dpo_0622_policy2

This model is a fine-tuned version of /root/LLM_Data_Engineer/LLaMA-Factory/models/Qwen2-7B-Instruct-sft-0622-iter1-policy2 on the dpo_data_5370_0621 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0645
• Rewards/chosen: 1.6397
• Rewards/rejected: -2.7117
• Rewards/accuracies: 1.0
• Rewards/margins: 4.3514
• Logps/rejected: -212.6626
• Logps/chosen: -291.2645
• Logits/rejected: -1.2750
• Logits/chosen: -0.2107

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: 5e-06
• train_batch_size: 4
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• 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