dadashzadeh commited on
Commit
d8b0ed7
1 Parent(s): 7e6c330

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +79 -74
README.md CHANGED
@@ -1,74 +1,79 @@
1
- ---
2
- license: apache-2.0
3
- base_model: dadashzadeh/tiny-bert-Sentiment-persian
4
- tags:
5
- - generated_from_trainer
6
- metrics:
7
- - accuracy
8
- model-index:
9
- - name: tiny-bert-Sentiment-persian
10
- results: []
11
- ---
12
-
13
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
- should probably proofread and complete it, then remove this comment. -->
15
-
16
- # tiny-bert-Sentiment-persian
17
-
18
- This model is a fine-tuned version of [dadashzadeh/tiny-bert-Sentiment-persian](https://huggingface.co/dadashzadeh/tiny-bert-Sentiment-persian) on an unknown dataset.
19
- It achieves the following results on the evaluation set:
20
- - Loss: 0.6553
21
- - Accuracy: 0.7611
22
-
23
- ## Model description
24
-
25
- More information needed
26
-
27
- ## Intended uses & limitations
28
-
29
- More information needed
30
-
31
- ## Training and evaluation data
32
-
33
- More information needed
34
-
35
- ## Training procedure
36
-
37
- ### Training hyperparameters
38
-
39
- The following hyperparameters were used during training:
40
- - learning_rate: 2e-05
41
- - train_batch_size: 2
42
- - eval_batch_size: 2
43
- - seed: 45
44
- - gradient_accumulation_steps: 4
45
- - total_train_batch_size: 8
46
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
- - lr_scheduler_type: linear
48
- - num_epochs: 12
49
- - mixed_precision_training: Native AMP
50
-
51
- ### Training results
52
-
53
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
- |:-------------:|:-------:|:-----:|:---------------:|:--------:|
55
- | 0.6157 | 0.9999 | 3575 | 0.6703 | 0.7577 |
56
- | 0.5833 | 1.9999 | 7150 | 0.7599 | 0.7171 |
57
- | 0.6015 | 2.9998 | 10725 | 0.6824 | 0.7590 |
58
- | 0.5601 | 4.0 | 14301 | 0.6780 | 0.7533 |
59
- | 0.5699 | 4.9999 | 17876 | 0.7071 | 0.7356 |
60
- | 0.5519 | 5.9999 | 21451 | 0.6931 | 0.7391 |
61
- | 0.5436 | 6.9998 | 25026 | 0.6736 | 0.7629 |
62
- | 0.5482 | 8.0 | 28602 | 0.6567 | 0.7685 |
63
- | 0.5367 | 8.9999 | 32177 | 0.6553 | 0.7611 |
64
- | 0.5399 | 9.9999 | 35752 | 0.6691 | 0.7616 |
65
- | 0.5112 | 10.9998 | 39327 | 0.6785 | 0.7564 |
66
- | 0.5113 | 11.9992 | 42900 | 0.6773 | 0.7572 |
67
-
68
-
69
- ### Framework versions
70
-
71
- - Transformers 4.40.2
72
- - Pytorch 2.2.2+cu118
73
- - Datasets 2.19.1
74
- - Tokenizers 0.19.1
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: dadashzadeh/tiny-bert-Sentiment-persian
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: tiny-bert-Sentiment-persian
10
+ results: []
11
+ datasets:
12
+ - hezarai/sentiment-dksf
13
+ language:
14
+ - fa
15
+ pipeline_tag: text-classification
16
+ ---
17
+
18
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
19
+ should probably proofread and complete it, then remove this comment. -->
20
+
21
+ # tiny-bert-Sentiment-persian
22
+
23
+ This model is a fine-tuned version of [dadashzadeh/tiny-bert-Sentiment-persian](https://huggingface.co/dadashzadeh/tiny-bert-Sentiment-persian) on an unknown dataset.
24
+ It achieves the following results on the evaluation set:
25
+ - Loss: 0.6553
26
+ - Accuracy: 0.7611
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 2e-05
46
+ - train_batch_size: 2
47
+ - eval_batch_size: 2
48
+ - seed: 45
49
+ - gradient_accumulation_steps: 4
50
+ - total_train_batch_size: 8
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 12
54
+ - mixed_precision_training: Native AMP
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
59
+ |:-------------:|:-------:|:-----:|:---------------:|:--------:|
60
+ | 0.6157 | 0.9999 | 3575 | 0.6703 | 0.7577 |
61
+ | 0.5833 | 1.9999 | 7150 | 0.7599 | 0.7171 |
62
+ | 0.6015 | 2.9998 | 10725 | 0.6824 | 0.7590 |
63
+ | 0.5601 | 4.0 | 14301 | 0.6780 | 0.7533 |
64
+ | 0.5699 | 4.9999 | 17876 | 0.7071 | 0.7356 |
65
+ | 0.5519 | 5.9999 | 21451 | 0.6931 | 0.7391 |
66
+ | 0.5436 | 6.9998 | 25026 | 0.6736 | 0.7629 |
67
+ | 0.5482 | 8.0 | 28602 | 0.6567 | 0.7685 |
68
+ | 0.5367 | 8.9999 | 32177 | 0.6553 | 0.7611 |
69
+ | 0.5399 | 9.9999 | 35752 | 0.6691 | 0.7616 |
70
+ | 0.5112 | 10.9998 | 39327 | 0.6785 | 0.7564 |
71
+ | 0.5113 | 11.9992 | 42900 | 0.6773 | 0.7572 |
72
+
73
+
74
+ ### Framework versions
75
+
76
+ - Transformers 4.40.2
77
+ - Pytorch 2.2.2+cu118
78
+ - Datasets 2.19.1
79
+ - Tokenizers 0.19.1