README.md

metadata

license: apache-2.0
base_model: oSabre/opus_books_es_pt
tags:
  - generated_from_trainer
datasets:
  - opus_books
metrics:
  - bleu
model-index:
  - name: opus_books_es_pt
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: opus_books
          type: opus_books
          config: es-pt
          split: train
          args: es-pt
        metrics:
          - name: Bleu
            type: bleu
            value: 0.5339

opus_books_es_pt

This model is a fine-tuned version of oSabre/opus_books_es_pt on the opus_books dataset. It achieves the following results on the evaluation set:

• Loss: 3.3469
• Bleu: 0.5339
• Gen Len: 18.3615

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: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	53	3.5692	0.1211	18.1174
No log	2.0	106	3.4566	0.4345	18.2207
No log	3.0	159	3.3922	0.4381	18.3756
No log	4.0	212	3.3586	0.5165	18.3615
No log	5.0	265	3.3469	0.5339	18.3615

Framework versions

• Transformers 4.36.1
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0