metadata
library_name: transformers
license: apache-2.0
base_model: google-t5/t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: summary-generator
results: []
summary-generator
This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6233
- Rouge1: 0.2385
- Rouge2: 0.1893
- Rougel: 0.2291
- Rougelsum: 0.2291
- Gen Len: 18.9979
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.2692 | 1.0 | 593 | 1.7477 | 0.2295 | 0.1793 | 0.2195 | 0.2195 | 19.0012 |
| 1.9395 | 2.0 | 1186 | 1.6635 | 0.2351 | 0.1859 | 0.2251 | 0.2251 | 18.9979 |
| 1.8828 | 3.0 | 1779 | 1.6317 | 0.2376 | 0.1883 | 0.228 | 0.228 | 18.9979 |
| 1.8478 | 4.0 | 2372 | 1.6233 | 0.2385 | 0.1893 | 0.2291 | 0.2291 | 18.9979 |
Framework versions
- Transformers 5.8.1
- Pytorch 2.5.1
- Datasets 4.8.5
- Tokenizers 0.22.2