|
{ |
|
"best_metric": NaN, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-25", |
|
"epoch": 1.035188739603327, |
|
"eval_steps": 25, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.020473448496481125, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.020473448496481125, |
|
"eval_loss": NaN, |
|
"eval_runtime": 2.9844, |
|
"eval_samples_per_second": 16.754, |
|
"eval_steps_per_second": 4.356, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.04094689699296225, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.061420345489443376, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.990365154573717e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0818937939859245, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.961501876182148e-05, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.10236724248240563, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.913533761814537e-05, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.12284069097888675, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.846666218300807e-05, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.1433141394753679, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.761185582727977e-05, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.163787587971849, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.657457896300791e-05, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.18426103646833014, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.535927336897098e-05, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.20473448496481125, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.397114317029975e-05, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.2252079334612924, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.241613255361455e-05, |
|
"loss": 0.0, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.2456813819577735, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.070090031310558e-05, |
|
"loss": 0.0, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.26615483045425464, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.883279133655399e-05, |
|
"loss": 0.0, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.2866282789507358, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.681980515339464e-05, |
|
"loss": 0.0, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.30710172744721687, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.467056167950311e-05, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.327575175943698, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.239426430539243e-05, |
|
"loss": 0.0, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.34804862444017914, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.000066048588211e-05, |
|
"loss": 0.0, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.3685220729366603, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.75e-05, |
|
"loss": 0.0, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.3889955214331414, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.490299105985507e-05, |
|
"loss": 0.0, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.4094689699296225, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.222075445642904e-05, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.42994241842610365, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.946477593864228e-05, |
|
"loss": 0.0, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.4504158669225848, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.664685702961344e-05, |
|
"loss": 0.0, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.4708893154190659, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.377906449072578e-05, |
|
"loss": 0.0, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.491362763915547, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.087367864990233e-05, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.5118362124120281, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.794314081535644e-05, |
|
"loss": 0.0, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.5118362124120281, |
|
"eval_loss": NaN, |
|
"eval_runtime": 3.0041, |
|
"eval_samples_per_second": 16.644, |
|
"eval_steps_per_second": 4.327, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.5323096609085093, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.500000000000001e-05, |
|
"loss": 0.0, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.5527831094049904, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.205685918464356e-05, |
|
"loss": 0.0, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.5732565579014716, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.912632135009769e-05, |
|
"loss": 0.0, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.5937300063979527, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.6220935509274235e-05, |
|
"loss": 0.0, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.6142034548944337, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.3353142970386564e-05, |
|
"loss": 0.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.6346769033909149, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.053522406135775e-05, |
|
"loss": 0.0, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.655150351887396, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.777924554357096e-05, |
|
"loss": 0.0, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.6756238003838771, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.509700894014496e-05, |
|
"loss": 0.0, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.6960972488803583, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.250000000000001e-05, |
|
"loss": 0.0, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.7165706973768394, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.9999339514117912e-05, |
|
"loss": 0.0, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.7370441458733206, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.760573569460757e-05, |
|
"loss": 0.0, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.7575175943698017, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.53294383204969e-05, |
|
"loss": 0.0, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.7779910428662828, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.3180194846605367e-05, |
|
"loss": 0.0, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.7984644913627639, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.1167208663446025e-05, |
|
"loss": 0.0, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.818937939859245, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.9299099686894423e-05, |
|
"loss": 0.0, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.8394113883557262, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.758386744638546e-05, |
|
"loss": 0.0, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.8598848368522073, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.602885682970026e-05, |
|
"loss": 0.0, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.8803582853486884, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.464072663102903e-05, |
|
"loss": 0.0, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.9008317338451696, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.3425421036992098e-05, |
|
"loss": 0.0, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.9213051823416507, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.2388144172720251e-05, |
|
"loss": 0.0, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.9417786308381318, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.1533337816991932e-05, |
|
"loss": 0.0, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.9622520793346129, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0864662381854632e-05, |
|
"loss": 0.0, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.982725527831094, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0384981238178534e-05, |
|
"loss": 0.0, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 1.0147152911068458, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0096348454262845e-05, |
|
"loss": 0.0, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 1.035188739603327, |
|
"grad_norm": NaN, |
|
"learning_rate": 1e-05, |
|
"loss": 0.0, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 1.035188739603327, |
|
"eval_loss": NaN, |
|
"eval_runtime": 2.9703, |
|
"eval_samples_per_second": 16.833, |
|
"eval_steps_per_second": 4.377, |
|
"step": 50 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 50, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"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": 2.229252309123072e+17, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|