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	12.6541	-0.0080	12.6540	3.5572
No log	2.0	4	10.5512	-0.0045	10.5511	3.2483
No log	3.0	6	8.9841	0.0	8.9842	2.9974
No log	4.0	8	7.7319	0.0	7.7322	2.7807
No log	5.0	10	6.4888	0.0	6.4890	2.5474
No log	6.0	12	5.5359	0.0115	5.5362	2.3529
No log	7.0	14	4.5771	0.0	4.5776	2.1395
No log	8.0	16	3.7057	0.0	3.7062	1.9252
No log	9.0	18	3.0396	0.0	3.0401	1.7436
No log	10.0	20	2.6476	0.0	2.6482	1.6273
No log	11.0	22	2.7789	-0.0027	2.7795	1.6672
No log	12.0	24	2.2022	0.0101	2.2028	1.4842
No log	13.0	26	1.9477	0.0857	1.9481	1.3958
No log	14.0	28	1.9247	0.0844	1.9252	1.3875
No log	15.0	30	1.7877	0.0774	1.7882	1.3372
No log	16.0	32	1.5826	0.0376	1.5831	1.2582
No log	17.0	34	1.4114	0.0307	1.4118	1.1882
No log	18.0	36	1.3709	0.0136	1.3713	1.1710
No log	19.0	38	1.2606	0.0136	1.2610	1.1230
No log	20.0	40	1.0548	0.0136	1.0551	1.0272
No log	21.0	42	1.0373	0.0425	1.0376	1.0186
No log	22.0	44	1.1269	0.0784	1.1271	1.0616
No log	23.0	46	0.9753	0.1507	0.9754	0.9876
No log	24.0	48	0.7864	0.4180	0.7866	0.8869
No log	25.0	50	0.7956	0.3063	0.7959	0.8921
No log	26.0	52	0.8392	0.1312	0.8395	0.9163
No log	27.0	54	0.7419	0.2689	0.7420	0.8614
No log	28.0	56	0.6583	0.4612	0.6584	0.8114
No log	29.0	58	0.8235	0.4452	0.8235	0.9075
No log	30.0	60	1.0592	0.3862	1.0592	1.0292
No log	31.0	62	1.1774	0.3125	1.1774	1.0851
No log	32.0	64	1.1755	0.3046	1.1756	1.0842
No log	33.0	66	0.8373	0.4547	0.8372	0.9150
No log	34.0	68	0.6167	0.4240	0.6167	0.7853
No log	35.0	70	0.6724	0.3058	0.6725	0.8201
No log	36.0	72	0.6376	0.3169	0.6378	0.7986
No log	37.0	74	0.6460	0.4443	0.6462	0.8039
No log	38.0	76	0.5981	0.4501	0.5982	0.7734
No log	39.0	78	0.5550	0.4300	0.5548	0.7448
No log	40.0	80	0.5705	0.4650	0.5702	0.7551
No log	41.0	82	0.6885	0.4687	0.6882	0.8296
No log	42.0	84	0.8450	0.4631	0.8448	0.9191
No log	43.0	86	0.7931	0.4475	0.7929	0.8905
No log	44.0	88	0.5716	0.4775	0.5714	0.7559
No log	45.0	90	0.5895	0.4109	0.5893	0.7677
No log	46.0	92	0.6532	0.3691	0.6533	0.8082
No log	47.0	94	0.7344	0.3131	0.7346	0.8571
No log	48.0	96	0.7351	0.3291	0.7352	0.8575
No log	49.0	98	0.6592	0.3672	0.6592	0.8119
No log	50.0	100	0.6669	0.3247	0.6667	0.8165
No log	51.0	102	0.6652	0.3336	0.6650	0.8155
No log	52.0	104	0.5872	0.3925	0.5870	0.7661
No log	53.0	106	0.5628	0.4512	0.5626	0.7501
No log	54.0	108	0.5789	0.4706	0.5786	0.7607
No log	55.0	110	0.6136	0.4937	0.6133	0.7831
No log	56.0	112	0.5707	0.4948	0.5703	0.7552
No log	57.0	114	0.5155	0.5179	0.5150	0.7177
No log	58.0	116	0.5699	0.5168	0.5695	0.7547
No log	59.0	118	0.5897	0.4915	0.5895	0.7678
No log	60.0	120	0.6113	0.4552	0.6112	0.7818
No log	61.0	122	0.6329	0.4293	0.6328	0.7955
No log	62.0	124	0.6457	0.4285	0.6455	0.8034
No log	63.0	126	0.6319	0.4456	0.6317	0.7948
No log	64.0	128	0.6245	0.4348	0.6243	0.7901
No log	65.0	130	0.6318	0.4357	0.6317	0.7948
No log	66.0	132	0.6629	0.4071	0.6628	0.8141
No log	67.0	134	0.6874	0.3915	0.6873	0.8291
No log	68.0	136	0.6536	0.4484	0.6534	0.8083
No log	69.0	138	0.6008	0.4780	0.6004	0.7749
No log	70.0	140	0.5990	0.4916	0.5986	0.7737
No log	71.0	142	0.6092	0.4749	0.6088	0.7803
No log	72.0	144	0.6293	0.4469	0.6290	0.7931
No log	73.0	146	0.6406	0.4375	0.6404	0.8002
No log	74.0	148	0.6481	0.4352	0.6478	0.8048
No log	75.0	150	0.6470	0.4401	0.6467	0.8042
No log	76.0	152	0.6429	0.4555	0.6426	0.8016
No log	77.0	154	0.6358	0.4681	0.6355	0.7972
No log	78.0	156	0.6521	0.4422	0.6517	0.8073
No log	79.0	158	0.6802	0.4750	0.6799	0.8245
No log	80.0	160	0.6804	0.4771	0.6801	0.8247
No log	81.0	162	0.6648	0.4758	0.6645	0.8152
No log	82.0	164	0.6278	0.4961	0.6275	0.7921
No log	83.0	166	0.6074	0.4946	0.6071	0.7792
No log	84.0	168	0.6111	0.4777	0.6108	0.7815
No log	85.0	170	0.6346	0.4588	0.6344	0.7965
No log	86.0	172	0.6801	0.4483	0.6800	0.8246
No log	87.0	174	0.7000	0.4192	0.6999	0.8366

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex30_lo00_k1_k1_fold2

BERT_V8_sp10_lw40_ex30_lo00_k1_k1_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex30_lo00_k1_k1_fold2