<!-- 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. -->
bert-base-german-cased-finetuned-subj_v6_7Epoch_v3
This model is a fine-tuned version of bert-base-german-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2732
- Precision: 0.7654
- Recall: 0.7829
- F1: 0.7740
- Accuracy: 0.9119
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: 16
- 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 |
---|---|---|---|---|---|---|---|
No log | 1.0 | 33 | 0.3281 | 0.6656 | 0.5914 | 0.6263 | 0.8623 |
No log | 2.0 | 66 | 0.2623 | 0.7440 | 0.7057 | 0.7243 | 0.8940 |
No log | 3.0 | 99 | 0.2460 | 0.7536 | 0.7514 | 0.7525 | 0.9067 |
No log | 4.0 | 132 | 0.2440 | 0.7778 | 0.76 | 0.7688 | 0.9124 |
No log | 5.0 | 165 | 0.2582 | 0.7723 | 0.7657 | 0.7690 | 0.9107 |
No log | 6.0 | 198 | 0.2681 | 0.7690 | 0.78 | 0.7745 | 0.9119 |
No log | 7.0 | 231 | 0.2732 | 0.7654 | 0.7829 | 0.7740 | 0.9119 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1