|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.0, |
|
"eval_steps": 500, |
|
"global_step": 250, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00019980267284282717, |
|
"loss": 1.8035, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.0001992114701314478, |
|
"loss": 1.7043, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.0001982287250728689, |
|
"loss": 1.5984, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.0001968583161128631, |
|
"loss": 1.6024, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00019510565162951537, |
|
"loss": 1.4862, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.00019297764858882514, |
|
"loss": 1.5183, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.00019048270524660196, |
|
"loss": 1.396, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.00018763066800438636, |
|
"loss": 1.5583, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.00018443279255020152, |
|
"loss": 1.4023, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.00018090169943749476, |
|
"loss": 1.4386, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 0.00017705132427757895, |
|
"loss": 1.4218, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 0.00017289686274214118, |
|
"loss": 1.4874, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 0.00016845471059286887, |
|
"loss": 1.4279, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 0.000163742398974869, |
|
"loss": 1.4142, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 0.00015877852522924732, |
|
"loss": 1.3489, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 0.00015358267949789966, |
|
"loss": 1.4629, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 0.00014817536741017152, |
|
"loss": 1.3914, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 0.00014257792915650728, |
|
"loss": 1.407, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 0.00013681245526846783, |
|
"loss": 1.3214, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 0.00013090169943749476, |
|
"loss": 1.5119, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 0.0001248689887164855, |
|
"loss": 1.431, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 0.00011873813145857249, |
|
"loss": 1.3285, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 0.00011253332335643043, |
|
"loss": 1.486, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 0.00010627905195293135, |
|
"loss": 1.3244, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4051, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 9.372094804706867e-05, |
|
"loss": 1.3832, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 8.746667664356956e-05, |
|
"loss": 1.3841, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 8.126186854142752e-05, |
|
"loss": 1.4901, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 7.513101128351454e-05, |
|
"loss": 1.3792, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 6.909830056250527e-05, |
|
"loss": 1.3908, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 6.318754473153221e-05, |
|
"loss": 1.3803, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 5.7422070843492734e-05, |
|
"loss": 1.3799, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 5.182463258982846e-05, |
|
"loss": 1.4348, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 4.6417320502100316e-05, |
|
"loss": 1.4014, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 4.12214747707527e-05, |
|
"loss": 1.3101, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 3.6257601025131026e-05, |
|
"loss": 1.3661, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 3.154528940713113e-05, |
|
"loss": 1.3185, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 2.7103137257858868e-05, |
|
"loss": 1.348, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 2.2948675722421086e-05, |
|
"loss": 1.4324, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 1.9098300562505266e-05, |
|
"loss": 1.4251, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 1.5567207449798515e-05, |
|
"loss": 1.2895, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 1.2369331995613665e-05, |
|
"loss": 1.2964, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 9.517294753398064e-06, |
|
"loss": 1.4526, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 7.022351411174866e-06, |
|
"loss": 1.4139, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 4.8943483704846475e-06, |
|
"loss": 1.3556, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 3.1416838871368924e-06, |
|
"loss": 1.3191, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 1.771274927131139e-06, |
|
"loss": 1.4144, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 7.885298685522235e-07, |
|
"loss": 1.4032, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 1.973271571728441e-07, |
|
"loss": 1.3548, |
|
"step": 245 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 0.0, |
|
"loss": 1.3039, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"step": 250, |
|
"total_flos": 3.5347307484020736e+16, |
|
"train_loss": 1.422109573364258, |
|
"train_runtime": 369.56, |
|
"train_samples_per_second": 10.824, |
|
"train_steps_per_second": 0.676 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 250, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 100, |
|
"total_flos": 3.5347307484020736e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|