metadata
license: apache-2.0
tags:
- generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.1
model-index:
- name: WeniGPT-Mistral-7B-instructBase
results: []
WeniGPT-Mistral-7B-instructBase
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on an unknown dataset.
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0004
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 8000
- mixed_precision_training: Native AMP
Training results
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.0
- Datasets 2.13.0
- Tokenizers 0.14.1
Open Portuguese LLM Leaderboard Evaluation Results
Detailed results can be found here and on the 🚀 Open Portuguese LLM Leaderboard
| Metric | Value |
|---|---|
| Average | 39.55 |
| ENEM Challenge (No Images) | 32.61 |
| BLUEX (No Images) | 23.50 |
| OAB Exams | 28.84 |
| Assin2 RTE | 61.42 |
| Assin2 STS | 40.02 |
| FaQuAD NLI | 34.50 |
| HateBR Binary | 44.16 |
| PT Hate Speech Binary | 39.71 |
| tweetSentBR | 51.18 |