email_extractor_more_data_model_t5_small
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1772
- Rouge1: 0.8316
- Rouge2: 0.7897
- Rougel: 0.8306
- Rougelsum: 0.8303
- Gen Len: 15.439
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: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 74 | 0.4608 | 0.6421 | 0.5952 | 0.632 | 0.6312 | 18.6829 |
| No log | 2.0 | 148 | 0.2775 | 0.7726 | 0.7305 | 0.7735 | 0.7734 | 16.9512 |
| No log | 3.0 | 222 | 0.2164 | 0.7865 | 0.7549 | 0.7854 | 0.7856 | 16.3659 |
| No log | 4.0 | 296 | 0.1901 | 0.8316 | 0.7897 | 0.8306 | 0.8303 | 15.439 |
| No log | 5.0 | 370 | 0.1772 | 0.8316 | 0.7897 | 0.8306 | 0.8303 | 15.439 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.15.0