oandreae commited on
Commit
2c1f91c
1 Parent(s): a5d5cee

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +86 -0
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - financial_phrasebank
7
+ metrics:
8
+ - recall
9
+ - accuracy
10
+ - precision
11
+ model-index:
12
+ - name: financial_sentiment_model
13
+ results:
14
+ - task:
15
+ name: Text Classification
16
+ type: text-classification
17
+ dataset:
18
+ name: financial_phrasebank
19
+ type: financial_phrasebank
20
+ args: sentences_50agree
21
+ metrics:
22
+ - name: Recall
23
+ type: recall
24
+ value: 0.8839956357328868
25
+ - name: Accuracy
26
+ type: accuracy
27
+ value: 0.8804123711340206
28
+ - name: Precision
29
+ type: precision
30
+ value: 0.8604175202419276
31
+ ---
32
+
33
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
34
+ should probably proofread and complete it, then remove this comment. -->
35
+
36
+ # financial_sentiment_model
37
+
38
+ This model is a fine-tuned version of [deepmind/language-perceiver](https://huggingface.co/deepmind/language-perceiver) on the financial_phrasebank dataset.
39
+ It achieves the following results on the evaluation set:
40
+ - Loss: 0.3467
41
+ - Recall: 0.8840
42
+ - Accuracy: 0.8804
43
+ - Precision: 0.8604
44
+
45
+ ## Model description
46
+
47
+ More information needed
48
+
49
+ ## Intended uses & limitations
50
+
51
+ More information needed
52
+
53
+ ## Training and evaluation data
54
+
55
+ More information needed
56
+
57
+ ## Training procedure
58
+
59
+ ### Training hyperparameters
60
+
61
+ The following hyperparameters were used during training:
62
+ - learning_rate: 2e-05
63
+ - train_batch_size: 16
64
+ - eval_batch_size: 16
65
+ - seed: 42
66
+ - distributed_type: tpu
67
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
68
+ - lr_scheduler_type: linear
69
+ - num_epochs: 4
70
+
71
+ ### Training results
72
+
73
+ | Training Loss | Epoch | Step | Validation Loss | Recall | Accuracy | Precision |
74
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|:---------:|
75
+ | 0.4481 | 1.0 | 273 | 0.4035 | 0.8526 | 0.8433 | 0.7955 |
76
+ | 0.4069 | 2.0 | 546 | 0.4478 | 0.8683 | 0.8289 | 0.8123 |
77
+ | 0.2225 | 3.0 | 819 | 0.3167 | 0.8747 | 0.8680 | 0.8387 |
78
+ | 0.1245 | 4.0 | 1092 | 0.3467 | 0.8840 | 0.8804 | 0.8604 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.15.0
84
+ - Pytorch 1.9.0+cu102
85
+ - Datasets 1.17.0
86
+ - Tokenizers 0.10.3