Edit model card

git-base-test3

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

  • eval_loss: 0.0608
  • eval_wer_score: 21.6785
  • eval_rouge_score: 0.0467
  • eval_bert_score: 0.7569
  • eval_runtime: 34.8187
  • eval_samples_per_second: 2.901
  • eval_steps_per_second: 0.373
  • epoch: 41.11
  • step: 50500

CIDEr-D: 106.96

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: 4
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 50
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.28.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.13.1
  • Tokenizers 0.13.3
Downloads last month
1