|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 4.0, |
|
"eval_steps": 500, |
|
"global_step": 20, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.23880597014925373, |
|
"grad_norm": 29.275244557684626, |
|
"learning_rate": 4.9692208514878445e-06, |
|
"loss": 1.492, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"grad_norm": 4.877218753196121, |
|
"learning_rate": 4.267766952966369e-06, |
|
"loss": 0.4997, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"grad_norm": 0.7924658588380961, |
|
"learning_rate": 2.5e-06, |
|
"loss": 0.2348, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"grad_norm": 0.6495439150180484, |
|
"learning_rate": 7.322330470336314e-07, |
|
"loss": 0.1975, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"grad_norm": 0.5855051339722586, |
|
"learning_rate": 0.0, |
|
"loss": 0.1812, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"step": 20, |
|
"total_flos": 9.994818287147418e+16, |
|
"train_loss": 0.3279022932052612, |
|
"train_runtime": 3201.833, |
|
"train_samples_per_second": 0.834, |
|
"train_steps_per_second": 0.006 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 20, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 5, |
|
"save_steps": 10, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 9.994818287147418e+16, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|