Version27NewTestASAP_FineTuningBERT_AugV27_k5_task1_organization_k5_k5_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: 0.6012
• Qwk: 0.5430
• Mse: 0.6004
• Rmse: 0.7749

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: 150

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	3	10.5240	0.0180	10.5216	3.2437
No log	2.0	6	8.2321	0.0	8.2296	2.8687
No log	3.0	9	4.9424	0.0271	4.9403	2.2227
No log	4.0	12	3.2079	0.0	3.2061	1.7905
No log	5.0	15	2.0196	0.0900	2.0180	1.4206
No log	6.0	18	1.2944	0.0211	1.2929	1.1371
No log	7.0	21	1.0114	0.0	1.0101	1.0050
No log	8.0	24	0.8447	0.2320	0.8436	0.9185
No log	9.0	27	0.7522	0.3588	0.7512	0.8667
No log	10.0	30	0.8849	0.3011	0.8837	0.9401
No log	11.0	33	0.6405	0.5092	0.6397	0.7998
No log	12.0	36	1.1887	0.3248	1.1874	1.0897
No log	13.0	39	0.6878	0.4229	0.6874	0.8291
No log	14.0	42	0.6515	0.4835	0.6508	0.8067
No log	15.0	45	0.8442	0.4811	0.8431	0.9182
No log	16.0	48	0.6053	0.5559	0.6045	0.7775
No log	17.0	51	0.6746	0.5510	0.6736	0.8207
No log	18.0	54	0.6230	0.5792	0.6221	0.7887
No log	19.0	57	0.7673	0.4689	0.7659	0.8751
No log	20.0	60	0.6780	0.5107	0.6770	0.8228
No log	21.0	63	0.7030	0.4452	0.7018	0.8378
No log	22.0	66	0.7193	0.4431	0.7185	0.8476
No log	23.0	69	0.6720	0.4686	0.6708	0.8190
No log	24.0	72	0.6510	0.5094	0.6500	0.8062
No log	25.0	75	0.6291	0.5053	0.6281	0.7925
No log	26.0	78	0.6084	0.5410	0.6075	0.7794
No log	27.0	81	0.6433	0.5257	0.6421	0.8013
No log	28.0	84	0.5848	0.5608	0.5839	0.7641
No log	29.0	87	0.6155	0.5304	0.6144	0.7838
No log	30.0	90	0.5931	0.4863	0.5922	0.7695
No log	31.0	93	0.6132	0.5000	0.6121	0.7824
No log	32.0	96	0.6545	0.5184	0.6537	0.8085
No log	33.0	99	0.6108	0.5209	0.6098	0.7809
No log	34.0	102	0.5920	0.5246	0.5911	0.7688
No log	35.0	105	0.5853	0.5728	0.5844	0.7645
No log	36.0	108	0.6044	0.5468	0.6034	0.7768
No log	37.0	111	0.5905	0.5244	0.5896	0.7678
No log	38.0	114	0.5974	0.5370	0.5965	0.7723
No log	39.0	117	0.6721	0.5044	0.6710	0.8191
No log	40.0	120	0.6050	0.5574	0.6043	0.7774
No log	41.0	123	0.5828	0.5411	0.5818	0.7628
No log	42.0	126	0.5763	0.5452	0.5754	0.7585
No log	43.0	129	0.5868	0.5509	0.5859	0.7655
No log	44.0	132	0.6061	0.5545	0.6050	0.7778
No log	45.0	135	0.5851	0.5581	0.5842	0.7644
No log	46.0	138	0.5886	0.5218	0.5877	0.7666
No log	47.0	141	0.5874	0.5445	0.5864	0.7658
No log	48.0	144	0.6012	0.5430	0.6004	0.7749

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.3.1
• Tokenizers 0.21.0