metadata

license: apache-2.0
base_model: facebook/dinov2-small-imagenet1k-1-layer
tags:
  - image-classification
  - vision
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: dinov2-small-imagenet1k-1-layer-finetuned-galaxy10-decals
    results: []

dinov2-small-imagenet1k-1-layer-finetuned-galaxy10-decals

This model is a fine-tuned version of facebook/dinov2-small-imagenet1k-1-layer on the matthieulel/galaxy10_decals dataset. It achieves the following results on the evaluation set:

Loss: 0.4242
Accuracy: 0.8715

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: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.924	0.9940	124	0.8075	0.7294
0.8226	1.9960	249	0.8195	0.7193
0.805	2.9980	374	0.6233	0.7903
0.752	4.0	499	0.6687	0.7796
0.6193	4.9940	623	0.5708	0.8050
0.5822	5.9960	748	0.5624	0.8061
0.6227	6.9980	873	0.5536	0.8134
0.6067	8.0	998	0.5687	0.8185
0.533	8.9940	1122	0.5919	0.8089
0.5423	9.9960	1247	0.5022	0.8371
0.4747	10.9980	1372	0.4419	0.8579
0.4367	12.0	1497	0.5084	0.8207
0.4907	12.9940	1621	0.4774	0.8365
0.4269	13.9960	1746	0.4945	0.8444
0.3787	14.9980	1871	0.4779	0.8478
0.3724	16.0	1996	0.4242	0.8715
0.354	16.9940	2120	0.4595	0.8529
0.3304	17.9960	2245	0.4543	0.8563
0.2849	18.9980	2370	0.4699	0.8608
0.2456	19.8798	2480	0.4505	0.8664

Framework versions

Transformers 4.40.1
Pytorch 2.2.1+cu121
Datasets 2.19.1
Tokenizers 0.19.1