Model save

README.md

@@ -17,12 +17,12 @@ model-index:
       name: imagefolder
       type: imagefolder
       config: default
-      split: test
+      split: train
       args: default
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7716666666666666
+      value: 0.8907407407407407
 ---
 
 <!-- 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-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1645
-- Accuracy: 0.7717
+- Loss: 0.4002
+- Accuracy: 0.8907
 
 ## Model description
 
@@ -52,25 +52,25 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
+- learning_rate: 0.0002
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.0072        | 0.91  | 500  | 1.1645          | 0.7717   |
+| 0.0841        | 3.7   | 1000 | 0.4002          | 0.8907   |
 
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu121
-- Datasets 2.16.0
-- Tokenizers 0.15.0
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -14,11 +14,10 @@
     "2": "country",
     "3": "disco",
     "4": "hiphop",
-    "5": "jazz",
-    "6": "metal",
-    "7": "pop",
-    "8": "reggae",
-    "9": "rock"
+    "5": "metal",
+    "6": "pop",
+    "7": "reggae",
+    "8": "rock"
   },
   "image_size": 224,
   "initializer_range": 0.02,
@@ -29,11 +28,10 @@
     "country": "2",
     "disco": "3",
     "hiphop": "4",
-    "jazz": "5",
-    "metal": "6",
-    "pop": "7",
-    "reggae": "8",
-    "rock": "9"
+    "metal": "5",
+    "pop": "6",
+    "reggae": "7",
+    "rock": "8"
   },
   "layer_norm_eps": 1e-12,
   "model_type": "vit",
@@ -44,5 +42,5 @@
   "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2"
+  "transformers_version": "4.38.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abbdc009182e7696031293c94c192c61c6f24445dadc81297e28c6d6d7df7961
-size 343248584
+oid sha256:5e9b32304bec56840d3e04c9bdf0d5c99b1d89352687a840187992b9cad96e44
+size 343245508

runs/Mar18_03-56-25_8e515caeb417/events.out.tfevents.1710734191.8e515caeb417.2485.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:562416510b325b9f777843b28fa5f387a5bc74bf5fc2b9a8a56aafb0d9406d5f
+size 33893

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad6692415b070db68f4a37e66816edaae1e4a06514056f81c53142100cabedcc
-size 4536
+oid sha256:076f18a557d228bc4658ceb819d314bb200c1ed02f65448a48d0daa4f673c0a9
+size 4856