|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"eval_steps": 500, |
|
"global_step": 166, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.12048192771084337, |
|
"grad_norm": 0.212890625, |
|
"learning_rate": 2.9411764705882355e-06, |
|
"loss": 1.2124, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.24096385542168675, |
|
"grad_norm": 0.1884765625, |
|
"learning_rate": 4.974553604702332e-06, |
|
"loss": 1.1499, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.3614457831325301, |
|
"grad_norm": 0.255859375, |
|
"learning_rate": 4.53643988012584e-06, |
|
"loss": 1.1143, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.4819277108433735, |
|
"grad_norm": 0.2353515625, |
|
"learning_rate": 3.6455663043185264e-06, |
|
"loss": 1.102, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.6024096385542169, |
|
"grad_norm": 0.3125, |
|
"learning_rate": 2.5e-06, |
|
"loss": 1.1122, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.7228915662650602, |
|
"grad_norm": 0.240234375, |
|
"learning_rate": 1.354433695681474e-06, |
|
"loss": 1.1106, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.8433734939759037, |
|
"grad_norm": 0.271484375, |
|
"learning_rate": 4.635601198741607e-07, |
|
"loss": 1.1641, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.963855421686747, |
|
"grad_norm": 0.2158203125, |
|
"learning_rate": 2.544639529766829e-08, |
|
"loss": 1.0859, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 166, |
|
"total_flos": 3.053266675118899e+16, |
|
"train_loss": 1.1294547391225056, |
|
"train_runtime": 852.7135, |
|
"train_samples_per_second": 0.778, |
|
"train_steps_per_second": 0.195 |
|
} |
|
], |
|
"logging_steps": 20, |
|
"max_steps": 166, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 100, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 3.053266675118899e+16, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|