metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: t5_news_summarizer
results: []
t5_news_summarizer
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.8582
- Rouge1: 0.1413
- Rouge2: 0.0434
- Rougel: 0.1086
- Rougelsum: 0.1086
- 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 313 | 2.9257 | 0.1367 | 0.0418 | 0.1043 | 0.1043 | 19.0 |
| 3.2916 | 2.0 | 626 | 2.8709 | 0.1404 | 0.0428 | 0.1079 | 0.1079 | 19.0 |
| 3.2916 | 3.0 | 939 | 2.8582 | 0.1413 | 0.0434 | 0.1086 | 0.1086 | 19.0 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2