Hugging Face's logo

ramybaly
/
ner_conll2003

Token Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Model card Files
xet
Metrics Community
2
ramybaly commited on
Commit
1727d8c
·
1 Parent(s): a733b6d

add model

Browse files
Files changed (8) hide show
  1. README.md +12 -17
  2. pytorch_model.bin +1 -1
  3. runs/Aug12_19-17-15_ip-172-31-23-147/1628795854.910452/events.out.tfevents.1628795854.ip-172-31-23-147.3799.1 +3 -0
  4. runs/Aug12_19-17-15_ip-172-31-23-147/events.out.tfevents.1628795854.ip-172-31-23-147.3799.0 +3 -0
  5. runs/Aug12_19-28-36_ip-172-31-23-147/1628796521.9948075/events.out.tfevents.1628796521.ip-172-31-23-147.8443.1 +3 -0
  6. runs/Aug12_19-28-36_ip-172-31-23-147/events.out.tfevents.1628796521.ip-172-31-23-147.8443.0 +3 -0
  7. runs/Aug12_19-28-36_ip-172-31-23-147/events.out.tfevents.1628796960.ip-172-31-23-147.8443.2 +3 -0
  8. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model_index:
22
  metric:
23
  name: Accuracy
24
  type: accuracy
25
- value: 0.9764571468139249
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,11 +32,11 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the conll2003 dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.1941
36
- - Precision: 0.8980
37
- - Recall: 0.9062
38
- - F1: 0.9021
39
- - Accuracy: 0.9765
40
 
41
  ## Model description
42
 
@@ -62,22 +62,17 @@ The following hyperparameters were used during training:
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_ratio: 0.1
65
- - num_epochs: 10
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
70
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
71
- | 0.3854 | 1.0 | 877 | 0.0670 | 0.9185 | 0.9248 | 0.9217 | 0.9818 |
72
- | 0.0578 | 2.0 | 1754 | 0.0511 | 0.9369 | 0.9484 | 0.9426 | 0.9864 |
73
- | 0.029 | 3.0 | 2631 | 0.0576 | 0.9393 | 0.9463 | 0.9428 | 0.9862 |
74
- | 0.0159 | 4.0 | 3508 | 0.0621 | 0.9373 | 0.9477 | 0.9425 | 0.9862 |
75
- | 0.0095 | 5.0 | 4385 | 0.0703 | 0.9370 | 0.9475 | 0.9422 | 0.9859 |
76
- | 0.006 | 6.0 | 5262 | 0.0728 | 0.9373 | 0.9474 | 0.9423 | 0.9860 |
77
- | 0.0042 | 7.0 | 6139 | 0.0728 | 0.9413 | 0.9529 | 0.9471 | 0.9872 |
78
- | 0.0025 | 8.0 | 7016 | 0.0783 | 0.9434 | 0.9505 | 0.9469 | 0.9868 |
79
- | 0.0017 | 9.0 | 7893 | 0.0782 | 0.9425 | 0.9532 | 0.9478 | 0.9870 |
80
- | 0.001 | 10.0 | 8770 | 0.0805 | 0.9431 | 0.9536 | 0.9483 | 0.9872 |
81
 
82
 
83
  ### Framework versions
 
22
  metric:
23
  name: Accuracy
24
  type: accuracy
25
+ value: 0.9765783232641474
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the conll2003 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.1586
36
+ - Precision: 0.8954
37
+ - Recall: 0.9057
38
+ - F1: 0.9005
39
+ - Accuracy: 0.9766
40
 
41
  ## Model description
42
 
 
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_ratio: 0.1
65
+ - num_epochs: 5
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
70
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
71
+ | 0.3167 | 1.0 | 877 | 0.0610 | 0.9198 | 0.9342 | 0.9269 | 0.9832 |
72
+ | 0.0476 | 2.0 | 1754 | 0.0561 | 0.9293 | 0.9405 | 0.9349 | 0.9851 |
73
+ | 0.0238 | 3.0 | 2631 | 0.0564 | 0.9421 | 0.9480 | 0.9450 | 0.9867 |
74
+ | 0.0119 | 4.0 | 3508 | 0.0597 | 0.9436 | 0.9526 | 0.9480 | 0.9872 |
75
+ | 0.0074 | 5.0 | 4385 | 0.0630 | 0.9443 | 0.9556 | 0.9499 | 0.9876 |
 
 
 
 
 
76
 
77
 
78
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79ee27e5626358aaaae45c75a020f1182dc7d57143563729c0bc330cfc4bcf0c
3
  size 435677681
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3373eec271888f667c11607d8981c592c33a784c5561b7b01ce92547aef76d98
3
  size 435677681
runs/Aug12_19-17-15_ip-172-31-23-147/1628795854.910452/events.out.tfevents.1628795854.ip-172-31-23-147.3799.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:392117e7b3ee494e92929e05296a192662d28f54c0b503a494bfd691d2c435a6
3
+ size 4215
runs/Aug12_19-17-15_ip-172-31-23-147/events.out.tfevents.1628795854.ip-172-31-23-147.3799.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:478bc7371b49413aa4703680cfdd54efabd822e6e372888cc2520dbc79a99340
3
+ size 7684
runs/Aug12_19-28-36_ip-172-31-23-147/1628796521.9948075/events.out.tfevents.1628796521.ip-172-31-23-147.8443.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:595569cd0551065b3b64787fee4cb5f52ea2ff0db9e6d1353dad82ad8e9811ee
3
+ size 4215
runs/Aug12_19-28-36_ip-172-31-23-147/events.out.tfevents.1628796521.ip-172-31-23-147.8443.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b9d3347ff8a6a6f17fd0497acc1fc764fe722c19c51ce4b636544e688890770
3
+ size 6779
runs/Aug12_19-28-36_ip-172-31-23-147/events.out.tfevents.1628796960.ip-172-31-23-147.8443.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b463fb1e133c7e46d79fd8e3b940328aa1c7262ea8fb78d1bbf64404b7b9a8af
3
+ size 512
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88b35e755e25520f77bb1f160b08d73c9cad77c77c8dd10a84eab593f19fac06
3
  size 2671
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c110b52c89945e45bc0ec644a7727618af4933534f67e4fa2ae22d222e28b3b3
3
  size 2671