| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.942507068803016, |
| "eval_steps": 500, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1885014137606032, |
| "grad_norm": 1.0064737796783447, |
| "learning_rate": 0.00018757062146892655, |
| "loss": 1.3494, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.3770028275212064, |
| "grad_norm": 0.8948984146118164, |
| "learning_rate": 0.00017501569365976148, |
| "loss": 0.5214, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.5655042412818096, |
| "grad_norm": 0.6106454133987427, |
| "learning_rate": 0.0001624607658505964, |
| "loss": 0.322, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.7540056550424128, |
| "grad_norm": 0.6189490556716919, |
| "learning_rate": 0.0001499058380414313, |
| "loss": 0.2375, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.942507068803016, |
| "grad_norm": 0.8603423833847046, |
| "learning_rate": 0.00013735091023226617, |
| "loss": 0.1995, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 1593, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 2.0601868049547264e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
