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	8.2636	0.0	8.2611	2.8742
No log	2.0	6	5.3690	0.0008	5.3670	2.3167
No log	3.0	9	3.7761	0.0040	3.7742	1.9427
No log	4.0	12	2.7362	0.0	2.7344	1.6536
No log	5.0	15	1.8365	0.0781	1.8349	1.3546
No log	6.0	18	1.4396	0.0106	1.4381	1.1992
No log	7.0	21	1.0839	0.0106	1.0825	1.0404
No log	8.0	24	1.0020	0.0211	1.0006	1.0003
No log	9.0	27	1.3691	0.0119	1.3674	1.1694
No log	10.0	30	0.9800	0.0542	0.9785	0.9892
No log	11.0	33	0.8507	0.2678	0.8494	0.9216
No log	12.0	36	0.6944	0.3985	0.6933	0.8326
No log	13.0	39	0.8804	0.2102	0.8794	0.9377
No log	14.0	42	0.6812	0.3497	0.6803	0.8248
No log	15.0	45	1.0545	0.1302	1.0533	1.0263
No log	16.0	48	0.7587	0.3125	0.7577	0.8704
No log	17.0	51	0.7282	0.3507	0.7274	0.8529
No log	18.0	54	1.1563	0.0926	1.1546	1.0745
No log	19.0	57	0.6886	0.4061	0.6879	0.8294
No log	20.0	60	1.0582	0.1635	1.0568	1.0280
No log	21.0	63	0.9381	0.3091	0.9366	0.9678
No log	22.0	66	0.8857	0.3799	0.8845	0.9405
No log	23.0	69	1.3752	0.0825	1.3730	1.1717
No log	24.0	72	0.8967	0.3781	0.8953	0.9462
No log	25.0	75	1.0474	0.2845	1.0459	1.0227
No log	26.0	78	1.2602	0.1870	1.2587	1.1219
No log	27.0	81	1.0575	0.3076	1.0561	1.0277
No log	28.0	84	0.8578	0.4492	0.8570	0.9258
No log	29.0	87	0.9750	0.3610	0.9738	0.9868
No log	30.0	90	1.3755	0.1660	1.3734	1.1719
No log	31.0	93	0.8177	0.4741	0.8165	0.9036
No log	32.0	96	1.0962	0.2600	1.0944	1.0462
No log	33.0	99	1.2572	0.1627	1.2556	1.1205
No log	34.0	102	1.1540	0.2158	1.1522	1.0734
No log	35.0	105	1.0080	0.3177	1.0064	1.0032
No log	36.0	108	1.0632	0.2894	1.0614	1.0303
No log	37.0	111	1.0182	0.3287	1.0170	1.0085
No log	38.0	114	1.2752	0.1835	1.2736	1.1285
No log	39.0	117	1.0319	0.3207	1.0306	1.0152
No log	40.0	120	1.0267	0.3071	1.0250	1.0124
No log	41.0	123	0.9845	0.3468	0.9830	0.9915
No log	42.0	126	1.2975	0.1428	1.2953	1.1381
No log	43.0	129	1.1183	0.2490	1.1167	1.0567
No log	44.0	132	1.1919	0.1629	1.1902	1.0909
No log	45.0	135	1.0574	0.2726	1.0560	1.0276
No log	46.0	138	1.1927	0.1828	1.1910	1.0913
No log	47.0	141	1.1369	0.2409	1.1351	1.0654
No log	48.0	144	0.9685	0.3329	0.9671	0.9834
No log	49.0	147	1.0893	0.2547	1.0874	1.0428
No log	50.0	150	0.9534	0.3382	0.9520	0.9757
No log	51.0	153	1.0958	0.2353	1.0940	1.0459
No log	52.0	156	1.1982	0.1649	1.1963	1.0938
No log	53.0	159	1.0185	0.2508	1.0170	1.0085
No log	54.0	162	1.0018	0.2943	1.0002	1.0001
No log	55.0	165	1.0355	0.2713	1.0340	1.0168
No log	56.0	168	1.0564	0.2449	1.0547	1.0270
No log	57.0	171	0.8722	0.3750	0.8709	0.9332
No log	58.0	174	1.0158	0.2781	1.0141	1.0070
No log	59.0	177	1.0380	0.2359	1.0364	1.0180
No log	60.0	180	0.9569	0.3058	0.9556	0.9776
No log	61.0	183	1.0932	0.2228	1.0914	1.0447

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex50_lo00_k3_k3_fold1

BERT_V8_sp20_lw10_ex50_lo00_k3_k3_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex50_lo00_k3_k3_fold1