mdroth commited on
Commit
9b6f44e
1 Parent(s): 440ed95

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -14
README.md CHANGED
@@ -22,16 +22,16 @@ model-index:
22
  metrics:
23
  - name: Precision
24
  type: precision
25
- value: 0.9233990962195525
26
  - name: Recall
27
  type: recall
28
- value: 0.9372413021590782
29
  - name: F1
30
  type: f1
31
- value: 0.9302687097490562
32
  - name: Accuracy
33
  type: accuracy
34
- value: 0.9833193003637981
35
  ---
36
 
37
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -41,11 +41,11 @@ should probably proofread and complete it, then remove this comment. -->
41
 
42
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the conll2003 dataset.
43
  It achieves the following results on the evaluation set:
44
- - Loss: 0.0619
45
- - Precision: 0.9234
46
- - Recall: 0.9372
47
- - F1: 0.9303
48
- - Accuracy: 0.9833
49
 
50
  ## Model description
51
 
@@ -65,8 +65,8 @@ More information needed
65
 
66
  The following hyperparameters were used during training:
67
  - learning_rate: 2e-05
68
- - train_batch_size: 16
69
- - eval_batch_size: 16
70
  - seed: 42
71
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
72
  - lr_scheduler_type: linear
@@ -76,9 +76,9 @@ The following hyperparameters were used during training:
76
 
77
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
78
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
79
- | 0.2421 | 1.0 | 878 | 0.0750 | 0.9086 | 0.9178 | 0.9132 | 0.9797 |
80
- | 0.056 | 2.0 | 1756 | 0.0601 | 0.9213 | 0.9363 | 0.9288 | 0.9828 |
81
- | 0.0319 | 3.0 | 2634 | 0.0619 | 0.9234 | 0.9372 | 0.9303 | 0.9833 |
82
 
83
 
84
  ### Framework versions
 
22
  metrics:
23
  - name: Precision
24
  type: precision
25
+ value: 0.9299878143347735
26
  - name: Recall
27
  type: recall
28
+ value: 0.9391430808815304
29
  - name: F1
30
  type: f1
31
+ value: 0.93454302571524
32
  - name: Accuracy
33
  type: accuracy
34
+ value: 0.9841453921553053
35
  ---
36
 
37
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
41
 
42
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the conll2003 dataset.
43
  It achieves the following results on the evaluation set:
44
+ - Loss: 0.0635
45
+ - Precision: 0.9300
46
+ - Recall: 0.9391
47
+ - F1: 0.9345
48
+ - Accuracy: 0.9841
49
 
50
  ## Model description
51
 
 
65
 
66
  The following hyperparameters were used during training:
67
  - learning_rate: 2e-05
68
+ - train_batch_size: 8
69
+ - eval_batch_size: 8
70
  - seed: 42
71
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
72
  - lr_scheduler_type: linear
 
76
 
77
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
78
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
79
+ | 0.0886 | 1.0 | 1756 | 0.0676 | 0.9198 | 0.9233 | 0.9215 | 0.9809 |
80
+ | 0.0382 | 2.0 | 3512 | 0.0605 | 0.9271 | 0.9360 | 0.9315 | 0.9836 |
81
+ | 0.0247 | 3.0 | 5268 | 0.0635 | 0.9300 | 0.9391 | 0.9345 | 0.9841 |
82
 
83
 
84
  ### Framework versions