tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix flaky tests; should be using train loss from final step rather than final avg train loss

Browse Source
This commit is contained in:
Wing Lian
2026-03-22 10:38:46 -04:00
parent 5b2e3f00ce
commit 6130e40c37
21 changed files with 37 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/e2e/multigpu/test_ray.py
View File

@@ -79,7 +79,7 @@ class TestMultiGPURay:
)
check_tensorboard(
temp_dir + "/runs", "train/train_loss", 2.3, "Train Loss (%s) is too high"
temp_dir + "/runs", "train/loss", 2.3, "Train Loss (%s) is too high"
)
@require_torch_2_7_0
@@ -138,7 +138,7 @@ class TestMultiGPURay:
)
check_tensorboard(
temp_dir + "/runs", "train/train_loss", 2.3, "Train Loss (%s) is too high"
temp_dir + "/runs", "train/loss", 2.3, "Train Loss (%s) is too high"
)
@require_torch_2_7_0
@@ -205,5 +205,5 @@ class TestMultiGPURay:
)
check_tensorboard(
temp_dir + "/runs", "train/train_loss", 2.3, "Train Loss (%s) is too high"
temp_dir + "/runs", "train/loss", 2.3, "Train Loss (%s) is too high"
)