<!-- 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. -->
RuBioRoBERTa
This model is a fine-tuned version of alexyalunin/RuBioRoBERTa on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3612
- Precision: 0.6352
- Recall: 0.7255
- F1: 0.6773
- Accuracy: 0.9355
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: 3
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 2.0 | 50 | 0.7066 | 0.0 | 0.0 | 0.0 | 0.7265 |
| No log | 4.0 | 100 | 0.5865 | 0.0276 | 0.0588 | 0.0376 | 0.7609 |
| No log | 6.0 | 150 | 0.3659 | 0.1347 | 0.2304 | 0.1700 | 0.8575 |
| No log | 8.0 | 200 | 0.2924 | 0.2550 | 0.3775 | 0.3043 | 0.8876 |
| No log | 10.0 | 250 | 0.2554 | 0.4084 | 0.5245 | 0.4592 | 0.9091 |
| No log | 12.0 | 300 | 0.2185 | 0.4843 | 0.6814 | 0.5662 | 0.9157 |
| No log | 14.0 | 350 | 0.2519 | 0.5128 | 0.6863 | 0.5870 | 0.9212 |
| No log | 16.0 | 400 | 0.2472 | 0.5176 | 0.7206 | 0.6025 | 0.9183 |
| No log | 18.0 | 450 | 0.2583 | 0.5387 | 0.7157 | 0.6147 | 0.9343 |
| 0.3156 | 20.0 | 500 | 0.2067 | 0.552 | 0.6765 | 0.6079 | 0.9398 |
| 0.3156 | 22.0 | 550 | 0.3767 | 0.5902 | 0.7696 | 0.6681 | 0.9278 |
| 0.3156 | 24.0 | 600 | 0.2705 | 0.5472 | 0.6814 | 0.6070 | 0.9343 |
| 0.3156 | 26.0 | 650 | 0.3329 | 0.6016 | 0.7255 | 0.6578 | 0.9372 |
| 0.3156 | 28.0 | 700 | 0.3566 | 0.5762 | 0.7598 | 0.6554 | 0.9269 |
| 0.3156 | 30.0 | 750 | 0.4002 | 0.5823 | 0.7108 | 0.6402 | 0.9321 |
| 0.3156 | 32.0 | 800 | 0.4065 | 0.6091 | 0.7255 | 0.6622 | 0.9352 |
| 0.3156 | 34.0 | 850 | 0.3235 | 0.6198 | 0.7353 | 0.6726 | 0.9409 |
| 0.3156 | 36.0 | 900 | 0.3196 | 0.5714 | 0.7451 | 0.6468 | 0.9298 |
| 0.3156 | 38.0 | 950 | 0.3946 | 0.6128 | 0.7059 | 0.6560 | 0.9278 |
| 0.0215 | 40.0 | 1000 | 0.3969 | 0.6245 | 0.7745 | 0.6915 | 0.9386 |
| 0.0215 | 42.0 | 1050 | 0.3967 | 0.5698 | 0.7402 | 0.6439 | 0.9220 |
| 0.0215 | 44.0 | 1100 | 0.3827 | 0.5843 | 0.7304 | 0.6492 | 0.9300 |
| 0.0215 | 46.0 | 1150 | 0.3173 | 0.6771 | 0.7402 | 0.7073 | 0.9461 |
| 0.0215 | 48.0 | 1200 | 0.3455 | 0.6552 | 0.7451 | 0.6972 | 0.9404 |
| 0.0215 | 50.0 | 1250 | 0.3419 | 0.5885 | 0.75 | 0.6595 | 0.9323 |
| 0.0215 | 52.0 | 1300 | 0.4034 | 0.6234 | 0.7304 | 0.6727 | 0.9409 |
| 0.0215 | 54.0 | 1350 | 0.4425 | 0.6475 | 0.7745 | 0.7054 | 0.9372 |
| 0.0215 | 56.0 | 1400 | 0.5201 | 0.6135 | 0.7549 | 0.6769 | 0.9249 |
| 0.0215 | 58.0 | 1450 | 0.3755 | 0.6724 | 0.7647 | 0.7156 | 0.9384 |
| 0.0152 | 60.0 | 1500 | 0.3500 | 0.5833 | 0.7549 | 0.6581 | 0.9289 |
| 0.0152 | 62.0 | 1550 | 0.4111 | 0.5641 | 0.6471 | 0.6027 | 0.9229 |
| 0.0152 | 64.0 | 1600 | 0.3612 | 0.6352 | 0.7255 | 0.6773 | 0.9355 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
