Kriyans commited on
Commit
912de35
1 Parent(s): 21e6ec9

End of training

Browse files
Files changed (1) hide show
  1. README.md +15 -20
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.980007544322897
29
  - name: Recall
30
  type: recall
31
- value: 0.979145728643216
32
  - name: F1
33
  type: f1
34
- value: 0.9795764469301829
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9962591162591162
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,11 +44,11 @@ should probably proofread and complete it, then remove this comment. -->
44
 
45
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the indian_names dataset.
46
  It achieves the following results on the evaluation set:
47
- - Loss: 0.0148
48
- - Precision: 0.9800
49
- - Recall: 0.9791
50
- - F1: 0.9796
51
- - Accuracy: 0.9963
52
 
53
  ## Model description
54
 
@@ -73,22 +73,17 @@ The following hyperparameters were used during training:
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
- - num_epochs: 10
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | No log | 1.0 | 66 | 0.1644 | 0.1903 | 0.1692 | 0.1791 | 0.8817 |
83
- | No log | 2.0 | 132 | 0.1154 | 0.9760 | 0.8181 | 0.8901 | 0.9703 |
84
- | No log | 3.0 | 198 | 0.0921 | 0.9755 | 0.9046 | 0.9387 | 0.9795 |
85
- | No log | 4.0 | 264 | 0.0586 | 0.9616 | 0.9193 | 0.9400 | 0.9849 |
86
- | No log | 5.0 | 330 | 0.0465 | 0.9588 | 0.9219 | 0.9400 | 0.9861 |
87
- | No log | 6.0 | 396 | 0.0346 | 0.9359 | 0.9460 | 0.9409 | 0.9902 |
88
- | No log | 7.0 | 462 | 0.0227 | 0.9708 | 0.9678 | 0.9693 | 0.9941 |
89
- | 0.1068 | 8.0 | 528 | 0.0199 | 0.9753 | 0.9734 | 0.9743 | 0.9946 |
90
- | 0.1068 | 9.0 | 594 | 0.0155 | 0.9801 | 0.9784 | 0.9793 | 0.9961 |
91
- | 0.1068 | 10.0 | 660 | 0.0148 | 0.9800 | 0.9791 | 0.9796 | 0.9963 |
92
 
93
 
94
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.9961035696329814
29
  - name: Recall
30
  type: recall
31
+ value: 0.9956030150753769
32
  - name: F1
33
  type: f1
34
+ value: 0.9958532294546368
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9992964392964393
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
44
 
45
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the indian_names dataset.
46
  It achieves the following results on the evaluation set:
47
+ - Loss: 0.0042
48
+ - Precision: 0.9961
49
+ - Recall: 0.9956
50
+ - F1: 0.9959
51
+ - Accuracy: 0.9993
52
 
53
  ## Model description
54
 
 
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
+ - num_epochs: 5
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | No log | 1.0 | 66 | 0.0152 | 0.9810 | 0.9820 | 0.9815 | 0.9963 |
83
+ | No log | 2.0 | 132 | 0.0108 | 0.9850 | 0.9849 | 0.9850 | 0.9971 |
84
+ | No log | 3.0 | 198 | 0.0067 | 0.9913 | 0.9920 | 0.9916 | 0.9986 |
85
+ | No log | 4.0 | 264 | 0.0056 | 0.9927 | 0.9928 | 0.9928 | 0.9988 |
86
+ | No log | 5.0 | 330 | 0.0042 | 0.9961 | 0.9956 | 0.9959 | 0.9993 |
 
 
 
 
 
87
 
88
 
89
  ### Framework versions