gec-ua-uk / README.md
BonySmoke's picture
3d stage 13k samples total
a009da9
|
raw
history blame
1.5 kB
metadata
license: mit
base_model: BonySmoke/gec-ua-uk
tags:
  - generated_from_trainer
metrics:
  - bleu
model-index:
  - name: gec-ua-uk
    results: []

gec-ua-uk

This model is a fine-tuned version of BonySmoke/gec-ua-uk on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0260
  • Bleu: 0.907
  • Gen Len: 27.9915

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: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
0.0458 1.0 625 0.0254 0.9027 27.9355
0.016 2.0 1250 0.0260 0.907 27.9915

Framework versions

  • Transformers 4.32.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3