🍻 cheers

README.md

@@ -3,6 +3,7 @@ library_name: transformers
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
 - generated_from_trainer
 metrics:
 - accuracy
@@ -16,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-base-beans-demo-v5
 
-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 ellabettison/logo-matching dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4711
-- Accuracy: 0.5886
+- Loss: 0.4710
+- Accuracy: 0.5788
 
 ## Model description
 

all_results.json

@@ -1,8 +1,13 @@
 {
     "epoch": 1.0,
+    "eval_accuracy": 0.5787671232876712,
+    "eval_loss": 0.4710308611392975,
+    "eval_runtime": 4.0877,
+    "eval_samples_per_second": 71.433,
+    "eval_steps_per_second": 9.051,
     "total_flos": 3.431561927399424e+16,
-    "train_loss": 0.5442130650792804,
-    "train_runtime": 45.7435,
-    "train_samples_per_second": 9.663,
-    "train_steps_per_second": 0.612
+    "train_loss": 0.5463629875864301,
+    "train_runtime": 51.9236,
+    "train_samples_per_second": 8.513,
+    "train_steps_per_second": 0.539
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.5787671232876712,
+    "eval_loss": 0.4710308611392975,
+    "eval_runtime": 4.0877,
+    "eval_samples_per_second": 71.433,
+    "eval_steps_per_second": 9.051
+}

runs/Jan15_19-02-27_a99b99d67614/events.out.tfevents.1736967830.a99b99d67614.505.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:360f926da13db2f5b92f7c7f2b867bceff82e221e83592ce782cd62362984183
+size 405

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 3.431561927399424e+16,
-    "train_loss": 0.5442130650792804,
-    "train_runtime": 45.7435,
-    "train_samples_per_second": 9.663,
-    "train_steps_per_second": 0.612
+    "train_loss": 0.5463629875864301,
+    "train_runtime": 51.9236,
+    "train_samples_per_second": 8.513,
+    "train_steps_per_second": 0.539
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.4711265563964844,
+  "best_metric": 0.47109532356262207,
   "best_model_checkpoint": "./vit-base-beans-demo-v5/checkpoint-28",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,35 +10,35 @@
   "log_history": [
     {
       "epoch": 0.35714285714285715,
-      "grad_norm": 0.18181030452251434,
+      "grad_norm": 0.18598148226737976,
       "learning_rate": 0.00012857142857142858,
-      "loss": 0.6256,
+      "loss": 0.6304,
       "step": 10
     },
     {
       "epoch": 0.7142857142857143,
-      "grad_norm": 0.1677406281232834,
+      "grad_norm": 0.1671164631843567,
       "learning_rate": 5.714285714285714e-05,
-      "loss": 0.5163,
+      "loss": 0.5174,
       "step": 20
     },
     {
       "epoch": 1.0,
-      "eval_loss": 0.4711265563964844,
-      "eval_roc_auc": NaN,
-      "eval_runtime": 3.4927,
-      "eval_samples_per_second": 85.607,
-      "eval_steps_per_second": 10.88,
+      "eval_accuracy": 0.5886287625418061,
+      "eval_loss": 0.47109532356262207,
+      "eval_runtime": 8.2385,
+      "eval_samples_per_second": 36.293,
+      "eval_steps_per_second": 4.613,
       "step": 28
     },
     {
       "epoch": 1.0,
       "step": 28,
       "total_flos": 3.431561927399424e+16,
-      "train_loss": 0.5442130650792804,
-      "train_runtime": 45.7435,
-      "train_samples_per_second": 9.663,
-      "train_steps_per_second": 0.612
+      "train_loss": 0.5463629875864301,
+      "train_runtime": 51.9236,
+      "train_samples_per_second": 8.513,
+      "train_steps_per_second": 0.539
     }
   ],
   "logging_steps": 10,