mT5-tfidf-10pass-all-questions-QA-22-06-2023-without-ams-3epochs-contextonly
This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0701
- Rouge1: 0.141
- Rouge2: 0.0269
- Rougel: 0.1158
- Rougelsum: 0.116
- Gen Len: 18.8553
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: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.812 | 1.0 | 5187 | 2.1633 | 0.0371 | 0.0058 | 0.0317 | 0.0318 | 9.2088 |
| 2.5987 | 2.0 | 10374 | 2.0883 | 0.1405 | 0.0277 | 0.1163 | 0.1164 | 18.8388 |
| 2.5587 | 3.0 | 15561 | 2.0701 | 0.141 | 0.0269 | 0.1158 | 0.116 | 18.8553 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3