eugenecamus commited on
Commit
bd81463
1 Parent(s): 1764fd5

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +77 -0
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imdb
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: distilbert-imdb-demo
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: imdb
17
+ type: imdb
18
+ args: plain_text
19
+ metrics:
20
+ - name: Accuracy
21
+ type: accuracy
22
+ value: 0.504
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-imdb-demo
29
+
30
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 0.6931
33
+ - Accuracy: 0.504
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: 0.002
53
+ - train_batch_size: 8
54
+ - eval_batch_size: 8
55
+ - seed: 1337
56
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
+ - lr_scheduler_type: cosine
58
+ - lr_scheduler_warmup_ratio: 0.1
59
+ - num_epochs: 5.0
60
+
61
+ ### Training results
62
+
63
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
64
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
65
+ | 0.6924 | 1.0 | 2657 | 0.6922 | 0.504 |
66
+ | 0.6919 | 2.0 | 5314 | 0.6920 | 0.504 |
67
+ | 0.7404 | 3.0 | 7971 | 0.7076 | 0.496 |
68
+ | 0.6939 | 4.0 | 10628 | 0.6932 | 0.496 |
69
+ | 0.6935 | 5.0 | 13285 | 0.6931 | 0.504 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.19.2
75
+ - Pytorch 1.11.0+cu102
76
+ - Datasets 2.2.1
77
+ - Tokenizers 0.12.1