##################################################
# Data config for Shakespeare
##################################################
test_size = 0.1
seed = 110892
shuffle = True
dataset_key = 'train'
num_proc = -1 # -1 for all, 1 for single process, 2 for two processes, etc.
tokenizer = 'gpt2' # 'gpt2' or 'cl100k_base' or 'gpt-4'

##################################################
# Training config for Shakespeare
##################################################
out_dir = 'gpt2'
eval_interval = 2000
log_interval = 1
eval_iters = 200
eval_only = False # if True, script exits right after the first eval
always_save_checkpoint = True # if True, always save a checkpoint after each eval
init_from = 'resume' # 'scratch' or 'resume' or 'gpt2*'
# wandb logging
wandb_log = False # disabled by default
wandb_project = 'SimpleLLM'
wandb_run_name = 'gpt2' # 'run' + str(time.time())
# data
dataset = 'openwebtext'
gradient_accumulation_steps = 5 * 8 # used to simulate larger batch sizes
batch_size = 12 # if gradient_accumulation_steps > 1, this is the micro-batch size
block_size = 1024
# model
n_layer = 12
n_head = 12
n_embd = 768
dropout = 0.0 # for pretraining 0 is good, for finetuning try 0.1+
bias = False # do we use bias inside LayerNorm and Linear layers?
# adamw optimizer
learning_rate = 6e-4 # max learning rate
max_iters = 600000 # total number of training iterations
weight_decay = 1e-1
beta1 = 0.9
beta2 = 0.95
grad_clip = 1.0 # clip gradients at this value, or disable if == 0.0
# learning rate decay settings
decay_lr = True # whether to decay the learning rate
warmup_iters = 2000 # how many steps to warm up for
lr_decay_iters = 600000 # should be ~= max_iters per Chinchilla
min_lr = 6e-5 # minimum learning rate, should be ~= learning_rate/10 per Chinchilla
# DDP settings
backend = 'nccl' # 'nccl', 'gloo', etc.

##################################################
# Generator config for Shakespeare
##################################################
# init_from = 'resume' # either 'resume' (from an out_dir) or a gpt2 variant (e.g. 'gpt2-xl')
start = "\n" # or "<|endoftext|>" or etc. Can also specify a file, use as: "FILE:prompt.txt"
num_samples = 10 # number of samples to draw
max_new_tokens = 500 # number of tokens generated in each sample
temperature = 0.8 # 1.0 = no change, < 1.0 = less random, > 1.0 = more random, in predictions
top_k = 200 # retain only the top_k most likely tokens, clamp others to have 0 probability
seed = 1337