distilbert-base-uncased-finetuned-ner_0212

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: 0.1755
• Precision: 0.8894
• Recall: 0.9402
• F1: 0.9141
• Accuracy: 0.9561

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	105	0.4362	0.6638	0.7654	0.7110	0.8662
No log	2.0	210	0.2527	0.7860	0.8686	0.8252	0.9127
No log	3.0	315	0.2411	0.8339	0.8942	0.8630	0.9223
No log	4.0	420	0.1801	0.8444	0.9021	0.8723	0.9403
0.3472	5.0	525	0.1569	0.8470	0.9166	0.8804	0.9439
0.3472	6.0	630	0.1424	0.8643	0.9205	0.8915	0.9531
0.3472	7.0	735	0.1526	0.8764	0.9271	0.9010	0.9476
0.3472	8.0	840	0.1804	0.8826	0.9284	0.9049	0.9452
0.3472	9.0	945	0.1650	0.8809	0.9330	0.9062	0.9504
0.068	10.0	1050	0.1458	0.8819	0.9271	0.9039	0.9574
0.068	11.0	1155	0.1618	0.8810	0.9336	0.9065	0.9511
0.068	12.0	1260	0.1817	0.8865	0.9343	0.9098	0.9489
0.068	13.0	1365	0.1530	0.8890	0.9363	0.912	0.9572
0.068	14.0	1470	0.1643	0.9032	0.9382	0.9204	0.9552
0.0342	15.0	1575	0.1710	0.9016	0.9336	0.9174	0.9550
0.0342	16.0	1680	0.1736	0.8879	0.9369	0.9118	0.9554
0.0342	17.0	1785	0.1722	0.8903	0.9382	0.9136	0.9556
0.0342	18.0	1890	0.1713	0.8848	0.9389	0.9111	0.9525
0.0342	19.0	1995	0.1692	0.88	0.9396	0.9088	0.9573
0.0224	20.0	2100	0.1755	0.8894	0.9402	0.9141	0.9561

Framework versions

• Transformers 4.20.1
• Pytorch 1.13.0+cu117
• Datasets 2.8.0
• Tokenizers 0.12.1