ASAP_FineTuningBERT_AugV5_k1_task1_organization_fold3

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: 2.6105
• Qwk: -0.0544
• Mse: 2.6109
• Rmse: 1.6158

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	10.0422	0.0	10.0414	3.1688
No log	4.0	4	8.3600	0.0	8.3593	2.8912
No log	6.0	6	6.7075	0.0	6.7070	2.5898
No log	8.0	8	5.6349	0.0246	5.6346	2.3737
5.0421	10.0	10	4.4175	0.0076	4.4173	2.1017
5.0421	12.0	12	3.9267	0.0	3.9267	1.9816
5.0421	14.0	14	3.0630	0.0	3.0632	1.7502
5.0421	16.0	16	2.5124	0.0813	2.5127	1.5852
5.0421	18.0	18	2.4738	0.0437	2.4742	1.5730
2.1507	20.0	20	1.7999	0.0345	1.8004	1.3418
2.1507	22.0	22	1.6600	0.0247	1.6606	1.2886
2.1507	24.0	24	2.0979	0.0403	2.0984	1.4486
2.1507	26.0	26	2.0805	0.0551	2.0810	1.4426
2.1507	28.0	28	1.7880	0.0361	1.7886	1.3374
1.672	30.0	30	2.0786	0.0283	2.0792	1.4420
1.672	32.0	32	2.3627	0.0348	2.3633	1.5373
1.672	34.0	34	2.1553	0.0171	2.1559	1.4683
1.672	36.0	36	2.5371	-0.0123	2.5376	1.5930
1.672	38.0	38	2.3045	0.0056	2.3049	1.5182
1.0568	40.0	40	2.0772	-0.0012	2.0775	1.4414
1.0568	42.0	42	2.7665	-0.0184	2.7666	1.6633
1.0568	44.0	44	2.0043	0.0129	2.0046	1.4158
1.0568	46.0	46	2.4202	-0.0133	2.4204	1.5558
1.0568	48.0	48	2.5292	-0.0404	2.5294	1.5904
0.455	50.0	50	2.3014	-0.0120	2.3017	1.5171
0.455	52.0	52	2.6276	-0.0418	2.6279	1.6211
0.455	54.0	54	2.5162	-0.0431	2.5165	1.5863
0.455	56.0	56	2.0312	-0.0028	2.0317	1.4254
0.455	58.0	58	3.0641	-0.0535	3.0643	1.7505
0.2076	60.0	60	3.0322	-0.0478	3.0324	1.7414
0.2076	62.0	62	1.8241	-0.0099	1.8246	1.3508
0.2076	64.0	64	1.6130	-0.0133	1.6136	1.2703
0.2076	66.0	66	2.4066	-0.0474	2.4069	1.5514
0.2076	68.0	68	3.6666	-0.0638	3.6666	1.9148
0.2273	70.0	70	3.5766	-0.0572	3.5766	1.8912
0.2273	72.0	72	2.6045	-0.0505	2.6048	1.6139
0.2273	74.0	74	2.2854	-0.0501	2.2859	1.5119
0.2273	76.0	76	2.6014	-0.0456	2.6017	1.6130
0.2273	78.0	78	2.5650	-0.0442	2.5654	1.6017
0.1557	80.0	80	2.3119	-0.0516	2.3123	1.5206
0.1557	82.0	82	2.4799	-0.0490	2.4803	1.5749
0.1557	84.0	84	2.6063	-0.0526	2.6067	1.6145
0.1557	86.0	86	2.7569	-0.0576	2.7572	1.6605
0.1557	88.0	88	2.7278	-0.0544	2.7282	1.6517
0.109	90.0	90	2.6859	-0.0511	2.6863	1.6390
0.109	92.0	92	2.5581	-0.0516	2.5585	1.5995
0.109	94.0	94	2.6192	-0.0530	2.6196	1.6185
0.109	96.0	96	2.6701	-0.0561	2.6705	1.6342
0.109	98.0	98	2.6373	-0.0530	2.6377	1.6241
0.1008	100.0	100	2.6105	-0.0544	2.6109	1.6158

Framework versions

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