🍻 cheers

README.md

@@ -2,7 +2,10 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: vit-base-beans
   results: []
@@ -13,7 +16,10 @@ 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: 0.0288
+- Accuracy: 1.0
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 4.0,
     "eval_accuracy": 1.0,
-    "eval_loss": 0.06532761454582214,
-    "eval_runtime": 1.8393,
-    "eval_samples_per_second": 31.533,
-    "eval_steps_per_second": 4.349,
+    "eval_loss": 0.02880885638296604,
+    "eval_runtime": 1.9696,
+    "eval_samples_per_second": 29.448,
+    "eval_steps_per_second": 4.062,
     "total_flos": 1.7978141590585344e+16,
-    "train_loss": 0.40461832682291665,
-    "train_runtime": 22.5515,
-    "train_samples_per_second": 10.288,
-    "train_steps_per_second": 2.661
+    "train_loss": 0.325518798828125,
+    "train_runtime": 22.8361,
+    "train_samples_per_second": 10.159,
+    "train_steps_per_second": 2.627
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "eval_accuracy": 1.0,
-    "eval_loss": 0.06532761454582214,
-    "eval_runtime": 1.8393,
-    "eval_samples_per_second": 31.533,
-    "eval_steps_per_second": 4.349
+    "eval_loss": 0.02880885638296604,
+    "eval_runtime": 1.9696,
+    "eval_samples_per_second": 29.448,
+    "eval_steps_per_second": 4.062
 }

runs/Aug30_08-23-02_7e2de4304170/events.out.tfevents.1725006228.7e2de4304170

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cf42fba2c70ff6db141b08a2a4041570c17b3e620d312d80161fef52177e496
+size 40

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "total_flos": 1.7978141590585344e+16,
-    "train_loss": 0.40461832682291665,
-    "train_runtime": 22.5515,
-    "train_samples_per_second": 10.288,
-    "train_steps_per_second": 2.661
+    "train_loss": 0.325518798828125,
+    "train_runtime": 22.8361,
+    "train_samples_per_second": 10.159,
+    "train_steps_per_second": 2.627
 }

trainer_state.json

@@ -10,54 +10,54 @@
   "log_history": [
     {
       "epoch": 0.6666666666666666,
-      "grad_norm": 2.283698558807373,
+      "grad_norm": 1.813136100769043,
       "learning_rate": 0.0001666666666666667,
-      "loss": 0.6508,
+      "loss": 0.6367,
       "step": 10
     },
     {
       "epoch": 1.3333333333333333,
-      "grad_norm": 2.1393485069274902,
+      "grad_norm": 3.1886422634124756,
       "learning_rate": 0.00013333333333333334,
-      "loss": 0.7352,
+      "loss": 0.7056,
       "step": 20
     },
     {
       "epoch": 2.0,
-      "grad_norm": 8.583788871765137,
+      "grad_norm": 10.936144828796387,
       "learning_rate": 0.0001,
-      "loss": 0.5144,
+      "loss": 0.3764,
       "step": 30
     },
     {
       "epoch": 2.6666666666666665,
-      "grad_norm": 2.3513376712799072,
+      "grad_norm": 0.5728101134300232,
       "learning_rate": 6.666666666666667e-05,
-      "loss": 0.3221,
+      "loss": 0.1584,
       "step": 40
     },
     {
       "epoch": 3.3333333333333335,
-      "grad_norm": 0.4516322910785675,
+      "grad_norm": 0.2492317408323288,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.1103,
+      "loss": 0.0441,
       "step": 50
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.6485121846199036,
+      "grad_norm": 0.311509370803833,
       "learning_rate": 0.0,
-      "loss": 0.095,
+      "loss": 0.0321,
       "step": 60
     },
     {
       "epoch": 4.0,
       "step": 60,
       "total_flos": 1.7978141590585344e+16,
-      "train_loss": 0.40461832682291665,
-      "train_runtime": 22.5515,
-      "train_samples_per_second": 10.288,
-      "train_steps_per_second": 2.661
+      "train_loss": 0.325518798828125,
+      "train_runtime": 22.8361,
+      "train_samples_per_second": 10.159,
+      "train_steps_per_second": 2.627
     }
   ],
   "logging_steps": 10,