tangg555's picture
Model save
d5b073a verified
metadata
library_name: transformers
base_model: openai/clip-vit-large-patch14-336
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: >-
      clip-vit-large-patch14-336-finetuned-openai-clip-vit-large-patch14-336-emnist-letter
    results: []

clip-vit-large-patch14-336-finetuned-openai-clip-vit-large-patch14-336-emnist-letter

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: 0.1417
  • Accuracy: 0.9489

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: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.8898 0.9994 877 0.3490 0.8834
0.8457 2.0 1755 0.2191 0.9224
0.7238 2.9994 2632 0.2113 0.9263
0.6685 4.0 3510 0.1838 0.9348
0.6236 4.9994 4387 0.2217 0.9205
0.6011 6.0 5265 0.1732 0.9386
0.6129 6.9994 6142 0.1582 0.9419
0.5606 8.0 7020 0.1478 0.9465
0.5136 8.9994 7897 0.1488 0.9458
0.4659 9.9943 8770 0.1417 0.9489

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1