Version_weird_ASAP_FineTuningBERT_AugV12_k6_task1_organization_k6_k6_fold4

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: 0.9653
• Qwk: 0.5828
• Mse: 0.9653
• Rmse: 0.9825

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	7.9975	0.0037	7.9975	2.8280
No log	2.0	4	5.4541	0.0449	5.4541	2.3354
No log	3.0	6	4.1685	0.0118	4.1685	2.0417
No log	4.0	8	3.2598	0.0118	3.2598	1.8055
No log	5.0	10	2.5700	0.0079	2.5700	1.6031
No log	6.0	12	2.0650	0.1041	2.0650	1.4370
No log	7.0	14	1.6176	0.0420	1.6176	1.2718
No log	8.0	16	1.3930	0.0316	1.3930	1.1803
No log	9.0	18	1.0774	0.0316	1.0774	1.0380
No log	10.0	20	0.9347	0.0316	0.9347	0.9668
No log	11.0	22	0.8550	0.1986	0.8550	0.9247
No log	12.0	24	0.7994	0.1587	0.7994	0.8941
No log	13.0	26	0.7714	0.1587	0.7714	0.8783
No log	14.0	28	0.7468	0.1751	0.7468	0.8642
No log	15.0	30	0.7266	0.2915	0.7266	0.8524
No log	16.0	32	0.6020	0.4483	0.6020	0.7759
No log	17.0	34	0.6210	0.5960	0.6210	0.7880
No log	18.0	36	0.7556	0.5338	0.7556	0.8692
No log	19.0	38	0.7287	0.5878	0.7287	0.8536
No log	20.0	40	0.9568	0.5492	0.9568	0.9782
No log	21.0	42	0.7246	0.6328	0.7246	0.8512
No log	22.0	44	0.8599	0.6331	0.8599	0.9273
No log	23.0	46	1.2360	0.5105	1.2360	1.1118
No log	24.0	48	0.8426	0.6299	0.8426	0.9180
No log	25.0	50	1.1873	0.5150	1.1873	1.0896
No log	26.0	52	0.7628	0.6277	0.7628	0.8734
No log	27.0	54	1.4321	0.4838	1.4321	1.1967
No log	28.0	56	1.1818	0.5136	1.1818	1.0871
No log	29.0	58	1.4707	0.4876	1.4707	1.2127
No log	30.0	60	0.8946	0.6126	0.8946	0.9459
No log	31.0	62	1.0482	0.5763	1.0482	1.0238
No log	32.0	64	1.7707	0.4705	1.7707	1.3307
No log	33.0	66	1.0094	0.5866	1.0094	1.0047
No log	34.0	68	1.0126	0.5811	1.0126	1.0063
No log	35.0	70	1.6173	0.4777	1.6173	1.2717
No log	36.0	72	0.9262	0.5865	0.9262	0.9624
No log	37.0	74	0.9788	0.5717	0.9788	0.9893
No log	38.0	76	1.4004	0.4823	1.4004	1.1834
No log	39.0	78	0.8096	0.6380	0.8096	0.8998
No log	40.0	80	0.5438	0.6646	0.5438	0.7374
No log	41.0	82	0.6508	0.6517	0.6508	0.8067
No log	42.0	84	1.1766	0.5006	1.1766	1.0847
No log	43.0	86	0.9797	0.5517	0.9797	0.9898
No log	44.0	88	0.6845	0.6571	0.6845	0.8273
No log	45.0	90	0.9307	0.5792	0.9307	0.9647
No log	46.0	92	1.4962	0.4712	1.4962	1.2232
No log	47.0	94	1.2444	0.5002	1.2444	1.1155
No log	48.0	96	0.8194	0.6206	0.8194	0.9052
No log	49.0	98	0.9670	0.5864	0.9670	0.9834
No log	50.0	100	1.3856	0.4793	1.3856	1.1771
No log	51.0	102	1.1314	0.5248	1.1314	1.0637
No log	52.0	104	0.9158	0.5868	0.9158	0.9570
No log	53.0	106	1.1422	0.5413	1.1422	1.0687
No log	54.0	108	1.0284	0.5795	1.0284	1.0141
No log	55.0	110	0.7949	0.6431	0.7949	0.8916
No log	56.0	112	0.9471	0.5970	0.9471	0.9732
No log	57.0	114	0.9746	0.5854	0.9746	0.9872
No log	58.0	116	1.0848	0.5279	1.0848	1.0415
No log	59.0	118	0.9107	0.5847	0.9107	0.9543
No log	60.0	120	0.9653	0.5828	0.9653	0.9825

Framework versions

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