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: 150

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	2	10.8254	0.0112	10.8254	3.2902
No log	2.0	4	9.5213	0.0018	9.5213	3.0857
No log	3.0	6	8.5037	0.0	8.5037	2.9161
No log	4.0	8	7.6250	0.0	7.6250	2.7613
No log	5.0	10	6.5466	0.0	6.5466	2.5586
No log	6.0	12	5.2344	0.0205	5.2344	2.2879
No log	7.0	14	4.1611	0.0095	4.1611	2.0399
No log	8.0	16	3.3314	0.0040	3.3314	1.8252
No log	9.0	18	2.5080	-0.0231	2.5080	1.5837
No log	10.0	20	1.7105	0.0457	1.7105	1.3079
No log	11.0	22	1.5172	0.0445	1.5172	1.2318
No log	12.0	24	1.2328	0.0445	1.2328	1.1103
No log	13.0	26	0.9834	0.0342	0.9834	0.9917
No log	14.0	28	0.9108	0.0893	0.9108	0.9544
No log	15.0	30	0.9141	-0.0127	0.9141	0.9561
No log	16.0	32	0.8104	0.3367	0.8104	0.9002
No log	17.0	34	1.1899	0.2394	1.1899	1.0908
No log	18.0	36	1.0142	0.3404	1.0142	1.0071
No log	19.0	38	0.8239	0.4349	0.8239	0.9077
No log	20.0	40	1.2817	0.3177	1.2817	1.1321
No log	21.0	42	1.1228	0.3689	1.1228	1.0596
No log	22.0	44	0.8966	0.3941	0.8966	0.9469
No log	23.0	46	0.9373	0.3872	0.9373	0.9681
No log	24.0	48	1.3742	0.3185	1.3742	1.1723
No log	25.0	50	0.9174	0.4505	0.9174	0.9578
No log	26.0	52	0.7717	0.4842	0.7717	0.8785
No log	27.0	54	0.9848	0.4343	0.9848	0.9924
No log	28.0	56	0.8065	0.4363	0.8065	0.8980
No log	29.0	58	0.9241	0.4097	0.9241	0.9613
No log	30.0	60	1.4129	0.3088	1.4129	1.1886
No log	31.0	62	0.8781	0.4352	0.8781	0.9371
No log	32.0	64	0.7912	0.5031	0.7912	0.8895
No log	33.0	66	0.7356	0.4876	0.7356	0.8577
No log	34.0	68	1.6763	0.2485	1.6763	1.2947
No log	35.0	70	2.0175	0.1797	2.0175	1.4204
No log	36.0	72	0.9313	0.3741	0.9313	0.9650
No log	37.0	74	0.9223	0.4171	0.9223	0.9604
No log	38.0	76	1.0105	0.3595	1.0105	1.0052
No log	39.0	78	1.0714	0.2885	1.0714	1.0351
No log	40.0	80	1.3796	0.1991	1.3796	1.1745
No log	41.0	82	0.9856	0.3078	0.9856	0.9928
No log	42.0	84	0.8492	0.4651	0.8492	0.9215
No log	43.0	86	0.7467	0.4995	0.7467	0.8641
No log	44.0	88	0.8346	0.3607	0.8346	0.9136
No log	45.0	90	1.0340	0.3462	1.0340	1.0168
No log	46.0	92	0.9012	0.3962	0.9012	0.9493
No log	47.0	94	0.7940	0.5058	0.7940	0.8911
No log	48.0	96	0.8359	0.4960	0.8359	0.9143
No log	49.0	98	0.7935	0.5174	0.7935	0.8908
No log	50.0	100	1.8813	0.2425	1.8813	1.3716
No log	51.0	102	2.4626	0.1823	2.4626	1.5693
No log	52.0	104	1.8100	0.2300	1.8100	1.3453
No log	53.0	106	0.8074	0.4522	0.8074	0.8986
No log	54.0	108	0.7660	0.5134	0.7660	0.8752
No log	55.0	110	0.8107	0.4955	0.8107	0.9004
No log	56.0	112	0.9500	0.3220	0.9500	0.9747
No log	57.0	114	1.1992	0.2831	1.1992	1.0951
No log	58.0	116	1.3056	0.2622	1.3056	1.1426
No log	59.0	118	1.0806	0.3109	1.0806	1.0395
No log	60.0	120	0.7831	0.4449	0.7831	0.8850
No log	61.0	122	0.7643	0.4851	0.7643	0.8742
No log	62.0	124	0.9112	0.3867	0.9112	0.9546
No log	63.0	126	1.0183	0.3578	1.0183	1.0091
No log	64.0	128	0.7928	0.4633	0.7928	0.8904

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_AugV8_k1_task1_organization_sp010_lw050_fold4

BERT_AugV8_k1_task1_organization_sp010_lw050_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_AugV8_k1_task1_organization_sp010_lw050_fold4