ASAP_FineTuningBERT_AugV6_k1_task1_organization_k1_k1_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: 0.6832
• Qwk: 0.4648
• Mse: 0.6821
• Rmse: 0.8259

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	9.0711	0.0018	9.0684	3.0114
No log	2.0	4	8.2853	0.0	8.2829	2.8780
No log	3.0	6	7.2977	0.0	7.2953	2.7010
No log	4.0	8	6.2710	0.0	6.2687	2.5037
No log	5.0	10	5.3707	0.0089	5.3685	2.3170
No log	6.0	12	4.4574	0.0	4.4553	2.1108
No log	7.0	14	3.7252	0.0	3.7233	1.9296
No log	8.0	16	3.1111	0.0	3.1093	1.7633
No log	9.0	18	2.5355	0.0	2.5337	1.5918
No log	10.0	20	2.0975	0.1036	2.0958	1.4477
No log	11.0	22	1.6936	0.0106	1.6919	1.3007
No log	12.0	24	1.4167	0.0	1.4152	1.1896
No log	13.0	26	1.2678	0.0	1.2663	1.1253
No log	14.0	28	1.2258	0.0211	1.2243	1.1065
No log	15.0	30	1.2334	0.0418	1.2318	1.1099
No log	16.0	32	1.1346	0.0834	1.1330	1.0644
No log	17.0	34	0.9743	0.0418	0.9731	0.9864
No log	18.0	36	0.9349	0.0418	0.9337	0.9663
No log	19.0	38	0.8947	0.1405	0.8934	0.9452
No log	20.0	40	1.2955	0.2216	1.2939	1.1375
No log	21.0	42	1.0225	0.2428	1.0211	1.0105
No log	22.0	44	0.8460	0.3275	0.8445	0.9190
No log	23.0	46	0.9054	0.3219	0.9039	0.9508
No log	24.0	48	0.7026	0.4752	0.7013	0.8375
No log	25.0	50	0.7253	0.3979	0.7240	0.8509
No log	26.0	52	0.7563	0.3885	0.7550	0.8689
No log	27.0	54	0.6378	0.4477	0.6365	0.7978
No log	28.0	56	0.7725	0.3952	0.7710	0.8781
No log	29.0	58	0.7750	0.3981	0.7735	0.8795
No log	30.0	60	0.6485	0.4024	0.6474	0.8046
No log	31.0	62	0.8012	0.3004	0.8003	0.8946
No log	32.0	64	1.0170	0.2640	1.0160	1.0079
No log	33.0	66	0.7040	0.4066	0.7031	0.8385
No log	34.0	68	0.6447	0.4577	0.6435	0.8022
No log	35.0	70	1.1439	0.2657	1.1424	1.0689
No log	36.0	72	1.0619	0.2585	1.0605	1.0298
No log	37.0	74	0.7097	0.4330	0.7087	0.8418
No log	38.0	76	0.8660	0.3515	0.8651	0.9301
No log	39.0	78	1.6362	0.1514	1.6348	1.2786
No log	40.0	80	1.6766	0.1578	1.6752	1.2943
No log	41.0	82	0.9300	0.3534	0.9291	0.9639
No log	42.0	84	0.8503	0.4187	0.8497	0.9218
No log	43.0	86	0.8224	0.4330	0.8217	0.9065
No log	44.0	88	0.6832	0.4648	0.6821	0.8259

Framework versions

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