distilbert-base-uncased-finetuned-ner

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: 0.1810
• Precision: 0.8617
• Recall: 0.8804
• F1: 0.8710
• Accuracy: 0.9685

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	13	1.7219	0.0	0.0	0.0	0.5826
No log	2.0	26	1.3066	0.0	0.0	0.0	0.7141
No log	3.0	39	0.9443	0.0588	0.0217	0.0317	0.7761
No log	4.0	52	0.6831	0.3448	0.2174	0.2667	0.8163
No log	5.0	65	0.5313	0.4516	0.4565	0.4541	0.8739
No log	6.0	78	0.4245	0.5437	0.6087	0.5744	0.9185
No log	7.0	91	0.3528	0.7019	0.7935	0.7449	0.9457
No log	8.0	104	0.3078	0.7551	0.8043	0.7789	0.9554
No log	9.0	117	0.2709	0.7835	0.8261	0.8042	0.9598
No log	10.0	130	0.2459	0.8191	0.8370	0.8280	0.9620
No log	11.0	143	0.2283	0.8696	0.8696	0.8696	0.9674
No log	12.0	156	0.2108	0.8804	0.8804	0.8804	0.9685
No log	13.0	169	0.2044	0.8804	0.8804	0.8804	0.9685
No log	14.0	182	0.1935	0.8710	0.8804	0.8757	0.9685
No log	15.0	195	0.1875	0.8901	0.8804	0.8852	0.9685
No log	16.0	208	0.1855	0.8710	0.8804	0.8757	0.9685
No log	17.0	221	0.1816	0.8901	0.8804	0.8852	0.9685
No log	18.0	234	0.1819	0.8710	0.8804	0.8757	0.9685
No log	19.0	247	0.1812	0.8710	0.8804	0.8757	0.9685
No log	20.0	260	0.1810	0.8617	0.8804	0.8710	0.9685

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.0+cpu
• Datasets 2.19.1
• Tokenizers 0.19.1