|
{ |
|
"best_metric": 1.3928134441375732, |
|
"best_model_checkpoint": "./outputs/checkpoint-500", |
|
"epoch": 0.6666666666666666, |
|
"eval_steps": 100, |
|
"global_step": 500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.0002, |
|
"loss": 1.3509, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"eval_loss": 1.4751445055007935, |
|
"eval_runtime": 155.0414, |
|
"eval_samples_per_second": 12.448, |
|
"eval_steps_per_second": 1.561, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.0002, |
|
"loss": 1.2006, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"eval_loss": 1.441214680671692, |
|
"eval_runtime": 151.6424, |
|
"eval_samples_per_second": 12.727, |
|
"eval_steps_per_second": 1.596, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.0002, |
|
"loss": 1.1801, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"eval_loss": 1.4250988960266113, |
|
"eval_runtime": 151.7377, |
|
"eval_samples_per_second": 12.719, |
|
"eval_steps_per_second": 1.595, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.0002, |
|
"loss": 1.1655, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"eval_loss": 1.4099382162094116, |
|
"eval_runtime": 151.5335, |
|
"eval_samples_per_second": 12.736, |
|
"eval_steps_per_second": 1.597, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 0.0002, |
|
"loss": 1.1486, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"eval_loss": 1.3928134441375732, |
|
"eval_runtime": 151.678, |
|
"eval_samples_per_second": 12.724, |
|
"eval_steps_per_second": 1.595, |
|
"step": 500 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 2250, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 100, |
|
"total_flos": 3.186631141392384e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|