|
{ |
|
"best_metric": NaN, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-25", |
|
"epoch": 0.06555764975825616, |
|
"eval_steps": 25, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0013111529951651234, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0013111529951651234, |
|
"eval_loss": NaN, |
|
"eval_runtime": 56.312, |
|
"eval_samples_per_second": 91.242, |
|
"eval_steps_per_second": 11.419, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0026223059903302467, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.00393345898549537, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.989294616193017e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0052446119806604935, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.957224306869053e-05, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.006555764975825617, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.903926402016153e-05, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.00786691797099074, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.829629131445342e-05, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.009178070966155864, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.73465064747553e-05, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.010489223961320987, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.619397662556435e-05, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.01180037695648611, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.484363707663442e-05, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.013111529951651234, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.330127018922194e-05, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.014422682946816357, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.157348061512727e-05, |
|
"loss": 0.0, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.01573383594198148, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.966766701456177e-05, |
|
"loss": 0.0, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.017044988937146604, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.759199037394887e-05, |
|
"loss": 0.0, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.018356141932311727, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 0.0, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.01966729492747685, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.296729075500344e-05, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.020978447922641974, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.043807145043604e-05, |
|
"loss": 0.0, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.022289600917807097, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.777851165098012e-05, |
|
"loss": 0.0, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.02360075391297222, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 0.0, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.024911906908137344, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.211443451095007e-05, |
|
"loss": 0.0, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.026223059903302467, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.91341716182545e-05, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.02753421289846759, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.607197326515808e-05, |
|
"loss": 0.0, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.028845365893632714, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.294095225512603e-05, |
|
"loss": 0.0, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.030156518888797838, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.9754516100806423e-05, |
|
"loss": 0.0, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.03146767188396296, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.6526309611002594e-05, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.03277882487912808, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.327015646150716e-05, |
|
"loss": 0.0, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.03277882487912808, |
|
"eval_loss": NaN, |
|
"eval_runtime": 55.857, |
|
"eval_samples_per_second": 91.985, |
|
"eval_steps_per_second": 11.512, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.03408997787429321, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.03540113086945833, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.6729843538492847e-05, |
|
"loss": 0.0, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.036712283864623454, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.347369038899744e-05, |
|
"loss": 0.0, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.038023436859788574, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.0245483899193595e-05, |
|
"loss": 0.0, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.0393345898549537, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.705904774487396e-05, |
|
"loss": 0.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.04064574285011882, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.392802673484193e-05, |
|
"loss": 0.0, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.04195689584528395, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.086582838174551e-05, |
|
"loss": 0.0, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.04326804884044907, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.7885565489049946e-05, |
|
"loss": 0.0, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.044579201835614195, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.500000000000001e-05, |
|
"loss": 0.0, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.045890354830779315, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.2221488349019903e-05, |
|
"loss": 0.0, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.04720150782594444, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.9561928549563968e-05, |
|
"loss": 0.0, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.04851266082110956, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.703270924499656e-05, |
|
"loss": 0.0, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.04982381381627469, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.4644660940672627e-05, |
|
"loss": 0.0, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.05113496681143981, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.2408009626051137e-05, |
|
"loss": 0.0, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.052446119806604935, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0332332985438248e-05, |
|
"loss": 0.0, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.053757272801770055, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.426519384872733e-06, |
|
"loss": 0.0, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.05506842579693518, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.698729810778065e-06, |
|
"loss": 0.0, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.0563795787921003, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.156362923365588e-06, |
|
"loss": 0.0, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.05769073178726543, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.8060233744356633e-06, |
|
"loss": 0.0, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.05900188478243055, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.653493525244721e-06, |
|
"loss": 0.0, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.060313037777595675, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.70370868554659e-06, |
|
"loss": 0.0, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.061624190772760795, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.607359798384785e-07, |
|
"loss": 0.0, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.06293534376792592, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.277569313094809e-07, |
|
"loss": 0.0, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.06424649676309105, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0705383806982606e-07, |
|
"loss": 0.0, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.06555764975825616, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 0.0, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.06555764975825616, |
|
"eval_loss": NaN, |
|
"eval_runtime": 55.8512, |
|
"eval_samples_per_second": 91.995, |
|
"eval_steps_per_second": 11.513, |
|
"step": 50 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 50, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 25, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 1, |
|
"early_stopping_threshold": 0.0 |
|
}, |
|
"attributes": { |
|
"early_stopping_patience_counter": 1 |
|
} |
|
}, |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.059536353886208e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|