End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8444444444444444
+      value: 0.8666666666666667
 ---
 
 <!-- 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 [Yogesh1p/swin-tiny-patch4-window7-224-finetuned-cp1](https://huggingface.co/Yogesh1p/swin-tiny-patch4-window7-224-finetuned-cp1) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3494
-- Accuracy: 0.8444
+- Loss: 0.3628
+- Accuracy: 0.8667
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 18.46,
+    "epoch": 27.69,
     "eval_accuracy": 0.8666666666666667,
-    "eval_loss": 0.3993411958217621,
-    "eval_runtime": 0.3745,
-    "eval_samples_per_second": 120.166,
-    "eval_steps_per_second": 5.341,
-    "total_flos": 1.8597770611196314e+17,
-    "train_loss": 0.41367613077163695,
-    "train_runtime": 161.4115,
-    "train_samples_per_second": 50.182,
-    "train_steps_per_second": 0.372
+    "eval_loss": 0.3628138601779938,
+    "eval_runtime": 0.4338,
+    "eval_samples_per_second": 103.734,
+    "eval_steps_per_second": 4.61,
+    "total_flos": 2.789665591679447e+17,
+    "train_loss": 0.2528756472799513,
+    "train_runtime": 227.9034,
+    "train_samples_per_second": 53.312,
+    "train_steps_per_second": 0.395
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 18.46,
+    "epoch": 27.69,
     "eval_accuracy": 0.8666666666666667,
-    "eval_loss": 0.3993411958217621,
-    "eval_runtime": 0.3745,
-    "eval_samples_per_second": 120.166,
-    "eval_steps_per_second": 5.341
+    "eval_loss": 0.3628138601779938,
+    "eval_runtime": 0.4338,
+    "eval_samples_per_second": 103.734,
+    "eval_steps_per_second": 4.61
 }

runs/Nov21_03-56-28_b5f9a6b3f51f/events.out.tfevents.1700539230.b5f9a6b3f51f.3745.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec6bbb74fb14c90936a6445574a8c72574518f9bf29416a1804d0e6d5f4b2094
+size 405

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 18.46,
-    "total_flos": 1.8597770611196314e+17,
-    "train_loss": 0.41367613077163695,
-    "train_runtime": 161.4115,
-    "train_samples_per_second": 50.182,
-    "train_steps_per_second": 0.372
+    "epoch": 27.69,
+    "total_flos": 2.789665591679447e+17,
+    "train_loss": 0.2528756472799513,
+    "train_runtime": 227.9034,
+    "train_samples_per_second": 53.312,
+    "train_steps_per_second": 0.395
 }

trainer_state.json

@@ -1,235 +1,334 @@
 {
   "best_metric": 0.8666666666666667,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-cp1/checkpoint-26",
-  "epoch": 18.46153846153846,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-cp1/checkpoint-22",
+  "epoch": 27.692307692307693,
   "eval_steps": 500,
-  "global_step": 60,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.92,
-      "eval_accuracy": 0.6666666666666666,
-      "eval_loss": 0.6966269016265869,
-      "eval_runtime": 0.565,
-      "eval_samples_per_second": 79.642,
-      "eval_steps_per_second": 3.54,
+      "eval_accuracy": 0.8222222222222222,
+      "eval_loss": 0.43046388030052185,
+      "eval_runtime": 0.7101,
+      "eval_samples_per_second": 63.368,
+      "eval_steps_per_second": 2.816,
       "step": 3
     },
     {
       "epoch": 1.85,
-      "eval_accuracy": 0.7777777777777778,
-      "eval_loss": 0.6159498691558838,
-      "eval_runtime": 0.6943,
-      "eval_samples_per_second": 64.815,
-      "eval_steps_per_second": 2.881,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.45104652643203735,
+      "eval_runtime": 0.2996,
+      "eval_samples_per_second": 150.201,
+      "eval_steps_per_second": 6.676,
       "step": 6
     },
     {
       "epoch": 2.77,
-      "eval_accuracy": 0.7111111111111111,
-      "eval_loss": 0.6517996191978455,
-      "eval_runtime": 0.3038,
-      "eval_samples_per_second": 148.127,
-      "eval_steps_per_second": 6.583,
+      "eval_accuracy": 0.7777777777777778,
+      "eval_loss": 0.4328728914260864,
+      "eval_runtime": 0.3627,
+      "eval_samples_per_second": 124.077,
+      "eval_steps_per_second": 5.515,
       "step": 9
     },
     {
       "epoch": 3.08,
-      "learning_rate": 4.62962962962963e-05,
-      "loss": 0.6821,
+      "learning_rate": 4.938271604938271e-05,
+      "loss": 0.3489,
       "step": 10
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.7555555555555555,
-      "eval_loss": 0.539168655872345,
-      "eval_runtime": 0.3472,
-      "eval_samples_per_second": 129.601,
-      "eval_steps_per_second": 5.76,
+      "eval_accuracy": 0.7777777777777778,
+      "eval_loss": 0.49650371074676514,
+      "eval_runtime": 0.3082,
+      "eval_samples_per_second": 145.987,
+      "eval_steps_per_second": 6.488,
       "step": 13
     },
     {
       "epoch": 4.92,
-      "eval_accuracy": 0.7333333333333333,
-      "eval_loss": 0.5302260518074036,
-      "eval_runtime": 0.3,
-      "eval_samples_per_second": 149.986,
-      "eval_steps_per_second": 6.666,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.4246769845485687,
+      "eval_runtime": 0.5832,
+      "eval_samples_per_second": 77.157,
+      "eval_steps_per_second": 3.429,
       "step": 16
     },
     {
       "epoch": 5.85,
-      "eval_accuracy": 0.7777777777777778,
-      "eval_loss": 0.45173752307891846,
-      "eval_runtime": 0.3526,
-      "eval_samples_per_second": 127.605,
-      "eval_steps_per_second": 5.671,
+      "eval_accuracy": 0.8444444444444444,
+      "eval_loss": 0.35588106513023376,
+      "eval_runtime": 0.3557,
+      "eval_samples_per_second": 126.495,
+      "eval_steps_per_second": 5.622,
       "step": 19
     },
     {
       "epoch": 6.15,
-      "learning_rate": 3.7037037037037037e-05,
-      "loss": 0.4852,
+      "learning_rate": 4.3209876543209875e-05,
+      "loss": 0.2872,
       "step": 20
     },
     {
       "epoch": 6.77,
-      "eval_accuracy": 0.8222222222222222,
-      "eval_loss": 0.45341956615448,
-      "eval_runtime": 0.3025,
-      "eval_samples_per_second": 148.775,
-      "eval_steps_per_second": 6.612,
+      "eval_accuracy": 0.8666666666666667,
+      "eval_loss": 0.3628138601779938,
+      "eval_runtime": 0.3453,
+      "eval_samples_per_second": 130.324,
+      "eval_steps_per_second": 5.792,
       "step": 22
     },
     {
       "epoch": 8.0,
       "eval_accuracy": 0.8666666666666667,
-      "eval_loss": 0.3993411958217621,
-      "eval_runtime": 0.3539,
-      "eval_samples_per_second": 127.164,
-      "eval_steps_per_second": 5.652,
+      "eval_loss": 0.35114532709121704,
+      "eval_runtime": 0.3013,
+      "eval_samples_per_second": 149.361,
+      "eval_steps_per_second": 6.638,
       "step": 26
     },
     {
       "epoch": 8.92,
       "eval_accuracy": 0.8666666666666667,
-      "eval_loss": 0.39546632766723633,
-      "eval_runtime": 0.301,
-      "eval_samples_per_second": 149.481,
-      "eval_steps_per_second": 6.644,
+      "eval_loss": 0.353840708732605,
+      "eval_runtime": 0.3515,
+      "eval_samples_per_second": 128.025,
+      "eval_steps_per_second": 5.69,
       "step": 29
     },
     {
       "epoch": 9.23,
-      "learning_rate": 2.777777777777778e-05,
-      "loss": 0.4126,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.3071,
       "step": 30
     },
     {
       "epoch": 9.85,
-      "eval_accuracy": 0.7777777777777778,
-      "eval_loss": 0.4562585651874542,
-      "eval_runtime": 0.3484,
-      "eval_samples_per_second": 129.155,
-      "eval_steps_per_second": 5.74,
+      "eval_accuracy": 0.8222222222222222,
+      "eval_loss": 0.3643886148929596,
+      "eval_runtime": 0.2957,
+      "eval_samples_per_second": 152.16,
+      "eval_steps_per_second": 6.763,
       "step": 32
     },
     {
       "epoch": 10.77,
-      "eval_accuracy": 0.8,
-      "eval_loss": 0.43147018551826477,
-      "eval_runtime": 0.2969,
-      "eval_samples_per_second": 151.556,
-      "eval_steps_per_second": 6.736,
+      "eval_accuracy": 0.8222222222222222,
+      "eval_loss": 0.38603129982948303,
+      "eval_runtime": 0.3509,
+      "eval_samples_per_second": 128.255,
+      "eval_steps_per_second": 5.7,
       "step": 35
     },
     {
       "epoch": 12.0,
-      "eval_accuracy": 0.7555555555555555,
-      "eval_loss": 0.6095713973045349,
-      "eval_runtime": 0.3589,
-      "eval_samples_per_second": 125.394,
-      "eval_steps_per_second": 5.573,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.5916851162910461,
+      "eval_runtime": 0.3126,
+      "eval_samples_per_second": 143.949,
+      "eval_steps_per_second": 6.398,
       "step": 39
     },
     {
       "epoch": 12.31,
-      "learning_rate": 1.8518518518518518e-05,
-      "loss": 0.3375,
+      "learning_rate": 3.08641975308642e-05,
+      "loss": 0.2765,
       "step": 40
     },
     {
       "epoch": 12.92,
-      "eval_accuracy": 0.7555555555555555,
-      "eval_loss": 0.5937639474868774,
-      "eval_runtime": 0.3093,
-      "eval_samples_per_second": 145.511,
-      "eval_steps_per_second": 6.467,
+      "eval_accuracy": 0.7777777777777778,
+      "eval_loss": 0.51491379737854,
+      "eval_runtime": 0.349,
+      "eval_samples_per_second": 128.934,
+      "eval_steps_per_second": 5.73,
       "step": 42
     },
     {
       "epoch": 13.85,
-      "eval_accuracy": 0.7333333333333333,
-      "eval_loss": 0.5607755184173584,
-      "eval_runtime": 0.6769,
-      "eval_samples_per_second": 66.477,
-      "eval_steps_per_second": 2.955,
+      "eval_accuracy": 0.7555555555555555,
+      "eval_loss": 0.5604969263076782,
+      "eval_runtime": 0.3081,
+      "eval_samples_per_second": 146.057,
+      "eval_steps_per_second": 6.491,
       "step": 45
     },
     {
       "epoch": 14.77,
-      "eval_accuracy": 0.7555555555555555,
-      "eval_loss": 0.49962636828422546,
-      "eval_runtime": 0.2986,
-      "eval_samples_per_second": 150.725,
-      "eval_steps_per_second": 6.699,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.4737274944782257,
+      "eval_runtime": 0.3434,
+      "eval_samples_per_second": 131.024,
+      "eval_steps_per_second": 5.823,
       "step": 48
     },
     {
       "epoch": 15.38,
-      "learning_rate": 9.259259259259259e-06,
-      "loss": 0.3164,
+      "learning_rate": 2.4691358024691357e-05,
+      "loss": 0.2637,
       "step": 50
     },
     {
       "epoch": 16.0,
-      "eval_accuracy": 0.7777777777777778,
-      "eval_loss": 0.4619426429271698,
-      "eval_runtime": 0.3496,
-      "eval_samples_per_second": 128.711,
-      "eval_steps_per_second": 5.72,
+      "eval_accuracy": 0.8444444444444444,
+      "eval_loss": 0.4108584523200989,
+      "eval_runtime": 0.3059,
+      "eval_samples_per_second": 147.129,
+      "eval_steps_per_second": 6.539,
       "step": 52
     },
     {
       "epoch": 16.92,
       "eval_accuracy": 0.8222222222222222,
-      "eval_loss": 0.41228044033050537,
-      "eval_runtime": 0.299,
-      "eval_samples_per_second": 150.515,
-      "eval_steps_per_second": 6.69,
+      "eval_loss": 0.3583980202674866,
+      "eval_runtime": 0.3526,
+      "eval_samples_per_second": 127.634,
+      "eval_steps_per_second": 5.673,
       "step": 55
     },
     {
       "epoch": 17.85,
       "eval_accuracy": 0.8222222222222222,
-      "eval_loss": 0.3872722089290619,
-      "eval_runtime": 0.3539,
-      "eval_samples_per_second": 127.14,
-      "eval_steps_per_second": 5.651,
+      "eval_loss": 0.3771374523639679,
+      "eval_runtime": 0.2992,
+      "eval_samples_per_second": 150.412,
+      "eval_steps_per_second": 6.685,
       "step": 58
     },
     {
       "epoch": 18.46,
-      "learning_rate": 0.0,
-      "loss": 0.2482,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 0.2082,
       "step": 60
     },
     {
-      "epoch": 18.46,
+      "epoch": 18.77,
       "eval_accuracy": 0.8222222222222222,
-      "eval_loss": 0.3830316364765167,
-      "eval_runtime": 0.3319,
-      "eval_samples_per_second": 135.589,
-      "eval_steps_per_second": 6.026,
-      "step": 60
+      "eval_loss": 0.4406029284000397,
+      "eval_runtime": 0.3532,
+      "eval_samples_per_second": 127.395,
+      "eval_steps_per_second": 5.662,
+      "step": 61
     },
     {
-      "epoch": 18.46,
-      "step": 60,
-      "total_flos": 1.8597770611196314e+17,
-      "train_loss": 0.41367613077163695,
-      "train_runtime": 161.4115,
-      "train_samples_per_second": 50.182,
-      "train_steps_per_second": 0.372
+      "epoch": 20.0,
+      "eval_accuracy": 0.8222222222222222,
+      "eval_loss": 0.35921329259872437,
+      "eval_runtime": 0.3008,
+      "eval_samples_per_second": 149.587,
+      "eval_steps_per_second": 6.648,
+      "step": 65
+    },
+    {
+      "epoch": 20.92,
+      "eval_accuracy": 0.8666666666666667,
+      "eval_loss": 0.3301694691181183,
+      "eval_runtime": 0.3427,
+      "eval_samples_per_second": 131.308,
+      "eval_steps_per_second": 5.836,
+      "step": 68
+    },
+    {
+      "epoch": 21.54,
+      "learning_rate": 1.2345679012345678e-05,
+      "loss": 0.1944,
+      "step": 70
+    },
+    {
+      "epoch": 21.85,
+      "eval_accuracy": 0.8444444444444444,
+      "eval_loss": 0.32061001658439636,
+      "eval_runtime": 0.3167,
+      "eval_samples_per_second": 142.092,
+      "eval_steps_per_second": 6.315,
+      "step": 71
+    },
+    {
+      "epoch": 22.77,
+      "eval_accuracy": 0.8666666666666667,
+      "eval_loss": 0.3215346336364746,
+      "eval_runtime": 0.354,
+      "eval_samples_per_second": 127.118,
+      "eval_steps_per_second": 5.65,
+      "step": 74
+    },
+    {
+      "epoch": 24.0,
+      "eval_accuracy": 0.8666666666666667,
+      "eval_loss": 0.32090896368026733,
+      "eval_runtime": 0.3006,
+      "eval_samples_per_second": 149.688,
+      "eval_steps_per_second": 6.653,
+      "step": 78
+    },
+    {
+      "epoch": 24.62,
+      "learning_rate": 6.172839506172839e-06,
+      "loss": 0.2144,
+      "step": 80
+    },
+    {
+      "epoch": 24.92,
+      "eval_accuracy": 0.8444444444444444,
+      "eval_loss": 0.3326983153820038,
+      "eval_runtime": 0.2977,
+      "eval_samples_per_second": 151.157,
+      "eval_steps_per_second": 6.718,
+      "step": 81
+    },
+    {
+      "epoch": 25.85,
+      "eval_accuracy": 0.8444444444444444,
+      "eval_loss": 0.3506452441215515,
+      "eval_runtime": 0.3014,
+      "eval_samples_per_second": 149.324,
+      "eval_steps_per_second": 6.637,
+      "step": 84
+    },
+    {
+      "epoch": 26.77,
+      "eval_accuracy": 0.8444444444444444,
+      "eval_loss": 0.3544660210609436,
+      "eval_runtime": 0.3073,
+      "eval_samples_per_second": 146.433,
+      "eval_steps_per_second": 6.508,
+      "step": 87
+    },
+    {
+      "epoch": 27.69,
+      "learning_rate": 0.0,
+      "loss": 0.1754,
+      "step": 90
+    },
+    {
+      "epoch": 27.69,
+      "eval_accuracy": 0.8444444444444444,
+      "eval_loss": 0.34937629103660583,
+      "eval_runtime": 0.3537,
+      "eval_samples_per_second": 127.228,
+      "eval_steps_per_second": 5.655,
+      "step": 90
+    },
+    {
+      "epoch": 27.69,
+      "step": 90,
+      "total_flos": 2.789665591679447e+17,
+      "train_loss": 0.2528756472799513,
+      "train_runtime": 227.9034,
+      "train_samples_per_second": 53.312,
+      "train_steps_per_second": 0.395
     }
   ],
   "logging_steps": 10,
-  "max_steps": 60,
-  "num_train_epochs": 20,
+  "max_steps": 90,
+  "num_train_epochs": 30,
   "save_steps": 500,
-  "total_flos": 1.8597770611196314e+17,
+  "total_flos": 2.789665591679447e+17,
   "trial_name": null,
   "trial_params": null
 }