Hugging Face's logo

Hartunka
/
distilbert_km_50_v2

Transformers
Safetensors
distilbert
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Community
Hartunka commited on
Commit
4a427fa
·
verified ·
1 Parent(s): 13ddde5

Model save

Browse files
Files changed (2) hide show
  1. README.md +9 -21
  2. model.safetensors +1 -1
README.md CHANGED
@@ -2,23 +2,11 @@
2
  library_name: transformers
3
  tags:
4
  - generated_from_trainer
5
- datasets:
6
- - Hartunka/processed_wikitext-103-raw-v1-km-50
7
  metrics:
8
  - accuracy
9
  model-index:
10
  - name: distilbert_km_50_v2
11
- results:
12
- - task:
13
- name: Masked Language Modeling
14
- type: fill-mask
15
- dataset:
16
- name: Hartunka/processed_wikitext-103-raw-v1-km-50
17
- type: Hartunka/processed_wikitext-103-raw-v1-km-50
18
- metrics:
19
- - name: Accuracy
20
- type: accuracy
21
- value: 0.15335932643950953
22
  ---
23
 
24
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -26,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
26
 
27
  # distilbert_km_50_v2
28
 
29
- This model is a fine-tuned version of [](https://huggingface.co/) on the Hartunka/processed_wikitext-103-raw-v1-km-50 dataset.
30
  It achieves the following results on the evaluation set:
31
- - Loss: 6.8309
32
- - Accuracy: 0.1534
33
 
34
  ## Model description
35
 
@@ -61,11 +49,11 @@ The following hyperparameters were used during training:
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
63
  |:-------------:|:-------:|:-----:|:---------------:|:--------:|
64
- | 7.0049 | 4.1982 | 10000 | 6.9876 | 0.1502 |
65
- | 6.5188 | 8.3963 | 20000 | 6.8562 | 0.1521 |
66
- | 6.2532 | 12.5945 | 30000 | 6.9999 | 0.1540 |
67
- | 6.0922 | 16.7926 | 40000 | 7.2141 | 0.1531 |
68
- | 6.0045 | 20.9908 | 50000 | 7.1422 | 0.1511 |
69
 
70
 
71
  ### Framework versions
 
2
  library_name: transformers
3
  tags:
4
  - generated_from_trainer
 
 
5
  metrics:
6
  - accuracy
7
  model-index:
8
  - name: distilbert_km_50_v2
9
+ results: []
 
 
 
 
 
 
 
 
 
 
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
14
 
15
  # distilbert_km_50_v2
16
 
17
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 7.0267
20
+ - Accuracy: 0.1516
21
 
22
  ## Model description
23
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-------:|:-----:|:---------------:|:--------:|
52
+ | 6.8364 | 4.1982 | 10000 | 6.8761 | 0.1504 |
53
+ | 6.4025 | 8.3963 | 20000 | 6.9074 | 0.1516 |
54
+ | 6.1886 | 12.5945 | 30000 | 6.9720 | 0.1543 |
55
+ | 6.0593 | 16.7926 | 40000 | 7.0526 | 0.1522 |
56
+ | 5.9809 | 20.9908 | 50000 | 7.0267 | 0.1516 |
57
 
58
 
59
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f74eaa2612b796ebf13621b79ac3fa7866510be45b66e3a37c55ab17380c0b71
3
  size 270471328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a0570e92cb250c288727706d4a1aea747e5dadd404f5a1ff11070c88bcaa4a1
3
  size 270471328