mireiaplalis
commited on
Commit
•
c0a8f05
1
Parent(s):
f97081e
Training complete
Browse files
README.md
CHANGED
@@ -3,8 +3,6 @@ license: apache-2.0
|
|
3 |
base_model: bert-base-cased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
-
datasets:
|
7 |
-
- wnut_17
|
8 |
metrics:
|
9 |
- precision
|
10 |
- recall
|
@@ -12,29 +10,7 @@ metrics:
|
|
12 |
- accuracy
|
13 |
model-index:
|
14 |
- name: bert-finetuned-ner
|
15 |
-
results:
|
16 |
-
- task:
|
17 |
-
name: Token Classification
|
18 |
-
type: token-classification
|
19 |
-
dataset:
|
20 |
-
name: wnut_17
|
21 |
-
type: wnut_17
|
22 |
-
config: wnut_17
|
23 |
-
split: test
|
24 |
-
args: wnut_17
|
25 |
-
metrics:
|
26 |
-
- name: Precision
|
27 |
-
type: precision
|
28 |
-
value: 0.5180180180180181
|
29 |
-
- name: Recall
|
30 |
-
type: recall
|
31 |
-
value: 0.31974050046339203
|
32 |
-
- name: F1
|
33 |
-
type: f1
|
34 |
-
value: 0.39541547277936967
|
35 |
-
- name: Accuracy
|
36 |
-
type: accuracy
|
37 |
-
value: 0.9357035175879397
|
38 |
---
|
39 |
|
40 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -42,67 +18,60 @@ should probably proofread and complete it, then remove this comment. -->
|
|
42 |
|
43 |
# bert-finetuned-ner
|
44 |
|
45 |
-
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the
|
46 |
It achieves the following results on the evaluation set:
|
47 |
-
- Loss: 0.
|
48 |
-
- Precision: 0.
|
49 |
-
- Recall: 0.
|
50 |
-
- F1: 0.
|
51 |
-
- Accuracy: 0.
|
52 |
-
-
|
53 |
-
-
|
54 |
-
-
|
55 |
-
-
|
56 |
-
-
|
57 |
-
-
|
58 |
-
-
|
59 |
-
-
|
60 |
-
-
|
61 |
-
-
|
62 |
-
-
|
63 |
-
-
|
64 |
-
-
|
65 |
-
-
|
66 |
-
-
|
67 |
-
-
|
68 |
-
-
|
69 |
-
-
|
70 |
-
- B-
|
71 |
-
- B-
|
72 |
-
- B-
|
73 |
-
- B-
|
74 |
-
- B-
|
75 |
-
- B-
|
76 |
-
- B-
|
77 |
-
- B-
|
78 |
-
- B-
|
79 |
-
- B-
|
80 |
-
- B-
|
81 |
-
- B-
|
82 |
-
-
|
83 |
-
-
|
84 |
-
-
|
85 |
-
-
|
86 |
-
-
|
87 |
-
-
|
88 |
-
- I-
|
89 |
-
- I-
|
90 |
-
- I-
|
91 |
-
- I-
|
92 |
-
- I-
|
93 |
-
- I-
|
94 |
-
- I-
|
95 |
-
- I-
|
96 |
-
- I-
|
97 |
-
-
|
98 |
-
-
|
99 |
-
- I-location F1: 0.4545
|
100 |
-
- I-person Precision: 0.7625
|
101 |
-
- I-person Recall: 0.3631
|
102 |
-
- I-person F1: 0.4919
|
103 |
-
- I-product Precision: 0.2222
|
104 |
-
- I-product Recall: 0.1488
|
105 |
-
- I-product F1: 0.1782
|
106 |
|
107 |
## Model description
|
108 |
|
@@ -131,16 +100,16 @@ The following hyperparameters were used during training:
|
|
131 |
|
132 |
### Training results
|
133 |
|
134 |
-
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
135 |
-
|
136 |
-
| No log | 1.0 |
|
137 |
-
|
|
138 |
-
|
|
139 |
|
140 |
|
141 |
### Framework versions
|
142 |
|
143 |
-
- Transformers 4.
|
144 |
- Pytorch 2.1.0+cu118
|
145 |
-
- Datasets 2.
|
146 |
-
- Tokenizers 0.
|
|
|
3 |
base_model: bert-base-cased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
metrics:
|
7 |
- precision
|
8 |
- recall
|
|
|
10 |
- accuracy
|
11 |
model-index:
|
12 |
- name: bert-finetuned-ner
|
13 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
---
|
15 |
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
18 |
|
19 |
# bert-finetuned-ner
|
20 |
|
21 |
+
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.2315
|
24 |
+
- Precision: 0.5909
|
25 |
+
- Recall: 0.6789
|
26 |
+
- F1: 0.6318
|
27 |
+
- Accuracy: 0.9259
|
28 |
+
- Adr Precision: 0.5587
|
29 |
+
- Adr Recall: 0.6872
|
30 |
+
- Adr F1: 0.6163
|
31 |
+
- Disease Precision: 0.05
|
32 |
+
- Disease Recall: 0.0312
|
33 |
+
- Disease F1: 0.0385
|
34 |
+
- Drug Precision: 0.8364
|
35 |
+
- Drug Recall: 0.9020
|
36 |
+
- Drug F1: 0.8679
|
37 |
+
- Finding Precision: 0.1389
|
38 |
+
- Finding Recall: 0.1724
|
39 |
+
- Finding F1: 0.1538
|
40 |
+
- Symptom Precision: 0.0
|
41 |
+
- Symptom Recall: 0.0
|
42 |
+
- Symptom F1: 0.0
|
43 |
+
- B-adr Precision: 0.7568
|
44 |
+
- B-adr Recall: 0.8279
|
45 |
+
- B-adr F1: 0.7907
|
46 |
+
- B-disease Precision: 0.5
|
47 |
+
- B-disease Recall: 0.0312
|
48 |
+
- B-disease F1: 0.0588
|
49 |
+
- B-drug Precision: 0.9194
|
50 |
+
- B-drug Recall: 0.9557
|
51 |
+
- B-drug F1: 0.9372
|
52 |
+
- B-finding Precision: 0.5417
|
53 |
+
- B-finding Recall: 0.4483
|
54 |
+
- B-finding F1: 0.4906
|
55 |
+
- B-symptom Precision: 0.0
|
56 |
+
- B-symptom Recall: 0.0
|
57 |
+
- B-symptom F1: 0.0
|
58 |
+
- I-adr Precision: 0.5747
|
59 |
+
- I-adr Recall: 0.6892
|
60 |
+
- I-adr F1: 0.6268
|
61 |
+
- I-disease Precision: 0.3684
|
62 |
+
- I-disease Recall: 0.2414
|
63 |
+
- I-disease F1: 0.2917
|
64 |
+
- I-drug Precision: 0.8732
|
65 |
+
- I-drug Recall: 0.9118
|
66 |
+
- I-drug F1: 0.8921
|
67 |
+
- I-finding Precision: 0.3043
|
68 |
+
- I-finding Recall: 0.2593
|
69 |
+
- I-finding F1: 0.2800
|
70 |
+
- I-symptom Precision: 0.0
|
71 |
+
- I-symptom Recall: 0.0
|
72 |
+
- I-symptom F1: 0.0
|
73 |
+
- Macro Avg F1: 0.4368
|
74 |
+
- Weighted Avg F1: 0.7182
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
75 |
|
76 |
## Model description
|
77 |
|
|
|
100 |
|
101 |
### Training results
|
102 |
|
103 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | Adr Precision | Adr Recall | Adr F1 | Disease Precision | Disease Recall | Disease F1 | Drug Precision | Drug Recall | Drug F1 | Finding Precision | Finding Recall | Finding F1 | Symptom Precision | Symptom Recall | Symptom F1 | B-adr Precision | B-adr Recall | B-adr F1 | B-disease Precision | B-disease Recall | B-disease F1 | B-drug Precision | B-drug Recall | B-drug F1 | B-finding Precision | B-finding Recall | B-finding F1 | B-symptom Precision | B-symptom Recall | B-symptom F1 | I-adr Precision | I-adr Recall | I-adr F1 | I-disease Precision | I-disease Recall | I-disease F1 | I-drug Precision | I-drug Recall | I-drug F1 | I-finding Precision | I-finding Recall | I-finding F1 | I-symptom Precision | I-symptom Recall | I-symptom F1 | Macro Avg F1 | Weighted Avg F1 |
|
104 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:-------------:|:----------:|:------:|:-----------------:|:--------------:|:----------:|:--------------:|:-----------:|:-------:|:-----------------:|:--------------:|:----------:|:-----------------:|:--------------:|:----------:|:---------------:|:------------:|:--------:|:-------------------:|:----------------:|:------------:|:----------------:|:-------------:|:---------:|:-------------------:|:----------------:|:------------:|:-------------------:|:----------------:|:------------:|:---------------:|:------------:|:--------:|:-------------------:|:----------------:|:------------:|:----------------:|:-------------:|:---------:|:-------------------:|:----------------:|:------------:|:-------------------:|:----------------:|:------------:|:------------:|:---------------:|
|
105 |
+
| No log | 1.0 | 127 | 0.2637 | 0.5378 | 0.6338 | 0.5819 | 0.9129 | 0.4869 | 0.6451 | 0.5550 | 0.0 | 0.0 | 0.0 | 0.7828 | 0.8480 | 0.8141 | 0.125 | 0.0690 | 0.0889 | 0.0 | 0.0 | 0.0 | 0.7377 | 0.7746 | 0.7557 | 0.0 | 0.0 | 0.0 | 0.8927 | 0.9015 | 0.8971 | 1.0 | 0.0690 | 0.1290 | 0.0 | 0.0 | 0.0 | 0.4813 | 0.6362 | 0.5480 | 0.0 | 0.0 | 0.0 | 0.8719 | 0.8676 | 0.8698 | 0.1875 | 0.1111 | 0.1395 | 0.0 | 0.0 | 0.0 | 0.3339 | 0.6592 |
|
106 |
+
| No log | 2.0 | 254 | 0.2329 | 0.5826 | 0.6621 | 0.6198 | 0.9242 | 0.5455 | 0.6677 | 0.6004 | 0.0455 | 0.0312 | 0.0370 | 0.8326 | 0.9020 | 0.8659 | 0.0769 | 0.0690 | 0.0727 | 0.0 | 0.0 | 0.0 | 0.7555 | 0.8075 | 0.7806 | 1.0 | 0.0312 | 0.0606 | 0.9159 | 0.9655 | 0.9400 | 0.6 | 0.3103 | 0.4091 | 0.0 | 0.0 | 0.0 | 0.5677 | 0.6819 | 0.6196 | 0.2727 | 0.2069 | 0.2353 | 0.8846 | 0.9020 | 0.8932 | 0.2667 | 0.1481 | 0.1905 | 0.0 | 0.0 | 0.0 | 0.4129 | 0.7090 |
|
107 |
+
| No log | 3.0 | 381 | 0.2315 | 0.5909 | 0.6789 | 0.6318 | 0.9259 | 0.5587 | 0.6872 | 0.6163 | 0.05 | 0.0312 | 0.0385 | 0.8364 | 0.9020 | 0.8679 | 0.1389 | 0.1724 | 0.1538 | 0.0 | 0.0 | 0.0 | 0.7568 | 0.8279 | 0.7907 | 0.5 | 0.0312 | 0.0588 | 0.9194 | 0.9557 | 0.9372 | 0.5417 | 0.4483 | 0.4906 | 0.0 | 0.0 | 0.0 | 0.5747 | 0.6892 | 0.6268 | 0.3684 | 0.2414 | 0.2917 | 0.8732 | 0.9118 | 0.8921 | 0.3043 | 0.2593 | 0.2800 | 0.0 | 0.0 | 0.0 | 0.4368 | 0.7182 |
|
108 |
|
109 |
|
110 |
### Framework versions
|
111 |
|
112 |
+
- Transformers 4.35.2
|
113 |
- Pytorch 2.1.0+cu118
|
114 |
+
- Datasets 2.15.0
|
115 |
+
- Tokenizers 0.15.0
|