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	10.7434	0.0143	10.7415	3.2774
No log	2.0	4	8.4193	0.0	8.4176	2.9013
No log	3.0	6	6.0316	0.0502	6.0302	2.4556
No log	4.0	8	5.3598	0.0056	5.3586	2.3149
No log	5.0	10	4.1254	0.0	4.1242	2.0308
No log	6.0	12	3.7768	0.0	3.7756	1.9431
No log	7.0	14	3.1211	0.0	3.1201	1.7664
No log	8.0	16	2.5183	0.1217	2.5175	1.5867
No log	9.0	18	1.9116	0.0202	1.9108	1.3823
No log	10.0	20	1.4791	0.0102	1.4785	1.2160
No log	11.0	22	1.3544	0.0497	1.3539	1.1636
No log	12.0	24	2.1013	0.1057	2.1010	1.4495
No log	13.0	26	1.3009	0.1143	1.3007	1.1405
No log	14.0	28	1.0120	0.0932	1.0118	1.0059
No log	15.0	30	1.6581	0.1709	1.6585	1.2878
No log	16.0	32	1.1347	0.2056	1.1351	1.0654
No log	17.0	34	0.8694	0.2817	0.8692	0.9323
No log	18.0	36	0.8866	0.3599	0.8872	0.9419
No log	19.0	38	0.9760	0.3129	0.9768	0.9883
No log	20.0	40	0.7469	0.4037	0.7473	0.8644
No log	21.0	42	0.8410	0.3785	0.8421	0.9177
No log	22.0	44	0.9566	0.3695	0.9578	0.9787
No log	23.0	46	0.6920	0.4401	0.6931	0.8325
No log	24.0	48	0.9642	0.3687	0.9658	0.9828
No log	25.0	50	0.8554	0.3981	0.8570	0.9257
No log	26.0	52	0.6773	0.4319	0.6784	0.8236
No log	27.0	54	0.6933	0.4614	0.6947	0.8335
No log	28.0	56	0.7441	0.4727	0.7455	0.8634
No log	29.0	58	0.6390	0.5107	0.6401	0.8001
No log	30.0	60	0.9933	0.4351	0.9943	0.9972
No log	31.0	62	0.9507	0.4517	0.9518	0.9756
No log	32.0	64	0.6983	0.5359	0.6995	0.8364
No log	33.0	66	1.1061	0.4242	1.1074	1.0523
No log	34.0	68	1.0793	0.4211	1.0809	1.0396
No log	35.0	70	0.7942	0.4827	0.7957	0.8920
No log	36.0	72	0.9832	0.4277	0.9848	0.9924
No log	37.0	74	0.8259	0.4645	0.8273	0.9096
No log	38.0	76	0.8298	0.4484	0.8309	0.9115
No log	39.0	78	0.8557	0.4797	0.8569	0.9257
No log	40.0	80	0.8625	0.4768	0.8636	0.9293
No log	41.0	82	0.7692	0.5005	0.7702	0.8776
No log	42.0	84	0.8929	0.4655	0.8939	0.9455
No log	43.0	86	0.8415	0.4785	0.8426	0.9179
No log	44.0	88	0.7963	0.4784	0.7973	0.8929
No log	45.0	90	0.7977	0.4898	0.7988	0.8937
No log	46.0	92	0.7956	0.4895	0.7968	0.8926
No log	47.0	94	0.8648	0.4832	0.8660	0.9306
No log	48.0	96	0.8451	0.4844	0.8461	0.9199
No log	49.0	98	0.8327	0.4909	0.8337	0.9130
No log	50.0	100	0.8817	0.4674	0.8827	0.9395
No log	51.0	102	0.8399	0.5047	0.8408	0.9169
No log	52.0	104	0.8617	0.4902	0.8627	0.9288
No log	53.0	106	0.8877	0.4730	0.8888	0.9428
No log	54.0	108	0.9688	0.4480	0.9699	0.9848
No log	55.0	110	0.8587	0.5061	0.8597	0.9272
No log	56.0	112	0.8678	0.5024	0.8688	0.9321
No log	57.0	114	0.8877	0.5150	0.8888	0.9428
No log	58.0	116	0.8854	0.5055	0.8865	0.9415
No log	59.0	118	0.8663	0.4937	0.8674	0.9314
No log	60.0	120	0.9194	0.4814	0.9205	0.9594
No log	61.0	122	0.9189	0.4963	0.9198	0.9591
No log	62.0	124	0.8488	0.5050	0.8498	0.9218

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/Version24NewTestASAP_FineTuningBERT_AugV24_k3_task1_organization_k3_k3_fold3

Version24NewTestASAP_FineTuningBERT_AugV24_k3_task1_organization_k3_k3_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
Version24NewTestASAP_FineTuningBERT_AugV24_k3_task1_organization_k3_k3_fold3