Hugging Face's logo

Aubins
/
distil-bumble-bert

Text Classification
Transformers
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Community
Aubins commited on
Commit
2caf1ef
·
verified ·
1 Parent(s): e328fb2

Aubins/distil-bumble-bert

Browse files
Files changed (3) hide show
  1. README.md +11 -12
  2. config.json +1 -1
  3. model.safetensors +1 -1
README.md CHANGED
@@ -1,13 +1,12 @@
1
  ---
2
  library_name: transformers
3
- base_model: Aubins/distil-bumble-bert
4
  tags:
5
  - generated_from_trainer
6
  metrics:
7
  - accuracy
 
8
  - precision
9
  - recall
10
- - f1
11
  model-index:
12
  - name: distil-bumble-bert
13
  results: []
@@ -18,13 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # distil-bumble-bert
20
 
21
- This model is a fine-tuned version of [Aubins/distil-bumble-bert](https://huggingface.co/Aubins/distil-bumble-bert) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.4451
24
  - Accuracy: 0.7896
 
 
25
  - Precision: 0.6403
26
  - Recall: 0.5816
27
- - F1: 0.6095
28
  - Roc Auc: 0.8318
29
 
30
  ## Model description
@@ -57,13 +56,13 @@ The following hyperparameters were used during training:
57
 
58
  ### Training results
59
 
60
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Roc Auc |
61
- |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-------:|
62
- | 0.4599 | 0.5204 | 500 | 0.4772 | 0.7726 | 0.6237 | 0.4914 | 0.5497 | 0.7998 |
63
- | 0.4529 | 1.0416 | 1000 | 0.4523 | 0.7869 | 0.6653 | 0.4940 | 0.5670 | 0.8199 |
64
- | 0.4542 | 1.5621 | 1500 | 0.4455 | 0.7893 | 0.6614 | 0.5201 | 0.5823 | 0.8268 |
65
- | 0.4428 | 2.0833 | 2000 | 0.4428 | 0.7898 | 0.6533 | 0.5451 | 0.5943 | 0.8306 |
66
- | 0.4999 | 2.6037 | 2500 | 0.4451 | 0.7896 | 0.6403 | 0.5816 | 0.6095 | 0.8318 |
67
 
68
 
69
  ### Framework versions
 
1
  ---
2
  library_name: transformers
 
3
  tags:
4
  - generated_from_trainer
5
  metrics:
6
  - accuracy
7
+ - f1
8
  - precision
9
  - recall
 
10
  model-index:
11
  - name: distil-bumble-bert
12
  results: []
 
17
 
18
  # distil-bumble-bert
19
 
20
+ This model was trained from scratch on the None dataset.
21
  It achieves the following results on the evaluation set:
 
22
  - Accuracy: 0.7896
23
+ - F1: 0.6095
24
+ - Loss: 0.4451
25
  - Precision: 0.6403
26
  - Recall: 0.5816
 
27
  - Roc Auc: 0.8318
28
 
29
  ## Model description
 
56
 
57
  ### Training results
58
 
59
+ | Training Loss | Epoch | Step | Accuracy | F1 | Validation Loss | Precision | Recall | Roc Auc |
60
+ |:-------------:|:------:|:----:|:--------:|:------:|:---------------:|:---------:|:------:|:-------:|
61
+ | 0.4599 | 0.5204 | 500 | 0.7726 | 0.5497 | 0.4772 | 0.6237 | 0.4914 | 0.7998 |
62
+ | 0.4529 | 1.0416 | 1000 | 0.7869 | 0.5670 | 0.4523 | 0.6653 | 0.4940 | 0.8199 |
63
+ | 0.4542 | 1.5621 | 1500 | 0.7893 | 0.5823 | 0.4455 | 0.6614 | 0.5201 | 0.8268 |
64
+ | 0.4428 | 2.0833 | 2000 | 0.7898 | 0.5943 | 0.4428 | 0.6533 | 0.5451 | 0.8306 |
65
+ | 0.4999 | 2.6037 | 2500 | 0.7896 | 0.6095 | 0.4451 | 0.6403 | 0.5816 | 0.8318 |
66
 
67
 
68
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "Aubins/distil-bumble-bert",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForSequenceClassification"
 
1
  {
2
+ "_name_or_path": "./distil-bumble-bert/last-checkpoint",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForSequenceClassification"
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:721ab7baab6c3b21bd02d3f19a376a3282ced13703db821d212f267123988469
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8f5e74ff88646dae0402d238201c4dd143c2e5798d5a0d85b0572bdd69f49b6
3
  size 267832560