Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: TrOCR-SIN(DeiT)
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# TrOCR-SIN(DeiT)
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 0.4335
|
| 17 |
+
- Cer: 0.1445
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 5e-05
|
| 37 |
+
- train_batch_size: 32
|
| 38 |
+
- eval_batch_size: 32
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- training_steps: 75000
|
| 43 |
+
- mixed_precision_training: Native AMP
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Cer | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:-----:|:------:|:---------------:|
|
| 49 |
+
| 1.3019 | 1.78 | 5000 | 0.6416 | 1.7769 |
|
| 50 |
+
| 0.6387 | 3.55 | 10000 | 0.4048 | 0.8457 |
|
| 51 |
+
| 0.3402 | 5.33 | 15000 | 0.2808 | 0.6898 |
|
| 52 |
+
| 0.1332 | 7.11 | 20000 | 0.2377 | 0.5765 |
|
| 53 |
+
| 0.1141 | 8.89 | 25000 | 0.2223 | 0.4460 |
|
| 54 |
+
| 0.0481 | 10.66 | 30000 | 0.1868 | 0.4128 |
|
| 55 |
+
| 0.0391 | 12.44 | 35000 | 0.1563 | 0.4172 |
|
| 56 |
+
| 0.0357 | 14.22 | 40000 | 0.1981 | 0.4756 |
|
| 57 |
+
| 0.0215 | 16.0 | 45000 | 0.1983 | 0.5838 |
|
| 58 |
+
| 0.0129 | 17.77 | 50000 | 0.1757 | 0.5511 |
|
| 59 |
+
| 0.0087 | 19.55 | 55000 | 0.1699 | 0.5568 |
|
| 60 |
+
| 0.003 | 21.33 | 60000 | 0.1648 | 0.4532 |
|
| 61 |
+
| 0.0042 | 23.11 | 65000 | 0.1582 | 0.4650 |
|
| 62 |
+
| 0.0066 | 24.88 | 70000 | 0.1654 | 0.4740 |
|
| 63 |
+
| 0.0014 | 26.66 | 75000 | 0.1448 | 0.4337 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
### Framework versions
|
| 67 |
+
|
| 68 |
+
- Transformers 4.35.2
|
| 69 |
+
- Pytorch 2.1.0+cu121
|
| 70 |
+
- Datasets 2.18.0
|
| 71 |
+
- Tokenizers 0.15.1
|