|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 6.0, |
|
"eval_steps": 500, |
|
"global_step": 60, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 1e-05, |
|
"loss": 0.3716, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 2e-05, |
|
"loss": 0.3104, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 1.998533413851124e-05, |
|
"loss": 0.1913, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 1.9941379571543597e-05, |
|
"loss": 0.532, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 1.9868265225415263e-05, |
|
"loss": 0.2109, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 1.976620555710087e-05, |
|
"loss": 0.1733, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 1.963549992519223e-05, |
|
"loss": 0.1951, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 1.9476531711828027e-05, |
|
"loss": 0.1818, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 1.9289767198167918e-05, |
|
"loss": 0.1708, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 1.9075754196709574e-05, |
|
"loss": 0.1764, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 1.883512044446023e-05, |
|
"loss": 0.167, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 1.8568571761675893e-05, |
|
"loss": 0.1697, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 1.827688998156891e-05, |
|
"loss": 0.1735, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 1.796093065705644e-05, |
|
"loss": 0.1555, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 1.7621620551276366e-05, |
|
"loss": 0.1552, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 1.725995491923131e-05, |
|
"loss": 0.1587, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 1.6876994588534234e-05, |
|
"loss": 0.1705, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 1.647386284781828e-05, |
|
"loss": 0.1467, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 1.6051742151937655e-05, |
|
"loss": 0.1431, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 1.5611870653623826e-05, |
|
"loss": 0.1644, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 2.1, |
|
"learning_rate": 1.515553857177022e-05, |
|
"loss": 0.1378, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 2.2, |
|
"learning_rate": 1.4684084406997903e-05, |
|
"loss": 0.1246, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 2.3, |
|
"learning_rate": 1.4198891015602648e-05, |
|
"loss": 0.1191, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 1.3701381553399147e-05, |
|
"loss": 0.1202, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"learning_rate": 1.31930153013598e-05, |
|
"loss": 0.0963, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 2.6, |
|
"learning_rate": 1.2675283385292212e-05, |
|
"loss": 0.126, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 2.7, |
|
"learning_rate": 1.2149704402110243e-05, |
|
"loss": 0.1219, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 2.8, |
|
"learning_rate": 1.161781996552765e-05, |
|
"loss": 0.1133, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 2.9, |
|
"learning_rate": 1.1081190184239418e-05, |
|
"loss": 0.1106, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 1.0541389085854177e-05, |
|
"loss": 0.0954, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 3.1, |
|
"learning_rate": 1e-05, |
|
"loss": 0.1003, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"learning_rate": 9.458610914145826e-06, |
|
"loss": 0.0885, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 3.3, |
|
"learning_rate": 8.918809815760585e-06, |
|
"loss": 0.0831, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 3.4, |
|
"learning_rate": 8.382180034472353e-06, |
|
"loss": 0.0771, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 3.5, |
|
"learning_rate": 7.85029559788976e-06, |
|
"loss": 0.0733, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 3.6, |
|
"learning_rate": 7.324716614707794e-06, |
|
"loss": 0.0789, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 3.7, |
|
"learning_rate": 6.806984698640202e-06, |
|
"loss": 0.0821, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 3.8, |
|
"learning_rate": 6.298618446600856e-06, |
|
"loss": 0.0753, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 3.9, |
|
"learning_rate": 5.801108984397355e-06, |
|
"loss": 0.0831, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 5.3159155930021e-06, |
|
"loss": 0.055, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 4.1, |
|
"learning_rate": 4.844461428229782e-06, |
|
"loss": 0.0485, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 4.2, |
|
"learning_rate": 4.388129346376177e-06, |
|
"loss": 0.0493, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 4.3, |
|
"learning_rate": 3.948257848062351e-06, |
|
"loss": 0.0645, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 4.4, |
|
"learning_rate": 3.5261371521817247e-06, |
|
"loss": 0.0503, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 4.5, |
|
"learning_rate": 3.123005411465766e-06, |
|
"loss": 0.0545, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 4.6, |
|
"learning_rate": 2.740045080768694e-06, |
|
"loss": 0.0412, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 4.7, |
|
"learning_rate": 2.3783794487236367e-06, |
|
"loss": 0.0461, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 4.8, |
|
"learning_rate": 2.0390693429435626e-06, |
|
"loss": 0.0426, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 4.9, |
|
"learning_rate": 1.7231100184310955e-06, |
|
"loss": 0.0699, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 1.4314282383241097e-06, |
|
"loss": 0.0374, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 5.1, |
|
"learning_rate": 1.1648795555397719e-06, |
|
"loss": 0.0304, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 5.2, |
|
"learning_rate": 9.242458032904311e-07, |
|
"loss": 0.0323, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 5.3, |
|
"learning_rate": 7.102328018320859e-07, |
|
"loss": 0.028, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 5.4, |
|
"learning_rate": 5.234682881719766e-07, |
|
"loss": 0.0292, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 5.5, |
|
"learning_rate": 3.645000748077709e-07, |
|
"loss": 0.0253, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 5.6, |
|
"learning_rate": 2.3379444289913344e-07, |
|
"loss": 0.0272, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 5.7, |
|
"learning_rate": 1.317347745847386e-07, |
|
"loss": 0.0313, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 5.8, |
|
"learning_rate": 5.862042845640403e-08, |
|
"loss": 0.0281, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 5.9, |
|
"learning_rate": 1.4665861488761813e-08, |
|
"loss": 0.0308, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"learning_rate": 0.0, |
|
"loss": 0.0297, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"step": 60, |
|
"total_flos": 1423268904960.0, |
|
"train_loss": 0.11460787455240885, |
|
"train_runtime": 682.0096, |
|
"train_samples_per_second": 5.217, |
|
"train_steps_per_second": 0.088 |
|
} |
|
], |
|
"logging_steps": 1.0, |
|
"max_steps": 60, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 6, |
|
"save_steps": 111, |
|
"total_flos": 1423268904960.0, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|