Commit
·
41746cb
1
Parent(s):
b9ebc98
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: spell_correction_M01_LM
|
| 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 |
+
# spell_correction_M01_LM
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.0170
|
| 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: 1e-05
|
| 37 |
+
- train_batch_size: 16
|
| 38 |
+
- eval_batch_size: 16
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 30
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
+
| No log | 1.0 | 264 | 0.3516 |
|
| 49 |
+
| 1.8892 | 2.0 | 528 | 0.0561 |
|
| 50 |
+
| 1.8892 | 3.0 | 792 | 0.0324 |
|
| 51 |
+
| 0.0396 | 4.0 | 1056 | 0.0264 |
|
| 52 |
+
| 0.0396 | 5.0 | 1320 | 0.0238 |
|
| 53 |
+
| 0.0163 | 6.0 | 1584 | 0.0212 |
|
| 54 |
+
| 0.0163 | 7.0 | 1848 | 0.0212 |
|
| 55 |
+
| 0.0081 | 8.0 | 2112 | 0.0194 |
|
| 56 |
+
| 0.0081 | 9.0 | 2376 | 0.0206 |
|
| 57 |
+
| 0.0061 | 10.0 | 2640 | 0.0195 |
|
| 58 |
+
| 0.0061 | 11.0 | 2904 | 0.0182 |
|
| 59 |
+
| 0.004 | 12.0 | 3168 | 0.0182 |
|
| 60 |
+
| 0.004 | 13.0 | 3432 | 0.0180 |
|
| 61 |
+
| 0.0042 | 14.0 | 3696 | 0.0172 |
|
| 62 |
+
| 0.0042 | 15.0 | 3960 | 0.0183 |
|
| 63 |
+
| 0.0026 | 16.0 | 4224 | 0.0184 |
|
| 64 |
+
| 0.0026 | 17.0 | 4488 | 0.0170 |
|
| 65 |
+
| 0.0034 | 18.0 | 4752 | 0.0169 |
|
| 66 |
+
| 0.0023 | 19.0 | 5016 | 0.0169 |
|
| 67 |
+
| 0.0023 | 20.0 | 5280 | 0.0167 |
|
| 68 |
+
| 0.0029 | 21.0 | 5544 | 0.0182 |
|
| 69 |
+
| 0.0029 | 22.0 | 5808 | 0.0178 |
|
| 70 |
+
| 0.0019 | 23.0 | 6072 | 0.0188 |
|
| 71 |
+
| 0.0019 | 24.0 | 6336 | 0.0179 |
|
| 72 |
+
| 0.0018 | 25.0 | 6600 | 0.0177 |
|
| 73 |
+
| 0.0018 | 26.0 | 6864 | 0.0171 |
|
| 74 |
+
| 0.0023 | 27.0 | 7128 | 0.0172 |
|
| 75 |
+
| 0.0023 | 28.0 | 7392 | 0.0171 |
|
| 76 |
+
| 0.0021 | 29.0 | 7656 | 0.0169 |
|
| 77 |
+
| 0.0021 | 30.0 | 7920 | 0.0170 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- Transformers 4.28.0
|
| 83 |
+
- Pytorch 1.12.1+cu102
|
| 84 |
+
- Datasets 2.13.1
|
| 85 |
+
- Tokenizers 0.13.3
|