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	8.7123	0.0	8.7106	2.9514
No log	2.0	6	7.1175	0.0	7.1160	2.6676
No log	3.0	9	5.3249	0.0076	5.3237	2.3073
No log	4.0	12	3.6771	0.0	3.6760	1.9173
No log	5.0	15	2.7392	0.0	2.7382	1.6548
No log	6.0	18	2.1056	0.0574	2.1049	1.4508
No log	7.0	21	1.5382	0.0202	1.5376	1.2400
No log	8.0	24	1.1727	0.0202	1.1721	1.0827
No log	9.0	27	0.9433	0.0966	0.9429	0.9710
No log	10.0	30	0.8037	0.3390	0.8034	0.8963
No log	11.0	33	0.7304	0.2567	0.7302	0.8545
No log	12.0	36	1.0821	0.1975	1.0817	1.0401
No log	13.0	39	0.6222	0.5053	0.6221	0.7887
No log	14.0	42	0.8735	0.3882	0.8734	0.9346
No log	15.0	45	1.8301	0.2398	1.8300	1.3528
No log	16.0	48	0.5588	0.5117	0.5588	0.7475
No log	17.0	51	0.7537	0.4604	0.7537	0.8681
No log	18.0	54	0.7132	0.4795	0.7132	0.8445
No log	19.0	57	0.6237	0.5294	0.6238	0.7898
No log	20.0	60	0.7166	0.4831	0.7168	0.8467
No log	21.0	63	0.7622	0.4547	0.7626	0.8733
No log	22.0	66	0.5129	0.5893	0.5134	0.7165
No log	23.0	69	0.6940	0.5181	0.6945	0.8334
No log	24.0	72	0.5687	0.5638	0.5690	0.7544
No log	25.0	75	1.2214	0.3322	1.2216	1.1052
No log	26.0	78	1.2714	0.3102	1.2715	1.1276
No log	27.0	81	0.6078	0.5500	0.6081	0.7798
No log	28.0	84	0.5426	0.5535	0.5430	0.7369
No log	29.0	87	1.1630	0.2768	1.1631	1.0785
No log	30.0	90	0.5477	0.5391	0.5481	0.7403
No log	31.0	93	0.5436	0.5540	0.5440	0.7375
No log	32.0	96	1.0418	0.3066	1.0421	1.0208
No log	33.0	99	0.6381	0.5199	0.6385	0.7990
No log	34.0	102	0.5425	0.5536	0.5429	0.7368
No log	35.0	105	0.7091	0.4959	0.7094	0.8422
No log	36.0	108	0.5328	0.5975	0.5331	0.7301
No log	37.0	111	0.6127	0.5599	0.6130	0.7829
No log	38.0	114	1.0154	0.3335	1.0156	1.0078
No log	39.0	117	0.5373	0.5851	0.5377	0.7332
No log	40.0	120	0.5367	0.5537	0.5370	0.7328
No log	41.0	123	1.0182	0.3133	1.0184	1.0091
No log	42.0	126	0.7765	0.4571	0.7767	0.8813
No log	43.0	129	0.5240	0.5894	0.5243	0.7241
No log	44.0	132	0.7627	0.4742	0.7630	0.8735
No log	45.0	135	1.0215	0.3347	1.0216	1.0108
No log	46.0	138	0.5761	0.5552	0.5764	0.7592
No log	47.0	141	0.6713	0.5076	0.6715	0.8195
No log	48.0	144	0.7055	0.4748	0.7057	0.8401
No log	49.0	147	0.5639	0.5377	0.5642	0.7511
No log	50.0	150	0.7936	0.4253	0.7938	0.8910
No log	51.0	153	0.7945	0.4214	0.7947	0.8914
No log	52.0	156	0.5801	0.5513	0.5804	0.7618
No log	53.0	159	0.7104	0.4939	0.7106	0.8429
No log	54.0	162	0.8088	0.4240	0.8090	0.8995
No log	55.0	165	0.5641	0.5658	0.5644	0.7513
No log	56.0	168	0.6811	0.4919	0.6813	0.8254
No log	57.0	171	0.6994	0.4951	0.6996	0.8364
No log	58.0	174	0.6241	0.5300	0.6244	0.7902
No log	59.0	177	0.7689	0.4363	0.7691	0.8770
No log	60.0	180	0.6197	0.5371	0.6200	0.7874
No log	61.0	183	0.6007	0.5377	0.6010	0.7752
No log	62.0	186	0.6136	0.5171	0.6138	0.7835
No log	63.0	189	0.6000	0.5262	0.6003	0.7748
No log	64.0	192	0.6560	0.5051	0.6562	0.8101
No log	65.0	195	0.6145	0.5509	0.6147	0.7840
No log	66.0	198	0.7227	0.4821	0.7230	0.8503

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_lo100_k5_k5_fold3

BERT_V8_sp10_lw20_ex100_lo100_k5_k5_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex100_lo100_k5_k5_fold3