git-base-pokemon / README.md
gaodrew's picture
update model card README.md
cc9013a
metadata
license: mit
base_model: microsoft/git-base
tags:
  - generated_from_trainer
model-index:
  - name: git-base-pokemon
    results: []

git-base-pokemon

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: 0.0348
  • Wer Score: 2.7147

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: 2
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss Wer Score
7.3601 4.17 50 4.5925 21.8560
2.4331 8.33 100 0.4978 15.2153
0.1504 12.5 150 0.0323 1.2062
0.0142 16.67 200 0.0288 3.0791
0.0039 20.83 250 0.0314 2.3619
0.0021 25.0 300 0.0327 2.6537
0.0016 29.17 350 0.0333 3.2049
0.0014 33.33 400 0.0344 2.9403
0.0012 37.5 450 0.0344 2.9624
0.0011 41.67 500 0.0345 2.8106
0.0011 45.83 550 0.0346 2.7393
0.0011 50.0 600 0.0348 2.7147

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.3
  • Tokenizers 0.13.3