🍻 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: 0.0096
+- Accuracy: 1.0
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 4.0,
     "eval_accuracy": 1.0,
-    "eval_loss": 0.015804477035999298,
-    "eval_runtime": 2.4811,
-    "eval_samples_per_second": 33.05,
-    "eval_steps_per_second": 4.433,
+    "eval_loss": 0.009642996825277805,
+    "eval_runtime": 2.6862,
+    "eval_samples_per_second": 30.526,
+    "eval_steps_per_second": 4.095,
     "total_flos": 2.5417372593586176e+16,
-    "train_loss": 0.22665784472510928,
-    "train_runtime": 28.7006,
-    "train_samples_per_second": 11.428,
-    "train_steps_per_second": 2.927
+    "train_loss": 0.15871779123942056,
+    "train_runtime": 30.4881,
+    "train_samples_per_second": 10.758,
+    "train_steps_per_second": 2.755
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "eval_accuracy": 1.0,
-    "eval_loss": 0.015804477035999298,
-    "eval_runtime": 2.4811,
-    "eval_samples_per_second": 33.05,
-    "eval_steps_per_second": 4.433
+    "eval_loss": 0.009642996825277805,
+    "eval_runtime": 2.6862,
+    "eval_samples_per_second": 30.526,
+    "eval_steps_per_second": 4.095
 }

runs/Aug30_09-27-15_7e2de4304170/events.out.tfevents.1725010090.7e2de4304170

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74ccc743383e0a22f5f70f7a6f976cbaf6b7455a920918f9fae79e94624d9319
+size 40

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "total_flos": 2.5417372593586176e+16,
-    "train_loss": 0.22665784472510928,
-    "train_runtime": 28.7006,
-    "train_samples_per_second": 11.428,
-    "train_steps_per_second": 2.927
+    "train_loss": 0.15871779123942056,
+    "train_runtime": 30.4881,
+    "train_samples_per_second": 10.758,
+    "train_steps_per_second": 2.755
 }

trainer_state.json

@@ -10,68 +10,68 @@
   "log_history": [
     {
       "epoch": 0.47619047619047616,
-      "grad_norm": 3.3773086071014404,
+      "grad_norm": 2.812675952911377,
       "learning_rate": 0.0001761904761904762,
-      "loss": 0.6171,
+      "loss": 0.5907,
       "step": 10
     },
     {
       "epoch": 0.9523809523809523,
-      "grad_norm": 4.038491249084473,
+      "grad_norm": 5.478332996368408,
       "learning_rate": 0.00015238095238095237,
-      "loss": 0.4746,
+      "loss": 0.4214,
       "step": 20
     },
     {
       "epoch": 1.4285714285714286,
-      "grad_norm": 0.7119430899620056,
+      "grad_norm": 1.4264696836471558,
       "learning_rate": 0.00012857142857142858,
-      "loss": 0.2603,
+      "loss": 0.1644,
       "step": 30
     },
     {
       "epoch": 1.9047619047619047,
-      "grad_norm": 0.4082745611667633,
+      "grad_norm": 0.1871589571237564,
       "learning_rate": 0.00010476190476190477,
-      "loss": 0.2766,
+      "loss": 0.1012,
       "step": 40
     },
     {
       "epoch": 2.380952380952381,
-      "grad_norm": 0.17519672214984894,
+      "grad_norm": 0.10930836200714111,
       "learning_rate": 8.095238095238096e-05,
-      "loss": 0.1537,
+      "loss": 0.0177,
       "step": 50
     },
     {
       "epoch": 2.857142857142857,
-      "grad_norm": 0.1577773243188858,
+      "grad_norm": 0.09269272536039352,
       "learning_rate": 5.714285714285714e-05,
-      "loss": 0.0797,
+      "loss": 0.0132,
       "step": 60
     },
     {
       "epoch": 3.3333333333333335,
-      "grad_norm": 0.12391568720340729,
+      "grad_norm": 0.08020050823688507,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.0181,
+      "loss": 0.0107,
       "step": 70
     },
     {
       "epoch": 3.8095238095238093,
-      "grad_norm": 0.28916484117507935,
+      "grad_norm": 0.08233410120010376,
       "learning_rate": 9.523809523809523e-06,
-      "loss": 0.0173,
+      "loss": 0.0098,
       "step": 80
     },
     {
       "epoch": 4.0,
       "step": 84,
       "total_flos": 2.5417372593586176e+16,
-      "train_loss": 0.22665784472510928,
-      "train_runtime": 28.7006,
-      "train_samples_per_second": 11.428,
-      "train_steps_per_second": 2.927
+      "train_loss": 0.15871779123942056,
+      "train_runtime": 30.4881,
+      "train_samples_per_second": 10.758,
+      "train_steps_per_second": 2.755
     }
   ],
   "logging_steps": 10,