lewtun HF Staff commited on
Commit
69bd8c6
·
1 Parent(s): 490e4b6

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +74 -0
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: distilbert-base-uncased__sst2__train-16-5
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # distilbert-base-uncased__sst2__train-16-5
16
+
17
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.6537
20
+ - Accuracy: 0.6332
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 2e-05
40
+ - train_batch_size: 4
41
+ - eval_batch_size: 4
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 50
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 0.6925 | 1.0 | 7 | 0.6966 | 0.2857 |
53
+ | 0.6703 | 2.0 | 14 | 0.7045 | 0.2857 |
54
+ | 0.6404 | 3.0 | 21 | 0.7205 | 0.2857 |
55
+ | 0.555 | 4.0 | 28 | 0.7548 | 0.2857 |
56
+ | 0.5179 | 5.0 | 35 | 0.6745 | 0.5714 |
57
+ | 0.3038 | 6.0 | 42 | 0.7260 | 0.5714 |
58
+ | 0.2089 | 7.0 | 49 | 0.8016 | 0.5714 |
59
+ | 0.1303 | 8.0 | 56 | 0.8202 | 0.5714 |
60
+ | 0.0899 | 9.0 | 63 | 0.9966 | 0.5714 |
61
+ | 0.0552 | 10.0 | 70 | 1.1887 | 0.5714 |
62
+ | 0.0333 | 11.0 | 77 | 1.2163 | 0.5714 |
63
+ | 0.0169 | 12.0 | 84 | 1.2874 | 0.5714 |
64
+ | 0.0136 | 13.0 | 91 | 1.3598 | 0.5714 |
65
+ | 0.0103 | 14.0 | 98 | 1.4237 | 0.5714 |
66
+ | 0.0089 | 15.0 | 105 | 1.4758 | 0.5714 |
67
+
68
+
69
+ ### Framework versions
70
+
71
+ - Transformers 4.15.0
72
+ - Pytorch 1.10.2+cu102
73
+ - Datasets 1.18.2
74
+ - Tokenizers 0.10.3