Tiger-DPO / README.md
leaderboard-pr-bot's picture
Adding Evaluation Results
760bd8c verified
|
raw
history blame
1.84 kB
metadata
license: other
library_name: peft
tags:
  - llama-factory
  - lora
  - generated_from_trainer
base_model: NeuralNovel/Tiger-7B-v0.1
model-index:
  - name: train_2024-02-16-12-09-1733333
    results: []

train_2024-02-16-12-09-1733333

This model is a fine-tuned version of NeuralNovel/Tiger-7B-v0.1 on the Neural-DPO 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
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 1.0

Training results

Framework versions

  • PEFT 0.8.2
  • Transformers 4.37.2
  • Pytorch 2.2.0+cu121
  • Datasets 2.17.0
  • Tokenizers 0.15.2

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 59.66
AI2 Reasoning Challenge (25-Shot) 48.21
HellaSwag (10-Shot) 81.82
MMLU (5-Shot) 59.85
TruthfulQA (0-shot) 50.76
Winogrande (5-shot) 76.32
GSM8k (5-shot) 41.02