|
{ |
|
"best_global_step": null, |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 10.0, |
|
"eval_steps": 500, |
|
"global_step": 3130, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.5974440894568689, |
|
"grad_norm": 1.9811842441558838, |
|
"learning_rate": 2.604950495049505e-05, |
|
"loss": 2.047, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 3.194888178913738, |
|
"grad_norm": 1.323052167892456, |
|
"learning_rate": 2.10990099009901e-05, |
|
"loss": 0.4026, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 4.792332268370607, |
|
"grad_norm": 1.4039280414581299, |
|
"learning_rate": 1.614851485148515e-05, |
|
"loss": 0.2068, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 6.389776357827476, |
|
"grad_norm": 0.6008857488632202, |
|
"learning_rate": 1.1198019801980199e-05, |
|
"loss": 0.1062, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 7.987220447284345, |
|
"grad_norm": 0.789228081703186, |
|
"learning_rate": 6.247524752475248e-06, |
|
"loss": 0.0555, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 9.584664536741213, |
|
"grad_norm": 0.2787887454032898, |
|
"learning_rate": 1.2970297029702972e-06, |
|
"loss": 0.0336, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"step": 3130, |
|
"total_flos": 9589481500311552.0, |
|
"train_loss": 0.4568236516306575, |
|
"train_runtime": 1164.9898, |
|
"train_samples_per_second": 21.477, |
|
"train_steps_per_second": 2.687 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 3130, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 10, |
|
"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": 9589481500311552.0, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|