| { |
| "best_global_step": 2156, |
| "best_metric": 0.3237510919570923, |
| "best_model_checkpoint": "face-confidence/checkpoint-2156", |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 2156, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.9276437847866419, |
| "grad_norm": 6.720329761505127, |
| "learning_rate": 1.5726495726495726e-05, |
| "loss": 0.4994, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8189497518070191, |
| "eval_loss": 0.3962201476097107, |
| "eval_model_preparation_time": 0.0025, |
| "eval_runtime": 141.0014, |
| "eval_samples_per_second": 81.439, |
| "eval_steps_per_second": 10.184, |
| "step": 539 |
| }, |
| { |
| "epoch": 1.8552875695732838, |
| "grad_norm": 8.098552703857422, |
| "learning_rate": 1.0978157644824312e-05, |
| "loss": 0.4083, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8331446486109901, |
| "eval_loss": 0.37225112318992615, |
| "eval_model_preparation_time": 0.0025, |
| "eval_runtime": 139.7716, |
| "eval_samples_per_second": 82.155, |
| "eval_steps_per_second": 10.274, |
| "step": 1078 |
| }, |
| { |
| "epoch": 2.782931354359926, |
| "grad_norm": 13.027604103088379, |
| "learning_rate": 6.229819563152897e-06, |
| "loss": 0.3556, |
| "step": 1500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8531742575981887, |
| "eval_loss": 0.33761295676231384, |
| "eval_model_preparation_time": 0.0025, |
| "eval_runtime": 139.2575, |
| "eval_samples_per_second": 82.459, |
| "eval_steps_per_second": 10.312, |
| "step": 1617 |
| }, |
| { |
| "epoch": 3.7105751391465676, |
| "grad_norm": 11.10226821899414, |
| "learning_rate": 1.4814814814814815e-06, |
| "loss": 0.3085, |
| "step": 2000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8599669076025429, |
| "eval_loss": 0.3237510919570923, |
| "eval_model_preparation_time": 0.0025, |
| "eval_runtime": 139.6031, |
| "eval_samples_per_second": 82.255, |
| "eval_steps_per_second": 10.286, |
| "step": 2156 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2156, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "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": 5.770418640105112e+18, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
