metadata

license: apache-2.0
base_model: t5-small
tags:
  - generated_from_trainer
datasets:
  - opus_books
metrics:
  - bleu
model-index:
  - name: model_en_pt
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: opus_books
          type: opus_books
          config: en-pt
          split: train
          args: en-pt
        metrics:
          - name: Bleu
            type: bleu
            value: 1.0547

model_en_pt

This model is a fine-tuned version of t5-small on the opus_books dataset. It achieves the following results on the evaluation set:

Loss: 3.1561
Bleu: 1.0547
Gen Len: 17.8369

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

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	79	3.4923	1.2907	17.2624
No log	2.0	158	3.3099	0.8388	17.2482
No log	3.0	237	3.2192	0.8526	17.7021
No log	4.0	316	3.1709	0.9618	17.8298
No log	5.0	395	3.1561	1.0547	17.8369

Framework versions

Transformers 4.34.0
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.14.0