Modelpublic

DamianBoborzi/SmolVLM-Base-smolvlmf_car_quality_2e_l16

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face

0likes5downloads

Model Card

SmolVLM-Base-smolvlmfcarquality2el16

This model is a fine-tuned version of HuggingFaceTB/SmolVLM-Base on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 0.0034

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

—learning_rate: 0.0001
—trainbatchsize: 8
—evalbatchsize: 4
—seed: 42
—gradientaccumulationsteps: 2
—totaltrainbatch_size: 16
—optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
—lrschedulertype: linear
—lrschedulerwarmup_steps: 100
—num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.66	0.1	30	0.4974
0.0312	0.2	60	0.0156
0.0067	0.3	90	0.0074
0.0053	0.4	120	0.0047
0.0044	0.5	150	0.0049
0.0035	0.6	180	0.0047
0.0044	0.7	210	0.0040
0.0029	0.8	240	0.0040
0.0032	0.9	270	0.0041
0.0041	1.0	300	0.0042
0.0033	1.1	330	0.0039
0.0031	1.2	360	0.0040
0.0036	1.3	390	0.0034
0.0029	1.4	420	0.0038
0.0033	1.5	450	0.0036
0.0031	1.6	480	0.0033
0.0028	1.7	510	0.0033
0.0028	1.8	540	0.0033
0.0027	1.9	570	0.0034
0.0029	2.0	600	0.0034

Framework versions

—PEFT 0.15.2
—Transformers 4.52.3
—Pytorch 2.6.0
—Datasets 3.6.0
—Tokenizers 0.21.1