mikojelly's picture
mikojelly/T5_large_billsum_fine_tune_base_model_3_epoch
f9336c1
metadata
license: apache-2.0
base_model: google/flan-t5-large
tags:
  - generated_from_trainer
datasets:
  - billsum
metrics:
  - rouge
model-index:
  - name: T5_large_billsum_fine_tune_base_model_3_epoch
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: billsum
          type: billsum
          config: default
          split: test
          args: default
        metrics:
          - name: Rouge1
            type: rouge
            value: 0.2489

T5_large_billsum_fine_tune_base_model_3_epoch

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

  • Loss: 0.9541
  • Rouge1: 0.2489
  • Rouge2: 0.2083
  • Rougel: 0.2424
  • Rougelsum: 0.2424
  • 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: 3e-05
  • train_batch_size: 10
  • eval_batch_size: 10
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
1.1242 1.0 1895 0.9894 0.2482 0.2063 0.2411 0.2411 19.0
1.0324 2.0 3790 0.9594 0.2493 0.2082 0.2426 0.2426 19.0
1.0014 3.0 5685 0.9541 0.2489 0.2083 0.2424 0.2424 19.0

Framework versions

  • Transformers 4.35.0.dev0
  • Pytorch 1.12.1+cu116
  • Datasets 2.4.0
  • Tokenizers 0.14.1