Hugging Face's logo

Mozilla
/
distilvit

Image-to-Text
Transformers
ONNX
Safetensors
vision-encoder-decoder
image-captioning
Eval Results
Inference Endpoints
Model card Files Community
1
distilvit / README.md
tarekziade's picture
tarekziade
Model save
6fafb82 verified
preview code
|
raw history blame
No virus
1.77 kB
metadata
license: apache-2.0
base_model: mozilla/distilvit
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: distilvit
    results: []

distilvit

This model is a fine-tuned version of mozilla/distilvit on an unknown dataset. It achieves the following results on the evaluation set:

  • Gen Len: 10.6487
  • Loss: 0.1739
  • Meteor: 0.4120
  • Rouge1: 50.0916
  • Rouge2: 24.7223
  • Rougel: 46.9416
  • Rougelsum: 46.9372

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: 100
  • eval_batch_size: 100
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1

Training results

Training Loss Epoch Step Gen Len Validation Loss Meteor Rouge1 Rouge2 Rougel Rougelsum
No log 0.3891 100 10.4163 0.1764 0.4117 50.0198 24.6331 46.9071 46.8907
No log 0.7782 200 10.6487 0.1739 0.4120 50.0916 24.7223 46.9416 46.9372

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1