dayone3nder's picture
Upload folder using huggingface_hub
8e26f61 verified
2025-04-05 20:32:09,135 INFO MainThread:2888806 [wandb_setup.py:_flush():68] Current SDK version is 0.19.1
2025-04-05 20:32:09,136 INFO MainThread:2888806 [wandb_setup.py:_flush():68] Configure stats pid to 2888806
2025-04-05 20:32:09,136 INFO MainThread:2888806 [wandb_setup.py:_flush():68] Loading settings from /home/yangyaodong/.config/wandb/settings
2025-04-05 20:32:09,136 INFO MainThread:2888806 [wandb_setup.py:_flush():68] Loading settings from /aifs4su/yaodong/wenqi/projects/align-anything_0218/align-anything/scripts/wandb/settings
2025-04-05 20:32:09,136 INFO MainThread:2888806 [wandb_setup.py:_flush():68] Loading settings from environment variables
2025-04-05 20:32:09,136 INFO MainThread:2888806 [wandb_init.py:_log_setup():528] Logging user logs to /aifs4su/yaodong/wenqi/projects/first-time_safety/output_models/Qwen2.5-7B-Instruct_safe_thinking/wandb/run-20250405_203209-jla7fqqr/logs/debug.log
2025-04-05 20:32:09,136 INFO MainThread:2888806 [wandb_init.py:_log_setup():529] Logging internal logs to /aifs4su/yaodong/wenqi/projects/first-time_safety/output_models/Qwen2.5-7B-Instruct_safe_thinking/wandb/run-20250405_203209-jla7fqqr/logs/debug-internal.log
2025-04-05 20:32:09,136 INFO MainThread:2888806 [wandb_init.py:init():644] calling init triggers
2025-04-05 20:32:09,136 INFO MainThread:2888806 [wandb_init.py:init():650] wandb.init called with sweep_config: {}
config: {'train_cfgs': {'ds_cfgs': 'ds_z3_config.json', 'epochs': 3, 'seed': 42, 'per_device_train_batch_size': 4, 'per_device_eval_batch_size': 4, 'gradient_accumulation_steps': 2, 'gradient_checkpointing': True, 'learning_rate': 2e-05, 'lr_scheduler_type': 'constant', 'lr_warmup_ratio': 0.03, 'weight_decay': 0.0, 'adam_betas': [0.9, 0.95], 'adam_epsilon': 1e-08, 'bf16': True, 'fp16': False, 'eval_strategy': 'steps', 'eval_interval': 10, 'max_grad_norm': 1.0}, 'data_cfgs': {'train_datasets': '/aifs4su/yaodong/wenqi/projects/first-time_safety/data_annotation/data_output/safe-o1_0403/baseline_dataset', 'train_template': 'Safe_thinking', 'train_size': {}, 'train_split': 'train', 'train_name': {}, 'train_data_files': {}, 'train_optional_args': [], 'eval_datasets': {}, 'eval_template': {}, 'eval_size': {}, 'eval_split': {}, 'eval_subset': {}, 'eval_data_files': {}, 'eval_optional_args': []}, 'logger_cfgs': {'log_type': 'wandb', 'log_project': 'safe-o1', 'log_run_name': 'sft', 'output_dir': '/aifs4su/yaodong/wenqi/projects/first-time_safety/output_models/Qwen2.5-7B-Instruct_safe_thinking', 'cache_dir': {}, 'save_interval': 100000}, 'model_cfgs': {'model_name_or_path': '/aifs4su/yaodong/wenqi/models/Qwen2.5-7B-Instruct', 'trust_remote_code': True, 'model_max_length': 16384}, 'lora_cfgs': {'use_lora': False, 'task_type': 'TaskType.CAUSAL_LM', 'inference_mode': False, 'r': 16, 'lora_alpha': 16, 'lora_dropout': 0.1, 'target_modules': ['q_proj', 'v_proj'], 'save_full_model': True}, 'bnb_cfgs': {'use_bnb': False, 'load_in_4bit': True, 'load_in_8bit': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'float16'}, 'special_tokens': {}}
2025-04-05 20:32:09,136 INFO MainThread:2888806 [wandb_init.py:init():680] starting backend
2025-04-05 20:32:09,136 INFO MainThread:2888806 [wandb_init.py:init():684] sending inform_init request
2025-04-05 20:32:09,141 INFO MainThread:2888806 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
2025-04-05 20:32:09,142 INFO MainThread:2888806 [wandb_init.py:init():697] backend started and connected
2025-04-05 20:32:09,143 INFO MainThread:2888806 [wandb_init.py:init():790] updated telemetry
2025-04-05 20:32:09,162 INFO MainThread:2888806 [wandb_init.py:init():822] communicating run to backend with 90.0 second timeout
2025-04-05 20:32:09,682 INFO MainThread:2888806 [wandb_init.py:init():874] starting run threads in backend
2025-04-05 20:32:10,106 INFO MainThread:2888806 [wandb_run.py:_console_start():2374] atexit reg
2025-04-05 20:32:10,106 INFO MainThread:2888806 [wandb_run.py:_redirect():2224] redirect: wrap_raw
2025-04-05 20:32:10,106 INFO MainThread:2888806 [wandb_run.py:_redirect():2289] Wrapping output streams.
2025-04-05 20:32:10,106 INFO MainThread:2888806 [wandb_run.py:_redirect():2314] Redirects installed.
2025-04-05 20:32:10,112 INFO MainThread:2888806 [wandb_init.py:init():916] run started, returning control to user process
2025-04-05 20:45:27,036 INFO MainThread:2888806 [wandb_run.py:_finish():2100] finishing run day-one/safe-o1/jla7fqqr
2025-04-05 20:45:27,036 INFO MainThread:2888806 [wandb_run.py:_atexit_cleanup():2339] got exitcode: 0
2025-04-05 20:45:27,037 INFO MainThread:2888806 [wandb_run.py:_restore():2321] restore
2025-04-05 20:45:27,037 INFO MainThread:2888806 [wandb_run.py:_restore():2327] restore done
2025-04-05 20:45:29,432 INFO MainThread:2888806 [wandb_run.py:_footer_history_summary_info():3892] rendering history
2025-04-05 20:45:29,433 INFO MainThread:2888806 [wandb_run.py:_footer_history_summary_info():3924] rendering summary
2025-04-05 20:45:29,439 INFO MainThread:2888806 [wandb_run.py:_footer_sync_info():3853] logging synced files