metadata

license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - wnut_17
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: my_awesome_wnut_model
    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: 0.558252427184466
          - name: Recall
            type: recall
            value: 0.4263206672845227
          - name: F1
            type: f1
            value: 0.48344718864950076
          - name: Accuracy
            type: accuracy
            value: 0.9477576845795391

my_awesome_wnut_model

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

Loss: 0.4207
Precision: 0.5583
Recall: 0.4263
F1: 0.4834
Accuracy: 0.9478

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	213	0.3267	0.5351	0.4235	0.4728	0.9472
No log	2.0	426	0.3741	0.4730	0.3818	0.4226	0.9428
0.0126	3.0	639	0.3431	0.5336	0.4189	0.4694	0.9466
0.0126	4.0	852	0.3790	0.5983	0.3920	0.4737	0.9477
0.008	5.0	1065	0.3610	0.5289	0.4328	0.4760	0.9472
0.008	6.0	1278	0.3580	0.5637	0.4347	0.4908	0.9477
0.008	7.0	1491	0.3569	0.5339	0.4458	0.4859	0.9474
0.0049	8.0	1704	0.3988	0.5602	0.4013	0.4676	0.9470
0.0049	9.0	1917	0.4180	0.5901	0.3976	0.4751	0.9471
0.0032	10.0	2130	0.3969	0.5320	0.4161	0.4670	0.9468
0.0032	11.0	2343	0.4265	0.5851	0.4013	0.4761	0.9473
0.003	12.0	2556	0.4003	0.5569	0.4263	0.4829	0.9475
0.003	13.0	2769	0.4234	0.5936	0.3967	0.4756	0.9480
0.003	14.0	2982	0.4016	0.5482	0.4272	0.4802	0.9482
0.002	15.0	3195	0.4312	0.5655	0.4041	0.4714	0.9471
0.002	16.0	3408	0.4310	0.5611	0.4087	0.4729	0.9470
0.0014	17.0	3621	0.4287	0.5556	0.4124	0.4734	0.9471
0.0014	18.0	3834	0.4193	0.5572	0.4198	0.4789	0.9475
0.0014	19.0	4047	0.4188	0.5583	0.4263	0.4834	0.9478
0.0014	20.0	4260	0.4207	0.5583	0.4263	0.4834	0.9478

Framework versions

Transformers 4.38.1
Pytorch 2.1.2
Datasets 2.1.0
Tokenizers 0.15.2