update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- clinc_oos
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: distilbert-base-uncased-distilled-clinc
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Text Classification
|
14 |
+
type: text-classification
|
15 |
+
dataset:
|
16 |
+
name: clinc_oos
|
17 |
+
type: clinc_oos
|
18 |
+
args: plus
|
19 |
+
metrics:
|
20 |
+
- name: Accuracy
|
21 |
+
type: accuracy
|
22 |
+
value: 0.9309677419354838
|
23 |
+
---
|
24 |
+
|
25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
26 |
+
should probably proofread and complete it, then remove this comment. -->
|
27 |
+
|
28 |
+
# distilbert-base-uncased-distilled-clinc
|
29 |
+
|
30 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
|
31 |
+
It achieves the following results on the evaluation set:
|
32 |
+
- Loss: 0.0389
|
33 |
+
- Accuracy: 0.9310
|
34 |
+
|
35 |
+
## Model description
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Intended uses & limitations
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training and evaluation data
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Training procedure
|
48 |
+
|
49 |
+
### Training hyperparameters
|
50 |
+
|
51 |
+
The following hyperparameters were used during training:
|
52 |
+
- learning_rate: 2e-05
|
53 |
+
- train_batch_size: 48
|
54 |
+
- eval_batch_size: 48
|
55 |
+
- seed: 42
|
56 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
57 |
+
- lr_scheduler_type: linear
|
58 |
+
- num_epochs: 10
|
59 |
+
|
60 |
+
### Training results
|
61 |
+
|
62 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
63 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
64 |
+
| 0.6206 | 1.0 | 318 | 0.3251 | 0.6610 |
|
65 |
+
| 0.2571 | 2.0 | 636 | 0.1366 | 0.8584 |
|
66 |
+
| 0.1392 | 3.0 | 954 | 0.0813 | 0.9081 |
|
67 |
+
| 0.0967 | 4.0 | 1272 | 0.0598 | 0.9152 |
|
68 |
+
| 0.0779 | 5.0 | 1590 | 0.0503 | 0.9229 |
|
69 |
+
| 0.0675 | 6.0 | 1908 | 0.0451 | 0.9271 |
|
70 |
+
| 0.0615 | 7.0 | 2226 | 0.0425 | 0.9326 |
|
71 |
+
| 0.058 | 8.0 | 2544 | 0.0403 | 0.9316 |
|
72 |
+
| 0.0557 | 9.0 | 2862 | 0.0393 | 0.9306 |
|
73 |
+
| 0.0544 | 10.0 | 3180 | 0.0389 | 0.9310 |
|
74 |
+
|
75 |
+
|
76 |
+
### Framework versions
|
77 |
+
|
78 |
+
- Transformers 4.19.3
|
79 |
+
- Pytorch 1.11.0+cu113
|
80 |
+
- Datasets 2.2.2
|
81 |
+
- Tokenizers 0.12.1
|