|
{ |
|
"best_metric": NaN, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-25", |
|
"epoch": 0.04511871862839095, |
|
"eval_steps": 25, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0009023743725678191, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0009023743725678191, |
|
"eval_loss": NaN, |
|
"eval_runtime": 3.3454, |
|
"eval_samples_per_second": 14.946, |
|
"eval_steps_per_second": 3.886, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0018047487451356382, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0027071231177034573, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.990365154573717e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0036094974902712764, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.961501876182148e-05, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.004511871862839095, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.913533761814537e-05, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.005414246235406915, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.846666218300807e-05, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.006316620607974733, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.761185582727977e-05, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.007218994980542553, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.657457896300791e-05, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.008121369353110372, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.535927336897098e-05, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.00902374372567819, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.397114317029975e-05, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.00992611809824601, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.241613255361455e-05, |
|
"loss": 0.0, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.01082849247081383, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.070090031310558e-05, |
|
"loss": 0.0, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.011730866843381649, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.883279133655399e-05, |
|
"loss": 0.0, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.012633241215949467, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.681980515339464e-05, |
|
"loss": 0.0, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.013535615588517286, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.467056167950311e-05, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.014437989961085106, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.239426430539243e-05, |
|
"loss": 0.0, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.015340364333652923, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.000066048588211e-05, |
|
"loss": 0.0, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.016242738706220745, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.75e-05, |
|
"loss": 0.0, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.017145113078788562, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.490299105985507e-05, |
|
"loss": 0.0, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.01804748745135638, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.222075445642904e-05, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.0189498618239242, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.946477593864228e-05, |
|
"loss": 0.0, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.01985223619649202, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.664685702961344e-05, |
|
"loss": 0.0, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.020754610569059837, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.377906449072578e-05, |
|
"loss": 0.0, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.02165698494162766, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.087367864990233e-05, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.022559359314195476, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.794314081535644e-05, |
|
"loss": 0.0, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.022559359314195476, |
|
"eval_loss": NaN, |
|
"eval_runtime": 2.9666, |
|
"eval_samples_per_second": 16.854, |
|
"eval_steps_per_second": 4.382, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.023461733686763298, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.500000000000001e-05, |
|
"loss": 0.0, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.024364108059331115, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.205685918464356e-05, |
|
"loss": 0.0, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.025266482431898933, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.912632135009769e-05, |
|
"loss": 0.0, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.026168856804466754, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.6220935509274235e-05, |
|
"loss": 0.0, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.027071231177034572, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.3353142970386564e-05, |
|
"loss": 0.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.02797360554960239, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.053522406135775e-05, |
|
"loss": 0.0, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.02887597992217021, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.777924554357096e-05, |
|
"loss": 0.0, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.02977835429473803, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.509700894014496e-05, |
|
"loss": 0.0, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.030680728667305847, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.250000000000001e-05, |
|
"loss": 0.0, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.03158310303987367, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.9999339514117912e-05, |
|
"loss": 0.0, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.03248547741244149, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.760573569460757e-05, |
|
"loss": 0.0, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.033387851785009304, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.53294383204969e-05, |
|
"loss": 0.0, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.034290226157577125, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.3180194846605367e-05, |
|
"loss": 0.0, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.035192600530144946, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.1167208663446025e-05, |
|
"loss": 0.0, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.03609497490271276, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.9299099686894423e-05, |
|
"loss": 0.0, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.03699734927528058, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.758386744638546e-05, |
|
"loss": 0.0, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.0378997236478484, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.602885682970026e-05, |
|
"loss": 0.0, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.03880209802041622, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.464072663102903e-05, |
|
"loss": 0.0, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.03970447239298404, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.3425421036992098e-05, |
|
"loss": 0.0, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.04060684676555186, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.2388144172720251e-05, |
|
"loss": 0.0, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.041509221138119674, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.1533337816991932e-05, |
|
"loss": 0.0, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.042411595510687496, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0864662381854632e-05, |
|
"loss": 0.0, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.04331396988325532, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0384981238178534e-05, |
|
"loss": 0.0, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.04421634425582313, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0096348454262845e-05, |
|
"loss": 0.0, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.04511871862839095, |
|
"grad_norm": NaN, |
|
"learning_rate": 1e-05, |
|
"loss": 0.0, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.04511871862839095, |
|
"eval_loss": NaN, |
|
"eval_runtime": 2.9634, |
|
"eval_samples_per_second": 16.872, |
|
"eval_steps_per_second": 4.387, |
|
"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": 5.624057810649088e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|