|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 11.0, |
|
"eval_steps": 500, |
|
"global_step": 88, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.25, |
|
"grad_norm": 0.29974979162216187, |
|
"learning_rate": 0.0001992114701314478, |
|
"loss": 3.4405, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"grad_norm": 0.3932454288005829, |
|
"learning_rate": 0.0001968583161128631, |
|
"loss": 3.3216, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 3.75, |
|
"grad_norm": 0.42628756165504456, |
|
"learning_rate": 0.00019297764858882514, |
|
"loss": 3.1985, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"grad_norm": 0.44253304600715637, |
|
"learning_rate": 0.00018763066800438636, |
|
"loss": 3.0415, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 6.25, |
|
"grad_norm": 0.4085797071456909, |
|
"learning_rate": 0.00018090169943749476, |
|
"loss": 2.8932, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 7.5, |
|
"grad_norm": 0.4421256184577942, |
|
"learning_rate": 0.00017289686274214118, |
|
"loss": 2.755, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 8.75, |
|
"grad_norm": 0.44413742423057556, |
|
"learning_rate": 0.000163742398974869, |
|
"loss": 2.6121, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"grad_norm": 0.4906141757965088, |
|
"learning_rate": 0.00015358267949789966, |
|
"loss": 2.4968, |
|
"step": 80 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 250, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 32, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 154913156775936.0, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|