End of training

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 3.0,
+    "epoch": 10.0,
     "eval_accuracy": 1.0,
     "eval_loss": 0.5404492020606995,
-    "eval_runtime": 0.0837,
-    "eval_samples_per_second": 47.792,
-    "eval_steps_per_second": 11.948,
-    "total_flos": 2609878843514880.0,
-    "train_loss": 0.3703581889470418,
-    "train_runtime": 17.2978,
-    "train_samples_per_second": 6.07,
-    "train_steps_per_second": 0.173
+    "eval_runtime": 0.0787,
+    "eval_samples_per_second": 50.832,
+    "eval_steps_per_second": 12.708,
+    "total_flos": 8699596145049600.0,
+    "train_loss": 0.20386319160461425,
+    "train_runtime": 41.2868,
+    "train_samples_per_second": 8.477,
+    "train_steps_per_second": 0.242
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
+    "epoch": 10.0,
     "eval_accuracy": 1.0,
     "eval_loss": 0.5404492020606995,
-    "eval_runtime": 0.0837,
-    "eval_samples_per_second": 47.792,
-    "eval_steps_per_second": 11.948
+    "eval_runtime": 0.0787,
+    "eval_samples_per_second": 50.832,
+    "eval_steps_per_second": 12.708
 }

runs/Sep05_21-38-17_4d01f37efe8d/events.out.tfevents.1662414227.4d01f37efe8d.71.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:357c841a60d6633e61c9f4e01b3ed60909ef5ae0efbdac46ebd7fa122e880a93
+size 357

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "total_flos": 2609878843514880.0,
-    "train_loss": 0.3703581889470418,
-    "train_runtime": 17.2978,
-    "train_samples_per_second": 6.07,
-    "train_steps_per_second": 0.173
+    "epoch": 10.0,
+    "total_flos": 8699596145049600.0,
+    "train_loss": 0.20386319160461425,
+    "train_runtime": 41.2868,
+    "train_samples_per_second": 8.477,
+    "train_steps_per_second": 0.242
 }

trainer_state.json

@@ -1,52 +1,121 @@
 {
   "best_metric": 1.0,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-vosap/checkpoint-3",
-  "epoch": 3.0,
-  "global_step": 3,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-vosap/checkpoint-1",
+  "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": 0.75,
-      "eval_loss": 0.5402008891105652,
-      "eval_runtime": 0.0643,
-      "eval_samples_per_second": 62.204,
-      "eval_steps_per_second": 15.551,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.5404492020606995,
+      "eval_runtime": 0.0625,
+      "eval_samples_per_second": 64.034,
+      "eval_steps_per_second": 16.008,
       "step": 1
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.75,
-      "eval_loss": 0.5328630805015564,
-      "eval_runtime": 0.0721,
-      "eval_samples_per_second": 55.489,
-      "eval_steps_per_second": 13.872,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.4876060485839844,
+      "eval_runtime": 0.0737,
+      "eval_samples_per_second": 54.286,
+      "eval_steps_per_second": 13.571,
       "step": 2
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 1.0,
-      "eval_loss": 0.5404492020606995,
-      "eval_runtime": 0.0704,
-      "eval_samples_per_second": 56.826,
-      "eval_steps_per_second": 14.206,
+      "eval_loss": 0.44556379318237305,
+      "eval_runtime": 0.0672,
+      "eval_samples_per_second": 59.503,
+      "eval_steps_per_second": 14.876,
       "step": 3
     },
     {
-      "epoch": 3.0,
-      "step": 3,
-      "total_flos": 2609878843514880.0,
-      "train_loss": 0.3703581889470418,
-      "train_runtime": 17.2978,
-      "train_samples_per_second": 6.07,
-      "train_steps_per_second": 0.173
+      "epoch": 4.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.41716501116752625,
+      "eval_runtime": 0.0654,
+      "eval_samples_per_second": 61.169,
+      "eval_steps_per_second": 15.292,
+      "step": 4
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.3770451843738556,
+      "eval_runtime": 0.0686,
+      "eval_samples_per_second": 58.32,
+      "eval_steps_per_second": 14.58,
+      "step": 5
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.3442598283290863,
+      "eval_runtime": 0.0676,
+      "eval_samples_per_second": 59.13,
+      "eval_steps_per_second": 14.783,
+      "step": 6
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.32264935970306396,
+      "eval_runtime": 0.0634,
+      "eval_samples_per_second": 63.066,
+      "eval_steps_per_second": 15.767,
+      "step": 7
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.3132918179035187,
+      "eval_runtime": 0.0661,
+      "eval_samples_per_second": 60.478,
+      "eval_steps_per_second": 15.12,
+      "step": 8
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.30815836787223816,
+      "eval_runtime": 0.0661,
+      "eval_samples_per_second": 60.509,
+      "eval_steps_per_second": 15.127,
+      "step": 9
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.2039,
+      "step": 10
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.30541735887527466,
+      "eval_runtime": 0.0689,
+      "eval_samples_per_second": 58.029,
+      "eval_steps_per_second": 14.507,
+      "step": 10
+    },
+    {
+      "epoch": 10.0,
+      "step": 10,
+      "total_flos": 8699596145049600.0,
+      "train_loss": 0.20386319160461425,
+      "train_runtime": 41.2868,
+      "train_samples_per_second": 8.477,
+      "train_steps_per_second": 0.242
     }
   ],
-  "max_steps": 3,
-  "num_train_epochs": 3,
-  "total_flos": 2609878843514880.0,
+  "max_steps": 10,
+  "num_train_epochs": 10,
+  "total_flos": 8699596145049600.0,
   "trial_name": null,
   "trial_params": null
 }