Hugging Face's logo

motheecreator
/
ViT-GPT2-Image-Captioning

Image-to-Text
Transformers
Safetensors
vision-encoder-decoder
image-text-to-text
Generated from Trainer
Inference Endpoints
Model card Files Community
ViT-GPT2-Image-Captioning / README.md
motheecreator's picture
motheecreator
Update README.md
73fc76f verified
preview code
|
raw
history blame contribute delete
1.88 kB
metadata
library_name: transformers
base_model: motheecreator/ViT-GPT2-Image_Captioning_model
tags:
  - generated_from_trainer
  - image-to-text
metrics:
  - bleu
model-index:
  - name: ViT-GPT2
    results: []

ViT-GPT2

This model is a fine-tuned version of motheecreator/ViT-GPT2-Image_Captioning_model on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.125337
  • Rouge2 Precision: None
  • Rouge2 Recall: None
  • Rouge2 Fmeasure: 0.155
  • Bleu: 9.7054

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: 8
  • total_train_batch_size: 256
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge2 Precision Rouge2 Recall Rouge2 Fmeasure Bleu
2.1537 0.9993 1171 2.13666 None None 0.1531 9.4673
2.0434 1.9985 2342 2.125337 None None 0.155 9.7054

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0
  • Datasets 3.0.0
  • Tokenizers 0.19.1