README.md

metadata

license: apache-2.0
library_name: peft
tags:
  - code
  - instruct
  - zephyr
datasets:
  - HuggingFaceH4/no_robots
base_model: HuggingFaceH4/zephyr-7b-alpha
model-index:
  - name: zephyr_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: 56.48
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=qblocks/zephyr_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: 79.64
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=qblocks/zephyr_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: 55.52
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=qblocks/zephyr_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: 44.6
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=qblocks/zephyr_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: 74.11
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=qblocks/zephyr_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: 20.62
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=qblocks/zephyr_7b_norobots
          name: Open LLM Leaderboard

Finetuning Overview:

Model Used: HuggingFaceH4/zephyr-7b-alpha

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 LLM finetuner, this finetuning:

• Was achieved with great cost-effectiveness.
• Completed in a total duration of 36mins 47secs for 1 epoch using an A6000 48GB GPU.
• Costed $1.212 for the entire epoch.

Hyperparameters & Additional Details:

• Epochs: 1
• Cost Per Epoch: $1.212
• Total Finetuning Cost: $1.212
• Model Path: HuggingFaceH4/zephyr-7b-alpha
• Learning Rate: 0.0002
• Data Split: 100% train
• Gradient Accumulation Steps: 4
• lora r: 32
• lora alpha: 64

---

Prompt Structure

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

Train loss :

license: apache-2.0

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	55.16
AI2 Reasoning Challenge (25-Shot)	56.48
HellaSwag (10-Shot)	79.64
MMLU (5-Shot)	55.52
TruthfulQA (0-shot)	44.60
Winogrande (5-shot)	74.11
GSM8k (5-shot)	20.62