|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.6, |
|
"eval_steps": 500, |
|
"global_step": 200, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00019991228300988585, |
|
"loss": 2.1829, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00019964928592495045, |
|
"loss": 1.8983, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.0001992114701314478, |
|
"loss": 1.7871, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.0001985996037070505, |
|
"loss": 1.8482, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00019781476007338058, |
|
"loss": 1.731, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.0001968583161128631, |
|
"loss": 1.6797, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.00019573194975320673, |
|
"loss": 1.6694, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.00019443763702374812, |
|
"loss": 1.7493, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.00019297764858882514, |
|
"loss": 1.7823, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.0001913545457642601, |
|
"loss": 1.6518, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 0.0001895711760239413, |
|
"loss": 1.7334, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 0.00018763066800438636, |
|
"loss": 1.7565, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 0.00018553642601605068, |
|
"loss": 1.6493, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 0.00018329212407100994, |
|
"loss": 1.7431, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 0.00018090169943749476, |
|
"loss": 1.7561, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 0.000178369345732584, |
|
"loss": 1.6185, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 0.00017569950556517566, |
|
"loss": 1.6059, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 0.00017289686274214118, |
|
"loss": 1.772, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 0.00016996633405133655, |
|
"loss": 1.5847, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 0.00016691306063588583, |
|
"loss": 1.615, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 0.000163742398974869, |
|
"loss": 1.5706, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 0.0001604599114862375, |
|
"loss": 1.6997, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 0.0001570713567684432, |
|
"loss": 1.5529, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 0.00015358267949789966, |
|
"loss": 1.6631, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.00015000000000000001, |
|
"loss": 1.7483, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 0.00014632960351198618, |
|
"loss": 1.708, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 0.00014257792915650728, |
|
"loss": 1.6979, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 0.0001387515586452103, |
|
"loss": 1.53, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 0.00013485720473218154, |
|
"loss": 1.6821, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 0.00013090169943749476, |
|
"loss": 1.7208, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 0.00012689198206152657, |
|
"loss": 1.6841, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 0.00012283508701106557, |
|
"loss": 1.544, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 0.00011873813145857249, |
|
"loss": 1.5851, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 0.00011460830285624118, |
|
"loss": 1.56, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 0.00011045284632676536, |
|
"loss": 1.5691, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 0.00010627905195293135, |
|
"loss": 1.5201, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 0.0001020942419883357, |
|
"loss": 1.5098, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 9.790575801166432e-05, |
|
"loss": 1.5805, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 9.372094804706867e-05, |
|
"loss": 1.6742, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 8.954715367323468e-05, |
|
"loss": 1.5656, |
|
"step": 200 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 375, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 100, |
|
"total_flos": 2.33056963362816e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|