patrickvonplaten commited on
Commit
aee6ef9
1 Parent(s): 80516d2

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -42
README.md CHANGED
@@ -2,24 +2,9 @@
2
  license: mit
3
  tags:
4
  - generated_from_trainer
5
- datasets:
6
- - amazon_reviews_multi
7
- metrics:
8
- - accuracy
9
  model-index:
10
  - name: deberta_v3_amazon_reviews
11
- results:
12
- - task:
13
- name: Text Classification
14
- type: text-classification
15
- dataset:
16
- name: amazon_reviews_multi
17
- type: amazon_reviews_multi
18
- args: en
19
- metrics:
20
- - name: Accuracy
21
- type: accuracy
22
- value: 0.61
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -27,10 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
27
 
28
  # deberta_v3_amazon_reviews
29
 
30
- This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the amazon_reviews_multi dataset.
31
- It achieves the following results on the evaluation set:
32
- - Loss: 0.9723
33
- - Accuracy: 0.61
34
 
35
  ## Model description
36
 
@@ -56,28 +38,7 @@ The following hyperparameters were used during training:
56
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
  - lr_scheduler_type: linear
58
  - lr_scheduler_warmup_steps: 200
59
- - num_epochs: 3
60
-
61
- ### Training results
62
-
63
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
64
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|
65
- | 0.9339 | 0.2 | 5000 | 0.9879 | 0.5876 |
66
- | 0.9386 | 0.4 | 10000 | 0.9408 | 0.5992 |
67
- | 0.9127 | 0.6 | 15000 | 0.9118 | 0.6004 |
68
- | 0.8997 | 0.8 | 20000 | 0.9192 | 0.607 |
69
- | 0.8853 | 1.0 | 25000 | 0.9167 | 0.6018 |
70
- | 0.8159 | 1.2 | 30000 | 0.9364 | 0.6064 |
71
- | 0.8367 | 1.4 | 35000 | 0.9215 | 0.6174 |
72
- | 0.8322 | 1.6 | 40000 | 0.9076 | 0.6108 |
73
- | 0.8142 | 1.8 | 45000 | 0.9305 | 0.6148 |
74
- | 0.8139 | 2.0 | 50000 | 0.9394 | 0.6092 |
75
- | 0.7279 | 2.2 | 55000 | 0.9868 | 0.605 |
76
- | 0.715 | 2.4 | 60000 | 0.9865 | 0.6072 |
77
- | 0.7515 | 2.6 | 65000 | 0.9783 | 0.606 |
78
- | 0.7363 | 2.8 | 70000 | 0.9765 | 0.6096 |
79
- | 0.7405 | 3.0 | 75000 | 0.9723 | 0.61 |
80
-
81
 
82
  ### Framework versions
83
 
 
2
  license: mit
3
  tags:
4
  - generated_from_trainer
 
 
 
 
5
  model-index:
6
  - name: deberta_v3_amazon_reviews
7
+ results: []
 
 
 
 
 
 
 
 
 
 
 
8
  ---
9
 
10
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
12
 
13
  # deberta_v3_amazon_reviews
14
 
15
+ This model is a fine-tuned version of [patrickvonplaten/deberta_v3_amazon_reviews](https://huggingface.co/patrickvonplaten/deberta_v3_amazon_reviews) on an unknown dataset.
 
 
 
16
 
17
  ## Model description
18
 
 
38
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
39
  - lr_scheduler_type: linear
40
  - lr_scheduler_warmup_steps: 200
41
+ - num_epochs: 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
 
43
  ### Framework versions
44