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	5	6.2463	0.0	6.2439	2.4988
No log	2.0	10	3.3582	0.0040	3.3563	1.8320
No log	3.0	15	1.8220	0.0730	1.8204	1.3492
No log	4.0	20	1.0947	0.0106	1.0934	1.0456
No log	5.0	25	0.9605	-0.0658	0.9592	0.9794
No log	6.0	30	1.0785	0.0882	1.0768	1.0377
No log	7.0	35	0.7906	0.2116	0.7895	0.8885
No log	8.0	40	0.7841	0.2445	0.7831	0.8849
No log	9.0	45	0.5447	0.4579	0.5437	0.7374
No log	10.0	50	0.5252	0.4952	0.5244	0.7242
No log	11.0	55	0.6174	0.5157	0.6167	0.7853
No log	12.0	60	0.5963	0.4924	0.5954	0.7716
No log	13.0	65	1.0271	0.3661	1.0257	1.0128
No log	14.0	70	0.5486	0.5524	0.5475	0.7400
No log	15.0	75	0.6165	0.5117	0.6155	0.7845
No log	16.0	80	0.6370	0.4952	0.6359	0.7975
No log	17.0	85	0.6076	0.5278	0.6066	0.7788
No log	18.0	90	0.5583	0.5455	0.5574	0.7466
No log	19.0	95	0.8912	0.3750	0.8900	0.9434
No log	20.0	100	0.6093	0.4848	0.6084	0.7800
No log	21.0	105	0.6362	0.4941	0.6354	0.7971
No log	22.0	110	0.6707	0.4740	0.6698	0.8184
No log	23.0	115	0.7232	0.4310	0.7222	0.8498
No log	24.0	120	0.6713	0.4319	0.6704	0.8188
No log	25.0	125	0.7036	0.4619	0.7026	0.8382
No log	26.0	130	0.6188	0.5156	0.6180	0.7861
No log	27.0	135	0.7081	0.4722	0.7071	0.8409
No log	28.0	140	0.8293	0.3886	0.8282	0.9101
No log	29.0	145	0.5894	0.5336	0.5886	0.7672
No log	30.0	150	1.0098	0.3164	1.0086	1.0043
No log	31.0	155	0.6031	0.4878	0.6023	0.7761
No log	32.0	160	1.0278	0.3120	1.0266	1.0132
No log	33.0	165	0.5991	0.4952	0.5983	0.7735
No log	34.0	170	0.7290	0.4127	0.7279	0.8532
No log	35.0	175	0.7695	0.4253	0.7685	0.8766
No log	36.0	180	0.7578	0.4317	0.7568	0.8699
No log	37.0	185	0.9907	0.3310	0.9895	0.9947
No log	38.0	190	0.6207	0.4636	0.6197	0.7872
No log	39.0	195	0.6724	0.4336	0.6713	0.8193
No log	40.0	200	0.8037	0.3766	0.8025	0.8958
No log	41.0	205	0.7156	0.4048	0.7145	0.8453
No log	42.0	210	0.8339	0.3578	0.8327	0.9125
No log	43.0	215	0.7751	0.3857	0.7740	0.8798
No log	44.0	220	0.8147	0.3687	0.8136	0.9020

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_k7_k7_fold1

BERT_V8_sp20_lw10_ex40_lo00_k7_k7_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex40_lo00_k7_k7_fold1