Hugging Face's logo

josh4fun
/
bert-finetuned-ner

Token Classification
Transformers
Safetensors
bert
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Community
josh4fun commited on
Commit
edeb7d6
·
verified ·
1 Parent(s): ebcf73e

Training_complete

Browse files
Files changed (1) hide show
  1. README.md +10 -10
README.md CHANGED
@@ -26,13 +26,13 @@ model-index:
26
  metrics:
27
  - name: Precision
28
  type: precision
29
- value: 0.930988938418359
30
  - name: Recall
31
  type: recall
32
- value: 0.9490070683271625
33
  - name: F1
34
  type: f1
35
- value: 0.939911659304942
36
  - name: Accuracy
37
  type: accuracy
38
  value: 0.9864308000235474
@@ -45,10 +45,10 @@ should probably proofread and complete it, then remove this comment. -->
45
 
46
  This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
47
  It achieves the following results on the evaluation set:
48
- - Loss: 0.1139
49
- - Precision: 0.9310
50
- - Recall: 0.9490
51
- - F1: 0.9399
52
  - Accuracy: 0.9864
53
 
54
  ## Model description
@@ -80,9 +80,9 @@ The following hyperparameters were used during training:
80
 
81
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
82
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
83
- | 0.4556 | 1.0 | 878 | 0.1273 | 0.8913 | 0.9291 | 0.9099 | 0.9813 |
84
- | 0.0918 | 2.0 | 1756 | 0.1192 | 0.9255 | 0.9456 | 0.9355 | 0.9855 |
85
- | 0.0519 | 3.0 | 2634 | 0.1139 | 0.9310 | 0.9490 | 0.9399 | 0.9864 |
86
 
87
 
88
  ### Framework versions
 
26
  metrics:
27
  - name: Precision
28
  type: precision
29
+ value: 0.9345267694347754
30
  - name: Recall
31
  type: recall
32
+ value: 0.9488387748232918
33
  - name: F1
34
  type: f1
35
+ value: 0.9416283924843424
36
  - name: Accuracy
37
  type: accuracy
38
  value: 0.9864308000235474
 
45
 
46
  This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
47
  It achieves the following results on the evaluation set:
48
+ - Loss: 0.1228
49
+ - Precision: 0.9345
50
+ - Recall: 0.9488
51
+ - F1: 0.9416
52
  - Accuracy: 0.9864
53
 
54
  ## Model description
 
80
 
81
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
82
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
83
+ | 0.4732 | 1.0 | 878 | 0.1339 | 0.8998 | 0.9298 | 0.9146 | 0.9821 |
84
+ | 0.0945 | 2.0 | 1756 | 0.1294 | 0.9297 | 0.9458 | 0.9377 | 0.9857 |
85
+ | 0.0542 | 3.0 | 2634 | 0.1228 | 0.9345 | 0.9488 | 0.9416 | 0.9864 |
86
 
87
 
88
  ### Framework versions