ASAP_FineTuningBERT_AugV5_k10_task1_organization_fold2

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: 0.5821
• Qwk: 0.5834
• Mse: 0.5823
• Rmse: 0.7631

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	2.0	2	10.1102	0.0	10.1098	3.1796
No log	4.0	4	8.5153	0.0	8.5150	2.9181
No log	6.0	6	6.9130	0.0	6.9126	2.6292
No log	8.0	8	5.4748	0.0330	5.4746	2.3398
9.0382	10.0	10	4.4633	0.0039	4.4632	2.1126
9.0382	12.0	12	3.6149	0.0	3.6149	1.9013
9.0382	14.0	14	2.9219	0.0	2.9219	1.7093
9.0382	16.0	16	2.3959	0.0965	2.3959	1.5479
9.0382	18.0	18	1.9642	0.0539	1.9643	1.4015
4.332	20.0	20	1.6434	0.0334	1.6435	1.2820
4.332	22.0	22	1.4010	0.0334	1.4011	1.1837
4.332	24.0	24	1.1567	0.0307	1.1570	1.0756
4.332	26.0	26	1.0073	0.0437	1.0075	1.0038
4.332	28.0	28	0.8614	0.2354	0.8616	0.9282
2.2501	30.0	30	0.7297	0.4421	0.7300	0.8544
2.2501	32.0	32	0.6508	0.4824	0.6513	0.8070
2.2501	34.0	34	0.6363	0.4827	0.6366	0.7979
2.2501	36.0	36	0.5677	0.4278	0.5682	0.7538
2.2501	38.0	38	0.5781	0.4109	0.5787	0.7607
1.1902	40.0	40	0.5452	0.4652	0.5456	0.7386
1.1902	42.0	42	0.5406	0.4471	0.5411	0.7356
1.1902	44.0	44	0.5490	0.4776	0.5495	0.7413
1.1902	46.0	46	0.5443	0.5829	0.5448	0.7381
1.1902	48.0	48	0.5611	0.6050	0.5616	0.7494
0.6288	50.0	50	0.5506	0.5916	0.5510	0.7423
0.6288	52.0	52	0.5505	0.5904	0.5509	0.7422
0.6288	54.0	54	0.6214	0.5851	0.6219	0.7886
0.6288	56.0	56	0.5689	0.5814	0.5693	0.7545
0.6288	58.0	58	0.5470	0.5856	0.5473	0.7398
0.3387	60.0	60	0.6808	0.5546	0.6811	0.8253
0.3387	62.0	62	0.6377	0.5669	0.6380	0.7988
0.3387	64.0	64	0.5568	0.5775	0.5570	0.7463
0.3387	66.0	66	0.5775	0.5689	0.5777	0.7601
0.3387	68.0	68	0.6875	0.5494	0.6877	0.8293
0.1982	70.0	70	0.6655	0.5540	0.6657	0.8159
0.1982	72.0	72	0.5663	0.5536	0.5665	0.7527
0.1982	74.0	74	0.5523	0.5651	0.5524	0.7432
0.1982	76.0	76	0.6181	0.5537	0.6182	0.7863
0.1982	78.0	78	0.7374	0.5493	0.7376	0.8588
0.1267	80.0	80	0.6437	0.5732	0.6439	0.8024
0.1267	82.0	82	0.5785	0.5661	0.5787	0.7607
0.1267	84.0	84	0.5934	0.5702	0.5935	0.7704
0.1267	86.0	86	0.6109	0.5710	0.6111	0.7817
0.1267	88.0	88	0.6239	0.5727	0.6241	0.7900
0.0849	90.0	90	0.5956	0.5785	0.5958	0.7719
0.0849	92.0	92	0.5650	0.5675	0.5652	0.7518
0.0849	94.0	94	0.5627	0.5764	0.5628	0.7502
0.0849	96.0	96	0.5699	0.5769	0.5701	0.7550
0.0849	98.0	98	0.5772	0.5813	0.5773	0.7598
0.0726	100.0	100	0.5821	0.5834	0.5823	0.7631

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1