update model card README.md

README.md

@@ -1,4 +1,5 @@
 ---
+license: apache-2.0
 tags:
 - generated_from_trainer
 datasets:
@@ -9,7 +10,24 @@ metrics:
 - f1
 model-index:
 - name: sd-panelization-v2
-  results: []
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: source_data_nlp
+      type: source_data_nlp
+      args: PANELIZATION
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.9134245120169964
+    - name: Recall
+      type: recall
+      value: 0.9494824016563147
+    - name: F1
+      type: f1
+      value: 0.9311044937736871
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,13 +35,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # sd-panelization-v2
 
-This model was trained from scratch on the source_data_nlp dataset.
+This model is a fine-tuned version of [michiyasunaga/BioLinkBERT-large](https://huggingface.co/michiyasunaga/BioLinkBERT-large) on the source_data_nlp dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0075
-- Accuracy Score: 0.9980
-- Precision: 0.9651
-- Recall: 0.9905
-- F1: 0.9776
+- Loss: 0.0050
+- Accuracy Score: 0.9982
+- Precision: 0.9134
+- Recall: 0.9495
+- F1: 0.9311
 
 ## Model description
 
@@ -43,19 +61,18 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 64
+- train_batch_size: 32
 - eval_batch_size: 256
 - seed: 42
 - optimizer: Adafactor
 - lr_scheduler_type: linear
-- num_epochs: 2.0
+- num_epochs: 1.0
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy Score | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------------:|:---------:|:------:|:------:|
-| 0.008         | 1.0   | 216  | 0.0072          | 0.9979         | 0.9715    | 0.9761 | 0.9738 |
-| 0.005         | 2.0   | 432  | 0.0075          | 0.9980         | 0.9651    | 0.9905 | 0.9776 |
+| 0.0048        | 1.0   | 431  | 0.0050          | 0.9982         | 0.9134    | 0.9495 | 0.9311 |
 
 
 ### Framework versions