| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 7, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.14285714285714285, |
| "grad_norm": 1.328730583190918, |
| "learning_rate": 0.0, |
| "loss": 2.0389, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.2857142857142857, |
| "grad_norm": 1.0750229358673096, |
| "learning_rate": 5e-05, |
| "loss": 1.8052, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 0.9114528298377991, |
| "learning_rate": 4.665063509461097e-05, |
| "loss": 1.8434, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.5714285714285714, |
| "grad_norm": 4.7995476722717285, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 2.1455, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 1.0328369140625, |
| "learning_rate": 2.5e-05, |
| "loss": 1.8704, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.8571428571428571, |
| "grad_norm": 5.873198986053467, |
| "learning_rate": 1.2500000000000006e-05, |
| "loss": 2.1626, |
| "step": 6 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.3790919780731201, |
| "learning_rate": 3.3493649053890326e-06, |
| "loss": 1.9265, |
| "step": 7 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 7, |
| "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": 1396953128632320.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
