ASAP_FineTuningBERT_AugV5_k1_task1_organization_fold1

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.6869
• Qwk: -0.0861
• Mse: 2.6868
• Rmse: 1.6392

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	2.0	2	9.5798	0.0	9.5776	3.0948
No log	4.0	4	7.9439	0.0	7.9420	2.8182
No log	6.0	6	6.4641	0.0	6.4625	2.5422
No log	8.0	8	5.2599	0.0559	5.2587	2.2932
4.9982	10.0	10	4.1481	0.0079	4.1471	2.0364
4.9982	12.0	12	3.5500	0.0040	3.5492	1.8839
4.9982	14.0	14	2.8411	0.0	2.8405	1.6854
4.9982	16.0	16	2.3024	0.0767	2.3021	1.5173
4.9982	18.0	18	2.3574	0.0732	2.3571	1.5353
2.1743	20.0	20	1.7681	0.0737	1.7680	1.3297
2.1743	22.0	22	1.9535	0.0785	1.9534	1.3976
2.1743	24.0	24	2.1043	0.0832	2.1042	1.4506
2.1743	26.0	26	1.6590	0.0559	1.6591	1.2881
2.1743	28.0	28	1.9849	-0.0140	1.9849	1.4089
1.5392	30.0	30	1.6709	0.0481	1.6711	1.2927
1.5392	32.0	32	1.7945	-0.0321	1.7946	1.3396
1.5392	34.0	34	1.8907	-0.0686	1.8907	1.3750
1.5392	36.0	36	1.6602	-0.1049	1.6604	1.2886
1.5392	38.0	38	2.2785	-0.0910	2.2784	1.5094
0.755	40.0	40	2.2639	-0.1086	2.2638	1.5046
0.755	42.0	42	2.4028	-0.1004	2.4026	1.5500
0.755	44.0	44	2.5434	-0.0962	2.5431	1.5947
0.755	46.0	46	2.6992	-0.0921	2.6989	1.6428
0.755	48.0	48	2.4887	-0.1009	2.4886	1.5775
0.2912	50.0	50	2.7323	-0.0885	2.7321	1.6529
0.2912	52.0	52	2.3700	-0.1372	2.3701	1.5395
0.2912	54.0	54	2.8160	-0.0862	2.8158	1.6780
0.2912	56.0	56	2.8669	-0.0842	2.8668	1.6932
0.2912	58.0	58	3.1945	-0.1022	3.1942	1.7872
0.1731	60.0	60	2.4518	-0.1396	2.4519	1.5659
0.1731	62.0	62	2.3844	-0.1415	2.3846	1.5442
0.1731	64.0	64	3.1398	-0.0998	3.1395	1.7719
0.1731	66.0	66	3.2908	-0.0909	3.2904	1.8140
0.1731	68.0	68	2.6689	-0.0892	2.6689	1.6337
0.1508	70.0	70	2.1683	-0.1689	2.1687	1.4726
0.1508	72.0	72	2.3213	-0.1308	2.3215	1.5236
0.1508	74.0	74	2.9226	-0.0855	2.9224	1.7095
0.1508	76.0	76	3.0932	-0.0985	3.0929	1.7587
0.1508	78.0	78	2.7406	-0.0817	2.7405	1.6554
0.1508	80.0	80	2.2736	-0.1348	2.2738	1.5079
0.1508	82.0	82	2.2387	-0.1408	2.2390	1.4963
0.1508	84.0	84	2.5085	-0.0976	2.5086	1.5838
0.1508	86.0	86	2.8004	-0.0813	2.8003	1.6734
0.1508	88.0	88	2.7728	-0.0805	2.7727	1.6652
0.1168	90.0	90	2.6308	-0.0823	2.6308	1.6220
0.1168	92.0	92	2.5054	-0.1084	2.5055	1.5829
0.1168	94.0	94	2.5466	-0.0988	2.5467	1.5958
0.1168	96.0	96	2.6464	-0.0844	2.6464	1.6268
0.1168	98.0	98	2.6876	-0.0888	2.6875	1.6394
0.0866	100.0	100	2.6869	-0.0861	2.6868	1.6392

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1