Training in progress, epoch 1

all_results.json

@@ -6,8 +6,8 @@
     "eval_samples_per_second": 114.611,
     "eval_steps_per_second": 4.093,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.4862130412033626,
-    "train_runtime": 82.6807,
-    "train_samples_per_second": 32.329,
-    "train_steps_per_second": 0.254
+    "train_loss": 0.46336238441013156,
+    "train_runtime": 87.0814,
+    "train_samples_per_second": 30.695,
+    "train_steps_per_second": 0.241
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:befc2ac97cf6f325af0eeea0f49e12fe14855242a36d1fc8a444c9be892d7aac
+oid sha256:607e7bd7b42f65da737e7e682964666ad34fe214c031f1ab1d111a3debe00687
 size 110394865

runs/Jul20_20-47-08_fcbe542fc008/events.out.tfevents.1689889338.fcbe542fc008.344.22

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed91d0874de94b6857d9c8e9b0c1605761fa2cd001cf47ed1046c94264e9cfa4
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.4862130412033626,
-    "train_runtime": 82.6807,
-    "train_samples_per_second": 32.329,
-    "train_steps_per_second": 0.254
+    "train_loss": 0.46336238441013156,
+    "train_runtime": 87.0814,
+    "train_samples_per_second": 30.695,
+    "train_steps_per_second": 0.241
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.7488789237668162,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-14",
+  "best_metric": 0.8071748878923767,
+  "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": 0.7443946188340808,
-      "eval_loss": 0.5228486061096191,
-      "eval_runtime": 1.6752,
-      "eval_samples_per_second": 133.12,
-      "eval_steps_per_second": 4.179,
+      "eval_accuracy": 0.7982062780269058,
+      "eval_loss": 0.48855507373809814,
+      "eval_runtime": 1.5225,
+      "eval_samples_per_second": 146.471,
+      "eval_steps_per_second": 4.598,
       "step": 7
     },
     {
       "epoch": 1.43,
       "learning_rate": 3.055555555555556e-05,
-      "loss": 0.4747,
+      "loss": 0.46,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7488789237668162,
-      "eval_loss": 0.5224886536598206,
-      "eval_runtime": 1.7714,
-      "eval_samples_per_second": 125.892,
-      "eval_steps_per_second": 3.952,
+      "eval_accuracy": 0.8026905829596412,
+      "eval_loss": 0.4880882799625397,
+      "eval_runtime": 1.5719,
+      "eval_samples_per_second": 141.862,
+      "eval_steps_per_second": 4.453,
       "step": 14
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.777777777777778e-06,
-      "loss": 0.5014,
+      "loss": 0.4674,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.726457399103139,
-      "eval_loss": 0.521872878074646,
-      "eval_runtime": 1.7911,
-      "eval_samples_per_second": 124.501,
-      "eval_steps_per_second": 3.908,
+      "eval_accuracy": 0.8071748878923767,
+      "eval_loss": 0.4813915193080902,
+      "eval_runtime": 1.5976,
+      "eval_samples_per_second": 139.581,
+      "eval_steps_per_second": 4.381,
       "step": 21
     },
     {
       "epoch": 3.0,
       "step": 21,
       "total_flos": 6.644005855919309e+16,
-      "train_loss": 0.4862130412033626,
-      "train_runtime": 82.6807,
-      "train_samples_per_second": 32.329,
-      "train_steps_per_second": 0.254
+      "train_loss": 0.46336238441013156,
+      "train_runtime": 87.0814,
+      "train_samples_per_second": 30.695,
+      "train_steps_per_second": 0.241
     }
   ],
   "max_steps": 21,