test_run
This model is a fine-tuned version of AIRI-Institute/gena-lm-bigbird-base-t2t on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0475
- F1: 0.9938
- Mcc Score: 0.9866
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Mcc Score |
|---|---|---|---|---|---|
| 0.5793 | 1.0 | 62 | 0.2541 | 0.9150 | 0.8319 |
| 0.2401 | 2.0 | 124 | 0.1078 | 0.9645 | 0.9226 |
| 0.1257 | 3.0 | 186 | 0.1660 | 0.9631 | 0.9258 |
| 0.0658 | 4.0 | 248 | 0.0823 | 0.9797 | 0.9564 |
| 0.0225 | 5.0 | 310 | 0.0759 | 0.9861 | 0.9697 |
| 0.0296 | 6.0 | 372 | 0.0754 | 0.9876 | 0.9731 |
| 0.0247 | 7.0 | 434 | 0.1813 | 0.9697 | 0.9383 |
| 0.0124 | 8.0 | 496 | 0.1256 | 0.9811 | 0.9605 |
| 0.0253 | 9.0 | 558 | 0.0912 | 0.9843 | 0.9668 |
| 0.0099 | 10.0 | 620 | 0.0475 | 0.9938 | 0.9866 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 4