filmo

q_learning walkthrough. GATech OMSCS. (School policy prohibits our publishing code for honor policy)

filmo

Used a 2-layer Fully Connected network with H1=100, H2=60 and ReLU

He Initialization of weights
Adam Optimizer. Initial learning rate = 0.001 Learning rate reduced using gamma of 0.50 every 350 episodes

Gamma = 0.99
Eps   = 1.00
Eps Decay = 0.98
Eps Decay every new episode. (not each step)

filmo

import numpy as np
np.set_printoptions(precision=4,suppress=True,linewidth=180)

def clamp(n, min, max):
    if n < min:
        return min
    if n > max:
        return max
    return n

filmo

On line 35 shuffle is imported from sklearn

from sklearn.utils import shuffle

and then later called inside the data generator with:

shuffle(keys)

However, shuffle from sklearn does ~not~ shuffle in-place. It returns a shuffled list, leaving the input parameter untouched.

filmo

  0%|          | 0/1000 [00:00<?, ?it/s]You're using a PreTrainedTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
Traceback (most recent call last):
  File "/home/philglau/PycharmProjects/tokenizersLLM/medium_article_falcon7b.py", line 87, in <module>
    trainer.train()
  File "/home/philglau/anaconda3/envs/pytorch_hug_llm_203/lib/python3.11/site-packages/transformers/trainer.py", line 1645, in train
    return inner_training_loop(
           ^^^^^^^^^^^^^^^^^^^^
  File "/home/philglau/anaconda3/envs/pytorch_hug_llm_203/lib/python3.11/site-packages/transformers/trainer.py", line 1938, in _inner_training_loop
    tr_loss_step = self.training_step(model, inputs)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^