---
license: other
tags:
- lora
- qlora
- adapter
license_name: yi-license
license_link: LICENSE
model-index:
- name: Yi-34b-200K-rawrr-v2-run-0902-LoRA
  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: 64.68
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Yi-34b-200K-rawrr-v2-run-0902-LoRA
      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: 84.5
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Yi-34b-200K-rawrr-v2-run-0902-LoRA
      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: 75.76
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Yi-34b-200K-rawrr-v2-run-0902-LoRA
      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: 46.66
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Yi-34b-200K-rawrr-v2-run-0902-LoRA
      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: 81.14
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Yi-34b-200K-rawrr-v2-run-0902-LoRA
      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: 62.17
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Yi-34b-200K-rawrr-v2-run-0902-LoRA
      name: Open LLM Leaderboard
---
This is not an instruct fine tune, instead it's an attempt to de-contaminate the model, remove gptslop and refusals. I want model to feel like it was trained on human data, not synthetic one.


About 961 steps total, Yi-34B-200K llamafied DPO trained for 1 epoch on rawrr_v2 dataset via unsloth qlora at prompt length of 400 and max length of 700, lr 0.000045 \
Model initialized with max_positional_embeddings of 4096 to not OOM. \
Training done on RTX 3090 Ti in about 14 hours. \
Average mem usage was like 23.89 / 23.99 GiB, so very close to OOM at all times. \
I trained it with XFCE on one 1080p monitor loaded up, on more fancy DM it would probably OOM with the same setup. \
I am not sure what's the purpose of max_prompt_length being separate from max_length, so I may have used it wrong, I should read up on it. \
Script I used to do this fine-tune is in the repo. I used chatml prompt format. Now I plan to fine-tune this on AEZAKMI v3 dataset soon.
# [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_adamo1139__Yi-34b-200K-rawrr-v2-run-0902-LoRA)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |69.15|
|AI2 Reasoning Challenge (25-Shot)|64.68|
|HellaSwag (10-Shot)              |84.50|
|MMLU (5-Shot)                    |75.76|
|TruthfulQA (0-shot)              |46.66|
|Winogrande (5-shot)              |81.14|
|GSM8k (5-shot)                   |62.17|