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	9.5775	0.0018	9.5757	3.0945
No log	2.0	6	8.1134	0.0	8.1118	2.8481
No log	3.0	9	6.3218	0.0038	6.3203	2.5140
No log	4.0	12	4.4954	0.0	4.4942	2.1200
No log	5.0	15	3.3515	0.0	3.3505	1.8304
No log	6.0	18	2.2244	0.1181	2.2237	1.4912
No log	7.0	21	1.5990	0.0266	1.5985	1.2643
No log	8.0	24	1.1746	0.0	1.1742	1.0836
No log	9.0	27	0.9070	0.2088	0.9068	0.9522
No log	10.0	30	0.8185	0.1451	0.8184	0.9047
No log	11.0	33	0.9047	0.0414	0.9046	0.9511
No log	12.0	36	0.8919	0.0567	0.8918	0.9443
No log	13.0	39	0.7041	0.3441	0.7037	0.8389
No log	14.0	42	0.6480	0.3439	0.6478	0.8049
No log	15.0	45	0.7771	0.4096	0.7770	0.8815
No log	16.0	48	0.5639	0.5759	0.5639	0.7509
No log	17.0	51	1.1526	0.3527	1.1524	1.0735
No log	18.0	54	0.5793	0.5836	0.5794	0.7612
No log	19.0	57	1.4143	0.3213	1.4142	1.1892
No log	20.0	60	1.1856	0.3459	1.1855	1.0888
No log	21.0	63	0.6070	0.5823	0.6071	0.7792
No log	22.0	66	0.8820	0.4277	0.8819	0.9391
No log	23.0	69	0.9432	0.3980	0.9431	0.9711
No log	24.0	72	0.6803	0.5378	0.6803	0.8248
No log	25.0	75	1.0273	0.3612	1.0274	1.0136
No log	26.0	78	1.0675	0.3640	1.0675	1.0332
No log	27.0	81	0.7962	0.4941	0.7962	0.8923
No log	28.0	84	0.7522	0.5032	0.7521	0.8672
No log	29.0	87	0.9092	0.3980	0.9091	0.9535
No log	30.0	90	0.9405	0.3821	0.9404	0.9697
No log	31.0	93	0.7791	0.4536	0.7790	0.8826
No log	32.0	96	0.8031	0.4457	0.8029	0.8961
No log	33.0	99	0.7485	0.5054	0.7484	0.8651
No log	34.0	102	0.7443	0.4994	0.7441	0.8626
No log	35.0	105	0.9639	0.3549	0.9637	0.9817
No log	36.0	108	0.7687	0.4863	0.7686	0.8767
No log	37.0	111	0.8160	0.4395	0.8159	0.9033
No log	38.0	114	0.7547	0.4817	0.7547	0.8687
No log	39.0	117	0.8370	0.4259	0.8370	0.9149
No log	40.0	120	0.6540	0.5484	0.6539	0.8087
No log	41.0	123	0.7814	0.4668	0.7814	0.8840
No log	42.0	126	0.7699	0.4617	0.7699	0.8774
No log	43.0	129	0.6419	0.5537	0.6418	0.8011
No log	44.0	132	0.8399	0.4282	0.8398	0.9164
No log	45.0	135	0.7169	0.5053	0.7168	0.8466
No log	46.0	138	0.7725	0.4784	0.7723	0.8788
No log	47.0	141	1.0605	0.3600	1.0603	1.0297
No log	48.0	144	0.6660	0.5260	0.6658	0.8160

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_lo50_k7_k7_fold3

BERT_V8_sp10_lw20_ex100_lo50_k7_k7_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex100_lo50_k7_k7_fold3