End of training

README.md

@@ -16,12 +16,12 @@ model-index:
       name: fair_face
       type: fair_face
       config: '0.25'
-      split: train[:10000]
+      split: train[:7000]
       args: '0.25'
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.5965
+      value: 0.5707142857142857
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [nateraw/vit-age-classifier](https://huggingface.co/nateraw/vit-age-classifier) on the fair_face dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9479
-- Accuracy: 0.5965
+- Loss: 1.0061
+- Accuracy: 0.5707
 
 ## Model description
 
@@ -66,14 +66,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.0425        | 1.0   | 125  | 0.9358          | 0.6035   |
-| 0.8553        | 2.0   | 250  | 0.9411          | 0.5905   |
-| 0.8872        | 3.0   | 375  | 0.9626          | 0.6035   |
+| 0.9702        | 0.99  | 87   | 0.9851          | 0.5657   |
+| 0.912         | 2.0   | 175  | 0.9593          | 0.58     |
+| 0.8171        | 2.98  | 261  | 1.0026          | 0.58     |
 
 
 ### Framework versions
 
-- Transformers 4.33.1
-- Pytorch 2.0.1+cu118
+- Transformers 4.34.0.dev0
+- Pytorch 1.12.1+cu116
 - Datasets 2.14.5
-- Tokenizers 0.13.3
+- Tokenizers 0.12.1

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba3bdeea2a7a79123069685c6d5d5108c693e4a5094a7fea683bdeefdfa290a5
+oid sha256:4c5883496867b13897143a8464cf649fc54bf2aa564e8780d34dd76f9528d2f2
 size 343288497