Mohammed Brıman
Update README.md
dbe3af1
|
raw
history blame
1.67 kB
metadata
license: apache-2.0
tags:
  - generated_from_keras_callback
model-index:
  - name: MkAtlas26/t5-small-finetuned-cnn-dm
    results: []

MkAtlas26/t5-small-finetuned-cnn-dm

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

  • Train Loss: 1.1086
  • Validation Loss: 1.0703
  • Train Rouge1: 24.2706
  • Train Rouge2: 11.6659
  • Train Rougel: 20.0926
  • Train Rougelsum: 20.1515
  • Train Gen Len: 18.9998
  • Epoch: 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:

  • optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
  • training_precision: float32

Training results

Train Loss Validation Loss Train Rouge1 Train Rouge2 Train Rougel Train Rougelsum Train Gen Len Epoch
1.1086 1.0703 24.2706 11.6659 20.0926 20.1515 18.9998 0

Framework versions

  • Transformers 4.21.2
  • TensorFlow 2.8.2
  • Datasets 2.4.0
  • Tokenizers 0.12.1