learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 32
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_HF 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: 2
num_epochs: 1

Training Loss	Epoch	Step	Validation Loss
1.7663	0.0580	100	0.3039
1.0343	0.1159	200	0.2727
1.0763	0.1739	300	0.2598
0.9531	0.2318	400	0.2480
0.8547	0.2898	500	0.2407
0.9085	0.3477	600	0.2314
0.8865	0.4057	700	0.2262
0.7912	0.4636	800	0.2216
0.8547	0.5216	900	0.2178
0.8279	0.5795	1000	0.2147
0.8697	0.6375	1100	0.2129
0.8538	0.6955	1200	0.2104
0.8126	0.7534	1300	0.2098
0.8165	0.8114	1400	0.2089
0.8485	0.8693	1500	0.2086
0.8075	0.9273	1600	0.2083
0.8574	0.9852	1700	0.2083

acchf/vision-tags-paligemma-qlora

vision-tags-paligemma-qlora