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	8.7864	0.0	8.7865	2.9642
No log	2.0	4	6.2838	0.0079	6.2841	2.5068
No log	3.0	6	4.7884	0.0147	4.7888	2.1883
No log	4.0	8	3.7149	0.0078	3.7155	1.9276
No log	5.0	10	3.0365	0.0	3.0372	1.7428
No log	6.0	12	2.3081	0.1720	2.3085	1.5194
No log	7.0	14	1.8785	0.0475	1.8789	1.3707
No log	8.0	16	1.4290	0.0213	1.4294	1.1956
No log	9.0	18	1.1096	0.0213	1.1100	1.0536
No log	10.0	20	0.8880	0.0213	0.8884	0.9425
No log	11.0	22	0.7763	0.3871	0.7766	0.8812
No log	12.0	24	0.6637	0.4081	0.6639	0.8148
No log	13.0	26	0.6660	0.4523	0.6662	0.8162
No log	14.0	28	0.5436	0.5024	0.5437	0.7374
No log	15.0	30	0.5332	0.4434	0.5332	0.7302
No log	16.0	32	0.8418	0.4233	0.8422	0.9177
No log	17.0	34	0.8255	0.4222	0.8259	0.9088
No log	18.0	36	0.4873	0.5689	0.4875	0.6982
No log	19.0	38	0.7041	0.4468	0.7045	0.8393
No log	20.0	40	0.6366	0.4686	0.6369	0.7981
No log	21.0	42	0.5001	0.5297	0.5003	0.7073
No log	22.0	44	0.6123	0.4721	0.6127	0.7827
No log	23.0	46	0.5708	0.5062	0.5710	0.7557
No log	24.0	48	0.6048	0.5291	0.6048	0.7777
No log	25.0	50	0.5784	0.4985	0.5786	0.7606
No log	26.0	52	0.5734	0.5179	0.5736	0.7574
No log	27.0	54	0.5325	0.6142	0.5327	0.7299
No log	28.0	56	0.5931	0.5171	0.5934	0.7703
No log	29.0	58	0.5476	0.5704	0.5478	0.7401
No log	30.0	60	0.7017	0.4809	0.7019	0.8378
No log	31.0	62	0.6162	0.5011	0.6164	0.7851
No log	32.0	64	0.5351	0.5911	0.5351	0.7315
No log	33.0	66	0.7228	0.4211	0.7230	0.8503
No log	34.0	68	0.7148	0.4106	0.7150	0.8456
No log	35.0	70	0.5364	0.5589	0.5365	0.7324
No log	36.0	72	0.6466	0.4529	0.6469	0.8043
No log	37.0	74	0.5967	0.4852	0.5969	0.7726
No log	38.0	76	0.5754	0.5246	0.5756	0.7587
No log	39.0	78	0.6508	0.4741	0.6510	0.8068
No log	40.0	80	0.5923	0.5148	0.5925	0.7697
No log	41.0	82	0.5983	0.4946	0.5984	0.7736
No log	42.0	84	0.6358	0.4898	0.6360	0.7975
No log	43.0	86	0.5749	0.5355	0.5750	0.7583
No log	44.0	88	0.7484	0.4130	0.7486	0.8652
No log	45.0	90	0.6498	0.4452	0.6500	0.8062
No log	46.0	92	0.5774	0.5286	0.5776	0.7600
No log	47.0	94	0.6533	0.4413	0.6536	0.8085
No log	48.0	96	0.6206	0.4765	0.6209	0.7880
No log	49.0	98	0.5571	0.5311	0.5573	0.7465
No log	50.0	100	0.5984	0.4886	0.5985	0.7736
No log	51.0	102	0.6976	0.4396	0.6977	0.8353
No log	52.0	104	0.5757	0.5300	0.5758	0.7588
No log	53.0	106	0.6096	0.4842	0.6097	0.7808
No log	54.0	108	0.6552	0.4642	0.6553	0.8095
No log	55.0	110	0.5642	0.5332	0.5642	0.7512
No log	56.0	112	0.5780	0.5207	0.5781	0.7604
No log	57.0	114	0.6935	0.4084	0.6936	0.8329

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex100_lo100_k3_k3_fold2

BERT_V8_sp10_lw20_ex100_lo100_k3_k3_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex100_lo100_k3_k3_fold2