|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.9975429975429976, |
|
"eval_steps": 500, |
|
"global_step": 203, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.0005, |
|
"loss": 0.7976, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.0004966952699028185, |
|
"loss": 0.165, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.0004868684495393958, |
|
"loss": 0.1474, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00047077933882184867, |
|
"loss": 0.1534, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.00044885329909757834, |
|
"loss": 0.1286, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.0004216700075136953, |
|
"loss": 0.1416, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.00038994813160490117, |
|
"loss": 0.1198, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.0003545263292756348, |
|
"loss": 0.1522, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 0.0003163410764959277, |
|
"loss": 0.137, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 0.0002764019088988165, |
|
"loss": 0.124, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 0.00023576473183801758, |
|
"loss": 0.122, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 0.00019550390453030946, |
|
"loss": 0.1249, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 0.0001566838363176219, |
|
"loss": 0.1287, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 0.00012033084598233163, |
|
"loss": 0.1395, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 8.740602809470736e-05, |
|
"loss": 0.124, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 5.877984374768877e-05, |
|
"loss": 0.1315, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 3.520910744510819e-05, |
|
"loss": 0.1109, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 1.7316978560340647e-05, |
|
"loss": 0.1236, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 5.576486348011222e-06, |
|
"loss": 0.1205, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 2.980240718784277e-07, |
|
"loss": 0.1078, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 203, |
|
"total_flos": 8.131633707692851e+16, |
|
"train_loss": 0.16439640081574763, |
|
"train_runtime": 1233.0121, |
|
"train_samples_per_second": 2.638, |
|
"train_steps_per_second": 0.165 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 203, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 100, |
|
"total_flos": 8.131633707692851e+16, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|