README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - opus_books
metrics:
  - bleu
model-index:
  - name: falahgs_en-fr_books_model
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: opus_books
          type: opus_books
          config: en-fr
          split: train
          args: en-fr
        metrics:
          - name: Bleu
            type: bleu
            value: 6.0805

falahgs_en-fr_books_model

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: 1.5439
• Bleu: 6.0805
• Gen Len: 17.5565

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: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
1.8416	1.0	6355	1.6150	5.5571	17.5985
1.7911	2.0	12710	1.5707	5.9025	17.5616
1.7539	3.0	19065	1.5492	6.0302	17.5599
1.7474	4.0	25420	1.5439	6.0805	17.5565

Framework versions

• Transformers 4.27.1
• Pytorch 2.0.1+cu118
• Datasets 2.9.0
• Tokenizers 0.13.3