<!-- 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. -->
rubert-base-cased
This model is a fine-tuned version of DeepPavlov/rubert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6843
- Precision: 0.4428
- Recall: 0.4886
- F1: 0.4645
- Accuracy: 0.8881
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: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 39 | 0.5804 | 0.36 | 0.5068 | 0.4210 | 0.8676 |
No log | 2.0 | 78 | 0.6388 | 0.4288 | 0.4490 | 0.4387 | 0.8867 |
No log | 3.0 | 117 | 0.5745 | 0.3855 | 0.4840 | 0.4291 | 0.8868 |
No log | 4.0 | 156 | 0.6354 | 0.4213 | 0.4688 | 0.4438 | 0.8883 |
No log | 5.0 | 195 | 0.5668 | 0.4156 | 0.4612 | 0.4372 | 0.8855 |
No log | 6.0 | 234 | 0.5282 | 0.4154 | 0.4597 | 0.4364 | 0.8859 |
No log | 7.0 | 273 | 0.5794 | 0.4182 | 0.4551 | 0.4359 | 0.8853 |
No log | 8.0 | 312 | 0.6013 | 0.4426 | 0.4992 | 0.4692 | 0.8878 |
No log | 9.0 | 351 | 0.6306 | 0.4394 | 0.5023 | 0.4688 | 0.8875 |
No log | 10.0 | 390 | 0.6161 | 0.4428 | 0.4947 | 0.4673 | 0.8879 |
No log | 11.0 | 429 | 0.6091 | 0.4265 | 0.4810 | 0.4521 | 0.8881 |
No log | 12.0 | 468 | 0.6010 | 0.4231 | 0.5023 | 0.4593 | 0.8861 |
0.0385 | 13.0 | 507 | 0.6319 | 0.4358 | 0.4855 | 0.4593 | 0.8902 |
0.0385 | 14.0 | 546 | 0.6605 | 0.4376 | 0.5175 | 0.4742 | 0.8858 |
0.0385 | 15.0 | 585 | 0.6416 | 0.4465 | 0.5145 | 0.4781 | 0.8883 |
0.0385 | 16.0 | 624 | 0.6792 | 0.4542 | 0.4825 | 0.4679 | 0.8897 |
0.0385 | 17.0 | 663 | 0.6762 | 0.4341 | 0.5114 | 0.4696 | 0.8854 |
0.0385 | 18.0 | 702 | 0.6738 | 0.4372 | 0.5084 | 0.4701 | 0.8872 |
0.0385 | 19.0 | 741 | 0.6808 | 0.4434 | 0.4886 | 0.4649 | 0.8881 |
0.0385 | 20.0 | 780 | 0.6843 | 0.4428 | 0.4886 | 0.4645 | 0.8881 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3