You can deploy this model and start earning money today!

legalaspro/
clip-partial0.8-model-tuning-oxford-pets

Name: clip-partial0.8-model-tuning-oxford-pets
Availability: InStock

zero-shot-image-classification

image-classification

generated_from_trainer

openai/clip-vit-base-patch32

finetune

endpoints_compatible

Views

No views yet

clip-partial0.8-model-tuning-oxford-pets

This model is a fine-tuned version of openai/clip-vit-base-patch32 on the pcuenq/oxford-pets dataset. It achieves the following results on the evaluation set:

Loss: 1.5668

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: 3e-05
train_batch_size: 128
eval_batch_size: 128
seed: 42
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
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.7204	1.0	41	1.5694
1.5997	2.0	82	1.5431
1.5192	3.0	123	1.5388
1.4793	4.0	164	1.5291
1.446	5.0	205	1.5335
1.4433	6.0	246	1.5320
1.4144	7.0	287	1.5408
1.3946	8.0	328	1.5491
1.3994	9.0	369	1.5554
1.3461	10.0	410	1.5668

Framework versions

Transformers 4.52.4
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1

legalaspro/clip-partial0.8-model-tuning-oxford-pets

clip-partial0.8-model-tuning-oxford-pets

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

legalaspro/
clip-partial0.8-model-tuning-oxford-pets