|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"eval_steps": 500, |
|
"global_step": 125, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.16, |
|
"grad_norm": 5.780210971832275, |
|
"learning_rate": 4.36e-05, |
|
"loss": 11.4213, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"grad_norm": 6.165759086608887, |
|
"learning_rate": 3.56e-05, |
|
"loss": 5.7177, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"grad_norm": 6.5082106590271, |
|
"learning_rate": 2.7600000000000003e-05, |
|
"loss": 4.4683, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"grad_norm": 4.297185897827148, |
|
"learning_rate": 1.9600000000000002e-05, |
|
"loss": 3.9999, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"grad_norm": 3.8283252716064453, |
|
"learning_rate": 1.16e-05, |
|
"loss": 3.7793, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"grad_norm": 4.412525177001953, |
|
"learning_rate": 3.6e-06, |
|
"loss": 3.6285, |
|
"step": 120 |
|
} |
|
], |
|
"logging_steps": 20, |
|
"max_steps": 125, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 60000, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 5314359328768000.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|