Version_weird_ASAP_FineTuningBERT_AugV12_k5_task1_organization_k5_k5_fold2

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: 0.7850
• Qwk: 0.5573
• Mse: 0.7841
• Rmse: 0.8855

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	9.6639	0.0	9.6642	3.1087
No log	2.0	4	9.2189	0.0	9.2191	3.0363
No log	3.0	6	8.7959	0.0	8.7960	2.9658
No log	4.0	8	7.8942	0.0	7.8943	2.8097
No log	5.0	10	6.4601	0.0	6.4603	2.5417
No log	6.0	12	5.4637	0.0039	5.4639	2.3375
No log	7.0	14	4.5712	0.0039	4.5715	2.1381
No log	8.0	16	3.7098	0.0	3.7102	1.9262
No log	9.0	18	3.1928	0.0	3.1932	1.7870
No log	10.0	20	2.7805	0.0	2.7809	1.6676
No log	11.0	22	2.3901	0.1057	2.3905	1.5461
No log	12.0	24	1.9453	0.0307	1.9458	1.3949
No log	13.0	26	1.6168	0.0107	1.6172	1.2717
No log	14.0	28	1.3765	0.0107	1.3770	1.1734
No log	15.0	30	1.1833	0.0	1.1838	1.0880
No log	16.0	32	1.0428	0.0	1.0432	1.0214
No log	17.0	34	0.9135	0.0	0.9139	0.9560
No log	18.0	36	0.8094	0.3650	0.8099	0.8999
No log	19.0	38	0.7714	0.1346	0.7719	0.8786
No log	20.0	40	0.6884	0.2229	0.6887	0.8299
No log	21.0	42	0.6741	0.2304	0.6743	0.8212
No log	22.0	44	0.6671	0.2697	0.6671	0.8168
No log	23.0	46	0.5217	0.4716	0.5213	0.7220
No log	24.0	48	0.5407	0.5894	0.5399	0.7348
No log	25.0	50	0.6517	0.5672	0.6510	0.8068
No log	26.0	52	0.6508	0.5777	0.6497	0.8061
No log	27.0	54	0.6425	0.5737	0.6414	0.8009
No log	28.0	56	0.7087	0.5872	0.7075	0.8411
No log	29.0	58	0.7163	0.5788	0.7154	0.8458
No log	30.0	60	0.7649	0.5789	0.7642	0.8742
No log	31.0	62	0.7301	0.5789	0.7292	0.8539
No log	32.0	64	0.7889	0.5140	0.7887	0.8881
No log	33.0	66	0.6603	0.5825	0.6597	0.8122
No log	34.0	68	1.4520	0.4381	1.4503	1.2043
No log	35.0	70	0.7404	0.5733	0.7394	0.8599
No log	36.0	72	1.0376	0.4026	1.0375	1.0186
No log	37.0	74	0.7596	0.5483	0.7593	0.8714
No log	38.0	76	0.8582	0.5610	0.8570	0.9258
No log	39.0	78	0.6823	0.5886	0.6815	0.8255
No log	40.0	80	0.7736	0.5291	0.7733	0.8794
No log	41.0	82	0.6738	0.6057	0.6731	0.8205
No log	42.0	84	1.0201	0.5433	1.0188	1.0094
No log	43.0	86	0.7886	0.5523	0.7875	0.8874
No log	44.0	88	0.6911	0.5729	0.6905	0.8310
No log	45.0	90	0.6929	0.5631	0.6921	0.8319
No log	46.0	92	0.9959	0.5271	0.9946	0.9973
No log	47.0	94	0.7890	0.5396	0.7879	0.8877
No log	48.0	96	0.6734	0.5759	0.6727	0.8202
No log	49.0	98	0.6742	0.5670	0.6734	0.8206
No log	50.0	100	0.8987	0.5330	0.8976	0.9474
No log	51.0	102	0.7565	0.5578	0.7556	0.8692
No log	52.0	104	0.6999	0.5605	0.6993	0.8362
No log	53.0	106	0.7378	0.5493	0.7370	0.8585
No log	54.0	108	1.1040	0.5075	1.1026	1.0500
No log	55.0	110	1.3060	0.4702	1.3044	1.1421
No log	56.0	112	0.9653	0.5212	0.9641	0.9819
No log	57.0	114	0.7870	0.5465	0.7864	0.8868
No log	58.0	116	0.7084	0.5699	0.7077	0.8412
No log	59.0	118	0.8627	0.5297	0.8618	0.9283
No log	60.0	120	0.9243	0.5156	0.9234	0.9609
No log	61.0	122	0.7850	0.5573	0.7841	0.8855

Framework versions

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