mireiaplalis
commited on
Commit
•
90c26f3
1
Parent(s):
9cdae54
Training complete
Browse files
README.md
CHANGED
@@ -20,58 +20,58 @@ should probably proofread and complete it, then remove this comment. -->
|
|
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.
|
24 |
-
- Precision: 0.
|
25 |
-
- Recall: 0.
|
26 |
-
- F1: 0.
|
27 |
-
- Accuracy: 0.
|
28 |
-
- Adr Precision: 0.
|
29 |
-
- Adr Recall: 0.
|
30 |
-
- Adr F1: 0.
|
31 |
-
- Disease Precision: 0.
|
32 |
-
- Disease Recall: 0.
|
33 |
-
- Disease F1: 0.
|
34 |
-
- Drug Precision: 0.
|
35 |
-
- Drug Recall: 0.
|
36 |
-
- Drug F1: 0.
|
37 |
-
- Finding Precision: 0.
|
38 |
-
- Finding Recall: 0.
|
39 |
-
- Finding F1: 0.
|
40 |
-
- Symptom Precision: 0.
|
41 |
-
- Symptom Recall: 0.
|
42 |
-
- Symptom F1: 0.
|
43 |
-
- B-adr Precision: 0.
|
44 |
-
- B-adr Recall: 0.
|
45 |
-
- B-adr F1: 0.
|
46 |
-
- B-disease Precision: 0
|
47 |
-
- B-disease Recall: 0.
|
48 |
-
- B-disease F1: 0.
|
49 |
-
- B-drug Precision: 0.
|
50 |
- B-drug Recall: 0.9557
|
51 |
-
- B-drug F1: 0.
|
52 |
-
- B-finding Precision: 0.
|
53 |
- B-finding Recall: 0.4483
|
54 |
-
- B-finding F1: 0.
|
55 |
-
- B-symptom Precision: 0.
|
56 |
-
- B-symptom Recall: 0.
|
57 |
-
- B-symptom F1: 0.
|
58 |
-
- I-adr Precision: 0.
|
59 |
-
- I-adr Recall: 0.
|
60 |
-
- I-adr F1: 0.
|
61 |
-
- I-disease Precision: 0.
|
62 |
-
- I-disease Recall: 0.
|
63 |
-
- I-disease F1: 0.
|
64 |
-
- I-drug Precision: 0.
|
65 |
-
- I-drug Recall: 0.
|
66 |
-
- I-drug F1: 0.
|
67 |
-
- I-finding Precision: 0.
|
68 |
-
- I-finding Recall: 0.
|
69 |
-
- I-finding F1: 0.
|
70 |
- I-symptom Precision: 0.0
|
71 |
- I-symptom Recall: 0.0
|
72 |
- I-symptom F1: 0.0
|
73 |
-
- Macro Avg F1: 0.
|
74 |
-
- Weighted Avg F1: 0.
|
75 |
|
76 |
## Model description
|
77 |
|
@@ -102,9 +102,9 @@ The following hyperparameters were used during training:
|
|
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.
|
106 |
-
| No log | 2.0 | 254 | 0.
|
107 |
-
| No log | 3.0 | 381 | 0.
|
108 |
|
109 |
|
110 |
### Framework versions
|
|
|
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: 0.2301
|
24 |
+
- Precision: 0.5948
|
25 |
+
- Recall: 0.6779
|
26 |
+
- F1: 0.6336
|
27 |
+
- Accuracy: 0.9265
|
28 |
+
- Adr Precision: 0.5579
|
29 |
+
- Adr Recall: 0.6812
|
30 |
+
- Adr F1: 0.6134
|
31 |
+
- Disease Precision: 0.2273
|
32 |
+
- Disease Recall: 0.1562
|
33 |
+
- Disease F1: 0.1852
|
34 |
+
- Drug Precision: 0.8136
|
35 |
+
- Drug Recall: 0.8775
|
36 |
+
- Drug F1: 0.8443
|
37 |
+
- Finding Precision: 0.2667
|
38 |
+
- Finding Recall: 0.2759
|
39 |
+
- Finding F1: 0.2712
|
40 |
+
- Symptom Precision: 0.5
|
41 |
+
- Symptom Recall: 0.0435
|
42 |
+
- Symptom F1: 0.08
|
43 |
+
- B-adr Precision: 0.7749
|
44 |
+
- B-adr Recall: 0.8513
|
45 |
+
- B-adr F1: 0.8113
|
46 |
+
- B-disease Precision: 1.0
|
47 |
+
- B-disease Recall: 0.1562
|
48 |
+
- B-disease F1: 0.2703
|
49 |
+
- B-drug Precision: 0.9327
|
50 |
- B-drug Recall: 0.9557
|
51 |
+
- B-drug F1: 0.9440
|
52 |
+
- B-finding Precision: 0.5909
|
53 |
- B-finding Recall: 0.4483
|
54 |
+
- B-finding F1: 0.5098
|
55 |
+
- B-symptom Precision: 0.5
|
56 |
+
- B-symptom Recall: 0.0435
|
57 |
+
- B-symptom F1: 0.08
|
58 |
+
- I-adr Precision: 0.5725
|
59 |
+
- I-adr Recall: 0.6782
|
60 |
+
- I-adr F1: 0.6209
|
61 |
+
- I-disease Precision: 0.4091
|
62 |
+
- I-disease Recall: 0.3103
|
63 |
+
- I-disease F1: 0.3529
|
64 |
+
- I-drug Precision: 0.8458
|
65 |
+
- I-drug Recall: 0.8873
|
66 |
+
- I-drug F1: 0.8660
|
67 |
+
- I-finding Precision: 0.3529
|
68 |
+
- I-finding Recall: 0.2222
|
69 |
+
- I-finding F1: 0.2727
|
70 |
- I-symptom Precision: 0.0
|
71 |
- I-symptom Recall: 0.0
|
72 |
- I-symptom F1: 0.0
|
73 |
+
- Macro Avg F1: 0.4728
|
74 |
+
- Weighted Avg F1: 0.7278
|
75 |
|
76 |
## Model description
|
77 |
|
|
|
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 | 0.2653 | 0.5472 | 0.6201 | 0.5814 | 0.9128 | 0.4942 | 0.6376 | 0.5568 | 0.0 | 0.0 | 0.0 | 0.7952 | 0.8186 | 0.8068 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.7530 | 0.7731 | 0.7629 | 0.0 | 0.0 | 0.0 | 0.9179 | 0.8818 | 0.8995 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.4915 | 0.6325 | 0.5532 | 0.1429 | 0.0345 | 0.0556 | 0.855 | 0.8382 | 0.8465 | 0.3333 | 0.0370 | 0.0667 | 0.0 | 0.0 | 0.0 | 0.3184 | 0.6587 |
|
106 |
+
| No log | 2.0 | 254 | 0.2307 | 0.5896 | 0.6632 | 0.6242 | 0.9254 | 0.5546 | 0.6722 | 0.6077 | 0.2222 | 0.1875 | 0.2034 | 0.8093 | 0.8529 | 0.8305 | 0.2083 | 0.1724 | 0.1887 | 0.0 | 0.0 | 0.0 | 0.7663 | 0.8263 | 0.7952 | 1.0 | 0.1562 | 0.2703 | 0.9366 | 0.9458 | 0.9412 | 0.625 | 0.3448 | 0.4444 | 0.0 | 0.0 | 0.0 | 0.5649 | 0.6600 | 0.6088 | 0.2963 | 0.2759 | 0.2857 | 0.8495 | 0.8578 | 0.8537 | 0.3846 | 0.1852 | 0.25 | 0.0 | 0.0 | 0.0 | 0.4449 | 0.7127 |
|
107 |
+
| No log | 3.0 | 381 | 0.2301 | 0.5948 | 0.6779 | 0.6336 | 0.9265 | 0.5579 | 0.6812 | 0.6134 | 0.2273 | 0.1562 | 0.1852 | 0.8136 | 0.8775 | 0.8443 | 0.2667 | 0.2759 | 0.2712 | 0.5 | 0.0435 | 0.08 | 0.7749 | 0.8513 | 0.8113 | 1.0 | 0.1562 | 0.2703 | 0.9327 | 0.9557 | 0.9440 | 0.5909 | 0.4483 | 0.5098 | 0.5 | 0.0435 | 0.08 | 0.5725 | 0.6782 | 0.6209 | 0.4091 | 0.3103 | 0.3529 | 0.8458 | 0.8873 | 0.8660 | 0.3529 | 0.2222 | 0.2727 | 0.0 | 0.0 | 0.0 | 0.4728 | 0.7278 |
|
108 |
|
109 |
|
110 |
### Framework versions
|