README.md

metadata

language:
  - en
tags:
  - llama
datasets:
  - chargoddard/Open-Platypus-Chat
model-index:
  - name: platypus2-22b-relora
    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: 57.51
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/platypus2-22b-relora
          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: 82.36
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/platypus2-22b-relora
          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: 54.94
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/platypus2-22b-relora
          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: 43.62
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/platypus2-22b-relora
          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: 77.11
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/platypus2-22b-relora
          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: 6.29
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=chargoddard/platypus2-22b-relora
          name: Open LLM Leaderboard

Experimental ReLoRA-trained model using the OpenPlatypus dataset. Ran for one epoch, with three lora restarts.

Not recommended for use yet. Mostly tossing this up for testing.

Base model was llama2-22b-blocktriangular.

Relevant training parameters:

adapter: qlora
load_in_4bit: true
lora_r: 32
lora_alpha: 16
lora_dropout: 0.001
lora_target_linear: true
relora_steps: 150
relora_warmup_steps: 10
gradient_accumulation_steps: 2
micro_batch_size: 3

Uses the same prompt format as Ypotryll-22b. Prefix messages with " ***System:", " ***Query:", or " ***Response:", paying attention to whitespace.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	52.21
ARC (25-shot)	57.68
HellaSwag (10-shot)	82.44
MMLU (5-shot)	55.33
TruthfulQA (0-shot)	43.61
Winogrande (5-shot)	77.35
GSM8K (5-shot)	6.6
DROP (3-shot)	42.46

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	53.64
AI2 Reasoning Challenge (25-Shot)	57.51
HellaSwag (10-Shot)	82.36
MMLU (5-Shot)	54.94
TruthfulQA (0-shot)	43.62
Winogrande (5-shot)	77.11
GSM8k (5-shot)	6.29