|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 5.0, |
|
"global_step": 10525, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 1.9049881235154395e-05, |
|
"loss": 0.3611, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 1.809976247030879e-05, |
|
"loss": 0.2398, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 1.7149643705463184e-05, |
|
"loss": 0.2149, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 1.6199524940617578e-05, |
|
"loss": 0.1939, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 1.5249406175771972e-05, |
|
"loss": 0.1514, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 1.4299287410926367e-05, |
|
"loss": 0.139, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 1.3349168646080762e-05, |
|
"loss": 0.136, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 1.2399049881235155e-05, |
|
"loss": 0.1295, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 1.144893111638955e-05, |
|
"loss": 0.1054, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 2.38, |
|
"learning_rate": 1.0498812351543943e-05, |
|
"loss": 0.0848, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"learning_rate": 9.548693586698338e-06, |
|
"loss": 0.0881, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 2.85, |
|
"learning_rate": 8.598574821852733e-06, |
|
"loss": 0.087, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 3.09, |
|
"learning_rate": 7.648456057007126e-06, |
|
"loss": 0.0715, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 3.33, |
|
"learning_rate": 6.698337292161521e-06, |
|
"loss": 0.0534, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 3.56, |
|
"learning_rate": 5.748218527315916e-06, |
|
"loss": 0.0513, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 3.8, |
|
"learning_rate": 4.798099762470309e-06, |
|
"loss": 0.0528, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 4.04, |
|
"learning_rate": 3.8479809976247036e-06, |
|
"loss": 0.0494, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 4.28, |
|
"learning_rate": 2.897862232779098e-06, |
|
"loss": 0.0283, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 4.51, |
|
"learning_rate": 1.947743467933492e-06, |
|
"loss": 0.0324, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 4.75, |
|
"learning_rate": 9.976247030878861e-07, |
|
"loss": 0.0275, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 4.99, |
|
"learning_rate": 4.750593824228029e-08, |
|
"loss": 0.0308, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"step": 10525, |
|
"total_flos": 14161246092288.0, |
|
"train_runtime": 1978.9597, |
|
"train_samples_per_second": 5.318 |
|
} |
|
], |
|
"max_steps": 10525, |
|
"num_train_epochs": 5, |
|
"total_flos": 14161246092288.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|