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	8.4810	0.0	8.4785	2.9118
No log	2.0	6	5.6190	-0.0088	5.6168	2.3700
No log	3.0	9	3.8666	0.0079	3.8648	1.9659
No log	4.0	12	2.7402	0.0	2.7385	1.6548
No log	5.0	15	1.8705	0.0669	1.8689	1.3671
No log	6.0	18	1.4404	0.0106	1.4389	1.1995
No log	7.0	21	1.1360	0.0106	1.1346	1.0652
No log	8.0	24	1.3802	-0.0038	1.3789	1.1743
No log	9.0	27	0.9121	0.0745	0.9109	0.9544
No log	10.0	30	0.9153	0.2709	0.9143	0.9562
No log	11.0	33	0.7348	0.3376	0.7339	0.8567
No log	12.0	36	1.0696	0.1054	1.0685	1.0337
No log	13.0	39	0.6176	0.4110	0.6168	0.7854
No log	14.0	42	0.7112	0.3513	0.7105	0.8429
No log	15.0	45	1.3003	-0.0092	1.2991	1.1398
No log	16.0	48	0.7195	0.3391	0.7190	0.8479
No log	17.0	51	1.0369	0.1847	1.0362	1.0179
No log	18.0	54	0.9295	0.2421	0.9289	0.9638
No log	19.0	57	0.8589	0.2804	0.8585	0.9266
No log	20.0	60	1.0068	0.2163	1.0061	1.0030
No log	21.0	63	0.8406	0.3258	0.8403	0.9167
No log	22.0	66	1.0472	0.1944	1.0467	1.0231
No log	23.0	69	0.9393	0.2885	0.9391	0.9691
No log	24.0	72	1.0840	0.1910	1.0836	1.0410
No log	25.0	75	0.8242	0.3880	0.8241	0.9078
No log	26.0	78	1.1931	0.1347	1.1925	1.0920
No log	27.0	81	0.9673	0.2814	0.9670	0.9834
No log	28.0	84	1.1784	0.0679	1.1778	1.0853
No log	29.0	87	1.0677	0.1409	1.0671	1.0330
No log	30.0	90	0.9080	0.2612	0.9075	0.9526
No log	31.0	93	1.2383	0.0695	1.2377	1.1125
No log	32.0	96	1.0087	0.2607	1.0083	1.0041
No log	33.0	99	1.1193	0.2097	1.1185	1.0576
No log	34.0	102	0.9155	0.3092	0.9149	0.9565
No log	35.0	105	1.1933	0.1549	1.1923	1.0919
No log	36.0	108	0.9539	0.2530	0.9532	0.9763
No log	37.0	111	1.1381	0.1616	1.1371	1.0663
No log	38.0	114	1.0803	0.1364	1.0794	1.0389
No log	39.0	117	0.9694	0.2206	0.9685	0.9841
No log	40.0	120	1.0585	0.1513	1.0576	1.0284
No log	41.0	123	1.0822	0.1379	1.0813	1.0399
No log	42.0	126	1.0198	0.2097	1.0188	1.0094
No log	43.0	129	0.9104	0.2572	0.9095	0.9537

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex100_lo00_k3_k3_fold1

BERT_V8_sp20_lw10_ex100_lo00_k3_k3_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex100_lo00_k3_k3_fold1