End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.66270783847981
+      value: 0.7102137767220903
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7669
-- Accuracy: 0.6627
+- Loss: 0.6785
+- Accuracy: 0.7102
 
 ## Model description
 
@@ -58,22 +58,22 @@ The following hyperparameters were used during training:
 - seed: 69
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.05
+- lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.6253        | 0.63  | 150  | 0.5451          | 0.7245   |
-| 0.486         | 1.27  | 300  | 0.5109          | 0.7411   |
-| 0.5475        | 1.9   | 450  | 0.5108          | 0.7363   |
-| 0.3781        | 2.53  | 600  | 0.6003          | 0.7078   |
-| 0.3875        | 3.16  | 750  | 0.4860          | 0.7720   |
-| 0.3855        | 3.8   | 900  | 0.4707          | 0.8100   |
-| 0.3493        | 4.43  | 1050 | 0.5047          | 0.7743   |
-| 0.3006        | 5.06  | 1200 | 0.5326          | 0.7625   |
-| 0.3104        | 5.7   | 1350 | 0.7669          | 0.6627   |
+| 0.6169        | 0.63  | 150  | 0.5812          | 0.6841   |
+| 0.4724        | 1.27  | 300  | 0.5037          | 0.7553   |
+| 0.5545        | 1.9   | 450  | 0.5195          | 0.7553   |
+| 0.3928        | 2.53  | 600  | 0.5964          | 0.7102   |
+| 0.3937        | 3.16  | 750  | 0.4637          | 0.7933   |
+| 0.3897        | 3.8   | 900  | 0.4548          | 0.8076   |
+| 0.356         | 4.43  | 1050 | 0.5327          | 0.7648   |
+| 0.319         | 5.06  | 1200 | 0.5126          | 0.7720   |
+| 0.3526        | 5.7   | 1350 | 0.6785          | 0.7102   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b93094ff9d33e201a2e4856b70372d184c0ec8eb887e227b133f6f1472726025
+oid sha256:0952b598af8f486e48dab3b6b0bf1a676b89e559753421664c1bff4e3e97fbf3
 size 343223968