|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.9876543209876543, |
|
"eval_steps": 500, |
|
"global_step": 40, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.12345679012345678, |
|
"grad_norm": 1.8914233446121216, |
|
"learning_rate": 0.0002, |
|
"loss": 1.5954, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.24691358024691357, |
|
"grad_norm": 0.7081738710403442, |
|
"learning_rate": 0.0002, |
|
"loss": 1.0488, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.37037037037037035, |
|
"grad_norm": 0.6127367615699768, |
|
"learning_rate": 0.0002, |
|
"loss": 0.8656, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.49382716049382713, |
|
"grad_norm": 0.766133189201355, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7746, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.6172839506172839, |
|
"grad_norm": 0.6299307942390442, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6941, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.7407407407407407, |
|
"grad_norm": 0.6025803089141846, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6348, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.8641975308641975, |
|
"grad_norm": 0.3971490263938904, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6172, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.9876543209876543, |
|
"grad_norm": 0.4407046437263489, |
|
"learning_rate": 0.0002, |
|
"loss": 0.5934, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.9876543209876543, |
|
"step": 40, |
|
"total_flos": 3.922995210878976e+16, |
|
"train_loss": 0.8529930114746094, |
|
"train_runtime": 388.5079, |
|
"train_samples_per_second": 13.246, |
|
"train_steps_per_second": 0.103 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 40, |
|
"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": 3.922995210878976e+16, |
|
"train_batch_size": 64, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|