End of training

all_results.json

@@ -2,11 +2,11 @@
     "epoch": 5.0,
     "eval_accuracy": 0.9699248120300752,
     "eval_loss": 0.13279759883880615,
-    "eval_runtime": 9.4426,
-    "eval_samples_per_second": 14.085,
-    "eval_steps_per_second": 0.953,
+    "eval_runtime": 9.6147,
+    "eval_samples_per_second": 13.833,
+    "eval_steps_per_second": 0.936,
     "train_loss": 0.0,
-    "train_runtime": 0.2729,
-    "train_samples_per_second": 18946.465,
-    "train_steps_per_second": 1191.025
+    "train_runtime": 0.3337,
+    "train_samples_per_second": 15491.466,
+    "train_steps_per_second": 973.835
 }

config.json

@@ -28,6 +28,7 @@
   "num_channels": 3,
   "num_hidden_layers": 12,
   "patch_size": 16,
+  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
   "transformers_version": "4.26.0.dev0"

eval_results.json

@@ -2,7 +2,7 @@
     "epoch": 5.0,
     "eval_accuracy": 0.9699248120300752,
     "eval_loss": 0.13279759883880615,
-    "eval_runtime": 9.4426,
-    "eval_samples_per_second": 14.085,
-    "eval_steps_per_second": 0.953
+    "eval_runtime": 9.6147,
+    "eval_samples_per_second": 13.833,
+    "eval_steps_per_second": 0.936
 }

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 5.0,
     "train_loss": 0.0,
-    "train_runtime": 0.2729,
-    "train_samples_per_second": 18946.465,
-    "train_steps_per_second": 1191.025
+    "train_runtime": 0.3337,
+    "train_samples_per_second": 15491.466,
+    "train_steps_per_second": 973.835
 }

trainer_state.json

@@ -249,9 +249,9 @@
       "step": 325,
       "total_flos": 4.006371770595533e+17,
       "train_loss": 0.0,
-      "train_runtime": 0.2729,
-      "train_samples_per_second": 18946.465,
-      "train_steps_per_second": 1191.025
+      "train_runtime": 0.3337,
+      "train_samples_per_second": 15491.466,
+      "train_steps_per_second": 973.835
     }
   ],
   "max_steps": 325,