Version_concise_ASAP_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_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: 0.7192
• Qwk: 0.6132
• Mse: 0.7197
• Rmse: 0.8484

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	10.2742	0.0	10.2722	3.2050
No log	2.0	4	9.7814	0.0	9.7793	3.1272
No log	3.0	6	8.9711	0.0	8.9691	2.9949
No log	4.0	8	7.5283	0.0	7.5268	2.7435
No log	5.0	10	5.8034	0.0423	5.8022	2.4088
No log	6.0	12	4.5242	0.0137	4.5230	2.1267
No log	7.0	14	3.7842	0.0	3.7831	1.9450
No log	8.0	16	2.9439	0.0	2.9430	1.7155
No log	9.0	18	2.2986	0.1673	2.2978	1.5159
No log	10.0	20	1.7883	0.0488	1.7876	1.3370
No log	11.0	22	1.3218	0.0202	1.3213	1.1495
No log	12.0	24	1.1069	0.0202	1.1065	1.0519
No log	13.0	26	1.1939	0.0365	1.1935	1.0925
No log	14.0	28	1.2194	0.0463	1.2189	1.1041
No log	15.0	30	0.9664	0.0833	0.9661	0.9829
No log	16.0	32	0.8848	0.2252	0.8847	0.9406
No log	17.0	34	0.9147	0.2667	0.9147	0.9564
No log	18.0	36	0.8259	0.3839	0.8260	0.9089
No log	19.0	38	0.6295	0.4309	0.6298	0.7936
No log	20.0	40	0.6090	0.4120	0.6093	0.7806
No log	21.0	42	0.6347	0.4723	0.6351	0.7969
No log	22.0	44	0.6742	0.4906	0.6745	0.8213
No log	23.0	46	0.5661	0.5157	0.5664	0.7526
No log	24.0	48	0.5470	0.5118	0.5475	0.7399
No log	25.0	50	0.5659	0.5405	0.5664	0.7526
No log	26.0	52	0.6043	0.5343	0.6049	0.7778
No log	27.0	54	0.6103	0.5733	0.6108	0.7816
No log	28.0	56	0.6132	0.5781	0.6138	0.7834
No log	29.0	58	0.6244	0.6286	0.6250	0.7906
No log	30.0	60	0.6832	0.5775	0.6840	0.8271
No log	31.0	62	0.6780	0.5939	0.6788	0.8239
No log	32.0	64	0.6931	0.6111	0.6937	0.8329
No log	33.0	66	0.7185	0.6087	0.7192	0.8481
No log	34.0	68	0.7462	0.6079	0.7468	0.8642
No log	35.0	70	0.7167	0.6000	0.7173	0.8470
No log	36.0	72	0.7189	0.5950	0.7196	0.8483
No log	37.0	74	0.7474	0.5959	0.7480	0.8649
No log	38.0	76	0.8152	0.5645	0.8160	0.9033
No log	39.0	78	0.7879	0.5666	0.7886	0.8880
No log	40.0	80	0.7641	0.5988	0.7644	0.8743
No log	41.0	82	0.7175	0.5963	0.7179	0.8473
No log	42.0	84	0.7647	0.5597	0.7654	0.8748
No log	43.0	86	0.7752	0.5648	0.7759	0.8809
No log	44.0	88	0.9973	0.5560	0.9977	0.9988
No log	45.0	90	1.0738	0.5306	1.0742	1.0365
No log	46.0	92	0.8349	0.5956	0.8357	0.9142
No log	47.0	94	0.7809	0.5650	0.7819	0.8842
No log	48.0	96	0.7247	0.6044	0.7254	0.8517
No log	49.0	98	0.7192	0.6132	0.7197	0.8484

Framework versions

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