README.md

metadata

license: apache-2.0
library_name: peft
tags:
  - code
  - instruct
  - mistral
datasets:
  - HuggingFaceH4/no_robots
base_model: mistralai/Mistral-7B-v0.1
model-index:
  - name: mistral_7b_norobots
    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: 58.96
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=qblocks/mistral_7b_norobots
          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: 80.57
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=qblocks/mistral_7b_norobots
          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: 57.66
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=qblocks/mistral_7b_norobots
          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: 41.91
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=qblocks/mistral_7b_norobots
          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: 75.61
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=qblocks/mistral_7b_norobots
          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: 38.36
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=qblocks/mistral_7b_norobots
          name: Open LLM Leaderboard

Finetuning Overview:

Model Used: mistralai/Mistral-7B-v0.1

Dataset: HuggingFaceH4/no_robots

Dataset Insights:

No Robots is a high-quality dataset of 10,000 instructions and demonstrations created by skilled human annotators. This data can be used for supervised fine-tuning (SFT) to make language models follow instructions better.

Finetuning Details:

With the utilization of MonsterAPI's no-code LLM finetuner, this finetuning:

• Was achieved with great cost-effectiveness.
• Completed in a total duration of 1h 15m 3s for 2 epochs using an A6000 48GB GPU.
• Costed $2.525 for the entire 2 epochs.

Hyperparameters & Additional Details:

• Epochs: 2
• Cost Per Epoch: $1.26
• Total Finetuning Cost: $2.525
• Model Path: mistralai/Mistral-7B-v0.1
• Learning Rate: 0.0002
• Data Split: 100% train
• Gradient Accumulation Steps: 64
• lora r: 64
• lora alpha: 16

Prompt Structure

<|system|> </s> <|user|> [USER PROMPT] </s> <|assistant|> [ASSISTANT ANSWER] </s>

Train loss :

Benchmarking results :

---

license: apache-2.0

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	58.85
AI2 Reasoning Challenge (25-Shot)	58.96
HellaSwag (10-Shot)	80.57
MMLU (5-Shot)	57.66
TruthfulQA (0-shot)	41.91
Winogrande (5-shot)	75.61
GSM8k (5-shot)	38.36