metadata
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-finetuned-pos
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: validation
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9028893991580559
- name: Recall
type: recall
value: 0.91583569886212
- name: F1
type: f1
value: 0.9093164709424872
- name: Accuracy
type: accuracy
value: 0.9267220257724449
ModernBERT-base-finetuned-pos
This model is a fine-tuned version of answerdotai/ModernBERT-base on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2935
- Precision: 0.9029
- Recall: 0.9158
- F1: 0.9093
- Accuracy: 0.9267
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.6485 | 1.0 | 878 | 0.3352 | 0.8911 | 0.9007 | 0.8959 | 0.9159 |
| 0.1997 | 2.0 | 1756 | 0.2890 | 0.9031 | 0.9110 | 0.9070 | 0.9246 |
| 0.1274 | 3.0 | 2634 | 0.2935 | 0.9029 | 0.9158 | 0.9093 | 0.9267 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0