End of training

README.md

@@ -3,6 +3,8 @@ library_name: transformers
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
+- vision
 - generated_from_trainer
 metrics:
 - accuracy
@@ -16,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # image_segmentation_classifier
 
-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.
+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 taresco/newspaper_ocr dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0036
-- Accuracy: 0.9990
+- Loss: 0.0033
+- Accuracy: 0.9993
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9993024066968957,
+    "eval_loss": 0.003324420191347599,
+    "eval_runtime": 127.0066,
+    "eval_samples_per_second": 22.574,
+    "eval_steps_per_second": 2.827,
+    "total_flos": 6.293899396497162e+18,
+    "train_loss": 0.00641422240726846,
+    "train_runtime": 5338.9651,
+    "train_samples_per_second": 15.213,
+    "train_steps_per_second": 1.902
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9993024066968957,
+    "eval_loss": 0.003324420191347599,
+    "eval_runtime": 127.0066,
+    "eval_samples_per_second": 22.574,
+    "eval_steps_per_second": 2.827
+}

runs/Apr22_18-18-04_ebfa2fd32231/events.out.tfevents.1745351689.ebfa2fd32231.204.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b670db8e66868369ff48638712cf12e4d5284c0c4baeaef8b54fee64d8bf8a8
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 6.293899396497162e+18,
+    "train_loss": 0.00641422240726846,
+    "train_runtime": 5338.9651,
+    "train_samples_per_second": 15.213,
+    "train_steps_per_second": 1.902
+}