elvish-translator-quenya-t5-base

This model is a fine-tuned version of google-t5/t5-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 3.4619
  • Bleu: 0.3386
  • Gen Len: 14.3889

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
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
4.5969 1.0 144 4.0271 0.1511 14.5278
4.1388 2.0 288 3.8283 0.1435 15.3819
3.9458 3.0 432 3.7158 0.2337 13.2639
3.808 4.0 576 3.6417 0.2594 14.0278
3.7546 5.0 720 3.5761 0.295 14.7639
3.6707 6.0 864 3.5284 0.2913 15.2986
3.6004 7.0 1008 3.4973 0.3018 14.9861
3.5505 8.0 1152 3.4758 0.3043 14.7431
3.5129 9.0 1296 3.4659 0.3296 14.4792
3.5232 10.0 1440 3.4619 0.3386 14.3889

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.2.1+cu121
  • Datasets 3.0.0
  • Tokenizers 0.19.1
Downloads last month
8
Safetensors
Model size
223M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Oysiyl/elvish-translator-quenya-t5-base

Base model

google-t5/t5-base
Finetuned
(414)
this model

Space using Oysiyl/elvish-translator-quenya-t5-base 1