Commit ·
b0175d0
1
Parent(s): 4b0795c
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_F03_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_F03_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: 0.0490
|
| 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 | 248 | 1.0015 |
|
| 49 |
+
| No log | 2.0 | 496 | 0.3499 |
|
| 50 |
+
| 2.4465 | 3.0 | 744 | 0.1456 |
|
| 51 |
+
| 2.4465 | 4.0 | 992 | 0.0854 |
|
| 52 |
+
| 0.1986 | 5.0 | 1240 | 0.0689 |
|
| 53 |
+
| 0.1986 | 6.0 | 1488 | 0.0619 |
|
| 54 |
+
| 0.0578 | 7.0 | 1736 | 0.0571 |
|
| 55 |
+
| 0.0578 | 8.0 | 1984 | 0.0525 |
|
| 56 |
+
| 0.0269 | 9.0 | 2232 | 0.0524 |
|
| 57 |
+
| 0.0269 | 10.0 | 2480 | 0.0517 |
|
| 58 |
+
| 0.0172 | 11.0 | 2728 | 0.0498 |
|
| 59 |
+
| 0.0172 | 12.0 | 2976 | 0.0488 |
|
| 60 |
+
| 0.0113 | 13.0 | 3224 | 0.0500 |
|
| 61 |
+
| 0.0113 | 14.0 | 3472 | 0.0493 |
|
| 62 |
+
| 0.0088 | 15.0 | 3720 | 0.0496 |
|
| 63 |
+
| 0.0088 | 16.0 | 3968 | 0.0495 |
|
| 64 |
+
| 0.0077 | 17.0 | 4216 | 0.0477 |
|
| 65 |
+
| 0.0077 | 18.0 | 4464 | 0.0489 |
|
| 66 |
+
| 0.0066 | 19.0 | 4712 | 0.0476 |
|
| 67 |
+
| 0.0066 | 20.0 | 4960 | 0.0489 |
|
| 68 |
+
| 0.0064 | 21.0 | 5208 | 0.0486 |
|
| 69 |
+
| 0.0064 | 22.0 | 5456 | 0.0494 |
|
| 70 |
+
| 0.0063 | 23.0 | 5704 | 0.0494 |
|
| 71 |
+
| 0.0063 | 24.0 | 5952 | 0.0497 |
|
| 72 |
+
| 0.004 | 25.0 | 6200 | 0.0495 |
|
| 73 |
+
| 0.004 | 26.0 | 6448 | 0.0493 |
|
| 74 |
+
| 0.0045 | 27.0 | 6696 | 0.0491 |
|
| 75 |
+
| 0.0045 | 28.0 | 6944 | 0.0490 |
|
| 76 |
+
| 0.0039 | 29.0 | 7192 | 0.0490 |
|
| 77 |
+
| 0.0039 | 30.0 | 7440 | 0.0490 |
|
| 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
|