apunkt/doc-to-lora
1
0
Fork 0
mirror of https://github.com/SakanaAI/doc-to-lora.git synced 2026-07-23 17:01:04 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix ds probs

Browse source
This commit is contained in:
51616 2025-06-03 14:29:20 +00:00
parent 5d793e329b
commit 57b63d3b8b
1 changed files with 6 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

10
intx_sft.py
View file

@ -2,7 +2,7 @@ import logging
import os
from copy import deepcopy
from functools import partial
from math import ceil
from math import ceil, isclose
import numpy as np
import torch
@ -70,11 +70,13 @@ def get_ds_prob(train_ds_len: list[int], total_len: int):
if ds_len / total_len <= 0.01:
probs[i] = 0.01
res_probs = 1 - sum(probs)
res_total_len = sum([l for l in train_ds_len if l / total_len > 0.01])
res_total_len = sum([l for l in train_ds_len if (l / total_len) > 0.01])
for i, ds_len in enumerate(train_ds_len):
if ds_len / total_len > 0.01:
if (ds_len / total_len) > 0.01:
probs[i] = ds_len / res_total_len * res_probs
assert sum(probs) == 1
assert isclose(sum(probs), 1.0), (
f"Probs sum to {sum(probs)} ({probs}), expected 1.0"
)
return probs