<!-- 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-small-finetuned-12feb-1
This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4285
- Rouge1: 18.23
- Rouge2: 5.42
- Rougel: 18.09
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: 5e-05
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 9
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
---|---|---|---|---|---|---|
3.0346 | 1.0 | 311 | 2.4880 | 17.19 | 5.28 | 17.06 |
2.8943 | 2.0 | 622 | 2.4751 | 17.77 | 5.18 | 17.59 |
2.8397 | 3.0 | 933 | 2.4719 | 17.65 | 5.38 | 17.55 |
2.806 | 4.0 | 1244 | 2.4614 | 18.26 | 5.23 | 18.03 |
2.7842 | 5.0 | 1555 | 2.4464 | 18.08 | 5.51 | 17.96 |
2.7855 | 6.0 | 1866 | 2.4437 | 17.9 | 5.37 | 17.8 |
2.7796 | 7.0 | 2177 | 2.4270 | 18.07 | 5.38 | 17.95 |
2.7951 | 8.0 | 2488 | 2.4267 | 17.96 | 5.36 | 17.85 |
2.7864 | 9.0 | 2799 | 2.4285 | 18.23 | 5.42 | 18.09 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2