<!-- 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-russian
This model is a fine-tuned version of UrukHan/t5-russian-summarization on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5818
- Rouge1: 10.7717
- Rouge2: 2.1384
- Rougel: 10.7467
- Rougelsum: 10.6793
- Gen Len: 14.413
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: 20
- eval_batch_size: 20
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 0.33
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.5917 | 0.22 | 5000 | 1.5818 | 10.7717 | 2.1384 | 10.7467 | 10.6793 | 14.413 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
