| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0008452123596053508, |
| "eval_steps": 10, |
| "global_step": 13, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 6.501633535425775e-05, |
| "eval_loss": 6.663437843322754, |
| "eval_runtime": 77.4622, |
| "eval_samples_per_second": 83.615, |
| "eval_steps_per_second": 41.814, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00032508167677128876, |
| "grad_norm": 3.2935903072357178, |
| "learning_rate": 5e-05, |
| "loss": 6.4505, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0006501633535425775, |
| "grad_norm": 2.8207027912139893, |
| "learning_rate": 0.0001, |
| "loss": 6.6583, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0006501633535425775, |
| "eval_loss": 6.633432388305664, |
| "eval_runtime": 76.7926, |
| "eval_samples_per_second": 84.344, |
| "eval_steps_per_second": 42.179, |
| "step": 10 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 13, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1688132517888.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
