learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
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
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	5	9.1006	0.0	9.0991	3.0165
No log	2.0	10	4.4652	0.0133	4.4639	2.1128
No log	3.0	15	2.2290	0.0426	2.2283	1.4927
No log	4.0	20	1.1343	0.0102	1.1338	1.0648
No log	5.0	25	1.4036	0.0201	1.4029	1.1844
No log	6.0	30	1.1699	0.0326	1.1694	1.0814
No log	7.0	35	1.4393	0.0529	1.4385	1.1994
No log	8.0	40	0.9654	0.1258	0.9653	0.9825
No log	9.0	45	1.9505	0.0493	1.9499	1.3964
No log	10.0	50	0.8296	0.2070	0.8299	0.9110
No log	11.0	55	1.5114	0.1616	1.5110	1.2292
No log	12.0	60	0.8892	0.2362	0.8892	0.9430
No log	13.0	65	0.8347	0.2131	0.8350	0.9138
No log	14.0	70	1.0932	0.2310	1.0934	1.0457
No log	15.0	75	0.7942	0.2795	0.7945	0.8914
No log	16.0	80	0.9512	0.2884	0.9514	0.9754
No log	17.0	85	1.3070	0.2158	1.3070	1.1433
No log	18.0	90	1.6531	0.0983	1.6529	1.2856
No log	19.0	95	0.8388	0.2749	0.8392	0.9161
No log	20.0	100	1.2164	0.2192	1.2164	1.1029
No log	21.0	105	1.2512	0.2243	1.2512	1.1186
No log	22.0	110	1.8776	0.0771	1.8773	1.3701
No log	23.0	115	1.0380	0.2447	1.0383	1.0189
No log	24.0	120	1.1613	0.2257	1.1615	1.0777
No log	25.0	125	1.3777	0.1994	1.3778	1.1738
No log	26.0	130	1.9082	0.0908	1.9080	1.3813
No log	27.0	135	1.1940	0.2329	1.1941	1.0928
No log	28.0	140	1.2159	0.2202	1.2161	1.1028
No log	29.0	145	1.0354	0.2676	1.0357	1.0177
No log	30.0	150	1.3963	0.1502	1.3965	1.1817
No log	31.0	155	1.5812	0.0914	1.5814	1.2575
No log	32.0	160	1.3953	0.1390	1.3955	1.1813
No log	33.0	165	1.2048	0.2138	1.2050	1.0977
No log	34.0	170	1.4473	0.1296	1.4474	1.2031
No log	35.0	175	1.8392	0.0862	1.8392	1.3562
No log	36.0	180	1.5515	0.1059	1.5516	1.2456
No log	37.0	185	1.1378	0.2015	1.1379	1.0667
No log	38.0	190	1.1149	0.2176	1.1150	1.0559
No log	39.0	195	1.2742	0.1633	1.2743	1.1288
No log	40.0	200	1.3904	0.1262	1.3904	1.1792
No log	41.0	205	1.3087	0.1851	1.3086	1.1439
No log	42.0	210	1.1071	0.2220	1.1072	1.0522
No log	43.0	215	1.2328	0.1804	1.2329	1.1104
No log	44.0	220	1.4088	0.1530	1.4088	1.1869
No log	45.0	225	1.5554	0.1131	1.5552	1.2471
No log	46.0	230	0.9898	0.2642	0.9899	0.9949

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex50_lo00_k7_k7_fold3

BERT_V8_sp20_lw10_ex50_lo00_k7_k7_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex50_lo00_k7_k7_fold3