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: Variome_0.0001_250
|
| 12 |
results: []
|
|
@@ -17,13 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
# Variome_0.0001_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: 0.0673
|
| 23 |
-
- Precision: 0.6558
|
| 24 |
-
- Recall: 0.5824
|
| 25 |
-
- F1: 0.6169
|
| 26 |
-
- Accuracy: 0.9867
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
@@ -50,32 +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 |
-
| 0.4275 | 0.35 | 25 | 0.1841 | 0.0 | 0.0 | 0.0 | 0.9760 |
|
| 58 |
-
| 0.1851 | 0.69 | 50 | 0.1800 | 0.0 | 0.0 | 0.0 | 0.9760 |
|
| 59 |
-
| 0.1622 | 1.04 | 75 | 0.1746 | 0.0 | 0.0 | 0.0 | 0.9760 |
|
| 60 |
-
| 0.1617 | 1.39 | 100 | 0.1281 | 0.2462 | 0.0418 | 0.0715 | 0.9764 |
|
| 61 |
-
| 0.1185 | 1.74 | 125 | 0.1175 | 0.1430 | 0.1537 | 0.1481 | 0.9749 |
|
| 62 |
-
| 0.1104 | 2.08 | 150 | 0.1066 | 0.1982 | 0.1486 | 0.1698 | 0.9776 |
|
| 63 |
-
| 0.0906 | 2.43 | 175 | 0.1057 | 0.3385 | 0.2041 | 0.2547 | 0.9793 |
|
| 64 |
-
| 0.0922 | 2.78 | 200 | 0.0919 | 0.3749 | 0.3185 | 0.3444 | 0.9807 |
|
| 65 |
-
| 0.0801 | 3.12 | 225 | 0.0836 | 0.4769 | 0.4142 | 0.4433 | 0.9823 |
|
| 66 |
-
| 0.0655 | 3.47 | 250 | 0.0808 | 0.5989 | 0.4552 | 0.5172 | 0.9840 |
|
| 67 |
-
| 0.0606 | 3.82 | 275 | 0.0716 | 0.5641 | 0.5038 | 0.5323 | 0.9851 |
|
| 68 |
-
| 0.0485 | 4.17 | 300 | 0.0707 | 0.5975 | 0.5235 | 0.5580 | 0.9856 |
|
| 69 |
-
| 0.0464 | 4.51 | 325 | 0.0686 | 0.6370 | 0.5320 | 0.5798 | 0.9858 |
|
| 70 |
-
| 0.0423 | 4.86 | 350 | 0.0678 | 0.6343 | 0.5628 | 0.5964 | 0.9862 |
|
| 71 |
-
| 0.0387 | 5.21 | 375 | 0.0669 | 0.6523 | 0.5542 | 0.5993 | 0.9866 |
|
| 72 |
-
| 0.0336 | 5.56 | 400 | 0.0677 | 0.6573 | 0.5602 | 0.6049 | 0.9866 |
|
| 73 |
-
| 0.033 | 5.9 | 425 | 0.0673 | 0.6500 | 0.5568 | 0.5998 | 0.9866 |
|
| 74 |
-
| 0.031 | 6.25 | 450 | 0.0673 | 0.6477 | 0.5824 | 0.6133 | 0.9864 |
|
| 75 |
-
| 0.0276 | 6.6 | 475 | 0.0676 | 0.6573 | 0.5798 | 0.6162 | 0.9868 |
|
| 76 |
-
| 0.0255 | 6.94 | 500 | 0.0673 | 0.6558 | 0.5824 | 0.6169 | 0.9867 |
|
| 77 |
-
|
| 78 |
-
|
| 79 |
### Framework versions
|
| 80 |
|
| 81 |
- Transformers 4.27.4
|
|
|
|
| 2 |
license: mit
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: Variome_0.0001_250
|
| 7 |
results: []
|
|
|
|
| 12 |
|
| 13 |
# Variome_0.0001_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
|