| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.7272727272727273, |
| "eval_steps": 1, |
| "global_step": 2, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.36363636363636365, |
| "grad_norm": 0.017898203805088997, |
| "learning_rate": 0.0002, |
| "loss": 1.2584, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.36363636363636365, |
| "eval_loss": 1.1288206577301025, |
| "eval_runtime": 0.4856, |
| "eval_samples_per_second": 6.177, |
| "eval_steps_per_second": 2.059, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.7272727272727273, |
| "grad_norm": 0.02099686488509178, |
| "learning_rate": 0.0002, |
| "loss": 1.3291, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.7272727272727273, |
| "eval_loss": 1.1258248090744019, |
| "eval_runtime": 0.4895, |
| "eval_samples_per_second": 6.129, |
| "eval_steps_per_second": 2.043, |
| "step": 2 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 2, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 807968778107904.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
