token_classification_test

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2740
• Precision: 0.9257
• Recall: 0.9158
• F1: 0.9207
• Accuracy: 0.9354

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	47	1.1923	0.6932	0.6053	0.6463	0.7206
No log	2.0	94	0.6271	0.8247	0.7896	0.8068	0.8400
No log	3.0	141	0.4480	0.8799	0.8512	0.8653	0.8918
No log	4.0	188	0.3751	0.8996	0.8744	0.8868	0.9088
No log	5.0	235	0.3377	0.9043	0.8882	0.8962	0.9155
No log	6.0	282	0.3139	0.9150	0.8976	0.9062	0.9223
No log	7.0	329	0.3060	0.9091	0.8972	0.9031	0.9214
No log	8.0	376	0.2918	0.9162	0.9064	0.9113	0.9271
No log	9.0	423	0.2856	0.9209	0.9070	0.9139	0.9293
No log	10.0	470	0.2809	0.9228	0.9081	0.9154	0.9311
0.5294	11.0	517	0.2803	0.9232	0.9104	0.9168	0.9321
0.5294	12.0	564	0.2761	0.9259	0.9154	0.9206	0.9349
0.5294	13.0	611	0.2737	0.9272	0.9156	0.9214	0.9357
0.5294	14.0	658	0.2742	0.9279	0.9164	0.9221	0.9362
0.5294	15.0	705	0.2740	0.9257	0.9158	0.9207	0.9354

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0