Modelpublic

silviacamplani/distilbert-base-uncased-finetuned-dapt-ner-ai_data_3labels

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face

0likes11downloads

Model Card

silviacamplani/distilbert-base-uncased-finetuned-dapt-ner-aidata3labels

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

—Train Loss: 0.6153
—Validation Loss: 0.5610
—Train Precision: 0.0
—Train Recall: 0.0
—Train F1: 0.0
—Train Accuracy: 0.8840
—Epoch: 9

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:

—optimizer: {'inneroptimizer': {'classname': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learningrate': {'classname': 'PolynomialDecay', 'config': {'initiallearningrate': 1e-05, 'decaysteps': 60, 'endlearningrate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta1': 0.9, 'beta2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weightdecayrate': 0.01}}, 'dynamic': True, 'initialscale': 32768.0, 'dynamicgrowthsteps': 2000}
—trainingprecision: mixedfloat16

Training results

Train Loss	Validation Loss	Train Precision	Train Recall	Train F1	Train Accuracy	Epoch
1.6831	1.5093	0.0031	0.0020	0.0024	0.8573	0
1.3863	1.2247	0.0	0.0	0.0	0.8839	1
1.1078	0.9646	0.0	0.0	0.0	0.8840	2
0.8884	0.7566	0.0	0.0	0.0	0.8840	3
0.7235	0.6484	0.0	0.0	0.0	0.8840	4
0.6686	0.6034	0.0	0.0	0.0	0.8840	5
0.6541	0.5804	0.0	0.0	0.0	0.8840	6
0.6347	0.5687	0.0	0.0	0.0	0.8840	7
0.6147	0.5630	0.0	0.0	0.0	0.8840	8
0.6153	0.5610	0.0	0.0	0.0	0.8840	9

Framework versions

—Transformers 4.20.1
—TensorFlow 2.6.4
—Datasets 2.1.0
—Tokenizers 0.12.1