Hugging Face's logo

alexandreacff
/
zephyr-enem-finetuned-v2

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
zephyr-enem-finetuned-v2 / README.md
alexandreacff's picture
alexandreacff
End of training
83eedf2
preview code
|
raw
history blame contribute delete
1.24 kB
metadata
license: mit
library_name: peft
tags:
  - generated_from_trainer
base_model: TheBloke/zephyr-7B-alpha-GPTQ
model-index:
  - name: zephyr-enem-finetuned-v2
    results: []

zephyr-enem-finetuned-v2

This model is a fine-tuned version of TheBloke/zephyr-7B-alpha-GPTQ on the None 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: 0.0002
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • PEFT 0.7.1
  • Transformers 4.36.2
  • Pytorch 1.13.0+cu117
  • Datasets 2.15.0
  • Tokenizers 0.15.0