tl-ceb-model-v2 / README.md
youdiniplays's picture
End of training
3e025f8 verified
|
raw
history blame
1.75 kB
metadata
license: apache-2.0
base_model: youdiniplays/tl-ceb-model-v2
tags:
  - generated_from_trainer
metrics:
  - bleu
model-index:
  - name: tl-ceb-model-v2
    results: []

tl-ceb-model-v2

This model is a fine-tuned version of youdiniplays/tl-ceb-model-v2 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4749
  • Bleu: 3.8223
  • Gen Len: 18.208

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: 0.001
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
0.6089 1.0 6516 0.5061 3.6822 18.235
0.5687 2.0 13032 0.4956 3.7119 18.222
0.525 3.0 19548 0.4869 3.8722 18.219
0.488 4.0 26064 0.4795 3.7886 18.23
0.4527 5.0 32580 0.4749 3.8223 18.208

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0