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 |