| { |
| "best_global_step": 626, |
| "best_metric": 0.4762755036354065, |
| "best_model_checkpoint": "./results/checkpoint-626", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 939, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9148684210526316, |
| "eval_f1": 0.9148397166441813, |
| "eval_loss": 0.5193027853965759, |
| "eval_runtime": 42.7151, |
| "eval_samples_per_second": 177.923, |
| "eval_steps_per_second": 11.12, |
| "step": 313 |
| }, |
| { |
| "epoch": 1.5974440894568689, |
| "grad_norm": 5.023766040802002, |
| "learning_rate": 9.3716719914803e-06, |
| "loss": 0.6489656372070313, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9231578947368421, |
| "eval_f1": 0.922976524551628, |
| "eval_loss": 0.4762755036354065, |
| "eval_runtime": 42.6522, |
| "eval_samples_per_second": 178.185, |
| "eval_steps_per_second": 11.137, |
| "step": 626 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9226315789473685, |
| "eval_f1": 0.9225226560837421, |
| "eval_loss": 0.5045727491378784, |
| "eval_runtime": 42.5236, |
| "eval_samples_per_second": 178.724, |
| "eval_steps_per_second": 11.17, |
| "step": 939 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 939, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 1973368350720000.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
