Summarization_model
This model is a fine-tuned version of t5-small on the billsum dataset. It achieves the following results on the evaluation set:
- Loss: 2.5515
- Rouge1: 0.1392
- Rouge2: 0.0503
- Rougel: 0.1161
- Rougelsum: 0.1159
- 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: 4
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 62 | 2.8419 | 0.1272 | 0.0393 | 0.108 | 0.1079 | 19.0 |
No log | 2.0 | 124 | 2.6329 | 0.1333 | 0.0458 | 0.1133 | 0.1131 | 19.0 |
No log | 3.0 | 186 | 2.5693 | 0.1379 | 0.0494 | 0.1164 | 0.1162 | 19.0 |
No log | 4.0 | 248 | 2.5515 | 0.1392 | 0.0503 | 0.1161 | 0.1159 | 19.0 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 4
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.