Fine-tuned BioGPT on ncbi-disease for BIO NER

README.md

@@ -26,16 +26,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.474835886214442
+      value: 0.4819148936170213
     - name: Recall
       type: recall
-      value: 0.5514612452350699
+      value: 0.5756035578144854
     - name: F1
       type: f1
-      value: 0.5102880658436214
+      value: 0.5246091488129705
     - name: Accuracy
       type: accuracy
-      value: 0.9598648253994744
+      value: 0.9604906337352414
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -45,11 +45,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 0.1390
-- Precision: 0.4748
-- Recall: 0.5515
-- F1: 0.5103
-- Accuracy: 0.9599
+- Loss: 0.1351
+- Precision: 0.4819
+- Recall: 0.5756
+- F1: 0.5246
+- Accuracy: 0.9605
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01c13641bc4486bda02022e1a83dc028f28af45e1a1e2bff8468fb74782658b7
+oid sha256:bd6727256298639d7858c8a9c67669d921fcafb7df0b17eaebaaa065839c636e
 size 1387087524

runs/Apr12_23-41-34_b84241ad1cdb/events.out.tfevents.1744501299.b84241ad1cdb.1244.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c000bda8125322ce0ce27920553d53223feb94a3585fac2480c2796b05e490
+size 6679

runs/Apr12_23-41-34_b84241ad1cdb/events.out.tfevents.1744502150.b84241ad1cdb.1244.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c0e0972762161520bb9d56c557c342da9c79c0ac835c02c1cd84dba78ad3ec
+size 560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:869aaa2ecb0b94f16aae6228f437b25a15816d742c49e308532ceb6c0da38d4e
+oid sha256:394412ddfed4b6dcf7d6930a722f455f57d50f8dc799fd809466150c5bd1ed69
 size 5304