<!-- 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. -->
ru_t5absum_for_legaltext
This model is a fine-tuned version of cointegrated/rut5-base-absum on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: nan
- Rouge1: 1.4175
- Rouge2: 0.0
- Rougel: 1.4476
- Rougelsum: 1.4302
- Gen Len: 17.2133
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: 0.002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 157 | nan | 1.4175 | 0.0 | 1.4476 | 1.4302 | 17.2133 |
| No log | 2.0 | 314 | nan | 1.4175 | 0.0 | 1.4476 | 1.4302 | 17.2133 |
| No log | 3.0 | 471 | nan | 1.4175 | 0.0 | 1.4476 | 1.4302 | 17.2133 |
| 0.0 | 4.0 | 628 | nan | 1.4175 | 0.0 | 1.4476 | 1.4302 | 17.2133 |
| 0.0 | 5.0 | 785 | nan | 1.4175 | 0.0 | 1.4476 | 1.4302 | 17.2133 |
| 0.0 | 6.0 | 942 | nan | 1.4175 | 0.0 | 1.4476 | 1.4302 | 17.2133 |
| 0.0 | 7.0 | 1099 | nan | 1.4175 | 0.0 | 1.4476 | 1.4302 | 17.2133 |
| 0.0 | 8.0 | 1256 | nan | 1.4175 | 0.0 | 1.4476 | 1.4302 | 17.2133 |
| 0.0 | 9.0 | 1413 | nan | 1.4175 | 0.0 | 1.4476 | 1.4302 | 17.2133 |
| 0.0 | 10.0 | 1570 | nan | 1.4175 | 0.0 | 1.4476 | 1.4302 | 17.2133 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1
