tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Accelerate 1.8.1 and BNB 0.46.0 update (#2815)

Browse Source 
* update accelerate to v1.8.0

* update bnb also

* fix multigpu ci timeout

* fix test set size

* use latest accelerate 1.8.1

* disable default dtype
This commit is contained in:
Wing Lian
2025-06-28 15:29:19 -04:00
committed by GitHub
parent a1a740608d
commit 81893c775c
11 changed files with 32 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/e2e/multigpu/test_eval.py
View File

@@ -38,12 +38,13 @@ class TestMultiGPUEval:
"lora_dropout": 0.05,
"lora_target_linear": True,
"lora_modules_to_save": ["embed_tokens", "lm_head"],
"val_set_size": 0.004,
"val_set_size": 0.05,
"special_tokens": {"pad_token": "<|endoftext|>"},
"datasets": [
{
"path": "teknium/GPT4-LLM-Cleaned",
"type": "alpaca",
"split": "train[:5%]",
},
],
"num_epochs": 1,
@@ -51,6 +52,7 @@ class TestMultiGPUEval:
"micro_batch_size": 2,
"gradient_accumulation_steps": 2,
"output_dir": temp_dir,
"dataset_prepared_path": temp_dir + "/last_run_prepared",
"learning_rate": 0.00001,
"optimizer": "adamw_8bit",
"lr_scheduler": "cosine",
@@ -107,12 +109,13 @@ class TestMultiGPUEval:
"lora_dropout": 0.05,
"lora_target_linear": True,
"lora_modules_to_save": ["embed_tokens", "lm_head"],
"val_set_size": 0.0004,
"val_set_size": 0.01,
"special_tokens": {"pad_token": "<|endoftext|>"},
"datasets": [
{
"path": "teknium/GPT4-LLM-Cleaned",
"type": "alpaca",
"split": "train[:5%]",
},
],
"num_epochs": 1,
@@ -120,6 +123,7 @@ class TestMultiGPUEval:
"micro_batch_size": 2,
"gradient_accumulation_steps": 2,
"output_dir": temp_dir,
"dataset_prepared_path": temp_dir + "/last_run_prepared",
"learning_rate": 0.00001,
"optimizer": "adamw_8bit",
"lr_scheduler": "cosine",