Hugging Face's logo

Rhuax
/
MiniLMv2-L12-H384-distilled-finetuned-spam-detection

Text Classification Transformers PyTorch TensorBoard
roberta generated_from_trainer Eval Results Inference Endpoints
Model card Files Metrics Community
3
Rhuax commited on
Commit
5ff852c
•
1 Parent(s): 056199a

End of training

Browse files
Files changed (3) hide show
  1. README.md +10 -14
  2. logs/events.out.tfevents.1654174135.algo-1.54.0 +2 -2
  3. pytorch_model.bin +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ model-index:
18
  metrics:
19
  - name: Accuracy
20
  type: accuracy
21
- value: 0.978494623655914
22
  ---
23
 
24
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,8 +28,8 @@ should probably proofread and complete it, then remove this comment. -->
28
 
29
  This model is a fine-tuned version of [nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large](https://huggingface.co/nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large) on the sms_spam dataset.
30
  It achieves the following results on the evaluation set:
31
- - Loss: 0.4473
32
- - Accuracy: 0.9785
33
 
34
  ## Model description
35
 
@@ -54,23 +54,19 @@ The following hyperparameters were used during training:
54
  - seed: 33
55
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
56
  - lr_scheduler_type: linear
57
- - num_epochs: 10
58
  - mixed_precision_training: Native AMP
59
 
60
  ### Training results
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
63
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
64
- | 4.1186 | 1.0 | 18 | 3.4012 | 0.8351 |
65
- | 2.9893 | 2.0 | 36 | 2.9206 | 0.8351 |
66
- | 2.6718 | 3.0 | 54 | 2.8932 | 0.8351 |
67
- | 2.5495 | 4.0 | 72 | 2.8916 | 0.8351 |
68
- | 1.7213 | 5.0 | 90 | 0.6804 | 0.9821 |
69
- | 0.7464 | 6.0 | 108 | 0.6017 | 0.9713 |
70
- | 1.2052 | 7.0 | 126 | 0.3425 | 0.9857 |
71
- | 0.438 | 8.0 | 144 | 0.2136 | 0.9857 |
72
- | 0.2282 | 9.0 | 162 | 0.4539 | 0.9785 |
73
- | 0.438 | 10.0 | 180 | 0.4473 | 0.9785 |
74
 
75
 
76
  ### Framework versions
18
  metrics:
19
  - name: Accuracy
20
  type: accuracy
21
+ value: 0.9928263988522238
22
  ---
23
 
24
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
 
29
  This model is a fine-tuned version of [nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large](https://huggingface.co/nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large) on the sms_spam dataset.
30
  It achieves the following results on the evaluation set:
31
+ - Loss: 0.0938
32
+ - Accuracy: 0.9928
33
 
34
  ## Model description
35
 
54
  - seed: 33
55
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
56
  - lr_scheduler_type: linear
57
+ - num_epochs: 6
58
  - mixed_precision_training: Native AMP
59
 
60
  ### Training results
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
63
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
64
+ | 1.4101 | 1.0 | 131 | 0.4930 | 0.9763 |
65
+ | 0.8003 | 2.0 | 262 | 0.3999 | 0.9799 |
66
+ | 0.377 | 3.0 | 393 | 0.3196 | 0.9828 |
67
+ | 0.302 | 4.0 | 524 | 0.3462 | 0.9828 |
68
+ | 0.1945 | 5.0 | 655 | 0.1094 | 0.9928 |
69
+ | 0.1393 | 6.0 | 786 | 0.0938 | 0.9928 |
 
 
 
 
70
 
71
 
72
  ### Framework versions
logs/events.out.tfevents.1654174135.algo-1.54.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e3a724f453ae8e6e467883ac738c8898b25eedaeb18c9c7f5b96b44c8e2d044
3
- size 6341
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f885d989888974b69a5521523cf8a9385d8018bc1df43a8d7a3be876641bf040
3
+ size 6695
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51171977ddd548c5b3591efecd0188602ffa05ad25e35fe08b6ac4f7d68935ab
3
  size 163856237
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e2bf34e5526ce70226848a14d9fbe55cfdfb033f1a7cf3398aef3525105cec7
3
  size 163856237