Version3ASAP_FineTuningBERT_AugV14_k5_task1_organization_k5_k5_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: 0.8578
• Qwk: 0.2850
• Mse: 0.8567
• Rmse: 0.9256

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	4	7.7444	0.0	7.7420	2.7824
No log	2.0	8	4.8316	0.0167	4.8296	2.1976
No log	3.0	12	3.1449	0.0	3.1431	1.7729
No log	4.0	16	2.0387	0.0825	2.0371	1.4273
No log	5.0	20	1.3921	0.0106	1.3906	1.1793
No log	6.0	24	1.1157	0.0106	1.1144	1.0556
No log	7.0	28	1.1337	0.0315	1.1323	1.0641
No log	8.0	32	1.3762	0.0592	1.3746	1.1724
No log	9.0	36	0.8612	0.2466	0.8599	0.9273
No log	10.0	40	0.7256	0.3996	0.7245	0.8512
No log	11.0	44	0.8530	0.2880	0.8516	0.9228
No log	12.0	48	0.7792	0.3233	0.7779	0.8820
No log	13.0	52	0.6417	0.3713	0.6409	0.8005
No log	14.0	56	0.6927	0.4544	0.6917	0.8317
No log	15.0	60	0.8974	0.3638	0.8962	0.9467
No log	16.0	64	0.9857	0.3290	0.9844	0.9922
No log	17.0	68	0.9016	0.3893	0.9005	0.9489
No log	18.0	72	0.7359	0.4334	0.7352	0.8574
No log	19.0	76	1.2859	0.2209	1.2842	1.1332
No log	20.0	80	0.7369	0.4396	0.7363	0.8581
No log	21.0	84	0.8340	0.3666	0.8329	0.9127
No log	22.0	88	0.6981	0.4623	0.6973	0.8351
No log	23.0	92	0.9209	0.3771	0.9197	0.9590
No log	24.0	96	0.7949	0.4007	0.7939	0.8910
No log	25.0	100	0.8195	0.3725	0.8186	0.9048
No log	26.0	104	0.7416	0.4153	0.7410	0.8608
No log	27.0	108	1.0782	0.2975	1.0772	1.0379
No log	28.0	112	0.7246	0.4269	0.7241	0.8510
No log	29.0	116	0.9036	0.3514	0.9026	0.9501
No log	30.0	120	0.9571	0.3224	0.9561	0.9778
No log	31.0	124	0.7552	0.4078	0.7546	0.8687
No log	32.0	128	0.7253	0.3861	0.7245	0.8512
No log	33.0	132	0.8447	0.3555	0.8437	0.9186
No log	34.0	136	0.7276	0.4230	0.7271	0.8527
No log	35.0	140	1.0157	0.3094	1.0145	1.0072
No log	36.0	144	0.6681	0.4144	0.6674	0.8170
No log	37.0	148	0.8372	0.3326	0.8361	0.9144
No log	38.0	152	0.8662	0.2979	0.8652	0.9302
No log	39.0	156	0.7728	0.3013	0.7719	0.8786
No log	40.0	160	0.7917	0.3697	0.7907	0.8892
No log	41.0	164	0.7827	0.3829	0.7817	0.8841
No log	42.0	168	0.8578	0.2850	0.8567	0.9256

Framework versions

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