|
--- |
|
license: apache-2.0 |
|
base_model: google-bert/bert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: nlpcw_bert-base-uncased-abbr |
|
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. --> |
|
|
|
# nlpcw_bert-base-uncased-abbr |
|
|
|
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: 0.2675 |
|
- Precision: 0.9390 |
|
- Recall: 0.9349 |
|
- F1: 0.9369 |
|
- Accuracy: 0.9317 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.6325 | 1.0 | 67 | 0.2629 | 0.9036 | 0.9090 | 0.9063 | 0.9043 | |
|
| 0.3169 | 2.0 | 134 | 0.2297 | 0.9309 | 0.9137 | 0.9223 | 0.9182 | |
|
| 0.1994 | 3.0 | 201 | 0.2282 | 0.9310 | 0.9193 | 0.9251 | 0.9223 | |
|
| 0.17 | 4.0 | 268 | 0.2193 | 0.9366 | 0.9286 | 0.9326 | 0.9278 | |
|
| 0.1457 | 5.0 | 335 | 0.2350 | 0.9395 | 0.9373 | 0.9384 | 0.9331 | |
|
| 0.1086 | 6.0 | 402 | 0.2435 | 0.9418 | 0.9340 | 0.9379 | 0.9331 | |
|
| 0.0908 | 7.0 | 469 | 0.2537 | 0.9357 | 0.9283 | 0.9319 | 0.9270 | |
|
| 0.0791 | 8.0 | 536 | 0.2675 | 0.9390 | 0.9349 | 0.9369 | 0.9317 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
|
|