metadata
license: mit
base_model: deepset/gbert-large
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: gbert-large_ner
results: []
gbert-large_ner
This model is a fine-tuned version of deepset/gbert-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3755
- Precision: 0.9010
- Recall: 0.8948
- F1: 0.8975
- Accuracy: 0.9521
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- 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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 438 | 0.2334 | 0.8727 | 0.8653 | 0.8649 | 0.9303 |
| 0.3598 | 2.0 | 876 | 0.2149 | 0.8885 | 0.8649 | 0.8757 | 0.9391 |
| 0.1678 | 3.0 | 1314 | 0.2257 | 0.8820 | 0.8906 | 0.8847 | 0.9461 |
| 0.1054 | 4.0 | 1752 | 0.2580 | 0.8902 | 0.8884 | 0.8884 | 0.9463 |
| 0.0645 | 5.0 | 2190 | 0.2881 | 0.8896 | 0.8820 | 0.8833 | 0.9451 |
| 0.0436 | 6.0 | 2628 | 0.2767 | 0.8922 | 0.8911 | 0.8914 | 0.9479 |
| 0.0245 | 7.0 | 3066 | 0.3190 | 0.9026 | 0.9038 | 0.9030 | 0.9534 |
| 0.0108 | 8.0 | 3504 | 0.3547 | 0.8879 | 0.8886 | 0.8876 | 0.9474 |
| 0.0108 | 9.0 | 3942 | 0.3780 | 0.8943 | 0.8886 | 0.8910 | 0.9494 |
| 0.0074 | 10.0 | 4380 | 0.3755 | 0.9010 | 0.8948 | 0.8975 | 0.9521 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1