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	9.5352	0.0	9.5333	3.0876
No log	2.0	12	7.7398	0.0	7.7381	2.7817
No log	3.0	18	4.9175	0.0045	4.9163	2.2173
No log	4.0	24	2.2714	0.1483	2.2707	1.5069
No log	5.0	30	1.1428	0.0	1.1425	1.0689
No log	6.0	36	0.8364	0.3291	0.8362	0.9144
No log	7.0	42	1.2426	0.0074	1.2421	1.1145
No log	8.0	48	0.7873	0.3485	0.7871	0.8872
No log	9.0	54	0.7154	0.3626	0.7153	0.8458
No log	10.0	60	0.6883	0.3487	0.6882	0.8296
No log	11.0	66	0.7037	0.4064	0.7035	0.8388
No log	12.0	72	0.8060	0.3773	0.8059	0.8977
No log	13.0	78	1.0131	0.3201	1.0130	1.0065
No log	14.0	84	1.0327	0.3331	1.0326	1.0162
No log	15.0	90	1.2477	0.2822	1.2475	1.1169
No log	16.0	96	1.1070	0.3168	1.1069	1.0521
No log	17.0	102	1.2419	0.2754	1.2417	1.1143
No log	18.0	108	1.5872	0.2335	1.5869	1.2597
No log	19.0	114	1.3818	0.2124	1.3815	1.1754
No log	20.0	120	1.8347	0.1717	1.8343	1.3544
No log	21.0	126	1.6629	0.2088	1.6626	1.2894
No log	22.0	132	1.8280	0.1624	1.8276	1.3519
No log	23.0	138	1.5426	0.2197	1.5424	1.2419
No log	24.0	144	1.6424	0.2141	1.6422	1.2815
No log	25.0	150	1.6208	0.2188	1.6206	1.2730
No log	26.0	156	1.2944	0.2803	1.2943	1.1377
No log	27.0	162	1.6188	0.2344	1.6186	1.2722
No log	28.0	168	1.5030	0.2569	1.5027	1.2259
No log	29.0	174	1.4281	0.2652	1.4278	1.1949
No log	30.0	180	1.5807	0.2174	1.5804	1.2572
No log	31.0	186	1.3399	0.2620	1.3397	1.1575
No log	32.0	192	1.0093	0.3436	1.0091	1.0046
No log	33.0	198	1.3784	0.2538	1.3781	1.1739
No log	34.0	204	1.4417	0.2558	1.4414	1.2006
No log	35.0	210	1.5121	0.2270	1.5118	1.2296
No log	36.0	216	1.3871	0.2645	1.3868	1.1776
No log	37.0	222	1.1920	0.2898	1.1918	1.0917
No log	38.0	228	1.1732	0.2915	1.1730	1.0831
No log	39.0	234	1.2327	0.2844	1.2325	1.1102
No log	40.0	240	1.2424	0.2838	1.2422	1.1146
No log	41.0	246	1.1874	0.3165	1.1872	1.0896

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_k10_k10_fold3

BERT_V8_sp10_lw40_ex50_lo100_k10_k10_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_k10_k10_fold3