Version_weird_ASAP_FineTuningBERT_AugV12_k6_task1_organization_k6_k6_fold3

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: 0.7269
• Qwk: 0.6361
• Mse: 0.7265
• Rmse: 0.8523

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	10.2786	0.0065	10.2771	3.2058
No log	2.0	4	7.4524	0.0	7.4512	2.7297
No log	3.0	6	5.6659	0.0738	5.6648	2.3801
No log	4.0	8	4.8243	0.0185	4.8232	2.1962
No log	5.0	10	3.6312	0.0038	3.6302	1.9053
No log	6.0	12	2.8737	0.0	2.8728	1.6949
No log	7.0	14	2.2989	0.1670	2.2980	1.5159
No log	8.0	16	1.7499	0.0514	1.7491	1.3225
No log	9.0	18	1.3488	0.0302	1.3481	1.1611
No log	10.0	20	1.1426	0.0202	1.1420	1.0686
No log	11.0	22	0.9162	0.2186	0.9157	0.9569
No log	12.0	24	0.8461	0.2284	0.8456	0.9196
No log	13.0	26	0.8048	0.1251	0.8044	0.8969
No log	14.0	28	0.8191	0.0959	0.8188	0.9049
No log	15.0	30	0.8902	0.0959	0.8898	0.9433
No log	16.0	32	0.9261	0.1107	0.9258	0.9622
No log	17.0	34	1.0863	0.2956	1.0861	1.0422
No log	18.0	36	1.1436	0.2995	1.1435	1.0694
No log	19.0	38	1.0366	0.3630	1.0366	1.0181
No log	20.0	40	0.9710	0.4481	0.9710	0.9854
No log	21.0	42	0.7450	0.5284	0.7449	0.8631
No log	22.0	44	0.7377	0.5775	0.7377	0.8589
No log	23.0	46	0.8809	0.5799	0.8807	0.9385
No log	24.0	48	0.8469	0.5838	0.8467	0.9202
No log	25.0	50	0.9120	0.6035	0.9117	0.9548
No log	26.0	52	0.7645	0.6257	0.7643	0.8743
No log	27.0	54	0.8131	0.6202	0.8128	0.9016
No log	28.0	56	0.5947	0.6618	0.5945	0.7710
No log	29.0	58	0.6686	0.6478	0.6684	0.8176
No log	30.0	60	0.6757	0.6357	0.6756	0.8219
No log	31.0	62	0.7400	0.6353	0.7398	0.8601
No log	32.0	64	0.6424	0.6416	0.6422	0.8014
No log	33.0	66	0.6528	0.6486	0.6525	0.8078
No log	34.0	68	0.6985	0.6444	0.6981	0.8355
No log	35.0	70	0.7241	0.6142	0.7238	0.8508
No log	36.0	72	0.8833	0.6027	0.8829	0.9396
No log	37.0	74	0.8346	0.6098	0.8343	0.9134
No log	38.0	76	0.8322	0.5430	0.8320	0.9122
No log	39.0	78	0.7145	0.6388	0.7142	0.8451
No log	40.0	80	1.0969	0.5560	1.0963	1.0471
No log	41.0	82	0.8800	0.5932	0.8796	0.9378
No log	42.0	84	0.6000	0.6434	0.5997	0.7744
No log	43.0	86	0.6564	0.6111	0.6562	0.8101
No log	44.0	88	0.6927	0.6215	0.6924	0.8321
No log	45.0	90	0.7357	0.6278	0.7353	0.8575
No log	46.0	92	0.7175	0.6153	0.7172	0.8469
No log	47.0	94	0.6707	0.6154	0.6705	0.8188
No log	48.0	96	0.7269	0.6361	0.7265	0.8523

Framework versions

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