Training in progress, epoch 1

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "total_flos": 2684446810472448.0,
-    "train_loss": 0.2830934325853984,
-    "train_runtime": 16.59,
-    "train_samples_per_second": 6.51,
-    "train_steps_per_second": 0.181
+    "epoch": 10.0,
+    "total_flos": 8948156034908160.0,
+    "train_loss": 0.19590264558792114,
+    "train_runtime": 49.0516,
+    "train_samples_per_second": 7.339,
+    "train_steps_per_second": 0.204
 }

runs/Aug20_17-49-57_dcaf84c0e0bc/1692553819.411282/events.out.tfevents.1692553819.dcaf84c0e0bc.1053.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd5985d2488f9916a3085597fcc1559b55f5e63bca3f93f75069c9c9f5e5a4d2
+size 5976

runs/Aug20_17-49-57_dcaf84c0e0bc/events.out.tfevents.1692553819.dcaf84c0e0bc.1053.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3326b9594c0f5a29f7fca228319b55e2c191b044fb59acc234eb9919d569c08
+size 4835

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "total_flos": 2684446810472448.0,
-    "train_loss": 0.2830934325853984,
-    "train_runtime": 16.59,
-    "train_samples_per_second": 6.51,
-    "train_steps_per_second": 0.181
+    "epoch": 10.0,
+    "total_flos": 8948156034908160.0,
+    "train_loss": 0.19590264558792114,
+    "train_runtime": 49.0516,
+    "train_samples_per_second": 7.339,
+    "train_steps_per_second": 0.204
 }

trainer_state.json

@@ -1,52 +1,121 @@
 {
-  "best_metric": 0.25,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-mulder-v-scully-colab/checkpoint-2",
-  "epoch": 3.0,
-  "global_step": 3,
+  "best_metric": 0.75,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-mulder-v-scully-colab/checkpoint-5",
+  "epoch": 10.0,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.0,
-      "eval_loss": 0.8255465626716614,
-      "eval_runtime": 0.31,
-      "eval_samples_per_second": 12.902,
-      "eval_steps_per_second": 3.225,
+      "eval_accuracy": 0.25,
+      "eval_loss": 0.8688191771507263,
+      "eval_runtime": 0.2785,
+      "eval_samples_per_second": 14.362,
+      "eval_steps_per_second": 3.591,
       "step": 1
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.25,
-      "eval_loss": 0.8688191771507263,
-      "eval_runtime": 0.3101,
-      "eval_samples_per_second": 12.9,
-      "eval_steps_per_second": 3.225,
+      "eval_loss": 0.7692552804946899,
+      "eval_runtime": 0.2993,
+      "eval_samples_per_second": 13.366,
+      "eval_steps_per_second": 3.341,
       "step": 2
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.25,
-      "eval_loss": 0.8737704753875732,
-      "eval_runtime": 0.3197,
-      "eval_samples_per_second": 12.511,
-      "eval_steps_per_second": 3.128,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.7055538892745972,
+      "eval_runtime": 0.2815,
+      "eval_samples_per_second": 14.211,
+      "eval_steps_per_second": 3.553,
       "step": 3
     },
     {
-      "epoch": 3.0,
-      "step": 3,
-      "total_flos": 2684446810472448.0,
-      "train_loss": 0.2830934325853984,
-      "train_runtime": 16.59,
-      "train_samples_per_second": 6.51,
-      "train_steps_per_second": 0.181
+      "epoch": 4.0,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.6579211950302124,
+      "eval_runtime": 0.2933,
+      "eval_samples_per_second": 13.636,
+      "eval_steps_per_second": 3.409,
+      "step": 4
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.6105230450630188,
+      "eval_runtime": 0.283,
+      "eval_samples_per_second": 14.136,
+      "eval_steps_per_second": 3.534,
+      "step": 5
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.601015031337738,
+      "eval_runtime": 0.2817,
+      "eval_samples_per_second": 14.202,
+      "eval_steps_per_second": 3.55,
+      "step": 6
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5963175892829895,
+      "eval_runtime": 0.2889,
+      "eval_samples_per_second": 13.845,
+      "eval_steps_per_second": 3.461,
+      "step": 7
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5912925601005554,
+      "eval_runtime": 0.2873,
+      "eval_samples_per_second": 13.924,
+      "eval_steps_per_second": 3.481,
+      "step": 8
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5851244926452637,
+      "eval_runtime": 0.2874,
+      "eval_samples_per_second": 13.917,
+      "eval_steps_per_second": 3.479,
+      "step": 9
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.1959,
+      "step": 10
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5820506811141968,
+      "eval_runtime": 0.2797,
+      "eval_samples_per_second": 14.3,
+      "eval_steps_per_second": 3.575,
+      "step": 10
+    },
+    {
+      "epoch": 10.0,
+      "step": 10,
+      "total_flos": 8948156034908160.0,
+      "train_loss": 0.19590264558792114,
+      "train_runtime": 49.0516,
+      "train_samples_per_second": 7.339,
+      "train_steps_per_second": 0.204
     }
   ],
-  "max_steps": 3,
-  "num_train_epochs": 3,
-  "total_flos": 2684446810472448.0,
+  "max_steps": 10,
+  "num_train_epochs": 10,
+  "total_flos": 8948156034908160.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5fe49813ec5b29c35a67b080a659761d7d6dd13fdce5828a214487df84bc619
+oid sha256:ccf3771df9680e65955f351e54d035088bcfeae9c7758b133d5557839f813811
 size 3643