update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: bart-base-detox
|
| 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 |
+
# bart-base-detox
|
| 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: 0.1819
|
| 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: 4
|
| 38 |
+
- eval_batch_size: 8
|
| 39 |
+
- seed: 42
|
| 40 |
+
- gradient_accumulation_steps: 16
|
| 41 |
+
- total_train_batch_size: 64
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 20
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
+
| 0.5633 | 1.0 | 135 | 0.2524 |
|
| 51 |
+
| 0.2589 | 2.0 | 270 | 0.2193 |
|
| 52 |
+
| 0.2307 | 3.0 | 405 | 0.1993 |
|
| 53 |
+
| 0.2171 | 4.0 | 540 | 0.2002 |
|
| 54 |
+
| 0.2027 | 5.0 | 675 | 0.1937 |
|
| 55 |
+
| 0.1946 | 6.0 | 810 | 0.1972 |
|
| 56 |
+
| 0.1874 | 7.0 | 945 | 0.1917 |
|
| 57 |
+
| 0.1853 | 8.0 | 1080 | 0.1868 |
|
| 58 |
+
| 0.1811 | 9.0 | 1215 | 0.1890 |
|
| 59 |
+
| 0.1776 | 10.0 | 1350 | 0.1871 |
|
| 60 |
+
| 0.1798 | 11.0 | 1485 | 0.1858 |
|
| 61 |
+
| 0.1745 | 12.0 | 1620 | 0.1820 |
|
| 62 |
+
| 0.1689 | 13.0 | 1755 | 0.1827 |
|
| 63 |
+
| 0.1707 | 14.0 | 1890 | 0.1843 |
|
| 64 |
+
| 0.1658 | 15.0 | 2025 | 0.1834 |
|
| 65 |
+
| 0.1647 | 16.0 | 2160 | 0.1820 |
|
| 66 |
+
| 0.1645 | 17.0 | 2295 | 0.1837 |
|
| 67 |
+
| 0.1633 | 18.0 | 2430 | 0.1814 |
|
| 68 |
+
| 0.1612 | 19.0 | 2565 | 0.1815 |
|
| 69 |
+
| 0.1603 | 20.0 | 2700 | 0.1819 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.16.2
|
| 75 |
+
- Pytorch 1.12.0.dev20220429
|
| 76 |
+
- Datasets 2.1.0
|
| 77 |
+
- Tokenizers 0.10.3
|