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	6	9.1159	0.0	9.1134	3.0188
No log	2.0	12	6.3779	0.0	6.3756	2.5250
No log	3.0	18	3.3583	0.0	3.3564	1.8320
No log	4.0	24	1.7537	0.0379	1.7521	1.3237
No log	5.0	30	1.0282	0.0	1.0269	1.0133
No log	6.0	36	0.8628	0.2709	0.8616	0.9282
No log	7.0	42	0.8981	0.1068	0.8968	0.9470
No log	8.0	48	0.8208	0.3101	0.8197	0.9054
No log	9.0	54	0.6621	0.4569	0.6614	0.8132
No log	10.0	60	0.7916	0.3827	0.7913	0.8896
No log	11.0	66	0.8126	0.4407	0.8125	0.9014
No log	12.0	72	1.2484	0.3140	1.2478	1.1170
No log	13.0	78	1.8294	0.2060	1.8287	1.3523
No log	14.0	84	1.1735	0.2902	1.1722	1.0827
No log	15.0	90	0.8976	0.3864	0.8963	0.9467
No log	16.0	96	1.2974	0.2801	1.2964	1.1386
No log	17.0	102	1.1357	0.3228	1.1349	1.0653
No log	18.0	108	1.1845	0.3122	1.1836	1.0880
No log	19.0	114	1.1104	0.3138	1.1093	1.0532
No log	20.0	120	0.8393	0.4266	0.8381	0.9155
No log	21.0	126	1.6294	0.1947	1.6280	1.2759
No log	22.0	132	1.1879	0.2778	1.1867	1.0893
No log	23.0	138	1.2077	0.2529	1.2064	1.0984
No log	24.0	144	1.2320	0.2732	1.2307	1.1094
No log	25.0	150	1.0231	0.3140	1.0219	1.0109
No log	26.0	156	1.1142	0.2890	1.1130	1.0550
No log	27.0	162	0.7791	0.4830	0.7780	0.8820
No log	28.0	168	1.2242	0.2765	1.2229	1.1058
No log	29.0	174	1.2292	0.2455	1.2277	1.1080
No log	30.0	180	1.2016	0.2717	1.2003	1.0956
No log	31.0	186	1.0980	0.2917	1.0966	1.0472
No log	32.0	192	1.2830	0.2174	1.2816	1.1321
No log	33.0	198	1.3997	0.2252	1.3985	1.1826
No log	34.0	204	1.2995	0.2470	1.2984	1.1395
No log	35.0	210	1.0741	0.3029	1.0729	1.0358
No log	36.0	216	1.0259	0.3222	1.0245	1.0122
No log	37.0	222	1.3499	0.2401	1.3484	1.1612
No log	38.0	228	1.2503	0.2766	1.2489	1.1175
No log	39.0	234	1.4240	0.2136	1.4225	1.1927
No log	40.0	240	1.2794	0.2517	1.2780	1.1305
No log	41.0	246	1.2456	0.2703	1.2443	1.1155
No log	42.0	252	1.2190	0.2453	1.2176	1.1034
No log	43.0	258	1.1492	0.2460	1.1477	1.0713
No log	44.0	264	1.1673	0.2757	1.1659	1.0798
No log	45.0	270	1.0433	0.3161	1.0420	1.0208
No log	46.0	276	1.0316	0.2900	1.0303	1.0150
No log	47.0	282	1.3885	0.2212	1.3870	1.1777
No log	48.0	288	1.2779	0.2547	1.2765	1.1298
No log	49.0	294	1.0344	0.3398	1.0331	1.0164
No log	50.0	300	1.0297	0.3353	1.0285	1.0141
No log	51.0	306	1.0814	0.2910	1.0801	1.0393
No log	52.0	312	1.1865	0.2733	1.1852	1.0887
No log	53.0	318	0.9924	0.3154	0.9911	0.9955
No log	54.0	324	1.0507	0.3210	1.0494	1.0244
No log	55.0	330	1.1345	0.2871	1.1332	1.0645
No log	56.0	336	1.2455	0.2687	1.2441	1.1154
No log	57.0	342	1.1779	0.2710	1.1765	1.0847

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_k10_k10_fold1

BERT_V8_sp10_lw40_ex10_lo00_k10_k10_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex10_lo00_k10_k10_fold1