sanali209/imagetypeBF

README.md

@@ -1,7 +1,5 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: google/vit-large-patch16-224
 tags:
 - generated_from_trainer
 datasets:
@@ -16,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # imagetypeBF
 
-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.
+This model was trained from scratch on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4854
+- Loss: 0.3213
 
 ## Model description
 
@@ -43,23 +41,21 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 6
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 37   | 0.5820          |
-| No log        | 2.0   | 74   | 0.5166          |
-| No log        | 3.0   | 111  | 0.5144          |
-| No log        | 4.0   | 148  | 0.5011          |
-| No log        | 5.0   | 185  | 0.4854          |
-| No log        | 6.0   | 222  | 0.4865          |
+| No log        | 1.0   | 78   | 0.3868          |
+| No log        | 2.0   | 156  | 0.3427          |
+| No log        | 3.0   | 234  | 0.3222          |
+| No log        | 4.0   | 312  | 0.3213          |
 
 
 ### Framework versions
 
-- Transformers 4.44.2
+- Transformers 4.45.1
 - Pytorch 2.4.1+cu121
-- Datasets 3.0.0
-- Tokenizers 0.19.1
+- Datasets 3.0.1
+- Tokenizers 0.20.0

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/vit-large-patch16-224",
+  "_name_or_path": "sanali209/imagetypeBF",
   "architectures": [
     "ViTForImageClassification"
   ],
@@ -38,5 +38,5 @@
   "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2"
+  "transformers_version": "4.45.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6d5b7109e61765976eb234ae737610ab4297ffaefbe8983c7f942001817cedb
+oid sha256:5b0f7036057c6e91727e6105cb7234626174c1afc18a98860831f190004ad5b5
 size 1213281772

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8235408d95eaddfb5000793e66337dc6a830439121600eb1713bbf8d46077abf
+oid sha256:00bdf156588642a0eb7d25b0e83a8e069d89741d07305337319ac6fe79ab1b49
 size 5176