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	13.5685	0.0001	13.5689	3.6836
No log	2.0	4	10.0295	0.0036	10.0299	3.1670
No log	3.0	6	7.3978	0.0	7.3982	2.7200
No log	4.0	8	6.4899	0.0	6.4902	2.5476
No log	5.0	10	6.3132	0.0	6.3135	2.5127
No log	6.0	12	6.1744	0.0	6.1747	2.4849
No log	7.0	14	6.0317	-0.0018	6.0320	2.4560
No log	8.0	16	5.8828	0.0	5.8831	2.4255
No log	9.0	18	5.7275	0.0	5.7279	2.3933
No log	10.0	20	5.5652	0.0	5.5655	2.3591
No log	11.0	22	5.3936	0.0	5.3939	2.3225
No log	12.0	24	5.2043	0.0	5.2047	2.2814
No log	13.0	26	4.9833	0.0	4.9836	2.2324
No log	14.0	28	4.6476	0.0	4.6480	2.1559
No log	15.0	30	4.1573	0.0	4.1578	2.0391
No log	16.0	32	3.6674	0.0	3.6678	1.9151
No log	17.0	34	3.1579	0.0	3.1583	1.7772
No log	18.0	36	2.7839	0.0	2.7843	1.6686
No log	19.0	38	2.5875	0.0036	2.5880	1.6087
No log	20.0	40	2.2106	0.1182	2.2110	1.4870
No log	21.0	42	1.6388	0.0213	1.6393	1.2803
No log	22.0	44	1.3650	0.0107	1.3655	1.1685
No log	23.0	46	1.4592	0.0213	1.4597	1.2082
No log	24.0	48	1.2236	0.0107	1.2241	1.1064
No log	25.0	50	0.9016	0.0	0.9020	0.9498
No log	26.0	52	0.8142	0.3695	0.8146	0.9026
No log	27.0	54	0.9872	0.0523	0.9877	0.9938
No log	28.0	56	0.8555	0.2657	0.8560	0.9252
No log	29.0	58	0.7056	0.3150	0.7059	0.8402
No log	30.0	60	0.8616	0.0353	0.8620	0.9284
No log	31.0	62	0.8213	0.1939	0.8216	0.9064
No log	32.0	64	0.6682	0.4021	0.6683	0.8175
No log	33.0	66	0.5883	0.5266	0.5884	0.7671
No log	34.0	68	0.9757	0.4261	0.9763	0.9881
No log	35.0	70	0.7035	0.5002	0.7038	0.8389
No log	36.0	72	0.5971	0.5355	0.5972	0.7728
No log	37.0	74	0.5858	0.5336	0.5860	0.7655
No log	38.0	76	0.7827	0.4636	0.7831	0.8849
No log	39.0	78	1.6464	0.1986	1.6472	1.2834
No log	40.0	80	2.2771	0.1411	2.2779	1.5093
No log	41.0	82	1.9863	0.1793	1.9871	1.4096
No log	42.0	84	1.1135	0.3144	1.1141	1.0555
No log	43.0	86	0.5761	0.5117	0.5763	0.7592
No log	44.0	88	0.5518	0.4461	0.5519	0.7429
No log	45.0	90	0.5972	0.3927	0.5973	0.7729
No log	46.0	92	0.5757	0.4108	0.5759	0.7589
No log	47.0	94	0.5460	0.5061	0.5462	0.7390
No log	48.0	96	0.9039	0.4435	0.9043	0.9509
No log	49.0	98	1.7918	0.1847	1.7927	1.3389
No log	50.0	100	1.8935	0.1774	1.8943	1.3763
No log	51.0	102	1.4777	0.2719	1.4784	1.2159
No log	52.0	104	1.1323	0.3708	1.1328	1.0643
No log	53.0	106	1.2575	0.3425	1.2581	1.1216
No log	54.0	108	1.7593	0.2050	1.7600	1.3267
No log	55.0	110	2.0535	0.1539	2.0543	1.4333
No log	56.0	112	1.7903	0.1957	1.7911	1.3383
No log	57.0	114	1.4786	0.2774	1.4794	1.2163
No log	58.0	116	1.7256	0.2161	1.7264	1.3139
No log	59.0	118	2.4337	0.1057	2.4345	1.5603
No log	60.0	120	2.5179	0.0971	2.5187	1.5870
No log	61.0	122	1.9596	0.1701	1.9605	1.4002
No log	62.0	124	1.0540	0.3679	1.0547	1.0270
No log	63.0	126	1.2932	0.2882	1.2940	1.1376
No log	64.0	128	2.5117	0.0802	2.5127	1.5851
No log	65.0	130	3.0757	0.0169	3.0765	1.7540
No log	66.0	132	3.2399	0.0062	3.2406	1.8002

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex40_lo00_k1_k1_fold2

BERT_V8_sp20_lw10_ex40_lo00_k1_k1_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex40_lo00_k1_k1_fold2