Hugging Face's logo

mankra
/
mini_text_classification_finetune_model

Text Classification
Transformers
PyTorch
TensorBoard
xlm-roberta
Generated from Trainer
Model card Files
xet
Metrics Community
1
mankra commited on
Commit
b4a08f0
·
1 Parent(s): e7be515

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +33 -13
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [microsoft/Multilingual-MiniLM-L12-H384](https://huggingface.co/microsoft/Multilingual-MiniLM-L12-H384) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.3661
20
- - Accuracy: 1.0
21
 
22
  ## Model description
23
 
@@ -42,22 +42,42 @@ The following hyperparameters were used during training:
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
- - num_epochs: 10
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
- | No log | 1.0 | 1 | 1.4030 | 0.0 |
52
- | No log | 2.0 | 2 | 1.3959 | 0.0 |
53
- | No log | 3.0 | 3 | 1.3896 | 0.0 |
54
- | No log | 4.0 | 4 | 1.3840 | 0.0 |
55
- | No log | 5.0 | 5 | 1.3790 | 0.0 |
56
- | No log | 6.0 | 6 | 1.3749 | 1.0 |
57
- | No log | 7.0 | 7 | 1.3714 | 1.0 |
58
- | No log | 8.0 | 8 | 1.3688 | 1.0 |
59
- | No log | 9.0 | 9 | 1.3670 | 1.0 |
60
- | No log | 10.0 | 10 | 1.3661 | 1.0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
 
62
 
63
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [microsoft/Multilingual-MiniLM-L12-H384](https://huggingface.co/microsoft/Multilingual-MiniLM-L12-H384) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.2095
20
+ - Accuracy: 0.3333
21
 
22
  ## Model description
23
 
 
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - num_epochs: 30
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
+ | No log | 1.0 | 1 | 1.3045 | 0.3333 |
52
+ | No log | 2.0 | 2 | 1.2998 | 0.3333 |
53
+ | No log | 3.0 | 3 | 1.2947 | 0.3333 |
54
+ | No log | 4.0 | 4 | 1.2899 | 0.3333 |
55
+ | No log | 5.0 | 5 | 1.2851 | 0.3333 |
56
+ | No log | 6.0 | 6 | 1.2809 | 0.3333 |
57
+ | No log | 7.0 | 7 | 1.2766 | 0.3333 |
58
+ | No log | 8.0 | 8 | 1.2721 | 0.3333 |
59
+ | No log | 9.0 | 9 | 1.2684 | 0.3333 |
60
+ | No log | 10.0 | 10 | 1.2645 | 0.3333 |
61
+ | No log | 11.0 | 11 | 1.2607 | 0.3333 |
62
+ | No log | 12.0 | 12 | 1.2567 | 0.3333 |
63
+ | No log | 13.0 | 13 | 1.2528 | 0.3333 |
64
+ | No log | 14.0 | 14 | 1.2490 | 0.3333 |
65
+ | No log | 15.0 | 15 | 1.2451 | 0.3333 |
66
+ | No log | 16.0 | 16 | 1.2413 | 0.3333 |
67
+ | No log | 17.0 | 17 | 1.2377 | 0.3333 |
68
+ | No log | 18.0 | 18 | 1.2342 | 0.3333 |
69
+ | No log | 19.0 | 19 | 1.2307 | 0.3333 |
70
+ | No log | 20.0 | 20 | 1.2275 | 0.3333 |
71
+ | No log | 21.0 | 21 | 1.2244 | 0.3333 |
72
+ | No log | 22.0 | 22 | 1.2215 | 0.3333 |
73
+ | No log | 23.0 | 23 | 1.2190 | 0.3333 |
74
+ | No log | 24.0 | 24 | 1.2167 | 0.3333 |
75
+ | No log | 25.0 | 25 | 1.2147 | 0.3333 |
76
+ | No log | 26.0 | 26 | 1.2130 | 0.3333 |
77
+ | No log | 27.0 | 27 | 1.2116 | 0.3333 |
78
+ | No log | 28.0 | 28 | 1.2105 | 0.3333 |
79
+ | No log | 29.0 | 29 | 1.2098 | 0.3333 |
80
+ | No log | 30.0 | 30 | 1.2095 | 0.3333 |
81
 
82
 
83
  ### Framework versions