metadata
base_model: bert-base-cased
license: apache-2.0
metrics:
- precision
- recall
- f1
- accuracy
tags:
- generated_from_trainer
model-index:
- name: bert-finetuned-ner4
results: []
bert-finetuned-ner4
This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1250
- Precision: 0.5977
- Recall: 0.7121
- F1: 0.6499
- Accuracy: 0.9640
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: 8
- 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 |
|---|---|---|---|---|---|---|---|
| 0.2424 | 1.0 | 2489 | 0.2411 | 0.1538 | 0.3948 | 0.2214 | 0.9097 |
| 0.1952 | 2.0 | 4978 | 0.2152 | 0.2033 | 0.4518 | 0.2804 | 0.9223 |
| 0.1771 | 3.0 | 7467 | 0.1737 | 0.2826 | 0.4268 | 0.3401 | 0.9387 |
| 0.1404 | 4.0 | 9956 | 0.1531 | 0.3981 | 0.5237 | 0.4524 | 0.9479 |
| 0.126 | 5.0 | 12445 | 0.1395 | 0.4761 | 0.6188 | 0.5382 | 0.9542 |
| 0.1084 | 6.0 | 14934 | 0.1339 | 0.4772 | 0.6758 | 0.5594 | 0.9555 |
| 0.0981 | 7.0 | 17423 | 0.1353 | 0.5228 | 0.6861 | 0.5934 | 0.9591 |
| 0.0865 | 8.0 | 19912 | 0.1308 | 0.5924 | 0.6871 | 0.6363 | 0.9628 |
| 0.0826 | 9.0 | 22401 | 0.1250 | 0.5897 | 0.7126 | 0.6453 | 0.9630 |
| 0.0754 | 10.0 | 24890 | 0.1250 | 0.5977 | 0.7121 | 0.6499 | 0.9640 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1