ASAP_FineTuningBERT_AugV8_k2_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: 0.8528
• Qwk: 0.4165
• Mse: 0.8528
• Rmse: 0.9234

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	11.6539	-0.0008	11.6513	3.4134
No log	2.0	4	9.3849	0.0018	9.3825	3.0631
No log	3.0	6	7.6266	0.0	7.6246	2.7613
No log	4.0	8	5.4934	0.0508	5.4920	2.3435
6.7916	5.0	10	4.3931	0.0123	4.3923	2.0958
6.7916	6.0	12	3.0448	0.0	3.0441	1.7447
6.7916	7.0	14	2.2296	0.0832	2.2293	1.4931
6.7916	8.0	16	1.9855	0.0328	1.9856	1.4091
6.7916	9.0	18	1.4409	0.0	1.4410	1.2004
2.5086	10.0	20	1.2988	0.0	1.2989	1.1397
2.5086	11.0	22	1.1447	0.0	1.1449	1.0700
2.5086	12.0	24	1.1339	0.0379	1.1340	1.0649
2.5086	13.0	26	2.0113	0.1854	2.0111	1.4181
2.5086	14.0	28	1.2906	0.0931	1.2906	1.1360
2.0289	15.0	30	0.8404	0.2454	0.8406	0.9168
2.0289	16.0	32	0.9015	0.0494	0.9016	0.9495
2.0289	17.0	34	1.3092	0.1163	1.3091	1.1441
2.0289	18.0	36	0.9852	0.1198	0.9851	0.9925
2.0289	19.0	38	0.7343	0.4036	0.7344	0.8570
1.5671	20.0	40	0.7353	0.3673	0.7353	0.8575
1.5671	21.0	42	1.0843	0.2391	1.0842	1.0413
1.5671	22.0	44	0.7988	0.3208	0.7988	0.8938
1.5671	23.0	46	0.7232	0.3634	0.7232	0.8504
1.5671	24.0	48	0.7083	0.4090	0.7082	0.8416
1.0508	25.0	50	0.7972	0.3992	0.7969	0.8927
1.0508	26.0	52	0.7033	0.4227	0.7031	0.8385
1.0508	27.0	54	0.7067	0.4363	0.7064	0.8405
1.0508	28.0	56	0.8035	0.4361	0.8030	0.8961
1.0508	29.0	58	0.7016	0.4756	0.7012	0.8374
0.5969	30.0	60	0.7273	0.4591	0.7270	0.8526
0.5969	31.0	62	0.8334	0.3869	0.8331	0.9128
0.5969	32.0	64	0.9936	0.3241	0.9934	0.9967
0.5969	33.0	66	0.9237	0.3678	0.9236	0.9610
0.5969	34.0	68	0.8983	0.3912	0.8982	0.9477
0.3652	35.0	70	0.9925	0.3293	0.9923	0.9961
0.3652	36.0	72	0.8462	0.4211	0.8461	0.9199
0.3652	37.0	74	0.8282	0.4324	0.8281	0.9100
0.3652	38.0	76	0.8497	0.4394	0.8496	0.9217
0.3652	39.0	78	0.8528	0.4165	0.8528	0.9234

Framework versions

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