README.md

metadata

tags:
  - generated_from_trainer
metrics:
  - bleu
model_index:
  - name: opus-mt-ja-en-finetuned-ja-to-en_test
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        metric:
          name: Bleu
          type: bleu
          value: 41.7379

opus-mt-ja-en-finetuned-ja-to-en_test

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

• Loss: 2.2845
• Bleu: 41.7379
• Gen Len: 12.0337

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: 0.0001
• 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	20	2.4396	18.3131	11.5506
No log	2.0	40	2.2467	27.0591	12.0562
No log	3.0	60	2.1419	33.5675	11.9888
No log	4.0	80	2.1646	37.728	12.5955
No log	5.0	100	2.1563	39.1659	12.191
No log	6.0	120	2.2355	38.2432	11.8652
No log	7.0	140	2.2503	41.4545	12.0
No log	8.0	160	2.2656	43.8778	12.2584
No log	9.0	180	2.2816	41.1478	12.2135
No log	10.0	200	2.2845	41.7379	12.0337

Framework versions

• Transformers 4.9.1
• Pytorch 1.9.0+cu102
• Datasets 1.10.2
• Tokenizers 0.10.3