Czert_fine_tuned_cs_wikann
This model is a fine-tuned version of UWB-AIR/Czert-B-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2400
- Precision: 0.9088
- Recall: 0.9287
- F1: 0.9186
- Accuracy: 0.9683
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: 8
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.3209 | 0.2 | 500 | 0.2147 | 0.7711 | 0.8252 | 0.7972 | 0.9393 |
0.197 | 0.4 | 1000 | 0.1891 | 0.8147 | 0.8565 | 0.8351 | 0.9493 |
0.1774 | 0.6 | 1500 | 0.1887 | 0.8267 | 0.8608 | 0.8434 | 0.9496 |
0.1647 | 0.8 | 2000 | 0.1482 | 0.8396 | 0.8947 | 0.8663 | 0.9564 |
0.1592 | 1.0 | 2500 | 0.1489 | 0.8687 | 0.8977 | 0.8830 | 0.9600 |
0.0869 | 1.2 | 3000 | 0.1694 | 0.8706 | 0.9062 | 0.8880 | 0.9616 |
0.0935 | 1.4 | 3500 | 0.1547 | 0.8850 | 0.9116 | 0.8981 | 0.9638 |
0.0973 | 1.6 | 4000 | 0.1478 | 0.8723 | 0.9077 | 0.8896 | 0.9638 |
0.1047 | 1.8 | 4500 | 0.1446 | 0.8891 | 0.9048 | 0.8969 | 0.9632 |
0.0938 | 2.0 | 5000 | 0.1419 | 0.8785 | 0.9125 | 0.8952 | 0.9639 |
0.0496 | 2.2 | 5500 | 0.1775 | 0.8779 | 0.9172 | 0.8971 | 0.9639 |
0.054 | 2.4 | 6000 | 0.1620 | 0.8996 | 0.9113 | 0.9054 | 0.9650 |
0.0532 | 2.6 | 6500 | 0.1717 | 0.8918 | 0.9176 | 0.9045 | 0.9652 |
0.0527 | 2.8 | 7000 | 0.1774 | 0.8978 | 0.9216 | 0.9096 | 0.9658 |
0.0576 | 3.0 | 7500 | 0.1678 | 0.9013 | 0.9198 | 0.9105 | 0.9674 |
0.027 | 3.2 | 8000 | 0.1844 | 0.9004 | 0.9212 | 0.9107 | 0.9674 |
0.0356 | 3.4 | 8500 | 0.1700 | 0.8952 | 0.9203 | 0.9076 | 0.9672 |
0.0315 | 3.6 | 9000 | 0.1864 | 0.9012 | 0.9230 | 0.9120 | 0.9667 |
0.0307 | 3.8 | 9500 | 0.1886 | 0.8968 | 0.9238 | 0.9101 | 0.9662 |
0.0288 | 4.0 | 10000 | 0.1985 | 0.8990 | 0.9244 | 0.9115 | 0.9669 |
0.0141 | 4.2 | 10500 | 0.2069 | 0.8953 | 0.9260 | 0.9104 | 0.9672 |
0.0187 | 4.4 | 11000 | 0.2051 | 0.9024 | 0.9207 | 0.9114 | 0.9668 |
0.0169 | 4.6 | 11500 | 0.2010 | 0.9036 | 0.9252 | 0.9143 | 0.9677 |
0.0233 | 4.8 | 12000 | 0.2028 | 0.8978 | 0.9268 | 0.9120 | 0.9671 |
0.02 | 5.0 | 12500 | 0.1958 | 0.9042 | 0.9263 | 0.9151 | 0.9678 |
0.0089 | 5.2 | 13000 | 0.2155 | 0.9043 | 0.9267 | 0.9154 | 0.9675 |
0.0084 | 5.4 | 13500 | 0.2289 | 0.9047 | 0.9285 | 0.9164 | 0.9674 |
0.0146 | 5.6 | 14000 | 0.2195 | 0.9032 | 0.9281 | 0.9155 | 0.9681 |
0.0066 | 5.8 | 14500 | 0.2239 | 0.9064 | 0.9280 | 0.9171 | 0.9681 |
0.01 | 6.0 | 15000 | 0.2256 | 0.9084 | 0.9270 | 0.9176 | 0.9681 |
0.0034 | 6.2 | 15500 | 0.2323 | 0.9065 | 0.9284 | 0.9173 | 0.9678 |
0.0065 | 6.4 | 16000 | 0.2339 | 0.9088 | 0.9277 | 0.9182 | 0.9680 |
0.0041 | 6.6 | 16500 | 0.2384 | 0.9086 | 0.9283 | 0.9184 | 0.9679 |
0.0038 | 6.8 | 17000 | 0.2396 | 0.9095 | 0.9287 | 0.9190 | 0.9683 |
0.0044 | 7.0 | 17500 | 0.2400 | 0.9088 | 0.9287 | 0.9186 | 0.9683 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 9
Inference API (serverless) is not available, repository is disabled.
Model tree for stulcrad/Czert_fine_tuned_cs_wikann
Base model
UWB-AIR/Czert-B-base-cased
Finetuned
this model