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: pkemon_cap_v0
|
| 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 |
+
# pkemon_cap_v0
|
| 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: 7.6491
|
| 18 |
+
- Wer Score: 127.2727
|
| 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: 2
|
| 39 |
+
- eval_batch_size: 2
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 2
|
| 42 |
+
- total_train_batch_size: 4
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 3
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|
|
| 51 |
+
| 11.2497 | 0.17 | 2 | 10.0191 | 96.6364 |
|
| 52 |
+
| 9.9157 | 0.35 | 4 | 9.5544 | 111.1818 |
|
| 53 |
+
| 9.4907 | 0.52 | 6 | 9.1167 | 143.5909 |
|
| 54 |
+
| 9.0975 | 0.7 | 8 | 8.8422 | 154.5455 |
|
| 55 |
+
| 8.8568 | 0.87 | 10 | 8.6143 | 144.6364 |
|
| 56 |
+
| 8.6299 | 1.04 | 12 | 8.4336 | 118.7727 |
|
| 57 |
+
| 8.4659 | 1.22 | 14 | 8.2808 | 112.4091 |
|
| 58 |
+
| 8.3233 | 1.39 | 16 | 8.1538 | 124.3636 |
|
| 59 |
+
| 8.2213 | 1.57 | 18 | 8.0420 | 122.8636 |
|
| 60 |
+
| 8.0876 | 1.74 | 20 | 7.9463 | 124.5 |
|
| 61 |
+
| 7.9863 | 1.91 | 22 | 7.8647 | 153.9545 |
|
| 62 |
+
| 7.9169 | 2.09 | 24 | 7.7966 | 156.0 |
|
| 63 |
+
| 7.8652 | 2.26 | 26 | 7.7400 | 155.5455 |
|
| 64 |
+
| 7.8245 | 2.43 | 28 | 7.6962 | 142.0909 |
|
| 65 |
+
| 7.7512 | 2.61 | 30 | 7.6659 | 129.9545 |
|
| 66 |
+
| 7.7344 | 2.78 | 32 | 7.6491 | 127.2727 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- Transformers 4.28.0
|
| 72 |
+
- Pytorch 2.0.0+cu118
|
| 73 |
+
- Datasets 2.12.0
|
| 74 |
+
- Tokenizers 0.13.3
|