mor40 commited on
Commit
10084fe
1 Parent(s): da3b1f0

Training complete

Browse files
Files changed (1) hide show
  1. README.md +9 -24
README.md CHANGED
@@ -2,26 +2,11 @@
2
  base_model: mor40/BulBERT-finetuned-cinexio
3
  tags:
4
  - generated_from_trainer
5
- datasets:
6
- - bgglue
7
  metrics:
8
  - accuracy
9
  model-index:
10
  - name: BulBERT-cinexio-5pochs
11
- results:
12
- - task:
13
- name: Text Classification
14
- type: text-classification
15
- dataset:
16
- name: bgglue
17
- type: bgglue
18
- config: cinexio
19
- split: validation
20
- args: cinexio
21
- metrics:
22
- - name: Accuracy
23
- type: accuracy
24
- value: 0.5265104808877928
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
29
 
30
  # BulBERT-cinexio-5pochs
31
 
32
- This model is a fine-tuned version of [mor40/BulBERT-finetuned-cinexio](https://huggingface.co/mor40/BulBERT-finetuned-cinexio) on the bgglue dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 2.2358
35
- - Accuracy: 0.5265
36
 
37
  ## Model description
38
 
@@ -63,11 +48,11 @@ The following hyperparameters were used during training:
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
- | No log | 1.0 | 64 | 2.0429 | 0.5129 |
67
- | No log | 2.0 | 128 | 2.1526 | 0.5265 |
68
- | No log | 3.0 | 192 | 2.1576 | 0.5216 |
69
- | No log | 4.0 | 256 | 2.2160 | 0.5179 |
70
- | No log | 5.0 | 320 | 2.2358 | 0.5265 |
71
 
72
 
73
  ### Framework versions
 
2
  base_model: mor40/BulBERT-finetuned-cinexio
3
  tags:
4
  - generated_from_trainer
 
 
5
  metrics:
6
  - accuracy
7
  model-index:
8
  - name: BulBERT-cinexio-5pochs
9
+ results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
14
 
15
  # BulBERT-cinexio-5pochs
16
 
17
+ This model is a fine-tuned version of [mor40/BulBERT-finetuned-cinexio](https://huggingface.co/mor40/BulBERT-finetuned-cinexio) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.1071
20
+ - Accuracy: 0.97
21
 
22
  ## Model description
23
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
+ | No log | 1.0 | 388 | 0.2160 | 0.92 |
52
+ | 0.244 | 2.0 | 776 | 0.1136 | 0.95 |
53
+ | 0.2092 | 3.0 | 1164 | 0.1366 | 0.95 |
54
+ | 0.1607 | 4.0 | 1552 | 0.1228 | 0.94 |
55
+ | 0.1607 | 5.0 | 1940 | 0.1071 | 0.97 |
56
 
57
 
58
  ### Framework versions