deberta-large-semeval25_EN08_fold1

This model is a fine-tuned version of microsoft/deberta-v3-large on the None dataset. It achieves the following results on the evaluation set:

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.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: 10

Training Loss	Epoch	Step	Validation Loss	Precision Samples	Recall Samples	F1 Samples	Precision Macro	Recall Macro	F1 Macro	Precision Micro	Recall Micro	F1 Micro	Precision Weighted	Recall Weighted	F1 Weighted
9.8711	1.0	73	8.8570	0.0978	0.4834	0.1557	0.8682	0.3461	0.2448	0.0975	0.4043	0.1571	0.5919	0.4043	0.0854
8.2971	2.0	146	8.2276	0.1082	0.6729	0.1741	0.7046	0.4763	0.2696	0.0946	0.6173	0.1641	0.3929	0.6173	0.1405
7.5948	3.0	219	7.9992	0.0990	0.6954	0.1650	0.6089	0.5297	0.2772	0.0914	0.6512	0.1603	0.2959	0.6512	0.1492
7.0815	4.0	292	7.8758	0.0929	0.7629	0.1597	0.5483	0.6015	0.2645	0.0883	0.7191	0.1573	0.2531	0.7191	0.1680
8.4958	5.0	365	7.5246	0.0945	0.7963	0.1625	0.5313	0.6367	0.2740	0.0859	0.7469	0.1541	0.2431	0.7469	0.1821
6.9189	6.0	438	7.5150	0.1045	0.8052	0.1680	0.5023	0.6561	0.2707	0.0906	0.7654	0.1621	0.2333	0.7654	0.1919
6.9602	7.0	511	7.4003	0.0983	0.8095	0.1691	0.4487	0.6672	0.2613	0.0903	0.7778	0.1618	0.2010	0.7778	0.2003
6.313	8.0	584	7.2823	0.1004	0.8072	0.1719	0.4318	0.6775	0.2579	0.0930	0.7840	0.1663	0.1996	0.7840	0.2071
6.7969	9.0	657	7.3025	0.1037	0.8251	0.1775	0.4212	0.6896	0.2595	0.0965	0.7901	0.1720	0.2114	0.7901	0.2231
6.5913	10.0	730	7.2150	0.1016	0.8120	0.1744	0.4040	0.6916	0.2551	0.0950	0.7870	0.1695	0.2008	0.7870	0.2171