ner-fine-tune-bert-ner

This model is a fine-tuned version of dslim/bert-base-NER on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3662
• Precision: 0.2383
• Recall: 0.2818
• F1: 0.2582
• Accuracy: 0.9406

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	122	0.2295	0.1255	0.0716	0.0912	0.9514
No log	2.0	244	0.2152	0.2022	0.1270	0.1560	0.9514
No log	3.0	366	0.2044	0.1696	0.1547	0.1618	0.9497
No log	4.0	488	0.2269	0.1980	0.1363	0.1614	0.9536
0.2142	5.0	610	0.2335	0.1931	0.1547	0.1718	0.9521
0.2142	6.0	732	0.2516	0.1959	0.1778	0.1864	0.9491
0.2142	7.0	854	0.2446	0.2565	0.2517	0.2541	0.9542
0.2142	8.0	976	0.2527	0.2273	0.2656	0.2449	0.9481
0.0658	9.0	1098	0.2724	0.2459	0.2055	0.2239	0.9526
0.0658	10.0	1220	0.2620	0.2895	0.2748	0.2820	0.9549
0.0658	11.0	1342	0.2846	0.2102	0.2748	0.2382	0.9416
0.0658	12.0	1464	0.2943	0.2292	0.2610	0.2441	0.9450
0.0273	13.0	1586	0.3154	0.2064	0.2679	0.2332	0.9381
0.0273	14.0	1708	0.3097	0.2254	0.2217	0.2235	0.9464
0.0273	15.0	1830	0.3313	0.2375	0.2517	0.2444	0.9426
0.0273	16.0	1952	0.3256	0.2098	0.2864	0.2422	0.9361
0.0155	17.0	2074	0.3333	0.2162	0.2656	0.2383	0.9393
0.0155	18.0	2196	0.3073	0.2446	0.2864	0.2638	0.9449
0.0155	19.0	2318	0.3241	0.2418	0.2725	0.2562	0.9437
0.0155	20.0	2440	0.3348	0.2338	0.2587	0.2456	0.9446
0.0091	21.0	2562	0.3595	0.234	0.2702	0.2508	0.9402
0.0091	22.0	2684	0.3658	0.2263	0.2818	0.2510	0.9387
0.0091	23.0	2806	0.3495	0.2391	0.2794	0.2577	0.9419
0.0091	24.0	2928	0.3545	0.2398	0.2841	0.2600	0.9409
0.0066	25.0	3050	0.3557	0.2309	0.2864	0.2557	0.9402
0.0066	26.0	3172	0.3498	0.2449	0.2748	0.2590	0.9432
0.0066	27.0	3294	0.3586	0.2375	0.2841	0.2587	0.9416
0.0066	28.0	3416	0.3676	0.2389	0.2725	0.2546	0.9417
0.005	29.0	3538	0.3663	0.2412	0.2864	0.2619	0.9404
0.005	30.0	3660	0.3662	0.2383	0.2818	0.2582	0.9406

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1