Training in progress epoch 1

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_keras_callback
+model-index:
+- name: ansilmbabl/vit-base-patch16-224-in21k-Cards
+  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. -->
+
+# ansilmbabl/vit-base-patch16-224-in21k-Cards
+
+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: 1.3188
+- Train Accuracy: 0.6043
+- Train Top-3-accuracy: 0.8822
+- Validation Loss: 0.8883
+- Validation Accuracy: 0.7130
+- Validation Top-3-accuracy: 0.9537
+- 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': {'module': 'transformers.optimization_tf', 'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 53200, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.8999999761581421, 'beta_2': 0.9990000128746033, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}, 'registered_name': 'AdamWeightDecay'}, '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 |
+|:----------:|:--------------:|:--------------------:|:---------------:|:-------------------:|:-------------------------:|:-----:|
+| 1.3188     | 0.6043         | 0.8822               | 0.8883          | 0.7130              | 0.9537                    | 0     |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- TensorFlow 2.14.0
+- Datasets 2.19.1
+- Tokenizers 0.19.1

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,46 @@
+{
+  "_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": "Grade_08",
+    "1": "Grade_09",
+    "2": "Grade_02",
+    "3": "Grade_06",
+    "4": "Grade_04",
+    "5": "Grade_10",
+    "6": "Grade_05",
+    "7": "Grade_07",
+    "8": "Grade_03",
+    "9": "Grade_01"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Grade_01": "9",
+    "Grade_02": "2",
+    "Grade_03": "8",
+    "Grade_04": "4",
+    "Grade_05": "6",
+    "Grade_06": "3",
+    "Grade_07": "7",
+    "Grade_08": "0",
+    "Grade_09": "1",
+    "Grade_10": "5"
+  },
+  "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": "4.41.2"
+}

README.md

@@ -15,13 +15,13 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.3188
-- Train Accuracy: 0.6043
-- Train Top-3-accuracy: 0.8822
-- Validation Loss: 0.8883
-- Validation Accuracy: 0.7130
-- Validation Top-3-accuracy: 0.9537
-- Epoch: 0
+- Train Loss: 0.6864
+- Train Accuracy: 0.7853
+- Train Top-3-accuracy: 0.9705
+- Validation Loss: 0.6807
+- Validation Accuracy: 0.7647
+- Validation Top-3-accuracy: 0.9650
+- Epoch: 1
 
 ## Model description
 
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
 | Train Loss | Train Accuracy | Train Top-3-accuracy | Validation Loss | Validation Accuracy | Validation Top-3-accuracy | Epoch |
 |:----------:|:--------------:|:--------------------:|:---------------:|:-------------------:|:-------------------------:|:-----:|
 | 1.3188     | 0.6043         | 0.8822               | 0.8883          | 0.7130              | 0.9537                    | 0     |
+| 0.6864     | 0.7853         | 0.9705               | 0.6807          | 0.7647              | 0.9650                    | 1     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1717140134.e2e-60-58.11212.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ca6feecf14a71e698c0351b8530244d59432be8c5f57da0f94b0aeb939c3534
-size 3388345
+oid sha256:cea82ffb16c5e6d065899285d1175aa6b332d9dfb0ef2b74ba31b074bc54100c
+size 3388640

logs/validation/events.out.tfevents.1717140628.e2e-60-58.11212.2.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74f1f6abb44c1fef026e237d894e22a6efbe1246d3f5d9baf35966ecf1d3e03a
-size 568
+oid sha256:4dc05908cdd64a602ebc38ea79006b6f052cde32a6fc5e97728f5564dea479d4
+size 1064

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c2e0869496f8d31056b1e87947bcea72f908f860d8565d3516205e4766db049
+oid sha256:119e0c028b2fc6faab292f5a5ac938f05d0a020e5e70c799eeee914173853b3e
 size 343510712