Training in progress, epoch 1

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.6785714285714286,
-    "eval_loss": 0.6288004517555237,
-    "eval_runtime": 0.9772,
-    "eval_samples_per_second": 114.611,
-    "eval_steps_per_second": 4.093,
-    "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.444974768729437,
-    "train_runtime": 90.986,
-    "train_samples_per_second": 29.378,
-    "train_steps_per_second": 0.231
+    "eval_accuracy": 0.7657657657657657,
+    "eval_loss": 0.4793723225593567,
+    "eval_runtime": 1.6099,
+    "eval_samples_per_second": 137.894,
+    "eval_steps_per_second": 4.348,
+    "total_flos": 6.651462652615066e+16,
+    "train_loss": 0.42075500176066444,
+    "train_runtime": 87.6563,
+    "train_samples_per_second": 30.528,
+    "train_steps_per_second": 0.24
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.6785714285714286,
-    "eval_loss": 0.6288004517555237,
-    "eval_runtime": 0.9772,
-    "eval_samples_per_second": 114.611,
-    "eval_steps_per_second": 4.093
+    "eval_accuracy": 0.7657657657657657,
+    "eval_loss": 0.4793723225593567,
+    "eval_runtime": 1.6099,
+    "eval_samples_per_second": 137.894,
+    "eval_steps_per_second": 4.348
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80d29bf5f83bc585b4e454a2d6113d48fb54e87920cb8cb11294bdd49b0a703a
+oid sha256:ed1934d42fef32764532269a1d9213b39cef86555a103faecb10b276a0bbc107
 size 110394865

runs/Jul20_20-47-08_fcbe542fc008/events.out.tfevents.1689889566.fcbe542fc008.344.24

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34cd72226ac074b888991a9a71596605f4eb24a871c141dc003d032ff192d285
+size 405

runs/Jul20_20-47-08_fcbe542fc008/events.out.tfevents.1689889911.fcbe542fc008.344.25

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:833f5923eb52de97bbb27fc73bc24e16ae866f69d53dc726eaf5b039eebd8061
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.444974768729437,
-    "train_runtime": 90.986,
-    "train_samples_per_second": 29.378,
-    "train_steps_per_second": 0.231
+    "total_flos": 6.651462652615066e+16,
+    "train_loss": 0.42075500176066444,
+    "train_runtime": 87.6563,
+    "train_samples_per_second": 30.528,
+    "train_steps_per_second": 0.24
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8699551569506726,
+  "best_metric": 0.7657657657657657,
   "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-7",
   "epoch": 3.0,
   "global_step": 21,
@@ -9,56 +9,56 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.8699551569506726,
-      "eval_loss": 0.3753786087036133,
-      "eval_runtime": 1.6113,
-      "eval_samples_per_second": 138.397,
-      "eval_steps_per_second": 4.344,
+      "eval_accuracy": 0.7657657657657657,
+      "eval_loss": 0.4793723225593567,
+      "eval_runtime": 1.6515,
+      "eval_samples_per_second": 134.422,
+      "eval_steps_per_second": 4.239,
       "step": 7
     },
     {
       "epoch": 1.43,
       "learning_rate": 3.055555555555556e-05,
-      "loss": 0.4064,
+      "loss": 0.392,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8654708520179372,
-      "eval_loss": 0.3956727981567383,
-      "eval_runtime": 1.8829,
-      "eval_samples_per_second": 118.435,
-      "eval_steps_per_second": 3.718,
+      "eval_accuracy": 0.7657657657657657,
+      "eval_loss": 0.5003733038902283,
+      "eval_runtime": 1.8598,
+      "eval_samples_per_second": 119.367,
+      "eval_steps_per_second": 3.764,
       "step": 14
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.777777777777778e-06,
-      "loss": 0.482,
+      "loss": 0.4452,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8565022421524664,
-      "eval_loss": 0.39934080839157104,
-      "eval_runtime": 1.5733,
-      "eval_samples_per_second": 141.738,
-      "eval_steps_per_second": 4.449,
+      "eval_accuracy": 0.7612612612612613,
+      "eval_loss": 0.4964040219783783,
+      "eval_runtime": 1.8628,
+      "eval_samples_per_second": 119.173,
+      "eval_steps_per_second": 3.758,
       "step": 21
     },
     {
       "epoch": 3.0,
       "step": 21,
-      "total_flos": 6.644005855919309e+16,
-      "train_loss": 0.444974768729437,
-      "train_runtime": 90.986,
-      "train_samples_per_second": 29.378,
-      "train_steps_per_second": 0.231
+      "total_flos": 6.651462652615066e+16,
+      "train_loss": 0.42075500176066444,
+      "train_runtime": 87.6563,
+      "train_samples_per_second": 30.528,
+      "train_steps_per_second": 0.24
     }
   ],
   "max_steps": 21,
   "num_train_epochs": 3,
-  "total_flos": 6.644005855919309e+16,
+  "total_flos": 6.651462652615066e+16,
   "trial_name": null,
   "trial_params": null
 }