Version12LowDevASAP_FineTuningBERT_AugV12_k5_task1_organization_k5_k5_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: 1.0964
• Qwk: 0.6100
• Mse: 1.0964
• Rmse: 1.0471

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	10.5713	0.0052	10.5713	3.2513
No log	2.0	4	8.0991	0.0	8.0991	2.8459
No log	3.0	6	6.3506	0.0	6.3506	2.5200
No log	4.0	8	4.7814	-0.0179	4.7814	2.1867
No log	5.0	10	3.3419	0.0	3.3419	1.8281
No log	6.0	12	2.6695	0.0	2.6695	1.6339
No log	7.0	14	2.3143	-0.0183	2.3143	1.5213
No log	8.0	16	1.7305	0.0489	1.7305	1.3155
No log	9.0	18	1.2666	0.0	1.2666	1.1254
No log	10.0	20	1.1016	0.0	1.1016	1.0496
No log	11.0	22	1.0201	-0.0113	1.0201	1.0100
No log	12.0	24	0.9248	0.1253	0.9248	0.9617
No log	13.0	26	0.9761	0.0564	0.9761	0.9880
No log	14.0	28	1.1252	0.0564	1.1252	1.0607
No log	15.0	30	1.0053	0.0909	1.0053	1.0026
No log	16.0	32	1.1336	0.0909	1.1336	1.0647
No log	17.0	34	0.7815	0.4466	0.7815	0.8840
No log	18.0	36	1.0664	0.4315	1.0664	1.0327
No log	19.0	38	0.6680	0.6086	0.6680	0.8173
No log	20.0	40	0.8091	0.5765	0.8091	0.8995
No log	21.0	42	0.5411	0.6541	0.5411	0.7356
No log	22.0	44	0.6359	0.6617	0.6359	0.7974
No log	23.0	46	0.5699	0.6739	0.5699	0.7549
No log	24.0	48	1.0526	0.5745	1.0526	1.0259
No log	25.0	50	0.4763	0.7537	0.4763	0.6902
No log	26.0	52	0.7295	0.6580	0.7295	0.8541
No log	27.0	54	1.6945	0.4814	1.6945	1.3017
No log	28.0	56	0.6855	0.6959	0.6855	0.8280
No log	29.0	58	0.7193	0.6742	0.7193	0.8481
No log	30.0	60	1.5739	0.5099	1.5739	1.2546
No log	31.0	62	0.6769	0.6869	0.6769	0.8227
No log	32.0	64	0.7386	0.6756	0.7386	0.8594
No log	33.0	66	1.3844	0.5393	1.3844	1.1766
No log	34.0	68	0.6101	0.7007	0.6101	0.7811
No log	35.0	70	0.6145	0.7007	0.6145	0.7839
No log	36.0	72	1.1029	0.6042	1.1029	1.0502
No log	37.0	74	0.8722	0.6488	0.8722	0.9339
No log	38.0	76	1.3056	0.5708	1.3056	1.1426
No log	39.0	78	1.0424	0.6192	1.0424	1.0210
No log	40.0	80	1.1727	0.5933	1.1727	1.0829
No log	41.0	82	0.8549	0.6569	0.8549	0.9246
No log	42.0	84	1.1651	0.5833	1.1651	1.0794
No log	43.0	86	0.9435	0.6483	0.9435	0.9713
No log	44.0	88	0.8338	0.6604	0.8338	0.9131
No log	45.0	90	1.0964	0.6100	1.0964	1.0471

Framework versions

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