🍻 cheers

README.md

@@ -2,7 +2,11 @@
 license: apache-2.0
 base_model: google/vit-large-patch32-384
 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-large-patch32-384](https://huggingface.co/google/vit-large-patch32-384) on an unknown dataset.
+This model is a fine-tuned version of [google/vit-large-patch32-384](https://huggingface.co/google/vit-large-patch32-384) on the beans dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0003
+- Accuracy: 1.0
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 4.0,
     "eval_accuracy": 1.0,
-    "eval_loss": 0.011184412986040115,
-    "eval_runtime": 2.4321,
-    "eval_samples_per_second": 33.716,
-    "eval_steps_per_second": 4.523,
-    "total_flos": 2.5417372593586176e+16,
-    "train_loss": 0.17717325119745164,
-    "train_runtime": 30.5569,
-    "train_samples_per_second": 10.734,
-    "train_steps_per_second": 2.749
+    "eval_loss": 0.00034369202330708504,
+    "eval_runtime": 3.9237,
+    "eval_samples_per_second": 20.899,
+    "eval_steps_per_second": 2.804,
+    "total_flos": 2.6605778719997952e+17,
+    "train_loss": 0.25595739838622866,
+    "train_runtime": 81.3097,
+    "train_samples_per_second": 4.034,
+    "train_steps_per_second": 1.033
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "eval_accuracy": 1.0,
-    "eval_loss": 0.011184412986040115,
-    "eval_runtime": 2.4321,
-    "eval_samples_per_second": 33.716,
-    "eval_steps_per_second": 4.523
+    "eval_loss": 0.00034369202330708504,
+    "eval_runtime": 3.9237,
+    "eval_samples_per_second": 20.899,
+    "eval_steps_per_second": 2.804
 }

runs/Aug30_09-47-54_7e2de4304170/events.out.tfevents.1725011417.7e2de4304170

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:336149fb84d5fa72bb3822856b3a44d935c6a5cf2ae18a9bdf8de681d418ba76
+size 40

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
-    "total_flos": 2.5417372593586176e+16,
-    "train_loss": 0.17717325119745164,
-    "train_runtime": 30.5569,
-    "train_samples_per_second": 10.734,
-    "train_steps_per_second": 2.749
+    "total_flos": 2.6605778719997952e+17,
+    "train_loss": 0.25595739838622866,
+    "train_runtime": 81.3097,
+    "train_samples_per_second": 4.034,
+    "train_steps_per_second": 1.033
 }

trainer_state.json

@@ -10,68 +10,68 @@
   "log_history": [
     {
       "epoch": 0.47619047619047616,
-      "grad_norm": 2.757856845855713,
-      "learning_rate": 0.0001761904761904762,
-      "loss": 0.5843,
+      "grad_norm": 9.25047492980957,
+      "learning_rate": 0.0001785714285714286,
+      "loss": 0.8938,
       "step": 10
     },
     {
       "epoch": 0.9523809523809523,
-      "grad_norm": 3.4689693450927734,
-      "learning_rate": 0.00015238095238095237,
-      "loss": 0.5473,
+      "grad_norm": 13.209284782409668,
+      "learning_rate": 0.00015476190476190478,
+      "loss": 0.4135,
       "step": 20
     },
     {
       "epoch": 1.4285714285714286,
-      "grad_norm": 0.5666776299476624,
-      "learning_rate": 0.00012857142857142858,
-      "loss": 0.1833,
+      "grad_norm": 0.18857085704803467,
+      "learning_rate": 0.00013095238095238096,
+      "loss": 0.1841,
       "step": 30
     },
     {
       "epoch": 1.9047619047619047,
-      "grad_norm": 0.2773081362247467,
-      "learning_rate": 0.00010476190476190477,
-      "loss": 0.1073,
+      "grad_norm": 3.675966262817383,
+      "learning_rate": 0.00010714285714285715,
+      "loss": 0.2689,
       "step": 40
     },
     {
       "epoch": 2.380952380952381,
-      "grad_norm": 0.14523948729038239,
-      "learning_rate": 8.095238095238096e-05,
-      "loss": 0.0217,
+      "grad_norm": 0.023952171206474304,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 0.276,
       "step": 50
     },
     {
       "epoch": 2.857142857142857,
-      "grad_norm": 0.10562175512313843,
-      "learning_rate": 5.714285714285714e-05,
-      "loss": 0.0158,
+      "grad_norm": 0.010658332146704197,
+      "learning_rate": 5.9523809523809524e-05,
+      "loss": 0.1114,
       "step": 60
     },
     {
       "epoch": 3.3333333333333335,
-      "grad_norm": 0.09110253304243088,
-      "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.0125,
+      "grad_norm": 0.013588939793407917,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.0018,
       "step": 70
     },
     {
       "epoch": 3.8095238095238093,
-      "grad_norm": 0.09965213388204575,
-      "learning_rate": 9.523809523809523e-06,
-      "loss": 0.0116,
+      "grad_norm": 0.011217363178730011,
+      "learning_rate": 1.1904761904761905e-05,
+      "loss": 0.0004,
       "step": 80
     },
     {
       "epoch": 4.0,
       "step": 84,
-      "total_flos": 2.5417372593586176e+16,
-      "train_loss": 0.17717325119745164,
-      "train_runtime": 30.5569,
-      "train_samples_per_second": 10.734,
-      "train_steps_per_second": 2.749
+      "total_flos": 2.6605778719997952e+17,
+      "train_loss": 0.25595739838622866,
+      "train_runtime": 81.3097,
+      "train_samples_per_second": 4.034,
+      "train_steps_per_second": 1.033
     }
   ],
   "logging_steps": 10,
@@ -91,7 +91,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5417372593586176e+16,
+  "total_flos": 2.6605778719997952e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null