ASAP_FineTuningBERT_AugV8_k1_task1_organization_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: 0.7391
• Qwk: 0.5287
• Mse: 0.7399
• Rmse: 0.8602

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	10.3196	0.0014	10.3178	3.2121
No log	2.0	4	7.2215	0.0	7.2202	2.6870
No log	3.0	6	5.3307	0.0161	5.3295	2.3086
No log	4.0	8	4.0710	0.0	4.0699	2.0174
No log	5.0	10	3.3146	0.0	3.3134	1.8203
No log	6.0	12	2.5785	-0.0111	2.5776	1.6055
No log	7.0	14	2.0507	0.0266	2.0499	1.4318
No log	8.0	16	1.6022	0.0202	1.6015	1.2655
No log	9.0	18	1.2505	0.0266	1.2500	1.1180
No log	10.0	20	1.3209	0.0202	1.3204	1.1491
No log	11.0	22	1.0664	0.0717	1.0661	1.0325
No log	12.0	24	1.0138	0.3620	1.0139	1.0069
No log	13.0	26	0.8288	0.5269	0.8291	0.9105
No log	14.0	28	0.8755	0.2203	0.8753	0.9356
No log	15.0	30	1.0460	0.2004	1.0458	1.0227
No log	16.0	32	0.9638	0.3144	0.9639	0.9818
No log	17.0	34	0.8350	0.5351	0.8354	0.9140
No log	18.0	36	0.8384	0.5377	0.8388	0.9159
No log	19.0	38	0.8951	0.4324	0.8954	0.9462
No log	20.0	40	0.8969	0.4082	0.8973	0.9472
No log	21.0	42	0.8200	0.5473	0.8205	0.9058
No log	22.0	44	0.7806	0.5406	0.7811	0.8838
No log	23.0	46	0.7539	0.4906	0.7545	0.8686
No log	24.0	48	0.7043	0.5153	0.7048	0.8395
No log	25.0	50	0.6591	0.5214	0.6596	0.8122
No log	26.0	52	0.6587	0.5178	0.6593	0.8120
No log	27.0	54	0.6943	0.5135	0.6951	0.8337
No log	28.0	56	0.6894	0.5219	0.6902	0.8308
No log	29.0	58	0.7109	0.5223	0.7118	0.8437
No log	30.0	60	0.8405	0.4449	0.8412	0.9172
No log	31.0	62	0.7391	0.5287	0.7399	0.8602

Framework versions

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