Version2ASAP_FineTuningBERT_AugV8_k7_task1_organization_k7_k7_fold1

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: 1.0820
• Qwk: 0.1762
• Mse: 1.0806
• Rmse: 1.0395

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	6	6.9771	0.0	6.9748	2.6410
No log	2.0	12	2.7887	0.0	2.7868	1.6694
No log	3.0	18	1.3002	0.0106	1.2988	1.1396
No log	4.0	24	1.8834	0.0454	1.8817	1.3717
No log	5.0	30	1.3841	0.0106	1.3827	1.1759
No log	6.0	36	1.4808	0.0390	1.4793	1.2163
No log	7.0	42	1.0784	0.0327	1.0771	1.0378
No log	8.0	48	0.9558	0.1228	0.9544	0.9769
No log	9.0	54	0.9750	0.1509	0.9735	0.9866
No log	10.0	60	0.9217	0.2167	0.9204	0.9594
No log	11.0	66	1.0088	0.2358	1.0074	1.0037
No log	12.0	72	1.1336	0.2197	1.1321	1.0640
No log	13.0	78	1.5798	0.1747	1.5778	1.2561
No log	14.0	84	1.5702	0.2122	1.5682	1.2523
No log	15.0	90	1.1219	0.2481	1.1205	1.0585
No log	16.0	96	1.0619	0.2806	1.0611	1.0301
No log	17.0	102	1.0894	0.2258	1.0883	1.0432
No log	18.0	108	1.3516	0.1626	1.3501	1.1620
No log	19.0	114	1.1598	0.1736	1.1586	1.0764
No log	20.0	120	1.0415	0.2555	1.0403	1.0199
No log	21.0	126	1.0449	0.2950	1.0440	1.0218
No log	22.0	132	1.1387	0.1959	1.1376	1.0666
No log	23.0	138	0.9666	0.3169	0.9659	0.9828
No log	24.0	144	1.1913	0.1679	1.1898	1.0908
No log	25.0	150	1.3347	0.1602	1.3330	1.1546
No log	26.0	156	1.3828	0.1508	1.3811	1.1752
No log	27.0	162	1.2579	0.1832	1.2564	1.1209
No log	28.0	168	1.4087	0.1653	1.4070	1.1862
No log	29.0	174	0.9986	0.2759	0.9975	0.9987
No log	30.0	180	0.9774	0.2646	0.9763	0.9881
No log	31.0	186	1.0423	0.2363	1.0410	1.0203
No log	32.0	192	1.2272	0.1931	1.2256	1.1071
No log	33.0	198	1.1808	0.1722	1.1793	1.0859
No log	34.0	204	1.1538	0.1824	1.1524	1.0735
No log	35.0	210	0.9562	0.2479	0.9550	0.9772
No log	36.0	216	1.0451	0.2389	1.0440	1.0218
No log	37.0	222	1.0413	0.2056	1.0401	1.0199
No log	38.0	228	1.0996	0.2015	1.0984	1.0481
No log	39.0	234	0.9685	0.2558	0.9674	0.9836
No log	40.0	240	1.0207	0.2350	1.0195	1.0097
No log	41.0	246	1.2166	0.1672	1.2150	1.1023
No log	42.0	252	1.1833	0.1786	1.1817	1.0871
No log	43.0	258	1.0820	0.1762	1.0806	1.0395

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.3.1
• Tokenizers 0.21.0