| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.857142857142857, |
| "eval_steps": 500, |
| "global_step": 15, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.9523809523809523, |
| "grad_norm": 1.2834333181381226, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 1.3709, |
| "num_input_tokens_seen": 14048, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.9047619047619047, |
| "grad_norm": 0.9274190068244934, |
| "learning_rate": 1.2500000000000006e-05, |
| "loss": 0.9871, |
| "num_input_tokens_seen": 28128, |
| "step": 10 |
| }, |
| { |
| "epoch": 2.857142857142857, |
| "grad_norm": 0.8120085000991821, |
| "learning_rate": 0.0, |
| "loss": 0.9033, |
| "num_input_tokens_seen": 42160, |
| "step": 15 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 15, |
| "num_input_tokens_seen": 42160, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1909403794145280.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
