Kayvane commited on
Commit
1eb2038
1 Parent(s): ceb80be

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
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - consumer-finance-complaints
7
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ - recall
11
+ - precision
12
+ model-index:
13
+ - name: distilroberta-base-wandb-week-3-complaints-classifier-512
14
+ results:
15
+ - task:
16
+ name: Text Classification
17
+ type: text-classification
18
+ dataset:
19
+ name: consumer-finance-complaints
20
+ type: consumer-finance-complaints
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.8038326283064064
26
+ - name: F1
27
+ type: f1
28
+ value: 0.791857014338201
29
+ - name: Recall
30
+ type: recall
31
+ value: 0.8038326283064064
32
+ - name: Precision
33
+ type: precision
34
+ value: 0.7922430702228043
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
+ # distilroberta-base-wandb-week-3-complaints-classifier-512
41
+
42
+ This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the consumer-finance-complaints dataset.
43
+ It achieves the following results on the evaluation set:
44
+ - Loss: 0.6004
45
+ - Accuracy: 0.8038
46
+ - F1: 0.7919
47
+ - Recall: 0.8038
48
+ - Precision: 0.7922
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: 1.7835312622444155e-05
68
+ - train_batch_size: 32
69
+ - eval_batch_size: 32
70
+ - seed: 42
71
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
72
+ - lr_scheduler_type: linear
73
+ - lr_scheduler_warmup_steps: 512
74
+ - num_epochs: 2
75
+ - mixed_precision_training: Native AMP
76
+
77
+ ### Training results
78
+
79
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision |
80
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:|
81
+ | 0.7559 | 0.61 | 1500 | 0.7307 | 0.7733 | 0.7411 | 0.7733 | 0.7286 |
82
+ | 0.6361 | 1.22 | 3000 | 0.6559 | 0.7846 | 0.7699 | 0.7846 | 0.7718 |
83
+ | 0.5774 | 1.83 | 4500 | 0.6004 | 0.8038 | 0.7919 | 0.8038 | 0.7922 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.20.1
89
+ - Pytorch 1.11.0+cu102
90
+ - Datasets 2.3.2
91
+ - Tokenizers 0.12.1