Training in progress epoch 0

README.md

@@ -0,0 +1,57 @@
+---
+license: apache-2.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: TariqJamil/vit-base-patch16-224-in21k-handsActDetect
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# TariqJamil/vit-base-patch16-224-in21k-handsActDetect
+
+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:
+- Train Loss: 0.2926
+- Train Accuracy: 0.9548
+- Train Top-3-accuracy: 0.9928
+- Validation Loss: 0.0623
+- Validation Accuracy: 0.9973
+- Validation Top-3-accuracy: 1.0
+- Epoch: 0
+
+## 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:
+- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 2645, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
+- training_precision: mixed_float16
+
+### Training results
+
+| Train Loss | Train Accuracy | Train Top-3-accuracy | Validation Loss | Validation Accuracy | Validation Top-3-accuracy | Epoch |
+|:----------:|:--------------:|:--------------------:|:---------------:|:-------------------:|:-------------------------:|:-----:|
+| 0.2926     | 0.9548         | 0.9928               | 0.0623          | 0.9973              | 1.0                       | 0     |
+
+
+### Framework versions
+
+- Transformers 4.27.4
+- TensorFlow 2.12.0
+- Datasets 2.11.0
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,36 @@
+{
+  "_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": "Thumbs_Up",
+    "1": "Stop_Gesture",
+    "2": "Right_Swipe",
+    "3": "Thumbs_Down",
+    "4": "Left_Swipe"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Left_Swipe": "4",
+    "Right_Swipe": "2",
+    "Stop_Gesture": "1",
+    "Thumbs_Down": "3",
+    "Thumbs_Up": "0"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "qkv_bias": true,
+  "transformers_version": "4.27.4"
+}

logs/train/events.out.tfevents.1680836848.2a6883624ba2.24534.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0da8ae3c8bacb152be5744af37328f56c5e99e94ce4a5eaae3f08b662d7bf790
+size 3307558

logs/validation/events.out.tfevents.1680837463.2a6883624ba2.24534.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:972299ed4066f6375733c02348fd74422cac90aba61fed0d51859bfc707b2e64
+size 568

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:121171e466da1f14ae083db3fa04428e3f5cafb2ae0edd9efb31b8daefb147b8
+size 343478968