Hugging Face's logo

ssalvo41
/
git-base-isg_223

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
git
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
git-base-isg_223 / README.md
ssalvo41's picture
ssalvo41
End of training
713f4af verified
preview code
|
raw
history blame contribute delete
1.68 kB
metadata
library_name: transformers
license: mit
base_model: microsoft/git-base
tags:
  - generated_from_trainer
model-index:
  - name: git-base-isg
    results: []

git-base-isg

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

  • Loss: 0.0853
  • Wer Score: 0.6965

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: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Use 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: 40

Training results

Training Loss Epoch Step Validation Loss Wer Score
6.7202 7.1538 50 4.6376 22.2786
2.6302 14.3077 100 1.0906 10.7910
0.4603 21.4615 150 0.1619 12.5323
0.0822 28.6154 200 0.0853 0.6965

Framework versions

  • Transformers 4.47.0
  • Pytorch 2.5.1+cu121
  • Datasets 3.2.0
  • Tokenizers 0.21.0