TinyV-1.5B / README.md
zhangchenxu's picture
Update README.md
d7a4b56 verified
metadata
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen2.5-1.5B-Instruct
tags:
  - llama-factory
  - full
  - generated_from_trainer
model-index:
  - name: Qwen2.5-1.5B-Instruct-SFT-BigmathV_Simple_Balanced-LR1.0e-5-EPOCHS2
    results: []

TinyV is a reward system for efficient RL post-training that detects false negatives in current rule-based verifiers and provides more accurate reward signals via a small LLM during RL training. Experiments show that TinyV incurs only 6% additional computational cost while significantly increasing both RL efficiency and final model performance.

  • 📄 Technical Report - Including false negative analysis and theotical insights behind TinyV
  • 💾 Github Repo - Access the complete pipeline for more efficient RL training via TinyV
  • 🤗 HF Collection - Training Data, Benchmarks, and Model Artifact

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on zhangchenxu/TinyV_Training_Data_Balanced dataset.

Overview

TinyV Pipeline

How to use it?

Please refer to the codebase: https://github.com/uw-nsl/TinyV for details.

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 512
  • total_eval_batch_size: 64
  • 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_ratio: 0.1
  • num_epochs: 2.0

Framework versions

  • Transformers 4.48.3
  • Pytorch 2.5.0
  • Datasets 3.2.0
  • Tokenizers 0.21.0