Fine-tuning Complete

README.md

@@ -23,10 +23,10 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.926
+      value: 0.9225
     - name: F1
       type: f1
-      value: 0.9260875538517123
+      value: 0.922512086580173
 ---
 
 <!-- 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 emotion dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2045
-- Accuracy: 0.926
-- F1: 0.9261
+- Loss: 0.2175
+- Accuracy: 0.9225
+- F1: 0.9225
 
 ## Model description
 
@@ -58,8 +58,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 56
-- eval_batch_size: 56
+- train_batch_size: 64
+- eval_batch_size: 64
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -69,8 +69,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.4094        | 1.0   | 286  | 0.2890          | 0.9125   | 0.9121 |
-| 0.2244        | 2.0   | 572  | 0.2045          | 0.926    | 0.9261 |
+| 0.5816        | 1.0   | 250  | 0.3310          | 0.903    | 0.9030 |
+| 0.2304        | 2.0   | 500  | 0.2175          | 0.9225   | 0.9225 |
 
 
 ### Framework versions