---
base_model: microsoft/trocr-base-stage1
tags:
- generated_from_trainer
model-index:
- name: TrOCR_0216_All_data
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# TrOCR_0216_All_data

This model is a fine-tuned version of [microsoft/trocr-base-stage1](https://huggingface.co/microsoft/trocr-base-stage1) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4491
- Cer: 0.3676

## 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
- 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 | Cer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.8013        | 0.05  | 500  | 0.8621          | 0.1267 |
| 1.0882        | 0.09  | 1000 | 0.8068          | 0.1353 |
| 0.5746        | 0.14  | 1500 | 0.7315          | 0.0899 |
| 0.5403        | 0.18  | 2000 | 0.7111          | 0.2276 |
| 1.2505        | 0.23  | 2500 | 0.6538          | 0.1042 |
| 0.7987        | 0.27  | 3000 | 0.6687          | 0.1228 |
| 0.3878        | 0.32  | 3500 | 0.6745          | 0.0879 |
| 0.4788        | 0.36  | 4000 | 0.7084          | 0.0781 |
| 0.449         | 0.41  | 4500 | 1.4491          | 0.3676 |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.13.0
- Tokenizers 0.15.0