End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7555555555555555
+      value: 0.7777777777777778
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4821
-- Accuracy: 0.7556
+- Loss: 0.5789
+- Accuracy: 0.7778
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 2.57,
-    "eval_accuracy": 0.5208333333333334,
-    "eval_loss": 0.7238028645515442,
-    "eval_runtime": 13.1416,
-    "eval_samples_per_second": 3.653,
-    "eval_steps_per_second": 0.152,
-    "total_flos": 2.759014777430016e+16,
-    "train_loss": 0.6113484700520834,
-    "train_runtime": 1056.1299,
-    "train_samples_per_second": 1.213,
-    "train_steps_per_second": 0.009
+    "epoch": 9.23,
+    "eval_accuracy": 0.7777777777777778,
+    "eval_loss": 0.5788682699203491,
+    "eval_runtime": 0.368,
+    "eval_samples_per_second": 122.284,
+    "eval_steps_per_second": 5.435,
+    "total_flos": 9.298885305598157e+16,
+    "train_loss": 0.6447619756062826,
+    "train_runtime": 94.3594,
+    "train_samples_per_second": 42.921,
+    "train_steps_per_second": 0.318
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.57,
-    "eval_accuracy": 0.5208333333333334,
-    "eval_loss": 0.7238028645515442,
-    "eval_runtime": 13.1416,
-    "eval_samples_per_second": 3.653,
-    "eval_steps_per_second": 0.152
+    "epoch": 9.23,
+    "eval_accuracy": 0.7777777777777778,
+    "eval_loss": 0.5788682699203491,
+    "eval_runtime": 0.368,
+    "eval_samples_per_second": 122.284,
+    "eval_steps_per_second": 5.435
 }

runs/Nov17_09-35-47_5aafc1ba1313/events.out.tfevents.1700213853.5aafc1ba1313.3404.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f02a3252789ccdc305d4e4edc9d8127633f0cef199acaa8efa36eaa2e2d789f7
+size 405

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.57,
-    "total_flos": 2.759014777430016e+16,
-    "train_loss": 0.6113484700520834,
-    "train_runtime": 1056.1299,
-    "train_samples_per_second": 1.213,
-    "train_steps_per_second": 0.009
+    "epoch": 9.23,
+    "total_flos": 9.298885305598157e+16,
+    "train_loss": 0.6447619756062826,
+    "train_runtime": 94.3594,
+    "train_samples_per_second": 42.921,
+    "train_steps_per_second": 0.318
 }

trainer_state.json

@@ -1,55 +1,136 @@
 {
-  "best_metric": 0.5208333333333334,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-3",
-  "epoch": 2.571428571428571,
+  "best_metric": 0.7777777777777778,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-13",
+  "epoch": 9.23076923076923,
   "eval_steps": 500,
-  "global_step": 9,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.86,
-      "eval_accuracy": 0.5208333333333334,
-      "eval_loss": 0.7238028645515442,
-      "eval_runtime": 14.8765,
-      "eval_samples_per_second": 3.227,
-      "eval_steps_per_second": 0.134,
+      "epoch": 0.92,
+      "eval_accuracy": 0.6,
+      "eval_loss": 0.8975929021835327,
+      "eval_runtime": 0.398,
+      "eval_samples_per_second": 113.062,
+      "eval_steps_per_second": 5.025,
       "step": 3
     },
     {
-      "epoch": 2.0,
-      "eval_accuracy": 0.5208333333333334,
-      "eval_loss": 0.6829412579536438,
-      "eval_runtime": 14.552,
-      "eval_samples_per_second": 3.299,
-      "eval_steps_per_second": 0.137,
-      "step": 7
+      "epoch": 1.85,
+      "eval_accuracy": 0.4888888888888889,
+      "eval_loss": 0.9455941915512085,
+      "eval_runtime": 0.6725,
+      "eval_samples_per_second": 66.915,
+      "eval_steps_per_second": 2.974,
+      "step": 6
     },
     {
-      "epoch": 2.57,
-      "eval_accuracy": 0.5208333333333334,
-      "eval_loss": 0.6898583769798279,
-      "eval_runtime": 14.5901,
-      "eval_samples_per_second": 3.29,
-      "eval_steps_per_second": 0.137,
+      "epoch": 2.77,
+      "eval_accuracy": 0.6222222222222222,
+      "eval_loss": 0.7694690227508545,
+      "eval_runtime": 0.3539,
+      "eval_samples_per_second": 127.154,
+      "eval_steps_per_second": 5.651,
       "step": 9
     },
     {
-      "epoch": 2.57,
-      "step": 9,
-      "total_flos": 2.759014777430016e+16,
-      "train_loss": 0.6113484700520834,
-      "train_runtime": 1056.1299,
-      "train_samples_per_second": 1.213,
-      "train_steps_per_second": 0.009
+      "epoch": 3.08,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.8575,
+      "step": 10
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7777777777777778,
+      "eval_loss": 0.5788682699203491,
+      "eval_runtime": 0.3556,
+      "eval_samples_per_second": 126.56,
+      "eval_steps_per_second": 5.625,
+      "step": 13
+    },
+    {
+      "epoch": 4.92,
+      "eval_accuracy": 0.7333333333333333,
+      "eval_loss": 0.5423295497894287,
+      "eval_runtime": 0.7951,
+      "eval_samples_per_second": 56.594,
+      "eval_steps_per_second": 2.515,
+      "step": 16
+    },
+    {
+      "epoch": 5.85,
+      "eval_accuracy": 0.7111111111111111,
+      "eval_loss": 0.5268533229827881,
+      "eval_runtime": 0.3341,
+      "eval_samples_per_second": 134.673,
+      "eval_steps_per_second": 5.985,
+      "step": 19
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 0.5728,
+      "step": 20
+    },
+    {
+      "epoch": 6.77,
+      "eval_accuracy": 0.7555555555555555,
+      "eval_loss": 0.4836295545101166,
+      "eval_runtime": 0.3452,
+      "eval_samples_per_second": 130.368,
+      "eval_steps_per_second": 5.794,
+      "step": 22
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7555555555555555,
+      "eval_loss": 0.48133209347724915,
+      "eval_runtime": 0.3034,
+      "eval_samples_per_second": 148.304,
+      "eval_steps_per_second": 6.591,
+      "step": 26
+    },
+    {
+      "epoch": 8.92,
+      "eval_accuracy": 0.7555555555555555,
+      "eval_loss": 0.48230746388435364,
+      "eval_runtime": 0.2978,
+      "eval_samples_per_second": 151.102,
+      "eval_steps_per_second": 6.716,
+      "step": 29
+    },
+    {
+      "epoch": 9.23,
+      "learning_rate": 0.0,
+      "loss": 0.504,
+      "step": 30
+    },
+    {
+      "epoch": 9.23,
+      "eval_accuracy": 0.7555555555555555,
+      "eval_loss": 0.48209622502326965,
+      "eval_runtime": 0.3871,
+      "eval_samples_per_second": 116.245,
+      "eval_steps_per_second": 5.166,
+      "step": 30
+    },
+    {
+      "epoch": 9.23,
+      "step": 30,
+      "total_flos": 9.298885305598157e+16,
+      "train_loss": 0.6447619756062826,
+      "train_runtime": 94.3594,
+      "train_samples_per_second": 42.921,
+      "train_steps_per_second": 0.318
     }
   ],
   "logging_steps": 10,
-  "max_steps": 9,
-  "num_train_epochs": 3,
+  "max_steps": 30,
+  "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 2.759014777430016e+16,
+  "total_flos": 9.298885305598157e+16,
   "trial_name": null,
   "trial_params": null
 }