CoolFace
Modelpublic

Samuael/geez_t5-big-15k

sourceHugging Faceupdated 2y agoView on Hugging Face
1likes16downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

geez_t5-big-15k

This model is a fine-tuned version of Samuael/geez_t5-big-15k on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.8007
  • —Wer: 0.2339
  • —Cer: 0.0556
  • —Bleu: 58.8529

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: 0.0005
  • —trainbatchsize: 64
  • —evalbatchsize: 128
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 1
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossWerCerBleu
0.21361.0293110.80070.23390.055658.8529

Framework versions

  • —Transformers 4.38.2
  • —Pytorch 2.2.1+cu121
  • —Datasets 2.18.0
  • —Tokenizers 0.15.2