metadata
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Cpod/t5-small-finetuned-cnn_dailymail-3-epochs
results: []
Cpod/t5-small-finetuned-cnn_dailymail-3-epochs
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 1.8014
- Validation Loss: 1.6484
- Train Rouge1: 24.6091
- Train Rouge2: 11.8866
- Train Rougel: 20.3754
- Train Rougelsum: 23.2320
- Train Gen Len: 18.9998
- Epoch: 2
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 |
---|---|---|---|---|---|---|---|
1.8623 | 1.6757 | 24.4518 | 11.7242 | 20.1766 | 23.0440 | 18.9987 | 0 |
1.8212 | 1.6567 | 24.5313 | 11.7909 | 20.2584 | 23.1484 | 18.9992 | 1 |
1.8014 | 1.6484 | 24.6091 | 11.8866 | 20.3754 | 23.2320 | 18.9998 | 2 |
Framework versions
- Transformers 4.26.1
- TensorFlow 2.11.0
- Datasets 2.10.1
- Tokenizers 0.13.2