| { |
| "best_global_step": 100, |
| "best_metric": 0.9707561861913826, |
| "best_model_checkpoint": "outputs/finetune/checkpoint-100", |
| "epoch": 20.0, |
| "eval_steps": 100, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 10.0, |
| "grad_norm": 2.57930326461792, |
| "learning_rate": 2.35e-06, |
| "loss": 47.79998046875, |
| "step": 50 |
| }, |
| { |
| "epoch": 20.0, |
| "grad_norm": 0.42219385504722595, |
| "learning_rate": 4.85e-06, |
| "loss": 3.656361083984375, |
| "step": 100 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_loss": 0.6268529295921326, |
| "eval_runtime": 2.4798, |
| "eval_samples_per_second": 55.651, |
| "eval_steps_per_second": 14.114, |
| "eval_token_accuracy": 0.9707561861913826, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 200, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.241918498787715e+19, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
