|
--- |
|
license: apache-2.0 |
|
base_model: google-bert/bert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: bert-base-uncased-finetuned-ner |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# bert-base-uncased-finetuned-ner |
|
|
|
This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7238 |
|
- Precision: 0.3864 |
|
- Recall: 0.2742 |
|
- F1: 0.3208 |
|
- Accuracy: 0.9134 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 25 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 16 | 0.6017 | 0.4286 | 0.2258 | 0.2958 | 0.9187 | |
|
| No log | 2.0 | 32 | 0.6134 | 0.3311 | 0.2688 | 0.2967 | 0.9075 | |
|
| No log | 3.0 | 48 | 0.5969 | 0.3525 | 0.2634 | 0.3015 | 0.9096 | |
|
| No log | 4.0 | 64 | 0.6446 | 0.3208 | 0.2742 | 0.2957 | 0.9071 | |
|
| No log | 5.0 | 80 | 0.6219 | 0.4182 | 0.2473 | 0.3108 | 0.9176 | |
|
| No log | 6.0 | 96 | 0.6519 | 0.3401 | 0.2688 | 0.3003 | 0.9103 | |
|
| No log | 7.0 | 112 | 0.6576 | 0.3551 | 0.2634 | 0.3025 | 0.9120 | |
|
| No log | 8.0 | 128 | 0.6534 | 0.3676 | 0.2688 | 0.3106 | 0.9106 | |
|
| No log | 9.0 | 144 | 0.6522 | 0.3732 | 0.2849 | 0.3232 | 0.9124 | |
|
| No log | 10.0 | 160 | 0.6879 | 0.3503 | 0.2957 | 0.3207 | 0.9078 | |
|
| No log | 11.0 | 176 | 0.6825 | 0.3696 | 0.2742 | 0.3148 | 0.9124 | |
|
| No log | 12.0 | 192 | 0.7115 | 0.3732 | 0.2849 | 0.3232 | 0.9120 | |
|
| No log | 13.0 | 208 | 0.7013 | 0.3984 | 0.2742 | 0.3248 | 0.9138 | |
|
| No log | 14.0 | 224 | 0.7016 | 0.3732 | 0.2849 | 0.3232 | 0.9117 | |
|
| No log | 15.0 | 240 | 0.7313 | 0.3643 | 0.2742 | 0.3129 | 0.9110 | |
|
| No log | 16.0 | 256 | 0.7267 | 0.3442 | 0.2849 | 0.3118 | 0.9082 | |
|
| No log | 17.0 | 272 | 0.7159 | 0.3624 | 0.2903 | 0.3224 | 0.9096 | |
|
| No log | 18.0 | 288 | 0.6946 | 0.3542 | 0.2742 | 0.3091 | 0.9099 | |
|
| No log | 19.0 | 304 | 0.7017 | 0.3852 | 0.2796 | 0.3240 | 0.9127 | |
|
| No log | 20.0 | 320 | 0.7229 | 0.3467 | 0.2796 | 0.3095 | 0.9089 | |
|
| No log | 21.0 | 336 | 0.7188 | 0.3817 | 0.2688 | 0.3155 | 0.9124 | |
|
| No log | 22.0 | 352 | 0.7269 | 0.3669 | 0.2742 | 0.3138 | 0.9110 | |
|
| No log | 23.0 | 368 | 0.7248 | 0.3714 | 0.2796 | 0.3190 | 0.9113 | |
|
| No log | 24.0 | 384 | 0.7235 | 0.3835 | 0.2742 | 0.3197 | 0.9131 | |
|
| No log | 25.0 | 400 | 0.7238 | 0.3864 | 0.2742 | 0.3208 | 0.9134 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
