Training Completed!

README.md

@@ -1,5 +1,6 @@
 ---
 license: apache-2.0
+base_model: distilbert-base-uncased
 tags:
 - generated_from_trainer
 datasets:
@@ -16,16 +17,16 @@ model-index:
     dataset:
       name: emotion
       type: emotion
-      config: default
-      split: train
-      args: default
+      config: split
+      split: validation
+      args: split
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9265
+      value: 0.9235
     - name: F1
       type: f1
-      value: 0.9265277328493297
+      value: 0.9234211273536393
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,9 +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: 0.2240
-- Accuracy: 0.9265
-- F1: 0.9265
+- Loss: 0.2134
+- Accuracy: 0.9235
+- F1: 0.9234
 
 ## Model description
 
@@ -68,13 +69,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.8488        | 1.0   | 250  | 0.3268          | 0.9055   | 0.9031 |
-| 0.2532        | 2.0   | 500  | 0.2240          | 0.9265   | 0.9265 |
+| 0.8105        | 1.0   | 250  | 0.3134          | 0.9075   | 0.9068 |
+| 0.2438        | 2.0   | 500  | 0.2134          | 0.9235   | 0.9234 |
 
 
 ### Framework versions
 
-- Transformers 4.21.1
-- Pytorch 1.12.0+cu113
-- Datasets 2.4.0
-- Tokenizers 0.12.1
+- Transformers 4.33.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.13.3