Training in progress, epoch 1

all_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 2.0,
-    "eval_accuracy": 0.9463276836158192,
-    "eval_loss": 0.16774888336658478,
-    "eval_runtime": 6.5505,
-    "eval_samples_per_second": 108.084,
-    "eval_steps_per_second": 3.511,
-    "train_loss": 0.3428042984008789,
-    "train_runtime": 253.1417,
-    "train_samples_per_second": 50.335,
-    "train_steps_per_second": 0.395
+    "epoch": 1.0,
+    "eval_accuracy": 0.9067796610169492,
+    "eval_loss": 0.2143896520137787,
+    "eval_runtime": 6.5896,
+    "eval_samples_per_second": 107.442,
+    "eval_steps_per_second": 3.49,
+    "train_loss": 0.3968027877807617,
+    "train_runtime": 131.1462,
+    "train_samples_per_second": 48.579,
+    "train_steps_per_second": 0.381
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.0,
-    "eval_accuracy": 0.9463276836158192,
-    "eval_loss": 0.16774888336658478,
-    "eval_runtime": 6.5505,
-    "eval_samples_per_second": 108.084,
-    "eval_steps_per_second": 3.511
+    "epoch": 1.0,
+    "eval_accuracy": 0.9067796610169492,
+    "eval_loss": 0.2143896520137787,
+    "eval_runtime": 6.5896,
+    "eval_samples_per_second": 107.442,
+    "eval_steps_per_second": 3.49
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00eb4de406524ddcf7967c6517608a95da1f95db09a0bd70e156cbcacadd4acc
+oid sha256:43b35d3c87dea27eae9dcfa2c8c7789586838650990f5e7433d03e90b1fdc018
 size 110392879

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 2.0,
-    "train_loss": 0.3428042984008789,
-    "train_runtime": 253.1417,
-    "train_samples_per_second": 50.335,
-    "train_steps_per_second": 0.395
+    "epoch": 1.0,
+    "train_loss": 0.3968027877807617,
+    "train_runtime": 131.1462,
+    "train_samples_per_second": 48.579,
+    "train_steps_per_second": 0.381
 }

trainer_state.json

@@ -1,103 +1,64 @@
 {
-  "best_metric": 0.9463276836158192,
+  "best_metric": 0.9067796610169492,
   "best_model_checkpoint": "swin-tiny-patch4-window7-224-thecbbbfs/checkpoint-50",
-  "epoch": 2.0,
-  "global_step": 100,
+  "epoch": 1.0,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.2,
-      "learning_rate": 5e-05,
-      "loss": 0.6807,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.6272,
       "step": 10
     },
     {
       "epoch": 0.4,
-      "learning_rate": 4.4444444444444447e-05,
-      "loss": 0.4571,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.4233,
       "step": 20
     },
     {
       "epoch": 0.6,
-      "learning_rate": 3.888888888888889e-05,
-      "loss": 0.3641,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.3504,
       "step": 30
     },
     {
       "epoch": 0.8,
-      "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.3032,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.2985,
       "step": 40
     },
     {
       "epoch": 1.0,
-      "learning_rate": 2.777777777777778e-05,
-      "loss": 0.3049,
+      "learning_rate": 0.0,
+      "loss": 0.2846,
       "step": 50
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.9463276836158192,
-      "eval_loss": 0.16774888336658478,
-      "eval_runtime": 6.932,
-      "eval_samples_per_second": 102.135,
-      "eval_steps_per_second": 3.318,
+      "eval_accuracy": 0.9067796610169492,
+      "eval_loss": 0.2143896520137787,
+      "eval_runtime": 6.7574,
+      "eval_samples_per_second": 104.774,
+      "eval_steps_per_second": 3.404,
       "step": 50
     },
     {
-      "epoch": 1.2,
-      "learning_rate": 2.2222222222222223e-05,
-      "loss": 0.2846,
-      "step": 60
-    },
-    {
-      "epoch": 1.4,
-      "learning_rate": 1.6666666666666667e-05,
-      "loss": 0.2731,
-      "step": 70
-    },
-    {
-      "epoch": 1.6,
-      "learning_rate": 1.1111111111111112e-05,
-      "loss": 0.2579,
-      "step": 80
-    },
-    {
-      "epoch": 1.8,
-      "learning_rate": 5.555555555555556e-06,
-      "loss": 0.2618,
-      "step": 90
-    },
-    {
-      "epoch": 2.0,
-      "learning_rate": 0.0,
-      "loss": 0.2405,
-      "step": 100
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.940677966101695,
-      "eval_loss": 0.15754352509975433,
-      "eval_runtime": 6.3662,
-      "eval_samples_per_second": 111.213,
-      "eval_steps_per_second": 3.613,
-      "step": 100
-    },
-    {
-      "epoch": 2.0,
-      "step": 100,
-      "total_flos": 3.1671501165777715e+17,
-      "train_loss": 0.3428042984008789,
-      "train_runtime": 253.1417,
-      "train_samples_per_second": 50.335,
-      "train_steps_per_second": 0.395
+      "epoch": 1.0,
+      "step": 50,
+      "total_flos": 1.5835750582888858e+17,
+      "train_loss": 0.3968027877807617,
+      "train_runtime": 131.1462,
+      "train_samples_per_second": 48.579,
+      "train_steps_per_second": 0.381
     }
   ],
-  "max_steps": 100,
-  "num_train_epochs": 2,
-  "total_flos": 3.1671501165777715e+17,
+  "max_steps": 50,
+  "num_train_epochs": 1,
+  "total_flos": 1.5835750582888858e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f775c3bce8a1ee56a857253ed12068ffa1dcb2c624eac03aecb4af3a0d6f0d6
+oid sha256:e6e45c29cfe7ae9fc3fba51df7814b77b855ece047c83528b97c18ae4cd99789
 size 3375