You can deploy this model and start earning money today!

grazh/
distilbert-base-uncased-finetuned-ner-combined-v1

Name: distilbert-base-uncased-finetuned-ner-combined-v1
Availability: InStock

generated_from_trainer

distilbert/distilbert-base-uncased

finetune

apache-2.0

endpoints_compatible

Views

No views yet

distilbert-base-uncased-finetuned-ner-combined-v1

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

Loss: 0.2614
Precision: 0.7181
Recall: 0.7404
F1: 0.7291
Accuracy: 0.9201

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: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	240	0.3337	0.6076	0.6251	0.6162	0.8959
No log	2.0	480	0.2803	0.6819	0.6935	0.6876	0.9116
0.3943	3.0	720	0.2579	0.7206	0.7040	0.7122	0.9172
0.3943	4.0	960	0.2523	0.7225	0.7149	0.7187	0.9174
0.2108	5.0	1200	0.2556	0.7153	0.7288	0.7220	0.9191
0.2108	6.0	1440	0.2532	0.7234	0.7232	0.7233	0.9198
0.1727	7.0	1680	0.2614	0.7181	0.7404	0.7291	0.9201
0.1727	8.0	1920	0.2688	0.7013	0.7414	0.7208	0.9176
0.1407	9.0	2160	0.2759	0.7061	0.7449	0.7250	0.9187
0.1407	10.0	2400	0.2824	0.7161	0.7320	0.7239	0.9189
0.1157	11.0	2640	0.2891	0.7295	0.7179	0.7237	0.9200
0.1157	12.0	2880	0.3048	0.7210	0.7227	0.7218	0.9190

Framework versions

Transformers 4.57.3
Pytorch 2.9.0+cu126
Datasets 3.6.0
Tokenizers 0.22.1

grazh/distilbert-base-uncased-finetuned-ner-combined-v1

distilbert-base-uncased-finetuned-ner-combined-v1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

grazh/
distilbert-base-uncased-finetuned-ner-combined-v1