|
--- |
|
license: apache-2.0 |
|
base_model: distilbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: distilbert-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. --> |
|
|
|
# distilbert-base-uncased-finetuned-ner |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4181 |
|
- Precision: 0.6106 |
|
- Recall: 0.6615 |
|
- F1: 0.635 |
|
- Accuracy: 0.9189 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 23 | 0.3610 | 0.4795 | 0.6094 | 0.5367 | 0.9045 | |
|
| No log | 2.0 | 46 | 0.3516 | 0.5330 | 0.5885 | 0.5594 | 0.9141 | |
|
| No log | 3.0 | 69 | 0.3591 | 0.5346 | 0.6042 | 0.5672 | 0.9147 | |
|
| No log | 4.0 | 92 | 0.3602 | 0.5226 | 0.6615 | 0.5839 | 0.9129 | |
|
| No log | 5.0 | 115 | 0.3706 | 0.5315 | 0.6146 | 0.5700 | 0.9123 | |
|
| No log | 6.0 | 138 | 0.3652 | 0.5631 | 0.6042 | 0.5829 | 0.9165 | |
|
| No log | 7.0 | 161 | 0.3618 | 0.5640 | 0.6198 | 0.5906 | 0.9153 | |
|
| No log | 8.0 | 184 | 0.3680 | 0.5755 | 0.6354 | 0.6040 | 0.9165 | |
|
| No log | 9.0 | 207 | 0.3782 | 0.5789 | 0.6302 | 0.6035 | 0.9183 | |
|
| No log | 10.0 | 230 | 0.3926 | 0.6020 | 0.6302 | 0.6158 | 0.9189 | |
|
| No log | 11.0 | 253 | 0.3816 | 0.5845 | 0.6667 | 0.6229 | 0.9171 | |
|
| No log | 12.0 | 276 | 0.3811 | 0.5942 | 0.6406 | 0.6165 | 0.9195 | |
|
| No log | 13.0 | 299 | 0.3857 | 0.5885 | 0.6406 | 0.6135 | 0.9189 | |
|
| No log | 14.0 | 322 | 0.3966 | 0.5714 | 0.6458 | 0.6064 | 0.9141 | |
|
| No log | 15.0 | 345 | 0.3927 | 0.6019 | 0.6615 | 0.6303 | 0.9183 | |
|
| No log | 16.0 | 368 | 0.3955 | 0.5907 | 0.6615 | 0.6241 | 0.9165 | |
|
| No log | 17.0 | 391 | 0.4124 | 0.5931 | 0.6302 | 0.6111 | 0.9171 | |
|
| No log | 18.0 | 414 | 0.4112 | 0.5733 | 0.6719 | 0.6187 | 0.9135 | |
|
| No log | 19.0 | 437 | 0.4177 | 0.5829 | 0.6406 | 0.6104 | 0.9159 | |
|
| No log | 20.0 | 460 | 0.4100 | 0.6028 | 0.6719 | 0.6355 | 0.9159 | |
|
| No log | 21.0 | 483 | 0.4159 | 0.5869 | 0.6510 | 0.6173 | 0.9165 | |
|
| 0.0279 | 22.0 | 506 | 0.4100 | 0.5853 | 0.6615 | 0.6210 | 0.9153 | |
|
| 0.0279 | 23.0 | 529 | 0.4127 | 0.6172 | 0.6719 | 0.6434 | 0.9189 | |
|
| 0.0279 | 24.0 | 552 | 0.4074 | 0.5945 | 0.6719 | 0.6308 | 0.9153 | |
|
| 0.0279 | 25.0 | 575 | 0.4056 | 0.5909 | 0.6771 | 0.6311 | 0.9165 | |
|
| 0.0279 | 26.0 | 598 | 0.4079 | 0.5740 | 0.6667 | 0.6169 | 0.9153 | |
|
| 0.0279 | 27.0 | 621 | 0.4184 | 0.6117 | 0.6562 | 0.6332 | 0.9189 | |
|
| 0.0279 | 28.0 | 644 | 0.4177 | 0.6165 | 0.6615 | 0.6382 | 0.9195 | |
|
| 0.0279 | 29.0 | 667 | 0.4178 | 0.6106 | 0.6615 | 0.635 | 0.9189 | |
|
| 0.0279 | 30.0 | 690 | 0.4181 | 0.6106 | 0.6615 | 0.635 | 0.9189 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.2+cu118 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.0 |
|
|
