|
--- |
|
license: apache-2.0 |
|
base_model: distilbert/distilroberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: distilroberta-base-finetuned-ner-harem |
|
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. --> |
|
|
|
# distilroberta-base-finetuned-ner-harem |
|
|
|
This model is a fine-tuned version of [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1882 |
|
- Precision: 0.6628 |
|
- Recall: 0.6836 |
|
- F1: 0.6730 |
|
- Accuracy: 0.9512 |
|
|
|
## 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: 100 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 282 | 0.2799 | 0.4758 | 0.4403 | 0.4574 | 0.9202 | |
|
| 0.3348 | 2.0 | 564 | 0.2225 | 0.5810 | 0.5940 | 0.5875 | 0.9396 | |
|
| 0.3348 | 3.0 | 846 | 0.2105 | 0.6015 | 0.6149 | 0.6081 | 0.9389 | |
|
| 0.1571 | 4.0 | 1128 | 0.1979 | 0.6732 | 0.6642 | 0.6687 | 0.9534 | |
|
| 0.1571 | 5.0 | 1410 | 0.1882 | 0.6628 | 0.6836 | 0.6730 | 0.9512 | |
|
| 0.0948 | 6.0 | 1692 | 0.2099 | 0.6196 | 0.6612 | 0.6397 | 0.9495 | |
|
| 0.0948 | 7.0 | 1974 | 0.2251 | 0.6900 | 0.6776 | 0.6837 | 0.9540 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.1 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
