Model save

README.md

@@ -0,0 +1,63 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: finetuned-bangladeshi-traditional-food
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# finetuned-bangladeshi-traditional-food
+
+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.
+It achieves the following results on the evaluation set:
+- Loss: 0.3867
+- Accuracy: 0.9190
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 32
+- eval_batch_size: 16
+- 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: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.703         | 1.5625 | 100  | 0.6128          | 0.9022   |
+| 0.252         | 3.125  | 200  | 0.3867          | 0.9190   |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.4.0
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,64 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Peanut Chikki",
+    "1": "Popped Rice",
+    "10": "\u0995\u09a6\u09ae\u09be",
+    "11": "\u0997\u099c\u09be",
+    "12": "\u09a4\u09bf\u09b2\u09c7\u09b0 \u0996\u09be\u099c\u09be",
+    "13": "\u09a8\u0995\u09c1\u09b2\u09a6\u09be\u09a8\u09be",
+    "14": "\u09a8\u09be\u09b0\u09bf\u0995\u09c7\u09b2 \u09a8\u09be\u09a1\u09bc\u09c1",
+    "15": "\u09a8\u09bf\u09ae\u0995\u09bf",
+    "16": "\u09ac\u09be\u09a4\u09be\u09b8\u09be",
+    "17": "\u09ae\u09bf\u099b\u09b0\u09bf",
+    "2": "Puffed Rice",
+    "3": "bakarkhani",
+    "4": "flattened rice",
+    "5": "jalebi",
+    "6": "morobba",
+    "7": "muri mowa",
+    "8": "soan papdi",
+    "9": "\u0986\u09ae\u09b8\u09a4\u09cd\u09a4\u09cd\u09ac"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Peanut Chikki": "0",
+    "Popped Rice": "1",
+    "Puffed Rice": "2",
+    "bakarkhani": "3",
+    "flattened rice": "4",
+    "jalebi": "5",
+    "morobba": "6",
+    "muri mowa": "7",
+    "soan papdi": "8",
+    "\u0986\u09ae\u09b8\u09a4\u09cd\u09a4\u09cd\u09ac": "9",
+    "\u0995\u09a6\u09ae\u09be": "10",
+    "\u0997\u099c\u09be": "11",
+    "\u09a4\u09bf\u09b2\u09c7\u09b0 \u0996\u09be\u099c\u09be": "12",
+    "\u09a8\u0995\u09c1\u09b2\u09a6\u09be\u09a8\u09be": "13",
+    "\u09a8\u09be\u09b0\u09bf\u0995\u09c7\u09b2 \u09a8\u09be\u09a1\u09bc\u09c1": "14",
+    "\u09a8\u09bf\u09ae\u0995\u09bf": "15",
+    "\u09ac\u09be\u09a4\u09be\u09b8\u09be": "16",
+    "\u09ae\u09bf\u099b\u09b0\u09bf": "17"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9f3dba1a76e37593fb689472f69a374aa2f9c7b3e5fafa5035ea86715d4da93
+size 343273192

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTFeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Dec08_07-41-29_64968b5b03f4/events.out.tfevents.1733643820.64968b5b03f4.23.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5c1355fca57ff3f89ba13d2948053a1e4ba413814adc7cf427a118d4d0bb263
+size 8477

runs/Dec08_08-00-19_64968b5b03f4/events.out.tfevents.1733644833.64968b5b03f4.23.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1fe5f0036ab694a2b64c6bc3f1737ee1b3d2579cd9fe6154f207b61721869cb
+size 12628

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7e1f115672319c84ee8bd77531e74158bdd740ee70414f95bc86a912db901d1
+size 5304