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

make e2e tests a bit faster by reducing test split size (#2522) [skip ci]

Browse Source 
* [ci] make e2e tests a bit faster by reducing test split size

* use 10% split of alpaca dataset to speed up dataset loading/tokenization

* reduce gas 4->2 for most e2e tests

* increase val set size for packing
This commit is contained in:
Wing Lian
2025-04-12 07:24:43 -07:00
committed by GitHub
parent 51267ded04
commit de8a625dd7
24 changed files with 54 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/e2e/test_falcon.py
View File

@@ -41,7 +41,7 @@ class TestFalcon(unittest.TestCase):
"word_embeddings",
"lm_head",
],
"val_set_size": 0.1,
"val_set_size": 0.02,
"special_tokens": {
"bos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>",
@@ -92,7 +92,7 @@ class TestFalcon(unittest.TestCase):
"word_embeddings",
"lm_head",
],
"val_set_size": 0.1,
"val_set_size": 0.02,
"special_tokens": {
"bos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>",
@@ -137,7 +137,7 @@ class TestFalcon(unittest.TestCase):
"base_model": "illuin/tiny-random-FalconForCausalLM",
"flash_attention": True,
"sequence_len": 1024,
"val_set_size": 0.1,
"val_set_size": 0.02,
"special_tokens": {
"bos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>",