Hugging Face's logo

aimarsg
/
ner-2

Token Classification
Transformers
PyTorch
TensorBoard
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
aimarsg commited on
Commit
adaae75
•
1 Parent(s): 79a36a5

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +37 -37
README.md CHANGED
@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [PlanTL-GOB-ES/bsc-bio-ehr-es-pharmaconer](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es-pharmaconer) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.1804
23
- - Precision: 0.6443
24
- - Recall: 0.5708
25
- - F1: 0.6053
26
- - Accuracy: 0.9691
27
 
28
  ## Model description
29
 
@@ -42,7 +42,7 @@ More information needed
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
- - learning_rate: 7e-05
46
  - train_batch_size: 32
47
  - eval_batch_size: 8
48
  - seed: 42
@@ -54,41 +54,41 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
56
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
57
- | No log | 1.0 | 29 | 0.2727 | 0.0 | 0.0 | 0.0 | 0.9392 |
58
- | No log | 2.0 | 58 | 0.2246 | 0.1163 | 0.0228 | 0.0382 | 0.9383 |
59
- | No log | 3.0 | 87 | 0.1744 | 0.3718 | 0.1324 | 0.1953 | 0.9480 |
60
- | No log | 4.0 | 116 | 0.1492 | 0.4734 | 0.3653 | 0.4124 | 0.9569 |
61
- | No log | 5.0 | 145 | 0.1472 | 0.4905 | 0.4703 | 0.4802 | 0.9581 |
62
- | No log | 6.0 | 174 | 0.1320 | 0.5403 | 0.5205 | 0.5302 | 0.9618 |
63
- | No log | 7.0 | 203 | 0.1423 | 0.5922 | 0.5571 | 0.5741 | 0.9667 |
64
- | No log | 8.0 | 232 | 0.1616 | 0.5838 | 0.5251 | 0.5529 | 0.9648 |
65
- | No log | 9.0 | 261 | 0.1443 | 0.6082 | 0.5388 | 0.5714 | 0.9676 |
66
- | No log | 10.0 | 290 | 0.1681 | 0.5990 | 0.5662 | 0.5822 | 0.9654 |
67
- | No log | 11.0 | 319 | 0.1611 | 0.4853 | 0.6027 | 0.5377 | 0.9599 |
68
- | No log | 12.0 | 348 | 0.1751 | 0.4887 | 0.5936 | 0.5361 | 0.9588 |
69
- | No log | 13.0 | 377 | 0.1796 | 0.4819 | 0.6073 | 0.5374 | 0.9593 |
70
- | No log | 14.0 | 406 | 0.1609 | 0.6760 | 0.5525 | 0.6080 | 0.9699 |
71
- | No log | 15.0 | 435 | 0.1821 | 0.5136 | 0.6027 | 0.5546 | 0.9606 |
72
- | No log | 16.0 | 464 | 0.1581 | 0.6462 | 0.5753 | 0.6087 | 0.9691 |
73
- | No log | 17.0 | 493 | 0.1582 | 0.6531 | 0.5845 | 0.6169 | 0.9692 |
74
- | 0.0763 | 18.0 | 522 | 0.1641 | 0.5574 | 0.6210 | 0.5875 | 0.9648 |
75
- | 0.0763 | 19.0 | 551 | 0.1681 | 0.5671 | 0.5982 | 0.5822 | 0.9663 |
76
- | 0.0763 | 20.0 | 580 | 0.1710 | 0.5917 | 0.5890 | 0.5904 | 0.9667 |
77
- | 0.0763 | 21.0 | 609 | 0.1794 | 0.6703 | 0.5662 | 0.6139 | 0.9702 |
78
- | 0.0763 | 22.0 | 638 | 0.1759 | 0.6103 | 0.5936 | 0.6019 | 0.9672 |
79
- | 0.0763 | 23.0 | 667 | 0.1762 | 0.6298 | 0.5982 | 0.6136 | 0.9687 |
80
- | 0.0763 | 24.0 | 696 | 0.1811 | 0.6176 | 0.5753 | 0.5957 | 0.9681 |
81
- | 0.0763 | 25.0 | 725 | 0.1793 | 0.6337 | 0.5845 | 0.6081 | 0.9696 |
82
- | 0.0763 | 26.0 | 754 | 0.1794 | 0.6796 | 0.5616 | 0.615 | 0.9702 |
83
- | 0.0763 | 27.0 | 783 | 0.1776 | 0.6293 | 0.5890 | 0.6085 | 0.9692 |
84
- | 0.0763 | 28.0 | 812 | 0.1796 | 0.6443 | 0.5708 | 0.6053 | 0.9694 |
85
- | 0.0763 | 29.0 | 841 | 0.1803 | 0.6410 | 0.5708 | 0.6039 | 0.9692 |
86
- | 0.0763 | 30.0 | 870 | 0.1804 | 0.6443 | 0.5708 | 0.6053 | 0.9691 |
87
 
88
 
89
  ### Framework versions
90
 
91
  - Transformers 4.28.1
92
  - Pytorch 2.0.0+cu118
93
- - Datasets 2.11.0
94
  - Tokenizers 0.13.3
 
19
 
20
  This model is a fine-tuned version of [PlanTL-GOB-ES/bsc-bio-ehr-es-pharmaconer](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es-pharmaconer) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.1618
23
+ - Precision: 0.7352
24
+ - Recall: 0.6436
25
+ - F1: 0.6863
26
+ - Accuracy: 0.9712
27
 
28
  ## Model description
29
 
 
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
+ - learning_rate: 5e-05
46
  - train_batch_size: 32
47
  - eval_batch_size: 8
48
  - seed: 42
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
56
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
57
+ | No log | 1.0 | 29 | 0.3028 | 0.0 | 0.0 | 0.0 | 0.9220 |
58
+ | No log | 2.0 | 58 | 0.2800 | 0.0 | 0.0 | 0.0 | 0.9220 |
59
+ | No log | 3.0 | 87 | 0.2136 | 0.2105 | 0.0277 | 0.0489 | 0.9302 |
60
+ | No log | 4.0 | 116 | 0.1803 | 0.375 | 0.0727 | 0.1217 | 0.9391 |
61
+ | No log | 5.0 | 145 | 0.1737 | 0.4923 | 0.2215 | 0.3055 | 0.9462 |
62
+ | No log | 6.0 | 174 | 0.1354 | 0.6124 | 0.3772 | 0.4668 | 0.9584 |
63
+ | No log | 7.0 | 203 | 0.1399 | 0.6062 | 0.4048 | 0.4855 | 0.9589 |
64
+ | No log | 8.0 | 232 | 0.1444 | 0.6220 | 0.5294 | 0.5720 | 0.9623 |
65
+ | No log | 9.0 | 261 | 0.1252 | 0.6439 | 0.6194 | 0.6314 | 0.9662 |
66
+ | No log | 10.0 | 290 | 0.1757 | 0.7216 | 0.4394 | 0.5462 | 0.9604 |
67
+ | No log | 11.0 | 319 | 0.1352 | 0.6707 | 0.5779 | 0.6208 | 0.9667 |
68
+ | No log | 12.0 | 348 | 0.1276 | 0.6797 | 0.6021 | 0.6385 | 0.9677 |
69
+ | No log | 13.0 | 377 | 0.1542 | 0.7328 | 0.5882 | 0.6526 | 0.9688 |
70
+ | No log | 14.0 | 406 | 0.1418 | 0.7192 | 0.6471 | 0.6812 | 0.9712 |
71
+ | No log | 15.0 | 435 | 0.1678 | 0.7162 | 0.5502 | 0.6223 | 0.9672 |
72
+ | No log | 16.0 | 464 | 0.1559 | 0.7075 | 0.6194 | 0.6605 | 0.9689 |
73
+ | No log | 17.0 | 493 | 0.1446 | 0.6568 | 0.6886 | 0.6723 | 0.9681 |
74
+ | 0.079 | 18.0 | 522 | 0.1582 | 0.7348 | 0.5848 | 0.6513 | 0.9693 |
75
+ | 0.079 | 19.0 | 551 | 0.1519 | 0.6977 | 0.6228 | 0.6581 | 0.9705 |
76
+ | 0.079 | 20.0 | 580 | 0.1503 | 0.7251 | 0.6298 | 0.6741 | 0.9703 |
77
+ | 0.079 | 21.0 | 609 | 0.1585 | 0.6834 | 0.6125 | 0.6460 | 0.9703 |
78
+ | 0.079 | 22.0 | 638 | 0.1594 | 0.7126 | 0.6263 | 0.6667 | 0.9705 |
79
+ | 0.079 | 23.0 | 667 | 0.1558 | 0.7008 | 0.6401 | 0.6691 | 0.9703 |
80
+ | 0.079 | 24.0 | 696 | 0.1570 | 0.7273 | 0.6367 | 0.6790 | 0.9708 |
81
+ | 0.079 | 25.0 | 725 | 0.1553 | 0.7022 | 0.6609 | 0.6809 | 0.9705 |
82
+ | 0.079 | 26.0 | 754 | 0.1592 | 0.7148 | 0.6332 | 0.6716 | 0.9701 |
83
+ | 0.079 | 27.0 | 783 | 0.1579 | 0.7170 | 0.6574 | 0.6859 | 0.9710 |
84
+ | 0.079 | 28.0 | 812 | 0.1597 | 0.7148 | 0.6505 | 0.6812 | 0.9708 |
85
+ | 0.079 | 29.0 | 841 | 0.1625 | 0.7309 | 0.6298 | 0.6766 | 0.9705 |
86
+ | 0.079 | 30.0 | 870 | 0.1618 | 0.7352 | 0.6436 | 0.6863 | 0.9712 |
87
 
88
 
89
  ### Framework versions
90
 
91
  - Transformers 4.28.1
92
  - Pytorch 2.0.0+cu118
93
+ - Datasets 2.12.0
94
  - Tokenizers 0.13.3