opus-mt-ko-en-finetuned-en-to-ko

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

  • Loss: 2.8819
  • Bleu: 3.0442
  • Gen Len: 29.6731

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: 10

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
No log 1.0 167 3.5090 1.476 100.3664
No log 2.0 334 3.2940 1.563 54.8715
3.6569 3.0 501 3.1777 2.8026 34.1871
3.6569 4.0 668 3.0641 2.409 35.7632
3.6569 5.0 835 2.9988 3.0125 33.5423
3.0398 6.0 1002 2.9581 2.7402 27.7182
3.0398 7.0 1169 2.9170 2.7127 31.9346
3.0398 8.0 1336 2.9007 2.907 28.7711
2.8619 9.0 1503 2.8891 2.9215 28.9775
2.8619 10.0 1670 2.8819 3.0442 29.6731

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.0.1
  • Datasets 2.16.1
  • Tokenizers 0.15.0
Downloads last month
32
Safetensors
Model size
77.5M 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 LizzyBennet/opus-mt-ko-en-finetuned-en-to-ko

Finetuned
(8)
this model