<!-- 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_v5
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: 3.4805
- F1: 0.3751
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 |
---|---|---|---|---|
3.9061 | 1.0 | 4050 | 3.8927 | 0.0909 |
3.0607 | 2.0 | 8100 | 3.1700 | 0.2214 |
2.4112 | 3.0 | 12150 | 2.8376 | 0.2764 |
1.9961 | 4.0 | 16200 | 2.6672 | 0.3388 |
1.5209 | 5.0 | 20250 | 2.5776 | 0.3428 |
1.2317 | 6.0 | 24300 | 2.5766 | 0.3578 |
0.9831 | 7.0 | 28350 | 2.6033 | 0.3691 |
0.7033 | 8.0 | 32400 | 2.7067 | 0.3633 |
0.5462 | 9.0 | 36450 | 2.7621 | 0.3672 |
0.4332 | 10.0 | 40500 | 2.8558 | 0.3750 |
0.3114 | 11.0 | 44550 | 2.9402 | 0.3729 |
0.2379 | 12.0 | 48600 | 3.0508 | 0.3738 |
0.1877 | 13.0 | 52650 | 3.1642 | 0.3703 |
0.1923 | 14.0 | 56700 | 3.2413 | 0.3754 |
0.1489 | 15.0 | 60750 | 3.3047 | 0.3856 |
0.1202 | 16.0 | 64800 | 3.3581 | 0.3764 |
0.1065 | 17.0 | 68850 | 3.4211 | 0.3767 |
0.1107 | 18.0 | 72900 | 3.4589 | 0.3725 |
0.1004 | 19.0 | 76950 | 3.4768 | 0.3723 |
0.1082 | 20.0 | 81000 | 3.4805 | 0.3751 |
Framework versions
- Transformers 4.27.1
- Pytorch 2.1.0.dev20230414+cu117
- Datasets 2.9.0
- Tokenizers 0.13.3