---
license: apache-2.0
tags:
- sft
dataset:
- teknium/openhermes
base_model:
- unsloth/mistral-7b-bnb-4bit
model-index:
- name: mistral-7b-openhermes-sft
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 60.58
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/mistral-7b-openhermes-sft
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 82.01
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/mistral-7b-openhermes-sft
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 60.95
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/mistral-7b-openhermes-sft
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 46.31
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/mistral-7b-openhermes-sft
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 77.58
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/mistral-7b-openhermes-sft
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 31.24
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=CorticalStack/mistral-7b-openhermes-sft
      name: Open LLM Leaderboard
---

# mistral-7b-openhermes-sft

mistral-7b-openhermes-sft is an SFT fine-tuned version of [unsloth/mistral-7b-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-bnb-4bit) using the [teknium/openhermes](https://huggingface.co/datasets/teknium/openhermes) dataset.

## Fine-tuning configuration
### LoRA
- r: 256
- LoRA alpha: 128
- LoRA dropout: 0.0

### Training arguments
- Epochs: 1
- Batch size: 4
- Gradient accumulation steps: 6
- Optimizer: adamw_torch_fused
- Max steps: 100
- Learning rate: 0.0002
- Weight decay: 0.1
- Learning rate scheduler type: linear
- Max seq length: 2048
- 4-bit bnb: True

Trained with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_CorticalStack__mistral-7b-openhermes-sft)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |59.78|
|AI2 Reasoning Challenge (25-Shot)|60.58|
|HellaSwag (10-Shot)              |82.01|
|MMLU (5-Shot)                    |60.95|
|TruthfulQA (0-shot)              |46.31|
|Winogrande (5-shot)              |77.58|
|GSM8k (5-shot)                   |31.24|