Training in progress, epoch 1

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.5446428571428571,
-    "eval_loss": 0.7017055153846741,
-    "eval_runtime": 0.8235,
-    "eval_samples_per_second": 136.007,
-    "eval_steps_per_second": 4.857,
-    "total_flos": 7.471710289148314e+16,
-    "train_loss": 0.6822827259699503,
-    "train_runtime": 78.5418,
-    "train_samples_per_second": 38.273,
-    "train_steps_per_second": 0.306
+    "eval_accuracy": 0.6875,
+    "eval_loss": 0.6389141082763672,
+    "eval_runtime": 1.4896,
+    "eval_samples_per_second": 75.188,
+    "eval_steps_per_second": 2.685,
+    "total_flos": 6.651462652615066e+16,
+    "train_loss": 0.6625232639766875,
+    "train_runtime": 75.1281,
+    "train_samples_per_second": 35.619,
+    "train_steps_per_second": 0.28
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.5446428571428571,
-    "eval_loss": 0.7017055153846741,
-    "eval_runtime": 0.8235,
-    "eval_samples_per_second": 136.007,
-    "eval_steps_per_second": 4.857
+    "eval_accuracy": 0.6875,
+    "eval_loss": 0.6389141082763672,
+    "eval_runtime": 1.4896,
+    "eval_samples_per_second": 75.188,
+    "eval_steps_per_second": 2.685
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad1574a31bb1aec72c3fdea4212c83d4b35411f0dedefcb43571bda2992b852e
+oid sha256:d8af6b07d33c7b7065d4585f641437008c17714e4d6b62d7a3fb64563d7810db
 size 110394865

runs/Jul24_17-23-16_79617dc78cd9/events.out.tfevents.1690220095.79617dc78cd9.248.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c078076e77e7caa2eda44a9916d9bbd8ba905682bfc99a8b36fd1bf23616fc9
+size 405

runs/Jul24_17-23-16_79617dc78cd9/events.out.tfevents.1690220157.79617dc78cd9.248.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab3ea2ba6d8dfae420a1315f9dc4330c77172a78dfffd348c4581a4271cbefc
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "total_flos": 7.471710289148314e+16,
-    "train_loss": 0.6822827259699503,
-    "train_runtime": 78.5418,
-    "train_samples_per_second": 38.273,
-    "train_steps_per_second": 0.306
+    "total_flos": 6.651462652615066e+16,
+    "train_loss": 0.6625232639766875,
+    "train_runtime": 75.1281,
+    "train_samples_per_second": 35.619,
+    "train_steps_per_second": 0.28
 }

trainer_state.json

@@ -1,64 +1,64 @@
 {
-  "best_metric": 0.5446428571428571,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-8",
+  "best_metric": 0.6875,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-21",
   "epoch": 3.0,
-  "global_step": 24,
+  "global_step": 21,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5446428571428571,
-      "eval_loss": 0.7017055153846741,
-      "eval_runtime": 0.7757,
-      "eval_samples_per_second": 144.381,
-      "eval_steps_per_second": 5.156,
-      "step": 8
+      "eval_accuracy": 0.5892857142857143,
+      "eval_loss": 0.6659354567527771,
+      "eval_runtime": 0.8649,
+      "eval_samples_per_second": 129.489,
+      "eval_steps_per_second": 4.625,
+      "step": 7
     },
     {
-      "epoch": 1.25,
-      "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.7035,
+      "epoch": 1.43,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 0.6765,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5357142857142857,
-      "eval_loss": 0.6943592429161072,
-      "eval_runtime": 0.8752,
-      "eval_samples_per_second": 127.978,
-      "eval_steps_per_second": 4.571,
-      "step": 16
+      "eval_accuracy": 0.6517857142857143,
+      "eval_loss": 0.6479455232620239,
+      "eval_runtime": 0.8944,
+      "eval_samples_per_second": 125.219,
+      "eval_steps_per_second": 4.472,
+      "step": 14
     },
     {
-      "epoch": 2.5,
-      "learning_rate": 9.523809523809523e-06,
-      "loss": 0.6688,
+      "epoch": 2.86,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 0.6502,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5178571428571429,
-      "eval_loss": 0.6939972043037415,
-      "eval_runtime": 0.7259,
-      "eval_samples_per_second": 154.282,
-      "eval_steps_per_second": 5.51,
-      "step": 24
+      "eval_accuracy": 0.6875,
+      "eval_loss": 0.6389141082763672,
+      "eval_runtime": 0.8926,
+      "eval_samples_per_second": 125.472,
+      "eval_steps_per_second": 4.481,
+      "step": 21
     },
     {
       "epoch": 3.0,
-      "step": 24,
-      "total_flos": 7.471710289148314e+16,
-      "train_loss": 0.6822827259699503,
-      "train_runtime": 78.5418,
-      "train_samples_per_second": 38.273,
-      "train_steps_per_second": 0.306
+      "step": 21,
+      "total_flos": 6.651462652615066e+16,
+      "train_loss": 0.6625232639766875,
+      "train_runtime": 75.1281,
+      "train_samples_per_second": 35.619,
+      "train_steps_per_second": 0.28
     }
   ],
-  "max_steps": 24,
+  "max_steps": 21,
   "num_train_epochs": 3,
-  "total_flos": 7.471710289148314e+16,
+  "total_flos": 6.651462652615066e+16,
   "trial_name": null,
   "trial_params": null
 }