learning_rate: 1e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 6
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Accuracy	Auc	F1	Validation Loss	Precision	Recall
0.4959	1.0	1012	0.7664	0.8395	0.7056	0.5189	0.7833	0.6418
0.4136	2.0	2024	0.7890	0.8549	0.7295	0.5210	0.8271	0.6526
0.413	3.0	3036	0.4964	0.8008	0.7605	0.7994	0.7252	0.8650
0.4113	4.0	4048	0.5015	0.8066	0.7620	0.8222	0.7100	0.8706
0.3754	5.0	5060	0.4990	0.8113	0.7671	0.8306	0.7126	0.8738
0.3449	6.0	6072	0.4923	0.8096	0.7725	0.8067	0.7410	0.8745

Arnold145/adima_training_new_2

adima_training_new_2