<!-- 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. -->
Timelist_T5Summarization
This model is a fine-tuned version of IlyaGusev/rut5_base_sum_gazeta on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0047
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 278 | 0.1841 |
| 8.8411 | 2.0 | 556 | 1.1110 |
| 8.8411 | 3.0 | 834 | 0.0111 |
| 9.9911 | 4.0 | 1112 | 0.0071 |
| 9.9911 | 5.0 | 1390 | 0.0060 |
| 0.0595 | 6.0 | 1668 | 0.0054 |
| 0.0595 | 7.0 | 1946 | 0.0053 |
| 0.0109 | 8.0 | 2224 | 0.0051 |
| 0.0099 | 9.0 | 2502 | 0.0049 |
| 0.0099 | 10.0 | 2780 | 0.0048 |
| 0.0079 | 11.0 | 3058 | 0.0048 |
| 0.0079 | 12.0 | 3336 | 0.0048 |
| 0.0078 | 13.0 | 3614 | 0.0047 |
| 0.0078 | 14.0 | 3892 | 0.0047 |
| 0.006 | 15.0 | 4170 | 0.0047 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
