leaderboard-pt-pr-bot's picture
Adding the Open Portuguese LLM Leaderboard Evaluation Results
44e4dcb verified
|
raw
history blame
6.23 kB
metadata
language:
  - pt
library_name: peft
model-index:
  - name: WeniGPT-Mistral-7B-instructBase-4bit
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: ENEM Challenge (No Images)
          type: eduagarcia/enem_challenge
          split: train
          args:
            num_few_shot: 3
        metrics:
          - type: acc
            value: 29.18
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Weni/WeniGPT-Mistral-7B-instructBase-4bit
          name: Open Portuguese LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BLUEX (No Images)
          type: eduagarcia-temp/BLUEX_without_images
          split: train
          args:
            num_few_shot: 3
        metrics:
          - type: acc
            value: 24.48
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Weni/WeniGPT-Mistral-7B-instructBase-4bit
          name: Open Portuguese LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: OAB Exams
          type: eduagarcia/oab_exams
          split: train
          args:
            num_few_shot: 3
        metrics:
          - type: acc
            value: 29.79
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Weni/WeniGPT-Mistral-7B-instructBase-4bit
          name: Open Portuguese LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Assin2 RTE
          type: assin2
          split: test
          args:
            num_few_shot: 15
        metrics:
          - type: f1_macro
            value: 74.66
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Weni/WeniGPT-Mistral-7B-instructBase-4bit
          name: Open Portuguese LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Assin2 STS
          type: eduagarcia/portuguese_benchmark
          split: test
          args:
            num_few_shot: 15
        metrics:
          - type: pearson
            value: 55.21
            name: pearson
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Weni/WeniGPT-Mistral-7B-instructBase-4bit
          name: Open Portuguese LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: FaQuAD NLI
          type: ruanchaves/faquad-nli
          split: test
          args:
            num_few_shot: 15
        metrics:
          - type: f1_macro
            value: 21.57
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Weni/WeniGPT-Mistral-7B-instructBase-4bit
          name: Open Portuguese LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HateBR Binary
          type: ruanchaves/hatebr
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: f1_macro
            value: 46.02
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Weni/WeniGPT-Mistral-7B-instructBase-4bit
          name: Open Portuguese LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: PT Hate Speech Binary
          type: hate_speech_portuguese
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: f1_macro
            value: 56.82
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Weni/WeniGPT-Mistral-7B-instructBase-4bit
          name: Open Portuguese LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: tweetSentBR
          type: eduagarcia/tweetsentbr_fewshot
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: f1_macro
            value: 41.56
            name: f1-macro
        source:
          url: >-
            https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Weni/WeniGPT-Mistral-7B-instructBase-4bit
          name: Open Portuguese LLM Leaderboard

Training procedure

The following bitsandbytes quantization config was used during training:

  • quant_method: bitsandbytes
  • load_in_8bit: False
  • load_in_4bit: True
  • 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: nf4
  • bnb_4bit_use_double_quant: True
  • bnb_4bit_compute_dtype: bfloat16

Framework versions

  • PEFT 0.4.0

This model was trained with this parameters:

max_seq_length = 2048

training_arguments_mistral = {
    'num_train_epochs':10,
    'per_device_train_batch_size':2,
    'gradient_accumulation_steps':2,
    'gradient_checkpointing':True,
    'optim':'adamw_torch',
    'lr_scheduler_type':'constant_with_warmup',
    'logging_steps':10,
    'evaluation_strategy':'epoch',
    'save_strategy':"epoch",
    'load_best_model_at_end':True,
    'learning_rate':4e-4,
    'save_total_limit':3,
    'fp16':True,
    'tf32': True, 
    'max_steps':8000,
    'max_grad_norm':0.3,
    'warmup_ratio':0.03,
    'disable_tqdm':False,
    'weight_decay':0.001,
    'hub_model_id':'Weni/WeniGPT-Mistral-7B-instructBase-4bit',
    'push_to_hub':True,
    'hub_strategy':'every_save',
    'hub_token':token,
    'hub_private_repo':True, 

Open Portuguese LLM Leaderboard Evaluation Results

Detailed results can be found here and on the 🚀 Open Portuguese LLM Leaderboard

Metric Value
Average 42.14
ENEM Challenge (No Images) 29.18
BLUEX (No Images) 24.48
OAB Exams 29.79
Assin2 RTE 74.66
Assin2 STS 55.21
FaQuAD NLI 21.57
HateBR Binary 46.02
PT Hate Speech Binary 56.82
tweetSentBR 41.56