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": 0.6436980593772161,
-    "train_runtime": 88.5395,
-    "train_samples_per_second": 30.19,
-    "train_steps_per_second": 0.237
+    "train_loss": 0.6271869596980867,
+    "train_runtime": 88.238,
+    "train_samples_per_second": 30.293,
+    "train_steps_per_second": 0.238
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f9f2af55cf6d79c53e4f56939600f7cde6664b6e0ce04a3884226c9d241475d
+oid sha256:775fbed217e031e3a8e4bdee153a4fdc61ce066369a1e4fdd8f7122f387f6879
 size 110394865

runs/Jul20_20-47-08_fcbe542fc008/events.out.tfevents.1689887103.fcbe542fc008.344.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54eb90d87a39cbf174d25cd7ab1bd27c63df3a915784d9d22413a20dc85a78f1
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.6436980593772161,
-    "train_runtime": 88.5395,
-    "train_samples_per_second": 30.19,
-    "train_steps_per_second": 0.237
+    "train_loss": 0.6271869596980867,
+    "train_runtime": 88.238,
+    "train_samples_per_second": 30.293,
+    "train_steps_per_second": 0.238
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5964125560538116,
+  "best_metric": 0.6547085201793722,
   "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": 0.5964125560538116,
-      "eval_loss": 0.6732161045074463,
-      "eval_runtime": 1.4803,
-      "eval_samples_per_second": 150.647,
-      "eval_steps_per_second": 4.729,
+      "eval_accuracy": 0.6547085201793722,
+      "eval_loss": 0.6397882699966431,
+      "eval_runtime": 1.501,
+      "eval_samples_per_second": 148.564,
+      "eval_steps_per_second": 4.663,
       "step": 7
     },
     {
       "epoch": 1.43,
       "learning_rate": 3.055555555555556e-05,
-      "loss": 0.658,
+      "loss": 0.6431,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5874439461883408,
-      "eval_loss": 0.6781052947044373,
-      "eval_runtime": 1.4909,
-      "eval_samples_per_second": 149.572,
-      "eval_steps_per_second": 4.695,
+      "eval_accuracy": 0.6367713004484304,
+      "eval_loss": 0.6460248827934265,
+      "eval_runtime": 1.5012,
+      "eval_samples_per_second": 148.551,
+      "eval_steps_per_second": 4.663,
       "step": 14
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.777777777777778e-06,
-      "loss": 0.6276,
+      "loss": 0.6143,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.57847533632287,
-      "eval_loss": 0.6808013916015625,
-      "eval_runtime": 1.5079,
-      "eval_samples_per_second": 147.89,
-      "eval_steps_per_second": 4.642,
+      "eval_accuracy": 0.6233183856502242,
+      "eval_loss": 0.644560694694519,
+      "eval_runtime": 1.5227,
+      "eval_samples_per_second": 146.446,
+      "eval_steps_per_second": 4.597,
       "step": 21
     },
     {
       "epoch": 3.0,
       "step": 21,
       "total_flos": 6.644005855919309e+16,
-      "train_loss": 0.6436980593772161,
-      "train_runtime": 88.5395,
-      "train_samples_per_second": 30.19,
-      "train_steps_per_second": 0.237
+      "train_loss": 0.6271869596980867,
+      "train_runtime": 88.238,
+      "train_samples_per_second": 30.293,
+      "train_steps_per_second": 0.238
     }
   ],
   "max_steps": 21,