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": 0.5089511360440936,
-    "train_runtime": 89.722,
-    "train_samples_per_second": 29.792,
-    "train_steps_per_second": 0.234
+    "train_loss": 0.4862130412033626,
+    "train_runtime": 82.6807,
+    "train_samples_per_second": 32.329,
+    "train_steps_per_second": 0.254
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:614a1fc44aa249f2dcc800394500918f6ffd42be99b134fa9c799349bbc800ba
+oid sha256:68e2d93db2f7ff2997f9f520b598a798dc25aa9133109cc0063c37c7c4ac924d
 size 110394865

runs/Jul20_20-47-08_fcbe542fc008/events.out.tfevents.1689889227.fcbe542fc008.344.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96051e431bffe4e4c6d1e04c51c684d00a3f488838f7c112bcf81572ad186937
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.5089511360440936,
-    "train_runtime": 89.722,
-    "train_samples_per_second": 29.792,
-    "train_steps_per_second": 0.234
+    "train_loss": 0.4862130412033626,
+    "train_runtime": 82.6807,
+    "train_samples_per_second": 32.329,
+    "train_steps_per_second": 0.254
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.7309417040358744,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-7",
+  "best_metric": 0.7488789237668162,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-14",
   "epoch": 3.0,
   "global_step": 21,
   "is_hyper_param_search": false,
@@ -9,51 +9,51 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7309417040358744,
-      "eval_loss": 0.5390371680259705,
-      "eval_runtime": 2.0357,
-      "eval_samples_per_second": 109.545,
-      "eval_steps_per_second": 3.439,
+      "eval_accuracy": 0.7443946188340808,
+      "eval_loss": 0.5228486061096191,
+      "eval_runtime": 1.6752,
+      "eval_samples_per_second": 133.12,
+      "eval_steps_per_second": 4.179,
       "step": 7
     },
     {
       "epoch": 1.43,
       "learning_rate": 3.055555555555556e-05,
-      "loss": 0.4872,
+      "loss": 0.4747,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7040358744394619,
-      "eval_loss": 0.5610103011131287,
-      "eval_runtime": 1.5053,
-      "eval_samples_per_second": 148.139,
-      "eval_steps_per_second": 4.65,
+      "eval_accuracy": 0.7488789237668162,
+      "eval_loss": 0.5224886536598206,
+      "eval_runtime": 1.7714,
+      "eval_samples_per_second": 125.892,
+      "eval_steps_per_second": 3.952,
       "step": 14
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.777777777777778e-06,
-      "loss": 0.5271,
+      "loss": 0.5014,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.7174887892376681,
-      "eval_loss": 0.5560548901557922,
-      "eval_runtime": 1.4756,
-      "eval_samples_per_second": 151.129,
-      "eval_steps_per_second": 4.744,
+      "eval_accuracy": 0.726457399103139,
+      "eval_loss": 0.521872878074646,
+      "eval_runtime": 1.7911,
+      "eval_samples_per_second": 124.501,
+      "eval_steps_per_second": 3.908,
       "step": 21
     },
     {
       "epoch": 3.0,
       "step": 21,
       "total_flos": 6.644005855919309e+16,
-      "train_loss": 0.5089511360440936,
-      "train_runtime": 89.722,
-      "train_samples_per_second": 29.792,
-      "train_steps_per_second": 0.234
+      "train_loss": 0.4862130412033626,
+      "train_runtime": 82.6807,
+      "train_samples_per_second": 32.329,
+      "train_steps_per_second": 0.254
     }
   ],
   "max_steps": 21,