Version_Test_ASAP_FineTuningBERT_AugV14_k1_task1_organization_k1_k1_fold2

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: 0.7180
• Qwk: 0.5511
• Mse: 0.7172
• Rmse: 0.8469

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: 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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	2	11.5162	0.0089	11.5163	3.3936
No log	2.0	4	9.9129	0.0018	9.9131	3.1485
No log	3.0	6	7.8183	0.0	7.8186	2.7962
No log	4.0	8	6.6278	0.0	6.6282	2.5745
No log	5.0	10	5.3386	0.0091	5.3390	2.3106
No log	6.0	12	3.8930	0.0039	3.8935	1.9732
No log	7.0	14	3.6741	0.0078	3.6745	1.9169
No log	8.0	16	2.9349	0.0	2.9354	1.7133
No log	9.0	18	1.8461	0.0372	1.8465	1.3589
No log	10.0	20	1.5699	0.0213	1.5704	1.2532
No log	11.0	22	1.2508	0.0107	1.2513	1.1186
No log	12.0	24	0.9687	0.0107	0.9691	0.9844
No log	13.0	26	0.8360	0.2321	0.8364	0.9145
No log	14.0	28	0.7517	0.2347	0.7521	0.8672
No log	15.0	30	0.7229	0.2171	0.7232	0.8504
No log	16.0	32	0.7336	0.1388	0.7338	0.8566
No log	17.0	34	0.7627	0.1694	0.7626	0.8733
No log	18.0	36	0.6761	0.4378	0.6762	0.8223
No log	19.0	38	0.6851	0.4475	0.6853	0.8278
No log	20.0	40	0.6773	0.4808	0.6768	0.8227
No log	21.0	42	0.7823	0.4316	0.7817	0.8841
No log	22.0	44	0.5129	0.5312	0.5126	0.7160
No log	23.0	46	0.6371	0.5105	0.6370	0.7981
No log	24.0	48	0.5679	0.5254	0.5677	0.7535
No log	25.0	50	0.7360	0.5377	0.7353	0.8575
No log	26.0	52	0.9406	0.4171	0.9398	0.9694
No log	27.0	54	0.6632	0.5398	0.6626	0.8140
No log	28.0	56	0.5634	0.6036	0.5628	0.7502
No log	29.0	58	0.6051	0.5857	0.6043	0.7774
No log	30.0	60	0.5283	0.5668	0.5279	0.7265
No log	31.0	62	0.5373	0.5272	0.5369	0.7328
No log	32.0	64	0.5237	0.5451	0.5232	0.7234
No log	33.0	66	0.5845	0.5588	0.5839	0.7642
No log	34.0	68	0.5484	0.5859	0.5479	0.7402
No log	35.0	70	0.5821	0.5763	0.5816	0.7626
No log	36.0	72	0.5900	0.5611	0.5895	0.7678
No log	37.0	74	0.5665	0.5193	0.5662	0.7525
No log	38.0	76	0.5911	0.5112	0.5909	0.7687
No log	39.0	78	0.6200	0.5396	0.6197	0.7872
No log	40.0	80	0.6575	0.5662	0.6571	0.8106
No log	41.0	82	0.6431	0.5759	0.6425	0.8016
No log	42.0	84	0.6120	0.5856	0.6115	0.7820
No log	43.0	86	0.8164	0.4833	0.8158	0.9032
No log	44.0	88	0.8132	0.4378	0.8128	0.9015
No log	45.0	90	0.5934	0.4997	0.5933	0.7703
No log	46.0	92	0.5401	0.5037	0.5399	0.7348
No log	47.0	94	0.5760	0.5613	0.5757	0.7587
No log	48.0	96	0.7180	0.5511	0.7172	0.8469

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0