README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - new_dataset
metrics:
  - sacrebleu
model-index:
  - name: jwt300_mt-Italian-to-Spanish_transformers
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: new_dataset
          type: new_dataset
          args: jwt300_mt
        metrics:
          - name: Sacrebleu
            type: sacrebleu
            value: 0.9057

jwt300_mt-Italian-to-Spanish_transformers

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

• Loss: 2.4425
• Sacrebleu: 0.9057
• Gen Len: 18.1276

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Sacrebleu	Gen Len
2.7545	1.0	2229	2.4425	0.9057	18.1276

Framework versions

• Transformers 4.17.0
• Pytorch 1.11.0
• Datasets 2.0.0
• Tokenizers 0.11.6