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	9.4033	0.0	9.4033	3.0665
No log	2.0	6	8.2670	0.0	8.2670	2.8752
No log	3.0	9	6.7456	0.0	6.7456	2.5972
No log	4.0	12	5.0210	0.0079	5.0210	2.2408
No log	5.0	15	3.4877	0.0040	3.4877	1.8675
No log	6.0	18	2.4066	0.0632	2.4066	1.5513
No log	7.0	21	1.7352	0.0572	1.7352	1.3173
No log	8.0	24	1.1424	0.0213	1.1424	1.0689
No log	9.0	27	0.9077	0.0801	0.9077	0.9527
No log	10.0	30	0.8875	0.1665	0.8875	0.9421
No log	11.0	33	0.7861	0.2833	0.7861	0.8866
No log	12.0	36	0.7900	0.2376	0.7900	0.8888
No log	13.0	39	1.3284	0.0046	1.3284	1.1526
No log	14.0	42	0.7389	0.3744	0.7389	0.8596
No log	15.0	45	1.5569	0.0081	1.5569	1.2478
No log	16.0	48	0.7200	0.4197	0.7200	0.8485
No log	17.0	51	1.4564	0.0264	1.4564	1.2068
No log	18.0	54	0.7382	0.4220	0.7382	0.8592
No log	19.0	57	1.2955	0.0415	1.2955	1.1382
No log	20.0	60	0.7754	0.4308	0.7754	0.8806
No log	21.0	63	1.2656	0.0796	1.2656	1.1250
No log	22.0	66	0.8881	0.3686	0.8881	0.9424
No log	23.0	69	1.4060	0.0468	1.4060	1.1857
No log	24.0	72	1.3353	0.1089	1.3353	1.1555
No log	25.0	75	1.1531	0.1787	1.1531	1.0738
No log	26.0	78	1.9475	-0.0293	1.9475	1.3955
No log	27.0	81	1.3889	0.1281	1.3889	1.1785
No log	28.0	84	0.8586	0.4737	0.8586	0.9266
No log	29.0	87	1.7084	0.0325	1.7084	1.3070
No log	30.0	90	1.3454	0.1493	1.3454	1.1599
No log	31.0	93	1.1845	0.2105	1.1845	1.0884
No log	32.0	96	1.4301	0.1689	1.4301	1.1959
No log	33.0	99	1.2824	0.1937	1.2824	1.1324
No log	34.0	102	1.5050	0.0852	1.5050	1.2268
No log	35.0	105	1.0761	0.2483	1.0761	1.0374
No log	36.0	108	1.6174	0.0866	1.6174	1.2718
No log	37.0	111	1.2485	0.2339	1.2485	1.1174
No log	38.0	114	1.4936	0.1244	1.4936	1.2221
No log	39.0	117	1.3209	0.1873	1.3209	1.1493
No log	40.0	120	1.3576	0.1512	1.3576	1.1652
No log	41.0	123	1.2272	0.1639	1.2272	1.1078
No log	42.0	126	1.1869	0.2032	1.1869	1.0895
No log	43.0	129	1.5270	0.1054	1.5270	1.2357
No log	44.0	132	1.1968	0.1810	1.1968	1.0940
No log	45.0	135	1.3977	0.1448	1.3977	1.1822
No log	46.0	138	1.2293	0.1636	1.2293	1.1087
No log	47.0	141	1.2864	0.1372	1.2864	1.1342
No log	48.0	144	1.8224	0.0131	1.8224	1.3500
No log	49.0	147	1.3008	0.1455	1.3008	1.1405
No log	50.0	150	0.9325	0.3526	0.9325	0.9656
No log	51.0	153	1.2406	0.1850	1.2406	1.1138
No log	52.0	156	1.6194	0.0802	1.6194	1.2726
No log	53.0	159	1.1785	0.1927	1.1785	1.0856
No log	54.0	162	1.4833	0.1298	1.4833	1.2179
No log	55.0	165	1.2894	0.1477	1.2894	1.1355
No log	56.0	168	1.3273	0.1449	1.3273	1.1521
No log	57.0	171	1.2392	0.1465	1.2392	1.1132
No log	58.0	174	1.1539	0.1924	1.1539	1.0742

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_k3_k3_fold4

BERT_V8_sp20_lw10_ex50_lo00_k3_k3_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex50_lo00_k3_k3_fold4