Training in progress, epoch 1

all_results.json

@@ -1,8 +1,13 @@
 {
     "epoch": 3.0,
-    "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.6010840450014386,
-    "train_runtime": 82.3084,
-    "train_samples_per_second": 32.475,
-    "train_steps_per_second": 0.255
+    "eval_accuracy": 0.6071428571428571,
+    "eval_loss": 0.6862359046936035,
+    "eval_runtime": 0.8492,
+    "eval_samples_per_second": 131.885,
+    "eval_steps_per_second": 4.71,
+    "total_flos": 7.471710289148314e+16,
+    "train_loss": 0.6844675143559774,
+    "train_runtime": 103.9833,
+    "train_samples_per_second": 28.908,
+    "train_steps_per_second": 0.231
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.6071428571428571,
+    "eval_loss": 0.6862359046936035,
+    "eval_runtime": 0.8492,
+    "eval_samples_per_second": 131.885,
+    "eval_steps_per_second": 4.71
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93819f614ab1a7071e3e3d55ec9a7d4ace4d0c3a0a1c70ade6fc49224fb6448c
+oid sha256:a25a101dde9f32f27810cad590e197ed56f0b94aa1f6df21db8d1ec277f16959
 size 110394865

runs/Jul20_19-45-58_fcbe542fc008/events.out.tfevents.1689882673.fcbe542fc008.344.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:508742c08776fe84217d5e5e06b76f830cccabe34dca5a59b176a3e83f86190e
+size 405

runs/Jul20_19-45-58_fcbe542fc008/events.out.tfevents.1689884242.fcbe542fc008.344.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd9df98b3146add3883dcb1fa6f9b09cba1b37fec446a89d5dbe27af2a8de5df
+size 4839

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "total_flos": 6.644005855919309e+16,
-    "train_loss": 0.6010840450014386,
-    "train_runtime": 82.3084,
-    "train_samples_per_second": 32.475,
-    "train_steps_per_second": 0.255
+    "total_flos": 7.471710289148314e+16,
+    "train_loss": 0.6844675143559774,
+    "train_runtime": 103.9833,
+    "train_samples_per_second": 28.908,
+    "train_steps_per_second": 0.231
 }

trainer_state.json

@@ -1,64 +1,64 @@
 {
-  "best_metric": 0.7130044843049327,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-14",
+  "best_metric": 0.6071428571428571,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-jvadlamudi2/checkpoint-24",
   "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": 0.6860986547085202,
-      "eval_loss": 0.5776408314704895,
-      "eval_runtime": 1.5327,
-      "eval_samples_per_second": 145.496,
-      "eval_steps_per_second": 4.567,
-      "step": 7
+      "eval_accuracy": 0.5892857142857143,
+      "eval_loss": 0.7051630616188049,
+      "eval_runtime": 0.9526,
+      "eval_samples_per_second": 117.567,
+      "eval_steps_per_second": 4.199,
+      "step": 8
     },
     {
-      "epoch": 1.43,
-      "learning_rate": 3.055555555555556e-05,
-      "loss": 0.6176,
+      "epoch": 1.25,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.7036,
       "step": 10
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7130044843049327,
-      "eval_loss": 0.5827417969703674,
-      "eval_runtime": 1.532,
-      "eval_samples_per_second": 145.559,
-      "eval_steps_per_second": 4.569,
-      "step": 14
+      "eval_accuracy": 0.5803571428571429,
+      "eval_loss": 0.6873636245727539,
+      "eval_runtime": 0.7758,
+      "eval_samples_per_second": 144.369,
+      "eval_steps_per_second": 5.156,
+      "step": 16
     },
     {
-      "epoch": 2.86,
-      "learning_rate": 2.777777777777778e-06,
-      "loss": 0.5847,
+      "epoch": 2.5,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 0.6691,
       "step": 20
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.7040358744394619,
-      "eval_loss": 0.586353063583374,
-      "eval_runtime": 1.5413,
-      "eval_samples_per_second": 144.679,
-      "eval_steps_per_second": 4.541,
-      "step": 21
+      "eval_accuracy": 0.6071428571428571,
+      "eval_loss": 0.6862359046936035,
+      "eval_runtime": 0.8007,
+      "eval_samples_per_second": 139.883,
+      "eval_steps_per_second": 4.996,
+      "step": 24
     },
     {
       "epoch": 3.0,
-      "step": 21,
-      "total_flos": 6.644005855919309e+16,
-      "train_loss": 0.6010840450014386,
-      "train_runtime": 82.3084,
-      "train_samples_per_second": 32.475,
-      "train_steps_per_second": 0.255
+      "step": 24,
+      "total_flos": 7.471710289148314e+16,
+      "train_loss": 0.6844675143559774,
+      "train_runtime": 103.9833,
+      "train_samples_per_second": 28.908,
+      "train_steps_per_second": 0.231
     }
   ],
-  "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
 }