|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 10.0, |
|
"eval_steps": 500, |
|
"global_step": 20, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.5, |
|
"grad_norm": 18.490420290038628, |
|
"learning_rate": 1e-05, |
|
"loss": 1.1109, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 1.3244118690490723, |
|
"eval_runtime": 5.4616, |
|
"eval_samples_per_second": 18.127, |
|
"eval_steps_per_second": 0.366, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.9689944386482239, |
|
"eval_runtime": 5.3534, |
|
"eval_samples_per_second": 18.493, |
|
"eval_steps_per_second": 0.374, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"grad_norm": 24.423394115352504, |
|
"learning_rate": 8.94570254698197e-06, |
|
"loss": 1.1415, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 0.8217005133628845, |
|
"eval_runtime": 5.3528, |
|
"eval_samples_per_second": 18.495, |
|
"eval_steps_per_second": 0.374, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_loss": 0.6269264221191406, |
|
"eval_runtime": 5.322, |
|
"eval_samples_per_second": 18.602, |
|
"eval_steps_per_second": 0.376, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"grad_norm": 6.734044641807279, |
|
"learning_rate": 5.412896727361663e-06, |
|
"loss": 0.7246, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_loss": 0.48788779973983765, |
|
"eval_runtime": 5.328, |
|
"eval_samples_per_second": 18.581, |
|
"eval_steps_per_second": 0.375, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_loss": 0.37585097551345825, |
|
"eval_runtime": 5.3264, |
|
"eval_samples_per_second": 18.587, |
|
"eval_steps_per_second": 0.375, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_loss": 0.28014644980430603, |
|
"eval_runtime": 5.3426, |
|
"eval_samples_per_second": 18.53, |
|
"eval_steps_per_second": 0.374, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 7.5, |
|
"grad_norm": 2.833636235664597, |
|
"learning_rate": 1.6135921418712959e-06, |
|
"loss": 0.3832, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_loss": 0.21719852089881897, |
|
"eval_runtime": 5.327, |
|
"eval_samples_per_second": 18.585, |
|
"eval_steps_per_second": 0.375, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"eval_loss": 0.1864246279001236, |
|
"eval_runtime": 5.3426, |
|
"eval_samples_per_second": 18.53, |
|
"eval_steps_per_second": 0.374, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"grad_norm": 1.675995133235129, |
|
"learning_rate": 0.0, |
|
"loss": 0.2054, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"eval_loss": 0.17900313436985016, |
|
"eval_runtime": 5.3121, |
|
"eval_samples_per_second": 18.637, |
|
"eval_steps_per_second": 0.376, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"step": 20, |
|
"total_flos": 8375186227200.0, |
|
"train_loss": 0.6121411263942719, |
|
"train_runtime": 321.7144, |
|
"train_samples_per_second": 3.077, |
|
"train_steps_per_second": 0.062 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 20, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 10, |
|
"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": 8375186227200.0, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|