<!-- 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. -->
t5-small-finetuned-dialogsum
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2855
- Rouge1: 36.3668
- Rouge2: 13.9199
- Rougel: 30.9962
- Rougelsum: 32.8081
- Gen Len: 18.878
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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.5044 | 1.0 | 779 | 1.3732 | 34.348 | 11.9709 | 28.927 | 30.8692 | 18.858 |
| 1.4536 | 2.0 | 1558 | 1.3361 | 34.7487 | 12.3134 | 29.3339 | 31.3522 | 18.894 |
| 1.432 | 3.0 | 2337 | 1.3187 | 35.7545 | 12.8085 | 30.3746 | 32.2789 | 18.836 |
| 1.4018 | 4.0 | 3116 | 1.3078 | 35.7193 | 12.9168 | 30.1988 | 32.0836 | 18.892 |
| 1.3956 | 5.0 | 3895 | 1.2943 | 36.189 | 13.4094 | 30.7898 | 32.6249 | 18.884 |
| 1.3789 | 6.0 | 4674 | 1.2893 | 36.2545 | 13.7438 | 30.9043 | 32.7441 | 18.88 |
| 1.374 | 7.0 | 5453 | 1.2863 | 36.148 | 13.7422 | 30.8583 | 32.6798 | 18.874 |
| 1.3673 | 8.0 | 6232 | 1.2855 | 36.3668 | 13.9199 | 30.9962 | 32.8081 | 18.878 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
