|
{ |
|
"best_metric": 0.6620756983757019, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-50", |
|
"epoch": 0.7299270072992701, |
|
"eval_steps": 50, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.014598540145985401, |
|
"grad_norm": 33.662986755371094, |
|
"learning_rate": 1e-05, |
|
"loss": 6.8288, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.014598540145985401, |
|
"eval_loss": 6.846549987792969, |
|
"eval_runtime": 8.1835, |
|
"eval_samples_per_second": 14.053, |
|
"eval_steps_per_second": 3.544, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.029197080291970802, |
|
"grad_norm": 38.6097526550293, |
|
"learning_rate": 2e-05, |
|
"loss": 6.8553, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.043795620437956206, |
|
"grad_norm": 39.742008209228516, |
|
"learning_rate": 3e-05, |
|
"loss": 6.6102, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.058394160583941604, |
|
"grad_norm": 35.009727478027344, |
|
"learning_rate": 4e-05, |
|
"loss": 5.16, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.072992700729927, |
|
"grad_norm": 21.071718215942383, |
|
"learning_rate": 5e-05, |
|
"loss": 2.973, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.08759124087591241, |
|
"grad_norm": 11.949044227600098, |
|
"learning_rate": 6e-05, |
|
"loss": 1.5887, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.10218978102189781, |
|
"grad_norm": 3.4320690631866455, |
|
"learning_rate": 7e-05, |
|
"loss": 0.8089, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.11678832116788321, |
|
"grad_norm": 4.1433844566345215, |
|
"learning_rate": 8e-05, |
|
"loss": 0.6951, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.13138686131386862, |
|
"grad_norm": 2.0591485500335693, |
|
"learning_rate": 9e-05, |
|
"loss": 0.6693, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.145985401459854, |
|
"grad_norm": 0.7576547265052795, |
|
"learning_rate": 0.0001, |
|
"loss": 0.6251, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.16058394160583941, |
|
"grad_norm": 8.802155494689941, |
|
"learning_rate": 9.999316524962345e-05, |
|
"loss": 1.0039, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.17518248175182483, |
|
"grad_norm": 2.171154737472534, |
|
"learning_rate": 9.997266286704631e-05, |
|
"loss": 0.7494, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.1897810218978102, |
|
"grad_norm": 34.5106201171875, |
|
"learning_rate": 9.993849845741524e-05, |
|
"loss": 0.9494, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.20437956204379562, |
|
"grad_norm": 0.998836874961853, |
|
"learning_rate": 9.989068136093873e-05, |
|
"loss": 0.6674, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.21897810218978103, |
|
"grad_norm": 0.34883710741996765, |
|
"learning_rate": 9.98292246503335e-05, |
|
"loss": 0.6382, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.23357664233576642, |
|
"grad_norm": 2.8341825008392334, |
|
"learning_rate": 9.975414512725057e-05, |
|
"loss": 0.7636, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.24817518248175183, |
|
"grad_norm": 1.3019286394119263, |
|
"learning_rate": 9.966546331768191e-05, |
|
"loss": 0.7001, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.26277372262773724, |
|
"grad_norm": 0.6097630262374878, |
|
"learning_rate": 9.956320346634876e-05, |
|
"loss": 0.6695, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.2773722627737226, |
|
"grad_norm": 0.5195863842964172, |
|
"learning_rate": 9.944739353007344e-05, |
|
"loss": 0.6628, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.291970802919708, |
|
"grad_norm": 1.1216007471084595, |
|
"learning_rate": 9.931806517013612e-05, |
|
"loss": 0.6775, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.30656934306569344, |
|
"grad_norm": 1.6819016933441162, |
|
"learning_rate": 9.917525374361912e-05, |
|
"loss": 0.7628, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.32116788321167883, |
|
"grad_norm": 0.5767019391059875, |
|
"learning_rate": 9.901899829374047e-05, |
|
"loss": 0.6679, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.3357664233576642, |
|
"grad_norm": 0.6141683459281921, |
|
"learning_rate": 9.884934153917997e-05, |
|
"loss": 0.6266, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.35036496350364965, |
|
"grad_norm": 0.6812053918838501, |
|
"learning_rate": 9.86663298624003e-05, |
|
"loss": 0.5757, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.36496350364963503, |
|
"grad_norm": 3.8009650707244873, |
|
"learning_rate": 9.847001329696653e-05, |
|
"loss": 0.7547, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.3795620437956204, |
|
"grad_norm": 5.604429244995117, |
|
"learning_rate": 9.826044551386744e-05, |
|
"loss": 1.0209, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.39416058394160586, |
|
"grad_norm": 2.7158730030059814, |
|
"learning_rate": 9.803768380684242e-05, |
|
"loss": 0.7527, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.40875912408759124, |
|
"grad_norm": 1.0342605113983154, |
|
"learning_rate": 9.780178907671789e-05, |
|
"loss": 0.7118, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.4233576642335766, |
|
"grad_norm": 0.5667628049850464, |
|
"learning_rate": 9.755282581475769e-05, |
|
"loss": 0.6418, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.43795620437956206, |
|
"grad_norm": 0.42152413725852966, |
|
"learning_rate": 9.729086208503174e-05, |
|
"loss": 0.6735, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.45255474452554745, |
|
"grad_norm": 1.0017098188400269, |
|
"learning_rate": 9.701596950580806e-05, |
|
"loss": 0.7253, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.46715328467153283, |
|
"grad_norm": 0.56270432472229, |
|
"learning_rate": 9.672822322997305e-05, |
|
"loss": 0.6713, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.48175182481751827, |
|
"grad_norm": 0.8998551368713379, |
|
"learning_rate": 9.642770192448536e-05, |
|
"loss": 0.6585, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.49635036496350365, |
|
"grad_norm": 0.5632476806640625, |
|
"learning_rate": 9.611448774886924e-05, |
|
"loss": 0.7139, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.5109489051094891, |
|
"grad_norm": 0.6208569407463074, |
|
"learning_rate": 9.578866633275288e-05, |
|
"loss": 0.6542, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.5255474452554745, |
|
"grad_norm": 0.9806542992591858, |
|
"learning_rate": 9.545032675245813e-05, |
|
"loss": 0.674, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.5401459854014599, |
|
"grad_norm": 0.3306947946548462, |
|
"learning_rate": 9.509956150664796e-05, |
|
"loss": 0.6498, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.5547445255474452, |
|
"grad_norm": 0.32137709856033325, |
|
"learning_rate": 9.473646649103818e-05, |
|
"loss": 0.5396, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.5693430656934306, |
|
"grad_norm": 0.6273882985115051, |
|
"learning_rate": 9.43611409721806e-05, |
|
"loss": 0.6116, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.583941605839416, |
|
"grad_norm": 1.3096363544464111, |
|
"learning_rate": 9.397368756032445e-05, |
|
"loss": 0.7802, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.5985401459854015, |
|
"grad_norm": 0.6243460774421692, |
|
"learning_rate": 9.357421218136386e-05, |
|
"loss": 0.6692, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.6131386861313869, |
|
"grad_norm": 0.8591530323028564, |
|
"learning_rate": 9.316282404787871e-05, |
|
"loss": 0.725, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.6277372262773723, |
|
"grad_norm": 0.5638594627380371, |
|
"learning_rate": 9.273963562927695e-05, |
|
"loss": 0.6857, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.6423357664233577, |
|
"grad_norm": 0.8377383947372437, |
|
"learning_rate": 9.230476262104677e-05, |
|
"loss": 0.6591, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.656934306569343, |
|
"grad_norm": 0.6511130928993225, |
|
"learning_rate": 9.185832391312644e-05, |
|
"loss": 0.7041, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.6715328467153284, |
|
"grad_norm": 0.9163225889205933, |
|
"learning_rate": 9.140044155740101e-05, |
|
"loss": 0.6581, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.6861313868613139, |
|
"grad_norm": 0.71990567445755, |
|
"learning_rate": 9.093124073433463e-05, |
|
"loss": 0.6998, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.7007299270072993, |
|
"grad_norm": 0.4144147038459778, |
|
"learning_rate": 9.045084971874738e-05, |
|
"loss": 0.7007, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.7153284671532847, |
|
"grad_norm": 0.35297536849975586, |
|
"learning_rate": 8.995939984474624e-05, |
|
"loss": 0.6089, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.7299270072992701, |
|
"grad_norm": 0.28604188561439514, |
|
"learning_rate": 8.945702546981969e-05, |
|
"loss": 0.674, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.7299270072992701, |
|
"eval_loss": 0.6620756983757019, |
|
"eval_runtime": 8.3706, |
|
"eval_samples_per_second": 13.739, |
|
"eval_steps_per_second": 3.465, |
|
"step": 50 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 200, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 50, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 5, |
|
"early_stopping_threshold": 0.0 |
|
}, |
|
"attributes": { |
|
"early_stopping_patience_counter": 0 |
|
} |
|
}, |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 6.72883802112e+16, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|