|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 20.773824980524537, |
|
"eval_steps": 500, |
|
"global_step": 400000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 2.596728122565567, |
|
"grad_norm": 0.9470382332801819, |
|
"learning_rate": 0.0002, |
|
"loss": 1.7054, |
|
"step": 50000 |
|
}, |
|
{ |
|
"epoch": 5.193456245131134, |
|
"grad_norm": 0.6922363638877869, |
|
"learning_rate": 0.0002, |
|
"loss": 1.6798, |
|
"step": 100000 |
|
}, |
|
{ |
|
"epoch": 7.790184367696702, |
|
"grad_norm": 0.6903401017189026, |
|
"learning_rate": 0.0002, |
|
"loss": 1.6738, |
|
"step": 150000 |
|
}, |
|
{ |
|
"epoch": 10.386912490262269, |
|
"grad_norm": 1.2185564041137695, |
|
"learning_rate": 0.0002, |
|
"loss": 1.6705, |
|
"step": 200000 |
|
}, |
|
{ |
|
"epoch": 12.983640612827838, |
|
"grad_norm": 0.7960174083709717, |
|
"learning_rate": 0.0002, |
|
"loss": 1.6691, |
|
"step": 250000 |
|
}, |
|
{ |
|
"epoch": 15.580368735393405, |
|
"grad_norm": 0.7023811936378479, |
|
"learning_rate": 0.0002, |
|
"loss": 1.6667, |
|
"step": 300000 |
|
}, |
|
{ |
|
"epoch": 18.177096857958972, |
|
"grad_norm": 0.6432592868804932, |
|
"learning_rate": 0.0002, |
|
"loss": 1.6664, |
|
"step": 350000 |
|
}, |
|
{ |
|
"epoch": 20.773824980524537, |
|
"grad_norm": 1.1296038627624512, |
|
"learning_rate": 0.0002, |
|
"loss": 1.6651, |
|
"step": 400000 |
|
} |
|
], |
|
"logging_steps": 50000, |
|
"max_steps": 577650, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 30, |
|
"save_steps": 50000, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 4.227652833030557e+19, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|