|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.2590966122961103, |
|
"eval_steps": 200, |
|
"global_step": 1200, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 2e-05, |
|
"loss": 3.0055, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"eval_runtime": 1014.7039, |
|
"eval_samples_per_second": 2.217, |
|
"eval_steps_per_second": 0.278, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 2e-05, |
|
"loss": 0.711, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"eval_runtime": 1015.2415, |
|
"eval_samples_per_second": 2.216, |
|
"eval_steps_per_second": 0.278, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 2e-05, |
|
"loss": 0.6912, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"eval_runtime": 1010.7698, |
|
"eval_samples_per_second": 2.226, |
|
"eval_steps_per_second": 0.279, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"learning_rate": 2e-05, |
|
"loss": 0.657, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"eval_runtime": 1009.8349, |
|
"eval_samples_per_second": 2.228, |
|
"eval_steps_per_second": 0.279, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 2e-05, |
|
"loss": 0.6491, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"eval_runtime": 1014.137, |
|
"eval_samples_per_second": 2.219, |
|
"eval_steps_per_second": 0.278, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 2.26, |
|
"learning_rate": 2e-05, |
|
"loss": 0.6355, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 2.26, |
|
"eval_runtime": 1008.6366, |
|
"eval_samples_per_second": 2.231, |
|
"eval_steps_per_second": 0.28, |
|
"step": 1200 |
|
} |
|
], |
|
"logging_steps": 200, |
|
"max_steps": 1593, |
|
"num_train_epochs": 3, |
|
"save_steps": 200, |
|
"total_flos": 2.6799726998677094e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|