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	11.1841	0.0012	11.1841	3.3443
No log	2.0	6	6.6253	0.0018	6.6253	2.5740
No log	3.0	9	4.1930	0.0214	4.1930	2.0477
No log	4.0	12	2.8164	0.0079	2.8164	1.6782
No log	5.0	15	1.8317	0.1103	1.8317	1.3534
No log	6.0	18	1.6232	0.1451	1.6232	1.2740
No log	7.0	21	1.0081	0.0445	1.0081	1.0041
No log	8.0	24	0.8942	0.0870	0.8942	0.9456
No log	9.0	27	1.8116	0.1842	1.8116	1.3459
No log	10.0	30	0.8277	0.2786	0.8277	0.9098
No log	11.0	33	0.9578	0.1673	0.9578	0.9787
No log	12.0	36	1.4035	0.1499	1.4035	1.1847
No log	13.0	39	0.9536	0.1996	0.9536	0.9765
No log	14.0	42	0.7851	0.3284	0.7851	0.8861
No log	15.0	45	1.0824	0.2580	1.0824	1.0404
No log	16.0	48	1.1660	0.2802	1.1660	1.0798
No log	17.0	51	0.8035	0.3887	0.8035	0.8964
No log	18.0	54	1.3369	0.2987	1.3369	1.1563
No log	19.0	57	0.7330	0.4104	0.7330	0.8561
No log	20.0	60	1.1564	0.3240	1.1564	1.0754
No log	21.0	63	0.8147	0.3602	0.8147	0.9026
No log	22.0	66	0.9248	0.2953	0.9248	0.9617
No log	23.0	69	1.0162	0.3227	1.0162	1.0081
No log	24.0	72	0.8522	0.3478	0.8522	0.9231
No log	25.0	75	0.9099	0.4070	0.9099	0.9539
No log	26.0	78	0.7775	0.5267	0.7775	0.8817
No log	27.0	81	1.1633	0.3526	1.1633	1.0786
No log	28.0	84	0.8321	0.4656	0.8321	0.9122
No log	29.0	87	1.2012	0.3303	1.2012	1.0960
No log	30.0	90	0.7417	0.4929	0.7417	0.8612
No log	31.0	93	1.1453	0.3161	1.1453	1.0702
No log	32.0	96	0.7498	0.4611	0.7498	0.8659
No log	33.0	99	0.9378	0.3686	0.9378	0.9684
No log	34.0	102	0.8431	0.3740	0.8431	0.9182
No log	35.0	105	1.0529	0.3239	1.0529	1.0261
No log	36.0	108	0.8038	0.4539	0.8038	0.8965
No log	37.0	111	1.1793	0.3096	1.1793	1.0859
No log	38.0	114	0.7629	0.4778	0.7629	0.8734
No log	39.0	117	1.3419	0.2877	1.3419	1.1584
No log	40.0	120	1.2156	0.3167	1.2156	1.1025
No log	41.0	123	0.7754	0.4051	0.7754	0.8806
No log	42.0	126	1.2704	0.2981	1.2704	1.1271
No log	43.0	129	0.9415	0.3297	0.9415	0.9703
No log	44.0	132	1.2514	0.3093	1.2514	1.1187
No log	45.0	135	0.9478	0.3412	0.9478	0.9735
No log	46.0	138	0.8923	0.3640	0.8923	0.9446
No log	47.0	141	1.0052	0.3434	1.0052	1.0026
No log	48.0	144	0.9605	0.3455	0.9605	0.9801
No log	49.0	147	0.8615	0.3864	0.8615	0.9282
No log	50.0	150	1.0549	0.3594	1.0549	1.0271
No log	51.0	153	0.8412	0.3922	0.8412	0.9172
No log	52.0	156	0.8777	0.3634	0.8777	0.9369
No log	53.0	159	0.8645	0.3422	0.8645	0.9298
No log	54.0	162	0.8730	0.3376	0.8730	0.9343
No log	55.0	165	0.7549	0.4049	0.7549	0.8689
No log	56.0	168	1.1619	0.2833	1.1619	1.0779

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex100_lo00_k3_k3_fold4

BERT_V8_sp20_lw10_ex100_lo00_k3_k3_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex100_lo00_k3_k3_fold4