Hugging Face's logo

yomilimi
/
gy_Jeolla_test

Text2Text Generation
Transformers
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Community
gy_Jeolla_test / README.md
yomilimi's picture
yomilimi
End of training
994d3fe verified
preview code
|
raw
history blame contribute delete
1.6 kB
metadata
license: mit
base_model: yomilimi/Gyeongsang_encoder
tags:
  - generated_from_trainer
metrics:
  - bleu
model-index:
  - name: gy_Jeolla_test
    results: []

gy_Jeolla_test

This model is a fine-tuned version of yomilimi/Gyeongsang_encoder on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0642
  • Bleu: 80.4544
  • Gen Len: 14.1795

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: 2e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
0.0737 1.0 15477 0.0721 78.571 14.2081
0.0685 2.0 30954 0.0655 80.1472 14.1847
0.0643 3.0 46431 0.0642 80.4544 14.1795

Framework versions

  • Transformers 4.42.0.dev0
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1