RawMean commited on
Commit
acc490f
·
1 Parent(s): fd20a27

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +75 -0
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: farsi_lastname_classifier_4
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # farsi_lastname_classifier_4
16
+
17
+ This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.2337
20
+ - Accuracy: 0.96
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.0001
40
+ - train_batch_size: 128
41
+ - eval_batch_size: 256
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: cosine
45
+ - lr_scheduler_warmup_ratio: 0.1
46
+ - num_epochs: 15
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | No log | 1.0 | 12 | 0.5673 | 0.836 |
54
+ | No log | 2.0 | 24 | 0.4052 | 0.868 |
55
+ | No log | 3.0 | 36 | 0.2211 | 0.932 |
56
+ | No log | 4.0 | 48 | 0.2488 | 0.926 |
57
+ | No log | 5.0 | 60 | 0.1490 | 0.954 |
58
+ | No log | 6.0 | 72 | 0.1464 | 0.968 |
59
+ | No log | 7.0 | 84 | 0.1923 | 0.954 |
60
+ | No log | 8.0 | 96 | 0.2070 | 0.96 |
61
+ | No log | 9.0 | 108 | 0.2055 | 0.962 |
62
+ | No log | 10.0 | 120 | 0.2436 | 0.942 |
63
+ | No log | 11.0 | 132 | 0.2173 | 0.96 |
64
+ | No log | 12.0 | 144 | 0.2342 | 0.956 |
65
+ | No log | 13.0 | 156 | 0.2337 | 0.962 |
66
+ | No log | 14.0 | 168 | 0.2332 | 0.96 |
67
+ | No log | 15.0 | 180 | 0.2337 | 0.96 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.24.0
73
+ - Pytorch 1.12.1+cu113
74
+ - Datasets 2.6.1
75
+ - Tokenizers 0.13.2