wisenut-nlp-team/Qwen2-7B-IC-SFT-LoRA-DPO

Qwen2-7B-IC-SFT-DPO

This model is a fine-tuned version of wisenut-nlp-team/Qwen2-7B-IC-SFT on the dpo_90k dataset.

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-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• total_eval_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 20
• num_epochs: 1.0

Training results

Framework versions

• PEFT 0.12.0
• Transformers 4.46.1
• Pytorch 2.3.0a0+ebedce2
• Datasets 3.1.0
• Tokenizers 0.20.3