Hugging Face's logo

Anonumous
/
transformer-en-ru

Text2Text Generation
Transformers
Safetensors
marian
Generated from Trainer
Inference Endpoints
Model card Files Community
transformer-en-ru / README.md
Anonumous's picture
Anonumous
under-tree/finetuned-en2ru-opus-mt
11d48a8
preview code
|
raw
history blame contribute delete
1.66 kB
metadata
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-en-ru
tags:
  - generated_from_trainer
metrics:
  - bleu
model-index:
  - name: transformer-en-ru
    results: []

transformer-en-ru

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-ru on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6527
  • Bleu: 67.1147
  • Gen Len: 127.0651

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: 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: 4

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
0.7937 1.0 568 0.6373 68.0996 127.3319
0.6728 2.0 1136 0.6028 69.6232 127.2664
0.6136 3.0 1704 0.5853 70.2068 126.963
0.5733 4.0 2272 0.5806 70.2274 127.2151

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.0.0.dev20230205+cu117
  • Datasets 2.13.1
  • Tokenizers 0.14.1