README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - ccmatrix
metrics:
  - bleu
model-index:
  - name: opus-mt-id-en-ccmatrix-v2
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: ccmatrix
          type: ccmatrix
          config: en-id
          split: train
          args: en-id
        metrics:
          - name: Bleu
            type: bleu
            value: 52.173

opus-mt-id-en-ccmatrix-v2

This model was trained from scratch on the ccmatrix dataset. It achieves the following results on the evaluation set:

• Loss: 0.7667
• Bleu: 52.173

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: 1e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 4000
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu
0.803	1.0	148438	0.8185	50.3216
0.7212	2.0	296876	0.7904	51.282
0.6913	3.0	445314	0.7791	51.7806
0.6727	4.0	593752	0.7691	52.0263
0.6609	5.0	742190	0.7667	52.173

Framework versions

• Transformers 4.26.1
• Pytorch 2.0.0
• Datasets 2.10.1
• Tokenizers 0.11.0