Training in progress, epoch 1

all_results.json

@@ -6,8 +6,8 @@
     "eval_samples_per_second": 137.834,
     "eval_steps_per_second": 4.923,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.656469912756057,
-    "train_runtime": 80.0135,
-    "train_samples_per_second": 33.407,
-    "train_steps_per_second": 0.262
+    "train_loss": 0.6444190172922044,
+    "train_runtime": 83.0427,
+    "train_samples_per_second": 32.188,
+    "train_steps_per_second": 0.253
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61b915e87e39e94cf302a4bc041fdb85ee62323bdb35465b5157995e8175aa56
+oid sha256:c23a576d321a364ccf219ca0d6114085ad29d3a8fd44017a711352982c0ecc7a
 size 110394865

runs/Jul24_15-46-48_52196fe4459f/events.out.tfevents.1690214396.52196fe4459f.604.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72d2094112b62ff09cc8998897627fc534ae5867cbf385e12abaf16a2739e315
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.656469912756057,
-    "train_runtime": 80.0135,
-    "train_samples_per_second": 33.407,
-    "train_steps_per_second": 0.262
+    "train_loss": 0.6444190172922044,
+    "train_runtime": 83.0427,
+    "train_samples_per_second": 32.188,
+    "train_steps_per_second": 0.253
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.6278026905829597,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-7",
+  "best_metric": 0.600896860986547,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-14",
   "epoch": 3.0,
   "global_step": 21,
   "is_hyper_param_search": false,
@@ -9,51 +9,51 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6278026905829597,
-      "eval_loss": 0.6555958390235901,
-      "eval_runtime": 1.5748,
-      "eval_samples_per_second": 141.601,
-      "eval_steps_per_second": 4.445,
+      "eval_accuracy": 0.5964125560538116,
+      "eval_loss": 0.6616274118423462,
+      "eval_runtime": 1.4322,
+      "eval_samples_per_second": 155.707,
+      "eval_steps_per_second": 4.888,
       "step": 7
     },
     {
       "epoch": 1.43,
       "learning_rate": 3.055555555555556e-05,
-      "loss": 0.6679,
+      "loss": 0.6535,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5739910313901345,
-      "eval_loss": 0.6656145453453064,
-      "eval_runtime": 1.5156,
-      "eval_samples_per_second": 147.134,
-      "eval_steps_per_second": 4.619,
+      "eval_accuracy": 0.600896860986547,
+      "eval_loss": 0.6611329913139343,
+      "eval_runtime": 1.4515,
+      "eval_samples_per_second": 153.629,
+      "eval_steps_per_second": 4.822,
       "step": 14
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.777777777777778e-06,
-      "loss": 0.6482,
+      "loss": 0.6391,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5695067264573991,
-      "eval_loss": 0.6624228954315186,
-      "eval_runtime": 1.4959,
-      "eval_samples_per_second": 149.073,
-      "eval_steps_per_second": 4.679,
+      "eval_accuracy": 0.5829596412556054,
+      "eval_loss": 0.6599965691566467,
+      "eval_runtime": 1.4491,
+      "eval_samples_per_second": 153.891,
+      "eval_steps_per_second": 4.831,
       "step": 21
     },
     {
       "epoch": 3.0,
       "step": 21,
       "total_flos": 6.644005855919309e+16,
-      "train_loss": 0.656469912756057,
-      "train_runtime": 80.0135,
-      "train_samples_per_second": 33.407,
-      "train_steps_per_second": 0.262
+      "train_loss": 0.6444190172922044,
+      "train_runtime": 83.0427,
+      "train_samples_per_second": 32.188,
+      "train_steps_per_second": 0.253
     }
   ],
   "max_steps": 21,