<!-- 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-28feb-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: 2.3686
- Rouge1: 20.86
- Rouge2: 6.65
- Rougel: 20.57
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: 0.0001
- train_batch_size: 13
- eval_batch_size: 13
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 60
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
|---|---|---|---|---|---|---|
| 3.3725 | 2.09 | 500 | 2.5493 | 17.49 | 5.58 | 17.34 |
| 2.9876 | 4.18 | 1000 | 2.4931 | 18.9 | 5.35 | 18.8 |
| 2.7925 | 6.28 | 1500 | 2.4054 | 18.26 | 5.11 | 18.01 |
| 2.6561 | 8.37 | 2000 | 2.3951 | 19.83 | 5.84 | 19.43 |
| 2.5491 | 10.46 | 2500 | 2.3602 | 19.11 | 5.69 | 18.8 |
| 2.4504 | 12.55 | 3000 | 2.3458 | 20.83 | 6.74 | 20.52 |
| 2.3708 | 14.64 | 3500 | 2.3739 | 20.69 | 6.53 | 20.43 |
| 2.3075 | 16.74 | 4000 | 2.3414 | 19.32 | 6.58 | 19.12 |
| 2.2512 | 18.83 | 4500 | 2.3589 | 19.38 | 6.07 | 19.0 |
| 2.1554 | 20.92 | 5000 | 2.3686 | 20.86 | 6.65 | 20.57 |
| 2.1141 | 23.01 | 5500 | 2.3768 | 20.71 | 6.46 | 20.37 |
| 2.0774 | 25.1 | 6000 | 2.3627 | 20.25 | 6.22 | 20.0 |
| 2.0315 | 27.2 | 6500 | 2.3521 | 20.37 | 6.28 | 20.05 |
| 1.9787 | 29.29 | 7000 | 2.3699 | 20.75 | 6.6 | 20.43 |
| 1.9645 | 31.38 | 7500 | 2.3554 | 20.27 | 5.9 | 20.0 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2
