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	2	11.9063	-0.0279	11.9038	3.4502
No log	2.0	4	9.2561	0.0	9.2545	3.0421
No log	3.0	6	7.3906	0.0	7.3892	2.7183
No log	4.0	8	6.1470	0.0104	6.1455	2.4790
No log	5.0	10	4.7307	0.0114	4.7296	2.1748
No log	6.0	12	3.6712	0.0038	3.6702	1.9158
No log	7.0	14	2.9987	0.0	2.9976	1.7313
No log	8.0	16	2.2411	0.1175	2.2402	1.4967
No log	9.0	18	1.7994	0.0365	1.7986	1.3411
No log	10.0	20	1.5119	0.0302	1.5112	1.2293
No log	11.0	22	1.1775	0.0302	1.1769	1.0849
No log	12.0	24	1.0014	0.0202	1.0008	1.0004
No log	13.0	26	0.8976	0.3195	0.8970	0.9471
No log	14.0	28	0.8228	0.3673	0.8222	0.9068
No log	15.0	30	0.8523	0.2800	0.8517	0.9229
No log	16.0	32	0.7316	0.2326	0.7313	0.8551
No log	17.0	34	0.6307	0.3785	0.6306	0.7941
No log	18.0	36	0.6821	0.4362	0.6819	0.8258
No log	19.0	38	0.5622	0.4421	0.5621	0.7497
No log	20.0	40	0.5782	0.4760	0.5781	0.7603
No log	21.0	42	0.6375	0.5111	0.6373	0.7983
No log	22.0	44	0.5141	0.5263	0.5140	0.7169
No log	23.0	46	0.7375	0.4655	0.7373	0.8587
No log	24.0	48	0.5200	0.5555	0.5201	0.7212
No log	25.0	50	0.5088	0.6219	0.5088	0.7133
No log	26.0	52	0.7115	0.5143	0.7114	0.8435
No log	27.0	54	0.7079	0.4985	0.7077	0.8412
No log	28.0	56	0.5335	0.5843	0.5335	0.7304
No log	29.0	58	0.6170	0.5431	0.6170	0.7855
No log	30.0	60	0.5067	0.5731	0.5068	0.7119
No log	31.0	62	0.6167	0.5527	0.6169	0.7854
No log	32.0	64	0.5177	0.5983	0.5178	0.7196
No log	33.0	66	0.5050	0.6377	0.5049	0.7106
No log	34.0	68	0.5707	0.5896	0.5706	0.7554
No log	35.0	70	0.6511	0.5396	0.6510	0.8068
No log	36.0	72	0.5217	0.5770	0.5215	0.7222
No log	37.0	74	0.5531	0.5585	0.5529	0.7436
No log	38.0	76	0.6864	0.4928	0.6862	0.8284
No log	39.0	78	0.6373	0.5037	0.6372	0.7982
No log	40.0	80	0.5506	0.5552	0.5506	0.7420
No log	41.0	82	0.5623	0.5400	0.5622	0.7498
No log	42.0	84	0.6502	0.5007	0.6500	0.8062
No log	43.0	86	0.5781	0.5547	0.5779	0.7602
No log	44.0	88	0.5708	0.5663	0.5706	0.7554
No log	45.0	90	0.6341	0.5154	0.6339	0.7962
No log	46.0	92	0.5815	0.5502	0.5815	0.7626
No log	47.0	94	0.6164	0.5149	0.6164	0.7851
No log	48.0	96	0.5450	0.5598	0.5450	0.7382
No log	49.0	98	0.5788	0.5238	0.5788	0.7608
No log	50.0	100	0.5876	0.5205	0.5875	0.7665
No log	51.0	102	0.5490	0.5597	0.5489	0.7409
No log	52.0	104	0.5796	0.5422	0.5795	0.7612
No log	53.0	106	0.5875	0.5350	0.5874	0.7664
No log	54.0	108	0.5454	0.5723	0.5453	0.7384
No log	55.0	110	0.5645	0.5452	0.5643	0.7512
No log	56.0	112	0.5550	0.5512	0.5550	0.7450
No log	57.0	114	0.5879	0.5476	0.5878	0.7667
No log	58.0	116	0.5735	0.5610	0.5734	0.7572
No log	59.0	118	0.5411	0.5687	0.5410	0.7356
No log	60.0	120	0.5391	0.5799	0.5391	0.7342
No log	61.0	122	0.6113	0.5802	0.6113	0.7818
No log	62.0	124	0.6268	0.5376	0.6267	0.7916
No log	63.0	126	0.5564	0.5636	0.5564	0.7459

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_lo50_k2_k2_fold3

BERT_V8_sp10_lw40_ex50_lo50_k2_k2_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex50_lo50_k2_k2_fold3