[trainer] update config (#7174)

Former-commit-id: 9f535d0e3c4ee3cd0f1b65218c2eee5d03f43c6f

examples/train_lora/llama3_lora_dpo.yaml

@@ -18,6 +18,7 @@ cutoff_len: 2048
 max_samples: 1000
 overwrite_cache: true
 preprocessing_num_workers: 16
+dataloader_num_workers: 4
 
 ### output
 output_dir: saves/llama3-8b/lora/dpo
@@ -25,6 +26,7 @@ logging_steps: 10
 save_steps: 500
 plot_loss: true
 overwrite_output_dir: true
+save_only_model: false
 
 ### train
 per_device_train_batch_size: 1
@@ -35,6 +37,7 @@ lr_scheduler_type: cosine
 warmup_ratio: 0.1
 bf16: true
 ddp_timeout: 180000000
+resume_from_checkpoint: null
 
 ### eval
 # eval_dataset: dpo_en_demo