learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.06
num_epochs: 4
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	Accuracy Balanced	F1 Macro	F1 Weighted	F1 Micro	F1 Positive	Precision Macro	Precision Weighted	Recall Macro	Recall Weighted	Mcc	Roc Auc	Pr Auc
0.5396	1.0	832	0.3387	0.8821	0.8559	0.8658	0.8802	0.8821	0.9126	0.8797	0.8816	0.8559	0.8821	0.7352	0.9363	0.9605
0.288	2.0	1664	0.3936	0.8947	0.8827	0.8835	0.8946	0.8947	0.9197	0.8842	0.8945	0.8827	0.8947	0.7670	0.9509	0.9663
0.248	3.0	2496	0.4958	0.8961	0.8915	0.8866	0.8967	0.8961	0.9195	0.8825	0.8980	0.8915	0.8961	0.7739	0.9557	0.9689
0.1218	4.0	3328	0.4989	0.9004	0.8894	0.8898	0.9003	0.9004	0.9239	0.8902	0.9003	0.8894	0.9004	0.7796	0.9559	0.9699

mljn/mdeberta-v3-base-finetuned-climate-support-classification-full

mdeberta-v3-base-finetuned-climate-support-classification-full