End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7254901960784313
+      value: 0.7843137254901961
 ---
 
 <!-- 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 [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7451
-- Accuracy: 0.7255
+- Loss: 0.6623
+- Accuracy: 0.7843
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 11.43,
-    "eval_accuracy": 0.8627450980392157,
-    "eval_loss": 0.5809429883956909,
-    "eval_runtime": 1.0773,
-    "eval_samples_per_second": 47.339,
-    "eval_steps_per_second": 1.856,
-    "train_loss": 0.5459669225745731,
-    "train_runtime": 356.8634,
-    "train_samples_per_second": 67.589,
-    "train_steps_per_second": 0.504
+    "epoch": 11.61,
+    "eval_accuracy": 0.7843137254901961,
+    "eval_loss": 0.662259042263031,
+    "eval_runtime": 1.0269,
+    "eval_samples_per_second": 49.664,
+    "eval_steps_per_second": 1.948,
+    "train_loss": 0.5402387758096059,
+    "train_runtime": 360.9103,
+    "train_samples_per_second": 65.401,
+    "train_steps_per_second": 0.499
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 11.43,
-    "eval_accuracy": 0.8627450980392157,
-    "eval_loss": 0.5809429883956909,
-    "eval_runtime": 1.0773,
-    "eval_samples_per_second": 47.339,
-    "eval_steps_per_second": 1.856
+    "epoch": 11.61,
+    "eval_accuracy": 0.7843137254901961,
+    "eval_loss": 0.662259042263031,
+    "eval_runtime": 1.0269,
+    "eval_samples_per_second": 49.664,
+    "eval_steps_per_second": 1.948
 }

runs/Jun11_15-23-19_DESKTOP-SKBE9FB/events.out.tfevents.1718141549.DESKTOP-SKBE9FB.6016.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9b129bc72976bd7c1e3b2da6c686331fcb9716031d010fbe8ceb12baa104120
+size 411

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 11.43,
-    "train_loss": 0.5459669225745731,
-    "train_runtime": 356.8634,
-    "train_samples_per_second": 67.589,
-    "train_steps_per_second": 0.504
+    "epoch": 11.61,
+    "train_loss": 0.5402387758096059,
+    "train_runtime": 360.9103,
+    "train_samples_per_second": 65.401,
+    "train_steps_per_second": 0.499
 }

trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.8627450980392157,
-  "best_model_checkpoint": "vit-base-patch16-224-ve-U10-12\\checkpoint-94",
-  "epoch": 11.428571428571429,
+  "best_metric": 0.7843137254901961,
+  "best_model_checkpoint": "vit-base-patch16-224-ve-U10-12\\checkpoint-108",
+  "epoch": 11.612903225806452,
   "eval_steps": 500,
   "global_step": 180,
   "is_hyper_param_search": false,
@@ -9,229 +9,229 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.63,
+      "epoch": 0.65,
       "learning_rate": 5.467836257309941e-05,
-      "loss": 1.3634,
+      "loss": 1.3659,
       "step": 10
     },
     {
-      "epoch": 0.95,
-      "eval_accuracy": 0.49019607843137253,
-      "eval_loss": 1.228261113166809,
-      "eval_runtime": 0.912,
-      "eval_samples_per_second": 55.923,
-      "eval_steps_per_second": 2.193,
+      "epoch": 0.97,
+      "eval_accuracy": 0.47058823529411764,
+      "eval_loss": 1.2287312746047974,
+      "eval_runtime": 0.9667,
+      "eval_samples_per_second": 52.757,
+      "eval_steps_per_second": 2.069,
       "step": 15
     },
     {
-      "epoch": 1.27,
+      "epoch": 1.29,
       "learning_rate": 5.1461988304093566e-05,
-      "loss": 1.2422,
+      "loss": 1.2407,
       "step": 20
     },
     {
-      "epoch": 1.9,
+      "epoch": 1.94,
       "learning_rate": 4.824561403508772e-05,
-      "loss": 1.099,
+      "loss": 1.1063,
       "step": 30
     },
     {
-      "epoch": 1.97,
-      "eval_accuracy": 0.6274509803921569,
-      "eval_loss": 1.009804606437683,
-      "eval_runtime": 0.7828,
-      "eval_samples_per_second": 65.149,
-      "eval_steps_per_second": 2.555,
+      "epoch": 2.0,
+      "eval_accuracy": 0.6862745098039216,
+      "eval_loss": 1.0233995914459229,
+      "eval_runtime": 0.8689,
+      "eval_samples_per_second": 58.697,
+      "eval_steps_per_second": 2.302,
       "step": 31
     },
     {
-      "epoch": 2.54,
+      "epoch": 2.58,
       "learning_rate": 4.502923976608187e-05,
-      "loss": 0.9373,
+      "loss": 0.9468,
       "step": 40
     },
     {
-      "epoch": 2.98,
-      "eval_accuracy": 0.6666666666666666,
-      "eval_loss": 0.8729690909385681,
-      "eval_runtime": 0.7821,
-      "eval_samples_per_second": 65.206,
-      "eval_steps_per_second": 2.557,
-      "step": 47
+      "epoch": 2.97,
+      "eval_accuracy": 0.6862745098039216,
+      "eval_loss": 0.8665008544921875,
+      "eval_runtime": 0.8118,
+      "eval_samples_per_second": 62.826,
+      "eval_steps_per_second": 2.464,
+      "step": 46
     },
     {
-      "epoch": 3.17,
+      "epoch": 3.23,
       "learning_rate": 4.1812865497076025e-05,
-      "loss": 0.8023,
+      "loss": 0.8276,
       "step": 50
     },
     {
-      "epoch": 3.81,
+      "epoch": 3.87,
       "learning_rate": 3.859649122807018e-05,
-      "loss": 0.7066,
+      "loss": 0.6825,
       "step": 60
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.803921568627451,
-      "eval_loss": 0.6674012541770935,
-      "eval_runtime": 0.7999,
-      "eval_samples_per_second": 63.759,
-      "eval_steps_per_second": 2.5,
-      "step": 63
+      "eval_accuracy": 0.7058823529411765,
+      "eval_loss": 0.7481548190116882,
+      "eval_runtime": 0.7724,
+      "eval_samples_per_second": 66.031,
+      "eval_steps_per_second": 2.589,
+      "step": 62
     },
     {
-      "epoch": 4.44,
+      "epoch": 4.52,
       "learning_rate": 3.5380116959064324e-05,
-      "loss": 0.6035,
+      "loss": 0.5534,
       "step": 70
     },
     {
-      "epoch": 4.95,
-      "eval_accuracy": 0.7647058823529411,
-      "eval_loss": 0.6062445044517517,
-      "eval_runtime": 0.7697,
-      "eval_samples_per_second": 66.263,
-      "eval_steps_per_second": 2.599,
-      "step": 78
+      "epoch": 4.97,
+      "eval_accuracy": 0.7058823529411765,
+      "eval_loss": 0.7608624696731567,
+      "eval_runtime": 0.8338,
+      "eval_samples_per_second": 61.167,
+      "eval_steps_per_second": 2.399,
+      "step": 77
     },
     {
-      "epoch": 5.08,
+      "epoch": 5.16,
       "learning_rate": 3.216374269005848e-05,
-      "loss": 0.5052,
+      "loss": 0.4733,
       "step": 80
     },
     {
-      "epoch": 5.71,
+      "epoch": 5.81,
       "learning_rate": 2.894736842105263e-05,
-      "loss": 0.4011,
+      "loss": 0.4019,
       "step": 90
     },
     {
-      "epoch": 5.97,
-      "eval_accuracy": 0.8627450980392157,
-      "eval_loss": 0.5809429883956909,
-      "eval_runtime": 0.7759,
-      "eval_samples_per_second": 65.729,
-      "eval_steps_per_second": 2.578,
-      "step": 94
+      "epoch": 6.0,
+      "eval_accuracy": 0.7254901960784313,
+      "eval_loss": 0.7092276215553284,
+      "eval_runtime": 0.7947,
+      "eval_samples_per_second": 64.177,
+      "eval_steps_per_second": 2.517,
+      "step": 93
     },
     {
-      "epoch": 6.35,
+      "epoch": 6.45,
       "learning_rate": 2.5730994152046783e-05,
-      "loss": 0.3438,
+      "loss": 0.3323,
       "step": 100
     },
     {
-      "epoch": 6.98,
-      "learning_rate": 2.2514619883040936e-05,
-      "loss": 0.2799,
-      "step": 110
+      "epoch": 6.97,
+      "eval_accuracy": 0.7843137254901961,
+      "eval_loss": 0.662259042263031,
+      "eval_runtime": 0.7839,
+      "eval_samples_per_second": 65.057,
+      "eval_steps_per_second": 2.551,
+      "step": 108
     },
     {
-      "epoch": 6.98,
-      "eval_accuracy": 0.803921568627451,
-      "eval_loss": 0.623532235622406,
-      "eval_runtime": 0.8145,
-      "eval_samples_per_second": 62.613,
-      "eval_steps_per_second": 2.455,
+      "epoch": 7.1,
+      "learning_rate": 2.2514619883040936e-05,
+      "loss": 0.2759,
       "step": 110
     },
     {
-      "epoch": 7.62,
+      "epoch": 7.74,
       "learning_rate": 1.929824561403509e-05,
-      "loss": 0.2572,
+      "loss": 0.2743,
       "step": 120
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.7647058823529411,
-      "eval_loss": 0.669582724571228,
-      "eval_runtime": 0.778,
-      "eval_samples_per_second": 65.555,
-      "eval_steps_per_second": 2.571,
-      "step": 126
+      "eval_accuracy": 0.7058823529411765,
+      "eval_loss": 0.7407493591308594,
+      "eval_runtime": 0.7753,
+      "eval_samples_per_second": 65.783,
+      "eval_steps_per_second": 2.58,
+      "step": 124
     },
     {
-      "epoch": 8.25,
+      "epoch": 8.39,
       "learning_rate": 1.608187134502924e-05,
-      "loss": 0.2402,
+      "loss": 0.2411,
       "step": 130
     },
     {
-      "epoch": 8.89,
-      "learning_rate": 1.2865497076023392e-05,
-      "loss": 0.2384,
-      "step": 140
+      "epoch": 8.97,
+      "eval_accuracy": 0.7647058823529411,
+      "eval_loss": 0.6248741745948792,
+      "eval_runtime": 0.8159,
+      "eval_samples_per_second": 62.507,
+      "eval_steps_per_second": 2.451,
+      "step": 139
     },
     {
-      "epoch": 8.95,
-      "eval_accuracy": 0.7647058823529411,
-      "eval_loss": 0.6868889927864075,
-      "eval_runtime": 0.7916,
-      "eval_samples_per_second": 64.426,
-      "eval_steps_per_second": 2.526,
-      "step": 141
+      "epoch": 9.03,
+      "learning_rate": 1.2865497076023392e-05,
+      "loss": 0.2379,
+      "step": 140
     },
     {
-      "epoch": 9.52,
+      "epoch": 9.68,
       "learning_rate": 9.649122807017545e-06,
-      "loss": 0.2104,
+      "loss": 0.2021,
       "step": 150
     },
     {
-      "epoch": 9.97,
-      "eval_accuracy": 0.7254901960784313,
-      "eval_loss": 0.7198700308799744,
-      "eval_runtime": 0.7795,
-      "eval_samples_per_second": 65.43,
-      "eval_steps_per_second": 2.566,
-      "step": 157
+      "epoch": 10.0,
+      "eval_accuracy": 0.7450980392156863,
+      "eval_loss": 0.7221617102622986,
+      "eval_runtime": 0.7603,
+      "eval_samples_per_second": 67.081,
+      "eval_steps_per_second": 2.631,
+      "step": 155
     },
     {
-      "epoch": 10.16,
+      "epoch": 10.32,
       "learning_rate": 6.432748538011696e-06,
-      "loss": 0.2159,
+      "loss": 0.195,
       "step": 160
     },
     {
-      "epoch": 10.79,
+      "epoch": 10.97,
       "learning_rate": 3.216374269005848e-06,
-      "loss": 0.1894,
+      "loss": 0.1925,
       "step": 170
     },
     {
-      "epoch": 10.98,
-      "eval_accuracy": 0.8431372549019608,
-      "eval_loss": 0.5567971467971802,
-      "eval_runtime": 0.7722,
-      "eval_samples_per_second": 66.043,
-      "eval_steps_per_second": 2.59,
-      "step": 173
+      "epoch": 10.97,
+      "eval_accuracy": 0.7058823529411765,
+      "eval_loss": 0.7807687520980835,
+      "eval_runtime": 0.7671,
+      "eval_samples_per_second": 66.482,
+      "eval_steps_per_second": 2.607,
+      "step": 170
     },
     {
-      "epoch": 11.43,
+      "epoch": 11.61,
       "learning_rate": 0.0,
-      "loss": 0.1917,
+      "loss": 0.1748,
       "step": 180
     },
     {
-      "epoch": 11.43,
-      "eval_accuracy": 0.8431372549019608,
-      "eval_loss": 0.5610877275466919,
-      "eval_runtime": 0.7721,
-      "eval_samples_per_second": 66.054,
-      "eval_steps_per_second": 2.59,
+      "epoch": 11.61,
+      "eval_accuracy": 0.7254901960784313,
+      "eval_loss": 0.7451220750808716,
+      "eval_runtime": 0.7609,
+      "eval_samples_per_second": 67.03,
+      "eval_steps_per_second": 2.629,
       "step": 180
     },
     {
-      "epoch": 11.43,
+      "epoch": 11.61,
       "step": 180,
-      "total_flos": 1.7803328819545866e+18,
-      "train_loss": 0.5459669225745731,
-      "train_runtime": 356.8634,
-      "train_samples_per_second": 67.589,
-      "train_steps_per_second": 0.504
+      "total_flos": 1.7709561831334625e+18,
+      "train_loss": 0.5402387758096059,
+      "train_runtime": 360.9103,
+      "train_samples_per_second": 65.401,
+      "train_steps_per_second": 0.499
     }
   ],
   "logging_steps": 10,
@@ -239,7 +239,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 12,
   "save_steps": 500,
-  "total_flos": 1.7803328819545866e+18,
+  "total_flos": 1.7709561831334625e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null