ASAP_FineTuningBERT_AugV5_k10_task1_organization_fold4

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: 0.5758
• Qwk: 0.6718
• Mse: 0.5758
• Rmse: 0.7588

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	9.7683	0.0018	9.7683	3.1254
No log	4.0	4	8.2498	0.0018	8.2498	2.8722
No log	6.0	6	6.8328	0.0	6.8328	2.6140
No log	8.0	8	5.3375	0.0329	5.3375	2.3103
8.9731	10.0	10	4.3556	0.0118	4.3556	2.0870
8.9731	12.0	12	3.5608	0.0040	3.5608	1.8870
8.9731	14.0	14	2.8777	0.0040	2.8777	1.6964
8.9731	16.0	16	2.3505	0.1010	2.3505	1.5331
8.9731	18.0	18	1.9685	0.1264	1.9685	1.4030
4.3314	20.0	20	1.6149	0.0734	1.6149	1.2708
4.3314	22.0	22	1.4079	0.1092	1.4079	1.1865
4.3314	24.0	24	1.1654	0.0975	1.1654	1.0796
4.3314	26.0	26	0.9621	0.0975	0.9621	0.9809
4.3314	28.0	28	1.0460	0.1775	1.0460	1.0228
2.3195	30.0	30	0.7254	0.4930	0.7254	0.8517
2.3195	32.0	32	0.6288	0.5308	0.6288	0.7930
2.3195	34.0	34	0.7271	0.5327	0.7271	0.8527
2.3195	36.0	36	0.5334	0.5459	0.5334	0.7303
2.3195	38.0	38	0.5264	0.5264	0.5264	0.7256
1.2151	40.0	40	0.5444	0.6055	0.5444	0.7378
1.2151	42.0	42	0.4974	0.5838	0.4974	0.7053
1.2151	44.0	44	0.4992	0.5834	0.4992	0.7065
1.2151	46.0	46	0.4907	0.6217	0.4907	0.7005
1.2151	48.0	48	0.4903	0.6602	0.4903	0.7002
0.6065	50.0	50	0.4976	0.6520	0.4976	0.7054
0.6065	52.0	52	0.4928	0.6757	0.4928	0.7020
0.6065	54.0	54	0.5738	0.6383	0.5738	0.7575
0.6065	56.0	56	0.5469	0.6828	0.5469	0.7395
0.6065	58.0	58	0.5523	0.6760	0.5523	0.7432
0.3084	60.0	60	0.5803	0.6420	0.5803	0.7618
0.3084	62.0	62	0.6608	0.6124	0.6608	0.8129
0.3084	64.0	64	0.5481	0.6893	0.5481	0.7404
0.3084	66.0	66	0.5452	0.6779	0.5452	0.7384
0.3084	68.0	68	0.6938	0.6277	0.6938	0.8329
0.1723	70.0	70	0.7560	0.6070	0.7560	0.8695
0.1723	72.0	72	0.5880	0.6867	0.5880	0.7668
0.1723	74.0	74	0.5626	0.6901	0.5626	0.7501
0.1723	76.0	76	0.6318	0.6317	0.6318	0.7948
0.1723	78.0	78	0.6981	0.6187	0.6981	0.8355
0.1229	80.0	80	0.6227	0.6372	0.6227	0.7891
0.1229	82.0	82	0.6047	0.6486	0.6047	0.7776
0.1229	84.0	84	0.6171	0.6511	0.6171	0.7855
0.1229	86.0	86	0.6257	0.6465	0.6257	0.7910
0.1229	88.0	88	0.6828	0.6261	0.6828	0.8263
0.0736	90.0	90	0.6638	0.6255	0.6638	0.8147
0.0736	92.0	92	0.5854	0.6629	0.5854	0.7651
0.0736	94.0	94	0.5649	0.6745	0.5649	0.7516
0.0736	96.0	96	0.5690	0.6734	0.5690	0.7543
0.0736	98.0	98	0.5707	0.6734	0.5707	0.7554
0.0687	100.0	100	0.5758	0.6718	0.5758	0.7588

Framework versions

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