<!-- 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_v4
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: 3.1053
- F1: 0.3759
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 |
---|---|---|---|---|
4.4646 | 1.0 | 3330 | 4.3694 | 0.0721 |
3.6581 | 2.0 | 6660 | 3.6204 | 0.1511 |
2.9966 | 3.0 | 9990 | 3.2120 | 0.2086 |
2.5387 | 4.0 | 13320 | 2.9544 | 0.2708 |
2.0416 | 5.0 | 16650 | 2.8146 | 0.2977 |
1.6267 | 6.0 | 19980 | 2.7295 | 0.3328 |
1.3739 | 7.0 | 23310 | 2.6891 | 0.3428 |
1.0876 | 8.0 | 26640 | 2.7375 | 0.3475 |
0.8712 | 9.0 | 29970 | 2.7519 | 0.3505 |
0.65 | 10.0 | 33300 | 2.7600 | 0.3709 |
0.4981 | 11.0 | 36630 | 2.8050 | 0.3571 |
0.4128 | 12.0 | 39960 | 2.8641 | 0.3715 |
0.349 | 13.0 | 43290 | 2.9126 | 0.3744 |
0.2621 | 14.0 | 46620 | 2.9636 | 0.3807 |
0.2564 | 15.0 | 49950 | 2.9961 | 0.3786 |
0.1893 | 16.0 | 53280 | 3.0376 | 0.3724 |
0.1736 | 17.0 | 56610 | 3.0664 | 0.3750 |
0.1673 | 18.0 | 59940 | 3.0949 | 0.3762 |
0.1631 | 19.0 | 63270 | 3.1006 | 0.3745 |
0.1643 | 20.0 | 66600 | 3.1053 | 0.3759 |
Framework versions
- Transformers 4.27.1
- Pytorch 2.1.0.dev20230414+cu117
- Datasets 2.9.0
- Tokenizers 0.13.3