ASAP_FineTuningBERT_AugV8_k2_task1_organization_k2_fold0

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: 0.6667
• Qwk: 0.5141
• Mse: 0.6667
• Rmse: 0.8165

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	9.0519	0.0	9.0519	3.0086
No log	2.0	4	7.6555	0.0	7.6555	2.7669
No log	3.0	6	6.8388	0.0	6.8388	2.6151
No log	4.0	8	6.0378	0.0200	6.0378	2.4572
No log	5.0	10	5.2137	0.0115	5.2137	2.2833
No log	6.0	12	4.3979	0.0039	4.3979	2.0971
No log	7.0	14	3.6383	0.0	3.6383	1.9074
No log	8.0	16	2.9050	0.0	2.9050	1.7044
No log	9.0	18	2.2788	0.1035	2.2788	1.5096
No log	10.0	20	1.8176	0.0548	1.8176	1.3482
No log	11.0	22	1.4011	0.0316	1.4011	1.1837
No log	12.0	24	1.3229	0.0484	1.3229	1.1502
No log	13.0	26	1.2302	0.0484	1.2302	1.1092
No log	14.0	28	0.9426	0.0484	0.9426	0.9709
No log	15.0	30	1.2006	0.1344	1.2006	1.0957
No log	16.0	32	0.9119	0.2868	0.9119	0.9549
No log	17.0	34	0.8450	0.3851	0.8450	0.9193
No log	18.0	36	0.7595	0.4316	0.7595	0.8715
No log	19.0	38	0.6386	0.4271	0.6386	0.7991
No log	20.0	40	0.6012	0.4510	0.6012	0.7754
No log	21.0	42	0.5864	0.4365	0.5864	0.7658
No log	22.0	44	0.7143	0.4339	0.7143	0.8452
No log	23.0	46	0.6212	0.4174	0.6212	0.7882
No log	24.0	48	0.6290	0.4330	0.6290	0.7931
No log	25.0	50	0.7940	0.4388	0.7940	0.8911
No log	26.0	52	0.6145	0.4413	0.6145	0.7839
No log	27.0	54	0.6133	0.4551	0.6133	0.7832
No log	28.0	56	0.6525	0.5045	0.6525	0.8078
No log	29.0	58	0.6365	0.5209	0.6365	0.7978
No log	30.0	60	0.6471	0.5096	0.6471	0.8044
No log	31.0	62	0.6618	0.5050	0.6618	0.8135
No log	32.0	64	0.6884	0.5093	0.6884	0.8297
No log	33.0	66	0.7074	0.5115	0.7074	0.8411
No log	34.0	68	0.6597	0.5438	0.6597	0.8122
No log	35.0	70	0.6572	0.5217	0.6572	0.8107
No log	36.0	72	0.6584	0.5115	0.6584	0.8114
No log	37.0	74	0.6475	0.5099	0.6475	0.8047
No log	38.0	76	0.6982	0.5063	0.6982	0.8356
No log	39.0	78	0.7089	0.5067	0.7089	0.8420
No log	40.0	80	0.6991	0.4882	0.6991	0.8361
No log	41.0	82	0.6856	0.5231	0.6856	0.8280
No log	42.0	84	0.6082	0.5526	0.6082	0.7799
No log	43.0	86	0.6268	0.5317	0.6268	0.7917
No log	44.0	88	0.6813	0.5174	0.6813	0.8254
No log	45.0	90	0.6511	0.5251	0.6511	0.8069
No log	46.0	92	0.6679	0.5264	0.6679	0.8173
No log	47.0	94	0.6538	0.5093	0.6538	0.8086
No log	48.0	96	0.6250	0.5399	0.6250	0.7906
No log	49.0	98	0.6192	0.5446	0.6192	0.7869
No log	50.0	100	0.7182	0.5189	0.7182	0.8475
No log	51.0	102	0.6737	0.5108	0.6737	0.8208
No log	52.0	104	0.6667	0.5141	0.6667	0.8165

Framework versions

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