End of training

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 5.0,
     "eval_accuracy": 0.9924812030075187,
-    "eval_loss": 0.08177243918180466,
-    "eval_runtime": 3.0586,
-    "eval_samples_per_second": 43.484,
-    "eval_steps_per_second": 5.558,
+    "eval_loss": 0.08411169797182083,
+    "eval_runtime": 9.1617,
+    "eval_samples_per_second": 14.517,
+    "eval_steps_per_second": 1.856,
     "train_loss": 0.0,
-    "train_runtime": 0.7072,
-    "train_samples_per_second": 7310.944,
-    "train_steps_per_second": 919.171
+    "train_runtime": 83.963,
+    "train_samples_per_second": 61.575,
+    "train_steps_per_second": 7.742
 }

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": "4.28.1"

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "eval_accuracy": 0.9924812030075187,
-    "eval_loss": 0.08177243918180466,
-    "eval_runtime": 3.0586,
-    "eval_samples_per_second": 43.484,
-    "eval_steps_per_second": 5.558
+    "eval_loss": 0.08411169797182083,
+    "eval_runtime": 9.1617,
+    "eval_samples_per_second": 14.517,
+    "eval_steps_per_second": 1.856
 }

runs/May06_09-21-21_idea-Precision-5820-Tower/events.out.tfevents.1683336227.idea-Precision-5820-Tower.30654.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3149d9a2c74f4f8f06b2a219b27d4a89dd96f611c9939f0b9e4de42031b12ac6
+size 411

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 5.0,
     "train_loss": 0.0,
-    "train_runtime": 0.7072,
-    "train_samples_per_second": 7310.944,
-    "train_steps_per_second": 919.171
+    "train_runtime": 83.963,
+    "train_samples_per_second": 61.575,
+    "train_steps_per_second": 7.742
 }

trainer_state.json

@@ -447,9 +447,9 @@
       "step": 650,
       "total_flos": 4.006371770595533e+17,
       "train_loss": 0.0,
-      "train_runtime": 0.7072,
-      "train_samples_per_second": 7310.944,
-      "train_steps_per_second": 919.171
+      "train_runtime": 83.963,
+      "train_samples_per_second": 61.575,
+      "train_steps_per_second": 7.742
     }
   ],
   "max_steps": 650,