Training in progress, epoch 1

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.42857142857142855,
-    "eval_loss": 0.7569826245307922,
-    "eval_runtime": 0.8506,
-    "eval_samples_per_second": 131.671,
-    "eval_steps_per_second": 4.703,
+    "eval_accuracy": 0.5714285714285714,
+    "eval_loss": 0.6924265027046204,
+    "eval_runtime": 0.8412,
+    "eval_samples_per_second": 133.146,
+    "eval_steps_per_second": 4.755,
     "total_flos": 7.471710289148314e+16,
-    "train_loss": 0.6363129814465841,
-    "train_runtime": 92.001,
-    "train_samples_per_second": 32.674,
-    "train_steps_per_second": 0.261
+    "train_loss": 0.654710441827774,
+    "train_runtime": 88.8709,
+    "train_samples_per_second": 33.824,
+    "train_steps_per_second": 0.27
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.42857142857142855,
-    "eval_loss": 0.7569826245307922,
-    "eval_runtime": 0.8506,
-    "eval_samples_per_second": 131.671,
-    "eval_steps_per_second": 4.703
+    "eval_accuracy": 0.5714285714285714,
+    "eval_loss": 0.6924265027046204,
+    "eval_runtime": 0.8412,
+    "eval_samples_per_second": 133.146,
+    "eval_steps_per_second": 4.755
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efbbd76f34e542bd4d08b47634d711fba5759e29c5dbdaa1eb382d0848698017
+oid sha256:b539f2cade62369d3c4ef9422d6043aefc6005ee1b43f242ea0a42c42a9f471d
 size 110394865

runs/Jul20_22-02-13_fcbe542fc008/events.out.tfevents.1689891514.fcbe542fc008.53766.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ee7c0dc47bf206e63f774b65f765a858ed38d62d37b554d3ebd687cd6b700f5
+size 405

runs/Jul20_22-02-13_fcbe542fc008/events.out.tfevents.1689891576.fcbe542fc008.53766.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d366548a18d7d98826ee0f6486570e027b6b193d681ad4305ce94c858c9842fe
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 7.471710289148314e+16,
-    "train_loss": 0.6363129814465841,
-    "train_runtime": 92.001,
-    "train_samples_per_second": 32.674,
-    "train_steps_per_second": 0.261
+    "train_loss": 0.654710441827774,
+    "train_runtime": 88.8709,
+    "train_samples_per_second": 33.824,
+    "train_steps_per_second": 0.27
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.45535714285714285,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-8",
+  "best_metric": 0.5714285714285714,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-24",
   "epoch": 3.0,
   "global_step": 24,
   "is_hyper_param_search": false,
@@ -9,51 +9,51 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.45535714285714285,
-      "eval_loss": 0.7675586342811584,
-      "eval_runtime": 0.9181,
-      "eval_samples_per_second": 121.994,
-      "eval_steps_per_second": 4.357,
+      "eval_accuracy": 0.5535714285714286,
+      "eval_loss": 0.6885058283805847,
+      "eval_runtime": 0.7921,
+      "eval_samples_per_second": 141.395,
+      "eval_steps_per_second": 5.05,
       "step": 8
     },
     {
       "epoch": 1.25,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.6253,
+      "loss": 0.6664,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.4107142857142857,
-      "eval_loss": 0.8570971488952637,
-      "eval_runtime": 0.8041,
-      "eval_samples_per_second": 139.286,
-      "eval_steps_per_second": 4.974,
+      "eval_accuracy": 0.5357142857142857,
+      "eval_loss": 0.6903370022773743,
+      "eval_runtime": 0.9439,
+      "eval_samples_per_second": 118.655,
+      "eval_steps_per_second": 4.238,
       "step": 16
     },
     {
       "epoch": 2.5,
       "learning_rate": 9.523809523809523e-06,
-      "loss": 0.6525,
+      "loss": 0.6429,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.375,
-      "eval_loss": 0.8784260749816895,
-      "eval_runtime": 0.9474,
-      "eval_samples_per_second": 118.224,
-      "eval_steps_per_second": 4.222,
+      "eval_accuracy": 0.5714285714285714,
+      "eval_loss": 0.6924265027046204,
+      "eval_runtime": 0.8032,
+      "eval_samples_per_second": 139.443,
+      "eval_steps_per_second": 4.98,
       "step": 24
     },
     {
       "epoch": 3.0,
       "step": 24,
       "total_flos": 7.471710289148314e+16,
-      "train_loss": 0.6363129814465841,
-      "train_runtime": 92.001,
-      "train_samples_per_second": 32.674,
-      "train_steps_per_second": 0.261
+      "train_loss": 0.654710441827774,
+      "train_runtime": 88.8709,
+      "train_samples_per_second": 33.824,
+      "train_steps_per_second": 0.27
     }
   ],
   "max_steps": 24,