metadata
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-finetuned-ner
results: []
bert-base-finetuned-ner
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3723
- Precision: 0.5534
- Recall: 0.5362
- F1: 0.5447
- Accuracy: 0.9281
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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 121 | 0.4063 | 0.2711 | 0.2638 | 0.2674 | 0.8968 |
| No log | 2.0 | 242 | 0.3501 | 0.4935 | 0.3220 | 0.3897 | 0.9196 |
| No log | 3.0 | 363 | 0.2928 | 0.4839 | 0.4255 | 0.4528 | 0.9272 |
| No log | 4.0 | 484 | 0.3419 | 0.5407 | 0.3957 | 0.4570 | 0.9247 |
| 0.3258 | 5.0 | 605 | 0.3310 | 0.5431 | 0.4553 | 0.4954 | 0.9294 |
| 0.3258 | 6.0 | 726 | 0.3424 | 0.5248 | 0.4809 | 0.5019 | 0.9274 |
| 0.3258 | 7.0 | 847 | 0.3587 | 0.5471 | 0.5191 | 0.5328 | 0.9309 |
| 0.3258 | 8.0 | 968 | 0.3639 | 0.5396 | 0.5220 | 0.5306 | 0.9281 |
| 0.1033 | 9.0 | 1089 | 0.3695 | 0.5471 | 0.5277 | 0.5372 | 0.9276 |
| 0.1033 | 10.0 | 1210 | 0.3723 | 0.5534 | 0.5362 | 0.5447 | 0.9281 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1