End of training

all_results.json

@@ -2,11 +2,11 @@
     "epoch": 5.0,
     "eval_accuracy": 0.9924812030075187,
     "eval_loss": 0.08177243918180466,
-    "eval_runtime": 1.4306,
-    "eval_samples_per_second": 92.97,
-    "eval_steps_per_second": 11.883,
-    "train_loss": 0.23425721443616426,
-    "train_runtime": 139.5741,
-    "train_samples_per_second": 37.041,
-    "train_steps_per_second": 4.657
+    "eval_runtime": 3.0586,
+    "eval_samples_per_second": 43.484,
+    "eval_steps_per_second": 5.558,
+    "train_loss": 0.0,
+    "train_runtime": 0.7072,
+    "train_samples_per_second": 7310.944,
+    "train_steps_per_second": 919.171
 }

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": "4.29.0.dev0"

eval_results.json

@@ -2,7 +2,7 @@
     "epoch": 5.0,
     "eval_accuracy": 0.9924812030075187,
     "eval_loss": 0.08177243918180466,
-    "eval_runtime": 1.4306,
-    "eval_samples_per_second": 92.97,
-    "eval_steps_per_second": 11.883
+    "eval_runtime": 3.0586,
+    "eval_samples_per_second": 43.484,
+    "eval_steps_per_second": 5.558
 }

runs/May05_10-30-24_idea-Precision-5820-Tower/events.out.tfevents.1683253868.idea-Precision-5820-Tower.87221.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f47a46d6b0ccfa63f251b6afb652f93bdd6074f986fda61a71e42ffb9d5df35
+size 411

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 5.0,
-    "train_loss": 0.23425721443616426,
-    "train_runtime": 139.5741,
-    "train_samples_per_second": 37.041,
-    "train_steps_per_second": 4.657
+    "train_loss": 0.0,
+    "train_runtime": 0.7072,
+    "train_samples_per_second": 7310.944,
+    "train_steps_per_second": 919.171
 }

trainer_state.json

@@ -446,10 +446,10 @@
       "epoch": 5.0,
       "step": 650,
       "total_flos": 4.006371770595533e+17,
-      "train_loss": 0.23425721443616426,
-      "train_runtime": 139.5741,
-      "train_samples_per_second": 37.041,
-      "train_steps_per_second": 4.657
+      "train_loss": 0.0,
+      "train_runtime": 0.7072,
+      "train_samples_per_second": 7310.944,
+      "train_steps_per_second": 919.171
     }
   ],
   "max_steps": 650,