Motahar commited on
Commit
8a9af50
1 Parent(s): 28d6597

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -32
README.md CHANGED
@@ -4,26 +4,9 @@ tags:
4
  - generated_from_trainer
5
  datasets:
6
  - glue
7
- metrics:
8
- - accuracy
9
- - f1
10
  model-index:
11
  - name: distilbert-sst2-mahtab
12
- results:
13
- - task:
14
- name: Text Classification
15
- type: text-classification
16
- dataset:
17
- name: glue
18
- type: glue
19
- args: sst2
20
- metrics:
21
- - name: Accuracy
22
- type: accuracy
23
- value: 0.8979357798165137
24
- - name: F1
25
- type: f1
26
- value: 0.9010011123470522
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,9 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  This model is a fine-tuned version of [distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english) on the glue dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.5766
37
- - Accuracy: 0.8979
38
- - F1: 0.9010
 
 
 
 
39
 
40
  ## Model description
41
 
@@ -62,18 +49,9 @@ The following hyperparameters were used during training:
62
  - lr_scheduler_type: linear
63
  - num_epochs: 3.0
64
 
65
- ### Training results
66
-
67
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
68
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
69
- | 0.1802 | 1.0 | 8419 | 0.4982 | 0.8830 | 0.8833 |
70
- | 0.0987 | 2.0 | 16838 | 0.5416 | 0.8979 | 0.9025 |
71
- | 0.0534 | 3.0 | 25257 | 0.5766 | 0.8979 | 0.9010 |
72
-
73
-
74
  ### Framework versions
75
 
76
- - Transformers 4.13.0
77
  - Pytorch 1.10.0+cu111
78
- - Datasets 1.16.1
79
  - Tokenizers 0.10.3
 
4
  - generated_from_trainer
5
  datasets:
6
  - glue
 
 
 
7
  model-index:
8
  - name: distilbert-sst2-mahtab
9
+ results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
16
 
17
  This model is a fine-tuned version of [distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english) on the glue dataset.
18
  It achieves the following results on the evaluation set:
19
+ - eval_loss: 0.4982
20
+ - eval_accuracy: 0.8830
21
+ - eval_runtime: 2.3447
22
+ - eval_samples_per_second: 371.91
23
+ - eval_steps_per_second: 46.489
24
+ - epoch: 1.0
25
+ - step: 8419
26
 
27
  ## Model description
28
 
 
49
  - lr_scheduler_type: linear
50
  - num_epochs: 3.0
51
 
 
 
 
 
 
 
 
 
 
52
  ### Framework versions
53
 
54
+ - Transformers 4.15.0
55
  - Pytorch 1.10.0+cu111
56
+ - Datasets 1.17.0
57
  - Tokenizers 0.10.3