milyiyo commited on
Commit
a0f2a25
1 Parent(s): ebc1a8d

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +96 -0
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - amazon_reviews_multi
7
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ - precision
11
+ - recall
12
+ model-index:
13
+ - name: selectra-small-finetuned-amazon-review
14
+ results:
15
+ - task:
16
+ name: Text Classification
17
+ type: text-classification
18
+ dataset:
19
+ name: amazon_reviews_multi
20
+ type: amazon_reviews_multi
21
+ args: es
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.737
26
+ - name: F1
27
+ type: f1
28
+ value: 0.7437773019932409
29
+ - name: Precision
30
+ type: precision
31
+ value: 0.7524857881639091
32
+ - name: Recall
33
+ type: recall
34
+ value: 0.737
35
+ ---
36
+
37
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
38
+ should probably proofread and complete it, then remove this comment. -->
39
+
40
+ # selectra-small-finetuned-amazon-review
41
+
42
+ This model is a fine-tuned version of [Recognai/selectra_small](https://huggingface.co/Recognai/selectra_small) on the amazon_reviews_multi dataset.
43
+ It achieves the following results on the evaluation set:
44
+ - Loss: 0.6279
45
+ - Accuracy: 0.737
46
+ - F1: 0.7438
47
+ - Precision: 0.7525
48
+ - Recall: 0.737
49
+
50
+ ## Model description
51
+
52
+ More information needed
53
+
54
+ ## Intended uses & limitations
55
+
56
+ More information needed
57
+
58
+ ## Training and evaluation data
59
+
60
+ More information needed
61
+
62
+ ## Training procedure
63
+
64
+ ### Training hyperparameters
65
+
66
+ The following hyperparameters were used during training:
67
+ - learning_rate: 2e-05
68
+ - train_batch_size: 16
69
+ - eval_batch_size: 16
70
+ - seed: 42
71
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
72
+ - lr_scheduler_type: linear
73
+ - num_epochs: 5
74
+
75
+ ### Training results
76
+
77
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
78
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
79
+ | No log | 0.5 | 500 | 0.7041 | 0.7178 | 0.6724 | 0.6715 | 0.7178 |
80
+ | 0.7908 | 1.0 | 1000 | 0.6365 | 0.7356 | 0.7272 | 0.7211 | 0.7356 |
81
+ | 0.7908 | 1.5 | 1500 | 0.6204 | 0.7376 | 0.7380 | 0.7387 | 0.7376 |
82
+ | 0.6358 | 2.0 | 2000 | 0.6162 | 0.7386 | 0.7377 | 0.7380 | 0.7386 |
83
+ | 0.6358 | 2.5 | 2500 | 0.6228 | 0.7274 | 0.7390 | 0.7576 | 0.7274 |
84
+ | 0.5827 | 3.0 | 3000 | 0.6188 | 0.7378 | 0.7400 | 0.7425 | 0.7378 |
85
+ | 0.5827 | 3.5 | 3500 | 0.6246 | 0.7374 | 0.7416 | 0.7467 | 0.7374 |
86
+ | 0.5427 | 4.0 | 4000 | 0.6266 | 0.7446 | 0.7452 | 0.7465 | 0.7446 |
87
+ | 0.5427 | 4.5 | 4500 | 0.6331 | 0.7392 | 0.7421 | 0.7456 | 0.7392 |
88
+ | 0.5184 | 5.0 | 5000 | 0.6279 | 0.737 | 0.7438 | 0.7525 | 0.737 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - Transformers 4.15.0
94
+ - Pytorch 1.10.0+cu111
95
+ - Datasets 1.17.0
96
+ - Tokenizers 0.10.3