Network forgetting progress during training

I’m working on my first non-trivial tensorflow project (predicting moves-to-mate for chess endgames) and I’ve run across some odd behavior in the training stage. In multiple models I have trained on my data, the network looks like it has forgotten everything and restarts from scratch. How do I avoid this?

Training data is 40,000 samples, Adam optimizer, batch size 2000
I know my model is way over-parameterized at the moment, but the smaller models I tried weren’t accurate enough
def create_model_eg_bin2c(my_learning_rate):
“”“Create and compile a deep neural net.”""
# This is a first try to get a simple model that works
model = tf.keras.models.Sequential()
filters=64, kernel_size=(3,3), input_shape=(8,8,15), strides=(1, 1), padding=‘same’))
model.add(tf.keras.layers.MaxPooling2D((2, 2)))
filters=32, kernel_size=(3,3), strides=(1, 1), padding=‘same’))
model.add(tf.keras.layers.MaxPooling2D((2, 2)))

return model

Hi @Robert_Pope

Welcome to the TensorFlow Forum!

Please tell us what is the dataset type and shape of the dataset as Cov2D expects the input shape in (N,H,W,C) format where C is the channels which should be 1,2,3.
Please provide us some more details like which system OS, platform environment (Colab, Jupyter, Pycharm) you are using to execute the TF code. Thank you.