Downloading data from https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz
170500096/170498071 [==============================] - 9s 0us/step
170508288/170498071 [==============================] - 9s 0us/step
2022-07-04 12:31:45.748622: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  SSE4.2 AVX AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
Metal device set to: AMD Radeon PRO W6800

systemMemory: 64.00 GB
maxCacheSize: 14.99 GB

2022-07-04 12:31:45.749294: I tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:305] Could not identify NUMA node of platform GPU ID 0, defaulting to 0. Your kernel may not have been built with NUMA support.
2022-07-04 12:31:45.749576: I tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:271] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 0 MB memory) -> physical PluggableDevice (device: 0, name: METAL, pci bus id: <undefined>)
Epoch 1/8
2022-07-04 12:31:50.297710: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:185] None of the MLIR Optimization Passes are enabled (registered 2)
2022-07-04 12:31:50.309630: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:112] Plugin optimizer for device_type GPU is enabled.
100/100 [==============================] - ETA: 0s - loss: 1.6966 - accuracy: 0.39262022-07-04 12:32:15.971967: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:112] Plugin optimizer for device_type GPU is enabled.
100/100 [==============================] - 29s 151ms/step - loss: 1.6966 - accuracy: 0.3926 - val_loss: 3.7252 - val_accuracy: 0.1135
Epoch 2/8
100/100 [==============================] - 14s 143ms/step - loss: 1.2538 - accuracy: 0.5482 - val_loss: 2.5054 - val_accuracy: 0.2393
Epoch 3/8
100/100 [==============================] - 14s 144ms/step - loss: 1.0561 - accuracy: 0.6279 - val_loss: 1.9146 - val_accuracy: 0.3743
Epoch 4/8
100/100 [==============================] - 14s 145ms/step - loss: 0.8931 - accuracy: 0.6846 - val_loss: 1.4462 - val_accuracy: 0.5201
Epoch 5/8
100/100 [==============================] - 14s 145ms/step - loss: 0.7677 - accuracy: 0.7303 - val_loss: 1.7987 - val_accuracy: 0.4944
Epoch 6/8
100/100 [==============================] - 14s 145ms/step - loss: 0.6765 - accuracy: 0.7647 - val_loss: 1.9940 - val_accuracy: 0.4713
Epoch 7/8
100/100 [==============================] - 15s 145ms/step - loss: 0.5913 - accuracy: 0.7937 - val_loss: 2.2002 - val_accuracy: 0.4865
Epoch 8/8
100/100 [==============================] - 15s 146ms/step - loss: 0.5382 - accuracy: 0.8122 - val_loss: 2.5099 - val_accuracy: 0.4619