ASAP_FineTuningBERT_AugV8_k2_task1_organization_fold4

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: 1.1154
• Qwk: 0.3930
• Mse: 1.1154
• Rmse: 1.0561

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	10.3681	0.0037	10.3681	3.2200
No log	2.0	4	9.8337	0.0018	9.8337	3.1359
No log	3.0	6	9.2950	0.0018	9.2950	3.0488
No log	4.0	8	7.6364	0.0018	7.6364	2.7634
7.4321	5.0	10	6.3080	0.0	6.3080	2.5116
7.4321	6.0	12	5.3098	0.0222	5.3098	2.3043
7.4321	7.0	14	4.2319	0.0079	4.2319	2.0572
7.4321	8.0	16	3.2295	0.0079	3.2295	1.7971
7.4321	9.0	18	2.2769	0.1339	2.2769	1.5090
3.4188	10.0	20	1.5508	0.0445	1.5508	1.2453
3.4188	11.0	22	1.3006	0.0445	1.3006	1.1404
3.4188	12.0	24	1.1983	0.0495	1.1983	1.0947
3.4188	13.0	26	1.0830	0.0658	1.0830	1.0407
3.4188	14.0	28	1.3415	0.1436	1.3415	1.1582
1.9137	15.0	30	1.2975	0.1737	1.2975	1.1391
1.9137	16.0	32	1.1237	0.2462	1.1237	1.0601
1.9137	17.0	34	1.3118	0.2460	1.3118	1.1453
1.9137	18.0	36	1.0005	0.3452	1.0005	1.0003
1.9137	19.0	38	1.2575	0.3204	1.2575	1.1214
1.2854	20.0	40	0.8810	0.4113	0.8810	0.9386
1.2854	21.0	42	1.1965	0.3539	1.1965	1.0938
1.2854	22.0	44	0.8713	0.4240	0.8713	0.9334
1.2854	23.0	46	0.7629	0.4951	0.7629	0.8734
1.2854	24.0	48	1.0313	0.3921	1.0313	1.0155
0.6102	25.0	50	0.8027	0.4927	0.8027	0.8959
0.6102	26.0	52	1.1482	0.4121	1.1482	1.0715
0.6102	27.0	54	0.8849	0.4771	0.8849	0.9407
0.6102	28.0	56	1.0759	0.4125	1.0759	1.0373
0.6102	29.0	58	0.9356	0.4478	0.9356	0.9673
0.3083	30.0	60	1.1359	0.4229	1.1359	1.0658
0.3083	31.0	62	1.1750	0.4118	1.1750	1.0840
0.3083	32.0	64	1.1024	0.4296	1.1024	1.0500
0.3083	33.0	66	1.1154	0.3930	1.1154	1.0561

Framework versions

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