🍻 cheers

README.md

@@ -2,6 +2,7 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
 - generated_from_trainer
 metrics:
 - accuracy
@@ -15,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # food-recognition
 
-This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the indian_food_images dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.6230
-- Accuracy: 0.4518
+- Loss: 4.0433
+- Accuracy: 0.4436
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 4.0,
-    "eval_accuracy": 1.0,
-    "eval_loss": 3.4838707447052,
-    "eval_runtime": 1.3666,
-    "eval_samples_per_second": 3.659,
-    "eval_steps_per_second": 0.732,
-    "train_loss": 3.7712278366088867,
-    "train_runtime": 16.7176,
-    "train_samples_per_second": 1.196,
-    "train_steps_per_second": 0.239
+    "eval_accuracy": 0.44363636363636366,
+    "eval_loss": 4.043280601501465,
+    "eval_runtime": 282.0238,
+    "eval_samples_per_second": 3.9,
+    "eval_steps_per_second": 0.489,
+    "train_loss": 0.386546674683906,
+    "train_runtime": 3742.8868,
+    "train_samples_per_second": 1.176,
+    "train_steps_per_second": 0.074
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
-    "eval_accuracy": 1.0,
-    "eval_loss": 3.4838707447052,
-    "eval_runtime": 1.3666,
-    "eval_samples_per_second": 3.659,
-    "eval_steps_per_second": 0.732
+    "eval_accuracy": 0.44363636363636366,
+    "eval_loss": 4.043280601501465,
+    "eval_runtime": 282.0238,
+    "eval_samples_per_second": 3.9,
+    "eval_steps_per_second": 0.489
 }

runs/Dec04_13-31-59_LAPTOP-PH299HA6/events.out.tfevents.1701675975.LAPTOP-PH299HA6.21992.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a210a038a59acf9e315c154c1188d0b04d6164d66e133c21456a2b9bd16774b8
+size 363

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 4.0,
-    "train_loss": 3.7712278366088867,
-    "train_runtime": 16.7176,
-    "train_samples_per_second": 1.196,
-    "train_steps_per_second": 0.239
+    "train_loss": 0.386546674683906,
+    "train_runtime": 3742.8868,
+    "train_samples_per_second": 1.176,
+    "train_steps_per_second": 0.074
 }

trainer_state.json

@@ -1,28 +1,208 @@
 {
-  "best_metric": null,
-  "best_model_checkpoint": null,
+  "best_metric": 4.043280601501465,
+  "best_model_checkpoint": "food-recognition\\checkpoint-100",
   "epoch": 4.0,
   "eval_steps": 100,
-  "global_step": 4,
+  "global_step": 276,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0001927536231884058,
+      "loss": 3.2682,
+      "step": 10
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0001855072463768116,
+      "loss": 1.8646,
+      "step": 20
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0001782608695652174,
+      "loss": 1.287,
+      "step": 30
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0001710144927536232,
+      "loss": 0.9426,
+      "step": 40
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.000163768115942029,
+      "loss": 0.7407,
+      "step": 50
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0001565217391304348,
+      "loss": 0.5816,
+      "step": 60
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00014927536231884058,
+      "loss": 0.4059,
+      "step": 70
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00014202898550724638,
+      "loss": 0.27,
+      "step": 80
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0001347826086956522,
+      "loss": 0.1798,
+      "step": 90
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00012753623188405797,
+      "loss": 0.1598,
+      "step": 100
+    },
+    {
+      "epoch": 1.45,
+      "eval_accuracy": 0.44363636363636366,
+      "eval_loss": 4.043280601501465,
+      "eval_runtime": 278.9851,
+      "eval_samples_per_second": 3.943,
+      "eval_steps_per_second": 0.495,
+      "step": 100
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00012028985507246378,
+      "loss": 0.1136,
+      "step": 110
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.00011304347826086956,
+      "loss": 0.1096,
+      "step": 120
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00010579710144927538,
+      "loss": 0.0863,
+      "step": 130
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 9.855072463768117e-05,
+      "loss": 0.0664,
+      "step": 140
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 9.130434782608696e-05,
+      "loss": 0.0865,
+      "step": 150
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 8.405797101449276e-05,
+      "loss": 0.0441,
+      "step": 160
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 7.681159420289855e-05,
+      "loss": 0.0509,
+      "step": 170
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 6.956521739130436e-05,
+      "loss": 0.0412,
+      "step": 180
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 6.231884057971015e-05,
+      "loss": 0.0701,
+      "step": 190
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 5.507246376811594e-05,
+      "loss": 0.038,
+      "step": 200
+    },
+    {
+      "epoch": 2.9,
+      "eval_accuracy": 0.45181818181818184,
+      "eval_loss": 4.6229705810546875,
+      "eval_runtime": 289.4417,
+      "eval_samples_per_second": 3.8,
+      "eval_steps_per_second": 0.477,
+      "step": 200
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 4.782608695652174e-05,
+      "loss": 0.0318,
+      "step": 210
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 4.057971014492754e-05,
+      "loss": 0.0318,
+      "step": 220
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.0471,
+      "step": 230
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 2.608695652173913e-05,
+      "loss": 0.028,
+      "step": 240
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 1.8840579710144928e-05,
+      "loss": 0.0272,
+      "step": 250
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 1.1594202898550725e-05,
+      "loss": 0.0266,
+      "step": 260
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 0.0532,
+      "step": 270
+    },
     {
       "epoch": 4.0,
-      "step": 4,
-      "total_flos": 1551214973952000.0,
-      "train_loss": 3.7712278366088867,
-      "train_runtime": 16.7176,
-      "train_samples_per_second": 1.196,
-      "train_steps_per_second": 0.239
+      "step": 276,
+      "total_flos": 3.4126729426944e+17,
+      "train_loss": 0.386546674683906,
+      "train_runtime": 3742.8868,
+      "train_samples_per_second": 1.176,
+      "train_steps_per_second": 0.074
     }
   ],
   "logging_steps": 10,
-  "max_steps": 4,
+  "max_steps": 276,
   "num_train_epochs": 4,
   "save_steps": 100,
-  "total_flos": 1551214973952000.0,
+  "total_flos": 3.4126729426944e+17,
   "trial_name": null,
   "trial_params": null
 }