Version3ASAP_FineTuningBERT_AugV12_k10_task1_organization_k10_k10_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: 1.3482
• Qwk: 0.4694
• Mse: 1.3477
• Rmse: 1.1609

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	3	6.8445	0.0	6.8421	2.6157
No log	2.0	6	4.2982	0.0079	4.2962	2.0727
No log	3.0	9	3.0719	0.0	3.0701	1.7522
No log	4.0	12	2.2654	0.0509	2.2638	1.5046
No log	5.0	15	1.5906	0.0211	1.5891	1.2606
No log	6.0	18	1.2486	0.0	1.2472	1.1168
No log	7.0	21	1.0013	0.0	1.0000	1.0000
No log	8.0	24	0.8897	0.1661	0.8886	0.9426
No log	9.0	27	0.8663	0.0749	0.8653	0.9302
No log	10.0	30	0.8147	0.1312	0.8138	0.9021
No log	11.0	33	1.1934	0.0429	1.1926	1.0921
No log	12.0	36	1.2848	0.3013	1.2842	1.1332
No log	13.0	39	0.9429	0.4196	0.9424	0.9708
No log	14.0	42	1.5947	0.2706	1.5945	1.2627
No log	15.0	45	1.1223	0.4601	1.1220	1.0592
No log	16.0	48	0.6823	0.6325	0.6819	0.8258
No log	17.0	51	2.2544	0.3233	2.2543	1.5014
No log	18.0	54	1.4071	0.4862	1.4069	1.1861
No log	19.0	57	0.5306	0.6917	0.5304	0.7283
No log	20.0	60	1.8187	0.4227	1.8186	1.3486
No log	21.0	63	0.8853	0.6124	0.8852	0.9409
No log	22.0	66	0.6079	0.6486	0.6076	0.7795
No log	23.0	69	1.3528	0.4844	1.3526	1.1630
No log	24.0	72	0.9655	0.5518	0.9653	0.9825
No log	25.0	75	1.1439	0.5044	1.1437	1.0694
No log	26.0	78	0.6485	0.6657	0.6482	0.8051
No log	27.0	81	1.0402	0.5597	1.0399	1.0198
No log	28.0	84	1.0703	0.5020	1.0698	1.0343
No log	29.0	87	1.7184	0.3911	1.7179	1.3107
No log	30.0	90	0.6999	0.6274	0.6994	0.8363
No log	31.0	93	0.7360	0.6213	0.7356	0.8577
No log	32.0	96	1.3706	0.4827	1.3701	1.1705
No log	33.0	99	0.8476	0.6069	0.8471	0.9204
No log	34.0	102	1.4165	0.4730	1.4160	1.1899
No log	35.0	105	1.3546	0.5066	1.3542	1.1637
No log	36.0	108	0.9417	0.5729	0.9412	0.9701
No log	37.0	111	1.3669	0.4434	1.3663	1.1689
No log	38.0	114	1.0415	0.5570	1.0409	1.0203
No log	39.0	117	1.3482	0.4694	1.3477	1.1609

Framework versions

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