learning_rate: 1e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
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
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Macro F1	Weighted F1	Accuracy	Map@3
1.3548	0.2422	500	1.0357	0.2067	0.4193	0.4221	0.5941
0.9062	0.4845	1000	0.7145	0.3536	0.6222	0.6183	0.7672
0.5924	0.7267	1500	0.4780	0.4251	0.7250	0.7368	0.8460
0.4113	0.9690	2000	0.4354	0.4210	0.7139	0.7354	0.8430
0.2906	1.2112	2500	0.3885	0.4757	0.7373	0.7559	0.8635
0.3248	1.4535	3000	0.3100	0.5215	0.7591	0.7589	0.8651
0.264	1.6957	3500	0.3245	0.5371	0.7838	0.7864	0.8852
0.3461	1.9380	4000	0.2863	0.5582	0.8036	0.8136	0.8988
0.202	2.1802	4500	0.2697	0.5758	0.8058	0.8147	0.9013
0.1641	2.4225	5000	0.2837	0.6015	0.8224	0.8245	0.9062
0.1642	2.6647	5500	0.2991	0.5559	0.8113	0.8139	0.9009
0.1857	2.9070	6000	0.2518	0.5931	0.8051	0.8109	0.8995
0.1322	3.1492	6500	0.2595	0.6012	0.7862	0.7823	0.8846

AceVikings/deberta-misconception-classifier

deberta-misconception-classifier