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	4	7.0829	0.0	7.0829	2.6614
No log	2.0	8	4.1973	0.0079	4.1973	2.0487
No log	3.0	12	2.6711	0.0040	2.6711	1.6344
No log	4.0	16	1.5774	0.0213	1.5774	1.2559
No log	5.0	20	0.9993	0.0213	0.9993	0.9997
No log	6.0	24	0.8305	0.1003	0.8305	0.9113
No log	7.0	28	0.7078	0.2700	0.7078	0.8413
No log	8.0	32	0.6016	0.3501	0.6016	0.7756
No log	9.0	36	0.6037	0.5352	0.6037	0.7770
No log	10.0	40	0.5127	0.5782	0.5127	0.7161
No log	11.0	44	0.5053	0.5463	0.5053	0.7108
No log	12.0	48	0.5087	0.5922	0.5087	0.7132
No log	13.0	52	0.5315	0.6383	0.5315	0.7291
No log	14.0	56	0.5221	0.5917	0.5221	0.7226
No log	15.0	60	0.6781	0.5486	0.6781	0.8235
No log	16.0	64	0.5264	0.5788	0.5264	0.7255
No log	17.0	68	0.5895	0.6108	0.5895	0.7678
No log	18.0	72	0.5789	0.6025	0.5789	0.7609
No log	19.0	76	0.5224	0.5892	0.5224	0.7227
No log	20.0	80	0.5332	0.6306	0.5332	0.7302
No log	21.0	84	0.5358	0.6089	0.5358	0.7320
No log	22.0	88	0.5687	0.6131	0.5687	0.7541
No log	23.0	92	0.5352	0.6043	0.5352	0.7316
No log	24.0	96	0.5318	0.6232	0.5318	0.7293
No log	25.0	100	0.5250	0.6077	0.5250	0.7246
No log	26.0	104	0.5279	0.5927	0.5279	0.7266
No log	27.0	108	0.5137	0.6196	0.5137	0.7168
No log	28.0	112	0.5000	0.6179	0.5000	0.7071
No log	29.0	116	0.5525	0.5943	0.5525	0.7433
No log	30.0	120	0.5034	0.6382	0.5034	0.7095
No log	31.0	124	0.5163	0.5923	0.5163	0.7186
No log	32.0	128	0.5037	0.6316	0.5037	0.7097
No log	33.0	132	0.5075	0.6035	0.5075	0.7124
No log	34.0	136	0.4916	0.6214	0.4916	0.7011
No log	35.0	140	0.5220	0.5852	0.5220	0.7225
No log	36.0	144	0.4917	0.6287	0.4917	0.7012
No log	37.0	148	0.5179	0.5931	0.5179	0.7197
No log	38.0	152	0.4978	0.6135	0.4978	0.7055
No log	39.0	156	0.5145	0.6031	0.5145	0.7173
No log	40.0	160	0.5038	0.6039	0.5038	0.7098
No log	41.0	164	0.5208	0.5763	0.5208	0.7217
No log	42.0	168	0.5005	0.6101	0.5005	0.7075
No log	43.0	172	0.5040	0.6106	0.5040	0.7099

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex100_lo50_k10_k10_fold4

BERT_V8_sp10_lw20_ex100_lo50_k10_k10_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex100_lo50_k10_k10_fold4