End of training

README.md

@@ -17,8 +17,8 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.8884
-- Accuracy: 0.4847
+- Loss: 1.6266
+- Accuracy: 0.7355
 
 ## Model description
 
@@ -46,22 +46,32 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 10
+- num_epochs: 20
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 5.0138        | 1.0   | 227  | 5.2286          | 0.2802   |
-| 4.7675        | 2.0   | 455  | 4.9884          | 0.3151   |
-| 4.4753        | 3.0   | 682  | 4.7386          | 0.3547   |
-| 4.1843        | 4.0   | 910  | 4.5348          | 0.3852   |
-| 3.9013        | 5.0   | 1137 | 4.3369          | 0.4185   |
-| 3.7744        | 6.0   | 1365 | 4.1786          | 0.4363   |
-| 3.5452        | 7.0   | 1592 | 4.0784          | 0.4520   |
-| 3.472         | 8.0   | 1820 | 3.9941          | 0.4680   |
-| 3.3858        | 9.0   | 2047 | 3.9071          | 0.4834   |
-| 3.3678        | 9.98  | 2270 | 3.8884          | 0.4847   |
+| 3.2092        | 1.0   | 227  | 3.8429          | 0.4847   |
+| 3.1076        | 2.0   | 455  | 3.6825          | 0.4990   |
+| 2.7996        | 3.0   | 682  | 3.4241          | 0.5194   |
+| 2.4653        | 4.0   | 910  | 3.1673          | 0.5513   |
+| 2.117         | 5.0   | 1137 | 2.9653          | 0.5733   |
+| 1.977         | 6.0   | 1365 | 2.7396          | 0.6057   |
+| 1.7053        | 7.0   | 1592 | 2.6115          | 0.6107   |
+| 1.5829        | 8.0   | 1820 | 2.4370          | 0.6395   |
+| 1.4496        | 9.0   | 2047 | 2.2758          | 0.6635   |
+| 1.3663        | 10.0  | 2275 | 2.1700          | 0.6816   |
+| 1.2573        | 11.0  | 2502 | 2.0498          | 0.6910   |
+| 1.1949        | 12.0  | 2730 | 1.9767          | 0.6956   |
+| 1.1401        | 13.0  | 2957 | 1.8944          | 0.7050   |
+| 1.0346        | 14.0  | 3185 | 1.8601          | 0.7072   |
+| 0.9015        | 15.0  | 3412 | 1.7747          | 0.7215   |
+| 0.8774        | 16.0  | 3640 | 1.7055          | 0.7239   |
+| 0.875         | 17.0  | 3867 | 1.7231          | 0.7294   |
+| 0.9291        | 18.0  | 4095 | 1.6697          | 0.7303   |
+| 0.8888        | 19.0  | 4322 | 1.6108          | 0.7404   |
+| 0.8496        | 19.96 | 4540 | 1.6266          | 0.7355   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:207ebc65b2a3b5f159d317882db7df243b39c29f459e541758df482a1a09ce2f
+oid sha256:d3e78db8b3cffeb33a19d1affce3277415d264492a9f1477508b47a07ecc7abb
 size 346284620