Version_weird_ASAP_FineTuningBERT_AugV12_k6_task1_organization_k6_k6_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: 1.0784
• Qwk: 0.5608
• Mse: 1.0782
• Rmse: 1.0383

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	10.8694	0.0096	10.8669	3.2965
No log	2.0	4	9.7175	0.0	9.7152	3.1169
No log	3.0	6	8.3088	0.0	8.3064	2.8821
No log	4.0	8	6.8210	0.0	6.8186	2.6112
No log	5.0	10	4.9698	0.0229	4.9675	2.2288
No log	6.0	12	3.4020	0.0040	3.4000	1.8439
No log	7.0	14	2.5117	0.0403	2.5101	1.5843
No log	8.0	16	1.8690	0.1156	1.8673	1.3665
No log	9.0	18	1.3743	0.0315	1.3728	1.1717
No log	10.0	20	1.0810	0.0	1.0796	1.0391
No log	11.0	22	0.9004	0.2963	0.8992	0.9483
No log	12.0	24	0.9006	0.1427	0.8995	0.9484
No log	13.0	26	0.8883	0.0837	0.8873	0.9420
No log	14.0	28	0.8812	0.0749	0.8803	0.9382
No log	15.0	30	0.9998	0.0749	0.9991	0.9995
No log	16.0	32	0.9352	0.1278	0.9345	0.9667
No log	17.0	34	0.8939	0.3805	0.8932	0.9451
No log	18.0	36	0.8054	0.4902	0.8048	0.8971
No log	19.0	38	0.6013	0.5621	0.6006	0.7750
No log	20.0	40	0.5894	0.6118	0.5888	0.7674
No log	21.0	42	0.5613	0.6613	0.5608	0.7489
No log	22.0	44	0.7696	0.5847	0.7693	0.8771
No log	23.0	46	0.7002	0.6288	0.6999	0.8366
No log	24.0	48	0.8389	0.6261	0.8388	0.9159
No log	25.0	50	0.7440	0.6474	0.7441	0.8626
No log	26.0	52	1.4712	0.4941	1.4712	1.2129
No log	27.0	54	0.7426	0.6485	0.7425	0.8617
No log	28.0	56	0.8887	0.5991	0.8886	0.9426
No log	29.0	58	1.0579	0.5651	1.0577	1.0285
No log	30.0	60	0.8559	0.6267	0.8557	0.9251
No log	31.0	62	0.6509	0.6707	0.6505	0.8066
No log	32.0	64	1.2116	0.5249	1.2115	1.1007
No log	33.0	66	1.1074	0.5596	1.1072	1.0522
No log	34.0	68	0.6941	0.6444	0.6938	0.8329
No log	35.0	70	0.9711	0.5846	0.9709	0.9853
No log	36.0	72	0.9329	0.6052	0.9328	0.9658
No log	37.0	74	0.8585	0.6148	0.8584	0.9265
No log	38.0	76	1.1577	0.5540	1.1576	1.0759
No log	39.0	78	0.8270	0.6181	0.8268	0.9093
No log	40.0	80	1.0261	0.5649	1.0258	1.0128
No log	41.0	82	0.9168	0.6119	0.9165	0.9574
No log	42.0	84	0.8711	0.6167	0.8709	0.9332
No log	43.0	86	0.7902	0.6257	0.7898	0.8887
No log	44.0	88	1.0792	0.5453	1.0789	1.0387
No log	45.0	90	1.3722	0.5047	1.3719	1.1713
No log	46.0	92	0.8290	0.6247	0.8288	0.9104
No log	47.0	94	0.8507	0.6158	0.8504	0.9222
No log	48.0	96	1.0920	0.5546	1.0918	1.0449
No log	49.0	98	0.7932	0.6229	0.7929	0.8904
No log	50.0	100	0.7191	0.6534	0.7189	0.8479
No log	51.0	102	1.0784	0.5608	1.0782	1.0383

Framework versions

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