Upload folder using huggingface_hub
Browse files- debug-internal.log +7 -7
- debug.log +26 -24
debug-internal.log
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
-
{"time":"2025-03-
|
| 2 |
-
{"time":"2025-03-
|
| 3 |
-
{"time":"2025-03-
|
| 4 |
-
{"time":"2025-03-
|
| 5 |
-
{"time":"2025-03-
|
| 6 |
-
{"time":"2025-03-
|
| 7 |
-
{"time":"2025-03-
|
|
|
|
| 1 |
+
{"time":"2025-03-28T20:38:44.692258573+08:00","level":"INFO","msg":"stream: starting","core version":"0.19.8","symlink path":"../outputs/test_13B/wandb/offline-run-20250328_203844-gc2qytpj/logs/debug-core.log"}
|
| 2 |
+
{"time":"2025-03-28T20:38:44.90653769+08:00","level":"INFO","msg":"created new stream","id":"gc2qytpj"}
|
| 3 |
+
{"time":"2025-03-28T20:38:44.90660149+08:00","level":"INFO","msg":"stream: started","id":"gc2qytpj"}
|
| 4 |
+
{"time":"2025-03-28T20:38:44.906615038+08:00","level":"INFO","msg":"handler: started","stream_id":"gc2qytpj"}
|
| 5 |
+
{"time":"2025-03-28T20:38:44.906633311+08:00","level":"INFO","msg":"writer: Do: started","stream_id":"gc2qytpj"}
|
| 6 |
+
{"time":"2025-03-28T20:38:44.90663431+08:00","level":"INFO","msg":"sender: started","stream_id":"gc2qytpj"}
|
| 7 |
+
{"time":"2025-03-28T20:38:44.910439284+08:00","level":"INFO","msg":"Starting system monitor"}
|
debug.log
CHANGED
|
@@ -1,24 +1,26 @@
|
|
| 1 |
-
2025-03-
|
| 2 |
-
2025-03-
|
| 3 |
-
2025-03-
|
| 4 |
-
2025-03-
|
| 5 |
-
2025-03-
|
| 6 |
-
2025-03-
|
| 7 |
-
2025-03-
|
| 8 |
-
2025-03-
|
| 9 |
-
2025-03-
|
| 10 |
-
config: {'train_cfgs': {'save_checkpoint':
|
| 11 |
-
2025-03-
|
| 12 |
-
2025-03-
|
| 13 |
-
2025-03-
|
| 14 |
-
2025-03-
|
| 15 |
-
2025-03-
|
| 16 |
-
2025-03-
|
| 17 |
-
2025-03-
|
| 18 |
-
2025-03-
|
| 19 |
-
2025-03-
|
| 20 |
-
2025-03-
|
| 21 |
-
2025-03-
|
| 22 |
-
2025-03-
|
| 23 |
-
2025-03-
|
| 24 |
-
2025-03-
|
|
|
|
|
|
|
|
|
| 1 |
+
2025-03-28 20:38:44,447 INFO MainThread:3871311 [wandb_setup.py:_flush():67] Current SDK version is 0.19.8
|
| 2 |
+
2025-03-28 20:38:44,447 INFO MainThread:3871311 [wandb_setup.py:_flush():67] Configure stats pid to 3871311
|
| 3 |
+
2025-03-28 20:38:44,447 INFO MainThread:3871311 [wandb_setup.py:_flush():67] Loading settings from /home/yangyaodong/.config/wandb/settings
|
| 4 |
+
2025-03-28 20:38:44,447 INFO MainThread:3871311 [wandb_setup.py:_flush():67] Loading settings from /aifs4su/yaodong/hantao/align-anything/scripts/wandb/settings
|
| 5 |
+
2025-03-28 20:38:44,447 INFO MainThread:3871311 [wandb_setup.py:_flush():67] Loading settings from environment variables
|
| 6 |
+
2025-03-28 20:38:44,447 INFO MainThread:3871311 [wandb_init.py:setup_run_log_directory():647] Logging user logs to ../outputs/test_13B/wandb/offline-run-20250328_203844-gc2qytpj/logs/debug.log
|
| 7 |
+
2025-03-28 20:38:44,447 INFO MainThread:3871311 [wandb_init.py:setup_run_log_directory():648] Logging internal logs to ../outputs/test_13B/wandb/offline-run-20250328_203844-gc2qytpj/logs/debug-internal.log
|
| 8 |
+
2025-03-28 20:38:44,447 INFO MainThread:3871311 [wandb_init.py:init():761] calling init triggers
|
| 9 |
+
2025-03-28 20:38:44,447 INFO MainThread:3871311 [wandb_init.py:init():766] wandb.init called with sweep_config: {}
|
| 10 |
+
config: {'train_cfgs': {'save_checkpoint': True, 'load_checkpoint': False, 'ds_cfgs': 'ds_z3_config.json', 'epochs': 3, 'seed': 42, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 1, 'gradient_accumulation_steps': 1, 'gradient_checkpointing': True, 'learning_rate': 1e-06, 'lr_scheduler_type': 'cosine', 'lr_warmup_ratio': 0.03, 'weight_decay': 0.0, 'adam_betas': [0.9, 0.95], 'bf16': True, 'fp16': False, 'eval_strategy': 'epoch', 'eval_interval': 10, 'regularization': 0.001, 'scale_coeff': 0.1, 'freeze_mm_proj': False, 'freeze_vision_tower': True, 'freeze_language_model': False}, 'data_cfgs': {'train_datasets': '/aifs4su/yaodong/hantao/datasets/AA_preference_vicuna-13b_cosi_cut/merged/top1-10', 'train_template': 'AA_TI2T_LLAVA', 'train_size': {}, 'train_split': 'train', 'train_name': 'text-image-to-text', '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': 'align-anything', 'log_run_name': 'dpo', 'output_dir': '../outputs/test_13B', 'cache_dir': {}, 'save_total_limit': 6}, 'model_cfgs': {'model_name_or_path': '/aifs4su/yaodong/hantao/models/llava-v1.6-vicuna-13b-hf', 'trust_remote_code': True, 'model_max_length': 2048}, 'special_tokens': {}, '_wandb': {}}
|
| 11 |
+
2025-03-28 20:38:44,447 INFO MainThread:3871311 [wandb_init.py:init():784] starting backend
|
| 12 |
+
2025-03-28 20:38:44,657 INFO MainThread:3871311 [wandb_init.py:init():788] sending inform_init request
|
| 13 |
+
2025-03-28 20:38:44,660 INFO MainThread:3871311 [backend.py:_multiprocessing_setup():101] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
|
| 14 |
+
2025-03-28 20:38:44,660 INFO MainThread:3871311 [wandb_init.py:init():798] backend started and connected
|
| 15 |
+
2025-03-28 20:38:44,662 INFO MainThread:3871311 [wandb_init.py:init():891] updated telemetry
|
| 16 |
+
2025-03-28 20:38:44,672 INFO MainThread:3871311 [wandb_init.py:init():915] communicating run to backend with 90.0 second timeout
|
| 17 |
+
2025-03-28 20:38:44,908 INFO MainThread:3871311 [wandb_init.py:init():990] starting run threads in backend
|
| 18 |
+
2025-03-28 20:38:45,071 INFO MainThread:3871311 [wandb_run.py:_console_start():2375] atexit reg
|
| 19 |
+
2025-03-28 20:38:45,071 INFO MainThread:3871311 [wandb_run.py:_redirect():2227] redirect: wrap_raw
|
| 20 |
+
2025-03-28 20:38:45,071 INFO MainThread:3871311 [wandb_run.py:_redirect():2292] Wrapping output streams.
|
| 21 |
+
2025-03-28 20:38:45,071 INFO MainThread:3871311 [wandb_run.py:_redirect():2315] Redirects installed.
|
| 22 |
+
2025-03-28 20:38:45,074 INFO MainThread:3871311 [wandb_init.py:init():1032] run started, returning control to user process
|
| 23 |
+
2025-03-28 20:47:40,230 INFO MainThread:3871311 [wandb_run.py:_finish():2112] finishing run align-anything/gc2qytpj
|
| 24 |
+
2025-03-28 20:47:40,230 INFO MainThread:3871311 [wandb_run.py:_atexit_cleanup():2340] got exitcode: 0
|
| 25 |
+
2025-03-28 20:47:40,230 INFO MainThread:3871311 [wandb_run.py:_restore():2322] restore
|
| 26 |
+
2025-03-28 20:47:40,230 INFO MainThread:3871311 [wandb_run.py:_restore():2328] restore done
|