bert-base-german-cased-finetuned-subj_v5_11Epoch
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: 0.3467
- Precision: 0.8240
- Recall: 0.8287
- F1: 0.8263
- Accuracy: 0.9198
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: 11
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 32 | 0.3485 | 0.6992 | 0.7051 | 0.7021 | 0.8639 |
| No log | 2.0 | 64 | 0.2679 | 0.7947 | 0.7612 | 0.7776 | 0.8994 |
| No log | 3.0 | 96 | 0.2555 | 0.8073 | 0.8118 | 0.8095 | 0.9112 |
| No log | 4.0 | 128 | 0.2591 | 0.8290 | 0.8034 | 0.8160 | 0.9132 |
| No log | 5.0 | 160 | 0.2808 | 0.8450 | 0.8118 | 0.8281 | 0.9158 |
| No log | 6.0 | 192 | 0.2953 | 0.8386 | 0.8174 | 0.8279 | 0.9172 |
| No log | 7.0 | 224 | 0.3164 | 0.8347 | 0.8371 | 0.8359 | 0.9204 |
| No log | 8.0 | 256 | 0.3267 | 0.8329 | 0.8258 | 0.8293 | 0.9178 |
| No log | 9.0 | 288 | 0.3373 | 0.8268 | 0.8315 | 0.8291 | 0.9198 |
| No log | 10.0 | 320 | 0.3450 | 0.8324 | 0.8230 | 0.8277 | 0.9211 |
| No log | 11.0 | 352 | 0.3467 | 0.8240 | 0.8287 | 0.8263 | 0.9198 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6