gokuls commited on
Commit
6d176db
1 Parent(s): ffa0422

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -20
README.md CHANGED
@@ -1,6 +1,4 @@
1
  ---
2
- language:
3
- - en
4
  tags:
5
  - generated_from_trainer
6
  datasets:
@@ -15,7 +13,7 @@ model-index:
15
  name: Text Classification
16
  type: text-classification
17
  dataset:
18
- name: GLUE MRPC
19
  type: glue
20
  config: mrpc
21
  split: validation
@@ -23,10 +21,10 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.6838235294117647
27
  - name: F1
28
  type: f1
29
- value: 0.8122270742358079
30
  ---
31
 
32
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,12 +32,12 @@ should probably proofread and complete it, then remove this comment. -->
34
 
35
  # hBERTv1_new_pretrain_w_init__mrpc
36
 
37
- This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_wt_init](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_wt_init) on the GLUE MRPC dataset.
38
  It achieves the following results on the evaluation set:
39
- - Loss: 0.6237
40
- - Accuracy: 0.6838
41
- - F1: 0.8122
42
- - Combined Score: 0.7480
43
 
44
  ## Model description
45
 
@@ -58,7 +56,7 @@ More information needed
58
  ### Training hyperparameters
59
 
60
  The following hyperparameters were used during training:
61
- - learning_rate: 0.0005
62
  - train_batch_size: 128
63
  - eval_batch_size: 128
64
  - seed: 10
@@ -71,15 +69,15 @@ The following hyperparameters were used during training:
71
 
72
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
73
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
74
- | 3.2785 | 1.0 | 29 | 0.6238 | 0.6838 | 0.8122 | 0.7480 |
75
- | 0.7343 | 2.0 | 58 | 0.6786 | 0.6838 | 0.8122 | 0.7480 |
76
- | 0.6377 | 3.0 | 87 | 0.6245 | 0.6838 | 0.8122 | 0.7480 |
77
- | 0.6353 | 4.0 | 116 | 0.6237 | 0.6838 | 0.8122 | 0.7480 |
78
- | 0.6344 | 5.0 | 145 | 0.6244 | 0.6838 | 0.8122 | 0.7480 |
79
- | 0.6314 | 6.0 | 174 | 0.6324 | 0.6838 | 0.8122 | 0.7480 |
80
- | 0.6431 | 7.0 | 203 | 0.6402 | 0.6838 | 0.8122 | 0.7480 |
81
- | 0.6347 | 8.0 | 232 | 0.6336 | 0.6838 | 0.8122 | 0.7480 |
82
- | 0.6343 | 9.0 | 261 | 0.6258 | 0.6838 | 0.8122 | 0.7480 |
83
 
84
 
85
  ### Framework versions
 
1
  ---
 
 
2
  tags:
3
  - generated_from_trainer
4
  datasets:
 
13
  name: Text Classification
14
  type: text-classification
15
  dataset:
16
+ name: glue
17
  type: glue
18
  config: mrpc
19
  split: validation
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.5735294117647058
25
  - name: F1
26
  type: f1
27
+ value: 0.65748031496063
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  # hBERTv1_new_pretrain_w_init__mrpc
34
 
35
+ This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_wt_init](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_wt_init) on the glue dataset.
36
  It achieves the following results on the evaluation set:
37
+ - Loss: 1.3076
38
+ - Accuracy: 0.5735
39
+ - F1: 0.6575
40
+ - Combined Score: 0.6155
41
 
42
  ## Model description
43
 
 
56
  ### Training hyperparameters
57
 
58
  The following hyperparameters were used during training:
59
+ - learning_rate: 4e-05
60
  - train_batch_size: 128
61
  - eval_batch_size: 128
62
  - seed: 10
 
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
71
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
72
+ | 0.7111 | 1.0 | 29 | 0.6564 | 0.6838 | 0.8122 | 0.7480 |
73
+ | 0.6641 | 2.0 | 58 | 0.6160 | 0.6838 | 0.8122 | 0.7480 |
74
+ | 0.6156 | 3.0 | 87 | 0.6354 | 0.6838 | 0.8122 | 0.7480 |
75
+ | 0.5817 | 4.0 | 116 | 0.6082 | 0.6863 | 0.7895 | 0.7379 |
76
+ | 0.5091 | 5.0 | 145 | 0.7812 | 0.5074 | 0.5157 | 0.5115 |
77
+ | 0.3973 | 6.0 | 174 | 0.7949 | 0.6544 | 0.7565 | 0.7054 |
78
+ | 0.2966 | 7.0 | 203 | 1.0388 | 0.6078 | 0.6887 | 0.6483 |
79
+ | 0.2024 | 8.0 | 232 | 1.0065 | 0.6201 | 0.7124 | 0.6663 |
80
+ | 0.1621 | 9.0 | 261 | 1.3076 | 0.5735 | 0.6575 | 0.6155 |
81
 
82
 
83
  ### Framework versions