Hugging Face's logo

yomilimi
/
Jeolla_model

Text2Text Generation
Transformers
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Community
Jeolla_model / README.md
yomilimi's picture
yomilimi
End of training
3524cfb verified
preview code
|
raw
history blame contribute delete
No virus
1.58 kB
metadata
license: mit
base_model: gogamza/kobart-base-v2
tags:
  - generated_from_trainer
metrics:
  - bleu
model-index:
  - name: Jeolla_model
    results: []

Jeolla_model

This model is a fine-tuned version of gogamza/kobart-base-v2 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0117
  • Bleu: 88.9408
  • Gen Len: 14.085

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
0.015 1.0 15477 0.0136 88.803 14.0811
0.0111 2.0 30954 0.0122 88.8626 14.0804
0.0094 3.0 46431 0.0117 88.9408 14.085

Framework versions

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