| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.2178649237472767, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.054466230936819175, |
| "grad_norm": 5.168296813964844, |
| "learning_rate": 5e-05, |
| "loss": 1.747, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.10893246187363835, |
| "grad_norm": 0.6366938948631287, |
| "learning_rate": 4.711981566820277e-05, |
| "loss": 1.3516, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.16339869281045752, |
| "grad_norm": 0.5679114460945129, |
| "learning_rate": 4.423963133640553e-05, |
| "loss": 1.3809, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.2178649237472767, |
| "grad_norm": 1.4229077100753784, |
| "learning_rate": 4.13594470046083e-05, |
| "loss": 1.2784, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 9180, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 522584064000000.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
