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": 0.5679481143043155,
-    "train_runtime": 89.3275,
-    "train_samples_per_second": 29.924,
-    "train_steps_per_second": 0.235
+    "train_loss": 0.5569707949956259,
+    "train_runtime": 91.4341,
+    "train_samples_per_second": 29.234,
+    "train_steps_per_second": 0.23
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:754ec00aa6f1b85f9d23b272bc8f12e2bb7a49052838917be3ee2ac8cab1d38a
+oid sha256:602cc26f4b943cadc2805491051e71289e896178164e178c55656b8e4fcddfe2
 size 110394865

runs/Jul20_22-02-13_fcbe542fc008/events.out.tfevents.1689891923.fcbe542fc008.53766.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac06107c411531834cba55c2db20431c2da30479af145e3636e5322b329dedb5
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.5679481143043155,
-    "train_runtime": 89.3275,
-    "train_samples_per_second": 29.924,
-    "train_steps_per_second": 0.235
+    "train_loss": 0.5569707949956259,
+    "train_runtime": 91.4341,
+    "train_samples_per_second": 29.234,
+    "train_steps_per_second": 0.23
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.7130044843049327,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-7",
+  "best_metric": 0.7040358744394619,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-21",
   "epoch": 3.0,
   "global_step": 21,
   "is_hyper_param_search": false,
@@ -9,51 +9,51 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7130044843049327,
-      "eval_loss": 0.5689142346382141,
-      "eval_runtime": 1.5837,
-      "eval_samples_per_second": 140.806,
-      "eval_steps_per_second": 4.42,
+      "eval_accuracy": 0.6905829596412556,
+      "eval_loss": 0.5837827920913696,
+      "eval_runtime": 1.9252,
+      "eval_samples_per_second": 115.834,
+      "eval_steps_per_second": 3.636,
       "step": 7
     },
     {
       "epoch": 1.43,
       "learning_rate": 3.055555555555556e-05,
-      "loss": 0.5875,
+      "loss": 0.5697,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7040358744394619,
-      "eval_loss": 0.573447048664093,
-      "eval_runtime": 1.6172,
-      "eval_samples_per_second": 137.891,
-      "eval_steps_per_second": 4.328,
+      "eval_accuracy": 0.6995515695067265,
+      "eval_loss": 0.5890427827835083,
+      "eval_runtime": 1.9229,
+      "eval_samples_per_second": 115.97,
+      "eval_steps_per_second": 3.64,
       "step": 14
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.777777777777778e-06,
-      "loss": 0.5513,
+      "loss": 0.5435,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.7130044843049327,
-      "eval_loss": 0.5776330232620239,
-      "eval_runtime": 1.5834,
-      "eval_samples_per_second": 140.837,
-      "eval_steps_per_second": 4.421,
+      "eval_accuracy": 0.7040358744394619,
+      "eval_loss": 0.5816174149513245,
+      "eval_runtime": 1.8962,
+      "eval_samples_per_second": 117.607,
+      "eval_steps_per_second": 3.692,
       "step": 21
     },
     {
       "epoch": 3.0,
       "step": 21,
       "total_flos": 6.644005855919309e+16,
-      "train_loss": 0.5679481143043155,
-      "train_runtime": 89.3275,
-      "train_samples_per_second": 29.924,
-      "train_steps_per_second": 0.235
+      "train_loss": 0.5569707949956259,
+      "train_runtime": 91.4341,
+      "train_samples_per_second": 29.234,
+      "train_steps_per_second": 0.23
     }
   ],
   "max_steps": 21,