second": 3.475, | |
| "eval_steps_per_second": 0.893, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 0.1792, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.1061, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.1133, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.136, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.1425, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.2415, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.1614, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 0.0, | |
| "loss": 0.2419, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_accuracy": 0.9, | |
| "eval_loss": 0.27419859170913696, | |
| "eval_runtime": 19.7745, | |
| "eval_samples_per_second": 3.54, | |
| "eval_steps_per_second": 0.91, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "step": 300, | |
| "total_flos": 1.495384188125184e+18, | |
| "train_loss": 0.8827841822306315, | |
| "train_runtime": 900.6302, | |
| "train_samples_per_second": 1.332, | |
| "train_steps_per_second": 0.333 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_accuracy": 0.9225806451612903, | |
| "eval_loss": 0.22333580255508423, | |
| "eval_runtime": 46.1832, | |
| "eval_samples_per_second": 3.356, | |
| "eval_steps_per_second": 0.844, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_accuracy": 0.9225806451612903, | |
| "eval_loss": 0.22333580255508423, | |
| "eval_runtime": 43.3856, | |
| "eval_samples_per_second": 3.573, | |
| "eval_steps_per_second": 0.899, | |
| "step": 300 | |
| } | |
| ], | |
| "max_steps": 300, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 1.495384188125184e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |