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	3	7.0062	0.0	7.0068	2.6470
No log	2.0	6	4.3137	0.0039	4.3141	2.0771
No log	3.0	9	3.0076	0.0	3.0080	1.7344
No log	4.0	12	2.0513	0.0539	2.0517	1.4324
No log	5.0	15	1.4176	0.0107	1.4180	1.1908
No log	6.0	18	1.0355	0.0	1.0360	1.0178
No log	7.0	21	0.8286	0.2560	0.8291	0.9105
No log	8.0	24	0.7675	0.1043	0.7678	0.8763
No log	9.0	27	0.6571	0.2251	0.6572	0.8107
No log	10.0	30	0.5013	0.4925	0.5012	0.7080
No log	11.0	33	0.5207	0.5446	0.5207	0.7216
No log	12.0	36	0.4873	0.5927	0.4872	0.6980
No log	13.0	39	0.4674	0.6042	0.4674	0.6837
No log	14.0	42	0.4859	0.6133	0.4859	0.6971
No log	15.0	45	0.4853	0.6039	0.4853	0.6966
No log	16.0	48	0.4841	0.5654	0.4841	0.6958
No log	17.0	51	0.4943	0.6055	0.4942	0.7030
No log	18.0	54	0.4760	0.5963	0.4759	0.6898
No log	19.0	57	0.5989	0.6122	0.5986	0.7737
No log	20.0	60	0.5163	0.5789	0.5160	0.7183
No log	21.0	63	0.5536	0.6092	0.5533	0.7438
No log	22.0	66	0.4794	0.5955	0.4792	0.6922
No log	23.0	69	0.4822	0.6000	0.4819	0.6942
No log	24.0	72	0.4607	0.5884	0.4605	0.6786
No log	25.0	75	0.4620	0.5850	0.4618	0.6796
No log	26.0	78	0.5112	0.6236	0.5109	0.7148
No log	27.0	81	0.4619	0.5695	0.4617	0.6795
No log	28.0	84	0.5226	0.6056	0.5223	0.7227
No log	29.0	87	0.4671	0.5652	0.4668	0.6833
No log	30.0	90	0.4939	0.6099	0.4935	0.7025
No log	31.0	93	0.4708	0.5938	0.4706	0.6860
No log	32.0	96	0.4830	0.5910	0.4828	0.6948
No log	33.0	99	0.4777	0.5647	0.4775	0.6910
No log	34.0	102	0.4664	0.6009	0.4662	0.6828
No log	35.0	105	0.4510	0.5920	0.4508	0.6714
No log	36.0	108	0.4605	0.5990	0.4604	0.6785
No log	37.0	111	0.4589	0.6104	0.4587	0.6772
No log	38.0	114	0.4620	0.6099	0.4617	0.6795
No log	39.0	117	0.5344	0.6019	0.5341	0.7308
No log	40.0	120	0.4782	0.5659	0.4780	0.6914
No log	41.0	123	0.4591	0.5824	0.4590	0.6775
No log	42.0	126	0.4975	0.6011	0.4972	0.7052
No log	43.0	129	0.4692	0.5626	0.4690	0.6849
No log	44.0	132	0.4520	0.6119	0.4518	0.6721
No log	45.0	135	0.4720	0.6098	0.4718	0.6869
No log	46.0	138	0.4753	0.5287	0.4752	0.6893
No log	47.0	141	0.4613	0.6133	0.4611	0.6791
No log	48.0	144	0.4605	0.5561	0.4603	0.6785
No log	49.0	147	0.4497	0.6065	0.4495	0.6705
No log	50.0	150	0.4490	0.6048	0.4488	0.6700
No log	51.0	153	0.4599	0.5793	0.4597	0.6780
No log	52.0	156	0.4786	0.6116	0.4784	0.6917
No log	53.0	159	0.4597	0.5793	0.4595	0.6779
No log	54.0	162	0.4572	0.6115	0.4570	0.6760
No log	55.0	165	0.4833	0.5273	0.4831	0.6951
No log	56.0	168	0.4602	0.6115	0.4600	0.6782

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex100_lo50_k7_k7_fold2

BERT_V8_sp10_lw20_ex100_lo50_k7_k7_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex100_lo50_k7_k7_fold2