|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.0013582496689266432, |
|
"eval_steps": 8, |
|
"global_step": 30, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 4.527498896422144e-05, |
|
"grad_norm": NaN, |
|
"learning_rate": 1e-05, |
|
"loss": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 4.527498896422144e-05, |
|
"eval_loss": NaN, |
|
"eval_runtime": 3388.9697, |
|
"eval_samples_per_second": 10.977, |
|
"eval_steps_per_second": 5.488, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 9.054997792844289e-05, |
|
"grad_norm": NaN, |
|
"learning_rate": 2e-05, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.00013582496689266431, |
|
"grad_norm": NaN, |
|
"learning_rate": 3e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.00018109995585688577, |
|
"grad_norm": NaN, |
|
"learning_rate": 4e-05, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0002263749448211072, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.00027164993378532863, |
|
"grad_norm": NaN, |
|
"learning_rate": 6e-05, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.00031692492274955006, |
|
"grad_norm": NaN, |
|
"learning_rate": 7e-05, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.00036219991171377154, |
|
"grad_norm": NaN, |
|
"learning_rate": 8e-05, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.00036219991171377154, |
|
"eval_loss": NaN, |
|
"eval_runtime": 3327.3345, |
|
"eval_samples_per_second": 11.18, |
|
"eval_steps_per_second": 5.59, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.00040747490067799297, |
|
"grad_norm": NaN, |
|
"learning_rate": 9e-05, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.0004527498896422144, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.0004980248786064359, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.938441702975689e-05, |
|
"loss": 0.0, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.0005432998675706573, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.755282581475769e-05, |
|
"loss": 0.0, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.0005885748565348787, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.45503262094184e-05, |
|
"loss": 0.0, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.0006338498454991001, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.045084971874738e-05, |
|
"loss": 0.0, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.0006791248344633216, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.0007243998234275431, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.938926261462366e-05, |
|
"loss": 0.0, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.0007243998234275431, |
|
"eval_loss": NaN, |
|
"eval_runtime": 3327.915, |
|
"eval_samples_per_second": 11.178, |
|
"eval_steps_per_second": 5.589, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.0007696748123917645, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.269952498697734e-05, |
|
"loss": 0.0, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.0008149498013559859, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.545084971874738e-05, |
|
"loss": 0.0, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.0008602247903202073, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.782172325201155e-05, |
|
"loss": 0.0, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.0009054997792844288, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.0009507747682486503, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.2178276747988446e-05, |
|
"loss": 0.0, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.0009960497572128718, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.4549150281252636e-05, |
|
"loss": 0.0, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.0010413247461770931, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.7300475013022663e-05, |
|
"loss": 0.0, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.0010865997351413145, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.061073738537635e-05, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.0010865997351413145, |
|
"eval_loss": NaN, |
|
"eval_runtime": 3328.8869, |
|
"eval_samples_per_second": 11.175, |
|
"eval_steps_per_second": 5.587, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.001131874724105536, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.4644660940672627e-05, |
|
"loss": 0.0, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.0011771497130697575, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.549150281252633e-06, |
|
"loss": 0.0, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.0012224247020339789, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.449673790581611e-06, |
|
"loss": 0.0, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.0012676996909982002, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.4471741852423237e-06, |
|
"loss": 0.0, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.0013129746799624218, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.15582970243117e-07, |
|
"loss": 0.0, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.0013582496689266432, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 0.0, |
|
"step": 30 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 30, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 8, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 3.978923748202906e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|