|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.4, |
|
"eval_steps": 500, |
|
"global_step": 250, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.16, |
|
"grad_norm": 0.9218915104866028, |
|
"learning_rate": 0.00013209436098072095, |
|
"loss": 1.4285, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"grad_norm": 0.8104269504547119, |
|
"learning_rate": 1.9843301512912327e-05, |
|
"loss": 1.2598, |
|
"step": 200 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 250, |
|
"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": 311794752946176.0, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|