🍻 cheers

README.md

@@ -1,10 +1,14 @@
 ---
-license: apache-2.0
-base_model: google/vit-base-patch16-224-in21k
+base_model: d071696/vit-base-scraps
 tags:
+- image-classification
+- image-feature-extraction
+- image-to-text
 - generated_from_trainer
 datasets:
 - imagefolder
+metrics:
+- accuracy
 model-index:
 - name: vit-finetune-scrap
   results: []
@@ -15,7 +19,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-finetune-scrap
 
-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 imagefolder dataset.
+This model is a fine-tuned version of [d071696/vit-base-scraps](https://huggingface.co/d071696/vit-base-scraps) on the d071696/scraps1 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9564
+- Accuracy: 0.9
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 4.0,
-    "eval_accuracy": 1.0,
-    "eval_loss": 1.9239758253097534,
-    "eval_runtime": 1.3618,
-    "eval_samples_per_second": 22.029,
-    "eval_steps_per_second": 2.937,
+    "eval_accuracy": 0.9,
+    "eval_loss": 1.9563813209533691,
+    "eval_runtime": 1.2863,
+    "eval_samples_per_second": 23.323,
+    "eval_steps_per_second": 3.11,
     "total_flos": 9299872197181440.0,
-    "train_loss": 2.1698924899101257,
-    "train_runtime": 8.7843,
-    "train_samples_per_second": 13.661,
-    "train_steps_per_second": 1.821
+    "train_loss": 2.19787335395813,
+    "train_runtime": 9.3738,
+    "train_samples_per_second": 12.802,
+    "train_steps_per_second": 1.707
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
-    "eval_accuracy": 1.0,
-    "eval_loss": 1.9239758253097534,
-    "eval_runtime": 1.3618,
-    "eval_samples_per_second": 22.029,
-    "eval_steps_per_second": 2.937
+    "eval_accuracy": 0.9,
+    "eval_loss": 1.9563813209533691,
+    "eval_runtime": 1.2863,
+    "eval_samples_per_second": 23.323,
+    "eval_steps_per_second": 3.11
 }

runs/Mar22_10-27-06_X5C922065N/events.out.tfevents.1711099662.X5C922065N.86888.18

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37478166438963b122df771630a3aa50514282adaf4c77f58bbb6ff302ac404e
+size 405

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "total_flos": 9299872197181440.0,
-    "train_loss": 2.1698924899101257,
-    "train_runtime": 8.7843,
-    "train_samples_per_second": 13.661,
-    "train_steps_per_second": 1.821
+    "train_loss": 2.19787335395813,
+    "train_runtime": 9.3738,
+    "train_samples_per_second": 12.802,
+    "train_steps_per_second": 1.707
 }

trainer_state.json

@@ -10,19 +10,19 @@
   "log_history": [
     {
       "epoch": 2.5,
-      "grad_norm": 2.7402358055114746,
+      "grad_norm": 2.5156421661376953,
       "learning_rate": 1.8750000000000002e-05,
-      "loss": 2.28,
+      "loss": 2.3138,
       "step": 10
     },
     {
       "epoch": 4.0,
       "step": 16,
       "total_flos": 9299872197181440.0,
-      "train_loss": 2.1698924899101257,
-      "train_runtime": 8.7843,
-      "train_samples_per_second": 13.661,
-      "train_steps_per_second": 1.821
+      "train_loss": 2.19787335395813,
+      "train_runtime": 9.3738,
+      "train_samples_per_second": 12.802,
+      "train_steps_per_second": 1.707
     }
   ],
   "logging_steps": 10,