End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7450980392156863
+      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: 0.6647
-- Accuracy: 0.7451
+- Loss: 0.6632
+- Accuracy: 0.7843
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 11.61,
+    "epoch": 11.43,
     "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_loss": 0.6632380485534668,
+    "eval_runtime": 1.0573,
+    "eval_samples_per_second": 48.238,
+    "eval_steps_per_second": 1.892,
+    "train_loss": 0.5450452705224355,
+    "train_runtime": 382.131,
+    "train_samples_per_second": 63.12,
+    "train_steps_per_second": 0.471
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 11.61,
+    "epoch": 11.43,
     "eval_accuracy": 0.7843137254901961,
-    "eval_loss": 0.662259042263031,
-    "eval_runtime": 1.0269,
-    "eval_samples_per_second": 49.664,
-    "eval_steps_per_second": 1.948
+    "eval_loss": 0.6632380485534668,
+    "eval_runtime": 1.0573,
+    "eval_samples_per_second": 48.238,
+    "eval_steps_per_second": 1.892
 }

runs/Jun11_16-10-07_DESKTOP-SKBE9FB/events.out.tfevents.1718144279.DESKTOP-SKBE9FB.7192.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21c2bfd68cc9fffeb13536d5887d39f757ddb29022b6edbc32c7d7653772989f
+size 411

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 11.61,
-    "train_loss": 0.5402387758096059,
-    "train_runtime": 360.9103,
-    "train_samples_per_second": 65.401,
-    "train_steps_per_second": 0.499
+    "epoch": 11.43,
+    "train_loss": 0.5450452705224355,
+    "train_runtime": 382.131,
+    "train_samples_per_second": 63.12,
+    "train_steps_per_second": 0.471
 }

trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": 0.7843137254901961,
-  "best_model_checkpoint": "vit-base-patch16-224-ve-U10-12\\checkpoint-108",
-  "epoch": 11.612903225806452,
+  "best_model_checkpoint": "vit-base-patch16-224-ve-U10-12\\checkpoint-141",
+  "epoch": 11.428571428571429,
   "eval_steps": 500,
   "global_step": 180,
   "is_hyper_param_search": false,
@@ -9,229 +9,229 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.65,
+      "epoch": 0.63,
       "learning_rate": 5.467836257309941e-05,
-      "loss": 1.3659,
+      "loss": 1.3629,
       "step": 10
     },
     {
-      "epoch": 0.97,
+      "epoch": 0.95,
       "eval_accuracy": 0.47058823529411764,
-      "eval_loss": 1.2287312746047974,
-      "eval_runtime": 0.9667,
-      "eval_samples_per_second": 52.757,
-      "eval_steps_per_second": 2.069,
+      "eval_loss": 1.2289341688156128,
+      "eval_runtime": 0.8291,
+      "eval_samples_per_second": 61.515,
+      "eval_steps_per_second": 2.412,
       "step": 15
     },
     {
-      "epoch": 1.29,
+      "epoch": 1.27,
       "learning_rate": 5.1461988304093566e-05,
-      "loss": 1.2407,
+      "loss": 1.2419,
       "step": 20
     },
     {
-      "epoch": 1.94,
+      "epoch": 1.9,
       "learning_rate": 4.824561403508772e-05,
-      "loss": 1.1063,
+      "loss": 1.1038,
       "step": 30
     },
     {
-      "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,
+      "epoch": 1.97,
+      "eval_accuracy": 0.5882352941176471,
+      "eval_loss": 1.041306734085083,
+      "eval_runtime": 0.8646,
+      "eval_samples_per_second": 58.985,
+      "eval_steps_per_second": 2.313,
       "step": 31
     },
     {
-      "epoch": 2.58,
+      "epoch": 2.54,
       "learning_rate": 4.502923976608187e-05,
-      "loss": 0.9468,
+      "loss": 0.9375,
       "step": 40
     },
     {
-      "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": 2.98,
+      "eval_accuracy": 0.5882352941176471,
+      "eval_loss": 0.8989145755767822,
+      "eval_runtime": 0.8079,
+      "eval_samples_per_second": 63.128,
+      "eval_steps_per_second": 2.476,
+      "step": 47
     },
     {
-      "epoch": 3.23,
+      "epoch": 3.17,
       "learning_rate": 4.1812865497076025e-05,
-      "loss": 0.8276,
+      "loss": 0.7972,
       "step": 50
     },
     {
-      "epoch": 3.87,
+      "epoch": 3.81,
       "learning_rate": 3.859649122807018e-05,
-      "loss": 0.6825,
+      "loss": 0.6917,
       "step": 60
     },
     {
       "epoch": 4.0,
       "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
+      "eval_loss": 0.8519924283027649,
+      "eval_runtime": 0.8135,
+      "eval_samples_per_second": 62.692,
+      "eval_steps_per_second": 2.459,
+      "step": 63
     },
     {
-      "epoch": 4.52,
+      "epoch": 4.44,
       "learning_rate": 3.5380116959064324e-05,
-      "loss": 0.5534,
+      "loss": 0.5862,
       "step": 70
     },
     {
-      "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": 4.95,
+      "eval_accuracy": 0.7254901960784313,
+      "eval_loss": 0.6827210783958435,
+      "eval_runtime": 0.8863,
+      "eval_samples_per_second": 57.54,
+      "eval_steps_per_second": 2.256,
+      "step": 78
     },
     {
-      "epoch": 5.16,
+      "epoch": 5.08,
       "learning_rate": 3.216374269005848e-05,
-      "loss": 0.4733,
+      "loss": 0.5063,
       "step": 80
     },
     {
-      "epoch": 5.81,
+      "epoch": 5.71,
       "learning_rate": 2.894736842105263e-05,
-      "loss": 0.4019,
+      "loss": 0.4042,
       "step": 90
     },
     {
-      "epoch": 6.0,
+      "epoch": 5.97,
       "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
+      "eval_loss": 0.728096067905426,
+      "eval_runtime": 0.8825,
+      "eval_samples_per_second": 57.792,
+      "eval_steps_per_second": 2.266,
+      "step": 94
     },
     {
-      "epoch": 6.45,
+      "epoch": 6.35,
       "learning_rate": 2.5730994152046783e-05,
-      "loss": 0.3323,
+      "loss": 0.3605,
       "step": 100
     },
     {
-      "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,
+      "learning_rate": 2.2514619883040936e-05,
+      "loss": 0.2987,
+      "step": 110
     },
     {
-      "epoch": 7.1,
-      "learning_rate": 2.2514619883040936e-05,
-      "loss": 0.2759,
+      "epoch": 6.98,
+      "eval_accuracy": 0.7647058823529411,
+      "eval_loss": 0.7262123823165894,
+      "eval_runtime": 0.849,
+      "eval_samples_per_second": 60.074,
+      "eval_steps_per_second": 2.356,
       "step": 110
     },
     {
-      "epoch": 7.74,
+      "epoch": 7.62,
       "learning_rate": 1.929824561403509e-05,
-      "loss": 0.2743,
+      "loss": 0.2571,
       "step": 120
     },
     {
       "epoch": 8.0,
-      "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
+      "eval_accuracy": 0.7254901960784313,
+      "eval_loss": 0.7603896856307983,
+      "eval_runtime": 0.8862,
+      "eval_samples_per_second": 57.552,
+      "eval_steps_per_second": 2.257,
+      "step": 126
     },
     {
-      "epoch": 8.39,
+      "epoch": 8.25,
       "learning_rate": 1.608187134502924e-05,
-      "loss": 0.2411,
+      "loss": 0.249,
       "step": 130
     },
     {
-      "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": 9.03,
+      "epoch": 8.89,
       "learning_rate": 1.2865497076023392e-05,
-      "loss": 0.2379,
+      "loss": 0.2326,
       "step": 140
     },
     {
-      "epoch": 9.68,
+      "epoch": 8.95,
+      "eval_accuracy": 0.7843137254901961,
+      "eval_loss": 0.6632380485534668,
+      "eval_runtime": 0.7605,
+      "eval_samples_per_second": 67.061,
+      "eval_steps_per_second": 2.63,
+      "step": 141
+    },
+    {
+      "epoch": 9.52,
       "learning_rate": 9.649122807017545e-06,
-      "loss": 0.2021,
+      "loss": 0.1994,
       "step": 150
     },
     {
-      "epoch": 10.0,
+      "epoch": 9.97,
       "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
+      "eval_loss": 0.6744426488876343,
+      "eval_runtime": 0.8645,
+      "eval_samples_per_second": 58.993,
+      "eval_steps_per_second": 2.313,
+      "step": 157
     },
     {
-      "epoch": 10.32,
+      "epoch": 10.16,
       "learning_rate": 6.432748538011696e-06,
-      "loss": 0.195,
+      "loss": 0.2004,
       "step": 160
     },
     {
-      "epoch": 10.97,
+      "epoch": 10.79,
       "learning_rate": 3.216374269005848e-06,
-      "loss": 0.1925,
+      "loss": 0.1968,
       "step": 170
     },
     {
-      "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": 10.98,
+      "eval_accuracy": 0.7450980392156863,
+      "eval_loss": 0.6864146590232849,
+      "eval_runtime": 0.7962,
+      "eval_samples_per_second": 64.055,
+      "eval_steps_per_second": 2.512,
+      "step": 173
     },
     {
-      "epoch": 11.61,
+      "epoch": 11.43,
       "learning_rate": 0.0,
-      "loss": 0.1748,
+      "loss": 0.1847,
       "step": 180
     },
     {
-      "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,
+      "epoch": 11.43,
+      "eval_accuracy": 0.7450980392156863,
+      "eval_loss": 0.6646667122840881,
+      "eval_runtime": 0.7818,
+      "eval_samples_per_second": 65.235,
+      "eval_steps_per_second": 2.558,
       "step": 180
     },
     {
-      "epoch": 11.61,
+      "epoch": 11.43,
       "step": 180,
-      "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
+      "total_flos": 1.7803328819545866e+18,
+      "train_loss": 0.5450452705224355,
+      "train_runtime": 382.131,
+      "train_samples_per_second": 63.12,
+      "train_steps_per_second": 0.471
     }
   ],
   "logging_steps": 10,
@@ -239,7 +239,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 12,
   "save_steps": 500,
-  "total_flos": 1.7709561831334625e+18,
+  "total_flos": 1.7803328819545866e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null