metadata
license: apache-2.0
base_model: t5-base
tags:
- generated_from_keras_callback
model-index:
- name: mfaraggg/t5-basefinetuned-summscreen-modhyperparams
results: []
mfaraggg/t5-basefinetuned-summscreen-modhyperparams
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 2.9369
- Validation Loss: 2.8029
- Train Rouge1: 15.1361
- Train Rouge2: 3.0992
- Train Rougel: 11.7925
- Train Rougelsum: 13.1963
- Train Gen Len: 18.9908
- 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': 3e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.001}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
|---|---|---|---|---|---|---|---|
| 3.2939 | 2.9001 | 14.3953 | 2.5567 | 11.0942 | 12.5452 | 19.0 | 0 |
| 3.0163 | 2.8419 | 14.9975 | 2.9256 | 11.5849 | 12.9266 | 19.0 | 1 |
| 2.9369 | 2.8029 | 15.1361 | 3.0992 | 11.7925 | 13.1963 | 18.9908 | 2 |
Framework versions
- Transformers 4.35.0
- TensorFlow 2.14.0
- Datasets 2.14.6
- Tokenizers 0.14.1