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	3	10.1165	0.0058	10.1165	3.1806
No log	2.0	6	6.8448	0.0018	6.8448	2.6163
No log	3.0	9	4.6093	0.0176	4.6093	2.1469
No log	4.0	12	3.3989	0.0079	3.3989	1.8436
No log	5.0	15	2.2546	0.1762	2.2546	1.5015
No log	6.0	18	1.5667	0.0420	1.5666	1.2517
No log	7.0	21	1.2897	0.0420	1.2897	1.1357
No log	8.0	24	0.9689	0.0316	0.9689	0.9843
No log	9.0	27	0.8187	0.3621	0.8187	0.9048
No log	10.0	30	0.7304	0.2413	0.7304	0.8546
No log	11.0	33	0.6653	0.3203	0.6653	0.8157
No log	12.0	36	0.5600	0.4870	0.5600	0.7483
No log	13.0	39	0.5625	0.5405	0.5625	0.7500
No log	14.0	42	0.6087	0.5523	0.6087	0.7802
No log	15.0	45	0.5554	0.5799	0.5554	0.7453
No log	16.0	48	0.5348	0.5904	0.5348	0.7313
No log	17.0	51	0.5338	0.6124	0.5338	0.7306
No log	18.0	54	0.5271	0.6192	0.5271	0.7260
No log	19.0	57	0.8788	0.4736	0.8788	0.9374
No log	20.0	60	0.5265	0.6063	0.5265	0.7256
No log	21.0	63	0.5191	0.6014	0.5191	0.7205
No log	22.0	66	0.8305	0.4787	0.8305	0.9113
No log	23.0	69	0.5749	0.5409	0.5749	0.7582
No log	24.0	72	0.6363	0.5314	0.6363	0.7977
No log	25.0	75	0.5192	0.4884	0.5192	0.7205
No log	26.0	78	0.6546	0.5448	0.6546	0.8091
No log	27.0	81	0.5602	0.5781	0.5602	0.7484
No log	28.0	84	0.5602	0.5870	0.5602	0.7485
No log	29.0	87	0.7528	0.5507	0.7528	0.8677
No log	30.0	90	0.5259	0.6200	0.5259	0.7252
No log	31.0	93	0.6245	0.5450	0.6245	0.7902
No log	32.0	96	0.4847	0.6231	0.4847	0.6962
No log	33.0	99	0.5186	0.5992	0.5186	0.7201
No log	34.0	102	0.5964	0.5602	0.5964	0.7723
No log	35.0	105	0.4914	0.6190	0.4914	0.7010
No log	36.0	108	0.6498	0.5653	0.6498	0.8061
No log	37.0	111	0.5312	0.5964	0.5312	0.7288
No log	38.0	114	0.5627	0.6028	0.5627	0.7501
No log	39.0	117	0.7187	0.5761	0.7187	0.8478
No log	40.0	120	0.8061	0.5349	0.8061	0.8978
No log	41.0	123	0.5029	0.6183	0.5029	0.7091
No log	42.0	126	0.5984	0.5813	0.5984	0.7736
No log	43.0	129	0.5303	0.6151	0.5303	0.7282
No log	44.0	132	0.5528	0.5906	0.5528	0.7435
No log	45.0	135	0.5033	0.5928	0.5033	0.7094
No log	46.0	138	0.5090	0.6180	0.5090	0.7134
No log	47.0	141	0.6236	0.6091	0.6236	0.7897
No log	48.0	144	0.5748	0.6221	0.5748	0.7582
No log	49.0	147	0.6929	0.5407	0.6929	0.8324
No log	50.0	150	0.8660	0.4764	0.8660	0.9306
No log	51.0	153	0.5208	0.6127	0.5208	0.7216
No log	52.0	156	0.5522	0.6115	0.5522	0.7431
No log	53.0	159	0.5130	0.6054	0.5130	0.7163
No log	54.0	162	0.5077	0.6115	0.5077	0.7125
No log	55.0	165	0.5334	0.6114	0.5334	0.7303
No log	56.0	168	0.5109	0.6197	0.5109	0.7148
No log	57.0	171	0.5792	0.6090	0.5792	0.7610
No log	58.0	174	0.4943	0.6276	0.4943	0.7031
No log	59.0	177	0.4897	0.6205	0.4897	0.6998
No log	60.0	180	0.5164	0.6100	0.5164	0.7186
No log	61.0	183	0.4888	0.6051	0.4888	0.6991
No log	62.0	186	0.5079	0.6158	0.5079	0.7127
No log	63.0	189	0.4932	0.6266	0.4932	0.7023
No log	64.0	192	0.4960	0.6325	0.4960	0.7043
No log	65.0	195	0.5240	0.5986	0.5240	0.7239
No log	66.0	198	0.4901	0.6078	0.4901	0.7000
No log	67.0	201	0.4938	0.6045	0.4938	0.7027
No log	68.0	204	0.4905	0.6001	0.4905	0.7004
No log	69.0	207	0.4946	0.6021	0.4946	0.7033
No log	70.0	210	0.4903	0.6098	0.4903	0.7002
No log	71.0	213	0.4896	0.6354	0.4896	0.6997
No log	72.0	216	0.4820	0.5979	0.4820	0.6942
No log	73.0	219	0.5233	0.5784	0.5233	0.7234
No log	74.0	222	0.4975	0.5819	0.4975	0.7054
No log	75.0	225	0.4909	0.5973	0.4909	0.7006
No log	76.0	228	0.5067	0.5945	0.5067	0.7118
No log	77.0	231	0.5077	0.6225	0.5077	0.7125
No log	78.0	234	0.4948	0.6124	0.4948	0.7034
No log	79.0	237	0.4844	0.6089	0.4844	0.6960
No log	80.0	240	0.4894	0.6195	0.4894	0.6995
No log	81.0	243	0.4861	0.6278	0.4861	0.6972
No log	82.0	246	0.4933	0.6117	0.4933	0.7023
No log	83.0	249	0.4892	0.6349	0.4892	0.6994
No log	84.0	252	0.4883	0.6347	0.4883	0.6988
No log	85.0	255	0.4890	0.6104	0.4890	0.6993
No log	86.0	258	0.4877	0.6223	0.4877	0.6984
No log	87.0	261	0.4878	0.6134	0.4878	0.6984
No log	88.0	264	0.4970	0.6029	0.4970	0.7050
No log	89.0	267	0.4960	0.6021	0.4960	0.7043
No log	90.0	270	0.4870	0.6048	0.4870	0.6978
No log	91.0	273	0.4858	0.6023	0.4858	0.6970
No log	92.0	276	0.4877	0.5939	0.4877	0.6984
No log	93.0	279	0.4906	0.5942	0.4906	0.7004
No log	94.0	282	0.4895	0.5941	0.4895	0.6996
No log	95.0	285	0.4873	0.6013	0.4873	0.6981
No log	96.0	288	0.4864	0.6105	0.4864	0.6974
No log	97.0	291	0.4860	0.6176	0.4860	0.6972
No log	98.0	294	0.4864	0.6182	0.4864	0.6975
No log	99.0	297	0.4867	0.6161	0.4867	0.6976
No log	100.0	300	0.4869	0.6155	0.4869	0.6978

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_lo50_k5_k5_fold4

BERT_V8_sp10_lw20_ex100_lo50_k5_k5_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex100_lo50_k5_k5_fold4