Hugging Face's logo

Acadys
/
PointCon-Vigogne13B

Safetensors
Generated from Trainer
Model card Files Community
PointCon-Vigogne13B / README.md
IUseAMouse's picture
IUseAMouse
Update README.md
93240ab
preview code
|
raw
history blame
No virus
1.44 kB
metadata
base_model: bofenghuang/vigogne-2-13b-instruct
tags:
  - generated_from_trainer
  - lora
model-index:
  - name: PointCon-vigogne-2-13b-instruct-QLoRA-Instruct
    results: []
datasets:
  - IUseAMouse/POINTCON-QA-Light
language:
  - fr

PointCon-vigogne-2-13b-instruct-QLoRA-Instruct

This model is a fine-tuned version of bofenghuang/vigogne-2-13b-instruct on the .CON corpus of books. It achieves the following results on the evaluation set:

  • Loss: 1.8921

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: 0.0002
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
1.9628 1.0 91 1.8921

Framework versions

  • Transformers 4.32.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3