learning_rate: 0.0003
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: 15

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
0.6793	1.0	447	0.6713	0.5639	0.7355	0.6384
0.6342	2.0	894	0.6474	0.5714	0.7971	0.6657
0.5915	3.0	1341	0.7200	0.5845	0.7391	0.6528
0.551	4.0	1788	0.7096	0.5890	0.8152	0.6839
0.4821	5.0	2235	0.8309	0.5695	0.7717	0.6554
0.4188	6.0	2682	0.8327	0.6174	0.6957	0.6542
0.3621	7.0	3129	1.1130	0.5914	0.5978	0.5946
0.3069	8.0	3576	1.4566	0.5828	0.6884	0.6312
0.2551	9.0	4023	1.8830	0.5848	0.6993	0.6370
0.2014	10.0	4470	2.3017	0.5855	0.6449	0.6138
0.1637	11.0	4917	2.6628	0.5796	0.6993	0.6338
0.1029	12.0	5364	3.0285	0.5852	0.6594	0.6201
0.124	13.0	5811	3.3504	0.6055	0.6341	0.6195
0.0737	14.0	6258	3.6600	0.6013	0.6667	0.6323
0.0508	15.0	6705	3.8181	0.5895	0.6920	0.6367

maud-dr/baseline_1-seed_42

baseline_1-seed_42