| { |
| "best_global_step": 2130, |
| "best_metric": 1.8180431127548218, |
| "best_model_checkpoint": "clothes_image_detection/checkpoint-2130", |
| "epoch": 30.0, |
| "eval_steps": 500, |
| "global_step": 2130, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.10233333333333333, |
| "eval_loss": 2.6948089599609375, |
| "eval_runtime": 70.0693, |
| "eval_samples_per_second": 42.815, |
| "eval_steps_per_second": 2.683, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.18266666666666667, |
| "eval_loss": 2.653669834136963, |
| "eval_runtime": 70.636, |
| "eval_samples_per_second": 42.471, |
| "eval_steps_per_second": 2.662, |
| "step": 142 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.3, |
| "eval_loss": 2.607344627380371, |
| "eval_runtime": 69.0089, |
| "eval_samples_per_second": 43.473, |
| "eval_steps_per_second": 2.724, |
| "step": 213 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.4013333333333333, |
| "eval_loss": 2.554607629776001, |
| "eval_runtime": 70.6852, |
| "eval_samples_per_second": 42.442, |
| "eval_steps_per_second": 2.66, |
| "step": 284 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.4686666666666667, |
| "eval_loss": 2.500070333480835, |
| "eval_runtime": 69.3278, |
| "eval_samples_per_second": 43.273, |
| "eval_steps_per_second": 2.712, |
| "step": 355 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.5256666666666666, |
| "eval_loss": 2.4449872970581055, |
| "eval_runtime": 69.2123, |
| "eval_samples_per_second": 43.345, |
| "eval_steps_per_second": 2.716, |
| "step": 426 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.564, |
| "eval_loss": 2.3903112411499023, |
| "eval_runtime": 71.1389, |
| "eval_samples_per_second": 42.171, |
| "eval_steps_per_second": 2.643, |
| "step": 497 |
| }, |
| { |
| "epoch": 7.042253521126761, |
| "grad_norm": 1.266236662864685, |
| "learning_rate": 2.352403846153846e-06, |
| "loss": 2.5488, |
| "step": 500 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.5986666666666667, |
| "eval_loss": 2.335465431213379, |
| "eval_runtime": 70.0301, |
| "eval_samples_per_second": 42.839, |
| "eval_steps_per_second": 2.685, |
| "step": 568 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.615, |
| "eval_loss": 2.285032272338867, |
| "eval_runtime": 67.7999, |
| "eval_samples_per_second": 44.248, |
| "eval_steps_per_second": 2.773, |
| "step": 639 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.635, |
| "eval_loss": 2.2357773780822754, |
| "eval_runtime": 74.8161, |
| "eval_samples_per_second": 40.098, |
| "eval_steps_per_second": 2.513, |
| "step": 710 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_accuracy": 0.6423333333333333, |
| "eval_loss": 2.1898272037506104, |
| "eval_runtime": 67.9117, |
| "eval_samples_per_second": 44.175, |
| "eval_steps_per_second": 2.768, |
| "step": 781 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_accuracy": 0.6563333333333333, |
| "eval_loss": 2.14731502532959, |
| "eval_runtime": 67.716, |
| "eval_samples_per_second": 44.303, |
| "eval_steps_per_second": 2.776, |
| "step": 852 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_accuracy": 0.6706666666666666, |
| "eval_loss": 2.1075637340545654, |
| "eval_runtime": 66.5891, |
| "eval_samples_per_second": 45.052, |
| "eval_steps_per_second": 2.823, |
| "step": 923 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_accuracy": 0.684, |
| "eval_loss": 2.07025408744812, |
| "eval_runtime": 68.2256, |
| "eval_samples_per_second": 43.972, |
| "eval_steps_per_second": 2.756, |
| "step": 994 |
| }, |
| { |
| "epoch": 14.084507042253522, |
| "grad_norm": 1.6214760541915894, |
| "learning_rate": 1.6312499999999998e-06, |
| "loss": 2.1454, |
| "step": 1000 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_accuracy": 0.6923333333333334, |
| "eval_loss": 2.0363104343414307, |
| "eval_runtime": 68.9027, |
| "eval_samples_per_second": 43.54, |
| "eval_steps_per_second": 2.728, |
| "step": 1065 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_accuracy": 0.6963333333333334, |
| "eval_loss": 2.0070388317108154, |
| "eval_runtime": 69.1515, |
| "eval_samples_per_second": 43.383, |
| "eval_steps_per_second": 2.719, |
| "step": 1136 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_accuracy": 0.7033333333333334, |
| "eval_loss": 1.9784883260726929, |
| "eval_runtime": 67.8293, |
| "eval_samples_per_second": 44.229, |
| "eval_steps_per_second": 2.772, |
| "step": 1207 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_accuracy": 0.707, |
| "eval_loss": 1.953794002532959, |
| "eval_runtime": 69.2767, |
| "eval_samples_per_second": 43.305, |
| "eval_steps_per_second": 2.714, |
| "step": 1278 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_accuracy": 0.7116666666666667, |
| "eval_loss": 1.931581974029541, |
| "eval_runtime": 71.7133, |
| "eval_samples_per_second": 41.833, |
| "eval_steps_per_second": 2.622, |
| "step": 1349 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_accuracy": 0.713, |
| "eval_loss": 1.910805344581604, |
| "eval_runtime": 69.9572, |
| "eval_samples_per_second": 42.883, |
| "eval_steps_per_second": 2.687, |
| "step": 1420 |
| }, |
| { |
| "epoch": 21.0, |
| "eval_accuracy": 0.7203333333333334, |
| "eval_loss": 1.891245722770691, |
| "eval_runtime": 69.272, |
| "eval_samples_per_second": 43.308, |
| "eval_steps_per_second": 2.714, |
| "step": 1491 |
| }, |
| { |
| "epoch": 21.12676056338028, |
| "grad_norm": 1.8623607158660889, |
| "learning_rate": 9.100961538461538e-07, |
| "loss": 1.8743, |
| "step": 1500 |
| }, |
| { |
| "epoch": 22.0, |
| "eval_accuracy": 0.7196666666666667, |
| "eval_loss": 1.8760639429092407, |
| "eval_runtime": 69.8208, |
| "eval_samples_per_second": 42.967, |
| "eval_steps_per_second": 2.693, |
| "step": 1562 |
| }, |
| { |
| "epoch": 23.0, |
| "eval_accuracy": 0.722, |
| "eval_loss": 1.861554503440857, |
| "eval_runtime": 67.5377, |
| "eval_samples_per_second": 44.42, |
| "eval_steps_per_second": 2.784, |
| "step": 1633 |
| }, |
| { |
| "epoch": 24.0, |
| "eval_accuracy": 0.7216666666666667, |
| "eval_loss": 1.8497190475463867, |
| "eval_runtime": 71.5731, |
| "eval_samples_per_second": 41.915, |
| "eval_steps_per_second": 2.627, |
| "step": 1704 |
| }, |
| { |
| "epoch": 25.0, |
| "eval_accuracy": 0.7233333333333334, |
| "eval_loss": 1.8401118516921997, |
| "eval_runtime": 68.06, |
| "eval_samples_per_second": 44.079, |
| "eval_steps_per_second": 2.762, |
| "step": 1775 |
| }, |
| { |
| "epoch": 26.0, |
| "eval_accuracy": 0.725, |
| "eval_loss": 1.8322726488113403, |
| "eval_runtime": 69.1568, |
| "eval_samples_per_second": 43.38, |
| "eval_steps_per_second": 2.718, |
| "step": 1846 |
| }, |
| { |
| "epoch": 27.0, |
| "eval_accuracy": 0.7266666666666667, |
| "eval_loss": 1.8260819911956787, |
| "eval_runtime": 68.2959, |
| "eval_samples_per_second": 43.926, |
| "eval_steps_per_second": 2.753, |
| "step": 1917 |
| }, |
| { |
| "epoch": 28.0, |
| "eval_accuracy": 0.7263333333333334, |
| "eval_loss": 1.8216170072555542, |
| "eval_runtime": 70.5282, |
| "eval_samples_per_second": 42.536, |
| "eval_steps_per_second": 2.666, |
| "step": 1988 |
| }, |
| { |
| "epoch": 28.169014084507044, |
| "grad_norm": 1.6054729223251343, |
| "learning_rate": 1.889423076923077e-07, |
| "loss": 1.7411, |
| "step": 2000 |
| }, |
| { |
| "epoch": 29.0, |
| "eval_accuracy": 0.7263333333333334, |
| "eval_loss": 1.8188596963882446, |
| "eval_runtime": 70.6348, |
| "eval_samples_per_second": 42.472, |
| "eval_steps_per_second": 2.662, |
| "step": 2059 |
| }, |
| { |
| "epoch": 30.0, |
| "eval_accuracy": 0.7263333333333334, |
| "eval_loss": 1.8180431127548218, |
| "eval_runtime": 69.8284, |
| "eval_samples_per_second": 42.962, |
| "eval_steps_per_second": 2.692, |
| "step": 2130 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2130, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 30, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.046263750898688e+19, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
