Training in progress, epoch 1

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 3.0,
-    "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": 6.644005855919309e+16,
-    "train_loss": 0.5345479193187895,
-    "train_runtime": 87.5066,
-    "train_samples_per_second": 30.546,
-    "train_steps_per_second": 0.24
+    "eval_accuracy": 0.49107142857142855,
+    "eval_loss": 0.7152572274208069,
+    "eval_runtime": 0.8126,
+    "eval_samples_per_second": 137.834,
+    "eval_steps_per_second": 4.923,
+    "total_flos": 7.471710289148314e+16,
+    "train_loss": 0.7044070760409037,
+    "train_runtime": 101.1597,
+    "train_samples_per_second": 29.715,
+    "train_steps_per_second": 0.237
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.5714285714285714,
-    "eval_loss": 0.6924265027046204,
-    "eval_runtime": 0.8412,
-    "eval_samples_per_second": 133.146,
-    "eval_steps_per_second": 4.755
+    "eval_accuracy": 0.49107142857142855,
+    "eval_loss": 0.7152572274208069,
+    "eval_runtime": 0.8126,
+    "eval_samples_per_second": 137.834,
+    "eval_steps_per_second": 4.923
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:366f04dee424389cc546120dfa3a0d79059d4b1f5fa079570f209c415961a9c3
+oid sha256:a903932b0d32682e1013a98938e515ce833c6f35a0ed8ee9f7f64c962dded96c
 size 110394865

runs/Jul24_15-46-48_52196fe4459f/events.out.tfevents.1690213775.52196fe4459f.604.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc918c94ea0c92c958b51c9d3458d22d92328b74c894649469eb1cb563beed8f
+size 405

runs/Jul24_15-46-48_52196fe4459f/events.out.tfevents.1690214084.52196fe4459f.604.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42254acdbe48389ce19849d6304d1a067d2948882c2962f90cad7b0efdc1e8c6
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.5345479193187895,
-    "train_runtime": 87.5066,
-    "train_samples_per_second": 30.546,
-    "train_steps_per_second": 0.24
+    "total_flos": 7.471710289148314e+16,
+    "train_loss": 0.7044070760409037,
+    "train_runtime": 101.1597,
+    "train_samples_per_second": 29.715,
+    "train_steps_per_second": 0.237
 }

trainer_state.json

@@ -1,64 +1,64 @@
 {
-  "best_metric": 0.7982062780269058,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-7",
+  "best_metric": 0.49107142857142855,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-16",
   "epoch": 3.0,
-  "global_step": 21,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7982062780269058,
-      "eval_loss": 0.49021604657173157,
-      "eval_runtime": 1.6014,
-      "eval_samples_per_second": 139.251,
-      "eval_steps_per_second": 4.371,
-      "step": 7
+      "eval_accuracy": 0.44642857142857145,
+      "eval_loss": 0.7373398542404175,
+      "eval_runtime": 0.7604,
+      "eval_samples_per_second": 147.293,
+      "eval_steps_per_second": 5.26,
+      "step": 8
     },
     {
-      "epoch": 1.43,
-      "learning_rate": 3.055555555555556e-05,
-      "loss": 0.5414,
+      "epoch": 1.25,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.7302,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7713004484304933,
-      "eval_loss": 0.49885380268096924,
-      "eval_runtime": 1.6196,
-      "eval_samples_per_second": 137.684,
-      "eval_steps_per_second": 4.322,
-      "step": 14
+      "eval_accuracy": 0.49107142857142855,
+      "eval_loss": 0.7152572274208069,
+      "eval_runtime": 0.7234,
+      "eval_samples_per_second": 154.816,
+      "eval_steps_per_second": 5.529,
+      "step": 16
     },
     {
-      "epoch": 2.86,
-      "learning_rate": 2.777777777777778e-06,
-      "loss": 0.5271,
+      "epoch": 2.5,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 0.6892,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.7847533632286996,
-      "eval_loss": 0.50569748878479,
-      "eval_runtime": 1.5885,
-      "eval_samples_per_second": 140.385,
-      "eval_steps_per_second": 4.407,
-      "step": 21
+      "eval_accuracy": 0.4642857142857143,
+      "eval_loss": 0.7121878266334534,
+      "eval_runtime": 0.7337,
+      "eval_samples_per_second": 152.652,
+      "eval_steps_per_second": 5.452,
+      "step": 24
     },
     {
       "epoch": 3.0,
-      "step": 21,
-      "total_flos": 6.644005855919309e+16,
-      "train_loss": 0.5345479193187895,
-      "train_runtime": 87.5066,
-      "train_samples_per_second": 30.546,
-      "train_steps_per_second": 0.24
+      "step": 24,
+      "total_flos": 7.471710289148314e+16,
+      "train_loss": 0.7044070760409037,
+      "train_runtime": 101.1597,
+      "train_samples_per_second": 29.715,
+      "train_steps_per_second": 0.237
     }
   ],
-  "max_steps": 21,
+  "max_steps": 24,
   "num_train_epochs": 3,
-  "total_flos": 6.644005855919309e+16,
+  "total_flos": 7.471710289148314e+16,
   "trial_name": null,
   "trial_params": null
 }