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	10.8336	0.0200	10.8336	3.2914
No log	2.0	4	10.1757	0.0018	10.1757	3.1899
No log	3.0	6	9.3953	0.0018	9.3953	3.0652
No log	4.0	8	8.0273	0.0	8.0273	2.8332
No log	5.0	10	7.0912	0.0	7.0912	2.6629
No log	6.0	12	6.5443	0.0	6.5443	2.5582
No log	7.0	14	5.6034	0.0190	5.6034	2.3671
No log	8.0	16	4.5884	0.0079	4.5884	2.1420
No log	9.0	18	3.7443	0.0079	3.7443	1.9350
No log	10.0	20	2.9873	0.0	2.9873	1.7284
No log	11.0	22	2.4067	-0.0022	2.4067	1.5514
No log	12.0	24	2.3562	0.0978	2.3562	1.5350
No log	13.0	26	1.9512	0.0746	1.9512	1.3969
No log	14.0	28	1.6386	0.0213	1.6386	1.2801
No log	15.0	30	1.4932	0.0213	1.4932	1.2220
No log	16.0	32	1.2126	0.0213	1.2126	1.1012
No log	17.0	34	1.3339	0.0585	1.3339	1.1549
No log	18.0	36	1.1644	0.0660	1.1644	1.0791
No log	19.0	38	0.8490	0.1022	0.8490	0.9214
No log	20.0	40	0.7610	0.3869	0.7610	0.8723
No log	21.0	42	0.6992	0.4677	0.6992	0.8362
No log	22.0	44	0.8524	0.3854	0.8524	0.9233
No log	23.0	46	1.2297	0.2904	1.2297	1.1089
No log	24.0	48	1.2814	0.3244	1.2814	1.1320
No log	25.0	50	1.6245	0.3051	1.6245	1.2746
No log	26.0	52	1.1582	0.4203	1.1582	1.0762
No log	27.0	54	0.8972	0.5185	0.8972	0.9472
No log	28.0	56	1.1089	0.4570	1.1089	1.0530
No log	29.0	58	2.2835	0.2550	2.2835	1.5111
No log	30.0	60	1.3275	0.3858	1.3275	1.1522
No log	31.0	62	0.5993	0.5631	0.5993	0.7742
No log	32.0	64	0.7305	0.5628	0.7305	0.8547
No log	33.0	66	2.6112	0.2056	2.6112	1.6159
No log	34.0	68	3.0929	0.1488	3.0929	1.7587
No log	35.0	70	1.3600	0.3875	1.3600	1.1662
No log	36.0	72	0.5797	0.5571	0.5797	0.7614
No log	37.0	74	0.5875	0.5605	0.5875	0.7665
No log	38.0	76	1.3074	0.3444	1.3074	1.1434
No log	39.0	78	1.6204	0.2953	1.6204	1.2730
No log	40.0	80	1.0208	0.4309	1.0208	1.0104
No log	41.0	82	0.5932	0.5518	0.5932	0.7702
No log	42.0	84	0.6092	0.5764	0.6092	0.7805
No log	43.0	86	0.7870	0.4947	0.7870	0.8872
No log	44.0	88	0.9524	0.4591	0.9524	0.9759
No log	45.0	90	0.6450	0.5942	0.6450	0.8031
No log	46.0	92	0.6467	0.6195	0.6467	0.8041
No log	47.0	94	0.7952	0.5353	0.7952	0.8917
No log	48.0	96	0.6796	0.6284	0.6796	0.8244
No log	49.0	98	0.6427	0.6195	0.6427	0.8017
No log	50.0	100	0.6366	0.6120	0.6366	0.7979
No log	51.0	102	0.6551	0.6043	0.6551	0.8094
No log	52.0	104	0.6514	0.6064	0.6514	0.8071
No log	53.0	106	0.7397	0.5575	0.7397	0.8601
No log	54.0	108	1.1388	0.4351	1.1388	1.0671
No log	55.0	110	1.1090	0.4609	1.1090	1.0531
No log	56.0	112	0.8256	0.5582	0.8256	0.9086
No log	57.0	114	0.8766	0.5353	0.8766	0.9363
No log	58.0	116	0.9233	0.4839	0.9233	0.9609
No log	59.0	118	0.7440	0.5497	0.7440	0.8625
No log	60.0	120	0.7474	0.5414	0.7474	0.8646
No log	61.0	122	0.9433	0.4160	0.9433	0.9713
No log	62.0	124	0.8431	0.4304	0.8431	0.9182
No log	63.0	126	0.6493	0.5564	0.6493	0.8058

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_sp030_lw040_fold4

BERT_AugV8_k1_task1_organization_sp030_lw040_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_AugV8_k1_task1_organization_sp030_lw040_fold4