metadata

base_model: Mprimus/T5-summarize
tags:
  - generated_from_trainer
datasets:
  - cnn_dailymail
metrics:
  - rouge
  - bleu
model-index:
  - name: T5-summarize
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: cnn_dailymail
          type: cnn_dailymail
          config: 3.0.0
          split: train
          args: 3.0.0
        metrics:
          - name: Rouge1
            type: rouge
            value: 24.0364
          - name: Bleu
            type: bleu
            value: 0.0141

T5-summarize

This model is a fine-tuned version of Mprimus/T5-summarize on the cnn_dailymail dataset. It achieves the following results on the evaluation set:

Loss: 0.9246
Rouge1: 24.0364
Rouge2: 11.0646
Rougel: 19.9812
Rougelsum: 22.5659
Bleu: 0.0141
Gen Len: 18.9845

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: 80
eval_batch_size: 80
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Bleu	Gen Len
1.0307	1.0	2872	0.9246	24.0364	11.0646	19.9812	22.5659	0.0141	18.9845

Framework versions

Transformers 4.35.2
Pytorch 2.1.1+cu121
Datasets 2.15.0
Tokenizers 0.15.0