|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.1, |
|
"eval_steps": 25, |
|
"global_step": 75, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 2.3797595190380762e-05, |
|
"loss": 3.5104, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"eval_loss": 2.643505334854126, |
|
"eval_runtime": 13.8992, |
|
"eval_samples_per_second": 17.987, |
|
"eval_steps_per_second": 2.302, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 2.2545090180360722e-05, |
|
"loss": 2.2052, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"eval_loss": 1.966366171836853, |
|
"eval_runtime": 13.6092, |
|
"eval_samples_per_second": 18.37, |
|
"eval_steps_per_second": 2.351, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 2.1292585170340683e-05, |
|
"loss": 1.81, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"eval_loss": 1.8134992122650146, |
|
"eval_runtime": 13.5125, |
|
"eval_samples_per_second": 18.501, |
|
"eval_steps_per_second": 2.368, |
|
"step": 75 |
|
} |
|
], |
|
"logging_steps": 25, |
|
"max_steps": 500, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 25, |
|
"total_flos": 1232559931392000.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|