metadata
license: apache-2.0
base_model: bert-large-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-large-cased_ner
results: []
bert-large-cased_ner
This model is a fine-tuned version of bert-large-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6758
- Precision: 0.8709
- Recall: 0.8781
- F1: 0.8737
- Accuracy: 0.9135
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 | 0.3035 | 0.8701 | 0.8816 | 0.8748 | 0.9096 |
| 0.4531 | 2.0 | 876 | 0.3008 | 0.8820 | 0.8839 | 0.8819 | 0.9197 |
| 0.2183 | 3.0 | 1314 | 0.4003 | 0.8706 | 0.8759 | 0.8715 | 0.9119 |
| 0.1254 | 4.0 | 1752 | 0.3581 | 0.8843 | 0.8912 | 0.8870 | 0.9219 |
| 0.0704 | 5.0 | 2190 | 0.4627 | 0.8668 | 0.8683 | 0.8669 | 0.9092 |
| 0.0408 | 6.0 | 2628 | 0.5183 | 0.8703 | 0.8783 | 0.8737 | 0.9144 |
| 0.0264 | 7.0 | 3066 | 0.6201 | 0.8705 | 0.8784 | 0.8738 | 0.9122 |
| 0.0092 | 8.0 | 3504 | 0.6004 | 0.8673 | 0.8766 | 0.8712 | 0.9113 |
| 0.0092 | 9.0 | 3942 | 0.6578 | 0.8716 | 0.8782 | 0.8744 | 0.9133 |
| 0.004 | 10.0 | 4380 | 0.6758 | 0.8709 | 0.8781 | 0.8737 | 0.9135 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1