<!-- 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_v9
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: 3.5929
- F1: 0.5297
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 |
---|---|---|---|---|
2.2808 | 1.0 | 5400 | 2.1415 | 0.3679 |
1.6929 | 2.0 | 10800 | 1.7846 | 0.4759 |
1.3599 | 3.0 | 16200 | 1.7242 | 0.5074 |
0.9222 | 4.0 | 21600 | 1.7964 | 0.5209 |
0.7198 | 5.0 | 27000 | 1.9035 | 0.5388 |
0.4649 | 6.0 | 32400 | 2.1145 | 0.5251 |
0.3202 | 7.0 | 37800 | 2.3236 | 0.5345 |
0.3077 | 8.0 | 43200 | 2.6312 | 0.5326 |
0.2691 | 9.0 | 48600 | 2.8500 | 0.5318 |
0.145 | 10.0 | 54000 | 3.0650 | 0.5266 |
0.1024 | 11.0 | 59400 | 3.2150 | 0.5305 |
0.0765 | 12.0 | 64800 | 3.3284 | 0.5297 |
0.0958 | 13.0 | 70200 | 3.4167 | 0.5227 |
0.0612 | 14.0 | 75600 | 3.4837 | 0.5260 |
0.089 | 15.0 | 81000 | 3.5519 | 0.5236 |
0.078 | 16.0 | 86400 | 3.5877 | 0.5224 |
0.0495 | 17.0 | 91800 | 3.5553 | 0.5270 |
0.0889 | 18.0 | 97200 | 3.5820 | 0.5237 |
0.0763 | 19.0 | 102600 | 3.5900 | 0.5260 |
0.0375 | 20.0 | 108000 | 3.5929 | 0.5297 |
Framework versions
- Transformers 4.27.1
- Pytorch 2.1.0.dev20230414+cu117
- Datasets 2.9.0
- Tokenizers 0.13.3