🍻 cheers

README.md

@@ -2,7 +2,11 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
+- vision
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: vit-base-beans
   results: []
@@ -13,7 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-base-beans
 
-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 beans dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0158
+- Accuracy: 1.0
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 4.0,
     "eval_accuracy": 1.0,
-    "eval_loss": 0.01724555343389511,
-    "eval_runtime": 2.9509,
-    "eval_samples_per_second": 29.822,
-    "eval_steps_per_second": 3.728,
-    "total_flos": 2.7277180344336384e+16,
-    "train_loss": 0.29457727345553314,
-    "train_runtime": 29.6451,
-    "train_samples_per_second": 11.874,
-    "train_steps_per_second": 2.968
+    "eval_loss": 0.015804477035999298,
+    "eval_runtime": 2.4811,
+    "eval_samples_per_second": 33.05,
+    "eval_steps_per_second": 4.433,
+    "total_flos": 2.5417372593586176e+16,
+    "train_loss": 0.22665784472510928,
+    "train_runtime": 28.7006,
+    "train_samples_per_second": 11.428,
+    "train_steps_per_second": 2.927
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "eval_accuracy": 1.0,
-    "eval_loss": 0.01724555343389511,
-    "eval_runtime": 2.9509,
-    "eval_samples_per_second": 29.822,
-    "eval_steps_per_second": 3.728
+    "eval_loss": 0.015804477035999298,
+    "eval_runtime": 2.4811,
+    "eval_samples_per_second": 33.05,
+    "eval_steps_per_second": 4.433
 }

runs/Aug30_08-59-56_7e2de4304170/events.out.tfevents.1725008448.7e2de4304170

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee6cd84f5103fa598b7e1860dc7f5cbc6187a4a5ba54ec4de32f3ea68fc1810f
+size 40

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
-    "total_flos": 2.7277180344336384e+16,
-    "train_loss": 0.29457727345553314,
-    "train_runtime": 29.6451,
-    "train_samples_per_second": 11.874,
-    "train_steps_per_second": 2.968
+    "total_flos": 2.5417372593586176e+16,
+    "train_loss": 0.22665784472510928,
+    "train_runtime": 28.7006,
+    "train_samples_per_second": 11.428,
+    "train_steps_per_second": 2.927
 }

trainer_state.json

@@ -3,79 +3,79 @@
   "best_model_checkpoint": null,
   "epoch": 4.0,
   "eval_steps": 100,
-  "global_step": 88,
+  "global_step": 84,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.45454545454545453,
-      "grad_norm": 2.2645957469940186,
-      "learning_rate": 0.00017727272727272728,
-      "loss": 0.5609,
+      "epoch": 0.47619047619047616,
+      "grad_norm": 3.3773086071014404,
+      "learning_rate": 0.0001761904761904762,
+      "loss": 0.6171,
       "step": 10
     },
     {
-      "epoch": 0.9090909090909091,
-      "grad_norm": 3.18221116065979,
-      "learning_rate": 0.00015454545454545454,
-      "loss": 0.8267,
+      "epoch": 0.9523809523809523,
+      "grad_norm": 4.038491249084473,
+      "learning_rate": 0.00015238095238095237,
+      "loss": 0.4746,
       "step": 20
     },
     {
-      "epoch": 1.3636363636363638,
-      "grad_norm": 3.1673595905303955,
-      "learning_rate": 0.0001318181818181818,
-      "loss": 0.5182,
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.7119430899620056,
+      "learning_rate": 0.00012857142857142858,
+      "loss": 0.2603,
       "step": 30
     },
     {
-      "epoch": 1.8181818181818183,
-      "grad_norm": 0.5910093784332275,
-      "learning_rate": 0.00010909090909090909,
-      "loss": 0.2435,
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.4082745611667633,
+      "learning_rate": 0.00010476190476190477,
+      "loss": 0.2766,
       "step": 40
     },
     {
-      "epoch": 2.2727272727272725,
-      "grad_norm": 3.6887409687042236,
-      "learning_rate": 8.636363636363637e-05,
-      "loss": 0.2545,
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.17519672214984894,
+      "learning_rate": 8.095238095238096e-05,
+      "loss": 0.1537,
       "step": 50
     },
     {
-      "epoch": 2.7272727272727275,
-      "grad_norm": 0.7244749665260315,
-      "learning_rate": 6.363636363636364e-05,
-      "loss": 0.1302,
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.1577773243188858,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 0.0797,
       "step": 60
     },
     {
-      "epoch": 3.1818181818181817,
-      "grad_norm": 0.1487322300672531,
-      "learning_rate": 4.0909090909090915e-05,
-      "loss": 0.0252,
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.12391568720340729,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.0181,
       "step": 70
     },
     {
-      "epoch": 3.6363636363636362,
-      "grad_norm": 0.1414584219455719,
-      "learning_rate": 1.8181818181818182e-05,
-      "loss": 0.0192,
+      "epoch": 3.8095238095238093,
+      "grad_norm": 0.28916484117507935,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 0.0173,
       "step": 80
     },
     {
       "epoch": 4.0,
-      "step": 88,
-      "total_flos": 2.7277180344336384e+16,
-      "train_loss": 0.29457727345553314,
-      "train_runtime": 29.6451,
-      "train_samples_per_second": 11.874,
-      "train_steps_per_second": 2.968
+      "step": 84,
+      "total_flos": 2.5417372593586176e+16,
+      "train_loss": 0.22665784472510928,
+      "train_runtime": 28.7006,
+      "train_samples_per_second": 11.428,
+      "train_steps_per_second": 2.927
     }
   ],
   "logging_steps": 10,
-  "max_steps": 88,
+  "max_steps": 84,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 100,
@@ -91,7 +91,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.7277180344336384e+16,
+  "total_flos": 2.5417372593586176e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null