|
--- |
|
license: mit |
|
base_model: dslim/bert-base-NER |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: Products_NER8 |
|
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. --> |
|
|
|
# Products_NER8 |
|
|
|
This model is a fine-tuned version of [dslim/bert-base-NER](https://huggingface.co/dslim/bert-base-NER) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2028 |
|
- Precision: 0.9227 |
|
- Recall: 0.9267 |
|
- F1: 0.9247 |
|
- Accuracy: 0.9446 |
|
|
|
## 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: 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: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.1326 | 1.0 | 1235 | 0.1052 | 0.8887 | 0.9121 | 0.9003 | 0.9386 | |
|
| 0.0959 | 2.0 | 2470 | 0.0927 | 0.8742 | 0.9085 | 0.8910 | 0.9417 | |
|
| 0.0824 | 3.0 | 3705 | 0.0931 | 0.8970 | 0.9174 | 0.9070 | 0.9433 | |
|
| 0.079 | 4.0 | 4940 | 0.0948 | 0.9067 | 0.9209 | 0.9137 | 0.9432 | |
|
| 0.0762 | 5.0 | 6175 | 0.0962 | 0.8963 | 0.9179 | 0.9070 | 0.9437 | |
|
| 0.0721 | 6.0 | 7410 | 0.1030 | 0.9095 | 0.9223 | 0.9159 | 0.9443 | |
|
| 0.0683 | 7.0 | 8645 | 0.1070 | 0.9128 | 0.9233 | 0.9181 | 0.9439 | |
|
| 0.0637 | 8.0 | 9880 | 0.1178 | 0.9157 | 0.9240 | 0.9199 | 0.9439 | |
|
| 0.059 | 9.0 | 11115 | 0.1215 | 0.9176 | 0.9248 | 0.9212 | 0.9443 | |
|
| 0.0527 | 10.0 | 12350 | 0.1367 | 0.9189 | 0.9247 | 0.9218 | 0.9438 | |
|
| 0.0475 | 11.0 | 13585 | 0.1504 | 0.9199 | 0.9250 | 0.9224 | 0.9441 | |
|
| 0.0431 | 12.0 | 14820 | 0.1484 | 0.9207 | 0.9259 | 0.9233 | 0.9446 | |
|
| 0.0389 | 13.0 | 16055 | 0.1706 | 0.9224 | 0.9267 | 0.9246 | 0.9446 | |
|
| 0.0368 | 14.0 | 17290 | 0.1847 | 0.9223 | 0.9265 | 0.9244 | 0.9445 | |
|
| 0.0351 | 15.0 | 18525 | 0.2028 | 0.9227 | 0.9267 | 0.9247 | 0.9446 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.0 |
|
- Pytorch 1.13.1+cu117 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.13.3 |
|
|
