|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 12.0, |
|
"global_step": 36, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 1e-05, |
|
"loss": 2.0078, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 2e-05, |
|
"loss": 1.8555, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 1.9957341762950346e-05, |
|
"loss": 1.9727, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 1.982973099683902e-05, |
|
"loss": 1.9648, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"learning_rate": 1.961825643172819e-05, |
|
"loss": 1.9531, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 1.932472229404356e-05, |
|
"loss": 1.8516, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 2.33, |
|
"learning_rate": 1.8951632913550625e-05, |
|
"loss": 1.8047, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"learning_rate": 1.8502171357296144e-05, |
|
"loss": 2.0195, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 1.7980172272802398e-05, |
|
"loss": 1.7578, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 3.33, |
|
"learning_rate": 1.7390089172206594e-05, |
|
"loss": 1.7539, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 3.67, |
|
"learning_rate": 1.6736956436465573e-05, |
|
"loss": 1.7461, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 1.6026346363792565e-05, |
|
"loss": 1.7109, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 4.33, |
|
"learning_rate": 1.526432162877356e-05, |
|
"loss": 1.7227, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 4.67, |
|
"learning_rate": 1.4457383557765385e-05, |
|
"loss": 1.4961, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 1.3612416661871532e-05, |
|
"loss": 1.4961, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 5.33, |
|
"learning_rate": 1.2736629900720832e-05, |
|
"loss": 1.5039, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 5.67, |
|
"learning_rate": 1.1837495178165706e-05, |
|
"loss": 1.2852, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"learning_rate": 1.092268359463302e-05, |
|
"loss": 1.4375, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 6.33, |
|
"learning_rate": 1e-05, |
|
"loss": 1.3555, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 6.67, |
|
"learning_rate": 9.07731640536698e-06, |
|
"loss": 1.2539, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"learning_rate": 8.162504821834296e-06, |
|
"loss": 1.2578, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 7.33, |
|
"learning_rate": 7.263370099279173e-06, |
|
"loss": 1.1641, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 7.67, |
|
"learning_rate": 6.387583338128471e-06, |
|
"loss": 1.2461, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"learning_rate": 5.542616442234618e-06, |
|
"loss": 1.1445, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 8.33, |
|
"learning_rate": 4.7356783712264405e-06, |
|
"loss": 1.2344, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 8.67, |
|
"learning_rate": 3.973653636207437e-06, |
|
"loss": 1.1367, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"learning_rate": 3.2630435635344283e-06, |
|
"loss": 1.0488, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 9.33, |
|
"learning_rate": 2.6099108277934105e-06, |
|
"loss": 1.043, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 9.67, |
|
"learning_rate": 2.019827727197605e-06, |
|
"loss": 1.1328, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 1.4978286427038602e-06, |
|
"loss": 1.1758, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 10.33, |
|
"learning_rate": 1.0483670864493777e-06, |
|
"loss": 1.0723, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 10.67, |
|
"learning_rate": 6.752777059564431e-07, |
|
"loss": 1.1367, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 11.0, |
|
"learning_rate": 3.817435682718096e-07, |
|
"loss": 1.082, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 11.33, |
|
"learning_rate": 1.7026900316098217e-07, |
|
"loss": 1.0742, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 11.67, |
|
"learning_rate": 4.2658237049655325e-08, |
|
"loss": 1.1172, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 12.0, |
|
"learning_rate": 0.0, |
|
"loss": 1.0938, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 12.0, |
|
"step": 36, |
|
"total_flos": 1.4460629960097792e+16, |
|
"train_loss": 1.4474826388888888, |
|
"train_runtime": 1003.5962, |
|
"train_samples_per_second": 1.148, |
|
"train_steps_per_second": 0.036 |
|
} |
|
], |
|
"max_steps": 36, |
|
"num_train_epochs": 12, |
|
"total_flos": 1.4460629960097792e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|