Update readme with accuracy
Browse files
README.md
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- emotion
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: xtremedistil-emotion
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Text Classification
|
| 14 |
+
type: text-classification
|
| 15 |
+
dataset:
|
| 16 |
+
name: emotion
|
| 17 |
+
type: emotion
|
| 18 |
+
args: default
|
| 19 |
+
metrics:
|
| 20 |
+
- name: Accuracy
|
| 21 |
+
type: accuracy
|
| 22 |
+
value: 0.9265
|
| 23 |
+
---
|
| 24 |
+
|
| 25 |
+
# xtremedistil-emotion
|
| 26 |
+
This model is a fine-tuned version of [microsoft/xtremedistil-l6-h256-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h256-uncased) on the emotion dataset.
|
| 27 |
+
It achieves the following results on the evaluation set:
|
| 28 |
+
- Accuracy: 0.9265
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
### Training hyperparameters
|
| 32 |
+
The following hyperparameters were used during training:
|
| 33 |
+
- learning_rate: 3e-05
|
| 34 |
+
- train_batch_size: 128
|
| 35 |
+
- eval_batch_size: 8
|
| 36 |
+
- seed: 42
|
| 37 |
+
- num_epochs: 24
|
| 38 |
+
|
| 39 |
+
### Training results
|
| 40 |
+
<pre>
|
| 41 |
+
Epoch Training Loss Validation Loss Accuracy
|
| 42 |
+
1 No log 1.238589 0.609000
|
| 43 |
+
2 No log 0.934423 0.714000
|
| 44 |
+
3 No log 0.768701 0.742000
|
| 45 |
+
4 1.074800 0.638208 0.805500
|
| 46 |
+
5 1.074800 0.551363 0.851500
|
| 47 |
+
6 1.074800 0.476291 0.875500
|
| 48 |
+
7 1.074800 0.427313 0.883500
|
| 49 |
+
8 0.531500 0.392633 0.886000
|
| 50 |
+
9 0.531500 0.357979 0.892000
|
| 51 |
+
10 0.531500 0.330304 0.899500
|
| 52 |
+
11 0.531500 0.304529 0.907000
|
| 53 |
+
12 0.337200 0.287447 0.918000
|
| 54 |
+
13 0.337200 0.277067 0.921000
|
| 55 |
+
14 0.337200 0.259483 0.921000
|
| 56 |
+
15 0.337200 0.257564 0.916500
|
| 57 |
+
16 0.246200 0.241970 0.919500
|
| 58 |
+
17 0.246200 0.241537 0.921500
|
| 59 |
+
18 0.246200 0.235705 0.924500
|
| 60 |
+
19 0.246200 0.237325 0.920500
|
| 61 |
+
20 0.201400 0.229699 0.923500
|
| 62 |
+
21 0.201400 0.227426 0.923000
|
| 63 |
+
22 0.201400 0.228554 0.924000
|
| 64 |
+
23 0.201400 0.226941 0.925500
|
| 65 |
+
24 0.184300 0.225816 0.926500
|
| 66 |
+
</pre>
|