Version3ASAP_FineTuningBERT_AugV12_k10_task1_organization_k10_k10_fold3

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: 0.9770
• Qwk: 0.5597
• Mse: 0.9758
• Rmse: 0.9878

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	3	7.0239	0.0	7.0223	2.6500
No log	2.0	6	4.5327	0.0076	4.5315	2.1287
No log	3.0	9	3.3000	0.0	3.2991	1.8163
No log	4.0	12	2.4226	0.0543	2.4218	1.5562
No log	5.0	15	1.6966	0.0202	1.6959	1.3023
No log	6.0	18	1.3410	0.0	1.3404	1.1578
No log	7.0	21	0.9905	0.0209	0.9900	0.9950
No log	8.0	24	0.8677	0.0852	0.8673	0.9313
No log	9.0	27	0.9047	0.0314	0.9044	0.9510
No log	10.0	30	0.9799	0.0414	0.9797	0.9898
No log	11.0	33	1.2914	0.0235	1.2913	1.1364
No log	12.0	36	1.5902	0.1282	1.5902	1.2610
No log	13.0	39	1.2143	0.2541	1.2142	1.1019
No log	14.0	42	1.8820	0.1786	1.8819	1.3718
No log	15.0	45	1.4104	0.3576	1.4102	1.1875
No log	16.0	48	0.7954	0.5388	0.7951	0.8917
No log	17.0	51	1.1935	0.5304	1.1925	1.0920
No log	18.0	54	0.9172	0.5904	0.9163	0.9572
No log	19.0	57	0.6818	0.5687	0.6812	0.8254
No log	20.0	60	1.1476	0.4754	1.1468	1.0709
No log	21.0	63	1.2699	0.4705	1.2691	1.1265
No log	22.0	66	0.6683	0.6098	0.6676	0.8171
No log	23.0	69	0.8433	0.6027	0.8424	0.9178
No log	24.0	72	0.8357	0.6110	0.8348	0.9137
No log	25.0	75	0.6726	0.6489	0.6719	0.8197
No log	26.0	78	1.3829	0.4613	1.3819	1.1755
No log	27.0	81	1.3860	0.4639	1.3849	1.1768
No log	28.0	84	0.7712	0.6222	0.7703	0.8777
No log	29.0	87	0.9150	0.5990	0.9140	0.9560
No log	30.0	90	0.8455	0.6044	0.8446	0.9190
No log	31.0	93	1.0813	0.5216	1.0805	1.0395
No log	32.0	96	0.7851	0.5846	0.7844	0.8856
No log	33.0	99	0.6808	0.5846	0.6800	0.8246
No log	34.0	102	0.7450	0.6033	0.7442	0.8627
No log	35.0	105	0.7109	0.6092	0.7101	0.8427
No log	36.0	108	0.9390	0.5465	0.9380	0.9685
No log	37.0	111	0.9528	0.5586	0.9517	0.9756
No log	38.0	114	0.7407	0.6232	0.7399	0.8602
No log	39.0	117	0.8105	0.5959	0.8097	0.8998
No log	40.0	120	1.2730	0.4817	1.2718	1.1277
No log	41.0	123	1.3054	0.4707	1.3041	1.1420
No log	42.0	126	0.8738	0.5780	0.8727	0.9342
No log	43.0	129	0.6802	0.5863	0.6794	0.8242
No log	44.0	132	0.7616	0.5976	0.7606	0.8721
No log	45.0	135	0.9770	0.5597	0.9758	0.9878

Framework versions

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