learning_rate: 0.0002
train_batch_size: 7
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 28
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
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
0.2092	0.2356	100	0.0749
0.0615	0.4711	200	0.0742
0.0557	0.7067	300	0.0625
0.051	0.9423	400	0.0669
0.0418	1.1767	500	0.0567
0.0384	1.4122	600	0.0690
0.0309	1.6478	700	0.0470
0.0271	1.8834	800	0.0559
0.0201	2.1178	900	0.0498
0.0154	2.3534	1000	0.0617

sseongsukim/ft_paligemma2_cwv

ft_paligemma2_cwv