Hugging Face's logo

KellyShiiii
/
bert-finetuned-ner

Token Classification
Transformers
PyTorch
xlm-roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
KellyShiiii commited on
Commit
374056b
•
1 Parent(s): a60dcd6

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +27 -38
README.md CHANGED
@@ -1,5 +1,4 @@
1
  ---
2
- license: mit
3
  tags:
4
  - generated_from_trainer
5
  metrics:
@@ -17,13 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # bert-finetuned-ner
19
 
20
- This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.7548
23
- - Precision: 0.5675
24
- - Recall: 0.6595
25
- - F1: 0.6101
26
- - Accuracy: 0.8643
27
 
28
  ## Model description
29
 
@@ -48,42 +47,32 @@ The following hyperparameters were used during training:
48
  - seed: 42
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
- - num_epochs: 30
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
56
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
57
- | No log | 1.0 | 50 | 0.8557 | 0.0617 | 0.0862 | 0.0719 | 0.7201 |
58
- | No log | 2.0 | 100 | 0.6027 | 0.2938 | 0.3607 | 0.3238 | 0.8110 |
59
- | No log | 3.0 | 150 | 0.4913 | 0.3897 | 0.5009 | 0.4384 | 0.8415 |
60
- | No log | 4.0 | 200 | 0.4807 | 0.4517 | 0.5365 | 0.4905 | 0.8490 |
61
- | No log | 5.0 | 250 | 0.4643 | 0.4915 | 0.5651 | 0.5257 | 0.8559 |
62
- | No log | 6.0 | 300 | 0.4885 | 0.4896 | 0.6043 | 0.5410 | 0.8514 |
63
- | No log | 7.0 | 350 | 0.4952 | 0.5066 | 0.6144 | 0.5553 | 0.8578 |
64
- | No log | 8.0 | 400 | 0.4889 | 0.5298 | 0.6179 | 0.5705 | 0.8621 |
65
- | No log | 9.0 | 450 | 0.5160 | 0.5554 | 0.6286 | 0.5897 | 0.8668 |
66
- | 0.4185 | 10.0 | 500 | 0.5422 | 0.5277 | 0.6275 | 0.5733 | 0.8581 |
67
- | 0.4185 | 11.0 | 550 | 0.5709 | 0.5414 | 0.6411 | 0.5871 | 0.8579 |
68
- | 0.4185 | 12.0 | 600 | 0.5952 | 0.5275 | 0.6494 | 0.5822 | 0.8531 |
69
- | 0.4185 | 13.0 | 650 | 0.5890 | 0.5479 | 0.6453 | 0.5926 | 0.8621 |
70
- | 0.4185 | 14.0 | 700 | 0.5938 | 0.5437 | 0.6542 | 0.5939 | 0.8602 |
71
- | 0.4185 | 15.0 | 750 | 0.6271 | 0.5417 | 0.6441 | 0.5885 | 0.8597 |
72
- | 0.4185 | 16.0 | 800 | 0.6643 | 0.5428 | 0.6518 | 0.5923 | 0.8557 |
73
- | 0.4185 | 17.0 | 850 | 0.6526 | 0.5620 | 0.6405 | 0.5987 | 0.8647 |
74
- | 0.4185 | 18.0 | 900 | 0.6820 | 0.5656 | 0.6477 | 0.6039 | 0.8619 |
75
- | 0.4185 | 19.0 | 950 | 0.6864 | 0.5582 | 0.6667 | 0.6076 | 0.8620 |
76
- | 0.0767 | 20.0 | 1000 | 0.6959 | 0.5625 | 0.6655 | 0.6097 | 0.8638 |
77
- | 0.0767 | 21.0 | 1050 | 0.7041 | 0.5625 | 0.6607 | 0.6077 | 0.8632 |
78
- | 0.0767 | 22.0 | 1100 | 0.7204 | 0.5587 | 0.6583 | 0.6045 | 0.8604 |
79
- | 0.0767 | 23.0 | 1150 | 0.7162 | 0.5645 | 0.6524 | 0.6053 | 0.8635 |
80
- | 0.0767 | 24.0 | 1200 | 0.7343 | 0.5503 | 0.6500 | 0.5960 | 0.8619 |
81
- | 0.0767 | 25.0 | 1250 | 0.7466 | 0.5633 | 0.6506 | 0.6038 | 0.8644 |
82
- | 0.0767 | 26.0 | 1300 | 0.7410 | 0.5743 | 0.6548 | 0.6119 | 0.8654 |
83
- | 0.0767 | 27.0 | 1350 | 0.7478 | 0.5699 | 0.6613 | 0.6122 | 0.8674 |
84
- | 0.0767 | 28.0 | 1400 | 0.7524 | 0.5714 | 0.6613 | 0.6131 | 0.8650 |
85
- | 0.0767 | 29.0 | 1450 | 0.7523 | 0.5728 | 0.6572 | 0.6121 | 0.8657 |
86
- | 0.0317 | 30.0 | 1500 | 0.7548 | 0.5675 | 0.6595 | 0.6101 | 0.8643 |
87
 
88
 
89
  ### Framework versions
 
1
  ---
 
2
  tags:
3
  - generated_from_trainer
4
  metrics:
 
16
 
17
  # bert-finetuned-ner
18
 
19
+ This model was trained from scratch on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.7451
22
+ - Precision: 0.4163
23
+ - Recall: 0.3481
24
+ - F1: 0.3791
25
+ - Accuracy: 0.9057
26
 
27
  ## Model description
28
 
 
47
  - seed: 42
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
+ - num_epochs: 20
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
56
+ | No log | 1.0 | 125 | 0.4506 | 0.2801 | 0.1713 | 0.2126 | 0.8852 |
57
+ | No log | 2.0 | 250 | 0.4257 | 0.3293 | 0.3039 | 0.3161 | 0.8992 |
58
+ | No log | 3.0 | 375 | 0.4821 | 0.3899 | 0.3260 | 0.3551 | 0.9059 |
59
+ | 0.1136 | 4.0 | 500 | 0.5208 | 0.3768 | 0.3775 | 0.3772 | 0.9062 |
60
+ | 0.1136 | 5.0 | 625 | 0.5434 | 0.3903 | 0.3996 | 0.3949 | 0.9087 |
61
+ | 0.1136 | 6.0 | 750 | 0.6386 | 0.4454 | 0.3683 | 0.4032 | 0.9079 |
62
+ | 0.1136 | 7.0 | 875 | 0.6286 | 0.4148 | 0.3812 | 0.3973 | 0.9056 |
63
+ | 0.0077 | 8.0 | 1000 | 0.6875 | 0.4151 | 0.3241 | 0.3640 | 0.9037 |
64
+ | 0.0077 | 9.0 | 1125 | 0.7166 | 0.4161 | 0.3241 | 0.3644 | 0.9039 |
65
+ | 0.0077 | 10.0 | 1250 | 0.7340 | 0.4118 | 0.3223 | 0.3616 | 0.9061 |
66
+ | 0.0077 | 11.0 | 1375 | 0.6873 | 0.4161 | 0.3517 | 0.3812 | 0.9075 |
67
+ | 0.0015 | 12.0 | 1500 | 0.7451 | 0.4195 | 0.3168 | 0.3610 | 0.9028 |
68
+ | 0.0015 | 13.0 | 1625 | 0.7303 | 0.4179 | 0.3517 | 0.3820 | 0.9068 |
69
+ | 0.0015 | 14.0 | 1750 | 0.7652 | 0.3968 | 0.3186 | 0.3534 | 0.9047 |
70
+ | 0.0015 | 15.0 | 1875 | 0.7891 | 0.4140 | 0.3149 | 0.3577 | 0.9036 |
71
+ | 0.0006 | 16.0 | 2000 | 0.7651 | 0.4209 | 0.3333 | 0.3720 | 0.9049 |
72
+ | 0.0006 | 17.0 | 2125 | 0.7746 | 0.4 | 0.3168 | 0.3535 | 0.9046 |
73
+ | 0.0006 | 18.0 | 2250 | 0.7457 | 0.4169 | 0.3462 | 0.3783 | 0.9053 |
74
+ | 0.0006 | 19.0 | 2375 | 0.7487 | 0.4178 | 0.3462 | 0.3787 | 0.9058 |
75
+ | 0.0004 | 20.0 | 2500 | 0.7451 | 0.4163 | 0.3481 | 0.3791 | 0.9057 |
 
 
 
 
 
 
 
 
 
 
76
 
77
 
78
  ### Framework versions