<!-- 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. -->
mT5-tfidf-10pass-all-questions-QA-22-06-2023-without-ams-with-nonfactual-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: 2.0871
- Rouge1: 0.1409
- Rouge2: 0.0288
- Rougel: 0.1159
- Rougelsum: 0.1158
- Gen Len: 18.8206
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 |
|---|---|---|---|---|---|---|---|---|
| 2.7223 | 1.0 | 7356 | 2.1686 | 0.139 | 0.0274 | 0.1148 | 0.1147 | 18.6219 |
| 2.6314 | 2.0 | 14712 | 2.1008 | 0.1416 | 0.0293 | 0.1167 | 0.1166 | 18.8697 |
| 2.5676 | 3.0 | 22068 | 2.0871 | 0.1409 | 0.0288 | 0.1159 | 0.1158 | 18.8206 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
