Training in progress, epoch 1

all_results.json

@@ -6,8 +6,8 @@
     "eval_samples_per_second": 137.834,
     "eval_steps_per_second": 4.923,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.6444190172922044,
-    "train_runtime": 83.0427,
-    "train_samples_per_second": 32.188,
+    "train_loss": 0.6146171859332493,
+    "train_runtime": 82.9798,
+    "train_samples_per_second": 32.213,
     "train_steps_per_second": 0.253
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5093e398c4d95af29205d98775d025a050547787fc302293a8ccb00cc74665e
+oid sha256:2ed6e1856bf3a1b80beb15c0861ee4fb540ac250d46cc735e2af5abf79c8c864
 size 110394865

runs/Jul24_15-46-48_52196fe4459f/events.out.tfevents.1690214498.52196fe4459f.604.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75b305748a7aee08138f3f192495bfabc133723265f7e1e32acfe85b5d3f1325
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.6444190172922044,
-    "train_runtime": 83.0427,
-    "train_samples_per_second": 32.188,
+    "train_loss": 0.6146171859332493,
+    "train_runtime": 82.9798,
+    "train_samples_per_second": 32.213,
     "train_steps_per_second": 0.253
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.600896860986547,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-14",
+  "best_metric": 0.6502242152466368,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-21",
   "epoch": 3.0,
   "global_step": 21,
   "is_hyper_param_search": false,
@@ -9,50 +9,50 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5964125560538116,
-      "eval_loss": 0.6616274118423462,
-      "eval_runtime": 1.4322,
-      "eval_samples_per_second": 155.707,
-      "eval_steps_per_second": 4.888,
+      "eval_accuracy": 0.6457399103139013,
+      "eval_loss": 0.6395749449729919,
+      "eval_runtime": 1.7175,
+      "eval_samples_per_second": 129.841,
+      "eval_steps_per_second": 4.076,
       "step": 7
     },
     {
       "epoch": 1.43,
       "learning_rate": 3.055555555555556e-05,
-      "loss": 0.6535,
+      "loss": 0.6256,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.600896860986547,
-      "eval_loss": 0.6611329913139343,
-      "eval_runtime": 1.4515,
-      "eval_samples_per_second": 153.629,
-      "eval_steps_per_second": 4.822,
+      "eval_accuracy": 0.6233183856502242,
+      "eval_loss": 0.6410998702049255,
+      "eval_runtime": 1.6676,
+      "eval_samples_per_second": 133.727,
+      "eval_steps_per_second": 4.198,
       "step": 14
     },
     {
       "epoch": 2.86,
       "learning_rate": 2.777777777777778e-06,
-      "loss": 0.6391,
+      "loss": 0.6027,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5829596412556054,
-      "eval_loss": 0.6599965691566467,
-      "eval_runtime": 1.4491,
-      "eval_samples_per_second": 153.891,
-      "eval_steps_per_second": 4.831,
+      "eval_accuracy": 0.6502242152466368,
+      "eval_loss": 0.6337841153144836,
+      "eval_runtime": 1.4535,
+      "eval_samples_per_second": 153.421,
+      "eval_steps_per_second": 4.816,
       "step": 21
     },
     {
       "epoch": 3.0,
       "step": 21,
       "total_flos": 6.644005855919309e+16,
-      "train_loss": 0.6444190172922044,
-      "train_runtime": 83.0427,
-      "train_samples_per_second": 32.188,
+      "train_loss": 0.6146171859332493,
+      "train_runtime": 82.9798,
+      "train_samples_per_second": 32.213,
       "train_steps_per_second": 0.253
     }
   ],