Add files using upload-large-folder tool

.gitattributes

@@ -101,3 +101,5 @@ wandb/run-20241129_083813-1lx1o6j4/run-1lx1o6j4.wandb filter=lfs diff=lfs merge=
 wandb/run-20241101_200535-kh416n4m/run-kh416n4m.wandb filter=lfs diff=lfs merge=lfs -text
 wandb/run-20241101_202058-jijqbvs1/run-jijqbvs1.wandb filter=lfs diff=lfs merge=lfs -text
 wandb/run-20241129_083813-gsvlu1z8/run-gsvlu1z8.wandb filter=lfs diff=lfs merge=lfs -text
+wandb/run-20241030_231835-o1t74f3e/run-o1t74f3e.wandb filter=lfs diff=lfs merge=lfs -text
+wandb/run-20241030_233740-98qje3cr/run-98qje3cr.wandb filter=lfs diff=lfs merge=lfs -text

wandb/run-20241030_010305-y2ohxj86/files/config.yaml

@@ -0,0 +1,47 @@
+_wandb:
+    value:
+        cli_version: 0.18.5
+        m: []
+        python_version: 3.9.19
+        t:
+            "1":
+                - 1
+                - 5
+                - 11
+                - 49
+                - 51
+                - 53
+                - 55
+                - 71
+                - 98
+            "2":
+                - 1
+                - 5
+                - 11
+                - 49
+                - 51
+                - 53
+                - 55
+                - 71
+                - 98
+            "3":
+                - 13
+                - 23
+                - 55
+            "4": 3.9.19
+            "5": 0.18.5
+            "6": 4.45.1
+            "8":
+                - 5
+            "12": 0.18.5
+            "13": linux-x86_64
+batch_size:
+    value: 3
+epoch:
+    value: 7
+perturbation:
+    value: reverse_control
+seed:
+    value: 0
+train_set:
+    value: 10M

wandb/run-20241030_010305-y2ohxj86/files/output.log

@@ -0,0 +1,4 @@
+Traceback (most recent call last):
+  File "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py", line 162, in <module>
+    dataset_name = f"babylm_{args.perturbation}_{args.train_zset}_seed{args.seed}"
+AttributeError: 'Namespace' object has no attribute 'train_zset'

wandb/run-20241030_010305-y2ohxj86/files/wandb-metadata.json

@@ -0,0 +1,97 @@
+{
+  "os":  "Linux-5.4.0-162-generic-x86_64-with-glibc2.31",
+  "python":  "3.9.19",
+  "startedAt":  "2024-10-30T05:03:05.880128Z",
+  "args":  [
+    "--perturbation",
+    "reverse_control",
+    "--train_set",
+    "10M",
+    "--batch_size",
+    "3",
+    "--epoch",
+    "7",
+    "--seed",
+    "0"
+  ],
+  "program":  "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py",
+  "codePath":  "train/train_deep_wandb.py",
+  "git":  {
+    "remote":  "git@hf.co:Yaning1001/Impossible_llm.git",
+    "commit":  "ed716cdcfcdea02b67f7ed0f3504c2b1c8b737c4"
+  },
+  "email":  "yaning1001@gmail.com",
+  "root":  "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train",
+  "host":  "mms-large-2",
+  "username":  "chunhui",
+  "executable":  "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/bin/python",
+  "codePathLocal":  "train_deep_wandb.py",
+  "cpu_count":  32,
+  "cpu_count_logical":  64,
+  "gpu":  "NVIDIA RTX A6000",
+  "gpu_count":  8,
+  "disk":  {
+    "/":  {
+      "total":  "1888559353856",
+      "used":  "1719200043008"
+    }
+  },
+  "memory":  {
+    "total":  "202617098240"
+  },
+  "cpu":  {
+    "count":  32,
+    "countLogical":  64
+  },
+  "gpu_nvidia":  [
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    }
+  ],
+  "cudaVersion":  "11.8"
+}

wandb/run-20241030_010305-y2ohxj86/files/wandb-summary.json

@@ -0,0 +1 @@
+{"_wandb":{"runtime":0}}

wandb/run-20241030_010305-y2ohxj86/logs/debug.log

@@ -0,0 +1,27 @@
+2024-10-30 01:03:05,878 INFO    MainThread:320660 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
+2024-10-30 01:03:05,878 INFO    MainThread:320660 [wandb_setup.py:_flush():79] Configure stats pid to 320660
+2024-10-30 01:03:05,878 INFO    MainThread:320660 [wandb_setup.py:_flush():79] Loading settings from /home/chunhui/.config/wandb/settings
+2024-10-30 01:03:05,878 INFO    MainThread:320660 [wandb_setup.py:_flush():79] Loading settings from /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/settings
+2024-10-30 01:03:05,878 INFO    MainThread:320660 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2024-10-30 01:03:05,878 INFO    MainThread:320660 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
+2024-10-30 01:03:05,878 INFO    MainThread:320660 [wandb_setup.py:_flush():79] Inferring run settings from compute environment: {'program_relpath': 'train/train_deep_wandb.py', 'program_abspath': '/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py', 'program': '/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py'}
+2024-10-30 01:03:05,878 INFO    MainThread:320660 [wandb_setup.py:_flush():79] Applying login settings: {}
+2024-10-30 01:03:05,878 INFO    MainThread:320660 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241030_010305-y2ohxj86/logs/debug.log
+2024-10-30 01:03:05,878 INFO    MainThread:320660 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241030_010305-y2ohxj86/logs/debug-internal.log
+2024-10-30 01:03:05,878 INFO    MainThread:320660 [wandb_init.py:init():621] calling init triggers
+2024-10-30 01:03:05,878 INFO    MainThread:320660 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
+config: {}
+2024-10-30 01:03:05,878 INFO    MainThread:320660 [wandb_init.py:init():671] starting backend
+2024-10-30 01:03:05,878 INFO    MainThread:320660 [wandb_init.py:init():675] sending inform_init request
+2024-10-30 01:03:05,879 INFO    MainThread:320660 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-10-30 01:03:05,879 INFO    MainThread:320660 [wandb_init.py:init():688] backend started and connected
+2024-10-30 01:03:05,883 INFO    MainThread:320660 [wandb_init.py:init():783] updated telemetry
+2024-10-30 01:03:05,914 INFO    MainThread:320660 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
+2024-10-30 01:03:06,150 INFO    MainThread:320660 [wandb_init.py:init():867] starting run threads in backend
+2024-10-30 01:03:06,258 INFO    MainThread:320660 [wandb_run.py:_console_start():2463] atexit reg
+2024-10-30 01:03:06,258 INFO    MainThread:320660 [wandb_run.py:_redirect():2311] redirect: wrap_raw
+2024-10-30 01:03:06,258 INFO    MainThread:320660 [wandb_run.py:_redirect():2376] Wrapping output streams.
+2024-10-30 01:03:06,258 INFO    MainThread:320660 [wandb_run.py:_redirect():2401] Redirects installed.
+2024-10-30 01:03:06,260 INFO    MainThread:320660 [wandb_init.py:init():911] run started, returning control to user process
+2024-10-30 01:03:06,260 INFO    MainThread:320660 [wandb_run.py:_config_callback():1390] config_cb None None {'perturbation': 'reverse_control', 'train_set': '10M', 'batch_size': 3, 'epoch': 7, 'seed': 0}
+2024-10-30 01:03:06,261 WARNING MsgRouterThr:320660 [router.py:message_loop():77] message_loop has been closed

wandb/run-20241030_013141-ie4x9mdj/files/config.yaml

@@ -0,0 +1,47 @@
+_wandb:
+    value:
+        cli_version: 0.18.5
+        m: []
+        python_version: 3.9.19
+        t:
+            "1":
+                - 1
+                - 5
+                - 11
+                - 49
+                - 51
+                - 53
+                - 55
+                - 71
+                - 98
+            "2":
+                - 1
+                - 5
+                - 11
+                - 49
+                - 51
+                - 53
+                - 55
+                - 71
+                - 98
+            "3":
+                - 13
+                - 23
+                - 55
+            "4": 3.9.19
+            "5": 0.18.5
+            "6": 4.45.1
+            "8":
+                - 5
+            "12": 0.18.5
+            "13": linux-x86_64
+batch_size:
+    value: 3
+epoch:
+    value: 7
+perturbation:
+    value: reverse_full
+seed:
+    value: 0
+train_set:
+    value: 10M

wandb/run-20241030_013141-ie4x9mdj/files/output.log

@@ -0,0 +1,35 @@
+config.json: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 844/844 [00:00<00:00, 416kB/s]
+Downloading shards:   0%|                                                                                                                                        | 0/2 [01:04<?, ?it/s]
+Error in sys.excepthook:
+Traceback (most recent call last):
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/wandb/sdk/lib/exit_hooks.py", line 41, in exc_handler
+    def exc_handler(
+KeyboardInterrupt
+
+Original exception was:
+Traceback (most recent call last):
+  File "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py", line 172, in <module>
+    model = AutoModelForCausalLM.from_pretrained(model_name,
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/transformers/models/auto/auto_factory.py", line 564, in from_pretrained
+    return model_class.from_pretrained(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/transformers/modeling_utils.py", line 3769, in from_pretrained
+    resolved_archive_file, sharded_metadata = get_checkpoint_shard_files(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/transformers/utils/hub.py", line 1098, in get_checkpoint_shard_files
+    cached_filename = cached_file(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/transformers/utils/hub.py", line 403, in cached_file
+    resolved_file = hf_hub_download(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/huggingface_hub/utils/_deprecation.py", line 101, in inner_f
+    return f(*args, **kwargs)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
+    return fn(*args, **kwargs)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/huggingface_hub/file_download.py", line 1232, in hf_hub_download
+    return _hf_hub_download_to_cache_dir(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/huggingface_hub/file_download.py", line 1380, in _hf_hub_download_to_cache_dir
+    with WeakFileLock(lock_path):
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/contextlib.py", line 119, in __enter__
+    return next(self.gen)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/huggingface_hub/utils/_fixes.py", line 98, in WeakFileLock
+    lock.acquire()
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/filelock/_api.py", line 225, in acquire
+    time.sleep(poll_interval)
+KeyboardInterrupt

wandb/run-20241030_013141-ie4x9mdj/files/requirements.txt

@@ -0,0 +1,147 @@
+funcsigs==1.0.2
+sentry-sdk==2.17.0
+multiprocess==0.70.16
+numpy==1.26.2
+pluralizer==1.2.0
+debugpy==1.6.7
+nvidia-cudnn-cu11==8.5.0.96
+deepspeed==0.15.2
+data==0.4
+pandas==2.1.3
+tomli==2.0.1
+charset-normalizer==3.3.2
+attrs==24.2.0
+aiosignal==1.3.1
+fsspec==2023.10.0
+nvidia-cusparse-cu11==11.7.4.91
+zipp==3.12.0
+mypy-extensions==1.0.0
+datasets==3.0.1
+joblib==1.3.2
+hjson==3.1.0
+traitlets==5.7.1
+stack-data==0.6.0
+transformers==4.45.1
+sympy==1.11.1
+Pygments==2.15.0
+docker-pycreds==0.4.0
+dill==0.3.8
+wheel==0.44.0
+prompt-toolkit==3.0.30
+parso==0.8.3
+ipykernel==6.23.1
+pyarrow==17.0.0
+certifi==2023.11.17
+nvidia-cufft-cu11==10.9.0.58
+six==1.16.0
+pydantic==2.9.2
+click==8.1.7
+nest-asyncio==1.5.6
+gmpy2==2.1.0
+matplotlib==3.8.2
+scipy==1.11.4
+typing_extensions==4.12.2
+statsmodels==0.14.0
+huggingface-hub==0.25.0
+frozenlist==1.4.1
+gpustat==1.1.1
+nvidia-nvtx-cu11==11.7.91
+safetensors==0.4.5
+stanza==1.9.2
+decorator==5.1.1
+seaborn==0.13.0
+sentencepiece==0.2.0
+PyYAML==6.0.1
+black==24.8.0
+protobuf==4.25.1
+pickleshare==0.7.5
+peft==0.13.0
+triton==2.0.0
+nvidia-cuda-runtime-cu11==11.7.99
+Jinja2==3.1.2
+nvidia-cusolver-cu11==11.4.0.1
+executing==1.2.0
+jupyter_client==8.1.0
+pluggy==1.3.0
+cmake==3.30.3
+pytz==2023.3.post1
+aiohappyeyeballs==2.4.2
+kiwisolver==1.4.5
+py-cpuinfo==9.0.0
+Pillow==10.1.0
+ptyprocess==0.7.0
+importlib_resources==6.4.5
+GitPython==3.1.43
+importlib-metadata==6.0.0
+iniconfig==2.0.0
+scikit-learn==1.3.2
+exceptiongroup==1.1.0
+networkx==2.8.6
+accelerate==1.0.0
+nltk==3.8.1
+shutilwhich==1.1.0
+fonttools==4.45.1
+future==0.18.3
+aiohttp==3.10.6
+wcwidth==0.2.5
+idna==3.6
+filelock==3.12.2
+pathspec==0.12.1
+jupyter_core==5.1.0
+lit==18.1.8
+nvidia-curand-cu11==10.2.10.91
+nvidia-cublas-cu11==11.10.3.66
+nvidia-ml-py==12.560.30
+msgpack==1.1.0
+python-dateutil==2.8.2
+blessed==1.20.0
+packaging==23.0
+gitdb==4.0.11
+yarl==1.13.0
+emoji==2.8.0
+tzdata==2023.3
+cycler==0.12.1
+tornado==6.2
+backcall==0.2.0
+plotnine==0.12.4
+ninja==1.11.1.1
+latex==0.7.0
+wandb==0.18.5
+setproctitle==1.3.3
+threadpoolctl==3.2.0
+requests==2.32.3
+pyparsing==3.1.1
+smmap==5.0.1
+pyzmq==23.0.0
+async-timeout==4.0.3
+annotated-types==0.7.0
+matplotlib-inline==0.1.6
+latexcodec==1.0.0
+ipython==8.0.0
+patsy==0.5.3
+contourpy==1.2.0
+multidict==6.1.0
+mizani==0.9.3
+urllib3==2.1.0
+tokenizers==0.20.0
+MarkupSafe==2.1.2
+pip==24.2
+pexpect==4.8.0
+tqdm==4.66.5
+jedi==0.18.2
+pydantic_core==2.23.4
+tempdir==0.7.1
+mpmath==1.2.1
+setuptools==72.1.0
+pytest==7.4.3
+pure-eval==0.2.2
+psutil==5.9.1
+comm==0.1.2
+nvidia-cuda-cupti-cu11==11.7.101
+nvidia-cuda-nvrtc-cu11==11.7.99
+regex==2023.10.3
+platformdirs==2.5.2
+asttokens==2.2.1
+torch==2.0.0
+nvidia-nccl-cu11==2.14.3
+xxhash==3.5.0

wandb/run-20241030_013141-ie4x9mdj/files/wandb-metadata.json

@@ -0,0 +1,97 @@
+{
+  "os":  "Linux-5.4.0-162-generic-x86_64-with-glibc2.31",
+  "python":  "3.9.19",
+  "startedAt":  "2024-10-30T05:31:41.778763Z",
+  "args":  [
+    "--perturbation",
+    "reverse_full",
+    "--train_set",
+    "10M",
+    "--batch_size",
+    "3",
+    "--epoch",
+    "7",
+    "--seed",
+    "0"
+  ],
+  "program":  "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py",
+  "codePath":  "train/train_deep_wandb.py",
+  "git":  {
+    "remote":  "git@hf.co:Yaning1001/Impossible_llm.git",
+    "commit":  "ed716cdcfcdea02b67f7ed0f3504c2b1c8b737c4"
+  },
+  "email":  "yaning1001@gmail.com",
+  "root":  "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train",
+  "host":  "mms-large-2",
+  "username":  "chunhui",
+  "executable":  "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/bin/python",
+  "codePathLocal":  "train_deep_wandb.py",
+  "cpu_count":  32,
+  "cpu_count_logical":  64,
+  "gpu":  "NVIDIA RTX A6000",
+  "gpu_count":  8,
+  "disk":  {
+    "/":  {
+      "total":  "1888559353856",
+      "used":  "1709824413696"
+    }
+  },
+  "memory":  {
+    "total":  "202617098240"
+  },
+  "cpu":  {
+    "count":  32,
+    "countLogical":  64
+  },
+  "gpu_nvidia":  [
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    }
+  ],
+  "cudaVersion":  "11.8"
+}

wandb/run-20241030_013141-ie4x9mdj/files/wandb-summary.json

@@ -0,0 +1 @@
+{"_wandb":{"runtime":94}}

wandb/run-20241030_013141-ie4x9mdj/logs/debug-internal.log

@@ -0,0 +1,11 @@
+{"time":"2024-10-30T01:31:41.781725348-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-10-30T01:31:41.781739018-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241030_013141-ie4x9mdj/logs/debug-core.log"}
+{"time":"2024-10-30T01:31:41.891449316-04:00","level":"INFO","msg":"created new stream","id":"ie4x9mdj"}
+{"time":"2024-10-30T01:31:41.891511467-04:00","level":"INFO","msg":"stream: started","id":"ie4x9mdj"}
+{"time":"2024-10-30T01:31:41.891546597-04:00","level":"INFO","msg":"sender: started","stream_id":"ie4x9mdj"}
+{"time":"2024-10-30T01:31:41.891536947-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"ie4x9mdj"}}
+{"time":"2024-10-30T01:31:41.891563967-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"ie4x9mdj"}}
+{"time":"2024-10-30T01:31:42.085980534-04:00","level":"INFO","msg":"Starting system monitor"}
+{"time":"2024-10-30T01:33:16.59613712-04:00","level":"INFO","msg":"stream: closing","id":"ie4x9mdj"}
+{"time":"2024-10-30T01:33:16.59622584-04:00","level":"INFO","msg":"Stopping system monitor"}
+{"time":"2024-10-30T01:33:16.597521969-04:00","level":"INFO","msg":"Stopped system monitor"}

wandb/run-20241030_013141-ie4x9mdj/logs/debug.log

@@ -0,0 +1,27 @@
+2024-10-30 01:31:41,775 INFO    MainThread:335758 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
+2024-10-30 01:31:41,775 INFO    MainThread:335758 [wandb_setup.py:_flush():79] Configure stats pid to 335758
+2024-10-30 01:31:41,775 INFO    MainThread:335758 [wandb_setup.py:_flush():79] Loading settings from /home/chunhui/.config/wandb/settings
+2024-10-30 01:31:41,775 INFO    MainThread:335758 [wandb_setup.py:_flush():79] Loading settings from /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/settings
+2024-10-30 01:31:41,775 INFO    MainThread:335758 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2024-10-30 01:31:41,775 INFO    MainThread:335758 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
+2024-10-30 01:31:41,776 INFO    MainThread:335758 [wandb_setup.py:_flush():79] Inferring run settings from compute environment: {'program_relpath': 'train/train_deep_wandb.py', 'program_abspath': '/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py', 'program': '/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py'}
+2024-10-30 01:31:41,776 INFO    MainThread:335758 [wandb_setup.py:_flush():79] Applying login settings: {}
+2024-10-30 01:31:41,776 INFO    MainThread:335758 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241030_013141-ie4x9mdj/logs/debug.log
+2024-10-30 01:31:41,776 INFO    MainThread:335758 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241030_013141-ie4x9mdj/logs/debug-internal.log
+2024-10-30 01:31:41,776 INFO    MainThread:335758 [wandb_init.py:init():621] calling init triggers
+2024-10-30 01:31:41,776 INFO    MainThread:335758 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
+config: {}
+2024-10-30 01:31:41,776 INFO    MainThread:335758 [wandb_init.py:init():671] starting backend
+2024-10-30 01:31:41,776 INFO    MainThread:335758 [wandb_init.py:init():675] sending inform_init request
+2024-10-30 01:31:41,777 INFO    MainThread:335758 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-10-30 01:31:41,778 INFO    MainThread:335758 [wandb_init.py:init():688] backend started and connected
+2024-10-30 01:31:41,781 INFO    MainThread:335758 [wandb_init.py:init():783] updated telemetry
+2024-10-30 01:31:41,811 INFO    MainThread:335758 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
+2024-10-30 01:31:42,082 INFO    MainThread:335758 [wandb_init.py:init():867] starting run threads in backend
+2024-10-30 01:31:42,173 INFO    MainThread:335758 [wandb_run.py:_console_start():2463] atexit reg
+2024-10-30 01:31:42,173 INFO    MainThread:335758 [wandb_run.py:_redirect():2311] redirect: wrap_raw
+2024-10-30 01:31:42,174 INFO    MainThread:335758 [wandb_run.py:_redirect():2376] Wrapping output streams.
+2024-10-30 01:31:42,174 INFO    MainThread:335758 [wandb_run.py:_redirect():2401] Redirects installed.
+2024-10-30 01:31:42,175 INFO    MainThread:335758 [wandb_init.py:init():911] run started, returning control to user process
+2024-10-30 01:31:42,175 INFO    MainThread:335758 [wandb_run.py:_config_callback():1390] config_cb None None {'perturbation': 'reverse_full', 'train_set': '10M', 'batch_size': 3, 'epoch': 7, 'seed': 0}
+2024-10-30 01:33:16,596 WARNING MsgRouterThr:335758 [router.py:message_loop():77] message_loop has been closed

wandb/run-20241030_231835-o1t74f3e/run-o1t74f3e.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38ce013a7d495d13853ea95c875ac41642d801349e6a601213f10ccf7e0a2284
+size 655360

wandb/run-20241030_233740-98qje3cr/run-98qje3cr.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57002d575e8101f28e83eadd110e5e246e26a1c57b86b0a296f93e3044577c09
+size 851968

wandb/run-20241031_002020-t2atf7xf/files/config.yaml

@@ -0,0 +1,50 @@
+_wandb:
+    value:
+        cli_version: 0.18.5
+        m: []
+        python_version: 3.9.19
+        t:
+            "1":
+                - 1
+                - 5
+                - 11
+                - 49
+                - 51
+                - 53
+                - 55
+                - 71
+                - 98
+            "2":
+                - 1
+                - 5
+                - 11
+                - 49
+                - 51
+                - 53
+                - 55
+                - 71
+                - 98
+            "3":
+                - 2
+                - 13
+                - 23
+                - 55
+            "4": 3.9.19
+            "5": 0.18.5
+            "6": 4.45.1
+            "8":
+                - 5
+            "12": 0.18.5
+            "13": linux-x86_64
+batch_size:
+    value: 3
+epoch:
+    value: 6
+lr:
+    value: 1e-05
+perturbation:
+    value: reverse_full
+seed:
+    value: 0
+train_set:
+    value: 10M

wandb/run-20241031_002020-t2atf7xf/files/output.log

@@ -0,0 +1,14 @@
+Downloading shards: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [02:33<00:00, 76.70s/it]
+Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:05<00:00,  2.86s/it]
+tokenized_valid: Dataset({
+    features: ['input_ids', 'attention_mask'],
+    num_rows: 600
+})
+/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/transformers/training_args.py:1545: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
+  warnings.warn(
+[2024-10-31 00:23:02,660] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2024-10-31 00:23:12,358] [INFO] [comm.py:652:init_distributed] cdb=None
+Installed CUDA version 11.8 does not match the version torch was compiled with 11.7 but since the APIs are compatible, accepting this combination
+Using /home/chunhui/.cache/torch_extensions/py39_cu117 as PyTorch extensions root...
+Loading extension module cpu_adam...
+Time to load cpu_adam op: 5.453424692153931 seconds

wandb/run-20241031_002020-t2atf7xf/files/wandb-metadata.json

@@ -0,0 +1,97 @@
+{
+  "os":  "Linux-5.4.0-162-generic-x86_64-with-glibc2.31",
+  "python":  "3.9.19",
+  "startedAt":  "2024-10-31T04:20:20.142252Z",
+  "args":  [
+    "--perturbation",
+    "reverse_full",
+    "--train_set",
+    "10M",
+    "--batch_size",
+    "3",
+    "--epoch",
+    "6",
+    "--seed",
+    "0"
+  ],
+  "program":  "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py",
+  "codePath":  "train/train_deep_wandb.py",
+  "git":  {
+    "remote":  "git@hf.co:Yaning1001/Impossible_llm.git",
+    "commit":  "ed716cdcfcdea02b67f7ed0f3504c2b1c8b737c4"
+  },
+  "email":  "yaning1001@gmail.com",
+  "root":  "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train",
+  "host":  "mms-large-2",
+  "username":  "chunhui",
+  "executable":  "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/bin/python",
+  "codePathLocal":  "train_deep_wandb.py",
+  "cpu_count":  32,
+  "cpu_count_logical":  64,
+  "gpu":  "NVIDIA RTX A6000",
+  "gpu_count":  8,
+  "disk":  {
+    "/":  {
+      "total":  "1888559353856",
+      "used":  "1735153242112"
+    }
+  },
+  "memory":  {
+    "total":  "202617098240"
+  },
+  "cpu":  {
+    "count":  32,
+    "countLogical":  64
+  },
+  "gpu_nvidia":  [
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    }
+  ],
+  "cudaVersion":  "11.8"
+}

wandb/run-20241031_002020-t2atf7xf/files/wandb-summary.json

@@ -0,0 +1 @@
+{"_wandb":{"runtime":32219}}

wandb/run-20241031_002020-t2atf7xf/logs/debug-internal.log

@@ -0,0 +1,17 @@
+{"time":"2024-10-31T00:20:20.144856997-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-10-31T00:20:20.144879858-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241031_002020-t2atf7xf/logs/debug-core.log"}
+{"time":"2024-10-31T00:20:20.252562662-04:00","level":"INFO","msg":"created new stream","id":"t2atf7xf"}
+{"time":"2024-10-31T00:20:20.253136626-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"t2atf7xf"}}
+{"time":"2024-10-31T00:20:20.253250477-04:00","level":"INFO","msg":"sender: started","stream_id":"t2atf7xf"}
+{"time":"2024-10-31T00:20:20.253229647-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"t2atf7xf"}}
+{"time":"2024-10-31T00:20:20.253218787-04:00","level":"INFO","msg":"stream: started","id":"t2atf7xf"}
+{"time":"2024-10-31T00:20:21.434842431-04:00","level":"INFO","msg":"Starting system monitor"}
+{"time":"2024-10-31T09:17:19.826967528-04:00","level":"INFO","msg":"Stopping system monitor"}
+{"time":"2024-10-31T09:17:19.903947447-04:00","level":"INFO","msg":"Stopped system monitor"}
+{"time":"2024-10-31T09:17:20.764796815-04:00","level":"INFO","msg":"handler: operation stats","stats":{"operations":[{"desc":"saving job artifact","runtime_seconds":0.608821579}],"total_operations":1}}
+{"time":"2024-10-31T09:17:21.827392577-04:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2024-10-31T09:17:22.951276585-04:00","level":"INFO","msg":"stream: closing","id":"t2atf7xf"}
+{"time":"2024-10-31T09:17:22.951306535-04:00","level":"INFO","msg":"handler: closed","stream_id":{"value":"t2atf7xf"}}
+{"time":"2024-10-31T09:17:22.951341595-04:00","level":"INFO","msg":"writer: Close: closed","stream_id":{"value":"t2atf7xf"}}
+{"time":"2024-10-31T09:17:22.951367016-04:00","level":"INFO","msg":"sender: closed","stream_id":"t2atf7xf"}
+{"time":"2024-10-31T09:17:22.951451446-04:00","level":"INFO","msg":"stream: closed","id":"t2atf7xf"}

wandb/run-20241031_002020-t2atf7xf/logs/debug.log

@@ -0,0 +1,33 @@
+2024-10-31 00:20:20,139 INFO    MainThread:484457 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
+2024-10-31 00:20:20,139 INFO    MainThread:484457 [wandb_setup.py:_flush():79] Configure stats pid to 484457
+2024-10-31 00:20:20,139 INFO    MainThread:484457 [wandb_setup.py:_flush():79] Loading settings from /home/chunhui/.config/wandb/settings
+2024-10-31 00:20:20,139 INFO    MainThread:484457 [wandb_setup.py:_flush():79] Loading settings from /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/settings
+2024-10-31 00:20:20,139 INFO    MainThread:484457 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2024-10-31 00:20:20,139 INFO    MainThread:484457 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
+2024-10-31 00:20:20,139 INFO    MainThread:484457 [wandb_setup.py:_flush():79] Inferring run settings from compute environment: {'program_relpath': 'train/train_deep_wandb.py', 'program_abspath': '/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py', 'program': '/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py'}
+2024-10-31 00:20:20,139 INFO    MainThread:484457 [wandb_setup.py:_flush():79] Applying login settings: {}
+2024-10-31 00:20:20,139 INFO    MainThread:484457 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241031_002020-t2atf7xf/logs/debug.log
+2024-10-31 00:20:20,139 INFO    MainThread:484457 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241031_002020-t2atf7xf/logs/debug-internal.log
+2024-10-31 00:20:20,140 INFO    MainThread:484457 [wandb_init.py:init():621] calling init triggers
+2024-10-31 00:20:20,140 INFO    MainThread:484457 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
+config: {}
+2024-10-31 00:20:20,140 INFO    MainThread:484457 [wandb_init.py:init():671] starting backend
+2024-10-31 00:20:20,140 INFO    MainThread:484457 [wandb_init.py:init():675] sending inform_init request
+2024-10-31 00:20:20,141 INFO    MainThread:484457 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-10-31 00:20:20,141 INFO    MainThread:484457 [wandb_init.py:init():688] backend started and connected
+2024-10-31 00:20:20,147 INFO    MainThread:484457 [wandb_init.py:init():783] updated telemetry
+2024-10-31 00:20:20,170 INFO    MainThread:484457 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
+2024-10-31 00:20:21,431 INFO    MainThread:484457 [wandb_init.py:init():867] starting run threads in backend
+2024-10-31 00:20:21,530 INFO    MainThread:484457 [wandb_run.py:_console_start():2463] atexit reg
+2024-10-31 00:20:21,530 INFO    MainThread:484457 [wandb_run.py:_redirect():2311] redirect: wrap_raw
+2024-10-31 00:20:21,530 INFO    MainThread:484457 [wandb_run.py:_redirect():2376] Wrapping output streams.
+2024-10-31 00:20:21,530 INFO    MainThread:484457 [wandb_run.py:_redirect():2401] Redirects installed.
+2024-10-31 00:20:21,532 INFO    MainThread:484457 [wandb_init.py:init():911] run started, returning control to user process
+2024-10-31 00:20:21,532 INFO    MainThread:484457 [wandb_run.py:_config_callback():1390] config_cb None None {'perturbation': 'reverse_full', 'train_set': '10M', 'batch_size': 3, 'epoch': 6, 'seed': 0, 'lr': 1e-05}
+2024-10-31 09:17:19,684 INFO    MainThread:484457 [wandb_run.py:_finish():2158] finishing run yaning1001-dartmouth-college/impossible_llm_reverse/t2atf7xf
+2024-10-31 09:17:19,700 INFO    MainThread:484457 [wandb_run.py:_atexit_cleanup():2426] got exitcode: 0
+2024-10-31 09:17:19,748 INFO    MainThread:484457 [wandb_run.py:_restore():2408] restore
+2024-10-31 09:17:19,749 INFO    MainThread:484457 [wandb_run.py:_restore():2414] restore done
+2024-10-31 09:17:22,944 INFO    MainThread:484457 [wandb_run.py:_footer_history_summary_info():3975] rendering history
+2024-10-31 09:17:22,944 INFO    MainThread:484457 [wandb_run.py:_footer_history_summary_info():4007] rendering summary
+2024-10-31 09:17:22,950 INFO    MainThread:484457 [wandb_run.py:_footer_sync_info():3934] logging synced files

wandb/run-20241101_012612-71qkhmiu/files/config.yaml

@@ -0,0 +1,49 @@
+_wandb:
+    value:
+        cli_version: 0.18.5
+        m: []
+        python_version: 3.9.19
+        t:
+            "1":
+                - 1
+                - 5
+                - 11
+                - 49
+                - 51
+                - 53
+                - 55
+                - 71
+                - 98
+            "2":
+                - 1
+                - 5
+                - 11
+                - 49
+                - 51
+                - 53
+                - 55
+                - 71
+                - 98
+            "3":
+                - 13
+                - 23
+                - 55
+            "4": 3.9.19
+            "5": 0.18.5
+            "6": 4.45.1
+            "8":
+                - 5
+            "12": 0.18.5
+            "13": linux-x86_64
+batch_size:
+    value: 3
+epoch:
+    value: 6
+lr:
+    value: 5e-06
+perturbation:
+    value: shuffle_nodeterministic
+seed:
+    value: 0
+train_set:
+    value: 10M

wandb/run-20241101_012612-71qkhmiu/files/output.log

@@ -0,0 +1,12 @@
+Traceback (most recent call last):
+  File "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py", line 164, in <module>
+    dataset = load_dataset('babylm_dataset_test.py', name=dataset_name, trust_remote_code=True)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/datasets/load.py", line 2074, in load_dataset
+    builder_instance = load_dataset_builder(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/datasets/load.py", line 1832, in load_dataset_builder
+    builder_instance: DatasetBuilder = builder_cls(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/datasets/builder.py", line 342, in __init__
+    self.config, self.config_id = self._create_builder_config(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/datasets/builder.py", line 569, in _create_builder_config
+    raise ValueError(
+ValueError: BuilderConfig 'babylm_shuffle_nodeterministic_10M_seed0' not found. Available: ['babylm_hop_control_10M_seed0', 'babylm_hop_tokens4_10M_seed0', 'babylm_hop_words4_10M_seed0', 'babylm_reverse_control_10M_seed0', 'babylm_reverse_partial_10M_seed0', 'babylm_reverse_full_10M_seed0', 'babylm_shuffle_control_10M_seed0', 'babylm_shuffle_nondeterministic_10M_seed0', 'babylm_shuffle_deterministic21_10M_seed0', 'babylm_shuffle_deterministic57_10M_seed0', 'babylm_shuffle_deterministic84_10M_seed0', 'babylm_shuffle_local3_10M_seed0', 'babylm_shuffle_local5_10M_seed0', 'babylm_shuffle_local10_10M_seed0', 'babylm_shuffle_even_odd_10M_seed0']

wandb/run-20241101_012612-71qkhmiu/files/wandb-metadata.json

@@ -0,0 +1,97 @@
+{
+  "os":  "Linux-5.4.0-162-generic-x86_64-with-glibc2.31",
+  "python":  "3.9.19",
+  "startedAt":  "2024-11-01T05:26:12.633153Z",
+  "args":  [
+    "--perturbation",
+    "shuffle_nodeterministic",
+    "--train_set",
+    "10M",
+    "--batch_size",
+    "3",
+    "--epoch",
+    "6",
+    "--seed",
+    "0"
+  ],
+  "program":  "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py",
+  "codePath":  "train/train_deep_wandb.py",
+  "git":  {
+    "remote":  "git@hf.co:Yaning1001/Impossible_llm.git",
+    "commit":  "ed716cdcfcdea02b67f7ed0f3504c2b1c8b737c4"
+  },
+  "email":  "yaning1001@gmail.com",
+  "root":  "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train",
+  "host":  "mms-large-2",
+  "username":  "chunhui",
+  "executable":  "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/bin/python",
+  "codePathLocal":  "train_deep_wandb.py",
+  "cpu_count":  32,
+  "cpu_count_logical":  64,
+  "gpu":  "NVIDIA RTX A6000",
+  "gpu_count":  8,
+  "disk":  {
+    "/":  {
+      "total":  "1888559353856",
+      "used":  "1753992224768"
+    }
+  },
+  "memory":  {
+    "total":  "202617098240"
+  },
+  "cpu":  {
+    "count":  32,
+    "countLogical":  64
+  },
+  "gpu_nvidia":  [
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    }
+  ],
+  "cudaVersion":  "11.8"
+}

wandb/run-20241101_012612-71qkhmiu/files/wandb-summary.json

@@ -0,0 +1 @@
+{"_wandb":{"runtime":0}}

wandb/run-20241101_012612-71qkhmiu/logs/debug-internal.log

@@ -0,0 +1,16 @@
+{"time":"2024-11-01T01:26:12.636802094-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-11-01T01:26:12.636827225-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_012612-71qkhmiu/logs/debug-core.log"}
+{"time":"2024-11-01T01:26:12.746392665-04:00","level":"INFO","msg":"created new stream","id":"71qkhmiu"}
+{"time":"2024-11-01T01:26:12.746437585-04:00","level":"INFO","msg":"stream: started","id":"71qkhmiu"}
+{"time":"2024-11-01T01:26:12.746483116-04:00","level":"INFO","msg":"sender: started","stream_id":"71qkhmiu"}
+{"time":"2024-11-01T01:26:12.746489706-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"71qkhmiu"}}
+{"time":"2024-11-01T01:26:12.746479956-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"71qkhmiu"}}
+{"time":"2024-11-01T01:26:12.954567681-04:00","level":"INFO","msg":"Starting system monitor"}
+{"time":"2024-11-01T01:26:13.065163989-04:00","level":"INFO","msg":"stream: closing","id":"71qkhmiu"}
+{"time":"2024-11-01T01:26:13.065199569-04:00","level":"INFO","msg":"Stopping system monitor"}
+{"time":"2024-11-01T01:26:13.065819814-04:00","level":"INFO","msg":"Stopped system monitor"}
+{"time":"2024-11-01T01:26:13.640887088-04:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2024-11-01T01:26:13.772963695-04:00","level":"INFO","msg":"handler: closed","stream_id":{"value":"71qkhmiu"}}
+{"time":"2024-11-01T01:26:13.773103686-04:00","level":"INFO","msg":"sender: closed","stream_id":"71qkhmiu"}
+{"time":"2024-11-01T01:26:13.773082126-04:00","level":"INFO","msg":"writer: Close: closed","stream_id":{"value":"71qkhmiu"}}
+{"time":"2024-11-01T01:26:13.773279647-04:00","level":"INFO","msg":"stream: closed","id":"71qkhmiu"}

wandb/run-20241101_012612-71qkhmiu/logs/debug.log

@@ -0,0 +1,27 @@
+2024-11-01 01:26:12,631 INFO    MainThread:677633 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
+2024-11-01 01:26:12,631 INFO    MainThread:677633 [wandb_setup.py:_flush():79] Configure stats pid to 677633
+2024-11-01 01:26:12,631 INFO    MainThread:677633 [wandb_setup.py:_flush():79] Loading settings from /home/chunhui/.config/wandb/settings
+2024-11-01 01:26:12,631 INFO    MainThread:677633 [wandb_setup.py:_flush():79] Loading settings from /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/settings
+2024-11-01 01:26:12,631 INFO    MainThread:677633 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2024-11-01 01:26:12,631 INFO    MainThread:677633 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
+2024-11-01 01:26:12,631 INFO    MainThread:677633 [wandb_setup.py:_flush():79] Inferring run settings from compute environment: {'program_relpath': 'train/train_deep_wandb.py', 'program_abspath': '/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py', 'program': '/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py'}
+2024-11-01 01:26:12,631 INFO    MainThread:677633 [wandb_setup.py:_flush():79] Applying login settings: {}
+2024-11-01 01:26:12,631 INFO    MainThread:677633 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_012612-71qkhmiu/logs/debug.log
+2024-11-01 01:26:12,631 INFO    MainThread:677633 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_012612-71qkhmiu/logs/debug-internal.log
+2024-11-01 01:26:12,631 INFO    MainThread:677633 [wandb_init.py:init():621] calling init triggers
+2024-11-01 01:26:12,631 INFO    MainThread:677633 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
+config: {}
+2024-11-01 01:26:12,631 INFO    MainThread:677633 [wandb_init.py:init():671] starting backend
+2024-11-01 01:26:12,631 INFO    MainThread:677633 [wandb_init.py:init():675] sending inform_init request
+2024-11-01 01:26:12,632 INFO    MainThread:677633 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-11-01 01:26:12,633 INFO    MainThread:677633 [wandb_init.py:init():688] backend started and connected
+2024-11-01 01:26:12,635 INFO    MainThread:677633 [wandb_init.py:init():783] updated telemetry
+2024-11-01 01:26:12,659 INFO    MainThread:677633 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
+2024-11-01 01:26:12,949 INFO    MainThread:677633 [wandb_init.py:init():867] starting run threads in backend
+2024-11-01 01:26:13,053 INFO    MainThread:677633 [wandb_run.py:_console_start():2463] atexit reg
+2024-11-01 01:26:13,053 INFO    MainThread:677633 [wandb_run.py:_redirect():2311] redirect: wrap_raw
+2024-11-01 01:26:13,054 INFO    MainThread:677633 [wandb_run.py:_redirect():2376] Wrapping output streams.
+2024-11-01 01:26:13,054 INFO    MainThread:677633 [wandb_run.py:_redirect():2401] Redirects installed.
+2024-11-01 01:26:13,055 INFO    MainThread:677633 [wandb_init.py:init():911] run started, returning control to user process
+2024-11-01 01:26:13,055 INFO    MainThread:677633 [wandb_run.py:_config_callback():1390] config_cb None None {'perturbation': 'shuffle_nodeterministic', 'train_set': '10M', 'batch_size': 3, 'epoch': 6, 'seed': 0, 'lr': 5e-06}
+2024-11-01 01:26:13,065 WARNING MsgRouterThr:677633 [router.py:message_loop():77] message_loop has been closed

wandb/run-20241101_093116-a95c3tmd/files/output.log

@@ -0,0 +1,13 @@
+Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:18<00:00,  9.07s/it]
+tokenized_valid: Dataset({
+    features: ['input_ids', 'attention_mask'],
+    num_rows: 600
+})
+/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/transformers/training_args.py:1545: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
+  warnings.warn(
+[2024-11-01 09:31:36,949] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2024-11-01 09:31:44,876] [INFO] [comm.py:652:init_distributed] cdb=None
+Installed CUDA version 11.8 does not match the version torch was compiled with 11.7 but since the APIs are compatible, accepting this combination
+Using /home/chunhui/.cache/torch_extensions/py39_cu117 as PyTorch extensions root...
+Loading extension module cpu_adam...
+Time to load cpu_adam op: 4.957409381866455 seconds

wandb/run-20241101_093116-a95c3tmd/files/requirements.txt

@@ -0,0 +1,147 @@
+funcsigs==1.0.2
+sentry-sdk==2.17.0
+multiprocess==0.70.16
+numpy==1.26.2
+pluralizer==1.2.0
+debugpy==1.6.7
+nvidia-cudnn-cu11==8.5.0.96
+deepspeed==0.15.2
+data==0.4
+pandas==2.1.3
+tomli==2.0.1
+charset-normalizer==3.3.2
+attrs==24.2.0
+aiosignal==1.3.1
+fsspec==2023.10.0
+nvidia-cusparse-cu11==11.7.4.91
+zipp==3.12.0
+mypy-extensions==1.0.0
+datasets==3.0.1
+joblib==1.3.2
+hjson==3.1.0
+traitlets==5.7.1
+stack-data==0.6.0
+transformers==4.45.1
+sympy==1.11.1
+Pygments==2.15.0
+docker-pycreds==0.4.0
+dill==0.3.8
+wheel==0.44.0
+prompt-toolkit==3.0.30
+parso==0.8.3
+ipykernel==6.23.1
+pyarrow==17.0.0
+certifi==2023.11.17
+nvidia-cufft-cu11==10.9.0.58
+six==1.16.0
+pydantic==2.9.2
+click==8.1.7
+nest-asyncio==1.5.6
+gmpy2==2.1.0
+matplotlib==3.8.2
+scipy==1.11.4
+typing_extensions==4.12.2
+statsmodels==0.14.0
+huggingface-hub==0.25.0
+frozenlist==1.4.1
+gpustat==1.1.1
+nvidia-nvtx-cu11==11.7.91
+safetensors==0.4.5
+stanza==1.9.2
+decorator==5.1.1
+seaborn==0.13.0
+sentencepiece==0.2.0
+PyYAML==6.0.1
+black==24.8.0
+protobuf==4.25.1
+pickleshare==0.7.5
+peft==0.13.0
+triton==2.0.0
+nvidia-cuda-runtime-cu11==11.7.99
+Jinja2==3.1.2
+nvidia-cusolver-cu11==11.4.0.1
+executing==1.2.0
+jupyter_client==8.1.0
+pluggy==1.3.0
+cmake==3.30.3
+pytz==2023.3.post1
+aiohappyeyeballs==2.4.2
+kiwisolver==1.4.5
+py-cpuinfo==9.0.0
+Pillow==10.1.0
+ptyprocess==0.7.0
+importlib_resources==6.4.5
+GitPython==3.1.43
+importlib-metadata==6.0.0
+iniconfig==2.0.0
+scikit-learn==1.3.2
+exceptiongroup==1.1.0
+networkx==2.8.6
+accelerate==1.0.0
+nltk==3.8.1
+shutilwhich==1.1.0
+fonttools==4.45.1
+future==0.18.3
+aiohttp==3.10.6
+wcwidth==0.2.5
+idna==3.6
+filelock==3.12.2
+pathspec==0.12.1
+jupyter_core==5.1.0
+lit==18.1.8
+nvidia-curand-cu11==10.2.10.91
+nvidia-cublas-cu11==11.10.3.66
+nvidia-ml-py==12.560.30
+msgpack==1.1.0
+python-dateutil==2.8.2
+blessed==1.20.0
+packaging==23.0
+gitdb==4.0.11
+yarl==1.13.0
+emoji==2.8.0
+tzdata==2023.3
+cycler==0.12.1
+tornado==6.2
+backcall==0.2.0
+plotnine==0.12.4
+ninja==1.11.1.1
+latex==0.7.0
+wandb==0.18.5
+setproctitle==1.3.3
+threadpoolctl==3.2.0
+requests==2.32.3
+pyparsing==3.1.1
+smmap==5.0.1
+pyzmq==23.0.0
+async-timeout==4.0.3
+annotated-types==0.7.0
+matplotlib-inline==0.1.6
+latexcodec==1.0.0
+ipython==8.0.0
+patsy==0.5.3
+contourpy==1.2.0
+multidict==6.1.0
+mizani==0.9.3
+urllib3==2.1.0
+tokenizers==0.20.0
+MarkupSafe==2.1.2
+pip==24.2
+pexpect==4.8.0
+tqdm==4.66.5
+jedi==0.18.2
+pydantic_core==2.23.4
+tempdir==0.7.1
+mpmath==1.2.1
+setuptools==72.1.0
+pytest==7.4.3
+pure-eval==0.2.2
+psutil==5.9.1
+comm==0.1.2
+nvidia-cuda-cupti-cu11==11.7.101
+nvidia-cuda-nvrtc-cu11==11.7.99
+regex==2023.10.3
+platformdirs==2.5.2
+asttokens==2.2.1
+torch==2.0.0
+nvidia-nccl-cu11==2.14.3
+xxhash==3.5.0

wandb/run-20241101_093116-a95c3tmd/files/wandb-metadata.json

@@ -0,0 +1,97 @@
+{
+  "os":  "Linux-5.4.0-162-generic-x86_64-with-glibc2.31",
+  "python":  "3.9.19",
+  "startedAt":  "2024-11-01T13:31:16.545998Z",
+  "args":  [
+    "--perturbation",
+    "reverse_control",
+    "--train_set",
+    "10M",
+    "--batch_size",
+    "3",
+    "--epoch",
+    "7",
+    "--seed",
+    "0"
+  ],
+  "program":  "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py",
+  "codePath":  "train/train_deep_wandb.py",
+  "git":  {
+    "remote":  "git@hf.co:Yaning1001/Impossible_llm.git",
+    "commit":  "ed716cdcfcdea02b67f7ed0f3504c2b1c8b737c4"
+  },
+  "email":  "yaning1001@gmail.com",
+  "root":  "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train",
+  "host":  "mms-large-2",
+  "username":  "chunhui",
+  "executable":  "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/bin/python",
+  "codePathLocal":  "train_deep_wandb.py",
+  "cpu_count":  32,
+  "cpu_count_logical":  64,
+  "gpu":  "NVIDIA RTX A6000",
+  "gpu_count":  8,
+  "disk":  {
+    "/":  {
+      "total":  "1888559353856",
+      "used":  "1754716262400"
+    }
+  },
+  "memory":  {
+    "total":  "202617098240"
+  },
+  "cpu":  {
+    "count":  32,
+    "countLogical":  64
+  },
+  "gpu_nvidia":  [
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    }
+  ],
+  "cudaVersion":  "11.8"
+}

wandb/run-20241101_093116-a95c3tmd/logs/debug-internal.log

@@ -0,0 +1,8 @@
+{"time":"2024-11-01T09:31:16.5475748-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-11-01T09:31:16.54758968-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_093116-a95c3tmd/logs/debug-core.log"}
+{"time":"2024-11-01T09:31:16.65343917-04:00","level":"INFO","msg":"created new stream","id":"a95c3tmd"}
+{"time":"2024-11-01T09:31:16.65346742-04:00","level":"INFO","msg":"stream: started","id":"a95c3tmd"}
+{"time":"2024-11-01T09:31:16.65353825-04:00","level":"INFO","msg":"sender: started","stream_id":"a95c3tmd"}
+{"time":"2024-11-01T09:31:16.65349743-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"a95c3tmd"}}
+{"time":"2024-11-01T09:31:16.6535028-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"a95c3tmd"}}
+{"time":"2024-11-01T09:31:16.864150193-04:00","level":"INFO","msg":"Starting system monitor"}

wandb/run-20241101_093116-a95c3tmd/logs/debug.log

@@ -0,0 +1,26 @@
+2024-11-01 09:31:16,543 INFO    MainThread:781947 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
+2024-11-01 09:31:16,543 INFO    MainThread:781947 [wandb_setup.py:_flush():79] Configure stats pid to 781947
+2024-11-01 09:31:16,543 INFO    MainThread:781947 [wandb_setup.py:_flush():79] Loading settings from /home/chunhui/.config/wandb/settings
+2024-11-01 09:31:16,543 INFO    MainThread:781947 [wandb_setup.py:_flush():79] Loading settings from /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/settings
+2024-11-01 09:31:16,543 INFO    MainThread:781947 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2024-11-01 09:31:16,543 INFO    MainThread:781947 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
+2024-11-01 09:31:16,543 INFO    MainThread:781947 [wandb_setup.py:_flush():79] Inferring run settings from compute environment: {'program_relpath': 'train/train_deep_wandb.py', 'program_abspath': '/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py', 'program': '/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py'}
+2024-11-01 09:31:16,543 INFO    MainThread:781947 [wandb_setup.py:_flush():79] Applying login settings: {}
+2024-11-01 09:31:16,543 INFO    MainThread:781947 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_093116-a95c3tmd/logs/debug.log
+2024-11-01 09:31:16,543 INFO    MainThread:781947 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_093116-a95c3tmd/logs/debug-internal.log
+2024-11-01 09:31:16,543 INFO    MainThread:781947 [wandb_init.py:init():621] calling init triggers
+2024-11-01 09:31:16,544 INFO    MainThread:781947 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
+config: {}
+2024-11-01 09:31:16,544 INFO    MainThread:781947 [wandb_init.py:init():671] starting backend
+2024-11-01 09:31:16,544 INFO    MainThread:781947 [wandb_init.py:init():675] sending inform_init request
+2024-11-01 09:31:16,545 INFO    MainThread:781947 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-11-01 09:31:16,545 INFO    MainThread:781947 [wandb_init.py:init():688] backend started and connected
+2024-11-01 09:31:16,548 INFO    MainThread:781947 [wandb_init.py:init():783] updated telemetry
+2024-11-01 09:31:16,575 INFO    MainThread:781947 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
+2024-11-01 09:31:16,861 INFO    MainThread:781947 [wandb_init.py:init():867] starting run threads in backend
+2024-11-01 09:31:16,955 INFO    MainThread:781947 [wandb_run.py:_console_start():2463] atexit reg
+2024-11-01 09:31:16,955 INFO    MainThread:781947 [wandb_run.py:_redirect():2311] redirect: wrap_raw
+2024-11-01 09:31:16,955 INFO    MainThread:781947 [wandb_run.py:_redirect():2376] Wrapping output streams.
+2024-11-01 09:31:16,955 INFO    MainThread:781947 [wandb_run.py:_redirect():2401] Redirects installed.
+2024-11-01 09:31:16,956 INFO    MainThread:781947 [wandb_init.py:init():911] run started, returning control to user process
+2024-11-01 09:31:16,957 INFO    MainThread:781947 [wandb_run.py:_config_callback():1390] config_cb None None {'perturbation': 'reverse_control', 'train_set': '10M', 'batch_size': 3, 'epoch': 7, 'seed': 0, 'lr': 5e-06}

wandb/run-20241101_201927-k1t1l8u4/files/output.log

@@ -0,0 +1,13 @@
+Loading checkpoint shards: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:05<00:00,  2.56s/it]
+tokenized_valid: Dataset({
+    features: ['input_ids', 'attention_mask'],
+    num_rows: 600
+})
+/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/transformers/training_args.py:1545: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
+  warnings.warn(
+[2024-11-01 20:19:34,950] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2024-11-01 20:19:46,428] [INFO] [comm.py:652:init_distributed] cdb=None
+Installed CUDA version 11.8 does not match the version torch was compiled with 11.7 but since the APIs are compatible, accepting this combination
+Using /home/chunhui/.cache/torch_extensions/py39_cu117 as PyTorch extensions root...
+Loading extension module cpu_adam...
+Time to load cpu_adam op: 5.344139575958252 seconds

wandb/run-20241101_201927-k1t1l8u4/files/requirements.txt

@@ -0,0 +1,147 @@
+funcsigs==1.0.2
+sentry-sdk==2.17.0
+multiprocess==0.70.16
+numpy==1.26.2
+pluralizer==1.2.0
+debugpy==1.6.7
+nvidia-cudnn-cu11==8.5.0.96
+deepspeed==0.15.2
+data==0.4
+pandas==2.1.3
+tomli==2.0.1
+charset-normalizer==3.3.2
+attrs==24.2.0
+aiosignal==1.3.1
+fsspec==2023.10.0
+nvidia-cusparse-cu11==11.7.4.91
+zipp==3.12.0
+mypy-extensions==1.0.0
+datasets==3.0.1
+joblib==1.3.2
+hjson==3.1.0
+traitlets==5.7.1
+stack-data==0.6.0
+transformers==4.45.1
+sympy==1.11.1
+Pygments==2.15.0
+docker-pycreds==0.4.0
+dill==0.3.8
+wheel==0.44.0
+prompt-toolkit==3.0.30
+parso==0.8.3
+ipykernel==6.23.1
+pyarrow==17.0.0
+certifi==2023.11.17
+nvidia-cufft-cu11==10.9.0.58
+six==1.16.0
+pydantic==2.9.2
+click==8.1.7
+nest-asyncio==1.5.6
+gmpy2==2.1.0
+matplotlib==3.8.2
+scipy==1.11.4
+typing_extensions==4.12.2
+statsmodels==0.14.0
+huggingface-hub==0.25.0
+frozenlist==1.4.1
+gpustat==1.1.1
+nvidia-nvtx-cu11==11.7.91
+safetensors==0.4.5
+stanza==1.9.2
+decorator==5.1.1
+seaborn==0.13.0
+sentencepiece==0.2.0
+PyYAML==6.0.1
+black==24.8.0
+protobuf==4.25.1
+pickleshare==0.7.5
+peft==0.13.0
+triton==2.0.0
+nvidia-cuda-runtime-cu11==11.7.99
+Jinja2==3.1.2
+nvidia-cusolver-cu11==11.4.0.1
+executing==1.2.0
+jupyter_client==8.1.0
+pluggy==1.3.0
+cmake==3.30.3
+pytz==2023.3.post1
+aiohappyeyeballs==2.4.2
+kiwisolver==1.4.5
+py-cpuinfo==9.0.0
+Pillow==10.1.0
+ptyprocess==0.7.0
+importlib_resources==6.4.5
+GitPython==3.1.43
+importlib-metadata==6.0.0
+iniconfig==2.0.0
+scikit-learn==1.3.2
+exceptiongroup==1.1.0
+networkx==2.8.6
+accelerate==1.0.0
+nltk==3.8.1
+shutilwhich==1.1.0
+fonttools==4.45.1
+future==0.18.3
+aiohttp==3.10.6
+wcwidth==0.2.5
+idna==3.6
+filelock==3.12.2
+pathspec==0.12.1
+jupyter_core==5.1.0
+lit==18.1.8
+nvidia-curand-cu11==10.2.10.91
+nvidia-cublas-cu11==11.10.3.66
+nvidia-ml-py==12.560.30
+msgpack==1.1.0
+python-dateutil==2.8.2
+blessed==1.20.0
+packaging==23.0
+gitdb==4.0.11
+yarl==1.13.0
+emoji==2.8.0
+tzdata==2023.3
+cycler==0.12.1
+tornado==6.2
+backcall==0.2.0
+plotnine==0.12.4
+ninja==1.11.1.1
+latex==0.7.0
+wandb==0.18.5
+setproctitle==1.3.3
+threadpoolctl==3.2.0
+requests==2.32.3
+pyparsing==3.1.1
+smmap==5.0.1
+pyzmq==23.0.0
+async-timeout==4.0.3
+annotated-types==0.7.0
+matplotlib-inline==0.1.6
+latexcodec==1.0.0
+ipython==8.0.0
+patsy==0.5.3
+contourpy==1.2.0
+multidict==6.1.0
+mizani==0.9.3
+urllib3==2.1.0
+tokenizers==0.20.0
+MarkupSafe==2.1.2
+pip==24.2
+pexpect==4.8.0
+tqdm==4.66.5
+jedi==0.18.2
+pydantic_core==2.23.4
+tempdir==0.7.1
+mpmath==1.2.1
+setuptools==72.1.0
+pytest==7.4.3
+pure-eval==0.2.2
+psutil==5.9.1
+comm==0.1.2
+nvidia-cuda-cupti-cu11==11.7.101
+nvidia-cuda-nvrtc-cu11==11.7.99
+regex==2023.10.3
+platformdirs==2.5.2
+asttokens==2.2.1
+torch==2.0.0
+nvidia-nccl-cu11==2.14.3
+xxhash==3.5.0

wandb/run-20241101_201927-k1t1l8u4/files/wandb-metadata.json

@@ -0,0 +1,97 @@
+{
+  "os":  "Linux-5.4.0-162-generic-x86_64-with-glibc2.31",
+  "python":  "3.9.19",
+  "startedAt":  "2024-11-02T00:19:27.293042Z",
+  "args":  [
+    "--perturbation",
+    "shuffle_nondeterministic",
+    "--train_set",
+    "10M",
+    "--batch_size",
+    "3",
+    "--epoch",
+    "3",
+    "--seed",
+    "0"
+  ],
+  "program":  "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py",
+  "codePath":  "train/train_deep_wandb.py",
+  "git":  {
+    "remote":  "git@hf.co:Yaning1001/Impossible_llm.git",
+    "commit":  "ed716cdcfcdea02b67f7ed0f3504c2b1c8b737c4"
+  },
+  "email":  "yaning1001@gmail.com",
+  "root":  "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train",
+  "host":  "mms-large-2",
+  "username":  "chunhui",
+  "executable":  "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/bin/python",
+  "codePathLocal":  "train_deep_wandb.py",
+  "cpu_count":  32,
+  "cpu_count_logical":  64,
+  "gpu":  "NVIDIA RTX A6000",
+  "gpu_count":  8,
+  "disk":  {
+    "/":  {
+      "total":  "1888559353856",
+      "used":  "1754803675136"
+    }
+  },
+  "memory":  {
+    "total":  "202617098240"
+  },
+  "cpu":  {
+    "count":  32,
+    "countLogical":  64
+  },
+  "gpu_nvidia":  [
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    }
+  ],
+  "cudaVersion":  "11.8"
+}

wandb/run-20241101_201927-k1t1l8u4/logs/debug-internal.log

@@ -0,0 +1,8 @@
+{"time":"2024-11-01T20:19:27.294939863-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-11-01T20:19:27.294953393-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_201927-k1t1l8u4/logs/debug-core.log"}
+{"time":"2024-11-01T20:19:27.401466899-04:00","level":"INFO","msg":"created new stream","id":"k1t1l8u4"}
+{"time":"2024-11-01T20:19:27.40151827-04:00","level":"INFO","msg":"stream: started","id":"k1t1l8u4"}
+{"time":"2024-11-01T20:19:27.40160308-04:00","level":"INFO","msg":"sender: started","stream_id":"k1t1l8u4"}
+{"time":"2024-11-01T20:19:27.40156729-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"k1t1l8u4"}}
+{"time":"2024-11-01T20:19:27.40158983-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"k1t1l8u4"}}
+{"time":"2024-11-01T20:19:27.616032711-04:00","level":"INFO","msg":"Starting system monitor"}

wandb/run-20241101_201927-k1t1l8u4/logs/debug.log

@@ -0,0 +1,26 @@
+2024-11-01 20:19:27,291 INFO    MainThread:878458 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
+2024-11-01 20:19:27,291 INFO    MainThread:878458 [wandb_setup.py:_flush():79] Configure stats pid to 878458
+2024-11-01 20:19:27,291 INFO    MainThread:878458 [wandb_setup.py:_flush():79] Loading settings from /home/chunhui/.config/wandb/settings
+2024-11-01 20:19:27,291 INFO    MainThread:878458 [wandb_setup.py:_flush():79] Loading settings from /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/settings
+2024-11-01 20:19:27,291 INFO    MainThread:878458 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2024-11-01 20:19:27,291 INFO    MainThread:878458 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
+2024-11-01 20:19:27,291 INFO    MainThread:878458 [wandb_setup.py:_flush():79] Inferring run settings from compute environment: {'program_relpath': 'train/train_deep_wandb.py', 'program_abspath': '/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py', 'program': '/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py'}
+2024-11-01 20:19:27,291 INFO    MainThread:878458 [wandb_setup.py:_flush():79] Applying login settings: {}
+2024-11-01 20:19:27,291 INFO    MainThread:878458 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_201927-k1t1l8u4/logs/debug.log
+2024-11-01 20:19:27,291 INFO    MainThread:878458 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_201927-k1t1l8u4/logs/debug-internal.log
+2024-11-01 20:19:27,291 INFO    MainThread:878458 [wandb_init.py:init():621] calling init triggers
+2024-11-01 20:19:27,291 INFO    MainThread:878458 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
+config: {}
+2024-11-01 20:19:27,291 INFO    MainThread:878458 [wandb_init.py:init():671] starting backend
+2024-11-01 20:19:27,291 INFO    MainThread:878458 [wandb_init.py:init():675] sending inform_init request
+2024-11-01 20:19:27,292 INFO    MainThread:878458 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-11-01 20:19:27,292 INFO    MainThread:878458 [wandb_init.py:init():688] backend started and connected
+2024-11-01 20:19:27,296 INFO    MainThread:878458 [wandb_init.py:init():783] updated telemetry
+2024-11-01 20:19:27,328 INFO    MainThread:878458 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
+2024-11-01 20:19:27,613 INFO    MainThread:878458 [wandb_init.py:init():867] starting run threads in backend
+2024-11-01 20:19:27,719 INFO    MainThread:878458 [wandb_run.py:_console_start():2463] atexit reg
+2024-11-01 20:19:27,719 INFO    MainThread:878458 [wandb_run.py:_redirect():2311] redirect: wrap_raw
+2024-11-01 20:19:27,719 INFO    MainThread:878458 [wandb_run.py:_redirect():2376] Wrapping output streams.
+2024-11-01 20:19:27,719 INFO    MainThread:878458 [wandb_run.py:_redirect():2401] Redirects installed.
+2024-11-01 20:19:27,721 INFO    MainThread:878458 [wandb_init.py:init():911] run started, returning control to user process
+2024-11-01 20:19:27,721 INFO    MainThread:878458 [wandb_run.py:_config_callback():1390] config_cb None None {'perturbation': 'shuffle_nondeterministic', 'train_set': '10M', 'batch_size': 3, 'epoch': 3, 'seed': 0, 'lr': 5e-06}

wandb/run-20241105_163029-2rkpz70q/files/config.yaml

@@ -0,0 +1,49 @@
+_wandb:
+    value:
+        cli_version: 0.18.5
+        m: []
+        python_version: 3.9.19
+        t:
+            "1":
+                - 1
+                - 5
+                - 11
+                - 49
+                - 51
+                - 53
+                - 55
+                - 71
+                - 98
+            "2":
+                - 1
+                - 5
+                - 11
+                - 49
+                - 51
+                - 53
+                - 55
+                - 71
+                - 98
+            "3":
+                - 13
+                - 23
+                - 55
+            "4": 3.9.19
+            "5": 0.18.5
+            "6": 4.45.1
+            "8":
+                - 5
+            "12": 0.18.5
+            "13": linux-x86_64
+batch_size:
+    value: 3
+epoch:
+    value: 3
+lr:
+    value: 5e-06
+perturbation:
+    value: shuffle_deterministic57
+seed:
+    value: 0
+train_set:
+    value: 10M

wandb/run-20241105_163029-2rkpz70q/files/output.log

@@ -0,0 +1,64 @@
+config.json: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 844/844 [00:00<00:00, 289kB/s]
+model.safetensors.index.json: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████| 20.9k/20.9k [00:00<00:00, 25.5MB/s]
+Downloading shards:   0%|                                                                                                                                        | 0/2 [01:34<?, ?it/s]
+Traceback (most recent call last): 80%|█████████████████████████████████████████████████████████████████████████████████████▍                     | 3.96G/4.97G [01:34<00:23, 42.3MB/s]
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/huggingface_hub/file_download.py", line 541, in http_get
+    for chunk in r.iter_content(chunk_size=constants.DOWNLOAD_CHUNK_SIZE):
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/requests/models.py", line 820, in generate
+    yield from self.raw.stream(chunk_size, decode_content=True)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/urllib3/response.py", line 934, in stream
+    data = self.read(amt=amt, decode_content=decode_content)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/urllib3/response.py", line 877, in read
+    data = self._raw_read(amt)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/urllib3/response.py", line 812, in _raw_read
+    data = self._fp_read(amt) if not fp_closed else b""
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/urllib3/response.py", line 797, in _fp_read
+    return self._fp.read(amt) if amt is not None else self._fp.read()
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/http/client.py", line 463, in read
+    n = self.readinto(b)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/http/client.py", line 507, in readinto
+    n = self.fp.readinto(b)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/socket.py", line 704, in readinto
+    return self._sock.recv_into(b)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/ssl.py", line 1275, in recv_into
+    return self.read(nbytes, buffer)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/ssl.py", line 1133, in read
+    return self._sslobj.read(len, buffer)
+KeyboardInterrupt
+
+During handling of the above exception, another exception occurred:
+
+Traceback (most recent call last):
+  File "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py", line 174, in <module>
+    model = AutoModelForCausalLM.from_pretrained(model_name,
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/transformers/models/auto/auto_factory.py", line 564, in from_pretrained
+    return model_class.from_pretrained(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/transformers/modeling_utils.py", line 3769, in from_pretrained
+    resolved_archive_file, sharded_metadata = get_checkpoint_shard_files(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/transformers/utils/hub.py", line 1098, in get_checkpoint_shard_files
+    cached_filename = cached_file(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/transformers/utils/hub.py", line 403, in cached_file
+    resolved_file = hf_hub_download(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/huggingface_hub/utils/_deprecation.py", line 101, in inner_f
+    return f(*args, **kwargs)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
+    return fn(*args, **kwargs)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/huggingface_hub/file_download.py", line 1232, in hf_hub_download
+    return _hf_hub_download_to_cache_dir(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/huggingface_hub/file_download.py", line 1381, in _hf_hub_download_to_cache_dir
+    _download_to_tmp_and_move(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/huggingface_hub/file_download.py", line 1915, in _download_to_tmp_and_move
+    http_get(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/huggingface_hub/file_download.py", line 558, in http_get
+    return http_get(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/tqdm/std.py", line 1140, in __exit__
+    self.close()
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/tqdm/std.py", line 1302, in close
+    self.display(pos=0)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/tqdm/std.py", line 1495, in display
+    self.sp(self.__str__() if msg is None else msg)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/tqdm/std.py", line 1151, in __str__
+    return self.format_meter(**self.format_dict)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/tqdm/std.py", line 576, in format_meter
+    eta_dt = (datetime.now() + timedelta(seconds=remaining)
+KeyboardInterrupt

wandb/run-20241105_163029-2rkpz70q/files/requirements.txt

@@ -0,0 +1,147 @@
+funcsigs==1.0.2
+sentry-sdk==2.17.0
+multiprocess==0.70.16
+numpy==1.26.2
+pluralizer==1.2.0
+debugpy==1.6.7
+nvidia-cudnn-cu11==8.5.0.96
+deepspeed==0.15.2
+data==0.4
+pandas==2.1.3
+tomli==2.0.1
+charset-normalizer==3.3.2
+attrs==24.2.0
+aiosignal==1.3.1
+fsspec==2023.10.0
+nvidia-cusparse-cu11==11.7.4.91
+zipp==3.12.0
+mypy-extensions==1.0.0
+datasets==3.0.1
+joblib==1.3.2
+hjson==3.1.0
+traitlets==5.7.1
+stack-data==0.6.0
+transformers==4.45.1
+sympy==1.11.1
+Pygments==2.15.0
+docker-pycreds==0.4.0
+dill==0.3.8
+wheel==0.44.0
+prompt-toolkit==3.0.30
+parso==0.8.3
+ipykernel==6.23.1
+pyarrow==17.0.0
+certifi==2023.11.17
+nvidia-cufft-cu11==10.9.0.58
+six==1.16.0
+pydantic==2.9.2
+click==8.1.7
+nest-asyncio==1.5.6
+gmpy2==2.1.0
+matplotlib==3.8.2
+scipy==1.11.4
+typing_extensions==4.12.2
+statsmodels==0.14.0
+huggingface-hub==0.25.0
+frozenlist==1.4.1
+gpustat==1.1.1
+nvidia-nvtx-cu11==11.7.91
+safetensors==0.4.5
+stanza==1.9.2
+decorator==5.1.1
+seaborn==0.13.0
+sentencepiece==0.2.0
+PyYAML==6.0.1
+black==24.8.0
+protobuf==4.25.1
+pickleshare==0.7.5
+peft==0.13.0
+triton==2.0.0
+nvidia-cuda-runtime-cu11==11.7.99
+Jinja2==3.1.2
+nvidia-cusolver-cu11==11.4.0.1
+executing==1.2.0
+jupyter_client==8.1.0
+pluggy==1.3.0
+cmake==3.30.3
+pytz==2023.3.post1
+aiohappyeyeballs==2.4.2
+kiwisolver==1.4.5
+py-cpuinfo==9.0.0
+Pillow==10.1.0
+ptyprocess==0.7.0
+importlib_resources==6.4.5
+GitPython==3.1.43
+importlib-metadata==6.0.0
+iniconfig==2.0.0
+scikit-learn==1.3.2
+exceptiongroup==1.1.0
+networkx==2.8.6
+accelerate==1.0.0
+nltk==3.8.1
+shutilwhich==1.1.0
+fonttools==4.45.1
+future==0.18.3
+aiohttp==3.10.6
+wcwidth==0.2.5
+idna==3.6
+filelock==3.12.2
+pathspec==0.12.1
+jupyter_core==5.1.0
+lit==18.1.8
+nvidia-curand-cu11==10.2.10.91
+nvidia-cublas-cu11==11.10.3.66
+nvidia-ml-py==12.560.30
+msgpack==1.1.0
+python-dateutil==2.8.2
+blessed==1.20.0
+packaging==23.0
+gitdb==4.0.11
+yarl==1.13.0
+emoji==2.8.0
+tzdata==2023.3
+cycler==0.12.1
+tornado==6.2
+backcall==0.2.0
+plotnine==0.12.4
+ninja==1.11.1.1
+latex==0.7.0
+wandb==0.18.5
+setproctitle==1.3.3
+threadpoolctl==3.2.0
+requests==2.32.3
+pyparsing==3.1.1
+smmap==5.0.1
+pyzmq==23.0.0
+async-timeout==4.0.3
+annotated-types==0.7.0
+matplotlib-inline==0.1.6
+latexcodec==1.0.0
+ipython==8.0.0
+patsy==0.5.3
+contourpy==1.2.0
+multidict==6.1.0
+mizani==0.9.3
+urllib3==2.1.0
+tokenizers==0.20.0
+MarkupSafe==2.1.2
+pip==24.2
+pexpect==4.8.0
+tqdm==4.66.5
+jedi==0.18.2
+pydantic_core==2.23.4
+tempdir==0.7.1
+mpmath==1.2.1
+setuptools==72.1.0
+pytest==7.4.3
+pure-eval==0.2.2
+psutil==5.9.1
+comm==0.1.2
+nvidia-cuda-cupti-cu11==11.7.101
+nvidia-cuda-nvrtc-cu11==11.7.99
+regex==2023.10.3
+platformdirs==2.5.2
+asttokens==2.2.1
+torch==2.0.0
+nvidia-nccl-cu11==2.14.3
+xxhash==3.5.0

wandb/run-20241105_163029-2rkpz70q/files/wandb-metadata.json

@@ -0,0 +1,97 @@
+{
+  "os":  "Linux-5.4.0-162-generic-x86_64-with-glibc2.31",
+  "python":  "3.9.19",
+  "startedAt":  "2024-11-05T21:30:29.293234Z",
+  "args":  [
+    "--perturbation",
+    "shuffle_deterministic57",
+    "--train_set",
+    "10M",
+    "--batch_size",
+    "3",
+    "--epoch",
+    "3",
+    "--seed",
+    "0"
+  ],
+  "program":  "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py",
+  "codePath":  "train/train_deep_wandb.py",
+  "git":  {
+    "remote":  "git@hf.co:Yaning1001/Impossible_llm.git",
+    "commit":  "ed716cdcfcdea02b67f7ed0f3504c2b1c8b737c4"
+  },
+  "email":  "yaning1001@gmail.com",
+  "root":  "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train",
+  "host":  "mms-large-2",
+  "username":  "chunhui",
+  "executable":  "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/bin/python",
+  "codePathLocal":  "train_deep_wandb.py",
+  "cpu_count":  32,
+  "cpu_count_logical":  64,
+  "gpu":  "NVIDIA RTX A6000",
+  "gpu_count":  8,
+  "disk":  {
+    "/":  {
+      "total":  "1888559353856",
+      "used":  "1785984946176"
+    }
+  },
+  "memory":  {
+    "total":  "202617098240"
+  },
+  "cpu":  {
+    "count":  32,
+    "countLogical":  64
+  },
+  "gpu_nvidia":  [
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    },
+    {
+      "name":  "NVIDIA RTX A6000",
+      "memoryTotal":  "51527024640",
+      "cudaCores":  10752,
+      "architecture":  "Ampere"
+    }
+  ],
+  "cudaVersion":  "11.8"
+}

wandb/run-20241105_163029-2rkpz70q/files/wandb-summary.json

@@ -0,0 +1 @@
+{"_wandb":{"runtime":95}}

wandb/run-20241105_163029-2rkpz70q/logs/debug-internal.log

@@ -0,0 +1,11 @@
+{"time":"2024-11-05T16:30:29.296088295-05:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-11-05T16:30:29.296109055-05:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241105_163029-2rkpz70q/logs/debug-core.log"}
+{"time":"2024-11-05T16:30:29.403034023-05:00","level":"INFO","msg":"created new stream","id":"2rkpz70q"}
+{"time":"2024-11-05T16:30:29.403087833-05:00","level":"INFO","msg":"stream: started","id":"2rkpz70q"}
+{"time":"2024-11-05T16:30:29.403122053-05:00","level":"INFO","msg":"sender: started","stream_id":"2rkpz70q"}
+{"time":"2024-11-05T16:30:29.403116283-05:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"2rkpz70q"}}
+{"time":"2024-11-05T16:30:29.403141933-05:00","level":"INFO","msg":"handler: started","stream_id":{"value":"2rkpz70q"}}
+{"time":"2024-11-05T16:30:29.655903657-05:00","level":"INFO","msg":"Starting system monitor"}
+{"time":"2024-11-05T16:32:04.673881802-05:00","level":"INFO","msg":"stream: closing","id":"2rkpz70q"}
+{"time":"2024-11-05T16:32:04.673919782-05:00","level":"INFO","msg":"Stopping system monitor"}
+{"time":"2024-11-05T16:32:04.674440985-05:00","level":"INFO","msg":"Stopped system monitor"}

wandb/run-20241105_163029-2rkpz70q/logs/debug.log

@@ -0,0 +1,27 @@
+2024-11-05 16:30:29,290 INFO    MainThread:1779704 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
+2024-11-05 16:30:29,290 INFO    MainThread:1779704 [wandb_setup.py:_flush():79] Configure stats pid to 1779704
+2024-11-05 16:30:29,290 INFO    MainThread:1779704 [wandb_setup.py:_flush():79] Loading settings from /home/chunhui/.config/wandb/settings
+2024-11-05 16:30:29,290 INFO    MainThread:1779704 [wandb_setup.py:_flush():79] Loading settings from /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/settings
+2024-11-05 16:30:29,290 INFO    MainThread:1779704 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2024-11-05 16:30:29,290 INFO    MainThread:1779704 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
+2024-11-05 16:30:29,290 INFO    MainThread:1779704 [wandb_setup.py:_flush():79] Inferring run settings from compute environment: {'program_relpath': 'train/train_deep_wandb.py', 'program_abspath': '/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py', 'program': '/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py'}
+2024-11-05 16:30:29,290 INFO    MainThread:1779704 [wandb_setup.py:_flush():79] Applying login settings: {}
+2024-11-05 16:30:29,290 INFO    MainThread:1779704 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241105_163029-2rkpz70q/logs/debug.log
+2024-11-05 16:30:29,290 INFO    MainThread:1779704 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241105_163029-2rkpz70q/logs/debug-internal.log
+2024-11-05 16:30:29,290 INFO    MainThread:1779704 [wandb_init.py:init():621] calling init triggers
+2024-11-05 16:30:29,290 INFO    MainThread:1779704 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
+config: {}
+2024-11-05 16:30:29,290 INFO    MainThread:1779704 [wandb_init.py:init():671] starting backend
+2024-11-05 16:30:29,290 INFO    MainThread:1779704 [wandb_init.py:init():675] sending inform_init request
+2024-11-05 16:30:29,292 INFO    MainThread:1779704 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-11-05 16:30:29,292 INFO    MainThread:1779704 [wandb_init.py:init():688] backend started and connected
+2024-11-05 16:30:29,297 INFO    MainThread:1779704 [wandb_init.py:init():783] updated telemetry
+2024-11-05 16:30:29,329 INFO    MainThread:1779704 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
+2024-11-05 16:30:29,653 INFO    MainThread:1779704 [wandb_init.py:init():867] starting run threads in backend
+2024-11-05 16:30:29,738 INFO    MainThread:1779704 [wandb_run.py:_console_start():2463] atexit reg
+2024-11-05 16:30:29,738 INFO    MainThread:1779704 [wandb_run.py:_redirect():2311] redirect: wrap_raw
+2024-11-05 16:30:29,739 INFO    MainThread:1779704 [wandb_run.py:_redirect():2376] Wrapping output streams.
+2024-11-05 16:30:29,739 INFO    MainThread:1779704 [wandb_run.py:_redirect():2401] Redirects installed.
+2024-11-05 16:30:29,740 INFO    MainThread:1779704 [wandb_init.py:init():911] run started, returning control to user process
+2024-11-05 16:30:29,740 INFO    MainThread:1779704 [wandb_run.py:_config_callback():1390] config_cb None None {'perturbation': 'shuffle_deterministic57', 'train_set': '10M', 'batch_size': 3, 'epoch': 3, 'seed': 0, 'lr': 5e-06}
+2024-11-05 16:32:04,674 WARNING MsgRouterThr:1779704 [router.py:message_loop():77] message_loop has been closed

wandb/run-20241105_163029-ccve22u0/files/config.yaml

@@ -0,0 +1,49 @@
+_wandb:
+    value:
+        cli_version: 0.18.5
+        m: []
+        python_version: 3.9.19
+        t:
+            "1":
+                - 1
+                - 5
+                - 11
+                - 49
+                - 51
+                - 53
+                - 55
+                - 71
+                - 98
+            "2":
+                - 1
+                - 5
+                - 11
+                - 49
+                - 51
+                - 53
+                - 55
+                - 71
+                - 98
+            "3":
+                - 13
+                - 23
+                - 55
+            "4": 3.9.19
+            "5": 0.18.5
+            "6": 4.45.1
+            "8":
+                - 5
+            "12": 0.18.5
+            "13": linux-x86_64
+batch_size:
+    value: 3
+epoch:
+    value: 3
+lr:
+    value: 5e-06
+perturbation:
+    value: shuffle_deterministic57
+seed:
+    value: 0
+train_set:
+    value: 10M

wandb/run-20241105_163029-ccve22u0/files/output.log

@@ -0,0 +1,37 @@
+Downloading shards:   0%|                                                                                                                                        | 0/2 [00:00<?, ?it/s]Exception ignored in: <generator object tqdm.__iter__ at 0x7f8ba15e2cf0>
+Traceback (most recent call last):
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/tqdm/std.py", line 1196, in __iter__
+    self.close()
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/tqdm/std.py", line 1302, in close
+    self.display(pos=0)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/tqdm/std.py", line 1495, in display
+    self.sp(self.__str__() if msg is None else msg)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/tqdm/std.py", line 459, in print_status
+    fp_write('\r' + s + (' ' * max(last_len[0] - len_s, 0)))
+KeyboardInterrupt:
+Traceback (most recent call last):
+  File "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py", line 174, in <module>
+    model = AutoModelForCausalLM.from_pretrained(model_name,
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/transformers/models/auto/auto_factory.py", line 564, in from_pretrained
+    return model_class.from_pretrained(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/transformers/modeling_utils.py", line 3769, in from_pretrained
+    resolved_archive_file, sharded_metadata = get_checkpoint_shard_files(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/transformers/utils/hub.py", line 1098, in get_checkpoint_shard_files
+    cached_filename = cached_file(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/transformers/utils/hub.py", line 403, in cached_file
+    resolved_file = hf_hub_download(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/huggingface_hub/utils/_deprecation.py", line 101, in inner_f
+    return f(*args, **kwargs)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
+    return fn(*args, **kwargs)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/huggingface_hub/file_download.py", line 1232, in hf_hub_download
+    return _hf_hub_download_to_cache_dir(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/huggingface_hub/file_download.py", line 1380, in _hf_hub_download_to_cache_dir
+    with WeakFileLock(lock_path):
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/contextlib.py", line 119, in __enter__
+    return next(self.gen)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/huggingface_hub/utils/_fixes.py", line 98, in WeakFileLock
+    lock.acquire()
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/filelock/_api.py", line 225, in acquire
+    time.sleep(poll_interval)
+KeyboardInterrupt