git-base-cartoon / README.md
minwook's picture
Model save
667d66e verified
|
raw
history blame
1.7 kB
metadata
license: mit
base_model: microsoft/git-base
tags:
  - generated_from_trainer
model-index:
  - name: git-base-cartoon
    results: []

git-base-cartoon

This model is a fine-tuned version of microsoft/git-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0646
  • Bleu Score: 0.0501

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu Score
7.4395 1.7544 50 4.7486 0.0011
2.8193 3.5088 100 0.9704 0.0094
0.4044 5.2632 150 0.1138 0.0588
0.0733 7.0175 200 0.0661 0.0438
0.0434 8.7719 250 0.0646 0.0501

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1