|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 4.861111111111111, |
|
"eval_steps": 500, |
|
"global_step": 3500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.6944444444444444, |
|
"grad_norm": 7.35616397857666, |
|
"learning_rate": 1.7222222222222224e-05, |
|
"loss": 0.2334, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.3888888888888888, |
|
"grad_norm": 4.325047969818115, |
|
"learning_rate": 1.4444444444444446e-05, |
|
"loss": 0.1592, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 2.0833333333333335, |
|
"grad_norm": 3.574897289276123, |
|
"learning_rate": 1.1666666666666668e-05, |
|
"loss": 0.1443, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 2.7777777777777777, |
|
"grad_norm": 2.2505545616149902, |
|
"learning_rate": 8.888888888888888e-06, |
|
"loss": 0.1236, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 3.4722222222222223, |
|
"grad_norm": 2.264756202697754, |
|
"learning_rate": 6.111111111111112e-06, |
|
"loss": 0.1174, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 4.166666666666667, |
|
"grad_norm": 0.6259239315986633, |
|
"learning_rate": 3.3333333333333333e-06, |
|
"loss": 0.1174, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 4.861111111111111, |
|
"grad_norm": 0.2633063793182373, |
|
"learning_rate": 5.555555555555555e-07, |
|
"loss": 0.0999, |
|
"step": 3500 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 3600, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 5, |
|
"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": 763827838151040.0, |
|
"train_batch_size": 32, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|