| { |
| "best_metric": 1.6845855712890625, |
| "best_model_checkpoint": "facial_age_estimator/checkpoint-2130", |
| "epoch": 10.0, |
| "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": 0.38575197889182056, |
| "eval_loss": 1.7030466794967651, |
| "eval_runtime": 15.5991, |
| "eval_samples_per_second": 121.482, |
| "eval_steps_per_second": 0.962, |
| "step": 213 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.3862796833773087, |
| "eval_loss": 1.7021386623382568, |
| "eval_runtime": 15.4209, |
| "eval_samples_per_second": 122.886, |
| "eval_steps_per_second": 0.973, |
| "step": 426 |
| }, |
| { |
| "epoch": 2.347417840375587, |
| "grad_norm": 6.318545818328857, |
| "learning_rate": 2.3509615384615386e-06, |
| "loss": 1.244, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.39050131926121373, |
| "eval_loss": 1.6881287097930908, |
| "eval_runtime": 15.5567, |
| "eval_samples_per_second": 121.813, |
| "eval_steps_per_second": 0.964, |
| "step": 639 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.3883905013192612, |
| "eval_loss": 1.698473334312439, |
| "eval_runtime": 15.7552, |
| "eval_samples_per_second": 120.278, |
| "eval_steps_per_second": 0.952, |
| "step": 852 |
| }, |
| { |
| "epoch": 4.694835680751174, |
| "grad_norm": 6.993715286254883, |
| "learning_rate": 1.6298076923076921e-06, |
| "loss": 1.1736, |
| "step": 1000 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.39472295514511874, |
| "eval_loss": 1.6962207555770874, |
| "eval_runtime": 15.3454, |
| "eval_samples_per_second": 123.49, |
| "eval_steps_per_second": 0.977, |
| "step": 1065 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.3899736147757256, |
| "eval_loss": 1.6851215362548828, |
| "eval_runtime": 15.5276, |
| "eval_samples_per_second": 122.041, |
| "eval_steps_per_second": 0.966, |
| "step": 1278 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.39366754617414246, |
| "eval_loss": 1.6846251487731934, |
| "eval_runtime": 15.4536, |
| "eval_samples_per_second": 122.625, |
| "eval_steps_per_second": 0.971, |
| "step": 1491 |
| }, |
| { |
| "epoch": 7.042253521126761, |
| "grad_norm": 7.442652225494385, |
| "learning_rate": 9.086538461538461e-07, |
| "loss": 1.1331, |
| "step": 1500 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.3941952506596306, |
| "eval_loss": 1.687286376953125, |
| "eval_runtime": 15.4771, |
| "eval_samples_per_second": 122.439, |
| "eval_steps_per_second": 0.969, |
| "step": 1704 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.38680738786279684, |
| "eval_loss": 1.6869077682495117, |
| "eval_runtime": 15.554, |
| "eval_samples_per_second": 121.834, |
| "eval_steps_per_second": 0.964, |
| "step": 1917 |
| }, |
| { |
| "epoch": 9.389671361502348, |
| "grad_norm": 11.96031665802002, |
| "learning_rate": 1.875e-07, |
| "loss": 1.1068, |
| "step": 2000 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.39261213720316623, |
| "eval_loss": 1.6845855712890625, |
| "eval_runtime": 15.5194, |
| "eval_samples_per_second": 122.105, |
| "eval_steps_per_second": 0.967, |
| "step": 2130 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2130, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "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": 1.0530629594950349e+19, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
