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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) 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: 0.0
|
32 |
- Disease Recall: 0.0
|
33 |
- Disease F1: 0.0
|
34 |
-
- Drug Precision: 0.
|
35 |
-
- Drug Recall: 0.
|
36 |
-
- Drug F1: 0.
|
37 |
- Finding Precision: 0.0
|
38 |
- Finding Recall: 0.0
|
39 |
- Finding F1: 0.0
|
40 |
- Symptom Precision: 0.0
|
41 |
- Symptom Recall: 0.0
|
42 |
- Symptom F1: 0.0
|
43 |
-
- B-adr Precision: 0.
|
44 |
-
- B-adr Recall: 0.
|
45 |
-
- B-adr F1: 0.
|
46 |
- B-disease Precision: 0.0
|
47 |
- B-disease Recall: 0.0
|
48 |
- B-disease F1: 0.0
|
49 |
-
- B-drug Precision: 0.
|
50 |
- B-drug Recall: 0.8511
|
51 |
-
- B-drug F1: 0.
|
52 |
- B-finding Precision: 0.0
|
53 |
- B-finding Recall: 0.0
|
54 |
- B-finding F1: 0.0
|
55 |
- B-symptom Precision: 0.0
|
56 |
- B-symptom Recall: 0.0
|
57 |
- B-symptom F1: 0.0
|
58 |
-
- I-adr Precision: 0.
|
59 |
-
- I-adr Recall: 0.
|
60 |
-
- I-adr F1: 0.
|
61 |
- I-disease Precision: 0.0
|
62 |
- I-disease Recall: 0.0
|
63 |
- I-disease F1: 0.0
|
64 |
-
- I-drug Precision: 0.
|
65 |
-
- I-drug Recall: 0.
|
66 |
-
- I-drug F1: 0.
|
67 |
- I-finding Precision: 0.0
|
68 |
- I-finding Recall: 0.0
|
69 |
- I-finding F1: 0.0
|
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 |
|
@@ -102,16 +102,16 @@ 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 |
|
106 |
-
| No log | 2.0 |
|
107 |
-
| No log | 3.0 |
|
108 |
-
| No log | 4.0 |
|
109 |
-
| No log | 5.0 |
|
110 |
-
| No log | 6.0 |
|
111 |
-
| No log | 7.0 |
|
112 |
-
| No log | 8.0 |
|
113 |
-
| No log | 9.0 |
|
114 |
-
| No log | 10.0 |
|
115 |
|
116 |
|
117 |
### Framework versions
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.3503
|
24 |
+
- Precision: 0.4853
|
25 |
+
- Recall: 0.5067
|
26 |
+
- F1: 0.4957
|
27 |
+
- Accuracy: 0.9003
|
28 |
+
- Adr Precision: 0.4156
|
29 |
+
- Adr Recall: 0.4971
|
30 |
+
- Adr F1: 0.4527
|
31 |
- Disease Precision: 0.0
|
32 |
- Disease Recall: 0.0
|
33 |
- Disease F1: 0.0
|
34 |
+
- Drug Precision: 0.7766
|
35 |
+
- Drug Recall: 0.8138
|
36 |
+
- Drug F1: 0.7948
|
37 |
- Finding Precision: 0.0
|
38 |
- Finding Recall: 0.0
|
39 |
- Finding F1: 0.0
|
40 |
- Symptom Precision: 0.0
|
41 |
- Symptom Recall: 0.0
|
42 |
- Symptom F1: 0.0
|
43 |
+
- B-adr Precision: 0.6582
|
44 |
+
- B-adr Recall: 0.6551
|
45 |
+
- B-adr F1: 0.6567
|
46 |
- B-disease Precision: 0.0
|
47 |
- B-disease Recall: 0.0
|
48 |
- B-disease F1: 0.0
|
49 |
+
- B-drug Precision: 0.9639
|
50 |
- B-drug Recall: 0.8511
|
51 |
+
- B-drug F1: 0.9040
|
52 |
- B-finding Precision: 0.0
|
53 |
- B-finding Recall: 0.0
|
54 |
- B-finding F1: 0.0
|
55 |
- B-symptom Precision: 0.0
|
56 |
- B-symptom Recall: 0.0
|
57 |
- B-symptom F1: 0.0
|
58 |
+
- I-adr Precision: 0.4091
|
59 |
+
- I-adr Recall: 0.4686
|
60 |
+
- I-adr F1: 0.4368
|
61 |
- I-disease Precision: 0.0
|
62 |
- I-disease Recall: 0.0
|
63 |
- I-disease F1: 0.0
|
64 |
+
- I-drug Precision: 0.8112
|
65 |
+
- I-drug Recall: 0.8503
|
66 |
+
- I-drug F1: 0.8303
|
67 |
- I-finding Precision: 0.0
|
68 |
- I-finding Recall: 0.0
|
69 |
- I-finding F1: 0.0
|
70 |
- I-symptom Precision: 0.0
|
71 |
- I-symptom Recall: 0.0
|
72 |
- I-symptom F1: 0.0
|
73 |
+
- Macro Avg F1: 0.2828
|
74 |
+
- Weighted Avg F1: 0.5661
|
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 | 24 | 0.7793 | 0.0 | 0.0 | 0.0 | 0.7876 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
|
106 |
+
| No log | 2.0 | 48 | 0.5127 | 0.3553 | 0.2375 | 0.2847 | 0.8510 | 0.2110 | 0.1613 | 0.1829 | 0.0 | 0.0 | 0.0 | 0.9528 | 0.6436 | 0.7683 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.9841 | 0.6596 | 0.7898 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0589 | 0.0557 | 0.0572 | 0.0 | 0.0 | 0.0 | 0.9603 | 0.6471 | 0.7732 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1620 | 0.1866 |
|
107 |
+
| No log | 3.0 | 72 | 0.4218 | 0.4082 | 0.3275 | 0.3634 | 0.8659 | 0.3101 | 0.2849 | 0.2970 | 0.0 | 0.0 | 0.0 | 0.8158 | 0.6596 | 0.7294 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.6667 | 0.0378 | 0.0715 | 0.0 | 0.0 | 0.0 | 0.9577 | 0.7234 | 0.8242 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1003 | 0.1131 | 0.1063 | 0.0 | 0.0 | 0.0 | 0.8658 | 0.6898 | 0.7679 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1770 | 0.2316 |
|
108 |
+
| No log | 4.0 | 96 | 0.3889 | 0.4168 | 0.3767 | 0.3957 | 0.8763 | 0.3183 | 0.3183 | 0.3183 | 0.0 | 0.0 | 0.0 | 0.7641 | 0.7926 | 0.7781 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.6684 | 0.2031 | 0.3116 | 0.0 | 0.0 | 0.0 | 0.95 | 0.8085 | 0.8736 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1453 | 0.1688 | 0.1561 | 0.0 | 0.0 | 0.0 | 0.7824 | 0.8075 | 0.7947 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2136 | 0.3433 |
|
109 |
+
| No log | 5.0 | 120 | 0.3734 | 0.4409 | 0.3859 | 0.4116 | 0.8866 | 0.3450 | 0.3285 | 0.3366 | 0.0 | 0.0 | 0.0 | 0.755 | 0.8032 | 0.7784 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.6884 | 0.3165 | 0.4337 | 0.0 | 0.0 | 0.0 | 0.9691 | 0.8351 | 0.8971 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2305 | 0.2442 | 0.2371 | 0.0 | 0.0 | 0.0 | 0.7588 | 0.8075 | 0.7824 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2350 | 0.4149 |
|
110 |
+
| No log | 6.0 | 144 | 0.3626 | 0.4608 | 0.4156 | 0.4370 | 0.8903 | 0.3699 | 0.3721 | 0.3710 | 0.0 | 0.0 | 0.0 | 0.7937 | 0.7979 | 0.7958 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.6873 | 0.4016 | 0.5070 | 0.0 | 0.0 | 0.0 | 0.9689 | 0.8298 | 0.8940 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2703 | 0.2926 | 0.2810 | 0.0 | 0.0 | 0.0 | 0.8032 | 0.8075 | 0.8053 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2487 | 0.4579 |
|
111 |
+
| No log | 7.0 | 168 | 0.3535 | 0.4488 | 0.4759 | 0.4620 | 0.8947 | 0.3723 | 0.4491 | 0.4071 | 0.0 | 0.0 | 0.0 | 0.7573 | 0.8298 | 0.7919 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.6261 | 0.5827 | 0.6036 | 0.0 | 0.0 | 0.0 | 0.9422 | 0.8670 | 0.9030 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.3303 | 0.3860 | 0.3560 | 0.0 | 0.0 | 0.0 | 0.7843 | 0.8556 | 0.8184 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2681 | 0.5195 |
|
112 |
+
| No log | 8.0 | 192 | 0.3528 | 0.4751 | 0.4985 | 0.4865 | 0.8969 | 0.4055 | 0.4898 | 0.4437 | 0.0 | 0.0 | 0.0 | 0.7732 | 0.7979 | 0.7853 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.6410 | 0.6299 | 0.6354 | 0.0 | 0.0 | 0.0 | 0.9636 | 0.8457 | 0.9008 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.3752 | 0.4399 | 0.4050 | 0.0 | 0.0 | 0.0 | 0.7979 | 0.8235 | 0.8105 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2752 | 0.5457 |
|
113 |
+
| No log | 9.0 | 216 | 0.3483 | 0.4822 | 0.5005 | 0.4912 | 0.8984 | 0.4108 | 0.4884 | 0.4462 | 0.0 | 0.0 | 0.0 | 0.7806 | 0.8138 | 0.7969 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.6589 | 0.6205 | 0.6391 | 0.0 | 0.0 | 0.0 | 0.9639 | 0.8511 | 0.9040 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.3777 | 0.4434 | 0.4079 | 0.0 | 0.0 | 0.0 | 0.8103 | 0.8449 | 0.8272 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2778 | 0.5501 |
|
114 |
+
| No log | 10.0 | 240 | 0.3503 | 0.4853 | 0.5067 | 0.4957 | 0.9003 | 0.4156 | 0.4971 | 0.4527 | 0.0 | 0.0 | 0.0 | 0.7766 | 0.8138 | 0.7948 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.6582 | 0.6551 | 0.6567 | 0.0 | 0.0 | 0.0 | 0.9639 | 0.8511 | 0.9040 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.4091 | 0.4686 | 0.4368 | 0.0 | 0.0 | 0.0 | 0.8112 | 0.8503 | 0.8303 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2828 | 0.5661 |
|
115 |
|
116 |
|
117 |
### Framework versions
|