|
{ |
|
"best_metric": 0.18073219060897827, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-25", |
|
"epoch": 0.022607810998700052, |
|
"eval_steps": 25, |
|
"global_step": 25, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0009043124399480021, |
|
"grad_norm": 5.457483291625977, |
|
"learning_rate": 5e-05, |
|
"loss": 1.118, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0009043124399480021, |
|
"eval_loss": 3.656862258911133, |
|
"eval_runtime": 3.9691, |
|
"eval_samples_per_second": 12.597, |
|
"eval_steps_per_second": 3.275, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0018086248798960041, |
|
"grad_norm": 9.676811218261719, |
|
"learning_rate": 0.0001, |
|
"loss": 1.9065, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.002712937319844006, |
|
"grad_norm": 6.939542293548584, |
|
"learning_rate": 9.990365154573717e-05, |
|
"loss": 1.8026, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0036172497597920083, |
|
"grad_norm": 4.408699035644531, |
|
"learning_rate": 9.961501876182148e-05, |
|
"loss": 1.1022, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.00452156219974001, |
|
"grad_norm": 3.139526128768921, |
|
"learning_rate": 9.913533761814537e-05, |
|
"loss": 0.7039, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.005425874639688012, |
|
"grad_norm": 3.6901752948760986, |
|
"learning_rate": 9.846666218300807e-05, |
|
"loss": 0.4753, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.006330187079636014, |
|
"grad_norm": 4.00541353225708, |
|
"learning_rate": 9.761185582727977e-05, |
|
"loss": 0.4156, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.007234499519584017, |
|
"grad_norm": 10.569222450256348, |
|
"learning_rate": 9.657457896300791e-05, |
|
"loss": 0.5245, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.008138811959532019, |
|
"grad_norm": 1.3185478448867798, |
|
"learning_rate": 9.535927336897098e-05, |
|
"loss": 0.3026, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.00904312439948002, |
|
"grad_norm": 3.6592326164245605, |
|
"learning_rate": 9.397114317029975e-05, |
|
"loss": 0.3811, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.009947436839428022, |
|
"grad_norm": 3.1792221069335938, |
|
"learning_rate": 9.241613255361455e-05, |
|
"loss": 0.3194, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.010851749279376025, |
|
"grad_norm": 1.6078685522079468, |
|
"learning_rate": 9.070090031310558e-05, |
|
"loss": 0.2317, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.011756061719324026, |
|
"grad_norm": 2.7015645503997803, |
|
"learning_rate": 8.883279133655399e-05, |
|
"loss": 0.3042, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.012660374159272028, |
|
"grad_norm": 3.5483405590057373, |
|
"learning_rate": 8.681980515339464e-05, |
|
"loss": 0.3244, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.01356468659922003, |
|
"grad_norm": 4.097019672393799, |
|
"learning_rate": 8.467056167950311e-05, |
|
"loss": 0.3704, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.014468999039168033, |
|
"grad_norm": 2.48213529586792, |
|
"learning_rate": 8.239426430539243e-05, |
|
"loss": 0.3323, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.015373311479116034, |
|
"grad_norm": 1.7427242994308472, |
|
"learning_rate": 8.000066048588211e-05, |
|
"loss": 0.296, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.016277623919064038, |
|
"grad_norm": 0.8796375393867493, |
|
"learning_rate": 7.75e-05, |
|
"loss": 0.2567, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.017181936359012037, |
|
"grad_norm": 0.987083911895752, |
|
"learning_rate": 7.490299105985507e-05, |
|
"loss": 0.2335, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.01808624879896004, |
|
"grad_norm": 0.6607208251953125, |
|
"learning_rate": 7.222075445642904e-05, |
|
"loss": 0.215, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.018990561238908042, |
|
"grad_norm": 0.7064231038093567, |
|
"learning_rate": 6.946477593864228e-05, |
|
"loss": 0.2372, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.019894873678856045, |
|
"grad_norm": 1.7021199464797974, |
|
"learning_rate": 6.664685702961344e-05, |
|
"loss": 0.2504, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.020799186118804047, |
|
"grad_norm": 1.9892632961273193, |
|
"learning_rate": 6.377906449072578e-05, |
|
"loss": 0.2139, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.02170349855875205, |
|
"grad_norm": 1.2977501153945923, |
|
"learning_rate": 6.087367864990233e-05, |
|
"loss": 0.2125, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.022607810998700052, |
|
"grad_norm": 0.8224288821220398, |
|
"learning_rate": 5.794314081535644e-05, |
|
"loss": 0.2192, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.022607810998700052, |
|
"eval_loss": 0.18073219060897827, |
|
"eval_runtime": 4.0909, |
|
"eval_samples_per_second": 12.222, |
|
"eval_steps_per_second": 3.178, |
|
"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": 3.087239672233984e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|