End of training

all_results.json

@@ -2,11 +2,11 @@
     "epoch": 5.0,
     "eval_accuracy": 0.9849624060150376,
     "eval_loss": 0.08750259131193161,
-    "eval_runtime": 2.5575,
-    "eval_samples_per_second": 52.005,
-    "eval_steps_per_second": 6.647,
+    "eval_runtime": 1.3924,
+    "eval_samples_per_second": 95.515,
+    "eval_steps_per_second": 12.209,
     "train_loss": 0.0,
-    "train_runtime": 0.6833,
-    "train_samples_per_second": 7566.428,
-    "train_steps_per_second": 951.292
+    "train_runtime": 0.0668,
+    "train_samples_per_second": 77408.059,
+    "train_steps_per_second": 9732.154
 }

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": "4.28.0.dev0"

eval_results.json

@@ -2,7 +2,7 @@
     "epoch": 5.0,
     "eval_accuracy": 0.9849624060150376,
     "eval_loss": 0.08750259131193161,
-    "eval_runtime": 2.5575,
-    "eval_samples_per_second": 52.005,
-    "eval_steps_per_second": 6.647
+    "eval_runtime": 1.3924,
+    "eval_samples_per_second": 95.515,
+    "eval_steps_per_second": 12.209
 }

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 5.0,
     "train_loss": 0.0,
-    "train_runtime": 0.6833,
-    "train_samples_per_second": 7566.428,
-    "train_steps_per_second": 951.292
+    "train_runtime": 0.0668,
+    "train_samples_per_second": 77408.059,
+    "train_steps_per_second": 9732.154
 }

trainer_state.json

@@ -447,9 +447,9 @@
       "step": 650,
       "total_flos": 4.006371770595533e+17,
       "train_loss": 0.0,
-      "train_runtime": 0.6833,
-      "train_samples_per_second": 7566.428,
-      "train_steps_per_second": 951.292
+      "train_runtime": 0.0668,
+      "train_samples_per_second": 77408.059,
+      "train_steps_per_second": 9732.154
     }
   ],
   "max_steps": 650,