<!-- 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. -->
text_to_subfunction_v6
This model is a fine-tuned version of cointegrated/rubert-tiny2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.2720
- F1: 0.4415
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | F1 |
---|---|---|---|---|
3.5055 | 1.0 | 4365 | 3.4067 | 0.1639 |
2.5598 | 2.0 | 8730 | 2.6935 | 0.2833 |
2.1499 | 3.0 | 13095 | 2.3594 | 0.3420 |
1.6575 | 4.0 | 17460 | 2.2243 | 0.3921 |
1.2463 | 5.0 | 21825 | 2.1722 | 0.4105 |
0.9624 | 6.0 | 26190 | 2.1955 | 0.4341 |
0.7407 | 7.0 | 30555 | 2.2434 | 0.4449 |
0.5608 | 8.0 | 34920 | 2.3604 | 0.4329 |
0.4233 | 9.0 | 39285 | 2.4747 | 0.4361 |
0.2433 | 10.0 | 43650 | 2.5562 | 0.4404 |
0.2154 | 11.0 | 48015 | 2.6678 | 0.4374 |
0.1811 | 12.0 | 52380 | 2.8158 | 0.4341 |
0.1374 | 13.0 | 56745 | 2.9037 | 0.4425 |
0.1406 | 14.0 | 61110 | 3.0182 | 0.4366 |
0.1135 | 15.0 | 65475 | 3.0941 | 0.4440 |
0.0992 | 16.0 | 69840 | 3.1516 | 0.4437 |
0.1159 | 17.0 | 74205 | 3.2001 | 0.4418 |
0.0809 | 18.0 | 78570 | 3.2489 | 0.4373 |
0.1035 | 19.0 | 82935 | 3.2650 | 0.4407 |
0.0558 | 20.0 | 87300 | 3.2720 | 0.4415 |
Framework versions
- Transformers 4.27.1
- Pytorch 2.1.0.dev20230414+cu117
- Datasets 2.9.0
- Tokenizers 0.13.3