|
{ |
|
"best_metric": NaN, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-25", |
|
"epoch": 0.08278145695364239, |
|
"eval_steps": 25, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0016556291390728477, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0016556291390728477, |
|
"eval_loss": NaN, |
|
"eval_runtime": 2.406, |
|
"eval_samples_per_second": 20.782, |
|
"eval_steps_per_second": 5.403, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0033112582781456954, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.004966887417218543, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.990365154573717e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.006622516556291391, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.961501876182148e-05, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.008278145695364239, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.913533761814537e-05, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.009933774834437087, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.846666218300807e-05, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.011589403973509934, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.761185582727977e-05, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.013245033112582781, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.657457896300791e-05, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.014900662251655629, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.535927336897098e-05, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.016556291390728478, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.397114317029975e-05, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.018211920529801324, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.241613255361455e-05, |
|
"loss": 0.0, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.019867549668874173, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.070090031310558e-05, |
|
"loss": 0.0, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.02152317880794702, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.883279133655399e-05, |
|
"loss": 0.0, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.023178807947019868, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.681980515339464e-05, |
|
"loss": 0.0, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.024834437086092714, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.467056167950311e-05, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.026490066225165563, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.239426430539243e-05, |
|
"loss": 0.0, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.028145695364238412, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.000066048588211e-05, |
|
"loss": 0.0, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.029801324503311258, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.75e-05, |
|
"loss": 0.0, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.03145695364238411, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.490299105985507e-05, |
|
"loss": 0.0, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.033112582781456956, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.222075445642904e-05, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.0347682119205298, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.946477593864228e-05, |
|
"loss": 0.0, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.03642384105960265, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.664685702961344e-05, |
|
"loss": 0.0, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.0380794701986755, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.377906449072578e-05, |
|
"loss": 0.0, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.039735099337748346, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.087367864990233e-05, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.041390728476821195, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.794314081535644e-05, |
|
"loss": 0.0, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.041390728476821195, |
|
"eval_loss": NaN, |
|
"eval_runtime": 1.7198, |
|
"eval_samples_per_second": 29.074, |
|
"eval_steps_per_second": 7.559, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.04304635761589404, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.500000000000001e-05, |
|
"loss": 0.0, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.04470198675496689, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.205685918464356e-05, |
|
"loss": 0.0, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.046357615894039736, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.912632135009769e-05, |
|
"loss": 0.0, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.048013245033112585, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.6220935509274235e-05, |
|
"loss": 0.0, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.04966887417218543, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.3353142970386564e-05, |
|
"loss": 0.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.05132450331125828, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.053522406135775e-05, |
|
"loss": 0.0, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.052980132450331126, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.777924554357096e-05, |
|
"loss": 0.0, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.054635761589403975, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.509700894014496e-05, |
|
"loss": 0.0, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.056291390728476824, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.250000000000001e-05, |
|
"loss": 0.0, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.057947019867549666, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.9999339514117912e-05, |
|
"loss": 0.0, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.059602649006622516, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.760573569460757e-05, |
|
"loss": 0.0, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.061258278145695365, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.53294383204969e-05, |
|
"loss": 0.0, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.06291390728476821, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.3180194846605367e-05, |
|
"loss": 0.0, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.06456953642384106, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.1167208663446025e-05, |
|
"loss": 0.0, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.06622516556291391, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.9299099686894423e-05, |
|
"loss": 0.0, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.06788079470198675, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.758386744638546e-05, |
|
"loss": 0.0, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.0695364238410596, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.602885682970026e-05, |
|
"loss": 0.0, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.07119205298013245, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.464072663102903e-05, |
|
"loss": 0.0, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.0728476821192053, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.3425421036992098e-05, |
|
"loss": 0.0, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.07450331125827815, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.2388144172720251e-05, |
|
"loss": 0.0, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.076158940397351, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.1533337816991932e-05, |
|
"loss": 0.0, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.07781456953642384, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0864662381854632e-05, |
|
"loss": 0.0, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.07947019867549669, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0384981238178534e-05, |
|
"loss": 0.0, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.08112582781456953, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0096348454262845e-05, |
|
"loss": 0.0, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.08278145695364239, |
|
"grad_norm": NaN, |
|
"learning_rate": 1e-05, |
|
"loss": 0.0, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.08278145695364239, |
|
"eval_loss": NaN, |
|
"eval_runtime": 1.7258, |
|
"eval_samples_per_second": 28.971, |
|
"eval_steps_per_second": 7.533, |
|
"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": 5.2640867875710566e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|