| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 10, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.21052631578947367, |
| "grad_norm": 0.8595283031463623, |
| "learning_rate": 0.0002, |
| "loss": 2.2998, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.42105263157894735, |
| "grad_norm": 0.9670653939247131, |
| "learning_rate": 0.0001866666666666667, |
| "loss": 2.8014, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.631578947368421, |
| "grad_norm": 0.7496209144592285, |
| "learning_rate": 0.00017333333333333334, |
| "loss": 1.8851, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.8421052631578947, |
| "grad_norm": 1.8216716051101685, |
| "learning_rate": 0.00016, |
| "loss": 2.5663, |
| "step": 4 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.9130350947380066, |
| "learning_rate": 0.00014666666666666666, |
| "loss": 2.4712, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.2105263157894737, |
| "grad_norm": 0.5203133225440979, |
| "learning_rate": 0.00013333333333333334, |
| "loss": 1.5523, |
| "step": 6 |
| }, |
| { |
| "epoch": 1.4210526315789473, |
| "grad_norm": 0.7877249121665955, |
| "learning_rate": 0.00012, |
| "loss": 1.8315, |
| "step": 7 |
| }, |
| { |
| "epoch": 1.631578947368421, |
| "grad_norm": 0.924498975276947, |
| "learning_rate": 0.00010666666666666667, |
| "loss": 2.1605, |
| "step": 8 |
| }, |
| { |
| "epoch": 1.8421052631578947, |
| "grad_norm": 0.7224551439285278, |
| "learning_rate": 9.333333333333334e-05, |
| "loss": 2.2001, |
| "step": 9 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.7880566120147705, |
| "learning_rate": 8e-05, |
| "loss": 2.0703, |
| "step": 10 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 15, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 10, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1179259170201600.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
