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": 0.5569707949956259,
-    "train_runtime": 91.4341,
-    "train_samples_per_second": 29.234,
-    "train_steps_per_second": 0.23
+    "train_loss": 0.5345479193187895,
+    "train_runtime": 87.5066,
+    "train_samples_per_second": 30.546,
+    "train_steps_per_second": 0.24
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:602cc26f4b943cadc2805491051e71289e896178164e178c55656b8e4fcddfe2
+oid sha256:7a3990e6718ef05ea50c4dd3ca9d0f528140bdf539b033327a23513a12eaa475
 size 110394865

runs/Jul20_22-02-13_fcbe542fc008/events.out.tfevents.1689892033.fcbe542fc008.53766.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a0c6947591bf73d2d3661b49e3f69003b87bf9357196edc71d65cdd74ad2e5b
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.5569707949956259,
-    "train_runtime": 91.4341,
-    "train_samples_per_second": 29.234,
-    "train_steps_per_second": 0.23
+    "train_loss": 0.5345479193187895,
+    "train_runtime": 87.5066,
+    "train_samples_per_second": 30.546,
+    "train_steps_per_second": 0.24
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.7040358744394619,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-21",
+  "best_metric": 0.7982062780269058,
+  "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": 0.6905829596412556,
-      "eval_loss": 0.5837827920913696,
-      "eval_runtime": 1.9252,
-      "eval_samples_per_second": 115.834,
-      "eval_steps_per_second": 3.636,
+      "eval_accuracy": 0.7982062780269058,
+      "eval_loss": 0.49021604657173157,
+      "eval_runtime": 1.6014,
+      "eval_samples_per_second": 139.251,
+      "eval_steps_per_second": 4.371,
       "step": 7
     },
     {
       "epoch": 1.43,
       "learning_rate": 3.055555555555556e-05,
-      "loss": 0.5697,
+      "loss": 0.5414,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6995515695067265,
-      "eval_loss": 0.5890427827835083,
-      "eval_runtime": 1.9229,
-      "eval_samples_per_second": 115.97,
-      "eval_steps_per_second": 3.64,
+      "eval_accuracy": 0.7713004484304933,
+      "eval_loss": 0.49885380268096924,
+      "eval_runtime": 1.6196,
+      "eval_samples_per_second": 137.684,
+      "eval_steps_per_second": 4.322,
       "step": 14
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.777777777777778e-06,
-      "loss": 0.5435,
+      "loss": 0.5271,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.7040358744394619,
-      "eval_loss": 0.5816174149513245,
-      "eval_runtime": 1.8962,
-      "eval_samples_per_second": 117.607,
-      "eval_steps_per_second": 3.692,
+      "eval_accuracy": 0.7847533632286996,
+      "eval_loss": 0.50569748878479,
+      "eval_runtime": 1.5885,
+      "eval_samples_per_second": 140.385,
+      "eval_steps_per_second": 4.407,
       "step": 21
     },
     {
       "epoch": 3.0,
       "step": 21,
       "total_flos": 6.644005855919309e+16,
-      "train_loss": 0.5569707949956259,
-      "train_runtime": 91.4341,
-      "train_samples_per_second": 29.234,
-      "train_steps_per_second": 0.23
+      "train_loss": 0.5345479193187895,
+      "train_runtime": 87.5066,
+      "train_samples_per_second": 30.546,
+      "train_steps_per_second": 0.24
     }
   ],
   "max_steps": 21,