Update README.md
Browse files
README.md
CHANGED
|
@@ -69,7 +69,7 @@ though this is still an important clinical task.
|
|
| 69 |
|
| 70 |
Use the code below to get started with the model.
|
| 71 |
|
| 72 |
-
|
| 73 |
|
| 74 |
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
| 75 |
|
|
@@ -77,7 +77,7 @@ tokenizer = AutoTokenizer.from_pretrained("semaj83/scibert_finetuned_ctmatch")
|
|
| 77 |
|
| 78 |
model = AutoModelForSequenceClassification.from_pretrained("semaj83/scibert_finetuned_ctmatch")
|
| 79 |
|
| 80 |
-
|
| 81 |
|
| 82 |
## Training Details
|
| 83 |
|
|
@@ -98,8 +98,8 @@ you may need to use ctproc or another method to extract relevant fields and prep
|
|
| 98 |
|
| 99 |
#### Training Hyperparameters
|
| 100 |
|
| 101 |
-
|
| 102 |
-
max_sequence_length=512
|
| 103 |
batch_size=8
|
| 104 |
padding='max_length'
|
| 105 |
truncation=True
|
|
@@ -112,7 +112,6 @@ splits={"train":0.8, "val":0.1}
|
|
| 112 |
use_trainer=True
|
| 113 |
fp16=True
|
| 114 |
early_stopping=True
|
| 115 |
-
|
| 116 |
`
|
| 117 |
|
| 118 |
|
|
@@ -120,7 +119,7 @@ early_stopping=True
|
|
| 120 |
|
| 121 |
sklearn classifier table on random test split:
|
| 122 |
|
| 123 |
-
|
| 124 |
|
| 125 |
precision recall f1-score support
|
| 126 |
|
|
@@ -132,8 +131,7 @@ sklearn classifier table on random test split:
|
|
| 132 |
macro avg 0.70 0.66 0.67 7939
|
| 133 |
weighted avg 0.79 0.80 0.79 7939
|
| 134 |
|
| 135 |
-
|
| 136 |
-
`
|
| 137 |
|
| 138 |
|
| 139 |
## Model Card Authors
|
|
|
|
| 69 |
|
| 70 |
Use the code below to get started with the model.
|
| 71 |
|
| 72 |
+
```
|
| 73 |
|
| 74 |
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
| 75 |
|
|
|
|
| 77 |
|
| 78 |
model = AutoModelForSequenceClassification.from_pretrained("semaj83/scibert_finetuned_ctmatch")
|
| 79 |
|
| 80 |
+
```
|
| 81 |
|
| 82 |
## Training Details
|
| 83 |
|
|
|
|
| 98 |
|
| 99 |
#### Training Hyperparameters
|
| 100 |
|
| 101 |
+
|
| 102 |
+
`max_sequence_length=512
|
| 103 |
batch_size=8
|
| 104 |
padding='max_length'
|
| 105 |
truncation=True
|
|
|
|
| 112 |
use_trainer=True
|
| 113 |
fp16=True
|
| 114 |
early_stopping=True
|
|
|
|
| 115 |
`
|
| 116 |
|
| 117 |
|
|
|
|
| 119 |
|
| 120 |
sklearn classifier table on random test split:
|
| 121 |
|
| 122 |
+
```
|
| 123 |
|
| 124 |
precision recall f1-score support
|
| 125 |
|
|
|
|
| 131 |
macro avg 0.70 0.66 0.67 7939
|
| 132 |
weighted avg 0.79 0.80 0.79 7939
|
| 133 |
|
| 134 |
+
```
|
|
|
|
| 135 |
|
| 136 |
|
| 137 |
## Model Card Authors
|