End of training

README.md

@@ -23,10 +23,10 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9033333333333333
+      value: 0.906
     - name: F1
       type: f1
-      value: 0.9045424621461486
+      value: 0.9076015727391874
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -36,9 +36,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5140
-- Accuracy: 0.9033
-- F1: 0.9045
+- Loss: 0.4657
+- Accuracy: 0.906
+- F1: 0.9076
 
 ## Model description
 
@@ -64,7 +64,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 2
-- label_smoothing_factor: 0.3
+- label_smoothing_factor: 0.2
 
 ### Training results
 

runs/Nov23_12-21-14_3b67a1353454/events.out.tfevents.1700742426.3b67a1353454.468.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df55db60e8ef27792a23466930423e6177ddb9d73ccf9391e83dcb920e9b6483
+size 457