| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 976, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.07025091350078583, |
| "eval_runtime": 5.0582, |
| "eval_samples_per_second": 1370.443, |
| "eval_steps_per_second": 10.873, |
| "step": 488 |
| }, |
| { |
| "epoch": 1.0245901639344261, |
| "grad_norm": 0.16141989827156067, |
| "learning_rate": 0.001659153005464481, |
| "loss": 0.1892, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.035591669380664825, |
| "eval_runtime": 5.0427, |
| "eval_samples_per_second": 1374.654, |
| "eval_steps_per_second": 10.907, |
| "step": 976 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2928, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.06089911336448e+16, |
| "train_batch_size": 128, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
