metadata

library_name: transformers
base_model: Samuael/ethiopic-sec2sec-tigrinya
tags:
  - generated_from_trainer
metrics:
  - wer
  - bleu
model-index:
  - name: ethiopic-sec2sec-tigrinya
    results: []

ethiopic-sec2sec-tigrinya

This model is a fine-tuned version of Samuael/ethiopic-sec2sec-tigrinya on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 3.5557
Wer: 0.2489
Cer: 0.1202
Bleu: 67.5274

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: 0.0002
train_batch_size: 64
eval_batch_size: 128
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 1
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer	Bleu
0.071	1.0	433	3.5557	0.2489	0.1202	67.5274

Framework versions

Transformers 4.46.3
Pytorch 2.5.1+cu121
Datasets 3.1.0
Tokenizers 0.20.3