Skip to content

disable qwen2 #4277

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
zjjlivein wants to merge 1 commit into
base: develop
Choose a base branch
from
Open

disable qwen2 #4277

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
51 changes: 0 additions & 51 deletions scripts/regression/config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -193,57 +193,6 @@ glm_moe:
- [10564, 10564, 102954, 47231, 47231, 47231, 47231, 47231, 47231, 47231]
dpo_full_function_call_excepted_result:
- [10564, 10564, 102954, 47231, 47231, 47231, 47231, 47231, 47231, 47231]
qwen2:
repo_id: PaddleFormers/tiny-random-qwen2v2
model_type: text
cli_args:
save_checkpoint_format: flex_checkpoint
load_checkpoint_format: flex_checkpoint
template: qwen
base_loss:
sft_full_loss: 12.751743795
sft_full_resume_loss: 12.75366116
dpo_full_loss: 0.69314718
dpo_full_resume_loss: 0.69314718
pt_full_loss: 12.9430995
pt_full_resume_loss: 12.94307518
sft_lora_loss: 12.751743795
sft_lora_resume_loss: 12.75366116
dpo_lora_loss: 0.69314718
dpo_lora_resume_loss: 0.69314718
pt_lora_loss: 12.9430995
pt_lora_resume_loss: 12.94307518
sft_full_tp_pp_loss: 12.835041045
sft_full_tp_pp_resume_loss: 12.83503151
dpo_full_tp_pp_loss: 0.69314718
dpo_full_tp_pp_resume_loss: 0.69314718
pt_full_tp_pp_loss: 12.943032265
pt_full_tp_pp_resume_loss: 12.94280052
sft_lora_tp_pp_loss: 12.83521986
sft_lora_tp_pp_resume_loss: 12.83525467
dpo_lora_tp_pp_loss: 0.69314718
dpo_lora_tp_pp_resume_loss: 0.69314718
pt_lora_tp_pp_loss: 12.943032265
pt_lora_tp_pp_resume_loss: 12.94280052
sft_full_function_call_loss: 12.800441265
sft_full_function_call_resume_loss: 12.80294609
dpo_full_function_call_loss: 0.69314718
dpo_full_function_call_resume_loss: 0.69314718
base_result:
pt_full_excepted_result: []
sft_full_excepted_result: []
dpo_full_excepted_result: []
pt_lora_excepted_result: []
sft_lora_excepted_result: []
dpo_lora_excepted_result: []
pt_full_tp_pp_excepted_result: []
sft_full_tp_pp_excepted_result: []
dpo_full_tp_pp_excepted_result: []
pt_lora_tp_pp_excepted_result: []
sft_lora_tp_pp_excepted_result: []
dpo_lora_tp_pp_excepted_result: []
sft_full_function_call_excepted_result: []
dpo_full_function_call_excepted_result: []
llama:
repo_id: PaddleFormers/tiny-random-llama3
model_type: text
Expand Down
2 changes: 1 addition & 1 deletion scripts/regression/test_models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -600,7 +600,7 @@ def execute_training_workflow(

# Test model generation
generate_log_file = os.path.join(LOG_PATH, f"{model_key}_{train_type}_{test_type}_generate.log")
skip_generation = model_key in ["qwen2_moe", "deepseek_v3"]
skip_generation = model_key in ["qwen2", "qwen2_moe", "deepseek_v3"]
if skip_generation:
result = None
else:
Expand Down
Loading