urbija commited on
Commit
9b0ba10
·
1 Parent(s): 082cee8

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -1
README.md CHANGED
@@ -2,6 +2,11 @@
2
  license: apache-2.0
3
  tags:
4
  - generated_from_trainer
 
 
 
 
 
5
  model-index:
6
  - name: ner-bio-annotated-3
7
  results: []
@@ -12,7 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
12
 
13
  # ner-bio-annotated-3
14
 
15
- This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 
 
 
 
 
 
16
 
17
  ## Model description
18
 
@@ -40,6 +51,15 @@ The following hyperparameters were used during training:
40
  - lr_scheduler_warmup_ratio: 0.2
41
  - num_epochs: 3
42
 
 
 
 
 
 
 
 
 
 
43
  ### Framework versions
44
 
45
  - Transformers 4.30.2
 
2
  license: apache-2.0
3
  tags:
4
  - generated_from_trainer
5
+ metrics:
6
+ - precision
7
+ - recall
8
+ - f1
9
+ - accuracy
10
  model-index:
11
  - name: ner-bio-annotated-3
12
  results: []
 
17
 
18
  # ner-bio-annotated-3
19
 
20
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.1888
23
+ - Precision: 0.7117
24
+ - Recall: 0.7350
25
+ - F1: 0.7232
26
+ - Accuracy: 0.9461
27
 
28
  ## Model description
29
 
 
51
  - lr_scheduler_warmup_ratio: 0.2
52
  - num_epochs: 3
53
 
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | No log | 1.0 | 67 | 0.2365 | 0.6361 | 0.6498 | 0.6429 | 0.9329 |
59
+ | No log | 2.0 | 134 | 0.2017 | 0.6667 | 0.7079 | 0.6866 | 0.9445 |
60
+ | No log | 3.0 | 201 | 0.1888 | 0.7117 | 0.7350 | 0.7232 | 0.9461 |
61
+
62
+
63
  ### Framework versions
64
 
65
  - Transformers 4.30.2