|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.007735148514851485, |
|
"eval_steps": 25, |
|
"global_step": 25, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0003094059405940594, |
|
"eval_loss": 9.276086807250977, |
|
"eval_runtime": 78.2213, |
|
"eval_samples_per_second": 4.602, |
|
"eval_steps_per_second": 4.602, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.001547029702970297, |
|
"grad_norm": 20.956584930419922, |
|
"learning_rate": 5e-05, |
|
"loss": 9.4537, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.003094059405940594, |
|
"grad_norm": 19.363298416137695, |
|
"learning_rate": 0.0001, |
|
"loss": 8.2148, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.004641089108910891, |
|
"grad_norm": 35.757205963134766, |
|
"learning_rate": 9.619397662556435e-05, |
|
"loss": 8.377, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.006188118811881188, |
|
"grad_norm": 16.865013122558594, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 8.3326, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.007735148514851485, |
|
"grad_norm": 29.526941299438477, |
|
"learning_rate": 6.91341716182545e-05, |
|
"loss": 8.19, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.007735148514851485, |
|
"eval_loss": 7.6531758308410645, |
|
"eval_runtime": 78.2396, |
|
"eval_samples_per_second": 4.601, |
|
"eval_steps_per_second": 4.601, |
|
"step": 25 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 50, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 25, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 112649109504000.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|