update model card README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,11 @@
|
|
| 2 |
license: mit
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: multiCorp_5e-05_LabelNorm_0404
|
| 7 |
results: []
|
|
@@ -12,7 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 12 |
|
| 13 |
# multiCorp_5e-05_LabelNorm_0404
|
| 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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
|
@@ -39,6 +50,44 @@ The following hyperparameters were used during training:
|
|
| 39 |
- lr_scheduler_type: linear
|
| 40 |
- training_steps: 2000
|
| 41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
### Framework versions
|
| 43 |
|
| 44 |
- Transformers 4.27.4
|
|
|
|
| 2 |
license: mit
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- precision
|
| 7 |
+
- recall
|
| 8 |
+
- f1
|
| 9 |
+
- accuracy
|
| 10 |
model-index:
|
| 11 |
- name: multiCorp_5e-05_LabelNorm_0404
|
| 12 |
results: []
|
|
|
|
| 17 |
|
| 18 |
# multiCorp_5e-05_LabelNorm_0404
|
| 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 the None dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.0310
|
| 23 |
+
- Precision: 0.6947
|
| 24 |
+
- Recall: 0.7305
|
| 25 |
+
- F1: 0.7121
|
| 26 |
+
- Accuracy: 0.9911
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
|
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
- training_steps: 2000
|
| 52 |
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 57 |
+
| 0.2337 | 0.08 | 25 | 0.1020 | 0.0 | 0.0 | 0.0 | 0.9838 |
|
| 58 |
+
| 0.0855 | 0.15 | 50 | 0.1026 | 0.0 | 0.0 | 0.0 | 0.9838 |
|
| 59 |
+
| 0.0834 | 0.23 | 75 | 0.1037 | 0.0 | 0.0 | 0.0 | 0.9838 |
|
| 60 |
+
| 0.0868 | 0.31 | 100 | 0.0682 | 0.0 | 0.0 | 0.0 | 0.9838 |
|
| 61 |
+
| 0.0569 | 0.39 | 125 | 0.0630 | 0.0 | 0.0 | 0.0 | 0.9838 |
|
| 62 |
+
| 0.0612 | 0.46 | 150 | 0.0595 | 0.0 | 0.0 | 0.0 | 0.9838 |
|
| 63 |
+
| 0.0551 | 0.54 | 175 | 0.0507 | 0.3790 | 0.3046 | 0.3378 | 0.9841 |
|
| 64 |
+
| 0.0347 | 0.62 | 200 | 0.0504 | 0.5773 | 0.2403 | 0.3393 | 0.9859 |
|
| 65 |
+
| 0.0472 | 0.7 | 225 | 0.0474 | 0.5132 | 0.3795 | 0.4363 | 0.9862 |
|
| 66 |
+
| 0.0374 | 0.77 | 250 | 0.0444 | 0.5509 | 0.3039 | 0.3917 | 0.9857 |
|
| 67 |
+
| 0.0525 | 0.85 | 275 | 0.0383 | 0.6984 | 0.4281 | 0.5309 | 0.9882 |
|
| 68 |
+
| 0.0406 | 0.93 | 300 | 0.0389 | 0.6280 | 0.5105 | 0.5632 | 0.9885 |
|
| 69 |
+
| 0.0347 | 1.01 | 325 | 0.0404 | 0.5134 | 0.6003 | 0.5535 | 0.9873 |
|
| 70 |
+
| 0.0333 | 1.08 | 350 | 0.0415 | 0.6409 | 0.4289 | 0.5139 | 0.9880 |
|
| 71 |
+
| 0.0267 | 1.16 | 375 | 0.0377 | 0.6010 | 0.4543 | 0.5175 | 0.9885 |
|
| 72 |
+
| 0.0406 | 1.24 | 400 | 0.0397 | 0.6406 | 0.6310 | 0.6357 | 0.9889 |
|
| 73 |
+
| 0.0252 | 1.32 | 425 | 0.0364 | 0.5946 | 0.5599 | 0.5767 | 0.9882 |
|
| 74 |
+
| 0.0351 | 1.39 | 450 | 0.0343 | 0.6632 | 0.6130 | 0.6371 | 0.9895 |
|
| 75 |
+
| 0.0304 | 1.47 | 475 | 0.0378 | 0.6756 | 0.5846 | 0.6268 | 0.9896 |
|
| 76 |
+
| 0.0242 | 1.55 | 500 | 0.0342 | 0.7061 | 0.5988 | 0.6480 | 0.9904 |
|
| 77 |
+
| 0.0291 | 1.63 | 525 | 0.0327 | 0.5841 | 0.6497 | 0.6152 | 0.9894 |
|
| 78 |
+
| 0.0307 | 1.7 | 550 | 0.0333 | 0.5815 | 0.5823 | 0.5819 | 0.9890 |
|
| 79 |
+
| 0.0278 | 1.78 | 575 | 0.0316 | 0.6654 | 0.6579 | 0.6616 | 0.9904 |
|
| 80 |
+
| 0.0293 | 1.86 | 600 | 0.0335 | 0.7969 | 0.4933 | 0.6093 | 0.9898 |
|
| 81 |
+
| 0.0241 | 1.93 | 625 | 0.0322 | 0.6473 | 0.6991 | 0.6722 | 0.9901 |
|
| 82 |
+
| 0.0288 | 2.01 | 650 | 0.0300 | 0.7431 | 0.5846 | 0.6544 | 0.9906 |
|
| 83 |
+
| 0.0192 | 2.09 | 675 | 0.0329 | 0.6908 | 0.7006 | 0.6957 | 0.9910 |
|
| 84 |
+
| 0.0184 | 2.17 | 700 | 0.0326 | 0.6788 | 0.6407 | 0.6592 | 0.9897 |
|
| 85 |
+
| 0.0171 | 2.24 | 725 | 0.0325 | 0.7131 | 0.6864 | 0.6995 | 0.9911 |
|
| 86 |
+
| 0.0161 | 2.32 | 750 | 0.0336 | 0.7138 | 0.6647 | 0.6884 | 0.9910 |
|
| 87 |
+
| 0.0218 | 2.4 | 775 | 0.0306 | 0.6892 | 0.6954 | 0.6923 | 0.9904 |
|
| 88 |
+
| 0.0209 | 2.48 | 800 | 0.0310 | 0.6947 | 0.7305 | 0.7121 | 0.9911 |
|
| 89 |
+
|
| 90 |
+
|
| 91 |
### Framework versions
|
| 92 |
|
| 93 |
- Transformers 4.27.4
|