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: 0.3430
Precision: 0.5581
Recall: 0.4050
F1: 0.4694
Accuracy: 0.9472

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 OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	213	0.2767	0.6807	0.2706	0.3873	0.9406
No log	2.0	426	0.2586	0.5602	0.3364	0.4204	0.9435
0.167	3.0	639	0.2965	0.5665	0.3475	0.4308	0.9449
0.167	4.0	852	0.3051	0.5599	0.3466	0.4282	0.9453
0.0426	5.0	1065	0.3027	0.5309	0.3976	0.4547	0.9462
0.0426	6.0	1278	0.3141	0.5496	0.4004	0.4633	0.9474
0.0426	7.0	1491	0.3236	0.5411	0.4022	0.4615	0.9470
0.0193	8.0	1704	0.3313	0.5443	0.4152	0.4711	0.9475
0.0193	9.0	1917	0.3390	0.5590	0.3994	0.4659	0.9471
0.0112	10.0	2130	0.3430	0.5581	0.4050	0.4694	0.9472

Framework versions

Transformers 4.55.2
Pytorch 2.8.0+cu128
Datasets 3.6.0
Tokenizers 0.21.4

koh43/distilbert-base-uncased-ner-wnut

distilbert-base-uncased-ner-wnut

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

koh43/
distilbert-base-uncased-ner-wnut