GS_bert2

biblo0507/GS_bert2

GS_bert2 is a machine learning model from biblo0507. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

7% of all-time downloads

All-time downloads

Public

Parameters

92.3M

7.4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors369 MB · 98%

At a glance

Library: transformers
Model type: bert
Access: Public
Created: Mar 25, 2025
Updated: Mar 25, 2025
SHA: 3dd7adde

Base models

skt/kobert-base-v1

Model card

From the Hugging Face model README

GS_bert2

This model is a fine-tuned version of skt/kobert-base-v1 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1128
F1: 0.4492
Precision: 0.4722
Recall: 0.4319

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-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Precision	Recall
0.6576	1.0	45	0.6338	0.0386	0.0407	0.0370
0.5782	2.0	90	0.5574	0.0317	0.0333	0.0306
0.4912	3.0	135	0.4505	0.0317	0.0333	0.0306
0.3491	4.0	180	0.3189	0.0476	0.0519	0.0444
0.2505	5.0	225	0.2204	0.0476	0.0519	0.0444
0.1905	6.0	270	0.1784	0.0442	0.0463	0.0426
0.1746	7.0	315	0.1656	0.0442	0.0463	0.0426
0.1683	8.0	360	0.1622	0.0442	0.0463	0.0426
0.1666	9.0	405	0.1614	0.0548	0.0574	0.0528
0.1677	10.0	450	0.1615	0.0479	0.05	0.0463
0.1673	11.0	495	0.1614	0.0394	0.0426	0.0370
0.1664	12.0	540	0.1610	0.0347	0.0370	0.0329
0.1658	13.0	585	0.1606	0.0812	0.0852	0.0782
0.1649	14.0	630	0.1597	0.1037	0.1093	0.0995
0.1618	15.0	675	0.1581	0.1429	0.15	0.1375
0.1615	16.0	720	0.1561	0.2042	0.2130	0.1977
0.1577	17.0	765	0.1537	0.2275	0.2389	0.2190
0.1552	18.0	810	0.1518	0.2352	0.2463	0.2269
0.1526	19.0	855	0.1499	0.2698	0.2833	0.2597
0.1502	20.0	900	0.1481	0.2862	0.3	0.2759
0.1509	21.0	945	0.1462	0.2952	0.3093	0.2847
0.1487	22.0	990	0.1445	0.3103	0.3259	0.2986
0.1455	23.0	1035	0.1429	0.3122	0.3278	0.3005
0.1451	24.0	1080	0.1412	0.3175	0.3333	0.3056
0.1403	25.0	1125	0.1396	0.3175	0.3333	0.3056
0.139	26.0	1170	0.1382	0.3222	0.3389	0.3097
0.1363	27.0	1215	0.1366	0.3254	0.3426	0.3125
0.1329	28.0	1260	0.1353	0.3442	0.3630	0.3301
0.1348	29.0	1305	0.1343	0.3466	0.3648	0.3329
0.1309	30.0	1350	0.1332	0.3463	0.3648	0.3324
0.1291	31.0	1395	0.1318	0.3516	0.3704	0.3375
0.1283	32.0	1440	0.1307	0.3593	0.3778	0.3454
0.1276	33.0	1485	0.1295	0.3632	0.3833	0.3481
0.127	34.0	1530	0.1284	0.3672	0.3870	0.3523
0.123	35.0	1575	0.1272	0.3669	0.3870	0.3519
0.1215	36.0	1620	0.1264	0.3656	0.3852	0.3509
0.1218	37.0	1665	0.1258	0.3738	0.3944	0.3583
0.1224	38.0	1710	0.1253	0.3780	0.3981	0.3630
0.1168	39.0	1755	0.1242	0.3881	0.4093	0.3722
0.1163	40.0	1800	0.1232	0.3868	0.4074	0.3713
0.1163	41.0	1845	0.1229	0.3865	0.4074	0.3708
0.1143	42.0	1890	0.1219	0.3847	0.4056	0.3690
0.1128	43.0	1935	0.1211	0.3950	0.4167	0.3787
0.1118	44.0	1980	0.1207	0.3950	0.4167	0.3787
0.1104	45.0	2025	0.1201	0.3960	0.4167	0.3806
0.1097	46.0	2070	0.1197	0.3955	0.4167	0.3796
0.1072	47.0	2115	0.1193	0.3905	0.4111	0.375
0.1049	48.0	2160	0.1187	0.4021	0.4241	0.3856
0.1059	49.0	2205	0.1185	0.3968	0.4185	0.3806
0.1045	50.0	2250	0.1178	0.4074	0.4296	0.3907
0.1051	51.0	2295	0.1176	0.4050	0.4259	0.3894
0.1014	52.0	2340	0.1169	0.4079	0.4296	0.3917
0.1015	53.0	2385	0.1168	0.4026	0.4241	0.3866
0.0979	54.0	2430	0.1164	0.4135	0.4352	0.3972
0.0971	55.0	2475	0.1161	0.4116	0.4333	0.3954
0.0964	56.0	2520	0.1161	0.4114	0.4333	0.3949
0.095	57.0	2565	0.1157	0.4159	0.4370	0.4
0.0937	58.0	2610	0.1158	0.4220	0.4444	0.4051
0.0942	59.0	2655	0.1154	0.4172	0.4389	0.4009
0.0917	60.0	2700	0.1150	0.4222	0.4444	0.4056
0.0896	61.0	2745	0.1152	0.4212	0.4426	0.4051
0.0868	62.0	2790	0.1148	0.4262	0.4481	0.4097
0.0868	63.0	2835	0.1143	0.4265	0.4481	0.4102
0.0862	64.0	2880	0.1142	0.4296	0.4519	0.4130
0.0846	65.0	2925	0.1144	0.4153	0.4370	0.3991
0.0821	66.0	2970	0.1135	0.4407	0.4630	0.4241
0.0834	67.0	3015	0.1140	0.4212	0.4426	0.4051
0.0816	68.0	3060	0.1136	0.4320	0.4537	0.4157
0.0812	69.0	3105	0.1131	0.4392	0.4611	0.4227
0.0784	70.0	3150	0.1139	0.4368	0.4593	0.4199
0.0777	71.0	3195	0.1135	0.4265	0.4481	0.4102
0.0767	72.0	3240	0.1134	0.4259	0.4481	0.4093
0.0764	73.0	3285	0.1135	0.4347	0.4574	0.4176
0.0761	74.0	3330	0.1127	0.4315	0.4537	0.4148
0.0759	75.0	3375	0.1127	0.4336	0.4556	0.4171
0.0732	76.0	3420	0.1133	0.4368	0.4593	0.4199
0.073	77.0	3465	0.1128	0.4389	0.4611	0.4222
0.072	78.0	3510	0.1132	0.4370	0.4593	0.4204
0.0719	79.0	3555	0.1128	0.4410	0.4630	0.4245
0.0714	80.0	3600	0.1127	0.4423	0.4648	0.4255
0.0694	81.0	3645	0.1129	0.4389	0.4611	0.4222
0.07	82.0	3690	0.1128	0.4405	0.4630	0.4236
0.067	83.0	3735	0.1126	0.4423	0.4648	0.4255
0.069	84.0	3780	0.1131	0.4423	0.4648	0.4255
0.0672	85.0	3825	0.1130	0.4460	0.4685	0.4292
0.0674	86.0	3870	0.1129	0.4442	0.4667	0.4273
0.0653	87.0	3915	0.1131	0.4407	0.4630	0.4241
0.065	88.0	3960	0.1131	0.4423	0.4648	0.4255
0.0642	89.0	4005	0.1128	0.4458	0.4685	0.4287
0.0641	90.0	4050	0.1127	0.4410	0.4630	0.4245
0.0636	91.0	4095	0.1128	0.4407	0.4630	0.4241
0.0657	92.0	4140	0.1129	0.4439	0.4667	0.4269
0.0643	93.0	4185	0.1128	0.4476	0.4704	0.4306
0.063	94.0	4230	0.1129	0.4495	0.4722	0.4324
0.0634	95.0	4275	0.1129	0.4455	0.4685	0.4282
0.0643	96.0	4320	0.1128	0.4474	0.4704	0.4301
0.0625	97.0	4365	0.1127	0.4474	0.4704	0.4301
0.0636	98.0	4410	0.1128	0.4492	0.4722	0.4319
0.0627	99.0	4455	0.1128	0.4492	0.4722	0.4319
0.063	100.0	4500	0.1128	0.4492	0.4722	0.4319

Framework versions

Transformers 4.50.0.dev0
Pytorch 2.5.1+cu121
Datasets 3.4.1
Tokenizers 0.21.0

Library: transformers
Type: bert
Created: Mar 25, 2025
Updated: Mar 25, 2025