metadata

library_name: transformers
base_model: openai/clip-vit-large-patch14-336
tags:
  - generated_from_trainer
model-index:
  - name: clip-finetuned-csu-p14-336-e3l55-l
    results: []

clip-finetuned-csu-p14-336-e3l55-l

This model is a fine-tuned version of openai/clip-vit-large-patch14-336 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.9056

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: 8.810707926567202e-07
train_batch_size: 128
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.7336	0.0921	500	2.0781
0.6953	0.1842	1000	2.0783
0.6953	0.2763	1500	2.0777
0.6932	0.3684	2000	2.0722
0.6907	0.4605	2500	2.0792
0.7043	0.5526	3000	2.0205
0.7078	0.6447	3500	2.1256
0.7034	0.7368	4000	2.0000
0.6671	0.8289	4500	2.1608
0.6899	0.9210	5000	2.0940
0.6649	1.0131	5500	1.9776
0.6748	1.1052	6000	1.9852
0.6456	1.1973	6500	1.9981
0.6514	1.2894	7000	1.9637
0.6179	1.3815	7500	2.0034
0.6561	1.4736	8000	2.2865
0.6328	1.5657	8500	2.4808
0.7053	1.6578	9000	2.1610
0.6533	1.7499	9500	1.9845
0.6594	1.8420	10000	1.9895
0.6597	1.9341	10500	2.0103
0.6435	2.0262	11000	2.0589
0.6404	2.1183	11500	2.0517
0.6348	2.2104	12000	1.9749
0.6545	2.3024	12500	1.9681
0.6323	2.3945	13000	1.9056
0.6045	2.4866	13500	1.9470
0.6492	2.5787	14000	2.0177
0.6512	2.6708	14500	1.9483
0.6382	2.7629	15000	1.9499
0.6203	2.8550	15500	1.9529
0.6241	2.9471	16000	1.9817

Framework versions

Transformers 4.45.0.dev0
Pytorch 1.12.1
Datasets 2.21.0
Tokenizers 0.19.1