Commit
·
e76119b
1
Parent(s):
15ab52c
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_F04_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_F04_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: 0.0242
|
| 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 | 269 | 0.3354 |
|
| 49 |
+
| 1.9104 | 2.0 | 538 | 0.0604 |
|
| 50 |
+
| 1.9104 | 3.0 | 807 | 0.0405 |
|
| 51 |
+
| 0.0433 | 4.0 | 1076 | 0.0337 |
|
| 52 |
+
| 0.0433 | 5.0 | 1345 | 0.0285 |
|
| 53 |
+
| 0.0164 | 6.0 | 1614 | 0.0263 |
|
| 54 |
+
| 0.0164 | 7.0 | 1883 | 0.0268 |
|
| 55 |
+
| 0.0099 | 8.0 | 2152 | 0.0244 |
|
| 56 |
+
| 0.0099 | 9.0 | 2421 | 0.0262 |
|
| 57 |
+
| 0.0065 | 10.0 | 2690 | 0.0264 |
|
| 58 |
+
| 0.0065 | 11.0 | 2959 | 0.0255 |
|
| 59 |
+
| 0.0044 | 12.0 | 3228 | 0.0243 |
|
| 60 |
+
| 0.0044 | 13.0 | 3497 | 0.0262 |
|
| 61 |
+
| 0.0037 | 14.0 | 3766 | 0.0247 |
|
| 62 |
+
| 0.0035 | 15.0 | 4035 | 0.0233 |
|
| 63 |
+
| 0.0035 | 16.0 | 4304 | 0.0230 |
|
| 64 |
+
| 0.0031 | 17.0 | 4573 | 0.0242 |
|
| 65 |
+
| 0.0031 | 18.0 | 4842 | 0.0223 |
|
| 66 |
+
| 0.0029 | 19.0 | 5111 | 0.0226 |
|
| 67 |
+
| 0.0029 | 20.0 | 5380 | 0.0245 |
|
| 68 |
+
| 0.0023 | 21.0 | 5649 | 0.0249 |
|
| 69 |
+
| 0.0023 | 22.0 | 5918 | 0.0244 |
|
| 70 |
+
| 0.0023 | 23.0 | 6187 | 0.0238 |
|
| 71 |
+
| 0.0023 | 24.0 | 6456 | 0.0237 |
|
| 72 |
+
| 0.0025 | 25.0 | 6725 | 0.0242 |
|
| 73 |
+
| 0.0025 | 26.0 | 6994 | 0.0239 |
|
| 74 |
+
| 0.0017 | 27.0 | 7263 | 0.0236 |
|
| 75 |
+
| 0.0018 | 28.0 | 7532 | 0.0242 |
|
| 76 |
+
| 0.0018 | 29.0 | 7801 | 0.0240 |
|
| 77 |
+
| 0.0016 | 30.0 | 8070 | 0.0242 |
|
| 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
|