Model save
Browse files- README.md +71 -0
- generation_config.json +13 -0
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: microsoft/trocr-base-stage1
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: norhand-hcr-beta1
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# norhand-hcr-beta1
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [microsoft/trocr-base-stage1](https://huggingface.co/microsoft/trocr-base-stage1) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 1.4687
|
| 18 |
+
- Cer: 0.0439
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 5e-05
|
| 38 |
+
- train_batch_size: 32
|
| 39 |
+
- eval_batch_size: 1
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- lr_scheduler_warmup_steps: 2000
|
| 44 |
+
- num_epochs: 10
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
| 49 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 50 |
+
| 0.7606 | 0.71 | 5000 | 1.0489 | 0.1266 |
|
| 51 |
+
| 0.5971 | 1.43 | 10000 | 1.2096 | 0.1028 |
|
| 52 |
+
| 0.4448 | 2.14 | 15000 | 1.3738 | 0.0771 |
|
| 53 |
+
| 0.3919 | 2.85 | 20000 | 1.2733 | 0.0670 |
|
| 54 |
+
| 0.2806 | 3.56 | 25000 | 1.3048 | 0.0597 |
|
| 55 |
+
| 0.2055 | 4.28 | 30000 | 1.3568 | 0.0557 |
|
| 56 |
+
| 0.2486 | 4.99 | 35000 | 0.9717 | 0.0527 |
|
| 57 |
+
| 0.1631 | 5.7 | 40000 | 1.3159 | 0.0506 |
|
| 58 |
+
| 0.1159 | 6.41 | 45000 | 1.3730 | 0.0480 |
|
| 59 |
+
| 0.0605 | 7.13 | 50000 | 1.3399 | 0.0469 |
|
| 60 |
+
| 0.0626 | 7.84 | 55000 | 1.3642 | 0.0460 |
|
| 61 |
+
| 0.0532 | 8.55 | 60000 | 1.3870 | 0.0450 |
|
| 62 |
+
| 0.0177 | 9.26 | 65000 | 1.4912 | 0.0439 |
|
| 63 |
+
| 0.0308 | 9.98 | 70000 | 1.4687 | 0.0439 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
### Framework versions
|
| 67 |
+
|
| 68 |
+
- Transformers 4.32.1
|
| 69 |
+
- Pytorch 2.1.1+cu121
|
| 70 |
+
- Datasets 2.15.0
|
| 71 |
+
- Tokenizers 0.13.3
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 0,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"early_stopping": true,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"length_penalty": 2.0,
|
| 7 |
+
"max_length": 128,
|
| 8 |
+
"no_repeat_ngram_size": 3,
|
| 9 |
+
"num_beams": 4,
|
| 10 |
+
"pad_token_id": 1,
|
| 11 |
+
"transformers_version": "4.32.1",
|
| 12 |
+
"use_cache": false
|
| 13 |
+
}
|