|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 8.0, |
|
"eval_steps": 500, |
|
"global_step": 3464, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.1547344110854503, |
|
"grad_norm": 8.039620399475098, |
|
"learning_rate": 2.5669745958429563e-05, |
|
"loss": 1.0155, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.3094688221709005, |
|
"grad_norm": 5.350721836090088, |
|
"learning_rate": 2.133949191685912e-05, |
|
"loss": 0.5088, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 3.464203233256351, |
|
"grad_norm": 12.881149291992188, |
|
"learning_rate": 1.7009237875288687e-05, |
|
"loss": 0.3687, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 4.618937644341801, |
|
"grad_norm": 7.129382133483887, |
|
"learning_rate": 1.2678983833718245e-05, |
|
"loss": 0.2937, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 5.773672055427252, |
|
"grad_norm": 6.728103160858154, |
|
"learning_rate": 8.348729792147807e-06, |
|
"loss": 0.2566, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 6.928406466512702, |
|
"grad_norm": 3.0549521446228027, |
|
"learning_rate": 4.018475750577367e-06, |
|
"loss": 0.2338, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"step": 3464, |
|
"total_flos": 5.78511019413504e+16, |
|
"train_loss": 0.4164542425036706, |
|
"train_runtime": 5827.0638, |
|
"train_samples_per_second": 37.995, |
|
"train_steps_per_second": 0.594 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 3464, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 8, |
|
"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": 5.78511019413504e+16, |
|
"train_batch_size": 64, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|