Commit
·
502a4b0
1
Parent(s):
d38fd8a
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: sinhala-book-captioning-repo
|
| 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 |
+
# sinhala-book-captioning-repo
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.0053
|
| 18 |
+
- Wer Score: 1.3218
|
| 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: 1
|
| 39 |
+
- eval_batch_size: 1
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 2
|
| 42 |
+
- total_train_batch_size: 2
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 5
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|
|
| 51 |
+
| 5.2519 | 0.3 | 50 | 4.5638 | 1.0 |
|
| 52 |
+
| 0.6662 | 0.6 | 100 | 0.3785 | 1.0 |
|
| 53 |
+
| 0.0214 | 0.9 | 150 | 0.0154 | 0.8161 |
|
| 54 |
+
| 0.0123 | 1.2 | 200 | 0.0104 | 0.7356 |
|
| 55 |
+
| 0.0077 | 1.5 | 250 | 0.0095 | 0.7126 |
|
| 56 |
+
| 0.0091 | 1.8 | 300 | 0.0080 | 0.6897 |
|
| 57 |
+
| 0.009 | 2.1 | 350 | 0.0076 | 0.6897 |
|
| 58 |
+
| 0.008 | 2.4 | 400 | 0.0076 | 0.7356 |
|
| 59 |
+
| 0.0066 | 2.69 | 450 | 0.0071 | 0.6667 |
|
| 60 |
+
| 0.0065 | 2.99 | 500 | 0.0068 | 0.6437 |
|
| 61 |
+
| 0.0068 | 3.29 | 550 | 0.0063 | 0.6207 |
|
| 62 |
+
| 0.0066 | 3.59 | 600 | 0.0063 | 5.1494 |
|
| 63 |
+
| 0.0063 | 3.89 | 650 | 0.0061 | 0.6322 |
|
| 64 |
+
| 0.0063 | 4.19 | 700 | 0.0055 | 0.5287 |
|
| 65 |
+
| 0.007 | 4.49 | 750 | 0.0053 | 0.5172 |
|
| 66 |
+
| 0.0054 | 4.79 | 800 | 0.0053 | 1.3218 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- Transformers 4.30.2
|
| 72 |
+
- Pytorch 1.13.0
|
| 73 |
+
- Datasets 2.11.0
|
| 74 |
+
- Tokenizers 0.13.0
|