learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 128
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

Training Loss	Epoch	Step	Acc Content	F1 Content	Validation Loss
0.0038	1.0	529	0.9013	0.8931	0.0031
0.0024	2.0	1058	0.9222	0.9147	0.0034
0.0018	3.0	1587	0.9360	0.9290	0.0052
0.0014	4.0	2116	0.9451	0.9387	0.0064
0.001	5.0	2645	0.9496	0.9435	0.0071
0.001	6.0	3174	0.9593	0.9539	0.0121
0.0007	7.0	3703	0.9647	0.9598	0.0157
0.0006	8.0	4232	0.9603	0.9550	0.0135
0.0005	9.0	4761	0.9659	0.9610	0.0185
0.0004	10.0	5290	0.9683	0.9637	0.0214

ttqdunggg/3adapter_backbone_100k_v2

3adapter_backbone_100k_v2