Model save

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: vikas117/finetuned-ai-real
+base_model: google/vit-large-patch16-224
 tags:
 - generated_from_trainer
 datasets:
@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8842975206611571
+      value: 0.9173553719008265
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # finetuned-ai-real
 
-This model is a fine-tuned version of [vikas117/finetuned-ai-real](https://huggingface.co/vikas117/finetuned-ai-real) on the imagefolder dataset.
+This model is a fine-tuned version of [google/vit-large-patch16-224](https://huggingface.co/google/vit-large-patch16-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2323
-- Accuracy: 0.8843
+- Loss: 0.3759
+- Accuracy: 0.9174
 
 ## Model description
 
@@ -59,15 +59,14 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 4
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 0.1995        | 2.2727 | 50   | 0.2829          | 0.8843   |
-| 0.2106        | 4.5455 | 100  | 0.2323          | 0.8843   |
+| 0.068         | 2.2727 | 50   | 0.3759          | 0.9174   |
 
 
 ### Framework versions

config.json

@@ -1,44 +1,29 @@
 {
-  "_name_or_path": "vikas117/finetuned-ai-real",
+  "_name_or_path": "google/vit-large-patch16-224",
   "architectures": [
     "ViTForImageClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
-  "depths": [
-    3,
-    8,
-    36,
-    3
-  ],
-  "downsample_in_first_stage": false,
-  "embedding_size": 64,
   "encoder_stride": 16,
-  "hidden_act": "relu",
+  "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
-  "hidden_size": 768,
-  "hidden_sizes": [
-    256,
-    512,
-    1024,
-    2048
-  ],
+  "hidden_size": 1024,
   "id2label": {
     "0": "AI",
     "1": "Real"
   },
   "image_size": 224,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "AI": "0",
     "Real": "1"
   },
   "layer_norm_eps": 1e-12,
-  "layer_type": "bottleneck",
   "model_type": "vit",
-  "num_attention_heads": 12,
+  "num_attention_heads": 16,
   "num_channels": 3,
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 24,
   "patch_size": 16,
   "problem_type": "single_label_classification",
   "qkv_bias": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab05b278e596869f216e30119c89da42979ecf48bd22071b3f7800e022328188
-size 343223968
+oid sha256:d5805fb053fda7d9ca3beafa9755ce0ead1c3731d86f1865c037f9c16232b9d1
+size 1213261264

preprocessor_config.json

@@ -1,21 +1,20 @@
 {
-  "crop_pct": 0.875,
   "do_convert_rgb": null,
   "do_normalize": true,
   "do_rescale": true,
   "do_resize": true,
   "image_mean": [
-    0.485,
-    0.456,
-    0.406
+    0.5,
+    0.5,
+    0.5
   ],
   "image_processor_type": "ViTFeatureExtractor",
   "image_std": [
-    0.229,
-    0.224,
-    0.225
+    0.5,
+    0.5,
+    0.5
   ],
-  "resample": 3,
+  "resample": 2,
   "rescale_factor": 0.00392156862745098,
   "size": {
     "height": 224,

runs/Dec31_07-42-40_3dcd8bc8b582/events.out.tfevents.1735630970.3dcd8bc8b582.519.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bde6e1572921bee87789a588c0286f80e820a54d503ec52bfc7aa27a79bc9d9f
+size 7210

runs/Dec31_07-45-03_3dcd8bc8b582/events.out.tfevents.1735631111.3dcd8bc8b582.519.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:114c9a99405f771bcc65c78e8f6daa8b4306df541ac8f837b4e702e851cc9fae
+size 7350

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0ef7cd3b5085ce6fa0e411c88c8eccfb54e4b757a3d0d75a7641d11bccd472a
+oid sha256:97c30a7a9b3fe7e7420f8506165095d7bbd6eb5dcbcd6513ba9a6c171d58879d
 size 5304