learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.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	10.4197	0.0037	10.4197	3.2280
No log	2.0	6	8.4082	0.0018	8.4082	2.8997
No log	3.0	9	6.0535	0.0013	6.0535	2.4604
No log	4.0	12	3.8834	0.0079	3.8834	1.9706
No log	5.0	15	2.2884	0.1388	2.2884	1.5127
No log	6.0	18	1.5759	0.0606	1.5759	1.2553
No log	7.0	21	1.0052	0.0213	1.0052	1.0026
No log	8.0	24	0.8401	0.2644	0.8401	0.9166
No log	9.0	27	0.7838	0.3267	0.7838	0.8853
No log	10.0	30	0.6625	0.4068	0.6625	0.8140
No log	11.0	33	0.6739	0.5052	0.6739	0.8209
No log	12.0	36	0.9373	0.3179	0.9373	0.9681
No log	13.0	39	0.6018	0.5539	0.6018	0.7757
No log	14.0	42	1.0389	0.3442	1.0389	1.0192
No log	15.0	45	0.5752	0.5455	0.5752	0.7584
No log	16.0	48	0.9805	0.3804	0.9805	0.9902
No log	17.0	51	0.6895	0.5027	0.6895	0.8304
No log	18.0	54	0.5842	0.4648	0.5842	0.7643
No log	19.0	57	0.6040	0.5244	0.6040	0.7772
No log	20.0	60	0.5454	0.5462	0.5454	0.7385
No log	21.0	63	0.5500	0.5647	0.5500	0.7416
No log	22.0	66	0.6096	0.5752	0.6096	0.7808
No log	23.0	69	0.7011	0.5715	0.7011	0.8373
No log	24.0	72	0.6295	0.5937	0.6295	0.7934
No log	25.0	75	0.6241	0.6015	0.6241	0.7900
No log	26.0	78	0.8829	0.4524	0.8829	0.9396
No log	27.0	81	0.7791	0.4978	0.7791	0.8827
No log	28.0	84	0.8435	0.4881	0.8435	0.9184
No log	29.0	87	0.8489	0.4560	0.8489	0.9214
No log	30.0	90	0.6422	0.5601	0.6422	0.8014
No log	31.0	93	1.0036	0.4312	1.0036	1.0018
No log	32.0	96	0.5978	0.5619	0.5978	0.7732
No log	33.0	99	0.6080	0.5706	0.6080	0.7797
No log	34.0	102	0.9745	0.4581	0.9745	0.9872
No log	35.0	105	0.5964	0.5614	0.5964	0.7723
No log	36.0	108	0.7422	0.5289	0.7422	0.8615
No log	37.0	111	0.8973	0.4786	0.8973	0.9472
No log	38.0	114	0.7494	0.5392	0.7494	0.8657
No log	39.0	117	0.6677	0.5453	0.6677	0.8172
No log	40.0	120	0.8192	0.5115	0.8192	0.9051
No log	41.0	123	0.7336	0.5322	0.7336	0.8565
No log	42.0	126	0.8516	0.4962	0.8516	0.9228
No log	43.0	129	0.6042	0.5688	0.6042	0.7773
No log	44.0	132	0.6304	0.5677	0.6304	0.7940
No log	45.0	135	0.9492	0.4431	0.9492	0.9743
No log	46.0	138	0.6211	0.5676	0.6211	0.7881
No log	47.0	141	0.8762	0.4610	0.8762	0.9360
No log	48.0	144	0.7644	0.4855	0.7644	0.8743
No log	49.0	147	0.5812	0.5630	0.5812	0.7624
No log	50.0	150	0.8839	0.4532	0.8839	0.9402
No log	51.0	153	0.7027	0.5098	0.7027	0.8383
No log	52.0	156	0.8175	0.5107	0.8175	0.9042
No log	53.0	159	0.6559	0.5443	0.6559	0.8098
No log	54.0	162	0.7849	0.5280	0.7849	0.8859
No log	55.0	165	0.8004	0.5043	0.8004	0.8946

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex10_lo00_k3_k3_fold4

BERT_V8_sp10_lw40_ex10_lo00_k3_k3_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex10_lo00_k3_k3_fold4