macildur commited on
Commit
d1ff97d
1 Parent(s): 003b7d7

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +90 -0
README.md ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - sentiment140
7
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ - precision
11
+ - recall
12
+ model-index:
13
+ - name: distilbert-base-uncasedv1-finetuned-twitter-sentiment
14
+ results:
15
+ - task:
16
+ name: Text Classification
17
+ type: text-classification
18
+ dataset:
19
+ name: sentiment140
20
+ type: sentiment140
21
+ config: sentiment140
22
+ split: train
23
+ args: sentiment140
24
+ metrics:
25
+ - name: Accuracy
26
+ type: accuracy
27
+ value: 0.82475
28
+ - name: F1
29
+ type: f1
30
+ value: 0.8246033480256058
31
+ - name: Precision
32
+ type: precision
33
+ value: 0.825087861584212
34
+ - name: Recall
35
+ type: recall
36
+ value: 0.8016811137378513
37
+ ---
38
+
39
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
40
+ should probably proofread and complete it, then remove this comment. -->
41
+
42
+ # distilbert-base-uncasedv1-finetuned-twitter-sentiment
43
+
44
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the sentiment140 dataset.
45
+ It achieves the following results on the evaluation set:
46
+ - Loss: 0.3985
47
+ - Accuracy: 0.8247
48
+ - F1: 0.8246
49
+ - Precision: 0.8251
50
+ - Recall: 0.8017
51
+
52
+ ## Model description
53
+
54
+ More information needed
55
+
56
+ ## Intended uses & limitations
57
+
58
+ More information needed
59
+
60
+ ## Training and evaluation data
61
+
62
+ More information needed
63
+
64
+ ## Training procedure
65
+
66
+ ### Training hyperparameters
67
+
68
+ The following hyperparameters were used during training:
69
+ - learning_rate: 2e-05
70
+ - train_batch_size: 64
71
+ - eval_batch_size: 64
72
+ - seed: 42
73
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
+ - lr_scheduler_type: linear
75
+ - num_epochs: 2
76
+
77
+ ### Training results
78
+
79
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
80
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
81
+ | No log | 1.0 | 500 | 0.4049 | 0.8181 | 0.8178 | 0.8236 | 0.7862 |
82
+ | No log | 2.0 | 1000 | 0.3985 | 0.8247 | 0.8246 | 0.8251 | 0.8017 |
83
+
84
+
85
+ ### Framework versions
86
+
87
+ - Transformers 4.22.2
88
+ - Pytorch 1.12.1+cu113
89
+ - Datasets 2.5.2
90
+ - Tokenizers 0.12.1