Model save

README.md

@@ -0,0 +1,106 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: Action_model
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.78
+---
+
+<!-- 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. -->
+
+# Action_model
+
+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: 0.9408
+- Accuracy: 0.78
+
+## 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: 0.0001
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.1382        | 0.32  | 100  | 1.0002          | 0.7676   |
+| 0.782         | 0.64  | 200  | 0.7673          | 0.7676   |
+| 0.6289        | 0.96  | 300  | 0.7073          | 0.7867   |
+| 0.5028        | 1.27  | 400  | 0.7261          | 0.7686   |
+| 0.4746        | 1.59  | 500  | 0.7464          | 0.7619   |
+| 0.4298        | 1.91  | 600  | 0.6551          | 0.7990   |
+| 0.3488        | 2.23  | 700  | 0.7359          | 0.7733   |
+| 0.266         | 2.55  | 800  | 0.8296          | 0.7514   |
+| 0.3651        | 2.87  | 900  | 0.8661          | 0.7305   |
+| 0.2796        | 3.18  | 1000 | 0.7188          | 0.7867   |
+| 0.2703        | 3.5   | 1100 | 0.8422          | 0.7476   |
+| 0.2608        | 3.82  | 1200 | 0.8207          | 0.7724   |
+| 0.251         | 4.14  | 1300 | 1.0252          | 0.7267   |
+| 0.2085        | 4.46  | 1400 | 1.0475          | 0.7171   |
+| 0.1715        | 4.78  | 1500 | 0.8852          | 0.7495   |
+| 0.2051        | 5.1   | 1600 | 0.8164          | 0.7790   |
+| 0.1481        | 5.41  | 1700 | 0.8825          | 0.7629   |
+| 0.177         | 5.73  | 1800 | 0.8623          | 0.7867   |
+| 0.1607        | 6.05  | 1900 | 0.9487          | 0.7610   |
+| 0.1273        | 6.37  | 2000 | 0.8985          | 0.7733   |
+| 0.1609        | 6.69  | 2100 | 0.9624          | 0.7505   |
+| 0.1583        | 7.01  | 2200 | 0.9015          | 0.7781   |
+| 0.1178        | 7.32  | 2300 | 0.9143          | 0.7762   |
+| 0.1175        | 7.64  | 2400 | 0.9671          | 0.7590   |
+| 0.1257        | 7.96  | 2500 | 0.8925          | 0.7838   |
+| 0.0939        | 8.28  | 2600 | 0.9257          | 0.7705   |
+| 0.1238        | 8.6   | 2700 | 0.9797          | 0.7648   |
+| 0.1219        | 8.92  | 2800 | 0.9399          | 0.7724   |
+| 0.0985        | 9.24  | 2900 | 0.9940          | 0.7648   |
+| 0.1069        | 9.55  | 3000 | 0.9392          | 0.7743   |
+| 0.0589        | 9.87  | 3100 | 0.9408          | 0.78     |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,48 @@
+{
+  "_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": "\u0995\u09a5\u09be_\u09ac\u09b2\u09be",
+    "1": "\u0995\u09ae\u09cd\u09aa\u09bf\u0989\u099f\u09be\u09b0_\u09ac\u09cd\u09af\u09ac\u09b9\u09be\u09b0_\u0995\u09b0\u09be",
+    "2": "\u0996\u09be\u0993\u09df\u09be",
+    "3": "\u0996\u09c7\u09b2\u09be_\u0995\u09b0\u09be",
+    "4": "\u0998\u09c1\u09ae\u09be\u09a8\u09cb",
+    "5": "\u09aa\u09be\u09a8_\u0995\u09b0\u09be",
+    "6": "\u09aa\u09dc\u09be",
+    "7": "\u09b0\u09be\u09a8\u09cd\u09a8\u09be_\u0995\u09b0\u09be",
+    "8": "\u09b2\u09c7\u0996\u09be",
+    "9": "\u09b9\u09be\u0981\u099f\u09be"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "\u0995\u09a5\u09be_\u09ac\u09b2\u09be": "0",
+    "\u0995\u09ae\u09cd\u09aa\u09bf\u0989\u099f\u09be\u09b0_\u09ac\u09cd\u09af\u09ac\u09b9\u09be\u09b0_\u0995\u09b0\u09be": "1",
+    "\u0996\u09be\u0993\u09df\u09be": "2",
+    "\u0996\u09c7\u09b2\u09be_\u0995\u09b0\u09be": "3",
+    "\u0998\u09c1\u09ae\u09be\u09a8\u09cb": "4",
+    "\u09aa\u09be\u09a8_\u0995\u09b0\u09be": "5",
+    "\u09aa\u09dc\u09be": "6",
+    "\u09b0\u09be\u09a8\u09cd\u09a8\u09be_\u0995\u09b0\u09be": "7",
+    "\u09b2\u09c7\u0996\u09be": "8",
+    "\u09b9\u09be\u0981\u099f\u09be": "9"
+  },
+  "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": "4.39.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ff997581ddd6642e58b1bb4fe1550a4aea0cc57679090651e721750b79b12b0
+size 343248584

preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "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/Apr15_19-54-29_beac81f7e97f/events.out.tfevents.1713210973.beac81f7e97f.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd7438baee405769b0c742d9a5b723ddc8ebdd18d7bcbdf38f27c74d46285eb8
+size 49066

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8894c7e4e95f3786de873c5a43602402b76fd332eea765b39d0b3d59a27cf039
+size 4920