|
{ |
|
"best_metric": NaN, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-25", |
|
"epoch": 1.0326086956521738, |
|
"eval_steps": 25, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.020460358056265986, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 25156482.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.020460358056265986, |
|
"eval_loss": NaN, |
|
"eval_runtime": 2.0415, |
|
"eval_samples_per_second": 24.492, |
|
"eval_steps_per_second": 6.368, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.04092071611253197, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.061381074168797956, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.990365154573717e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.08184143222506395, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.961501876182148e-05, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.10230179028132992, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.913533761814537e-05, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.12276214833759591, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.846666218300807e-05, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.1432225063938619, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.761185582727977e-05, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.1636828644501279, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.657457896300791e-05, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.18414322250639387, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.535927336897098e-05, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.20460358056265984, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.397114317029975e-05, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.22506393861892582, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.241613255361455e-05, |
|
"loss": 0.0, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.24552429667519182, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.070090031310558e-05, |
|
"loss": 0.0, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.2659846547314578, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.883279133655399e-05, |
|
"loss": 0.0, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.2864450127877238, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.681980515339464e-05, |
|
"loss": 0.0, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.3069053708439898, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.467056167950311e-05, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.3273657289002558, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.239426430539243e-05, |
|
"loss": 0.0, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.34782608695652173, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.000066048588211e-05, |
|
"loss": 0.0, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.36828644501278773, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.75e-05, |
|
"loss": 0.0, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.3887468030690537, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.490299105985507e-05, |
|
"loss": 0.0, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.4092071611253197, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.222075445642904e-05, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.4296675191815857, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.946477593864228e-05, |
|
"loss": 0.0, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.45012787723785164, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.664685702961344e-05, |
|
"loss": 0.0, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.47058823529411764, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.377906449072578e-05, |
|
"loss": 0.0, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.49104859335038364, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.087367864990233e-05, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.5115089514066496, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.794314081535644e-05, |
|
"loss": 0.0, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.5115089514066496, |
|
"eval_loss": NaN, |
|
"eval_runtime": 2.086, |
|
"eval_samples_per_second": 23.969, |
|
"eval_steps_per_second": 6.232, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.5319693094629157, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.500000000000001e-05, |
|
"loss": 0.0, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.5524296675191815, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.205685918464356e-05, |
|
"loss": 0.0, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.5728900255754475, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.912632135009769e-05, |
|
"loss": 0.0, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.5933503836317136, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.6220935509274235e-05, |
|
"loss": 0.0, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.6138107416879796, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.3353142970386564e-05, |
|
"loss": 0.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.6342710997442456, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.053522406135775e-05, |
|
"loss": 0.0, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.6547314578005116, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.777924554357096e-05, |
|
"loss": 0.0, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.6751918158567775, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.509700894014496e-05, |
|
"loss": 0.0, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.6956521739130435, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.250000000000001e-05, |
|
"loss": 0.0, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.7161125319693095, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.9999339514117912e-05, |
|
"loss": 0.0, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.7365728900255755, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.760573569460757e-05, |
|
"loss": 0.0, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.7570332480818415, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.53294383204969e-05, |
|
"loss": 0.0, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.7774936061381074, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.3180194846605367e-05, |
|
"loss": 0.0, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.7979539641943734, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.1167208663446025e-05, |
|
"loss": 0.0, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.8184143222506394, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.9299099686894423e-05, |
|
"loss": 0.0, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.8388746803069054, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.758386744638546e-05, |
|
"loss": 0.0, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.8593350383631714, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.602885682970026e-05, |
|
"loss": 0.0, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.8797953964194374, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.464072663102903e-05, |
|
"loss": 0.0, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.9002557544757033, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.3425421036992098e-05, |
|
"loss": 0.0, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.9207161125319693, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.2388144172720251e-05, |
|
"loss": 0.0, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.9411764705882353, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.1533337816991932e-05, |
|
"loss": 0.0, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.9616368286445013, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0864662381854632e-05, |
|
"loss": 0.0, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.9820971867007673, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0384981238178534e-05, |
|
"loss": 0.0, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 1.012148337595908, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0096348454262845e-05, |
|
"loss": 0.0, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 1.0326086956521738, |
|
"grad_norm": NaN, |
|
"learning_rate": 1e-05, |
|
"loss": 0.0, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 1.0326086956521738, |
|
"eval_loss": NaN, |
|
"eval_runtime": 1.9889, |
|
"eval_samples_per_second": 25.139, |
|
"eval_steps_per_second": 6.536, |
|
"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": 1.0641718235050803e+17, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|