| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.006399590426212722, |
| "eval_steps": 1000, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0012799180852425445, |
| "grad_norm": 395827.90625, |
| "learning_rate": 1.1523687580025607e-08, |
| "loss": 1.0217, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.002559836170485089, |
| "grad_norm": 425641.125, |
| "learning_rate": 2.4327784891165172e-08, |
| "loss": 0.9895, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0038397542557276334, |
| "grad_norm": 322450.875, |
| "learning_rate": 3.713188220230474e-08, |
| "loss": 1.0297, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.005119672340970178, |
| "grad_norm": 362794.28125, |
| "learning_rate": 4.9935979513444295e-08, |
| "loss": 1.0126, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.006399590426212722, |
| "grad_norm": 402867.875, |
| "learning_rate": 6.274007682458386e-08, |
| "loss": 1.0, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 841955377152000.0, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
