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	8.7795	0.0054	8.7795	2.9630
No log	2.0	6	6.8140	0.0	6.8140	2.6104
No log	3.0	9	4.4074	0.0115	4.4074	2.0994
No log	4.0	12	3.0212	0.0115	3.0212	1.7381
No log	5.0	15	2.0628	0.1117	2.0628	1.4363
No log	6.0	18	1.3656	0.0316	1.3656	1.1686
No log	7.0	21	1.0063	0.0316	1.0063	1.0032
No log	8.0	24	0.9483	0.0681	0.9483	0.9738
No log	9.0	27	0.7775	0.4194	0.7775	0.8818
No log	10.0	30	1.0736	0.2430	1.0736	1.0362
No log	11.0	33	0.9578	0.4467	0.9578	0.9787
No log	12.0	36	1.2156	0.3063	1.2156	1.1025
No log	13.0	39	0.6818	0.4923	0.6818	0.8257
No log	14.0	42	0.7699	0.4605	0.7699	0.8774
No log	15.0	45	0.9994	0.3934	0.9994	0.9997
No log	16.0	48	0.9358	0.4009	0.9358	0.9674
No log	17.0	51	1.1694	0.2970	1.1694	1.0814
No log	18.0	54	1.2852	0.2617	1.2852	1.1337
No log	19.0	57	0.7712	0.4243	0.7712	0.8782
No log	20.0	60	0.8954	0.3708	0.8954	0.9462
No log	21.0	63	2.5409	0.1193	2.5409	1.5940
No log	22.0	66	0.7922	0.3936	0.7922	0.8901
No log	23.0	69	0.8281	0.3889	0.8281	0.9100
No log	24.0	72	2.3502	0.0788	2.3502	1.5330
No log	25.0	75	1.6556	0.1614	1.6556	1.2867
No log	26.0	78	0.9405	0.2757	0.9405	0.9698
No log	27.0	81	0.9751	0.2643	0.9751	0.9875
No log	28.0	84	1.8486	0.1395	1.8486	1.3596
No log	29.0	87	1.0860	0.2523	1.0860	1.0421
No log	30.0	90	0.8810	0.3153	0.8810	0.9386
No log	31.0	93	1.5561	0.1871	1.5561	1.2474
No log	32.0	96	1.2519	0.2156	1.2519	1.1189
No log	33.0	99	0.9815	0.2729	0.9815	0.9907
No log	34.0	102	1.4722	0.2167	1.4722	1.2133
No log	35.0	105	1.0129	0.2991	1.0129	1.0064
No log	36.0	108	1.1163	0.2758	1.1163	1.0566
No log	37.0	111	1.7384	0.1409	1.7384	1.3185
No log	38.0	114	1.1008	0.2915	1.1008	1.0492
No log	39.0	117	0.9567	0.3361	0.9567	0.9781
No log	40.0	120	1.6281	0.1668	1.6281	1.2760
No log	41.0	123	1.5903	0.1867	1.5903	1.2611
No log	42.0	126	1.0100	0.3142	1.0100	1.0050
No log	43.0	129	1.2064	0.2504	1.2064	1.0984

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_k3_k3_fold0

BERT_V8_sp20_lw10_ex40_lo00_k3_k3_fold0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex40_lo00_k3_k3_fold0