|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.997867803837953, |
|
"eval_steps": 500, |
|
"global_step": 234, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0042643923240938165, |
|
"grad_norm": 8.194656057108729, |
|
"learning_rate": 8.333333333333333e-07, |
|
"loss": 1.2023, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.021321961620469083, |
|
"grad_norm": 10.77971864716952, |
|
"learning_rate": 4.166666666666667e-06, |
|
"loss": 1.1792, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.042643923240938165, |
|
"grad_norm": 2.886731531857203, |
|
"learning_rate": 8.333333333333334e-06, |
|
"loss": 1.0145, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.06396588486140725, |
|
"grad_norm": 0.8215086941910178, |
|
"learning_rate": 1.25e-05, |
|
"loss": 0.8758, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.08528784648187633, |
|
"grad_norm": 0.7913315554101064, |
|
"learning_rate": 1.6666666666666667e-05, |
|
"loss": 0.8588, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.10660980810234541, |
|
"grad_norm": 0.614308915294473, |
|
"learning_rate": 1.9998881018102735e-05, |
|
"loss": 0.853, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.1279317697228145, |
|
"grad_norm": 0.6225275949627647, |
|
"learning_rate": 1.9959742939952393e-05, |
|
"loss": 0.8394, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.14925373134328357, |
|
"grad_norm": 0.5982177518981041, |
|
"learning_rate": 1.9864905939235215e-05, |
|
"loss": 0.8203, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.17057569296375266, |
|
"grad_norm": 0.6070332077049073, |
|
"learning_rate": 1.9714900382928674e-05, |
|
"loss": 0.8166, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.19189765458422176, |
|
"grad_norm": 0.5825095419662176, |
|
"learning_rate": 1.9510565162951538e-05, |
|
"loss": 0.8066, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.21321961620469082, |
|
"grad_norm": 0.5967686246799795, |
|
"learning_rate": 1.9253043004739967e-05, |
|
"loss": 0.8143, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.2345415778251599, |
|
"grad_norm": 0.6193022162624499, |
|
"learning_rate": 1.8943774076663372e-05, |
|
"loss": 0.818, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.255863539445629, |
|
"grad_norm": 0.6292049515341538, |
|
"learning_rate": 1.8584487936018663e-05, |
|
"loss": 0.792, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.2771855010660981, |
|
"grad_norm": 0.6254465919572924, |
|
"learning_rate": 1.8177193856644315e-05, |
|
"loss": 0.7949, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.29850746268656714, |
|
"grad_norm": 0.586054382503889, |
|
"learning_rate": 1.7724169592245996e-05, |
|
"loss": 0.7798, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.31982942430703626, |
|
"grad_norm": 0.5758542373515736, |
|
"learning_rate": 1.7227948638273918e-05, |
|
"loss": 0.8047, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.3411513859275053, |
|
"grad_norm": 0.5756093933789175, |
|
"learning_rate": 1.6691306063588583e-05, |
|
"loss": 0.7905, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.3624733475479744, |
|
"grad_norm": 0.5975842502205215, |
|
"learning_rate": 1.6117242991150064e-05, |
|
"loss": 0.8063, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.3837953091684435, |
|
"grad_norm": 0.5873177139076834, |
|
"learning_rate": 1.5508969814521026e-05, |
|
"loss": 0.7962, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.4051172707889126, |
|
"grad_norm": 0.650246386643556, |
|
"learning_rate": 1.4869888244043674e-05, |
|
"loss": 0.7744, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.42643923240938164, |
|
"grad_norm": 0.5412117323958047, |
|
"learning_rate": 1.4203572283095657e-05, |
|
"loss": 0.7845, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.44776119402985076, |
|
"grad_norm": 0.5870347809678912, |
|
"learning_rate": 1.3513748240813429e-05, |
|
"loss": 0.778, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.4690831556503198, |
|
"grad_norm": 0.5649472553688369, |
|
"learning_rate": 1.2804273893060028e-05, |
|
"loss": 0.7677, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.4904051172707889, |
|
"grad_norm": 0.5632029804905192, |
|
"learning_rate": 1.2079116908177592e-05, |
|
"loss": 0.7788, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.511727078891258, |
|
"grad_norm": 0.5929487798956572, |
|
"learning_rate": 1.1342332658176556e-05, |
|
"loss": 0.7828, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.5330490405117271, |
|
"grad_norm": 0.6146751355552545, |
|
"learning_rate": 1.0598041539450344e-05, |
|
"loss": 0.7832, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.5543710021321961, |
|
"grad_norm": 0.5551970446057425, |
|
"learning_rate": 9.850405929847367e-06, |
|
"loss": 0.7701, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.5756929637526652, |
|
"grad_norm": 0.5917048776473024, |
|
"learning_rate": 9.103606910965666e-06, |
|
"loss": 0.775, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.5970149253731343, |
|
"grad_norm": 0.697971580891398, |
|
"learning_rate": 8.361820885848623e-06, |
|
"loss": 0.7749, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.6183368869936035, |
|
"grad_norm": 0.5560422629529225, |
|
"learning_rate": 7.629196222845027e-06, |
|
"loss": 0.7875, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 0.6396588486140725, |
|
"grad_norm": 0.5781710369695544, |
|
"learning_rate": 6.909830056250527e-06, |
|
"loss": 0.7782, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.6609808102345416, |
|
"grad_norm": 0.5776458863179287, |
|
"learning_rate": 6.207745373470717e-06, |
|
"loss": 0.7975, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 0.6823027718550106, |
|
"grad_norm": 0.5430180144353439, |
|
"learning_rate": 5.526868516843673e-06, |
|
"loss": 0.7887, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.7036247334754797, |
|
"grad_norm": 0.5507827393351278, |
|
"learning_rate": 4.87100722594094e-06, |
|
"loss": 0.7603, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 0.7249466950959488, |
|
"grad_norm": 0.5964681917261669, |
|
"learning_rate": 4.2438293431432665e-06, |
|
"loss": 0.7726, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.746268656716418, |
|
"grad_norm": 0.5612954365815341, |
|
"learning_rate": 3.6488423015782128e-06, |
|
"loss": 0.7699, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.767590618336887, |
|
"grad_norm": 0.5635912758786187, |
|
"learning_rate": 3.089373510131354e-06, |
|
"loss": 0.7687, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.7889125799573561, |
|
"grad_norm": 0.5547922610636185, |
|
"learning_rate": 2.5685517452260566e-06, |
|
"loss": 0.7616, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 0.8102345415778252, |
|
"grad_norm": 0.5776860776666484, |
|
"learning_rate": 2.08928965343659e-06, |
|
"loss": 0.7682, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.8315565031982942, |
|
"grad_norm": 0.5736928846399229, |
|
"learning_rate": 1.6542674627869738e-06, |
|
"loss": 0.7533, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 0.8528784648187633, |
|
"grad_norm": 0.628940916989025, |
|
"learning_rate": 1.2659179938287035e-06, |
|
"loss": 0.755, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.8742004264392325, |
|
"grad_norm": 0.5704475746987567, |
|
"learning_rate": 9.264130543213512e-07, |
|
"loss": 0.767, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 0.8955223880597015, |
|
"grad_norm": 0.5190056488397052, |
|
"learning_rate": 6.37651293602628e-07, |
|
"loss": 0.7482, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.9168443496801706, |
|
"grad_norm": 0.5642774861602795, |
|
"learning_rate": 4.012475845711106e-07, |
|
"loss": 0.7618, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 0.9381663113006397, |
|
"grad_norm": 0.5677038459228019, |
|
"learning_rate": 2.1852399266194312e-07, |
|
"loss": 0.7857, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.9594882729211087, |
|
"grad_norm": 0.59952294696821, |
|
"learning_rate": 9.0502382320653e-08, |
|
"loss": 0.7632, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.9808102345415778, |
|
"grad_norm": 0.5424542597626352, |
|
"learning_rate": 1.7898702322648453e-08, |
|
"loss": 0.7553, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.997867803837953, |
|
"eval_loss": 0.7915695905685425, |
|
"eval_runtime": 9.666, |
|
"eval_samples_per_second": 51.728, |
|
"eval_steps_per_second": 1.655, |
|
"step": 234 |
|
}, |
|
{ |
|
"epoch": 0.997867803837953, |
|
"step": 234, |
|
"total_flos": 33846814310400.0, |
|
"train_loss": 0.801683344392695, |
|
"train_runtime": 2309.6554, |
|
"train_samples_per_second": 12.989, |
|
"train_steps_per_second": 0.101 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 234, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 100, |
|
"total_flos": 33846814310400.0, |
|
"train_batch_size": 16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|