🍻 cheers

README.md

@@ -2,7 +2,11 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
+- vision
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: vit-base-beans
   results: []
@@ -13,7 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-base-beans
 
-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 beans dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0292
+- Accuracy: 1.0
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 4.0,
     "eval_accuracy": 1.0,
-    "eval_loss": 0.029831457883119583,
-    "eval_runtime": 1.8404,
-    "eval_samples_per_second": 31.515,
-    "eval_steps_per_second": 4.347,
+    "eval_loss": 0.02922426350414753,
+    "eval_runtime": 2.5047,
+    "eval_samples_per_second": 23.157,
+    "eval_steps_per_second": 3.194,
     "total_flos": 1.7978141590585344e+16,
-    "train_loss": 0.3446396509806315,
-    "train_runtime": 22.8779,
-    "train_samples_per_second": 10.141,
-    "train_steps_per_second": 2.623
+    "train_loss": 0.3442591349283854,
+    "train_runtime": 23.0063,
+    "train_samples_per_second": 10.084,
+    "train_steps_per_second": 2.608
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "eval_accuracy": 1.0,
-    "eval_loss": 0.029831457883119583,
-    "eval_runtime": 1.8404,
-    "eval_samples_per_second": 31.515,
-    "eval_steps_per_second": 4.347
+    "eval_loss": 0.02922426350414753,
+    "eval_runtime": 2.5047,
+    "eval_samples_per_second": 23.157,
+    "eval_steps_per_second": 3.194
 }

runs/Aug30_08-34-08_7e2de4304170/events.out.tfevents.1725006897.7e2de4304170

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23d06ac155fbb4568734ed446b12cd54ebe4029828ac5fd0efa1c8f9c0a8aa69
+size 40

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "total_flos": 1.7978141590585344e+16,
-    "train_loss": 0.3446396509806315,
-    "train_runtime": 22.8779,
-    "train_samples_per_second": 10.141,
-    "train_steps_per_second": 2.623
+    "train_loss": 0.3442591349283854,
+    "train_runtime": 23.0063,
+    "train_samples_per_second": 10.084,
+    "train_steps_per_second": 2.608
 }

trainer_state.json

@@ -10,54 +10,54 @@
   "log_history": [
     {
       "epoch": 0.6666666666666666,
-      "grad_norm": 0.9146473407745361,
+      "grad_norm": 2.396704912185669,
       "learning_rate": 0.0001666666666666667,
-      "loss": 0.636,
+      "loss": 0.616,
       "step": 10
     },
     {
       "epoch": 1.3333333333333333,
-      "grad_norm": 2.536752700805664,
+      "grad_norm": 2.4850783348083496,
       "learning_rate": 0.00013333333333333334,
-      "loss": 0.6707,
+      "loss": 0.7095,
       "step": 20
     },
     {
       "epoch": 2.0,
-      "grad_norm": 8.357431411743164,
+      "grad_norm": 15.093992233276367,
       "learning_rate": 0.0001,
-      "loss": 0.448,
+      "loss": 0.4833,
       "step": 30
     },
     {
       "epoch": 2.6666666666666665,
-      "grad_norm": 0.41346922516822815,
+      "grad_norm": 1.8995352983474731,
       "learning_rate": 6.666666666666667e-05,
-      "loss": 0.1903,
+      "loss": 0.1775,
       "step": 40
     },
     {
       "epoch": 3.3333333333333335,
-      "grad_norm": 0.2532810568809509,
+      "grad_norm": 0.27144622802734375,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.0844,
+      "loss": 0.0467,
       "step": 50
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.21754373610019684,
+      "grad_norm": 0.5607824921607971,
       "learning_rate": 0.0,
-      "loss": 0.0384,
+      "loss": 0.0327,
       "step": 60
     },
     {
       "epoch": 4.0,
       "step": 60,
       "total_flos": 1.7978141590585344e+16,
-      "train_loss": 0.3446396509806315,
-      "train_runtime": 22.8779,
-      "train_samples_per_second": 10.141,
-      "train_steps_per_second": 2.623
+      "train_loss": 0.3442591349283854,
+      "train_runtime": 23.0063,
+      "train_samples_per_second": 10.084,
+      "train_steps_per_second": 2.608
     }
   ],
   "logging_steps": 10,