bvandy commited on
Commit
9106de6
1 Parent(s): cf2fb95

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +82 -0
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - tweet_eval
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ model-index:
11
+ - name: bert-emotion
12
+ results:
13
+ - task:
14
+ name: Text Classification
15
+ type: text-classification
16
+ dataset:
17
+ name: tweet_eval
18
+ type: tweet_eval
19
+ config: emotion
20
+ split: train
21
+ args: emotion
22
+ metrics:
23
+ - name: Precision
24
+ type: precision
25
+ value: 0.6872092440165337
26
+ - name: Recall
27
+ type: recall
28
+ value: 0.6954893287385614
29
+ ---
30
+
31
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
32
+ should probably proofread and complete it, then remove this comment. -->
33
+
34
+ # bert-emotion
35
+
36
+ This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the tweet_eval dataset.
37
+ It achieves the following results on the evaluation set:
38
+ - Loss: 1.2767
39
+ - Precision: 0.6872
40
+ - Recall: 0.6955
41
+ - Fscore: 0.6906
42
+
43
+ ## Model description
44
+
45
+ More information needed
46
+
47
+ ## Intended uses & limitations
48
+
49
+ More information needed
50
+
51
+ ## Training and evaluation data
52
+
53
+ More information needed
54
+
55
+ ## Training procedure
56
+
57
+ ### Training hyperparameters
58
+
59
+ The following hyperparameters were used during training:
60
+ - learning_rate: 5e-05
61
+ - train_batch_size: 4
62
+ - eval_batch_size: 4
63
+ - seed: 42
64
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
65
+ - lr_scheduler_type: linear
66
+ - num_epochs: 3
67
+
68
+ ### Training results
69
+
70
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Fscore |
71
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
72
+ | 0.8803 | 1.0 | 815 | 0.7232 | 0.7435 | 0.6516 | 0.6775 |
73
+ | 0.549 | 2.0 | 1630 | 0.9588 | 0.7380 | 0.6640 | 0.6860 |
74
+ | 0.2732 | 3.0 | 2445 | 1.2767 | 0.6872 | 0.6955 | 0.6906 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.25.1
80
+ - Pytorch 1.13.0+cu116
81
+ - Datasets 2.8.0
82
+ - Tokenizers 0.13.2