T5_small_eurlexsum / README.md
Pierre-Arthur's picture
update model card README.md
d296505
metadata
license: apache-2.0
base_model: t5-small
tags:
  - generated_from_trainer
datasets:
  - eur-lex-sum
metrics:
  - rouge
model-index:
  - name: T5_small_eurlexsum
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: eur-lex-sum
          type: eur-lex-sum
          config: french
          split: test
          args: french
        metrics:
          - name: Rouge1
            type: rouge
            value: 0.2

T5_small_eurlexsum

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

  • Loss: 1.1159
  • Rouge1: 0.2
  • Rouge2: 0.1394
  • Rougel: 0.1833
  • Rougelsum: 0.1829
  • Gen Len: 19.0

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

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
No log 1.0 71 1.4740 0.1718 0.0935 0.1476 0.1476 19.0
No log 2.0 142 1.2138 0.1915 0.1207 0.1719 0.1719 19.0
No log 3.0 213 1.1368 0.1953 0.1306 0.1759 0.1759 19.0
No log 4.0 284 1.1159 0.2 0.1394 0.1833 0.1829 19.0

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.0
  • Tokenizers 0.13.3