Hugging Face's logo

Hartunka
/
tiny_bert_km_50_v2

Safetensors
distilbert
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Community
Hartunka commited on
Commit
0c7deea
·
verified ·
1 Parent(s): 6f273ef

Model save

Browse files
Files changed (2) hide show
  1. README.md +9 -21
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,23 +1,11 @@
1
  ---
2
  tags:
3
  - generated_from_trainer
4
- datasets:
5
- - Hartunka/processed_wikitext-103-raw-v1-km-50
6
  metrics:
7
  - accuracy
8
  model-index:
9
  - name: tiny_bert_km_50_v2
10
- results:
11
- - task:
12
- name: Masked Language Modeling
13
- type: fill-mask
14
- dataset:
15
- name: Hartunka/processed_wikitext-103-raw-v1-km-50
16
- type: Hartunka/processed_wikitext-103-raw-v1-km-50
17
- metrics:
18
- - name: Accuracy
19
- type: accuracy
20
- value: 0.15287901904277562
21
  ---
22
 
23
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -25,10 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
25
 
26
  # tiny_bert_km_50_v2
27
 
28
- This model is a fine-tuned version of [](https://huggingface.co/) on the Hartunka/processed_wikitext-103-raw-v1-km-50 dataset.
29
  It achieves the following results on the evaluation set:
30
- - Loss: 6.9191
31
- - Accuracy: 0.1529
32
 
33
  ## Model description
34
 
@@ -60,11 +48,11 @@ The following hyperparameters were used during training:
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
62
  |:-------------:|:-------:|:-----:|:---------------:|:--------:|
63
- | 7.0543 | 4.1982 | 10000 | 7.0519 | 0.1467 |
64
- | 6.6574 | 8.3963 | 20000 | 6.9088 | 0.1517 |
65
- | 6.4302 | 12.5945 | 30000 | 6.9433 | 0.1537 |
66
- | 6.2677 | 16.7926 | 40000 | 7.0326 | 0.1517 |
67
- | 6.1767 | 20.9908 | 50000 | 7.0453 | 0.1502 |
68
 
69
 
70
  ### Framework versions
 
1
  ---
2
  tags:
3
  - generated_from_trainer
 
 
4
  metrics:
5
  - accuracy
6
  model-index:
7
  - name: tiny_bert_km_50_v2
8
+ results: []
 
 
 
 
 
 
 
 
 
 
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
13
 
14
  # tiny_bert_km_50_v2
15
 
16
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 7.0162
19
+ - Accuracy: 0.1513
20
 
21
  ## Model description
22
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
  |:-------------:|:-------:|:-----:|:---------------:|:--------:|
51
+ | 6.9045 | 4.1982 | 10000 | 6.9532 | 0.1481 |
52
+ | 6.4983 | 8.3963 | 20000 | 6.8621 | 0.1524 |
53
+ | 6.3069 | 12.5945 | 30000 | 6.8769 | 0.1533 |
54
+ | 6.1769 | 16.7926 | 40000 | 6.9537 | 0.1523 |
55
+ | 6.0989 | 20.9908 | 50000 | 7.0162 | 0.1513 |
56
 
57
 
58
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc398e4f5d96d9287f4dfd22a5c24b25a8a7357517714cb45469b57ff55d30f1
3
  size 133132568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:056d0638a34e581702f1ead4f7cdffd7c648c681e566d7fab008186ea0a3a124
3
  size 133132568