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	2	7.4699	0.0	7.4677	2.7327
No log	2.0	4	6.3560	0.0	6.3537	2.5207
No log	3.0	6	5.4799	0.0201	5.4777	2.3405
No log	4.0	8	4.8517	0.0	4.8496	2.2022
No log	5.0	10	4.5161	0.0	4.5141	2.1246
No log	6.0	12	4.1484	0.0	4.1465	2.0363
No log	7.0	14	3.6413	0.0	3.6394	1.9077
No log	8.0	16	3.0571	0.0	3.0553	1.7479
No log	9.0	18	2.6407	0.0	2.6390	1.6245
No log	10.0	20	2.1871	0.1417	2.1855	1.4783
No log	11.0	22	1.8667	0.0730	1.8651	1.3657
No log	12.0	24	1.8626	0.1743	1.8610	1.3642
No log	13.0	26	1.4709	0.0768	1.4694	1.2122
No log	14.0	28	1.1424	0.0211	1.1410	1.0682
No log	15.0	30	1.0257	0.0106	1.0243	1.0121
No log	16.0	32	0.8837	0.0549	0.8825	0.9394
No log	17.0	34	0.7931	0.3725	0.7919	0.8899
No log	18.0	36	0.7533	0.4277	0.7522	0.8673
No log	19.0	38	0.7550	0.4377	0.7539	0.8683
No log	20.0	40	0.5844	0.5401	0.5834	0.7638
No log	21.0	42	0.5913	0.5912	0.5902	0.7683
No log	22.0	44	1.5463	0.2377	1.5450	1.2430
No log	23.0	46	1.9032	0.2284	1.9019	1.3791
No log	24.0	48	0.8951	0.4516	0.8940	0.9455
No log	25.0	50	0.5174	0.4751	0.5165	0.7186
No log	26.0	52	0.5348	0.4628	0.5340	0.7307
No log	27.0	54	0.5423	0.5859	0.5413	0.7358
No log	28.0	56	1.5995	0.2573	1.5981	1.2642
No log	29.0	58	2.2023	0.1906	2.2008	1.4835
No log	30.0	60	2.0269	0.2236	2.0255	1.4232
No log	31.0	62	1.2650	0.2962	1.2637	1.1242
No log	32.0	64	0.5376	0.5867	0.5366	0.7326
No log	33.0	66	0.4898	0.5301	0.4890	0.6993
No log	34.0	68	0.5014	0.5649	0.5005	0.7075
No log	35.0	70	0.7235	0.4934	0.7224	0.8499
No log	36.0	72	0.8007	0.4625	0.7995	0.8941
No log	37.0	74	0.6107	0.5436	0.6096	0.7807
No log	38.0	76	0.5377	0.5444	0.5367	0.7326
No log	39.0	78	0.5348	0.5649	0.5338	0.7306
No log	40.0	80	0.6387	0.5537	0.6375	0.7984
No log	41.0	82	0.8682	0.4607	0.8670	0.9311
No log	42.0	84	0.8078	0.4755	0.8067	0.8981
No log	43.0	86	0.6466	0.5481	0.6455	0.8034
No log	44.0	88	0.6374	0.5545	0.6362	0.7976
No log	45.0	90	0.9212	0.4135	0.9200	0.9592
No log	46.0	92	1.1270	0.3595	1.1258	1.0610
No log	47.0	94	1.2133	0.3414	1.2120	1.1009
No log	48.0	96	1.2036	0.3479	1.2022	1.0965
No log	49.0	98	0.8942	0.4022	0.8928	0.9449
No log	50.0	100	0.5684	0.5588	0.5671	0.7531
No log	51.0	102	0.6058	0.5751	0.6047	0.7776

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex40_lo00_k1_k1_fold1

BERT_V8_sp20_lw10_ex40_lo00_k1_k1_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex40_lo00_k1_k1_fold1