output / README.md
hadrakey's picture
Pushing tokenizer and training artifacts
e951a75 verified
metadata
base_model: microsoft/trocr-large-handwritten
library_name: peft
metrics:
  - wer
tags:
  - generated_from_trainer
model-index:
  - name: output
    results: []

output

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

  • Loss: 2.2610
  • Wer: 0.5593

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: 0.0001
  • 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: cosine
  • training_steps: 1000

Training results

Training Loss Epoch Step Validation Loss Wer
3.0289 0.2561 500 2.4179 0.5862
2.7336 0.5122 1000 2.2610 0.5593

Framework versions

  • PEFT 0.11.1
  • Transformers 4.44.2
  • Pytorch 2.5.1+cu124
  • Datasets 2.20.0
  • Tokenizers 0.19.1