sft_0626_after_2_dpo_9

This model is a fine-tuned version of /root/LLM_Data_Engineer/LLaMA-Factory/models/Qwen2-7B-Instruct-dpo-06250115-iter2-after-dpo-0.6 on the sft_data_1474_0624_9_iter2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.7347

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0001
• train_batch_size: 6
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 48
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 3.0

Training results

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.19.1