|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.7317073170731707, |
|
"eval_steps": 500, |
|
"global_step": 30, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 4.9995000000000005e-05, |
|
"loss": 1.5986, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 4.999e-05, |
|
"loss": 2.5591, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 4.9985e-05, |
|
"loss": 1.8778, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 4.9980000000000006e-05, |
|
"loss": 2.6038, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 4.9975e-05, |
|
"loss": 1.7417, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 4.997e-05, |
|
"loss": 1.6722, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 4.9965e-05, |
|
"loss": 1.4006, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 4.996e-05, |
|
"loss": 1.2633, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 4.9955e-05, |
|
"loss": 1.1828, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 4.995e-05, |
|
"loss": 1.0802, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 4.9945000000000004e-05, |
|
"loss": 0.9983, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 4.9940000000000006e-05, |
|
"loss": 1.0225, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 4.9935e-05, |
|
"loss": 0.996, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 4.9930000000000005e-05, |
|
"loss": 0.9677, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 4.992500000000001e-05, |
|
"loss": 0.8863, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 4.992e-05, |
|
"loss": 0.925, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 4.9915e-05, |
|
"loss": 0.8541, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 4.991e-05, |
|
"loss": 0.8547, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 4.9905000000000004e-05, |
|
"loss": 0.8159, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 4.99e-05, |
|
"loss": 0.8186, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 4.9895e-05, |
|
"loss": 0.7936, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 4.9890000000000005e-05, |
|
"loss": 0.792, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 4.9885e-05, |
|
"loss": 0.7438, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 4.9880000000000004e-05, |
|
"loss": 0.7641, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 4.9875000000000006e-05, |
|
"loss": 0.7644, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 4.987e-05, |
|
"loss": 0.7188, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 4.9865e-05, |
|
"loss": 0.7475, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 4.986e-05, |
|
"loss": 0.729, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 4.9855e-05, |
|
"loss": 0.719, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 4.9850000000000006e-05, |
|
"loss": 0.69, |
|
"step": 30 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 10000, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 244, |
|
"save_steps": 10, |
|
"total_flos": 5157614830556160.0, |
|
"train_batch_size": 3584, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|