Training in progress, epoch 1

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.6838125614892869,
-    "train_runtime": 87.4764,
-    "train_samples_per_second": 30.557,
-    "train_steps_per_second": 0.24
+    "train_loss": 0.6447433744158063,
+    "train_runtime": 77.82,
+    "train_samples_per_second": 34.349,
+    "train_steps_per_second": 0.27
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4add8ca90cbe8d1bf8ebb696610beafebfd564332b2a1fa9cf4ab370dc9376d2
+oid sha256:d9d1da2b09901862550f1848ca02b086dea10429c11280cab3036410c0f28fb1
 size 110394865

runs/Jul20_17-16-20_6f22dbce37db/events.out.tfevents.1689873668.6f22dbce37db.453.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:318acc4e43dbb72e1edbab0261a3394a9ce1895af956dda7b47bd520f094c2e6
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.6838125614892869,
-    "train_runtime": 87.4764,
-    "train_samples_per_second": 30.557,
-    "train_steps_per_second": 0.24
+    "train_loss": 0.6447433744158063,
+    "train_runtime": 77.82,
+    "train_samples_per_second": 34.349,
+    "train_steps_per_second": 0.27
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5695067264573991,
+  "best_metric": 0.600896860986547,
   "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-21",
   "epoch": 3.0,
   "global_step": 21,
@@ -9,51 +9,51 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5560538116591929,
-      "eval_loss": 0.7043889760971069,
-      "eval_runtime": 1.6759,
-      "eval_samples_per_second": 133.061,
-      "eval_steps_per_second": 4.177,
+      "eval_accuracy": 0.57847533632287,
+      "eval_loss": 0.6817072629928589,
+      "eval_runtime": 1.4871,
+      "eval_samples_per_second": 149.959,
+      "eval_steps_per_second": 4.707,
       "step": 7
     },
     {
       "epoch": 1.43,
       "learning_rate": 3.055555555555556e-05,
-      "loss": 0.7016,
+      "loss": 0.6619,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5560538116591929,
-      "eval_loss": 0.7037797570228577,
-      "eval_runtime": 1.4404,
-      "eval_samples_per_second": 154.816,
-      "eval_steps_per_second": 4.86,
+      "eval_accuracy": 0.5874439461883408,
+      "eval_loss": 0.6632333397865295,
+      "eval_runtime": 1.7773,
+      "eval_samples_per_second": 125.471,
+      "eval_steps_per_second": 3.939,
       "step": 14
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.777777777777778e-06,
-      "loss": 0.6662,
+      "loss": 0.6291,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5695067264573991,
-      "eval_loss": 0.702588677406311,
-      "eval_runtime": 1.4767,
-      "eval_samples_per_second": 151.008,
-      "eval_steps_per_second": 4.74,
+      "eval_accuracy": 0.600896860986547,
+      "eval_loss": 0.6647406816482544,
+      "eval_runtime": 1.6719,
+      "eval_samples_per_second": 133.383,
+      "eval_steps_per_second": 4.187,
       "step": 21
     },
     {
       "epoch": 3.0,
       "step": 21,
       "total_flos": 6.644005855919309e+16,
-      "train_loss": 0.6838125614892869,
-      "train_runtime": 87.4764,
-      "train_samples_per_second": 30.557,
-      "train_steps_per_second": 0.24
+      "train_loss": 0.6447433744158063,
+      "train_runtime": 77.82,
+      "train_samples_per_second": 34.349,
+      "train_steps_per_second": 0.27
     }
   ],
   "max_steps": 21,