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	8.2564	0.0	8.2564	2.8734
No log	2.0	6	6.5851	0.0	6.5851	2.5662
No log	3.0	9	4.6813	0.0118	4.6813	2.1636
No log	4.0	12	3.4795	0.0040	3.4795	1.8654
No log	5.0	15	2.3026	0.1698	2.3026	1.5174
No log	6.0	18	1.7386	0.0420	1.7386	1.3186
No log	7.0	21	1.1626	0.0317	1.1626	1.0782
No log	8.0	24	0.8917	0.0420	0.8917	0.9443
No log	9.0	27	0.7214	0.4595	0.7214	0.8494
No log	10.0	30	0.8303	0.1722	0.8303	0.9112
No log	11.0	33	0.7887	0.5014	0.7887	0.8881
No log	12.0	36	1.0154	0.4334	1.0154	1.0077
No log	13.0	39	1.0985	0.3747	1.0985	1.0481
No log	14.0	42	0.6796	0.5444	0.6796	0.8244
No log	15.0	45	0.8752	0.4190	0.8752	0.9355
No log	16.0	48	0.6660	0.4730	0.6660	0.8161
No log	17.0	51	0.9068	0.3797	0.9068	0.9522
No log	18.0	54	0.6308	0.4671	0.6308	0.7943
No log	19.0	57	0.7616	0.4823	0.7616	0.8727
No log	20.0	60	0.5668	0.4954	0.5668	0.7529
No log	21.0	63	0.5927	0.5391	0.5927	0.7699
No log	22.0	66	0.5739	0.5347	0.5739	0.7576
No log	23.0	69	0.6592	0.5620	0.6592	0.8119
No log	24.0	72	0.8593	0.4177	0.8593	0.9270
No log	25.0	75	0.7661	0.4749	0.7661	0.8753
No log	26.0	78	0.9342	0.4504	0.9342	0.9665
No log	27.0	81	0.6027	0.5710	0.6027	0.7764
No log	28.0	84	1.2724	0.3354	1.2724	1.1280
No log	29.0	87	0.6255	0.5479	0.6255	0.7909
No log	30.0	90	0.6726	0.5693	0.6726	0.8201
No log	31.0	93	0.6925	0.5166	0.6925	0.8322
No log	32.0	96	0.6795	0.5347	0.6795	0.8243
No log	33.0	99	0.6275	0.5864	0.6275	0.7921
No log	34.0	102	0.8929	0.4499	0.8929	0.9450
No log	35.0	105	0.6075	0.5444	0.6075	0.7794
No log	36.0	108	0.5898	0.5553	0.5898	0.7680
No log	37.0	111	0.7432	0.4659	0.7432	0.8621
No log	38.0	114	0.5662	0.6382	0.5662	0.7525
No log	39.0	117	0.7467	0.4893	0.7467	0.8641
No log	40.0	120	0.6966	0.5161	0.6966	0.8346
No log	41.0	123	0.5469	0.5972	0.5469	0.7395
No log	42.0	126	0.9667	0.3818	0.9667	0.9832
No log	43.0	129	0.7748	0.4637	0.7748	0.8802
No log	44.0	132	0.5893	0.5851	0.5893	0.7676
No log	45.0	135	0.6647	0.5070	0.6647	0.8153
No log	46.0	138	1.1063	0.3236	1.1063	1.0518
No log	47.0	141	0.7293	0.4606	0.7293	0.8540
No log	48.0	144	0.6964	0.4724	0.6964	0.8345
No log	49.0	147	0.8313	0.4616	0.8313	0.9118
No log	50.0	150	0.6358	0.5285	0.6358	0.7974
No log	51.0	153	0.9156	0.4550	0.9156	0.9569
No log	52.0	156	0.7314	0.4775	0.7314	0.8552
No log	53.0	159	0.7998	0.4696	0.7998	0.8943
No log	54.0	162	0.5830	0.5546	0.5830	0.7635
No log	55.0	165	0.9028	0.4063	0.9028	0.9502
No log	56.0	168	0.8722	0.4157	0.8722	0.9339
No log	57.0	171	0.6474	0.4763	0.6474	0.8046
No log	58.0	174	0.7111	0.4408	0.7111	0.8432
No log	59.0	177	0.5911	0.5022	0.5911	0.7688
No log	60.0	180	0.6420	0.4634	0.6420	0.8012
No log	61.0	183	0.6177	0.5004	0.6177	0.7859
No log	62.0	186	0.7340	0.4613	0.7340	0.8568
No log	63.0	189	0.6666	0.4701	0.6666	0.8164
No log	64.0	192	0.6273	0.4910	0.6273	0.7920
No log	65.0	195	0.5988	0.5197	0.5988	0.7738
No log	66.0	198	0.7749	0.4498	0.7749	0.8803
No log	67.0	201	0.6509	0.4909	0.6509	0.8068
No log	68.0	204	0.6041	0.5242	0.6041	0.7773

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex30_lo00_k3_k3_fold4

BERT_V8_sp20_lw10_ex30_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_ex30_lo00_k3_k3_fold4