Training in progress, epoch 1

all_results.json

@@ -6,8 +6,8 @@
     "eval_samples_per_second": 113.112,
     "eval_steps_per_second": 4.04,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.6073386215028309,
-    "train_runtime": 84.4749,
-    "train_samples_per_second": 31.643,
-    "train_steps_per_second": 0.249
+    "train_loss": 0.593576119059608,
+    "train_runtime": 88.2477,
+    "train_samples_per_second": 30.29,
+    "train_steps_per_second": 0.238
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad0d49d1fef91c1b3886dbe17211bf9054e384e51139e185fac0c3e89540d241
+oid sha256:e03f81102839b9d02e837830ee34ca481587f6bd61da75dede719914a0e861b1
 size 110394865

runs/Jul20_20-47-08_fcbe542fc008/events.out.tfevents.1689887330.fcbe542fc008.344.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3e2f7d0e88d5f7ccac4c72e6eccbd066a45e3c1ab323ca44106b76a5ab85544
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.6073386215028309,
-    "train_runtime": 84.4749,
-    "train_samples_per_second": 31.643,
-    "train_steps_per_second": 0.249
+    "train_loss": 0.593576119059608,
+    "train_runtime": 88.2477,
+    "train_samples_per_second": 30.29,
+    "train_steps_per_second": 0.238
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6547085201793722,
+  "best_metric": 0.7399103139013453,
   "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-7",
   "epoch": 3.0,
   "global_step": 21,
@@ -9,51 +9,51 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6547085201793722,
-      "eval_loss": 0.632817268371582,
-      "eval_runtime": 1.8167,
-      "eval_samples_per_second": 122.748,
-      "eval_steps_per_second": 3.853,
+      "eval_accuracy": 0.7399103139013453,
+      "eval_loss": 0.581782877445221,
+      "eval_runtime": 1.5173,
+      "eval_samples_per_second": 146.97,
+      "eval_steps_per_second": 4.613,
       "step": 7
     },
     {
       "epoch": 1.43,
       "learning_rate": 3.055555555555556e-05,
-      "loss": 0.6276,
+      "loss": 0.6105,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6412556053811659,
-      "eval_loss": 0.6409080028533936,
-      "eval_runtime": 1.6278,
-      "eval_samples_per_second": 136.991,
-      "eval_steps_per_second": 4.3,
+      "eval_accuracy": 0.7130044843049327,
+      "eval_loss": 0.5899503827095032,
+      "eval_runtime": 1.5152,
+      "eval_samples_per_second": 147.178,
+      "eval_steps_per_second": 4.62,
       "step": 14
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.777777777777778e-06,
-      "loss": 0.5891,
+      "loss": 0.5782,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6547085201793722,
-      "eval_loss": 0.6350741982460022,
-      "eval_runtime": 1.5827,
-      "eval_samples_per_second": 140.9,
-      "eval_steps_per_second": 4.423,
+      "eval_accuracy": 0.7174887892376681,
+      "eval_loss": 0.5907282829284668,
+      "eval_runtime": 1.5147,
+      "eval_samples_per_second": 147.227,
+      "eval_steps_per_second": 4.621,
       "step": 21
     },
     {
       "epoch": 3.0,
       "step": 21,
       "total_flos": 6.644005855919309e+16,
-      "train_loss": 0.6073386215028309,
-      "train_runtime": 84.4749,
-      "train_samples_per_second": 31.643,
-      "train_steps_per_second": 0.249
+      "train_loss": 0.593576119059608,
+      "train_runtime": 88.2477,
+      "train_samples_per_second": 30.29,
+      "train_steps_per_second": 0.238
     }
   ],
   "max_steps": 21,