VIT model tuned

README.md

@@ -2,6 +2,8 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
+- clothes-classification
 - generated_from_trainer
 metrics:
 - accuracy
@@ -15,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-clothes-classification
 
-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 DBQ/Matches.Fashion.Product.prices.France dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7642
-- Accuracy: 0.6989
+- Loss: 1.2328
+- Accuracy: 0.6395
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.6395238095238095,
+    "eval_loss": 1.2328253984451294,
+    "eval_runtime": 192.2029,
+    "eval_samples_per_second": 10.926,
+    "eval_steps_per_second": 1.368,
+    "total_flos": 4.342312894316544e+18,
+    "train_loss": 0.30790301413195476,
+    "train_runtime": 7468.7033,
+    "train_samples_per_second": 7.498,
+    "train_steps_per_second": 0.937
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.6395238095238095,
+    "eval_loss": 1.2328253984451294,
+    "eval_runtime": 192.2029,
+    "eval_samples_per_second": 10.926,
+    "eval_steps_per_second": 1.368
+}

runs/Apr24_04-18-24_ip-10-192-11-36/events.out.tfevents.1713939983.ip-10-192-11-36.16149.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:997c54dc7fe4baac86f277d9fcf928330c4b17bbb60621e456ea927accf42853
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 8.0,
+    "total_flos": 4.342312894316544e+18,
+    "train_loss": 0.30790301413195476,
+    "train_runtime": 7468.7033,
+    "train_samples_per_second": 7.498,
+    "train_steps_per_second": 0.937
+}