Hugging Face's logo

NeverLearn
/
deberta-v3-base-finetuned-ner

Token Classification
Transformers
Safetensors
deberta-v2
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Community
NeverLearn commited on
Commit
f078471
·
verified ·
1 Parent(s): 6337364

End of training

Browse files
Files changed (2) hide show
  1. README.md +40 -40
  2. model.safetensors +1 -1
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.7551322056166858
29
  - name: Recall
30
  type: recall
31
- value: 0.761636574457512
32
  - name: F1
33
  type: f1
34
- value: 0.7583704436747484
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.8401339561117476
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,11 +44,11 @@ should probably proofread and complete it, then remove this comment. -->
44
 
45
  This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the maccrobat_biomedical_ner dataset.
46
  It achieves the following results on the evaluation set:
47
- - Loss: 0.7336
48
- - Precision: 0.7551
49
- - Recall: 0.7616
50
- - F1: 0.7584
51
- - Accuracy: 0.8401
52
 
53
  ## Model description
54
 
@@ -67,7 +67,7 @@ More information needed
67
  ### Training hyperparameters
68
 
69
  The following hyperparameters were used during training:
70
- - learning_rate: 2e-05
71
  - train_batch_size: 8
72
  - eval_batch_size: 8
73
  - seed: 42
@@ -79,36 +79,36 @@ The following hyperparameters were used during training:
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | No log | 1.0 | 20 | 1.8660 | 0.4196 | 0.2490 | 0.3125 | 0.5855 |
83
- | No log | 2.0 | 40 | 1.3287 | 0.5964 | 0.4646 | 0.5223 | 0.6906 |
84
- | No log | 3.0 | 60 | 1.1197 | 0.6280 | 0.5811 | 0.6036 | 0.7431 |
85
- | No log | 4.0 | 80 | 0.9402 | 0.6943 | 0.6290 | 0.6600 | 0.7787 |
86
- | No log | 5.0 | 100 | 0.8331 | 0.6948 | 0.6954 | 0.6951 | 0.7979 |
87
- | No log | 6.0 | 120 | 0.7917 | 0.7451 | 0.6790 | 0.7105 | 0.8068 |
88
- | No log | 7.0 | 140 | 0.7181 | 0.7259 | 0.7138 | 0.7198 | 0.8133 |
89
- | No log | 8.0 | 160 | 0.7181 | 0.7389 | 0.6979 | 0.7178 | 0.8133 |
90
- | No log | 9.0 | 180 | 0.6882 | 0.7290 | 0.7204 | 0.7247 | 0.8163 |
91
- | No log | 10.0 | 200 | 0.6795 | 0.7709 | 0.7209 | 0.7451 | 0.8287 |
92
- | No log | 11.0 | 220 | 0.6718 | 0.7310 | 0.7323 | 0.7317 | 0.8227 |
93
- | No log | 12.0 | 240 | 0.6207 | 0.7547 | 0.7348 | 0.7446 | 0.8291 |
94
- | No log | 13.0 | 260 | 0.6354 | 0.7668 | 0.7398 | 0.7531 | 0.8363 |
95
- | No log | 14.0 | 280 | 0.6438 | 0.7436 | 0.7543 | 0.7490 | 0.8327 |
96
- | No log | 15.0 | 300 | 0.6689 | 0.7343 | 0.7442 | 0.7392 | 0.8281 |
97
- | No log | 16.0 | 320 | 0.6715 | 0.7246 | 0.7588 | 0.7413 | 0.8237 |
98
- | No log | 17.0 | 340 | 0.6284 | 0.7685 | 0.7469 | 0.7576 | 0.8397 |
99
- | No log | 18.0 | 360 | 0.6585 | 0.7378 | 0.7596 | 0.7486 | 0.8311 |
100
- | No log | 19.0 | 380 | 0.6183 | 0.7560 | 0.7492 | 0.7526 | 0.8378 |
101
- | No log | 20.0 | 400 | 0.6471 | 0.7470 | 0.7640 | 0.7554 | 0.8371 |
102
- | No log | 21.0 | 420 | 0.6743 | 0.7727 | 0.7383 | 0.7551 | 0.8391 |
103
- | No log | 22.0 | 440 | 0.6650 | 0.7755 | 0.7399 | 0.7573 | 0.8403 |
104
- | No log | 23.0 | 460 | 0.6918 | 0.7486 | 0.7563 | 0.7525 | 0.8358 |
105
- | No log | 24.0 | 480 | 0.6686 | 0.7732 | 0.7522 | 0.7626 | 0.8422 |
106
- | 0.6134 | 25.0 | 500 | 0.7168 | 0.7451 | 0.7729 | 0.7588 | 0.8386 |
107
- | 0.6134 | 26.0 | 520 | 0.6755 | 0.7770 | 0.7595 | 0.7681 | 0.8466 |
108
- | 0.6134 | 27.0 | 540 | 0.7206 | 0.7541 | 0.7613 | 0.7577 | 0.8393 |
109
- | 0.6134 | 28.0 | 560 | 0.7142 | 0.7597 | 0.7568 | 0.7583 | 0.8403 |
110
- | 0.6134 | 29.0 | 580 | 0.7382 | 0.7525 | 0.7630 | 0.7577 | 0.8409 |
111
- | 0.6134 | 30.0 | 600 | 0.7336 | 0.7551 | 0.7616 | 0.7584 | 0.8401 |
112
 
113
 
114
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.7843711467324291
29
  - name: Recall
30
  type: recall
31
+ value: 0.7816003686069728
32
  - name: F1
33
  type: f1
34
+ value: 0.7829833064081853
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.8584199081903842
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
44
 
45
  This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the maccrobat_biomedical_ner dataset.
46
  It achieves the following results on the evaluation set:
47
+ - Loss: 0.9704
48
+ - Precision: 0.7844
49
+ - Recall: 0.7816
50
+ - F1: 0.7830
51
+ - Accuracy: 0.8584
52
 
53
  ## Model description
54
 
 
67
  ### Training hyperparameters
68
 
69
  The following hyperparameters were used during training:
70
+ - learning_rate: 4.555607052152088e-05
71
  - train_batch_size: 8
72
  - eval_batch_size: 8
73
  - seed: 42
 
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | No log | 1.0 | 20 | 0.9499 | 0.7670 | 0.7685 | 0.7678 | 0.8477 |
83
+ | No log | 2.0 | 40 | 0.9042 | 0.7721 | 0.7629 | 0.7675 | 0.8484 |
84
+ | No log | 3.0 | 60 | 0.9360 | 0.7674 | 0.7573 | 0.7623 | 0.8475 |
85
+ | No log | 4.0 | 80 | 0.8984 | 0.7630 | 0.7589 | 0.7609 | 0.8442 |
86
+ | No log | 5.0 | 100 | 0.8159 | 0.7695 | 0.7701 | 0.7698 | 0.8495 |
87
+ | No log | 6.0 | 120 | 0.8086 | 0.7557 | 0.7730 | 0.7643 | 0.8454 |
88
+ | No log | 7.0 | 140 | 0.7937 | 0.7766 | 0.7712 | 0.7739 | 0.8509 |
89
+ | No log | 8.0 | 160 | 0.8430 | 0.7703 | 0.7707 | 0.7705 | 0.8513 |
90
+ | No log | 9.0 | 180 | 0.8711 | 0.7715 | 0.7710 | 0.7712 | 0.8517 |
91
+ | No log | 10.0 | 200 | 0.8649 | 0.7687 | 0.7626 | 0.7656 | 0.8485 |
92
+ | No log | 11.0 | 220 | 0.8686 | 0.7817 | 0.7635 | 0.7725 | 0.8516 |
93
+ | No log | 12.0 | 240 | 0.8644 | 0.7765 | 0.7802 | 0.7784 | 0.8546 |
94
+ | No log | 13.0 | 260 | 0.8680 | 0.7771 | 0.7796 | 0.7783 | 0.8550 |
95
+ | No log | 14.0 | 280 | 0.8845 | 0.7728 | 0.7748 | 0.7738 | 0.8528 |
96
+ | No log | 15.0 | 300 | 0.9084 | 0.7774 | 0.7713 | 0.7743 | 0.8537 |
97
+ | No log | 16.0 | 320 | 0.9396 | 0.7782 | 0.7659 | 0.7720 | 0.8509 |
98
+ | No log | 17.0 | 340 | 0.9338 | 0.7776 | 0.7781 | 0.7778 | 0.8547 |
99
+ | No log | 18.0 | 360 | 0.9205 | 0.7749 | 0.7770 | 0.7759 | 0.8537 |
100
+ | No log | 19.0 | 380 | 0.9426 | 0.7781 | 0.7724 | 0.7752 | 0.8523 |
101
+ | No log | 20.0 | 400 | 0.9403 | 0.7769 | 0.7827 | 0.7798 | 0.8550 |
102
+ | No log | 21.0 | 420 | 0.9393 | 0.7795 | 0.7713 | 0.7754 | 0.8536 |
103
+ | No log | 22.0 | 440 | 0.9618 | 0.7771 | 0.7790 | 0.7780 | 0.8547 |
104
+ | No log | 23.0 | 460 | 0.9420 | 0.7814 | 0.7836 | 0.7825 | 0.8582 |
105
+ | No log | 24.0 | 480 | 0.9455 | 0.7842 | 0.7808 | 0.7825 | 0.8583 |
106
+ | 0.0412 | 25.0 | 500 | 0.9599 | 0.7821 | 0.7801 | 0.7811 | 0.8571 |
107
+ | 0.0412 | 26.0 | 520 | 0.9518 | 0.7815 | 0.7833 | 0.7824 | 0.8578 |
108
+ | 0.0412 | 27.0 | 540 | 0.9570 | 0.7800 | 0.7818 | 0.7809 | 0.8567 |
109
+ | 0.0412 | 28.0 | 560 | 0.9634 | 0.7819 | 0.7801 | 0.7810 | 0.8573 |
110
+ | 0.0412 | 29.0 | 580 | 0.9685 | 0.7818 | 0.7831 | 0.7825 | 0.8579 |
111
+ | 0.0412 | 30.0 | 600 | 0.9704 | 0.7844 | 0.7816 | 0.7830 | 0.8584 |
112
 
113
 
114
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbd99ab904c0eec0ed88e971a6a1e1cedd4f8f19ec0bf7adec0d6cd7fd53bc40
3
  size 735605900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03d64f233475d26e61252b0d35e7b95c18b49de006c37cf4bce9083f9fe1be74
3
  size 735605900