ASAP_FineTuningBERT_AugV8_k4_task1_organization_fold0

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: 0.7178
• Qwk: 0.5077
• Mse: 0.7178
• Rmse: 0.8473

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	0.5	2	9.1129	0.0	9.1129	3.0188
No log	1.0	4	8.3059	0.0	8.3059	2.8820
No log	1.5	6	6.9032	0.0	6.9032	2.6274
No log	2.0	8	6.3813	-0.0079	6.3813	2.5261
5.5412	2.5	10	5.4734	0.0105	5.4734	2.3395
5.5412	3.0	12	4.6234	0.0077	4.6234	2.1502
5.5412	3.5	14	3.8774	0.0	3.8774	1.9691
5.5412	4.0	16	3.1538	0.0	3.1538	1.7759
5.5412	4.5	18	2.4766	0.1029	2.4766	1.5737
2.93	5.0	20	1.9257	0.0601	1.9257	1.3877
2.93	5.5	22	1.4639	0.0316	1.4639	1.2099
2.93	6.0	24	1.2256	0.0316	1.2256	1.1071
2.93	6.5	26	1.1470	0.0316	1.1470	1.0710
2.93	7.0	28	1.1984	0.0316	1.1984	1.0947
1.9098	7.5	30	1.6059	0.1263	1.6059	1.2672
1.9098	8.0	32	1.4074	0.1242	1.4074	1.1863
1.9098	8.5	34	1.0092	0.0575	1.0092	1.0046
1.9098	9.0	36	0.9623	0.0800	0.9623	0.9810
1.9098	9.5	38	1.0181	0.1161	1.0181	1.0090
1.6392	10.0	40	0.9731	0.2475	0.9731	0.9864
1.6392	10.5	42	0.8004	0.3896	0.8004	0.8946
1.6392	11.0	44	1.0286	0.3129	1.0286	1.0142
1.6392	11.5	46	0.7252	0.4633	0.7252	0.8516
1.6392	12.0	48	0.6164	0.4859	0.6164	0.7851
1.2892	12.5	50	0.7599	0.4533	0.7599	0.8717
1.2892	13.0	52	0.6152	0.4644	0.6152	0.7844
1.2892	13.5	54	0.6187	0.4652	0.6187	0.7866
1.2892	14.0	56	0.6183	0.4717	0.6183	0.7863
1.2892	14.5	58	0.5978	0.4848	0.5978	0.7732
0.9174	15.0	60	0.5820	0.4738	0.5820	0.7629
0.9174	15.5	62	0.6822	0.3910	0.6822	0.8260
0.9174	16.0	64	0.6618	0.5009	0.6618	0.8135
0.9174	16.5	66	0.6419	0.5039	0.6419	0.8012
0.9174	17.0	68	0.6573	0.4130	0.6573	0.8107
0.5727	17.5	70	0.6484	0.5274	0.6484	0.8052
0.5727	18.0	72	0.7442	0.5207	0.7442	0.8627
0.5727	18.5	74	0.6143	0.5192	0.6143	0.7838
0.5727	19.0	76	0.7735	0.4773	0.7735	0.8795
0.5727	19.5	78	0.6449	0.5210	0.6449	0.8030
0.4153	20.0	80	0.6810	0.5241	0.6810	0.8252
0.4153	20.5	82	0.9373	0.4403	0.9373	0.9681
0.4153	21.0	84	0.6982	0.4916	0.6982	0.8356
0.4153	21.5	86	0.7102	0.4775	0.7102	0.8428
0.4153	22.0	88	0.8496	0.4702	0.8496	0.9217
0.3274	22.5	90	0.7178	0.5077	0.7178	0.8473

Framework versions

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