Hugging Face's logo

Nathali99
/
bert-finetuned-ner4

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Nathali99 commited on
Commit
36aea36
•
1 Parent(s): 73c0d70

Training complete

Browse files
Files changed (1) hide show
  1. README.md +11 -16
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.0821
25
- - Precision: 0.7987
26
- - Recall: 0.8430
27
- - F1: 0.8202
28
- - Accuracy: 0.9729
29
 
30
  ## Model description
31
 
@@ -50,20 +50,15 @@ The following hyperparameters were used during training:
50
  - seed: 42
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
- - num_epochs: 5
54
 
55
  ### Training results
56
 
57
- | Training Loss | Epoch | Step | Accuracy | F1 | Validation Loss | Precision | Recall |
58
- |:-------------:|:-----:|:-----:|:--------:|:------:|:---------------:|:---------:|:------:|
59
- | 0.2376 | 1.0 | 2844 | 0.9370 | 0.7101 | 0.1703 | 0.6321 | 0.8101 |
60
- | 0.1568 | 2.0 | 5688 | 0.9418 | 0.7482 | 0.1650 | 0.6729 | 0.8424 |
61
- | 0.1848 | 3.0 | 8532 | 0.9435 | 0.7616 | 0.1608 | 0.6899 | 0.8500 |
62
- | 0.1275 | 3.0 | 10944 | 0.9643 | 0.7365 | 0.1070 | 0.7120 | 0.7627 |
63
- | 0.1023 | 4.0 | 14592 | 0.9654 | 0.7514 | 0.1035 | 0.7172 | 0.7890 |
64
- | 0.1018 | 5.0 | 18240 | 0.9665 | 0.7590 | 0.1012 | 0.7290 | 0.7917 |
65
- | 0.1234 | 4.0 | 23512 | 0.0815 | 0.7963 | 0.8435 | 0.8192 | 0.9730 |
66
- | 0.1303 | 5.0 | 29390 | 0.0821 | 0.7987 | 0.8430 | 0.8202 | 0.9729 |
67
 
68
 
69
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.1612
25
+ - Precision: 0.6881
26
+ - Recall: 0.8443
27
+ - F1: 0.7582
28
+ - Accuracy: 0.9428
29
 
30
  ## Model description
31
 
 
50
  - seed: 42
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
+ - num_epochs: 3
54
 
55
  ### Training results
56
 
57
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
+ | 0.2338 | 1.0 | 2844 | 0.1673 | 0.6431 | 0.8087 | 0.7164 | 0.9389 |
60
+ | 0.1542 | 2.0 | 5688 | 0.1638 | 0.6786 | 0.8411 | 0.7511 | 0.9420 |
61
+ | 0.1998 | 3.0 | 8532 | 0.1612 | 0.6881 | 0.8443 | 0.7582 | 0.9428 |
 
 
 
 
 
62
 
63
 
64
  ### Framework versions