<!-- 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_v8
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: 3.6827
- F1: 0.4859
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 |
---|---|---|---|---|
2.6282 | 1.0 | 4950 | 2.5323 | 0.2949 |
1.9369 | 2.0 | 9900 | 2.0942 | 0.3981 |
1.3918 | 3.0 | 14850 | 1.9598 | 0.4260 |
1.1864 | 4.0 | 19800 | 1.9722 | 0.4609 |
0.8131 | 5.0 | 24750 | 2.0583 | 0.4766 |
0.5978 | 6.0 | 29700 | 2.2249 | 0.4847 |
0.4297 | 7.0 | 34650 | 2.4185 | 0.4915 |
0.2789 | 8.0 | 39600 | 2.6352 | 0.4881 |
0.1875 | 9.0 | 44550 | 2.8330 | 0.4845 |
0.1423 | 10.0 | 49500 | 3.0958 | 0.4782 |
0.1223 | 11.0 | 54450 | 3.2171 | 0.4886 |
0.1069 | 12.0 | 59400 | 3.3491 | 0.4846 |
0.1047 | 13.0 | 64350 | 3.4500 | 0.4820 |
0.1141 | 14.0 | 69300 | 3.5516 | 0.4831 |
0.0631 | 15.0 | 74250 | 3.5998 | 0.4815 |
0.074 | 16.0 | 79200 | 3.6416 | 0.4844 |
0.0985 | 17.0 | 84150 | 3.6245 | 0.4875 |
0.0526 | 18.0 | 89100 | 3.6650 | 0.4837 |
0.0502 | 19.0 | 94050 | 3.6893 | 0.4837 |
0.0493 | 20.0 | 99000 | 3.6827 | 0.4859 |
Framework versions
- Transformers 4.27.1
- Pytorch 2.1.0.dev20230414+cu117
- Datasets 2.9.0
- Tokenizers 0.13.3