| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.6557377049180327, |
| "eval_steps": 500, |
| "global_step": 10, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.32786885245901637, |
| "grad_norm": 3.6749563217163086, |
| "learning_rate": 4.917142857142858e-06, |
| "loss": 1.2441, |
| "mean_token_accuracy": 0.6957027420401574, |
| "num_tokens": 1499762.0, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.6557377049180327, |
| "grad_norm": 0.7111566662788391, |
| "learning_rate": 1.106357142857143e-05, |
| "loss": 0.9906, |
| "mean_token_accuracy": 0.7224896475672722, |
| "num_tokens": 3011646.0, |
| "step": 10 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 32, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 1.8618336610647245e+17, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
