|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 6.097560975609756, |
|
"global_step": 500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 1.0000000000000002e-06, |
|
"loss": 1.7257, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 2.0000000000000003e-06, |
|
"loss": 1.3069, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 3e-06, |
|
"loss": 1.0021, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 4.000000000000001e-06, |
|
"loss": 0.827, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 5e-06, |
|
"loss": 0.733, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 1.83, |
|
"learning_rate": 6e-06, |
|
"loss": 0.6732, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 7e-06, |
|
"loss": 0.5834, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 2.44, |
|
"learning_rate": 8.000000000000001e-06, |
|
"loss": 0.5074, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 2.74, |
|
"learning_rate": 9e-06, |
|
"loss": 0.477, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 3.05, |
|
"learning_rate": 1e-05, |
|
"loss": 0.4321, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 3.35, |
|
"learning_rate": 9e-06, |
|
"loss": 0.3351, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 3.66, |
|
"learning_rate": 8.000000000000001e-06, |
|
"loss": 0.3216, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 3.96, |
|
"learning_rate": 7e-06, |
|
"loss": 0.3137, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 4.27, |
|
"learning_rate": 6e-06, |
|
"loss": 0.2335, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 4.57, |
|
"learning_rate": 5e-06, |
|
"loss": 0.2205, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 4.88, |
|
"learning_rate": 4.000000000000001e-06, |
|
"loss": 0.2107, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 5.18, |
|
"learning_rate": 3e-06, |
|
"loss": 0.1833, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 5.49, |
|
"learning_rate": 2.0000000000000003e-06, |
|
"loss": 0.1584, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 5.79, |
|
"learning_rate": 1.0000000000000002e-06, |
|
"loss": 0.1602, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 6.1, |
|
"learning_rate": 0.0, |
|
"loss": 0.1511, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 6.1, |
|
"step": 500, |
|
"total_flos": 1.846600259567616e+19, |
|
"train_loss": 0.52779975938797, |
|
"train_runtime": 27469.1066, |
|
"train_samples_per_second": 2.33, |
|
"train_steps_per_second": 0.018 |
|
} |
|
], |
|
"max_steps": 500, |
|
"num_train_epochs": 7, |
|
"total_flos": 1.846600259567616e+19, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|