End of training

README.md

@@ -23,10 +23,10 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9190789473684211
+      value: 0.9130263157894737
     - name: F1
       type: f1
-      value: 0.918950504570256
+      value: 0.913030189041398
 ---
 
 <!-- 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 ag_news dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2415
-- Accuracy: 0.9191
-- F1: 0.9190
+- Loss: 0.2713
+- Accuracy: 0.9130
+- F1: 0.9130
 
 ## Model description
 
@@ -69,13 +69,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| No log        | 1.0   | 313  | 0.2653          | 0.9128   | 0.9129 |
-| 0.306         | 2.0   | 626  | 0.2415          | 0.9191   | 0.9190 |
+| No log        | 1.0   | 313  | 0.2816          | 0.9046   | 0.9042 |
+| 0.2967        | 2.0   | 626  | 0.2713          | 0.9130   | 0.9130 |
 
 
 ### Framework versions
 
-- Transformers 4.34.0.dev0
+- Transformers 4.34.1
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.4
 - Tokenizers 0.14.0

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0074e5ff7b943ac8836b8137f36ac60f8152eab5c24be54f34d4b48aff0f3ed
+oid sha256:8924d9e1b21ec9765f95d93fbd4e6da0911cd9a94842a67ef33037be1fa6bdcd
 size 267861677