README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - wmt16
  - autoevaluate/wmt16-sample
metrics:
  - bleu
model-index:
  - name: translation
    results:
      - task:
          type: text2text-generation
          name: Sequence-to-sequence Language Modeling
        dataset:
          name: wmt16
          type: wmt16
          args: ro-en
        metrics:
          - type: bleu
            value: 28.5866
            name: Bleu
      - task:
          type: translation
          name: Translation
        dataset:
          name: autoevaluate/wmt16-ro-en-sample
          type: autoevaluate/wmt16-ro-en-sample
          config: autoevaluate--wmt16-ro-en-sample
          split: test
        metrics:
          - type: bleu
            value: 2.7663
            name: BLEU
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjRlMmFiNmViZmFmYTViZmQ4NWIwNDQ2NmI4MDBiZjg1MzZjMWZkMzY0YjA2ZjE2ZTZhZjI5MWVmOGZhOGRmNiIsInZlcnNpb24iOjF9.9may0WjvZnNl1ulo8rxh3Fl_g1om6QRC7ZklgV2rZ_-w8_ZhA7v62SEopmkIPLX_cpWinwKzg-p-2e18XDgvBQ
          - type: loss
            value: 4.943170070648193
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWQ2MmIwMjcxMDJhOGI1ODE5NjA2ZjViMDYxMjlhY2MzODIwMDI1YWU5NzExMTBjYWUxOTNhYzU1OTc5OGFjNyIsInZlcnNpb24iOjF9._ogVvMQzTw3w77SHzZx-lfKDqoBb3gxjdztg5TFKn_FujSxRw14NhcZxYrpEeZmWa7rcMshhzKFBjTYSaLxIAg
          - type: gen_len
            value: 40.35
            name: gen_len
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNWUwYWNkMmZkM2MxNjJjNmU1MTYzYzliMjU0NGFkZGM2MjBiNDkyNzMxYWJiM2ViNDYxZWMyMDFhMDdiNTJlYiIsInZlcnNpb24iOjF9.PBIJpF-XsDMCV1XrQBmFN_kjUKwlz4bqgNm698AtMgYTrsfkwgOq_CItdgjGK1aXzRqZMfGOzP2NIPeiy3dMBg

translation

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-ro on the wmt16 dataset. It achieves the following results on the evaluation set:

• Loss: 1.3170
• Bleu: 28.5866
• Gen Len: 33.9575

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
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
0.8302	0.03	1000	1.3170	28.5866	33.9575

Framework versions

• Transformers 4.19.2
• Pytorch 1.11.0+cu113
• Datasets 2.2.2
• Tokenizers 0.12.1