francisco-perez-sorrosal commited on
Commit
c21514a
1 Parent(s): 4cfb57a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +92 -0
README.md ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - dataset
7
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ - precision
11
+ - recall
12
+ model-index:
13
+ - name: distilbert-base-multilingual-cased-finetuned-with-spanish-tweets-clf-cleaned-ds
14
+ results:
15
+ - task:
16
+ name: Text Classification
17
+ type: text-classification
18
+ dataset:
19
+ name: dataset
20
+ type: dataset
21
+ config: 60-20-20
22
+ split: dev
23
+ args: 60-20-20
24
+ metrics:
25
+ - name: Accuracy
26
+ type: accuracy
27
+ value: 0.5950241879751209
28
+ - name: F1
29
+ type: f1
30
+ value: 0.5960495390531203
31
+ - name: Precision
32
+ type: precision
33
+ value: 0.6035704467576662
34
+ - name: Recall
35
+ type: recall
36
+ value: 0.5948663448786202
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-multilingual-cased-finetuned-with-spanish-tweets-clf-cleaned-ds
43
+
44
+ This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on the dataset dataset.
45
+ It achieves the following results on the evaluation set:
46
+ - Loss: 1.5095
47
+ - Accuracy: 0.5950
48
+ - F1: 0.5960
49
+ - Precision: 0.6036
50
+ - Recall: 0.5949
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: 5e-05
70
+ - train_batch_size: 8
71
+ - eval_batch_size: 32
72
+ - seed: 42
73
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
+ - lr_scheduler_type: linear
75
+ - num_epochs: 4.0
76
+
77
+ ### Training results
78
+
79
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
80
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
81
+ | 1.018 | 1.0 | 543 | 0.9421 | 0.5536 | 0.4949 | 0.5347 | 0.5146 |
82
+ | 0.8079 | 2.0 | 1086 | 0.9275 | 0.5957 | 0.5751 | 0.5921 | 0.5725 |
83
+ | 0.521 | 3.0 | 1629 | 1.1208 | 0.6033 | 0.6050 | 0.6146 | 0.6023 |
84
+ | 0.3225 | 4.0 | 2172 | 1.5095 | 0.5950 | 0.5960 | 0.6036 | 0.5949 |
85
+
86
+
87
+ ### Framework versions
88
+
89
+ - Transformers 4.26.0
90
+ - Pytorch 1.13.1
91
+ - Datasets 2.8.0
92
+ - Tokenizers 0.13.2