<!-- 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-ruspell-test
This model is a fine-tuned version of cointegrated/rut5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3537
- Rouge1: 5.6
- Rouge2: 1.2
- Rougel: 5.5333
- Rougelsum: 5.5333
- Gen Len: 11.968
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: 48
- eval_batch_size: 48
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.7755 | 0.48 | 5000 | 0.4513 | 5.6 | 1.2 | 5.5333 | 5.5333 | 11.998 |
| 0.6051 | 0.97 | 10000 | 0.3537 | 5.6 | 1.2 | 5.5333 | 5.5333 | 11.968 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
