README.md

metadata

license: llama2
library_name: peft
datasets:
  - tonytan48/TempReason
  - tasksource/tracie
  - tasksource/bigbench
  - time_dial
model-index:
  - name: vicuna-7b-v1.5-lora-temporal-without-mctaco-1
    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: 49.49
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Charlie911/vicuna-7b-v1.5-lora-temporal-without-mctaco-1
          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: 75.93
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Charlie911/vicuna-7b-v1.5-lora-temporal-without-mctaco-1
          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: 47.47
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Charlie911/vicuna-7b-v1.5-lora-temporal-without-mctaco-1
          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: 39.95
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Charlie911/vicuna-7b-v1.5-lora-temporal-without-mctaco-1
          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: 71.35
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Charlie911/vicuna-7b-v1.5-lora-temporal-without-mctaco-1
          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: 11.9
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Charlie911/vicuna-7b-v1.5-lora-temporal-without-mctaco-1
          name: Open LLM Leaderboard

Training procedure

The following bitsandbytes quantization config was used during training:

• quant_method: bitsandbytes
• load_in_8bit: True
• load_in_4bit: False
• llm_int8_threshold: 6.0
• llm_int8_skip_modules: None
• llm_int8_enable_fp32_cpu_offload: False
• llm_int8_has_fp16_weight: False
• bnb_4bit_quant_type: fp4
• bnb_4bit_use_double_quant: False
• bnb_4bit_compute_dtype: float32

Framework versions

• PEFT 0.5.0

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	49.35
AI2 Reasoning Challenge (25-Shot)	49.49
HellaSwag (10-Shot)	75.93
MMLU (5-Shot)	47.47
TruthfulQA (0-shot)	39.95
Winogrande (5-shot)	71.35
GSM8k (5-shot)	11.90