End of training

README.md

@@ -15,9 +15,9 @@ 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:
-- Train Loss: 2.7724
-- Validation Loss: 1.6762
-- Train Accuracy: 0.813
+- Train Loss: 2.8240
+- Validation Loss: 1.6827
+- Train Accuracy: 0.818
 - Epoch: 0
 
 ## Model description
@@ -44,12 +44,11 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 2.7724     | 1.6762          | 0.813          | 0     |
+| 2.8240     | 1.6827          | 0.818          | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.38.0.dev0
+- Transformers 4.35.2
 - TensorFlow 2.15.0
-- Datasets 2.16.1
 - Tokenizers 0.15.0

config.json

@@ -224,5 +224,5 @@
   "num_hidden_layers": 12,
   "patch_size": 16,
   "qkv_bias": true,
-  "transformers_version": "4.38.0.dev0"
+  "transformers_version": "4.35.2"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10b82c0b104c6f1e60705aa98d998940ea80e4c6aaa2fa57e95e9105dad85c25
+oid sha256:bef2e48cca8cbc34e452d58319abca0ff52fbf4c00e2b5be7cafae7642902e80
 size 343773880