|
{ |
|
"best_metric": 1.0986448526382446, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-30", |
|
"epoch": 0.0015047587997040642, |
|
"eval_steps": 5, |
|
"global_step": 30, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 5.0158626656802136e-05, |
|
"eval_loss": 1.8039422035217285, |
|
"eval_runtime": 812.9865, |
|
"eval_samples_per_second": 10.326, |
|
"eval_steps_per_second": 5.164, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00015047587997040642, |
|
"grad_norm": 0.5721948146820068, |
|
"learning_rate": 6e-05, |
|
"loss": 1.7091, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0002507931332840107, |
|
"eval_loss": 1.6594451665878296, |
|
"eval_runtime": 843.2851, |
|
"eval_samples_per_second": 9.955, |
|
"eval_steps_per_second": 4.978, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.00030095175994081285, |
|
"grad_norm": 1.1099064350128174, |
|
"learning_rate": 9.96057350657239e-05, |
|
"loss": 1.7172, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.00045142763991121924, |
|
"grad_norm": 0.8487201929092407, |
|
"learning_rate": 9.381533400219318e-05, |
|
"loss": 1.4969, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.0005015862665680214, |
|
"eval_loss": 1.317108392715454, |
|
"eval_runtime": 843.8013, |
|
"eval_samples_per_second": 9.949, |
|
"eval_steps_per_second": 4.975, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.0006019035198816257, |
|
"grad_norm": 0.7829315662384033, |
|
"learning_rate": 8.18711994874345e-05, |
|
"loss": 1.318, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.0007523793998520321, |
|
"grad_norm": 0.8488056063652039, |
|
"learning_rate": 6.545084971874738e-05, |
|
"loss": 1.1823, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.0007523793998520321, |
|
"eval_loss": 1.142626166343689, |
|
"eval_runtime": 843.7972, |
|
"eval_samples_per_second": 9.949, |
|
"eval_steps_per_second": 4.975, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.0009028552798224385, |
|
"grad_norm": 0.34353208541870117, |
|
"learning_rate": 4.6860474023534335e-05, |
|
"loss": 1.2084, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.0010031725331360428, |
|
"eval_loss": 1.1126813888549805, |
|
"eval_runtime": 844.4224, |
|
"eval_samples_per_second": 9.942, |
|
"eval_steps_per_second": 4.971, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.0010533311597928448, |
|
"grad_norm": 0.3344358801841736, |
|
"learning_rate": 2.8711035421746367e-05, |
|
"loss": 1.1238, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.0012038070397632514, |
|
"grad_norm": 0.3562895655632019, |
|
"learning_rate": 1.3551568628929434e-05, |
|
"loss": 1.1788, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.0012539656664200534, |
|
"eval_loss": 1.1017963886260986, |
|
"eval_runtime": 845.0947, |
|
"eval_samples_per_second": 9.934, |
|
"eval_steps_per_second": 4.967, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.0013542829197336578, |
|
"grad_norm": 0.3746950328350067, |
|
"learning_rate": 3.511175705587433e-06, |
|
"loss": 1.1727, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.0015047587997040642, |
|
"grad_norm": 0.38321593403816223, |
|
"learning_rate": 0.0, |
|
"loss": 1.2448, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.0015047587997040642, |
|
"eval_loss": 1.0986448526382446, |
|
"eval_runtime": 845.1473, |
|
"eval_samples_per_second": 9.933, |
|
"eval_steps_per_second": 4.967, |
|
"step": 30 |
|
} |
|
], |
|
"logging_steps": 3, |
|
"max_steps": 30, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 10, |
|
"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": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 4170173481222144.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|