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	2	11.1050	-0.0090	11.1050	3.3324
No log	2.0	4	9.6298	0.0018	9.6298	3.1032
No log	3.0	6	8.3833	0.0018	8.3833	2.8954
No log	4.0	8	6.9476	0.0	6.9476	2.6358
No log	5.0	10	5.8858	0.0248	5.8858	2.4261
No log	6.0	12	5.1433	0.0190	5.1433	2.2679
No log	7.0	14	4.4126	0.0079	4.4126	2.1006
No log	8.0	16	3.7393	0.0040	3.7393	1.9337
No log	9.0	18	3.1019	0.0040	3.1019	1.7612
No log	10.0	20	2.5487	0.0044	2.5487	1.5965
No log	11.0	22	2.0760	0.0981	2.0760	1.4408
No log	12.0	24	1.6496	0.0484	1.6496	1.2844
No log	13.0	26	1.5458	0.0484	1.5458	1.2433
No log	14.0	28	1.2531	0.0316	1.2531	1.1194
No log	15.0	30	1.1452	0.0107	1.1452	1.0702
No log	16.0	32	1.2052	0.0107	1.2052	1.0978
No log	17.0	34	1.0771	0.0107	1.0771	1.0378
No log	18.0	36	0.8797	0.1651	0.8797	0.9379
No log	19.0	38	0.7738	0.3835	0.7738	0.8797
No log	20.0	40	0.7311	0.4291	0.7311	0.8550
No log	21.0	42	0.7267	0.4535	0.7267	0.8525
No log	22.0	44	0.7690	0.4094	0.7690	0.8769
No log	23.0	46	0.6855	0.4948	0.6855	0.8279
No log	24.0	48	0.5633	0.5096	0.5633	0.7505
No log	25.0	50	0.5534	0.5107	0.5534	0.7439
No log	26.0	52	0.5234	0.5437	0.5234	0.7235
No log	27.0	54	0.6462	0.5537	0.6462	0.8039
No log	28.0	56	0.6608	0.5586	0.6608	0.8129
No log	29.0	58	0.5485	0.5675	0.5485	0.7406
No log	30.0	60	0.5485	0.5777	0.5485	0.7406
No log	31.0	62	0.5868	0.5736	0.5868	0.7660
No log	32.0	64	0.5479	0.5819	0.5479	0.7402
No log	33.0	66	0.5653	0.5916	0.5653	0.7519
No log	34.0	68	0.5882	0.5782	0.5882	0.7669
No log	35.0	70	0.5771	0.5811	0.5771	0.7597
No log	36.0	72	0.5871	0.5202	0.5871	0.7663
No log	37.0	74	0.5916	0.4905	0.5916	0.7692
No log	38.0	76	0.6381	0.5626	0.6381	0.7988
No log	39.0	78	0.6129	0.5652	0.6129	0.7829
No log	40.0	80	0.5969	0.5273	0.5969	0.7726
No log	41.0	82	0.7078	0.4791	0.7078	0.8413
No log	42.0	84	0.5755	0.5586	0.5755	0.7586
No log	43.0	86	0.7518	0.5386	0.7518	0.8671
No log	44.0	88	0.8800	0.5086	0.8800	0.9381
No log	45.0	90	0.7412	0.5313	0.7412	0.8609
No log	46.0	92	0.5725	0.5837	0.5725	0.7566
No log	47.0	94	0.7720	0.4592	0.7720	0.8787
No log	48.0	96	0.9504	0.4308	0.9504	0.9749
No log	49.0	98	0.7512	0.4783	0.7512	0.8667
No log	50.0	100	0.5930	0.5787	0.5930	0.7701
No log	51.0	102	0.9275	0.4938	0.9275	0.9630
No log	52.0	104	1.1917	0.4309	1.1917	1.0916
No log	53.0	106	1.1145	0.4572	1.1145	1.0557
No log	54.0	108	0.7655	0.5314	0.7655	0.8749
No log	55.0	110	0.5717	0.5745	0.5717	0.7561
No log	56.0	112	0.6529	0.5513	0.6529	0.8080
No log	57.0	114	0.6608	0.5434	0.6608	0.8129
No log	58.0	116	0.5809	0.5777	0.5809	0.7621
No log	59.0	118	0.6990	0.5440	0.6990	0.8360
No log	60.0	120	0.8434	0.5128	0.8434	0.9184
No log	61.0	122	0.7988	0.5143	0.7988	0.8938
No log	62.0	124	0.6793	0.5221	0.6793	0.8242
No log	63.0	126	0.6213	0.5702	0.6213	0.7882

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex40_lo00_k1_k1_fold4

BERT_V8_sp20_lw10_ex40_lo00_k1_k1_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex40_lo00_k1_k1_fold4