update model card README.md

README.md

@@ -4,9 +4,36 @@ tags:
 - generated_from_trainer
 datasets:
 - ncbi_disease
+metrics:
+- precision
+- recall
+- f1
+- accuracy
 model-index:
 - name: finetuned-biogpt
-  results: []
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: ncbi_disease
+      type: ncbi_disease
+      config: ncbi_disease
+      split: test
+      args: ncbi_disease
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.0761904761904762
+    - name: Recall
+      type: recall
+      value: 0.058333333333333334
+    - name: F1
+      type: f1
+      value: 0.06607669616519174
+    - name: Accuracy
+      type: accuracy
+      value: 0.9220180016640194
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,6 +42,12 @@ should probably proofread and complete it, then remove this comment. -->
 # finetuned-biogpt
 
 This model is a fine-tuned version of [microsoft/biogpt](https://huggingface.co/microsoft/biogpt) on the ncbi_disease dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2503
+- Precision: 0.0762
+- Recall: 0.0583
+- F1: 0.0661
+- Accuracy: 0.9220
 
 ## Model description
 
@@ -34,12 +67,20 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 340  | 0.2644          | 0.0426    | 0.0281 | 0.0339 | 0.9183   |
+| 0.3055        | 2.0   | 680  | 0.2503          | 0.0762    | 0.0583 | 0.0661 | 0.9220   |
+
 
 ### Framework versions