Version_weird_ASAP_FineTuningBERT_AugV12_k5_task1_organization_k5_k5_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: 0.6752
• Qwk: 0.6000
• Mse: 0.6752
• Rmse: 0.8217

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	9.0615	0.0	9.0615	3.0102
No log	2.0	4	7.6467	0.0	7.6467	2.7653
No log	3.0	6	6.9302	0.0	6.9302	2.6325
No log	4.0	8	6.0991	0.0135	6.0991	2.4696
No log	5.0	10	5.3158	0.0115	5.3158	2.3056
No log	6.0	12	4.5422	0.0039	4.5422	2.1312
No log	7.0	14	3.8261	0.0	3.8261	1.9560
No log	8.0	16	3.0635	0.0	3.0635	1.7503
No log	9.0	18	2.4307	0.0883	2.4307	1.5591
No log	10.0	20	1.8796	0.0484	1.8796	1.3710
No log	11.0	22	1.4767	0.0316	1.4767	1.2152
No log	12.0	24	1.1632	0.0316	1.1632	1.0785
No log	13.0	26	0.9444	0.0212	0.9444	0.9718
No log	14.0	28	0.8075	0.3541	0.8075	0.8986
No log	15.0	30	0.7375	0.2101	0.7375	0.8588
No log	16.0	32	0.6830	0.1927	0.6830	0.8264
No log	17.0	34	0.6923	0.1844	0.6923	0.8320
No log	18.0	36	0.7135	0.1904	0.7135	0.8447
No log	19.0	38	0.6358	0.2744	0.6358	0.7974
No log	20.0	40	0.6446	0.4066	0.6446	0.8028
No log	21.0	42	0.6765	0.4931	0.6765	0.8225
No log	22.0	44	0.5178	0.5778	0.5178	0.7196
No log	23.0	46	0.6448	0.5538	0.6448	0.8030
No log	24.0	48	0.4608	0.6478	0.4608	0.6788
No log	25.0	50	0.7700	0.5642	0.7700	0.8775
No log	26.0	52	0.5754	0.6658	0.5754	0.7585
No log	27.0	54	0.6436	0.6720	0.6436	0.8023
No log	28.0	56	1.1233	0.5339	1.1233	1.0599
No log	29.0	58	0.5608	0.6643	0.5608	0.7489
No log	30.0	60	0.5343	0.6672	0.5343	0.7310
No log	31.0	62	0.9756	0.5601	0.9756	0.9877
No log	32.0	64	0.5057	0.6710	0.5057	0.7111
No log	33.0	66	0.5248	0.6557	0.5248	0.7244
No log	34.0	68	0.9109	0.5749	0.9109	0.9544
No log	35.0	70	0.5171	0.6658	0.5171	0.7191
No log	36.0	72	0.4774	0.6385	0.4774	0.6909
No log	37.0	74	0.7698	0.5947	0.7698	0.8774
No log	38.0	76	0.7877	0.5861	0.7877	0.8875
No log	39.0	78	0.4753	0.6465	0.4753	0.6894
No log	40.0	80	0.5676	0.6389	0.5676	0.7534
No log	41.0	82	0.5678	0.6396	0.5678	0.7535
No log	42.0	84	0.5175	0.6471	0.5175	0.7194
No log	43.0	86	0.5954	0.6388	0.5954	0.7716
No log	44.0	88	0.4905	0.6223	0.4905	0.7003
No log	45.0	90	0.5035	0.6116	0.5035	0.7096
No log	46.0	92	0.5796	0.6304	0.5796	0.7613
No log	47.0	94	0.6752	0.6000	0.6752	0.8217

Framework versions

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