End of training

README.md

@@ -3,6 +3,8 @@ library_name: transformers
 license: apache-2.0
 base_model: google/vit-base-patch16-224
 tags:
+- image-classification
+- vision
 - generated_from_trainer
 metrics:
 - accuracy
@@ -16,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-base-cocoa
 
-This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the SemilleroCV/Cocoa-dataset dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5570
-- Accuracy: 0.9350
+- Loss: 0.2061
+- Accuracy: 0.9278
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 100.0,
+    "eval_accuracy": 0.927797833935018,
+    "eval_loss": 0.20614954829216003,
+    "eval_runtime": 1.0793,
+    "eval_samples_per_second": 256.658,
+    "eval_steps_per_second": 32.43,
+    "total_flos": 1.2135680631115776e+19,
+    "train_loss": 0.06464558898389924,
+    "train_runtime": 1480.7558,
+    "train_samples_per_second": 105.757,
+    "train_steps_per_second": 13.236
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 100.0,
+    "eval_accuracy": 0.927797833935018,
+    "eval_loss": 0.20614954829216003,
+    "eval_runtime": 1.0793,
+    "eval_samples_per_second": 256.658,
+    "eval_steps_per_second": 32.43
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 100.0,
+    "total_flos": 1.2135680631115776e+19,
+    "train_loss": 0.06464558898389924,
+    "train_runtime": 1480.7558,
+    "train_samples_per_second": 105.757,
+    "train_steps_per_second": 13.236
+}