metadata
license: apache-2.0
base_model: distilbert-base-cased
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: fine_tuned_model
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: 0.9086735530414822
- name: Recall
type: recall
value: 0.9326825984516998
- name: F1
type: f1
value: 0.9205215513661656
- name: Accuracy
type: accuracy
value: 0.9826043444987344
fine_tuned_model
This model is a fine-tuned version of distilbert-base-cased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0696
- Precision: 0.9087
- Recall: 0.9327
- F1: 0.9205
- Accuracy: 0.9826
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2455 | 1.0 | 878 | 0.0875 | 0.8705 | 0.9098 | 0.8897 | 0.9748 |
| 0.059 | 2.0 | 1756 | 0.0692 | 0.8992 | 0.9303 | 0.9145 | 0.9814 |
| 0.0324 | 3.0 | 2634 | 0.0696 | 0.9087 | 0.9327 | 0.9205 | 0.9826 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3