|
{ |
|
"best_metric": NaN, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-50", |
|
"epoch": 0.08321198252548367, |
|
"eval_steps": 50, |
|
"global_step": 75, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0011094931003397823, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-06, |
|
"loss": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0011094931003397823, |
|
"eval_loss": NaN, |
|
"eval_runtime": 421.2297, |
|
"eval_samples_per_second": 7.207, |
|
"eval_steps_per_second": 1.802, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0022189862006795646, |
|
"grad_norm": NaN, |
|
"learning_rate": 1e-05, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0033284793010193467, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.5e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.004437972401359129, |
|
"grad_norm": NaN, |
|
"learning_rate": 2e-05, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.005547465501698911, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.5e-05, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.006656958602038693, |
|
"grad_norm": NaN, |
|
"learning_rate": 3e-05, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.007766451702378475, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.5e-05, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.008875944802718258, |
|
"grad_norm": NaN, |
|
"learning_rate": 4e-05, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.00998543790305804, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.5e-05, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.011094931003397823, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.012204424103737605, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.500000000000001e-05, |
|
"loss": 0.0, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.013313917204077387, |
|
"grad_norm": NaN, |
|
"learning_rate": 6e-05, |
|
"loss": 0.0, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.01442341030441717, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.500000000000001e-05, |
|
"loss": 0.0, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.01553290340475695, |
|
"grad_norm": NaN, |
|
"learning_rate": 7e-05, |
|
"loss": 0.0, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.016642396505096736, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.017751889605436517, |
|
"grad_norm": NaN, |
|
"learning_rate": 8e-05, |
|
"loss": 0.0, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.018861382705776298, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.5e-05, |
|
"loss": 0.0, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.01997087580611608, |
|
"grad_norm": NaN, |
|
"learning_rate": 9e-05, |
|
"loss": 0.0, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.021080368906455864, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.5e-05, |
|
"loss": 0.0, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.022189862006795645, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.023299355107135426, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.991845519630678e-05, |
|
"loss": 0.0, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.02440884820747521, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.967408676742751e-05, |
|
"loss": 0.0, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.025518341307814992, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.926769179238466e-05, |
|
"loss": 0.0, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.026627834408154773, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.870059584711668e-05, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.027737327508494558, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.797464868072488e-05, |
|
"loss": 0.0, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.02884682060883434, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.709221818197624e-05, |
|
"loss": 0.0, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.02995631370917412, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.60561826557425e-05, |
|
"loss": 0.0, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.0310658068095139, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.486992143456792e-05, |
|
"loss": 0.0, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.03217529990985368, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.353730385598887e-05, |
|
"loss": 0.0, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.03328479301019347, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.206267664155907e-05, |
|
"loss": 0.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.03439428611053325, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.045084971874738e-05, |
|
"loss": 0.0, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.035503779210873034, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.870708053195413e-05, |
|
"loss": 0.0, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.036613272311212815, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.683705689382024e-05, |
|
"loss": 0.0, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.037722765411552596, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.484687843276469e-05, |
|
"loss": 0.0, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.03883225851189238, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.274303669726426e-05, |
|
"loss": 0.0, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.03994175161223216, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.053239398177191e-05, |
|
"loss": 0.0, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.041051244712571947, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.822216094333847e-05, |
|
"loss": 0.0, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.04216073781291173, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.58198730819481e-05, |
|
"loss": 0.0, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.04327023091325151, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.333336616128369e-05, |
|
"loss": 0.0, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.04437972401359129, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.077075065009433e-05, |
|
"loss": 0.0, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.04548921711393107, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.814038526753205e-05, |
|
"loss": 0.0, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.04659871021427085, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.545084971874738e-05, |
|
"loss": 0.0, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.04770820331461064, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.271091670967436e-05, |
|
"loss": 0.0, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.04881769641495042, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.992952333228728e-05, |
|
"loss": 0.0, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.0499271895152902, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.7115741913664264e-05, |
|
"loss": 0.0, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.051036682615629984, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.427875042394199e-05, |
|
"loss": 0.0, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.052146175715969766, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.142780253968481e-05, |
|
"loss": 0.0, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.05325566881630955, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.85721974603152e-05, |
|
"loss": 0.0, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.05436516191664933, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.5721249576058027e-05, |
|
"loss": 0.0, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.055474655016989116, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.288425808633575e-05, |
|
"loss": 0.0, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.055474655016989116, |
|
"eval_loss": NaN, |
|
"eval_runtime": 421.51, |
|
"eval_samples_per_second": 7.203, |
|
"eval_steps_per_second": 1.801, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.0565841481173289, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.007047666771274e-05, |
|
"loss": 0.0, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 0.05769364121766868, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.728908329032567e-05, |
|
"loss": 0.0, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 0.05880313431800846, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.4549150281252636e-05, |
|
"loss": 0.0, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 0.05991262741834824, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.1859614732467954e-05, |
|
"loss": 0.0, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 0.06102212051868802, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.9229249349905684e-05, |
|
"loss": 0.0, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.0621316136190278, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.6666633838716314e-05, |
|
"loss": 0.0, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 0.06324110671936758, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.418012691805191e-05, |
|
"loss": 0.0, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 0.06435059981970737, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.1777839056661554e-05, |
|
"loss": 0.0, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 0.06546009292004715, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.946760601822809e-05, |
|
"loss": 0.0, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 0.06656958602038694, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.725696330273575e-05, |
|
"loss": 0.0, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.06767907912072672, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.5153121567235335e-05, |
|
"loss": 0.0, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 0.0687885722210665, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.3162943106179749e-05, |
|
"loss": 0.0, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 0.06989806532140629, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.1292919468045877e-05, |
|
"loss": 0.0, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 0.07100755842174607, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.549150281252633e-06, |
|
"loss": 0.0, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 0.07211705152208585, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.937323358440935e-06, |
|
"loss": 0.0, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.07322654462242563, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.462696144011149e-06, |
|
"loss": 0.0, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 0.07433603772276541, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.13007856543209e-06, |
|
"loss": 0.0, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 0.07544553082310519, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.9438173442575e-06, |
|
"loss": 0.0, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 0.07655502392344497, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.9077818180237693e-06, |
|
"loss": 0.0, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 0.07766451702378475, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.0253513192751373e-06, |
|
"loss": 0.0, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.07877401012412454, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.2994041528833266e-06, |
|
"loss": 0.0, |
|
"step": 71 |
|
}, |
|
{ |
|
"epoch": 0.07988350322446432, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.323082076153509e-07, |
|
"loss": 0.0, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 0.08099299632480411, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.2591323257248893e-07, |
|
"loss": 0.0, |
|
"step": 73 |
|
}, |
|
{ |
|
"epoch": 0.08210248942514389, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.15448036932176e-08, |
|
"loss": 0.0, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 0.08321198252548367, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 0.0, |
|
"step": 75 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 75, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"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": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 4.279884942881587e+17, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|