Training in progress, epoch 1

all_results.json

@@ -6,8 +6,8 @@
     "eval_samples_per_second": 133.146,
     "eval_steps_per_second": 4.755,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.6124683845610845,
-    "train_runtime": 94.953,
-    "train_samples_per_second": 28.151,
-    "train_steps_per_second": 0.221
+    "train_loss": 0.5679481143043155,
+    "train_runtime": 89.3275,
+    "train_samples_per_second": 29.924,
+    "train_steps_per_second": 0.235
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0289ae4b9257a93f76df8e32ccaca3578177fa56b91eb65a771e8659bddcefbf
+oid sha256:f2b73c71d08559bd375613337535ebe8841b2ed4bb8ca7f70b63c421293871bd
 size 110394865

runs/Jul20_22-02-13_fcbe542fc008/events.out.tfevents.1689891809.fcbe542fc008.53766.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:445ad6993aff6ac37915bdd58bf067ceb86388e15f528c0b381b0449f2e05682
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.6124683845610845,
-    "train_runtime": 94.953,
-    "train_samples_per_second": 28.151,
-    "train_steps_per_second": 0.221
+    "train_loss": 0.5679481143043155,
+    "train_runtime": 89.3275,
+    "train_samples_per_second": 29.924,
+    "train_steps_per_second": 0.235
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.695067264573991,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-14",
+  "best_metric": 0.7130044843049327,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-7",
   "epoch": 3.0,
   "global_step": 21,
   "is_hyper_param_search": false,
@@ -9,51 +9,51 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6816143497757847,
-      "eval_loss": 0.5914890766143799,
-      "eval_runtime": 1.5735,
-      "eval_samples_per_second": 141.721,
-      "eval_steps_per_second": 4.449,
+      "eval_accuracy": 0.7130044843049327,
+      "eval_loss": 0.5689142346382141,
+      "eval_runtime": 1.5837,
+      "eval_samples_per_second": 140.806,
+      "eval_steps_per_second": 4.42,
       "step": 7
     },
     {
       "epoch": 1.43,
       "learning_rate": 3.055555555555556e-05,
-      "loss": 0.624,
+      "loss": 0.5875,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.695067264573991,
-      "eval_loss": 0.5945063829421997,
-      "eval_runtime": 1.8965,
-      "eval_samples_per_second": 117.586,
-      "eval_steps_per_second": 3.691,
+      "eval_accuracy": 0.7040358744394619,
+      "eval_loss": 0.573447048664093,
+      "eval_runtime": 1.6172,
+      "eval_samples_per_second": 137.891,
+      "eval_steps_per_second": 4.328,
       "step": 14
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.777777777777778e-06,
-      "loss": 0.6021,
+      "loss": 0.5513,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.695067264573991,
-      "eval_loss": 0.593137800693512,
-      "eval_runtime": 1.593,
-      "eval_samples_per_second": 139.987,
-      "eval_steps_per_second": 4.394,
+      "eval_accuracy": 0.7130044843049327,
+      "eval_loss": 0.5776330232620239,
+      "eval_runtime": 1.5834,
+      "eval_samples_per_second": 140.837,
+      "eval_steps_per_second": 4.421,
       "step": 21
     },
     {
       "epoch": 3.0,
       "step": 21,
       "total_flos": 6.644005855919309e+16,
-      "train_loss": 0.6124683845610845,
-      "train_runtime": 94.953,
-      "train_samples_per_second": 28.151,
-      "train_steps_per_second": 0.221
+      "train_loss": 0.5679481143043155,
+      "train_runtime": 89.3275,
+      "train_samples_per_second": 29.924,
+      "train_steps_per_second": 0.235
     }
   ],
   "max_steps": 21,