ASAP_FineTuningBERT_AugV8_k7_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: 2.2938
• Qwk: 0.1094
• Mse: 2.2935
• Rmse: 1.5144

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	0.3333	2	11.2858	0.0150	11.2855	3.3594
No log	0.6667	4	9.9343	0.0	9.9337	3.1518
No log	1.0	6	8.1472	0.0	8.1467	2.8542
No log	1.3333	8	6.5999	0.0	6.5995	2.5689
6.8882	1.6667	10	5.2095	0.0493	5.2092	2.2824
6.8882	2.0	12	4.1124	0.0	4.1122	2.0279
6.8882	2.3333	14	2.7768	0.0	2.7767	1.6663
6.8882	2.6667	16	2.1345	0.1175	2.1345	1.4610
6.8882	3.0	18	1.6101	0.0487	1.6102	1.2689
2.3761	3.3333	20	1.2754	0.0318	1.2755	1.1294
2.3761	3.6667	22	1.3909	0.0422	1.3910	1.1794
2.3761	4.0	24	1.2152	0.0487	1.2152	1.1024
2.3761	4.3333	26	1.2324	0.0487	1.2324	1.1101
2.3761	4.6667	28	0.8357	0.1514	0.8358	0.9142
1.835	5.0	30	0.8119	0.2241	0.8120	0.9011
1.835	5.3333	32	1.8790	0.2121	1.8787	1.3707
1.835	5.6667	34	2.0765	0.1948	2.0763	1.4409
1.835	6.0	36	1.2150	0.2134	1.2149	1.1022
1.835	6.3333	38	0.7821	0.3644	0.7821	0.8844
1.7846	6.6667	40	0.9700	0.1558	0.9701	0.9849
1.7846	7.0	42	1.4151	0.1997	1.4151	1.1896
1.7846	7.3333	44	1.0879	0.1604	1.0879	1.0430
1.7846	7.6667	46	0.8525	0.2917	0.8525	0.9233
1.7846	8.0	48	1.2183	0.2059	1.2184	1.1038
1.4933	8.3333	50	1.1663	0.2014	1.1665	1.0801
1.4933	8.6667	52	0.9618	0.3284	0.9622	0.9809
1.4933	9.0	54	0.9909	0.3446	0.9912	0.9956
1.4933	9.3333	56	1.2824	0.2387	1.2827	1.1326
1.4933	9.6667	58	0.8808	0.3690	0.8810	0.9386
0.9822	10.0	60	1.4120	0.2170	1.4120	1.1883
0.9822	10.3333	62	0.9666	0.3955	0.9666	0.9832
0.9822	10.6667	64	2.0153	0.1782	2.0152	1.4196
0.9822	11.0	66	1.4499	0.3026	1.4498	1.2041
0.9822	11.3333	68	0.7973	0.5056	0.7971	0.8928
0.634	11.6667	70	2.2539	0.1695	2.2537	1.5012
0.634	12.0	72	2.5144	0.1321	2.5143	1.5857
0.634	12.3333	74	0.8087	0.4145	0.8087	0.8993
0.634	12.6667	76	0.7944	0.4132	0.7944	0.8913
0.634	13.0	78	2.4109	0.0932	2.4108	1.5527
0.6471	13.3333	80	2.8257	0.0583	2.8256	1.6809
0.6471	13.6667	82	1.0035	0.3316	1.0035	1.0017
0.6471	14.0	84	0.8648	0.3706	0.8649	0.9300
0.6471	14.3333	86	2.0557	0.1425	2.0555	1.4337
0.6471	14.6667	88	2.2938	0.1094	2.2935	1.5144

Framework versions

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