romanian_bert-finetuned-on-REDv2-romanian
This model is a fine-tuned version of dumitrescustefan/bert-base-romanian-cased-v1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2788
- F1: 0.6915
- Roc Auc: 0.8084
- Accuracy: 0.5801
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.32 | 1.0 | 511 | 0.2475 | 0.6561 | 0.7697 | 0.5433 |
| 0.2069 | 2.0 | 1022 | 0.2434 | 0.6661 | 0.7827 | 0.5672 |
| 0.1433 | 3.0 | 1533 | 0.2548 | 0.6891 | 0.8026 | 0.5856 |
| 0.0968 | 4.0 | 2044 | 0.2677 | 0.6847 | 0.8050 | 0.5727 |
| 0.0758 | 5.0 | 2555 | 0.2788 | 0.6915 | 0.8084 | 0.5801 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
- Downloads last month
- 14
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.