Billsum_T5_finetuned_model
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.3953
- Rouge1: 0.1899
- Rouge2: 0.0922
- Rougel: 0.1604
- Rougelsum: 0.1605
- Gen Len: 20.0
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: 7
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 62 | 2.7967 | 0.1295 | 0.036 | 0.1067 | 0.1066 | 20.0 |
No log | 2.0 | 124 | 2.5706 | 0.1388 | 0.0503 | 0.115 | 0.1148 | 20.0 |
No log | 3.0 | 186 | 2.4827 | 0.1459 | 0.0547 | 0.1209 | 0.1208 | 20.0 |
No log | 4.0 | 248 | 2.4385 | 0.1598 | 0.0676 | 0.1338 | 0.1336 | 20.0 |
No log | 5.0 | 310 | 2.4119 | 0.1762 | 0.0797 | 0.1476 | 0.1477 | 20.0 |
No log | 6.0 | 372 | 2.3988 | 0.1883 | 0.0901 | 0.1586 | 0.1586 | 20.0 |
No log | 7.0 | 434 | 2.3953 | 0.1899 | 0.0922 | 0.1604 | 0.1605 | 20.0 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 27
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.