distilbert-base-uncased-finetuned-ner_0220_J_ORIDATA

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: 0.4949
Precision: 0.8987
Recall: 0.9551
F1: 0.9260
Accuracy: 0.9437

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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	111	0.2996	0.7246	0.8407	0.7783	0.9295
No log	2.0	222	0.2545	0.8067	0.8983	0.8500	0.9343
No log	3.0	333	0.2398	0.8649	0.9280	0.8953	0.9445
No log	4.0	444	0.2326	0.8651	0.9297	0.8962	0.9459
0.329	5.0	555	0.2200	0.8836	0.9263	0.9044	0.9459
0.329	6.0	666	0.2382	0.8365	0.9280	0.8799	0.9315
0.329	7.0	777	0.2349	0.8775	0.9347	0.9052	0.9395
0.329	8.0	888	0.2604	0.8832	0.9424	0.9118	0.9415
0.329	9.0	999	0.2705	0.8929	0.9331	0.9126	0.9483
0.124	10.0	1110	0.2986	0.8731	0.9390	0.9049	0.9410
0.124	11.0	1221	0.2960	0.8805	0.9432	0.9108	0.9441
0.124	12.0	1332	0.2798	0.8778	0.9373	0.9066	0.9401
0.124	13.0	1443	0.3364	0.8851	0.9534	0.9180	0.9422
0.0735	14.0	1554	0.3546	0.8943	0.9534	0.9229	0.9425
0.0735	15.0	1665	0.3449	0.8917	0.9492	0.9195	0.9443
0.0735	16.0	1776	0.3789	0.8817	0.9407	0.9102	0.9381
0.0735	17.0	1887	0.3727	0.8803	0.9407	0.9095	0.9443
0.0735	18.0	1998	0.3633	0.8841	0.9373	0.9099	0.9387
0.0453	19.0	2109	0.4279	0.8816	0.9398	0.9098	0.9328
0.0453	20.0	2220	0.4055	0.8939	0.95	0.9211	0.9431
0.0453	21.0	2331	0.4138	0.8924	0.9492	0.9199	0.9441
0.0453	22.0	2442	0.4275	0.8948	0.9441	0.9188	0.9422
0.0283	23.0	2553	0.4319	0.8955	0.9508	0.9223	0.9418
0.0283	24.0	2664	0.4179	0.8878	0.9525	0.9191	0.9464
0.0283	25.0	2775	0.4341	0.8937	0.9407	0.9166	0.9420
0.0283	26.0	2886	0.4420	0.9063	0.9508	0.9280	0.9439
0.0283	27.0	2997	0.4370	0.8986	0.9466	0.9220	0.9432
0.0188	28.0	3108	0.4557	0.8953	0.9492	0.9214	0.9430
0.0188	29.0	3219	0.4458	0.8934	0.9449	0.9185	0.9437
0.0188	30.0	3330	0.4461	0.8973	0.9475	0.9217	0.9425
0.0188	31.0	3441	0.4638	0.9014	0.9525	0.9262	0.9426
0.0132	32.0	3552	0.4732	0.9029	0.9534	0.9275	0.9437
0.0132	33.0	3663	0.4645	0.9062	0.9576	0.9312	0.9453
0.0132	34.0	3774	0.4542	0.8981	0.9483	0.9225	0.9447
0.0132	35.0	3885	0.4702	0.8974	0.9492	0.9226	0.9431
0.0132	36.0	3996	0.4824	0.9081	0.9542	0.9306	0.9428
0.0101	37.0	4107	0.4757	0.8978	0.9534	0.9248	0.9442
0.0101	38.0	4218	0.4750	0.8971	0.9534	0.9244	0.9453
0.0101	39.0	4329	0.4843	0.9008	0.9542	0.9267	0.9446
0.0101	40.0	4440	0.4840	0.9019	0.9585	0.9293	0.9464
0.0077	41.0	4551	0.4852	0.8939	0.9492	0.9207	0.9436
0.0077	42.0	4662	0.4864	0.9051	0.9542	0.9290	0.9447
0.0077	43.0	4773	0.4801	0.9010	0.9559	0.9276	0.9431
0.0077	44.0	4884	0.4887	0.9016	0.9551	0.9276	0.9435
0.0077	45.0	4995	0.4973	0.8972	0.9542	0.9248	0.9430
0.0065	46.0	5106	0.4942	0.9	0.9534	0.9259	0.9436
0.0065	47.0	5217	0.4933	0.9007	0.9534	0.9263	0.9436
0.0065	48.0	5328	0.4979	0.8987	0.9551	0.9260	0.9434
0.0065	49.0	5439	0.4966	0.9009	0.9551	0.9272	0.9434
0.0059	50.0	5550	0.4949	0.8987	0.9551	0.9260	0.9437

Framework versions

Transformers 4.20.1
Pytorch 1.13.0+cu117
Datasets 2.8.0
Tokenizers 0.12.1

morganchen1007/distilbert-base-uncased-finetuned-ner_0220_J_ORIDATA

distilbert-base-uncased-finetuned-ner_0220_J_ORIDATA

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

为此模型做种