Training in progress, epoch 1

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.6186181136540004,
-    "train_runtime": 2186.2247,
-    "train_samples_per_second": 1.223,
-    "train_steps_per_second": 0.01
+    "train_loss": 0.6838125614892869,
+    "train_runtime": 87.4764,
+    "train_samples_per_second": 30.557,
+    "train_steps_per_second": 0.24
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb746949991ca327d619d81337163beee13330e5adb199a66d90f826a425341f
+oid sha256:d9220bac582a4c0e54ee02e616ae725bba1e25ad38053f76d13d93fb2eb0a1ea
 size 110394865

runs/Jul20_17-16-20_6f22dbce37db/events.out.tfevents.1689873570.6f22dbce37db.453.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de2f82f5b1799fb17c4015336c54c8955d50407361cc7fa3349fafc9f2ddc38f
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.6186181136540004,
-    "train_runtime": 2186.2247,
-    "train_samples_per_second": 1.223,
-    "train_steps_per_second": 0.01
+    "train_loss": 0.6838125614892869,
+    "train_runtime": 87.4764,
+    "train_samples_per_second": 30.557,
+    "train_steps_per_second": 0.24
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.7174887892376681,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-7",
+  "best_metric": 0.5695067264573991,
+  "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": 0.7174887892376681,
-      "eval_loss": 0.6090329885482788,
-      "eval_runtime": 55.4023,
-      "eval_samples_per_second": 4.025,
-      "eval_steps_per_second": 0.126,
+      "eval_accuracy": 0.5560538116591929,
+      "eval_loss": 0.7043889760971069,
+      "eval_runtime": 1.6759,
+      "eval_samples_per_second": 133.061,
+      "eval_steps_per_second": 4.177,
       "step": 7
     },
     {
       "epoch": 1.43,
       "learning_rate": 3.055555555555556e-05,
-      "loss": 0.6292,
+      "loss": 0.7016,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6995515695067265,
-      "eval_loss": 0.6173889636993408,
-      "eval_runtime": 55.6036,
-      "eval_samples_per_second": 4.011,
-      "eval_steps_per_second": 0.126,
+      "eval_accuracy": 0.5560538116591929,
+      "eval_loss": 0.7037797570228577,
+      "eval_runtime": 1.4404,
+      "eval_samples_per_second": 154.816,
+      "eval_steps_per_second": 4.86,
       "step": 14
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.777777777777778e-06,
-      "loss": 0.6095,
+      "loss": 0.6662,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.672645739910314,
-      "eval_loss": 0.6186679601669312,
-      "eval_runtime": 60.7124,
-      "eval_samples_per_second": 3.673,
-      "eval_steps_per_second": 0.115,
+      "eval_accuracy": 0.5695067264573991,
+      "eval_loss": 0.702588677406311,
+      "eval_runtime": 1.4767,
+      "eval_samples_per_second": 151.008,
+      "eval_steps_per_second": 4.74,
       "step": 21
     },
     {
       "epoch": 3.0,
       "step": 21,
       "total_flos": 6.644005855919309e+16,
-      "train_loss": 0.6186181136540004,
-      "train_runtime": 2186.2247,
-      "train_samples_per_second": 1.223,
-      "train_steps_per_second": 0.01
+      "train_loss": 0.6838125614892869,
+      "train_runtime": 87.4764,
+      "train_samples_per_second": 30.557,
+      "train_steps_per_second": 0.24
     }
   ],
   "max_steps": 21,