|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: answerdotai/ModernBERT-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- conll2003 |
|
|
metrics: |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: modernbert-base-conll2003-english-ner |
|
|
results: |
|
|
- task: |
|
|
name: Token Classification |
|
|
type: token-classification |
|
|
dataset: |
|
|
name: conll2003 |
|
|
type: conll2003 |
|
|
config: conll2003 |
|
|
split: test |
|
|
args: conll2003 |
|
|
metrics: |
|
|
- name: Precision |
|
|
type: precision |
|
|
value: 0.7553173672751633 |
|
|
- name: Recall |
|
|
type: recall |
|
|
value: 0.7985127478753541 |
|
|
- name: F1 |
|
|
type: f1 |
|
|
value: 0.776314657027283 |
|
|
- name: Accuracy |
|
|
type: accuracy |
|
|
value: 0.9627651555938409 |
|
|
--- |
|
|
|
|
|
<!-- 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. --> |
|
|
|
|
|
# modernbert-base-conll2003-english-ner |
|
|
|
|
|
This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the conll2003 dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.1457 |
|
|
- Precision: 0.7553 |
|
|
- Recall: 0.7985 |
|
|
- F1: 0.7763 |
|
|
- Accuracy: 0.9628 |
|
|
|
|
|
## 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: 16 |
|
|
- seed: 42 |
|
|
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 5 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
|
| No log | 1.0 | 439 | 0.1737 | 0.6772 | 0.7236 | 0.6996 | 0.9521 | |
|
|
| 0.2272 | 2.0 | 878 | 0.1518 | 0.7403 | 0.7840 | 0.7615 | 0.9605 | |
|
|
| 0.1047 | 3.0 | 1317 | 0.1459 | 0.7522 | 0.7937 | 0.7724 | 0.9625 | |
|
|
| 0.0835 | 4.0 | 1756 | 0.1460 | 0.7514 | 0.7964 | 0.7733 | 0.9626 | |
|
|
| 0.076 | 5.0 | 2195 | 0.1457 | 0.7553 | 0.7985 | 0.7763 | 0.9628 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.48.0.dev0 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.1.0 |
|
|
- Tokenizers 0.21.0 |
|
|
|
