metadata
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-german-cased-finetuned-subj_v1
results: []
bert-base-german-cased-finetuned-subj_v1
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: 0.1594
- Precision: 0.1875
- Recall: 0.0077
- F1: 0.0147
- Accuracy: 0.9508
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 136 | 0.1591 | 1.0 | 0.0051 | 0.0102 | 0.9523 |
| No log | 2.0 | 272 | 0.1571 | 0.375 | 0.0077 | 0.015 | 0.9518 |
| No log | 3.0 | 408 | 0.1594 | 0.1875 | 0.0077 | 0.0147 | 0.9508 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6