metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - wnut_17
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: distilbert-base-multilingual-cased-WNUT-ner
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: wnut_17
          type: wnut_17
          config: wnut_17
          split: test
          args: wnut_17
        metrics:
          - name: Precision
            type: precision
            value: 0.5496503496503496
          - name: Recall
            type: recall
            value: 0.36422613531047265
          - name: F1
            type: f1
            value: 0.4381270903010034
          - name: Accuracy
            type: accuracy
            value: 0.9468667179618706

distilbert-base-multilingual-cased-WNUT-ner

This model is a fine-tuned version of distilbert-base-multilingual-cased on the wnut_17 dataset. It achieves the following results on the evaluation set:

Loss: 0.3516
Precision: 0.5497
Recall: 0.3642
F1: 0.4381
Accuracy: 0.9469

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	213	0.2727	0.6626	0.2530	0.3662	0.9402
No log	2.0	426	0.2636	0.5895	0.2715	0.3718	0.9429
0.1729	3.0	639	0.2933	0.5931	0.3040	0.4020	0.9447
0.1729	4.0	852	0.2861	0.5437	0.3457	0.4227	0.9453
0.0503	5.0	1065	0.3270	0.5627	0.3494	0.4311	0.9455
0.0503	6.0	1278	0.3277	0.5451	0.3531	0.4286	0.9463
0.0503	7.0	1491	0.3471	0.5828	0.3457	0.4340	0.9467
0.0231	8.0	1704	0.3594	0.5801	0.3457	0.4332	0.9464
0.0231	9.0	1917	0.3550	0.5567	0.3503	0.4300	0.9467
0.0121	10.0	2130	0.3516	0.5497	0.3642	0.4381	0.9469

Framework versions

Transformers 4.26.0
Pytorch 1.13.1+cu117
Datasets 2.9.0
Tokenizers 0.13.2