SloBertAA_Top20_WithOOC_082023_MultilingualBertBase
This model is a fine-tuned version of bert-base-multilingual-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3744
- Accuracy: 0.8212
- F1: 0.8199
- Precision: 0.8193
- Recall: 0.8212
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: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
0.7811 | 1.0 | 23853 | 0.7292 | 0.7689 | 0.7650 | 0.7654 | 0.7689 |
0.6535 | 2.0 | 47706 | 0.6647 | 0.7909 | 0.7829 | 0.7919 | 0.7909 |
0.5057 | 3.0 | 71559 | 0.6487 | 0.8052 | 0.8045 | 0.8063 | 0.8052 |
0.3796 | 4.0 | 95412 | 0.7108 | 0.8082 | 0.8036 | 0.8078 | 0.8082 |
0.3103 | 5.0 | 119265 | 0.8168 | 0.8130 | 0.8097 | 0.8108 | 0.8130 |
0.2389 | 6.0 | 143118 | 0.9502 | 0.8130 | 0.8096 | 0.8099 | 0.8130 |
0.1871 | 7.0 | 166971 | 1.0749 | 0.8174 | 0.8167 | 0.8165 | 0.8174 |
0.1189 | 8.0 | 190824 | 1.2305 | 0.8170 | 0.8143 | 0.8153 | 0.8170 |
0.0813 | 9.0 | 214677 | 1.3229 | 0.8203 | 0.8189 | 0.8184 | 0.8203 |
0.0617 | 10.0 | 238530 | 1.3744 | 0.8212 | 0.8199 | 0.8193 | 0.8212 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.8.0
- Datasets 2.10.1
- Tokenizers 0.13.2
- Downloads last month
- 8
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.