update model card README.md
Browse files
README.md
CHANGED
@@ -2,11 +2,6 @@
|
|
2 |
license: mit
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
-
metrics:
|
6 |
-
- precision
|
7 |
-
- recall
|
8 |
-
- f1
|
9 |
-
- accuracy
|
10 |
model-index:
|
11 |
- name: Yepes_2e-05_250
|
12 |
results: []
|
@@ -17,13 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
# Yepes_2e-05_250
|
19 |
|
20 |
-
This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on
|
21 |
-
It achieves the following results on the evaluation set:
|
22 |
-
- Loss: 0.1289
|
23 |
-
- Precision: 0.6094
|
24 |
-
- Recall: 0.4851
|
25 |
-
- F1: 0.5402
|
26 |
-
- Accuracy: 0.9772
|
27 |
|
28 |
## Model description
|
29 |
|
@@ -50,27 +39,6 @@ The following hyperparameters were used during training:
|
|
50 |
- lr_scheduler_type: linear
|
51 |
- training_steps: 500
|
52 |
|
53 |
-
### Training results
|
54 |
-
|
55 |
-
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
56 |
-
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
57 |
-
| 0.9077 | 1.39 | 25 | 0.2178 | 0.0 | 0.0 | 0.0 | 0.9672 |
|
58 |
-
| 0.2029 | 2.78 | 50 | 0.2096 | 0.0 | 0.0 | 0.0 | 0.9672 |
|
59 |
-
| 0.1942 | 4.17 | 75 | 0.1807 | 0.0 | 0.0 | 0.0 | 0.9672 |
|
60 |
-
| 0.142 | 5.56 | 100 | 0.1402 | 0.3529 | 0.2090 | 0.2625 | 0.9696 |
|
61 |
-
| 0.1139 | 6.94 | 125 | 0.1295 | 0.4875 | 0.3408 | 0.4012 | 0.9743 |
|
62 |
-
| 0.0884 | 8.33 | 150 | 0.1210 | 0.5428 | 0.3632 | 0.4352 | 0.9754 |
|
63 |
-
| 0.0738 | 9.72 | 175 | 0.1185 | 0.5254 | 0.3856 | 0.4448 | 0.9759 |
|
64 |
-
| 0.0647 | 11.11 | 200 | 0.1158 | 0.5061 | 0.4154 | 0.4563 | 0.9757 |
|
65 |
-
| 0.0549 | 12.5 | 225 | 0.1150 | 0.5106 | 0.4204 | 0.4611 | 0.9759 |
|
66 |
-
| 0.0486 | 13.89 | 250 | 0.1192 | 0.5071 | 0.4428 | 0.4728 | 0.9754 |
|
67 |
-
| 0.043 | 15.28 | 275 | 0.1223 | 0.5329 | 0.4428 | 0.4837 | 0.9757 |
|
68 |
-
| 0.0401 | 16.67 | 300 | 0.1249 | 0.5759 | 0.4527 | 0.5070 | 0.9767 |
|
69 |
-
| 0.0347 | 18.06 | 325 | 0.1269 | 0.6213 | 0.4652 | 0.5320 | 0.9775 |
|
70 |
-
| 0.033 | 19.44 | 350 | 0.1295 | 0.6198 | 0.4826 | 0.5427 | 0.9775 |
|
71 |
-
| 0.0293 | 20.83 | 375 | 0.1289 | 0.6094 | 0.4851 | 0.5402 | 0.9772 |
|
72 |
-
|
73 |
-
|
74 |
### Framework versions
|
75 |
|
76 |
- Transformers 4.27.4
|
|
|
2 |
license: mit
|
3 |
tags:
|
4 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
5 |
model-index:
|
6 |
- name: Yepes_2e-05_250
|
7 |
results: []
|
|
|
12 |
|
13 |
# Yepes_2e-05_250
|
14 |
|
15 |
+
This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
|
17 |
## Model description
|
18 |
|
|
|
39 |
- lr_scheduler_type: linear
|
40 |
- training_steps: 500
|
41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
### Framework versions
|
43 |
|
44 |
- Transformers 4.27.4
|