ner_base

This model is a fine-tuned version of vinai/phobert-base on the hts98/UIT dataset. It achieves the following results on the evaluation set:

Loss: 1.6160
Precision: 0.6525
Recall: 0.7066
F1: 0.6785
Accuracy: 0.8276

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: 3e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 120.0

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	244	0.8214	0.4246	0.5544	0.4809	0.7636
No log	2.0	488	0.6734	0.5305	0.6159	0.5700	0.8023
0.9764	3.0	732	0.6425	0.5591	0.6519	0.6020	0.8072
0.9764	4.0	976	0.6203	0.5664	0.6731	0.6151	0.8215
0.4504	5.0	1220	0.6483	0.5879	0.6795	0.6304	0.8171
0.4504	6.0	1464	0.6828	0.5478	0.6826	0.6078	0.8138
0.2877	7.0	1708	0.7097	0.5868	0.6803	0.6301	0.8115
0.2877	8.0	1952	0.7538	0.5864	0.6884	0.6334	0.8133
0.1968	9.0	2196	0.7853	0.5949	0.6837	0.6362	0.8129
0.1968	10.0	2440	0.8311	0.5984	0.6815	0.6373	0.8094
0.1443	11.0	2684	0.7910	0.6101	0.6898	0.6475	0.8190
0.1443	12.0	2928	0.8414	0.5927	0.6803	0.6335	0.8147
0.1118	13.0	3172	0.8946	0.6023	0.6857	0.6413	0.8069
0.1118	14.0	3416	0.9195	0.6055	0.6843	0.6425	0.8130
0.0838	15.0	3660	0.9149	0.6020	0.6882	0.6422	0.8192
0.0838	16.0	3904	0.9357	0.6072	0.6893	0.6457	0.8201
0.0661	17.0	4148	0.9784	0.6033	0.6887	0.6432	0.8173
0.0661	18.0	4392	0.9842	0.6121	0.6868	0.6473	0.8184
0.0514	19.0	4636	1.0097	0.6105	0.6896	0.6476	0.8164
0.0514	20.0	4880	1.0300	0.6086	0.6946	0.6488	0.8167
0.0416	21.0	5124	1.0250	0.6190	0.6904	0.6528	0.8205
0.0416	22.0	5368	1.0879	0.6171	0.6937	0.6532	0.8167
0.0324	23.0	5612	1.1349	0.6093	0.6817	0.6435	0.8127
0.0324	24.0	5856	1.0994	0.6191	0.6935	0.6542	0.8181
0.0277	25.0	6100	1.1401	0.6180	0.6951	0.6543	0.8153
0.0277	26.0	6344	1.1868	0.5984	0.6904	0.6411	0.8084
0.0223	27.0	6588	1.2052	0.6282	0.6859	0.6558	0.8139
0.0223	28.0	6832	1.1964	0.6168	0.6935	0.6529	0.8153
0.019	29.0	7076	1.1898	0.6214	0.6887	0.6533	0.8202
0.019	30.0	7320	1.2819	0.6136	0.6946	0.6516	0.8135
0.0159	31.0	7564	1.2687	0.6093	0.6912	0.6477	0.8128
0.0159	32.0	7808	1.2997	0.6128	0.6971	0.6522	0.8159
0.0141	33.0	8052	1.2800	0.6172	0.6843	0.6490	0.8157
0.0141	34.0	8296	1.3110	0.6220	0.6901	0.6543	0.8141
0.0107	35.0	8540	1.3343	0.6081	0.6910	0.6469	0.8160
0.0107	36.0	8784	1.3406	0.6111	0.6926	0.6493	0.8130
0.0106	37.0	9028	1.3921	0.6080	0.6876	0.6454	0.8127
0.0106	38.0	9272	1.4061	0.6086	0.6868	0.6453	0.8100
0.0088	39.0	9516	1.3828	0.6293	0.6921	0.6592	0.8166
0.0088	40.0	9760	1.4263	0.6242	0.6940	0.6572	0.8130
0.0086	41.0	10004	1.3521	0.6202	0.6993	0.6574	0.8185
0.0086	42.0	10248	1.3722	0.6451	0.6999	0.6714	0.8196
0.0086	43.0	10492	1.3784	0.6373	0.6946	0.6647	0.8226
0.0075	44.0	10736	1.4340	0.6334	0.6940	0.6623	0.8140
0.0075	45.0	10980	1.3902	0.6321	0.7002	0.6644	0.8161
0.0066	46.0	11224	1.4019	0.6230	0.6985	0.6586	0.8162
0.0066	47.0	11468	1.4320	0.6183	0.6960	0.6548	0.8161
0.0067	48.0	11712	1.4461	0.6326	0.6999	0.6645	0.8200
0.0067	49.0	11956	1.4327	0.6249	0.6982	0.6595	0.8202
0.0054	50.0	12200	1.4616	0.6348	0.6943	0.6632	0.8176
0.0054	51.0	12444	1.4537	0.6135	0.7010	0.6543	0.8177
0.0052	52.0	12688	1.5622	0.6265	0.6884	0.6560	0.8096
0.0052	53.0	12932	1.4217	0.6348	0.7027	0.6670	0.8236
0.0051	54.0	13176	1.4625	0.6266	0.6965	0.6597	0.8217
0.0051	55.0	13420	1.4359	0.6393	0.6918	0.6645	0.8257
0.0049	56.0	13664	1.4617	0.6447	0.6977	0.6702	0.8231
0.0049	57.0	13908	1.5171	0.6337	0.6951	0.6630	0.8181
0.0037	58.0	14152	1.4999	0.6339	0.7032	0.6668	0.8206
0.0037	59.0	14396	1.4841	0.6269	0.7007	0.6617	0.8208
0.004	60.0	14640	1.4361	0.6381	0.7044	0.6696	0.8244
0.004	61.0	14884	1.4800	0.6425	0.7035	0.6716	0.8235
0.004	62.0	15128	1.4700	0.6330	0.6991	0.6644	0.8241
0.004	63.0	15372	1.5107	0.6309	0.7016	0.6644	0.8212
0.0037	64.0	15616	1.5132	0.6389	0.7024	0.6691	0.8227
0.0037	65.0	15860	1.5229	0.6287	0.7016	0.6631	0.8239
0.0033	66.0	16104	1.5574	0.6395	0.7027	0.6696	0.8242
0.0033	67.0	16348	1.5216	0.6270	0.7052	0.6638	0.8196
0.0033	68.0	16592	1.4877	0.6347	0.6951	0.6636	0.8242
0.0033	69.0	16836	1.5373	0.6281	0.7021	0.6631	0.8195
0.0026	70.0	17080	1.5522	0.6335	0.7002	0.6652	0.8201
0.0026	71.0	17324	1.5180	0.6380	0.7035	0.6691	0.8227
0.0024	72.0	17568	1.5517	0.6504	0.6974	0.6730	0.8218
0.0024	73.0	17812	1.5392	0.6332	0.7021	0.6659	0.8206
0.0026	74.0	18056	1.5396	0.6415	0.7010	0.6700	0.8246
0.0026	75.0	18300	1.5638	0.6500	0.6999	0.6740	0.8233
0.0019	76.0	18544	1.5790	0.6438	0.6912	0.6667	0.8202
0.0019	77.0	18788	1.5546	0.6500	0.7052	0.6765	0.8216
0.0029	78.0	19032	1.5374	0.6369	0.7032	0.6684	0.8236
0.0029	79.0	19276	1.5923	0.6351	0.6982	0.6652	0.8180
0.0015	80.0	19520	1.5728	0.6354	0.7027	0.6674	0.8246
0.0015	81.0	19764	1.5646	0.6417	0.6979	0.6686	0.8229
0.0019	82.0	20008	1.5845	0.6247	0.7030	0.6615	0.8211
0.0019	83.0	20252	1.5894	0.6424	0.6935	0.6669	0.8193
0.0019	84.0	20496	1.6702	0.6428	0.6907	0.6659	0.8169
0.0012	85.0	20740	1.6313	0.6342	0.7027	0.6667	0.8189
0.0012	86.0	20984	1.5829	0.6357	0.7038	0.6680	0.8232
0.0015	87.0	21228	1.6056	0.6396	0.7085	0.6723	0.8210
0.0015	88.0	21472	1.5823	0.6471	0.7105	0.6773	0.8225
0.0015	89.0	21716	1.5736	0.6367	0.7016	0.6676	0.8249
0.0015	90.0	21960	1.5921	0.6457	0.7016	0.6725	0.8236
0.0012	91.0	22204	1.6114	0.6371	0.7030	0.6684	0.8231
0.0012	92.0	22448	1.5752	0.6408	0.7038	0.6708	0.8245
0.0014	93.0	22692	1.6123	0.6360	0.7018	0.6673	0.8217
0.0014	94.0	22936	1.6183	0.6374	0.7021	0.6682	0.8221
0.0009	95.0	23180	1.6078	0.6474	0.6988	0.6721	0.8275
0.0009	96.0	23424	1.6201	0.6401	0.6991	0.6683	0.8246
0.0008	97.0	23668	1.6216	0.6388	0.7016	0.6687	0.8238
0.0008	98.0	23912	1.6113	0.6410	0.7024	0.6703	0.8244
0.0011	99.0	24156	1.5995	0.6497	0.7027	0.6752	0.8245
0.0011	100.0	24400	1.5953	0.6423	0.7027	0.6711	0.8259
0.0009	101.0	24644	1.6178	0.6447	0.7027	0.6725	0.8248
0.0009	102.0	24888	1.6171	0.6408	0.7066	0.6721	0.8257
0.0006	103.0	25132	1.6054	0.6508	0.7077	0.6781	0.8271
0.0006	104.0	25376	1.6218	0.6412	0.7018	0.6701	0.8251
0.0008	105.0	25620	1.6308	0.6475	0.7024	0.6738	0.8245
0.0008	106.0	25864	1.6342	0.6471	0.7066	0.6756	0.8267
0.0004	107.0	26108	1.6346	0.6447	0.7058	0.6739	0.8254
0.0004	108.0	26352	1.6328	0.6437	0.7066	0.6737	0.8257
0.0008	109.0	26596	1.6220	0.6476	0.7038	0.6745	0.8257
0.0008	110.0	26840	1.6160	0.6525	0.7066	0.6785	0.8276
0.0006	111.0	27084	1.6100	0.6455	0.7055	0.6741	0.8270
0.0006	112.0	27328	1.6270	0.6394	0.7055	0.6708	0.8247
0.0005	113.0	27572	1.6234	0.6505	0.7024	0.6754	0.8273
0.0005	114.0	27816	1.6328	0.6417	0.7035	0.6712	0.8252
0.0004	115.0	28060	1.6352	0.6428	0.7018	0.6710	0.8251
0.0004	116.0	28304	1.6269	0.6458	0.7055	0.6743	0.8265
0.0005	117.0	28548	1.6377	0.6442	0.7041	0.6728	0.8253
0.0005	118.0	28792	1.6353	0.6450	0.7049	0.6736	0.8257
0.0004	119.0	29036	1.6395	0.6476	0.7044	0.6748	0.8257
0.0004	120.0	29280	1.6385	0.6467	0.7038	0.6741	0.8256

Framework versions

Transformers 4.32.0.dev0
Pytorch 2.1.0+cu121
Datasets 3.1.0
Tokenizers 0.13.3

hts98/ner_base

ner_base

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

为此模型做种