francisco-perez-sorrosal commited on
Commit
fbc98bb
1 Parent(s): c9cd005

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +91 -0
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - dataset
6
+ metrics:
7
+ - accuracy
8
+ - f1
9
+ - precision
10
+ - recall
11
+ model-index:
12
+ - name: dccuchile-distilbert-base-spanish-uncased-finetuned-with-spanish-tweets-clf-cleaned-ds
13
+ results:
14
+ - task:
15
+ name: Text Classification
16
+ type: text-classification
17
+ dataset:
18
+ name: dataset
19
+ type: dataset
20
+ config: 60-20-20
21
+ split: dev
22
+ args: 60-20-20
23
+ metrics:
24
+ - name: Accuracy
25
+ type: accuracy
26
+ value: 0.650310988251555
27
+ - name: F1
28
+ type: f1
29
+ value: 0.6518765643027159
30
+ - name: Precision
31
+ type: precision
32
+ value: 0.6625453481119005
33
+ - name: Recall
34
+ type: recall
35
+ value: 0.6498098682990169
36
+ ---
37
+
38
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
39
+ should probably proofread and complete it, then remove this comment. -->
40
+
41
+ # dccuchile-distilbert-base-spanish-uncased-finetuned-with-spanish-tweets-clf-cleaned-ds
42
+
43
+ This model is a fine-tuned version of [dccuchile/distilbert-base-spanish-uncased](https://huggingface.co/dccuchile/distilbert-base-spanish-uncased) on the dataset dataset.
44
+ It achieves the following results on the evaluation set:
45
+ - Loss: 1.6605
46
+ - Accuracy: 0.6503
47
+ - F1: 0.6519
48
+ - Precision: 0.6625
49
+ - Recall: 0.6498
50
+
51
+ ## Model description
52
+
53
+ More information needed
54
+
55
+ ## Intended uses & limitations
56
+
57
+ More information needed
58
+
59
+ ## Training and evaluation data
60
+
61
+ More information needed
62
+
63
+ ## Training procedure
64
+
65
+ ### Training hyperparameters
66
+
67
+ The following hyperparameters were used during training:
68
+ - learning_rate: 5e-05
69
+ - train_batch_size: 8
70
+ - eval_batch_size: 32
71
+ - seed: 42
72
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
73
+ - lr_scheduler_type: linear
74
+ - num_epochs: 4.0
75
+
76
+ ### Training results
77
+
78
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
79
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
80
+ | 0.8558 | 1.0 | 543 | 0.7705 | 0.6628 | 0.6408 | 0.6585 | 0.6404 |
81
+ | 0.5485 | 2.0 | 1086 | 0.8657 | 0.6593 | 0.6436 | 0.6578 | 0.6388 |
82
+ | 0.3071 | 3.0 | 1629 | 1.3021 | 0.6586 | 0.6556 | 0.6551 | 0.6581 |
83
+ | 0.1581 | 4.0 | 2172 | 1.6605 | 0.6503 | 0.6519 | 0.6625 | 0.6498 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.26.0
89
+ - Pytorch 1.13.1
90
+ - Datasets 2.8.0
91
+ - Tokenizers 0.13.2