learning_rate: 0.0001
train_batch_size: 8
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
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
lr_scheduler_warmup_steps: 150
num_epochs: 2

Training Loss	Epoch	Step	Validation Loss
0.7689	0.1	30	0.6595
0.1321	0.2	60	0.0555
0.0074	0.3	90	0.0069
0.005	0.4	120	0.0055
0.0044	0.5	150	0.0053
0.0037	0.6	180	0.0044
0.0044	0.7	210	0.0043
0.003	0.8	240	0.0038
0.0034	0.9	270	0.0039
0.0041	1.0	300	0.0038
0.0034	1.1	330	0.0044
0.0031	1.2	360	0.0045
0.0036	1.3	390	0.0039
0.0029	1.4	420	0.0039
0.0033	1.5	450	0.0038
0.003	1.6	480	0.0034
0.0029	1.7	510	0.0033
0.0028	1.8	540	0.0034
0.0026	1.9	570	0.0034
0.0028	2.0	600	0.0035

DamianBoborzi/SmolVLM-Base-smolvlmf_car_quality_2e_l8

SmolVLM-Base-smolvlmf_car_quality_2e_l8