PairRM-V2-phi3-3-mini-ultra-feedback-binarized-lora

This model is a fine-tuned version of microsoft/Phi-3-mini-128k-instruct on the ultra-feedback-binarized dataset. It achieves the following results on the evaluation set:

• Loss: 0.2605

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: 1e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.2858	0.6406	500	0.2640

Framework versions

• PEFT 0.11.1
• Transformers 4.43.1
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1