tacit/nanochat
1
0
Fork 0
mirror of https://github.com/karpathy/nanochat.git synced 2025-12-06 04:12:13 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Compare commits

base: tacit:2d09f8a7256a8a9b1826d3b35763284e5a4ab389
Branches Tags
tacit:master
...
compare: tacit:2311d38e3fb964f792292a5131954832c1918256
Branches Tags
tacit:master

2 Commits
2d09f8a725 ... 2311d38e3f

Author SHA1 Message Date
ericsilberstein1
2311d38e3f
Merge 4bcc3bb698 into 4a87a0d19f 2025-11-21 13:19:50 +01:00
svlandeg
4bcc3bb698 clarify comment 2025-11-21 13:19:45 +01:00
1 changed files with 1 additions and 1 deletions
Show Stats Expand all files Collapse all files

2
scripts/mid_train.py
View File

@ -112,7 +112,7 @@ val_dataset = TaskMixture([
# DataLoader is defined here, it emits inputs, targets : 2D tensors of shape (device_batch_size, max_seq_len) # DataLoader is defined here, it emits inputs, targets : 2D tensors of shape (device_batch_size, max_seq_len)
# A big problem is that we don't know the final num_iterations in advance. So we create # A big problem is that we don't know the final num_iterations in advance. So we create
# these two global variables and update them from within the data generator. # these two global variables and update them from within the data generator.
last_step = False # we will toggle this to True when we reach the end of the dataset last_step = False # we will toggle this to True when we reach the end of the training dataset
approx_progress = 0.0 # will go from 0 to 1 over the course of the epoch approx_progress = 0.0 # will go from 0 to 1 over the course of the epoch
def mid_data_generator(split): def mid_data_generator(split):
global last_step, approx_progress global last_step, approx_progress