<!-- 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. -->
dialogsum_bart_large
This model is a fine-tuned version of facebook/bart-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3282
- Rouge1: 0.4162
- Rouge2: 0.1783
- Rougel: 0.3551
- Rougelsum: 0.3553
- Gen Len: 19.838
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.1326 | 1.0 | 3115 | 1.3148 | 0.3975 | 0.1596 | 0.335 | 0.3352 | 19.942 |
| 0.937 | 2.0 | 6230 | 1.2903 | 0.3994 | 0.1613 | 0.3394 | 0.3393 | 19.858 |
| 0.7955 | 3.0 | 9345 | 1.3001 | 0.4171 | 0.1794 | 0.357 | 0.3569 | 19.784 |
| 0.6845 | 4.0 | 12460 | 1.3282 | 0.4162 | 0.1783 | 0.3551 | 0.3553 | 19.838 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.3
- Tokenizers 0.13.3
