Training in progress, epoch 1

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.6612757047017416,
-    "train_runtime": 2197.7594,
-    "train_samples_per_second": 1.216,
+    "train_loss": 0.6270546459016346,
+    "train_runtime": 2201.313,
+    "train_samples_per_second": 1.214,
     "train_steps_per_second": 0.01
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fd198b60e4e7d2757b4b4c45bb1ff1923113d7b71992ae754767bf4fcaec3f5
+oid sha256:74bc94ea4ecb29ddf0d6a97a7acf9bc6b29336aec4e48d07a32cf8df489ed4ac
 size 110391601

runs/Jul19_22-17-11_3beebab79852/events.out.tfevents.1689811891.3beebab79852.18500.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa11fa8dd3428d262d5ffd3f80d2341e7aa700c6d21875119857d46395779119
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.6612757047017416,
-    "train_runtime": 2197.7594,
-    "train_samples_per_second": 1.216,
+    "train_loss": 0.6270546459016346,
+    "train_runtime": 2201.313,
+    "train_samples_per_second": 1.214,
     "train_steps_per_second": 0.01
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.5964125560538116,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-21",
+  "best_metric": 0.6367713004484304,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-7",
   "epoch": 3.0,
   "global_step": 21,
   "is_hyper_param_search": false,
@@ -9,50 +9,50 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5919282511210763,
-      "eval_loss": 0.6753352284431458,
-      "eval_runtime": 56.0112,
-      "eval_samples_per_second": 3.981,
-      "eval_steps_per_second": 0.125,
+      "eval_accuracy": 0.6367713004484304,
+      "eval_loss": 0.6516510844230652,
+      "eval_runtime": 65.5128,
+      "eval_samples_per_second": 3.404,
+      "eval_steps_per_second": 0.107,
       "step": 7
     },
     {
       "epoch": 1.43,
       "learning_rate": 3.055555555555556e-05,
-      "loss": 0.6721,
+      "loss": 0.6406,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5919282511210763,
-      "eval_loss": 0.6616345047950745,
-      "eval_runtime": 57.7872,
-      "eval_samples_per_second": 3.859,
-      "eval_steps_per_second": 0.121,
+      "eval_accuracy": 0.6233183856502242,
+      "eval_loss": 0.6548570990562439,
+      "eval_runtime": 56.0015,
+      "eval_samples_per_second": 3.982,
+      "eval_steps_per_second": 0.125,
       "step": 14
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.777777777777778e-06,
-      "loss": 0.6522,
+      "loss": 0.6154,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5964125560538116,
-      "eval_loss": 0.6633050441741943,
-      "eval_runtime": 56.2827,
-      "eval_samples_per_second": 3.962,
-      "eval_steps_per_second": 0.124,
+      "eval_accuracy": 0.6278026905829597,
+      "eval_loss": 0.6554566621780396,
+      "eval_runtime": 61.9404,
+      "eval_samples_per_second": 3.6,
+      "eval_steps_per_second": 0.113,
       "step": 21
     },
     {
       "epoch": 3.0,
       "step": 21,
       "total_flos": 6.644005855919309e+16,
-      "train_loss": 0.6612757047017416,
-      "train_runtime": 2197.7594,
-      "train_samples_per_second": 1.216,
+      "train_loss": 0.6270546459016346,
+      "train_runtime": 2201.313,
+      "train_samples_per_second": 1.214,
       "train_steps_per_second": 0.01
     }
   ],