jinensetpal
/
transformer-belief-state-geometries
connected to https://github.com/jinensetpal/transformer-belief-state-geometries.git


  
1

	
2

	
3

	
4

	
5

	
6

	
7

	
8

	
            # evaluate the base gpt2
# n_layer=24, n_head=16, n_embd=1024
# 350M parameters
batch_size = 8
eval_iters = 500 # use more iterations to get good estimate
eval_only = True
wandb_log = False
init_from = 'gpt2-medium'