metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-TT2-exam
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9221537106364237
- name: Recall
type: recall
value: 0.9369056941492337
- name: F1
type: f1
value: 0.9294711725209478
- name: Accuracy
type: accuracy
value: 0.983509936931069
distilbert-base-uncased-finetuned-TT2-exam
This model is a fine-tuned version of distilbert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0620
- Precision: 0.9222
- Recall: 0.9369
- F1: 0.9295
- Accuracy: 0.9835
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 |
|---|---|---|---|---|---|---|---|
| 0.2509 | 1.0 | 879 | 0.0733 | 0.8855 | 0.9212 | 0.9030 | 0.9777 |
| 0.0505 | 2.0 | 1758 | 0.0618 | 0.9221 | 0.9330 | 0.9275 | 0.9827 |
| 0.0309 | 3.0 | 2637 | 0.0620 | 0.9222 | 0.9369 | 0.9295 | 0.9835 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1