metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - billsum
metrics:
  - rouge
  - bleu
model-index:
  - name: T5-small_finetuned_billsum_subset_model_bs16_lr2e-05
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: billsum
          type: billsum
          config: default
          split: ca_test
          args: default
        metrics:
          - name: Rouge1
            type: rouge
            value: 0.1931
          - name: Bleu
            type: bleu
            value: 0.0008

T5-small_finetuned_billsum_subset_model_bs16_lr2e-05

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

Loss: 2.0305
Rouge1: 0.1931
Rouge2: 0.0965
Rougel: 0.1667
Rougelsum: 0.1662
Gen Len: 19.0
Bleu: 0.0008

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	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len	Bleu
No log	1.0	62	2.0395	0.1922	0.0973	0.1672	0.1668	19.0	0.0008
No log	2.0	124	2.0364	0.1932	0.0973	0.1685	0.1681	19.0	0.0008
No log	3.0	186	2.0323	0.1921	0.0968	0.1671	0.1666	19.0	0.0008
No log	4.0	248	2.0305	0.1931	0.0965	0.1667	0.1662	19.0	0.0008

Framework versions

Transformers 4.27.4
Pytorch 2.0.0+cu118
Datasets 2.11.0
Tokenizers 0.13.3