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	8.5094	0.0	8.5094	2.9171
No log	2.0	4	8.0642	0.0	8.0642	2.8398
No log	3.0	6	7.5324	0.0	7.5324	2.7445
No log	4.0	8	6.5571	-0.0008	6.5571	2.5607
No log	5.0	10	5.2608	0.0067	5.2608	2.2937
No log	6.0	12	4.2349	0.0040	4.2349	2.0579
No log	7.0	14	3.2009	0.0040	3.2009	1.7891
No log	8.0	16	2.6484	0.0	2.6484	1.6274
No log	9.0	18	2.0586	0.0643	2.0586	1.4348
No log	10.0	20	1.5823	0.0239	1.5823	1.2579
No log	11.0	22	1.2444	0.0213	1.2444	1.1155
No log	12.0	24	1.0102	0.0213	1.0102	1.0051
No log	13.0	26	0.8789	0.2124	0.8789	0.9375
No log	14.0	28	0.9979	0.0380	0.9979	0.9990
No log	15.0	30	1.0082	0.0771	1.0082	1.0041
No log	16.0	32	0.7269	0.3926	0.7269	0.8526
No log	17.0	34	0.7736	0.3095	0.7736	0.8796
No log	18.0	36	0.6765	0.4313	0.6765	0.8225
No log	19.0	38	0.7980	0.4670	0.7980	0.8933
No log	20.0	40	0.8066	0.4704	0.8066	0.8981
No log	21.0	42	0.6488	0.5104	0.6488	0.8055
No log	22.0	44	0.5825	0.5318	0.5825	0.7632
No log	23.0	46	0.6420	0.5338	0.6420	0.8013
No log	24.0	48	0.6150	0.5454	0.6150	0.7842
No log	25.0	50	0.6083	0.5265	0.6083	0.7800
No log	26.0	52	0.8909	0.4094	0.8909	0.9439
No log	27.0	54	0.8399	0.4458	0.8399	0.9165
No log	28.0	56	0.6172	0.5143	0.6172	0.7856
No log	29.0	58	0.6655	0.5373	0.6655	0.8158
No log	30.0	60	0.7187	0.5143	0.7187	0.8478
No log	31.0	62	0.8102	0.5049	0.8102	0.9001
No log	32.0	64	0.6945	0.5260	0.6945	0.8333
No log	33.0	66	0.7226	0.5322	0.7226	0.8501
No log	34.0	68	0.9660	0.4552	0.9660	0.9829
No log	35.0	70	1.1218	0.4116	1.1218	1.0592
No log	36.0	72	0.8552	0.4910	0.8552	0.9248
No log	37.0	74	0.6975	0.5610	0.6975	0.8351
No log	38.0	76	0.7104	0.5432	0.7104	0.8429
No log	39.0	78	0.8246	0.5369	0.8246	0.9081
No log	40.0	80	0.8875	0.4839	0.8875	0.9421
No log	41.0	82	0.6990	0.5488	0.6990	0.8361
No log	42.0	84	0.6967	0.5373	0.6967	0.8347
No log	43.0	86	0.7060	0.5471	0.7060	0.8402
No log	44.0	88	0.8069	0.4962	0.8069	0.8983
No log	45.0	90	0.9477	0.4503	0.9477	0.9735
No log	46.0	92	0.9438	0.4936	0.9438	0.9715
No log	47.0	94	0.9031	0.5307	0.9031	0.9503
No log	48.0	96	0.7730	0.5682	0.7730	0.8792
No log	49.0	98	0.7753	0.5593	0.7753	0.8805
No log	50.0	100	0.8399	0.5138	0.8399	0.9165
No log	51.0	102	0.7723	0.5279	0.7723	0.8788
No log	52.0	104	0.7372	0.5583	0.7372	0.8586
No log	53.0	106	0.7263	0.5528	0.7263	0.8522
No log	54.0	108	0.8362	0.4684	0.8362	0.9144
No log	55.0	110	0.9074	0.4469	0.9074	0.9526
No log	56.0	112	0.7634	0.5089	0.7634	0.8737
No log	57.0	114	0.7570	0.5506	0.7570	0.8701
No log	58.0	116	0.7572	0.5381	0.7572	0.8702
No log	59.0	118	0.8221	0.5083	0.8221	0.9067
No log	60.0	120	0.8406	0.5039	0.8406	0.9168
No log	61.0	122	0.7768	0.5184	0.7768	0.8814
No log	62.0	124	0.7863	0.5193	0.7863	0.8867
No log	63.0	126	0.7715	0.5225	0.7715	0.8784

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_sp040_lw010_fold4

BERT_AugV8_k1_task1_organization_sp040_lw010_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_AugV8_k1_task1_organization_sp040_lw010_fold4