distilbert-base-uncased-finetuned-ner

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

Loss: 0.5531
Precision: 0.6720
Recall: 0.4706
F1: 0.5535
Accuracy: 0.9361

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: 5e-06
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	213	0.4459	0.0	0.0	0.0	0.8961
No log	2.0	426	0.3953	0.5267	0.2194	0.3098	0.9142
0.3131	3.0	639	0.3688	0.6150	0.3188	0.4199	0.9218
0.3131	4.0	852	0.3321	0.5778	0.4102	0.4798	0.9260
0.1114	5.0	1065	0.3361	0.6103	0.4157	0.4946	0.9305
0.1114	6.0	1278	0.3348	0.5981	0.4436	0.5094	0.9314
0.1114	7.0	1491	0.3494	0.6206	0.4356	0.5119	0.9328
0.0784	8.0	1704	0.3713	0.6491	0.4396	0.5242	0.9340
0.0784	9.0	1917	0.3773	0.6615	0.4412	0.5293	0.9343
0.0554	10.0	2130	0.3766	0.6299	0.4491	0.5244	0.9332
0.0554	11.0	2343	0.3837	0.6543	0.4499	0.5332	0.9347
0.0398	12.0	2556	0.3700	0.6239	0.4722	0.5376	0.9337
0.0398	13.0	2769	0.3820	0.6196	0.4674	0.5329	0.9340
0.0398	14.0	2982	0.4080	0.6586	0.4555	0.5385	0.9346
0.0294	15.0	3195	0.4066	0.6644	0.4658	0.5477	0.9354
0.0294	16.0	3408	0.4159	0.6601	0.4539	0.5379	0.9350
0.0219	17.0	3621	0.4071	0.6395	0.4738	0.5443	0.9351
0.0219	18.0	3834	0.3940	0.6161	0.4936	0.5481	0.9348
0.0170	19.0	4047	0.4265	0.6712	0.4754	0.5565	0.9358
0.0170	20.0	4260	0.4113	0.6419	0.4873	0.5540	0.9354
0.0170	21.0	4473	0.4341	0.6569	0.4642	0.5440	0.9353
0.0132	22.0	4686	0.4330	0.6338	0.4595	0.5327	0.9346
0.0132	23.0	4899	0.4422	0.6433	0.4531	0.5317	0.9347
0.0106	24.0	5112	0.4493	0.6534	0.4571	0.5379	0.9347
0.0106	25.0	5325	0.4509	0.6523	0.4579	0.5381	0.9349
0.0090	26.0	5538	0.4442	0.6292	0.4666	0.5358	0.9347
0.0090	27.0	5751	0.4650	0.6527	0.4571	0.5376	0.9349
0.0090	28.0	5964	0.4564	0.6359	0.4595	0.5335	0.9345
0.0080	29.0	6177	0.4647	0.6436	0.4650	0.5399	0.9348
0.0080	30.0	6390	0.4662	0.6448	0.4690	0.5430	0.9353
0.0064	31.0	6603	0.4572	0.6311	0.4746	0.5417	0.9348
0.0064	32.0	6816	0.4484	0.6463	0.4952	0.5608	0.9361
0.0062	33.0	7029	0.4647	0.6485	0.4722	0.5465	0.9361
0.0062	34.0	7242	0.4777	0.6615	0.4754	0.5532	0.9358
0.0062	35.0	7455	0.4591	0.6314	0.4833	0.5475	0.9346
0.0050	36.0	7668	0.4867	0.6587	0.4587	0.5408	0.9350
0.0050	37.0	7881	0.4814	0.6483	0.4762	0.5490	0.9355
0.0043	38.0	8094	0.4768	0.6627	0.4809	0.5573	0.9360
0.0043	39.0	8307	0.4675	0.6471	0.4913	0.5585	0.9361
0.0043	40.0	8520	0.4847	0.6484	0.4809	0.5523	0.9355
0.0043	41.0	8733	0.4689	0.6362	0.4865	0.5514	0.9349
0.0043	42.0	8946	0.4867	0.6470	0.4706	0.5449	0.9355
0.0037	43.0	9159	0.5036	0.6735	0.4690	0.5530	0.9353
0.0037	44.0	9372	0.5012	0.6771	0.4817	0.5629	0.9368
0.0029	45.0	9585	0.4810	0.6573	0.4849	0.5581	0.9361
0.0029	46.0	9798	0.4931	0.6848	0.4698	0.5573	0.9360
0.0035	47.0	10011	0.5137	0.6778	0.4531	0.5431	0.9353
0.0035	48.0	10224	0.4985	0.6738	0.4777	0.5591	0.9363
0.0035	49.0	10437	0.4957	0.6410	0.4769	0.5469	0.9355
0.0027	50.0	10650	0.5225	0.6659	0.4595	0.5437	0.9354
0.0027	51.0	10863	0.5483	0.6942	0.4348	0.5347	0.9350
0.0027	52.0	11076	0.5363	0.6878	0.4483	0.5428	0.9355
0.0027	53.0	11289	0.5284	0.6754	0.4531	0.5423	0.9357
0.0029	54.0	11502	0.5069	0.6741	0.4817	0.5619	0.9367
0.0029	55.0	11715	0.5333	0.6942	0.4547	0.5495	0.9360
0.0029	56.0	11928	0.4927	0.6399	0.4944	0.5578	0.9355
0.0021	57.0	12141	0.5098	0.6542	0.4857	0.5575	0.9365
0.0021	58.0	12354	0.5451	0.6854	0.4555	0.5473	0.9359
0.0025	59.0	12567	0.5178	0.6659	0.4817	0.5590	0.9367
0.0025	60.0	12780	0.5138	0.6631	0.4897	0.5633	0.9365
0.0025	61.0	12993	0.5260	0.6718	0.4817	0.5611	0.9367
0.0019	62.0	13206	0.5092	0.6581	0.4913	0.5626	0.9364
0.0019	63.0	13419	0.5244	0.6700	0.4762	0.5567	0.9362
0.0019	64.0	13632	0.5095	0.6514	0.4960	0.5632	0.9367
0.0019	65.0	13845	0.5369	0.6816	0.4714	0.5573	0.9363
0.0023	66.0	14058	0.5336	0.6652	0.4738	0.5534	0.9364
0.0023	67.0	14271	0.5231	0.6552	0.4849	0.5573	0.9365
0.0023	68.0	14484	0.5023	0.6377	0.5008	0.5610	0.9361
0.0018	69.0	14697	0.5209	0.6605	0.4857	0.5598	0.9364
0.0018	70.0	14910	0.5281	0.6630	0.4769	0.5548	0.9362
0.0020	71.0	15123	0.5273	0.6567	0.4730	0.5499	0.9354
0.0020	72.0	15336	0.5328	0.6670	0.4762	0.5557	0.9363
0.0016	73.0	15549	0.5461	0.6786	0.4682	0.5541	0.9363
0.0016	74.0	15762	0.5430	0.6868	0.4706	0.5585	0.9361
0.0016	75.0	15975	0.5555	0.6996	0.4610	0.5558	0.9360
0.0018	76.0	16188	0.5751	0.7037	0.4531	0.5513	0.9355
0.0018	77.0	16401	0.5402	0.6779	0.4785	0.5610	0.9367
0.0017	78.0	16614	0.5432	0.6845	0.4777	0.5627	0.9364
0.0017	79.0	16827	0.5405	0.6682	0.4754	0.5555	0.9360
0.0015	80.0	17040	0.5394	0.6791	0.4762	0.5598	0.9369
0.0015	81.0	17253	0.5440	0.6797	0.4706	0.5561	0.9365
0.0015	82.0	17466	0.5352	0.6715	0.4809	0.5604	0.9372
0.0015	83.0	17679	0.5391	0.6782	0.4825	0.5639	0.9371
0.0015	84.0	17892	0.5439	0.6749	0.4785	0.5600	0.9365
0.0017	85.0	18105	0.5343	0.6696	0.4865	0.5635	0.9371
0.0017	86.0	18318	0.5381	0.6670	0.4809	0.5589	0.9367
0.0013	87.0	18531	0.5430	0.6696	0.4769	0.5571	0.9367
0.0013	88.0	18744	0.5467	0.6742	0.4754	0.5576	0.9366
0.0013	89.0	18957	0.5428	0.6725	0.4849	0.5635	0.9371
0.0012	90.0	19170	0.5484	0.6712	0.4754	0.5565	0.9361
0.0012	91.0	19383	0.5402	0.6681	0.4849	0.5620	0.9367
0.0014	92.0	19596	0.5542	0.6743	0.4690	0.5532	0.9361
0.0014	93.0	19809	0.5565	0.6786	0.4682	0.5541	0.9361
0.0013	94.0	20022	0.5553	0.6782	0.4674	0.5534	0.9361
0.0013	95.0	20235	0.5534	0.6750	0.4706	0.5546	0.9363
0.0013	96.0	20448	0.5479	0.6708	0.4777	0.5580	0.9365
0.0013	97.0	20661	0.5490	0.6696	0.4769	0.5571	0.9365
0.0013	98.0	20874	0.5526	0.6719	0.4722	0.5546	0.9362
0.0012	99.0	21087	0.5520	0.6704	0.4738	0.5552	0.9362
0.0012	100.0	21300	0.5531	0.6720	0.4706	0.5535	0.9361

Framework versions

Transformers 5.18.0
Pytorch 2.14.1+cu126
Datasets 5.0.1
Tokenizers 0.23.2

tihon-nth/distilbert-base-uncased-finetuned-ner

distilbert-base-uncased-finetuned-ner

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions