<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
clupubhealth-mini-test-3
This model is a fine-tuned version of facebook/bart-base on the clupubhealth dataset. It achieves the following results on the evaluation set:
- Loss: 2.4191
- Rouge1: 30.0438
- Rouge2: 10.2364
- Rougel: 20.066
- Rougelsum: 20.1703
- Gen Len: 19.6
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: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 10
- total_train_batch_size: 20
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 0.5 | 5 | 2.5258 | 25.7171 | 6.7541 | 16.6375 | 17.2026 | 20.0 |
| 3.0394 | 1.0 | 10 | 2.4191 | 30.0438 | 10.2364 | 20.066 | 20.1703 | 19.6 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.7.1
- Tokenizers 0.13.2
