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	5	10.2788	0.0	10.2768	3.2057
No log	2.0	10	7.8422	0.0	7.8405	2.8001
No log	3.0	15	6.1109	0.0001	6.1091	2.4717
No log	4.0	20	3.7077	0.0	3.7068	1.9253
No log	5.0	25	1.9564	0.0628	1.9558	1.3985
No log	6.0	30	1.0802	0.0	1.0797	1.0391
No log	7.0	35	1.0492	0.0279	1.0489	1.0242
No log	8.0	40	1.3014	0.0	1.3010	1.1406
No log	9.0	45	0.8995	0.2742	0.8992	0.9483
No log	10.0	50	1.1599	0.1155	1.1595	1.0768
No log	11.0	55	0.7989	0.3136	0.7986	0.8937
No log	12.0	60	0.6937	0.3770	0.6934	0.8327
No log	13.0	65	1.0660	0.2627	1.0654	1.0322
No log	14.0	70	1.7492	0.1558	1.7482	1.3222
No log	15.0	75	0.7780	0.3849	0.7774	0.8817
No log	16.0	80	0.8886	0.3638	0.8880	0.9424
No log	17.0	85	1.4384	0.1527	1.4379	1.1991
No log	18.0	90	1.7034	0.1239	1.7029	1.3050
No log	19.0	95	0.8134	0.4053	0.8131	0.9017
No log	20.0	100	1.7117	0.1951	1.7111	1.3081
No log	21.0	105	0.8678	0.3539	0.8674	0.9314
No log	22.0	110	1.0402	0.3160	1.0399	1.0197
No log	23.0	115	1.1568	0.2396	1.1564	1.0754
No log	24.0	120	1.5997	0.1754	1.5991	1.2646
No log	25.0	125	1.4648	0.2454	1.4643	1.2101
No log	26.0	130	1.2381	0.2875	1.2377	1.1125
No log	27.0	135	1.2679	0.2731	1.2675	1.1258
No log	28.0	140	1.4275	0.2114	1.4271	1.1946
No log	29.0	145	1.5123	0.1975	1.5119	1.2296
No log	30.0	150	1.1561	0.2804	1.1559	1.0751
No log	31.0	155	1.1076	0.2956	1.1075	1.0524
No log	32.0	160	0.8095	0.3375	0.8094	0.8997
No log	33.0	165	1.1830	0.2600	1.1829	1.0876
No log	34.0	170	0.9578	0.3431	0.9576	0.9786
No log	35.0	175	1.0582	0.3255	1.0580	1.0286
No log	36.0	180	1.2843	0.2649	1.2841	1.1332
No log	37.0	185	1.1305	0.3186	1.1303	1.0631
No log	38.0	190	1.3607	0.2285	1.3604	1.1664
No log	39.0	195	1.2081	0.2705	1.2077	1.0990
No log	40.0	200	0.9804	0.3257	0.9801	0.9900
No log	41.0	205	1.3388	0.2434	1.3383	1.1569
No log	42.0	210	1.0435	0.3120	1.0432	1.0214
No log	43.0	215	1.6465	0.1612	1.6460	1.2830
No log	44.0	220	0.9153	0.3655	0.9151	0.9566
No log	45.0	225	0.9333	0.3660	0.9331	0.9660
No log	46.0	230	1.3119	0.2633	1.3116	1.1452
No log	47.0	235	0.9592	0.3400	0.9590	0.9793
No log	48.0	240	1.2323	0.2952	1.2319	1.1099
No log	49.0	245	1.2998	0.2773	1.2994	1.1399

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex50_lo100_k7_k7_fold3

BERT_V8_sp10_lw40_ex50_lo100_k7_k7_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex50_lo100_k7_k7_fold3