|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.018738738738738738, |
|
"eval_steps": 10, |
|
"global_step": 13, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0014414414414414415, |
|
"eval_loss": 1.645052194595337, |
|
"eval_runtime": 22.5295, |
|
"eval_samples_per_second": 13.005, |
|
"eval_steps_per_second": 6.525, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.007207207207207207, |
|
"grad_norm": 9.337347030639648, |
|
"learning_rate": 5e-05, |
|
"loss": 6.6234, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.014414414414414415, |
|
"grad_norm": 10.592222213745117, |
|
"learning_rate": 0.0001, |
|
"loss": 6.3621, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.014414414414414415, |
|
"eval_loss": 1.458554983139038, |
|
"eval_runtime": 23.5258, |
|
"eval_samples_per_second": 12.454, |
|
"eval_steps_per_second": 6.248, |
|
"step": 10 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 50, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 13, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 2322287466381312.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|