learning_rate: 3e-05
train_batch_size: 16
eval_batch_size: 16
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: 30

Training Loss	Epoch	Step	Validation Loss	Accuracy	Recall	Precision	F1	F Beta Score
0.7452	1.0	21	0.6425	0.7391	0.8364	0.8364	0.8364	0.8364
0.7627	2.0	42	0.6281	0.5072	0.4545	0.8621	0.5952	0.5319
0.6034	3.0	63	0.5713	0.7101	0.7091	0.9070	0.7959	0.7601
0.5791	4.0	84	0.5344	0.8551	0.9455	0.8814	0.9123	0.9248
0.5659	5.0	105	0.5025	0.8696	0.9636	0.8833	0.9217	0.9374
0.4525	6.0	126	0.3408	0.8696	0.8727	0.96	0.9143	0.8978
0.2975	7.0	147	0.3233	0.8696	0.8727	0.96	0.9143	0.8978
0.3961	8.0	168	0.2939	0.8696	0.8909	0.9423	0.9159	0.9061
0.3049	9.0	189	0.5152	0.8986	0.9818	0.9	0.9391	0.9551
0.2996	10.0	210	0.7450	0.8551	0.9818	0.8571	0.9153	0.9398
0.1767	11.0	231	0.5995	0.8986	0.9636	0.9138	0.9381	0.9477

buelfhood/irplag_codet5_ep30_bs16_lr3e-05_l512_s42_ppn_loss

irplag_codet5_ep30_bs16_lr3e-05_l512_s42_ppn_loss