Kriyans commited on
Commit
4d2cc11
1 Parent(s): 17fe338

End of training

Browse files
Files changed (1) hide show
  1. README.md +15 -17
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: bert-base-multilingual-cased
4
  tags:
5
  - generated_from_trainer
6
  datasets:
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.9950245302230862
29
  - name: Recall
30
  type: recall
31
- value: 0.9949324324324325
32
  - name: F1
33
  type: f1
34
- value: 0.9949784791965567
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9976269686240996
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -42,13 +42,13 @@ should probably proofread and complete it, then remove this comment. -->
42
 
43
  # my_awesome_wnut_model
44
 
45
- This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the ner dataset.
46
  It achieves the following results on the evaluation set:
47
- - Loss: 0.0019
48
- - Precision: 0.9950
49
- - Recall: 0.9949
50
- - F1: 0.9950
51
- - Accuracy: 0.9976
52
 
53
  ## Model description
54
 
@@ -73,17 +73,15 @@ 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: 5
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.0679 | 1.0 | 688 | 0.0131 | 0.9998 | 0.9826 | 0.9911 | 0.9920 |
83
- | 0.0331 | 2.0 | 1376 | 0.0085 | 0.9998 | 0.9826 | 0.9911 | 0.9921 |
84
- | 0.0248 | 3.0 | 2064 | 0.0057 | 0.9999 | 0.9826 | 0.9912 | 0.9921 |
85
- | 0.0155 | 4.0 | 2752 | 0.0026 | 0.9948 | 0.9936 | 0.9942 | 0.9969 |
86
- | 0.0103 | 5.0 | 3440 | 0.0019 | 0.9950 | 0.9949 | 0.9950 | 0.9976 |
87
 
88
 
89
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: distilbert-base-uncased
4
  tags:
5
  - generated_from_trainer
6
  datasets:
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.999514136319467
29
  - name: Recall
30
  type: recall
31
+ value: 0.999560388708931
32
  - name: F1
33
  type: f1
34
+ value: 0.9995372619791305
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9997259356253235
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
42
 
43
  # my_awesome_wnut_model
44
 
45
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the ner dataset.
46
  It achieves the following results on the evaluation set:
47
+ - Loss: 0.0004
48
+ - Precision: 0.9995
49
+ - Recall: 0.9996
50
+ - F1: 0.9995
51
+ - Accuracy: 0.9997
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: 3
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.0416 | 1.0 | 688 | 0.0029 | 0.9957 | 0.9972 | 0.9965 | 0.9980 |
83
+ | 0.008 | 2.0 | 1376 | 0.0010 | 0.9985 | 0.9990 | 0.9987 | 0.9993 |
84
+ | 0.0023 | 3.0 | 2064 | 0.0004 | 0.9995 | 0.9996 | 0.9995 | 0.9997 |
 
 
85
 
86
 
87
  ### Framework versions