|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.5555555555555554, |
|
"eval_steps": 500, |
|
"global_step": 12, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.5925925925925926, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00018333333333333334, |
|
"loss": 75.9901, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 1.1851851851851851, |
|
"grad_norm": 9.116338729858398, |
|
"learning_rate": 0.00015000000000000001, |
|
"loss": 74.6472, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 1.7777777777777777, |
|
"grad_norm": 13.230999946594238, |
|
"learning_rate": 0.00011666666666666668, |
|
"loss": 71.5201, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 2.3703703703703702, |
|
"grad_norm": 18.953718185424805, |
|
"learning_rate": 8.333333333333334e-05, |
|
"loss": 67.9205, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 2.962962962962963, |
|
"grad_norm": 15.519621849060059, |
|
"learning_rate": 5e-05, |
|
"loss": 64.3085, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 3.5555555555555554, |
|
"grad_norm": 12.424678802490234, |
|
"learning_rate": 1.6666666666666667e-05, |
|
"loss": 62.8551, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 3.5555555555555554, |
|
"step": 12, |
|
"total_flos": 54489554656632.0, |
|
"train_loss": 69.54023615519206, |
|
"train_runtime": 322.5483, |
|
"train_samples_per_second": 0.67, |
|
"train_steps_per_second": 0.037 |
|
} |
|
], |
|
"logging_steps": 2, |
|
"max_steps": 12, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 4, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 54489554656632.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|