|
{ |
|
"best_metric": 1.4605278968811035, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-25", |
|
"epoch": 0.39603960396039606, |
|
"eval_steps": 25, |
|
"global_step": 25, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.015841584158415842, |
|
"grad_norm": 116.92999267578125, |
|
"learning_rate": 5e-05, |
|
"loss": 3.8832, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.015841584158415842, |
|
"eval_loss": 4.637433052062988, |
|
"eval_runtime": 21.0893, |
|
"eval_samples_per_second": 20.2, |
|
"eval_steps_per_second": 2.561, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.031683168316831684, |
|
"grad_norm": 131.46612548828125, |
|
"learning_rate": 0.0001, |
|
"loss": 4.2831, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.047524752475247525, |
|
"grad_norm": 126.66082763671875, |
|
"learning_rate": 9.989294616193017e-05, |
|
"loss": 3.9478, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.06336633663366337, |
|
"grad_norm": 71.32660675048828, |
|
"learning_rate": 9.957224306869053e-05, |
|
"loss": 2.8603, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.07920792079207921, |
|
"grad_norm": 54.61603546142578, |
|
"learning_rate": 9.903926402016153e-05, |
|
"loss": 2.356, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.09504950495049505, |
|
"grad_norm": 35.58620834350586, |
|
"learning_rate": 9.829629131445342e-05, |
|
"loss": 2.1134, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.11089108910891089, |
|
"grad_norm": 20.115825653076172, |
|
"learning_rate": 9.73465064747553e-05, |
|
"loss": 1.7411, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.12673267326732673, |
|
"grad_norm": 11.28286075592041, |
|
"learning_rate": 9.619397662556435e-05, |
|
"loss": 1.5849, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.14257425742574256, |
|
"grad_norm": 11.435465812683105, |
|
"learning_rate": 9.484363707663442e-05, |
|
"loss": 1.6331, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.15841584158415842, |
|
"grad_norm": 9.596415519714355, |
|
"learning_rate": 9.330127018922194e-05, |
|
"loss": 1.4195, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.17425742574257425, |
|
"grad_norm": 7.852958679199219, |
|
"learning_rate": 9.157348061512727e-05, |
|
"loss": 1.4109, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.1900990099009901, |
|
"grad_norm": 8.66879653930664, |
|
"learning_rate": 8.966766701456177e-05, |
|
"loss": 1.5046, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.20594059405940593, |
|
"grad_norm": 16.069547653198242, |
|
"learning_rate": 8.759199037394887e-05, |
|
"loss": 1.7543, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.22178217821782178, |
|
"grad_norm": 24.858217239379883, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 1.9357, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.2376237623762376, |
|
"grad_norm": 13.183930397033691, |
|
"learning_rate": 8.296729075500344e-05, |
|
"loss": 1.6216, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.25346534653465347, |
|
"grad_norm": 9.433813095092773, |
|
"learning_rate": 8.043807145043604e-05, |
|
"loss": 1.4612, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.2693069306930693, |
|
"grad_norm": 6.984700679779053, |
|
"learning_rate": 7.777851165098012e-05, |
|
"loss": 1.4995, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.2851485148514851, |
|
"grad_norm": 6.329092979431152, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 1.3562, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.300990099009901, |
|
"grad_norm": 7.003969192504883, |
|
"learning_rate": 7.211443451095007e-05, |
|
"loss": 1.2849, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.31683168316831684, |
|
"grad_norm": 5.927999973297119, |
|
"learning_rate": 6.91341716182545e-05, |
|
"loss": 1.3567, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.3326732673267327, |
|
"grad_norm": 7.590511322021484, |
|
"learning_rate": 6.607197326515808e-05, |
|
"loss": 1.3672, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.3485148514851485, |
|
"grad_norm": 10.127204895019531, |
|
"learning_rate": 6.294095225512603e-05, |
|
"loss": 1.4314, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.36435643564356435, |
|
"grad_norm": 7.6939826011657715, |
|
"learning_rate": 5.9754516100806423e-05, |
|
"loss": 1.3994, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.3801980198019802, |
|
"grad_norm": 7.435072422027588, |
|
"learning_rate": 5.6526309611002594e-05, |
|
"loss": 1.3335, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.39603960396039606, |
|
"grad_norm": 10.735369682312012, |
|
"learning_rate": 5.327015646150716e-05, |
|
"loss": 1.5439, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.39603960396039606, |
|
"eval_loss": 1.4605278968811035, |
|
"eval_runtime": 21.1192, |
|
"eval_samples_per_second": 20.171, |
|
"eval_steps_per_second": 2.557, |
|
"step": 25 |
|
} |
|
], |
|
"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": 0 |
|
} |
|
}, |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 5.476375360176128e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|