Add files using upload-large-folder tool

wandb/run-20241030_010759-dim9v1es/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_010759-dim9v1es/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_011509-46hc4g2h/logs/debug-internal.log

@@ -0,0 +1,8 @@
+{"time":"2024-10-30T01:15:09.556689441-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-10-30T01:15:09.556707271-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241030_011509-46hc4g2h/logs/debug-core.log"}
+{"time":"2024-10-30T01:15:09.662171735-04:00","level":"INFO","msg":"created new stream","id":"46hc4g2h"}
+{"time":"2024-10-30T01:15:09.662202115-04:00","level":"INFO","msg":"stream: started","id":"46hc4g2h"}
+{"time":"2024-10-30T01:15:09.662224815-04:00","level":"INFO","msg":"sender: started","stream_id":"46hc4g2h"}
+{"time":"2024-10-30T01:15:09.662216935-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"46hc4g2h"}}
+{"time":"2024-10-30T01:15:09.662203965-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"46hc4g2h"}}
+{"time":"2024-10-30T01:15:09.829266444-04:00","level":"INFO","msg":"Starting system monitor"}

wandb/run-20241030_011509-46hc4g2h/logs/debug.log

@@ -0,0 +1,26 @@
+2024-10-30 01:15:09,552 INFO    MainThread:324928 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
+2024-10-30 01:15:09,552 INFO    MainThread:324928 [wandb_setup.py:_flush():79] Configure stats pid to 324928
+2024-10-30 01:15:09,552 INFO    MainThread:324928 [wandb_setup.py:_flush():79] Loading settings from /home/chunhui/.config/wandb/settings
+2024-10-30 01:15:09,552 INFO    MainThread:324928 [wandb_setup.py:_flush():79] Loading settings from /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/settings
+2024-10-30 01:15:09,552 INFO    MainThread:324928 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2024-10-30 01:15:09,552 INFO    MainThread:324928 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
+2024-10-30 01:15:09,552 INFO    MainThread:324928 [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 01:15:09,552 INFO    MainThread:324928 [wandb_setup.py:_flush():79] Applying login settings: {}
+2024-10-30 01:15:09,552 INFO    MainThread:324928 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241030_011509-46hc4g2h/logs/debug.log
+2024-10-30 01:15:09,552 INFO    MainThread:324928 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241030_011509-46hc4g2h/logs/debug-internal.log
+2024-10-30 01:15:09,552 INFO    MainThread:324928 [wandb_init.py:init():621] calling init triggers
+2024-10-30 01:15:09,552 INFO    MainThread:324928 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
+config: {}
+2024-10-30 01:15:09,552 INFO    MainThread:324928 [wandb_init.py:init():671] starting backend
+2024-10-30 01:15:09,552 INFO    MainThread:324928 [wandb_init.py:init():675] sending inform_init request
+2024-10-30 01:15:09,554 INFO    MainThread:324928 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-10-30 01:15:09,554 INFO    MainThread:324928 [wandb_init.py:init():688] backend started and connected
+2024-10-30 01:15:09,558 INFO    MainThread:324928 [wandb_init.py:init():783] updated telemetry
+2024-10-30 01:15:09,594 INFO    MainThread:324928 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
+2024-10-30 01:15:09,825 INFO    MainThread:324928 [wandb_init.py:init():867] starting run threads in backend
+2024-10-30 01:15:09,928 INFO    MainThread:324928 [wandb_run.py:_console_start():2463] atexit reg
+2024-10-30 01:15:09,928 INFO    MainThread:324928 [wandb_run.py:_redirect():2311] redirect: wrap_raw
+2024-10-30 01:15:09,929 INFO    MainThread:324928 [wandb_run.py:_redirect():2376] Wrapping output streams.
+2024-10-30 01:15:09,929 INFO    MainThread:324928 [wandb_run.py:_redirect():2401] Redirects installed.
+2024-10-30 01:15:09,931 INFO    MainThread:324928 [wandb_init.py:init():911] run started, returning control to user process
+2024-10-30 01:15:09,931 INFO    MainThread:324928 [wandb_run.py:_config_callback():1390] config_cb None None {'perturbation': 'reverse_control', 'train_set': '10M', 'batch_size': 3, 'epoch': 7, 'seed': 0}

wandb/run-20241030_012617-0h15y3p4/logs/debug-internal.log

@@ -0,0 +1,11 @@
+{"time":"2024-10-30T01:26:17.390480352-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-10-30T01:26:17.390492292-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241030_012617-0h15y3p4/logs/debug-core.log"}
+{"time":"2024-10-30T01:26:17.497198871-04:00","level":"INFO","msg":"created new stream","id":"0h15y3p4"}
+{"time":"2024-10-30T01:26:17.497231081-04:00","level":"INFO","msg":"stream: started","id":"0h15y3p4"}
+{"time":"2024-10-30T01:26:17.498386319-04:00","level":"INFO","msg":"sender: started","stream_id":"0h15y3p4"}
+{"time":"2024-10-30T01:26:17.498411899-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"0h15y3p4"}}
+{"time":"2024-10-30T01:26:17.498470659-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"0h15y3p4"}}
+{"time":"2024-10-30T01:26:17.697892892-04:00","level":"INFO","msg":"Starting system monitor"}
+{"time":"2024-10-30T01:26:32.054557486-04:00","level":"INFO","msg":"stream: closing","id":"0h15y3p4"}
+{"time":"2024-10-30T01:26:32.054592926-04:00","level":"INFO","msg":"Stopping system monitor"}
+{"time":"2024-10-30T01:26:32.055079549-04:00","level":"INFO","msg":"Stopped system monitor"}

wandb/run-20241030_112700-j5l8vh9z/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: 3
+perturbation:
+    value: reverse_control
+seed:
+    value: 0
+train_set:
+    value: 10M

wandb/run-20241030_112700-j5l8vh9z/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_112700-j5l8vh9z/files/wandb-summary.json

@@ -0,0 +1 @@
+{"_wandb":{"runtime":93}}

wandb/run-20241030_225833-frh96rd1/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":  "2024-10-31T02:58:33.401365Z",
+  "args":  [
+    "--perturbation",
+    "reverse_full",
+    "--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":  "1710970519552"
+    }
+  },
+  "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_225833-frh96rd1/logs/debug-internal.log

@@ -0,0 +1,8 @@
+{"time":"2024-10-30T22:58:33.403200163-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-10-30T22:58:33.403213043-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241030_225833-frh96rd1/logs/debug-core.log"}
+{"time":"2024-10-30T22:58:33.510780385-04:00","level":"INFO","msg":"created new stream","id":"frh96rd1"}
+{"time":"2024-10-30T22:58:33.510819765-04:00","level":"INFO","msg":"stream: started","id":"frh96rd1"}
+{"time":"2024-10-30T22:58:33.510841375-04:00","level":"INFO","msg":"sender: started","stream_id":"frh96rd1"}
+{"time":"2024-10-30T22:58:33.510849875-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"frh96rd1"}}
+{"time":"2024-10-30T22:58:33.510823865-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"frh96rd1"}}
+{"time":"2024-10-30T22:58:33.680830326-04:00","level":"INFO","msg":"Starting system monitor"}

wandb/run-20241030_225833-frh96rd1/logs/debug.log

@@ -0,0 +1,26 @@
+2024-10-30 22:58:33,399 INFO    MainThread:451913 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
+2024-10-30 22:58:33,399 INFO    MainThread:451913 [wandb_setup.py:_flush():79] Configure stats pid to 451913
+2024-10-30 22:58:33,399 INFO    MainThread:451913 [wandb_setup.py:_flush():79] Loading settings from /home/chunhui/.config/wandb/settings
+2024-10-30 22:58:33,399 INFO    MainThread:451913 [wandb_setup.py:_flush():79] Loading settings from /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/settings
+2024-10-30 22:58:33,399 INFO    MainThread:451913 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2024-10-30 22:58:33,399 INFO    MainThread:451913 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
+2024-10-30 22:58:33,399 INFO    MainThread:451913 [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 22:58:33,399 INFO    MainThread:451913 [wandb_setup.py:_flush():79] Applying login settings: {}
+2024-10-30 22:58:33,399 INFO    MainThread:451913 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241030_225833-frh96rd1/logs/debug.log
+2024-10-30 22:58:33,399 INFO    MainThread:451913 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241030_225833-frh96rd1/logs/debug-internal.log
+2024-10-30 22:58:33,399 INFO    MainThread:451913 [wandb_init.py:init():621] calling init triggers
+2024-10-30 22:58:33,399 INFO    MainThread:451913 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
+config: {}
+2024-10-30 22:58:33,399 INFO    MainThread:451913 [wandb_init.py:init():671] starting backend
+2024-10-30 22:58:33,400 INFO    MainThread:451913 [wandb_init.py:init():675] sending inform_init request
+2024-10-30 22:58:33,400 INFO    MainThread:451913 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-10-30 22:58:33,401 INFO    MainThread:451913 [wandb_init.py:init():688] backend started and connected
+2024-10-30 22:58:33,403 INFO    MainThread:451913 [wandb_init.py:init():783] updated telemetry
+2024-10-30 22:58:33,443 INFO    MainThread:451913 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
+2024-10-30 22:58:33,677 INFO    MainThread:451913 [wandb_init.py:init():867] starting run threads in backend
+2024-10-30 22:58:33,841 INFO    MainThread:451913 [wandb_run.py:_console_start():2463] atexit reg
+2024-10-30 22:58:33,841 INFO    MainThread:451913 [wandb_run.py:_redirect():2311] redirect: wrap_raw
+2024-10-30 22:58:33,841 INFO    MainThread:451913 [wandb_run.py:_redirect():2376] Wrapping output streams.
+2024-10-30 22:58:33,842 INFO    MainThread:451913 [wandb_run.py:_redirect():2401] Redirects installed.
+2024-10-30 22:58:33,844 INFO    MainThread:451913 [wandb_init.py:init():911] run started, returning control to user process
+2024-10-30 22:58:33,844 INFO    MainThread:451913 [wandb_run.py:_config_callback():1390] config_cb None None {'perturbation': 'reverse_full', 'train_set': '10M', 'batch_size': 3, 'epoch': 3, 'seed': 0}

wandb/run-20241031_000839-cu7972v5/files/output.log

@@ -0,0 +1,13 @@
+Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:18<00:00,  9.23s/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 00:09:00,035] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2024-10-31 00:09:09,768] [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: 5.32434344291687 seconds

wandb/run-20241031_000839-cu7972v5/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-20241031_000839-cu7972v5/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":  "2024-10-31T04:08:39.234664Z",
+  "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":  "1727270539264"
+    }
+  },
+  "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_000839-cu7972v5/logs/debug-internal.log

@@ -0,0 +1,8 @@
+{"time":"2024-10-31T00:08:39.237073048-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-10-31T00:08:39.237089559-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241031_000839-cu7972v5/logs/debug-core.log"}
+{"time":"2024-10-31T00:08:39.341923634-04:00","level":"INFO","msg":"created new stream","id":"cu7972v5"}
+{"time":"2024-10-31T00:08:39.341944484-04:00","level":"INFO","msg":"stream: started","id":"cu7972v5"}
+{"time":"2024-10-31T00:08:39.341969834-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"cu7972v5"}}
+{"time":"2024-10-31T00:08:39.341961834-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"cu7972v5"}}
+{"time":"2024-10-31T00:08:39.341998404-04:00","level":"INFO","msg":"sender: started","stream_id":"cu7972v5"}
+{"time":"2024-10-31T00:08:39.509463672-04:00","level":"INFO","msg":"Starting system monitor"}

wandb/run-20241031_000839-cu7972v5/logs/debug.log

@@ -0,0 +1,26 @@
+2024-10-31 00:08:39,232 INFO    MainThread:477298 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
+2024-10-31 00:08:39,232 INFO    MainThread:477298 [wandb_setup.py:_flush():79] Configure stats pid to 477298
+2024-10-31 00:08:39,232 INFO    MainThread:477298 [wandb_setup.py:_flush():79] Loading settings from /home/chunhui/.config/wandb/settings
+2024-10-31 00:08:39,232 INFO    MainThread:477298 [wandb_setup.py:_flush():79] Loading settings from /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/settings
+2024-10-31 00:08:39,232 INFO    MainThread:477298 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2024-10-31 00:08:39,232 INFO    MainThread:477298 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
+2024-10-31 00:08:39,232 INFO    MainThread:477298 [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 00:08:39,232 INFO    MainThread:477298 [wandb_setup.py:_flush():79] Applying login settings: {}
+2024-10-31 00:08:39,232 INFO    MainThread:477298 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241031_000839-cu7972v5/logs/debug.log
+2024-10-31 00:08:39,232 INFO    MainThread:477298 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241031_000839-cu7972v5/logs/debug-internal.log
+2024-10-31 00:08:39,232 INFO    MainThread:477298 [wandb_init.py:init():621] calling init triggers
+2024-10-31 00:08:39,232 INFO    MainThread:477298 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
+config: {}
+2024-10-31 00:08:39,232 INFO    MainThread:477298 [wandb_init.py:init():671] starting backend
+2024-10-31 00:08:39,232 INFO    MainThread:477298 [wandb_init.py:init():675] sending inform_init request
+2024-10-31 00:08:39,234 INFO    MainThread:477298 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-10-31 00:08:39,234 INFO    MainThread:477298 [wandb_init.py:init():688] backend started and connected
+2024-10-31 00:08:39,239 INFO    MainThread:477298 [wandb_init.py:init():783] updated telemetry
+2024-10-31 00:08:39,268 INFO    MainThread:477298 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
+2024-10-31 00:08:39,506 INFO    MainThread:477298 [wandb_init.py:init():867] starting run threads in backend
+2024-10-31 00:08:39,612 INFO    MainThread:477298 [wandb_run.py:_console_start():2463] atexit reg
+2024-10-31 00:08:39,612 INFO    MainThread:477298 [wandb_run.py:_redirect():2311] redirect: wrap_raw
+2024-10-31 00:08:39,612 INFO    MainThread:477298 [wandb_run.py:_redirect():2376] Wrapping output streams.
+2024-10-31 00:08:39,612 INFO    MainThread:477298 [wandb_run.py:_redirect():2401] Redirects installed.
+2024-10-31 00:08:39,613 INFO    MainThread:477298 [wandb_init.py:init():911] run started, returning control to user process
+2024-10-31 00:08:39,614 INFO    MainThread:477298 [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}

wandb/run-20241031_001055-32u9qnul/logs/debug-internal.log

@@ -0,0 +1,8 @@
+{"time":"2024-10-31T00:10:55.97661836-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-10-31T00:10:55.97666224-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241031_001055-32u9qnul/logs/debug-core.log"}
+{"time":"2024-10-31T00:10:56.085295995-04:00","level":"INFO","msg":"created new stream","id":"32u9qnul"}
+{"time":"2024-10-31T00:10:56.085346146-04:00","level":"INFO","msg":"stream: started","id":"32u9qnul"}
+{"time":"2024-10-31T00:10:56.085429147-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"32u9qnul"}}
+{"time":"2024-10-31T00:10:56.085619888-04:00","level":"INFO","msg":"sender: started","stream_id":"32u9qnul"}
+{"time":"2024-10-31T00:10:56.085632288-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"32u9qnul"}}
+{"time":"2024-10-31T00:10:56.308225083-04:00","level":"INFO","msg":"Starting system monitor"}

wandb/run-20241031_001055-32u9qnul/logs/debug.log

@@ -0,0 +1,26 @@
+2024-10-31 00:10:55,970 INFO    MainThread:479383 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
+2024-10-31 00:10:55,970 INFO    MainThread:479383 [wandb_setup.py:_flush():79] Configure stats pid to 479383
+2024-10-31 00:10:55,971 INFO    MainThread:479383 [wandb_setup.py:_flush():79] Loading settings from /home/chunhui/.config/wandb/settings
+2024-10-31 00:10:55,971 INFO    MainThread:479383 [wandb_setup.py:_flush():79] Loading settings from /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/settings
+2024-10-31 00:10:55,971 INFO    MainThread:479383 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2024-10-31 00:10:55,971 INFO    MainThread:479383 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
+2024-10-31 00:10:55,971 INFO    MainThread:479383 [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 00:10:55,971 INFO    MainThread:479383 [wandb_setup.py:_flush():79] Applying login settings: {}
+2024-10-31 00:10:55,971 INFO    MainThread:479383 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241031_001055-32u9qnul/logs/debug.log
+2024-10-31 00:10:55,971 INFO    MainThread:479383 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241031_001055-32u9qnul/logs/debug-internal.log
+2024-10-31 00:10:55,971 INFO    MainThread:479383 [wandb_init.py:init():621] calling init triggers
+2024-10-31 00:10:55,971 INFO    MainThread:479383 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
+config: {}
+2024-10-31 00:10:55,971 INFO    MainThread:479383 [wandb_init.py:init():671] starting backend
+2024-10-31 00:10:55,971 INFO    MainThread:479383 [wandb_init.py:init():675] sending inform_init request
+2024-10-31 00:10:55,972 INFO    MainThread:479383 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-10-31 00:10:55,973 INFO    MainThread:479383 [wandb_init.py:init():688] backend started and connected
+2024-10-31 00:10:55,976 INFO    MainThread:479383 [wandb_init.py:init():783] updated telemetry
+2024-10-31 00:10:56,016 INFO    MainThread:479383 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
+2024-10-31 00:10:56,304 INFO    MainThread:479383 [wandb_init.py:init():867] starting run threads in backend
+2024-10-31 00:10:56,408 INFO    MainThread:479383 [wandb_run.py:_console_start():2463] atexit reg
+2024-10-31 00:10:56,408 INFO    MainThread:479383 [wandb_run.py:_redirect():2311] redirect: wrap_raw
+2024-10-31 00:10:56,409 INFO    MainThread:479383 [wandb_run.py:_redirect():2376] Wrapping output streams.
+2024-10-31 00:10:56,409 INFO    MainThread:479383 [wandb_run.py:_redirect():2401] Redirects installed.
+2024-10-31 00:10:56,410 INFO    MainThread:479383 [wandb_init.py:init():911] run started, returning control to user process
+2024-10-31 00:10:56,410 INFO    MainThread:479383 [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}

wandb/run-20241031_114700-jx2hqvx3/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":  "2024-10-31T15:47:00.195452Z",
+  "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":  "1753158594560"
+    }
+  },
+  "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_012438-61w48leq/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_012438-61w48leq/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_012438-61w48leq/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":  "2024-11-01T05:24:38.161201Z",
+  "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":  "1753992159232"
+    }
+  },
+  "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_012438-61w48leq/files/wandb-summary.json

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

wandb/run-20241101_012734-m18lsdzn/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":  "2024-11-01T05:27:34.134177Z",
+  "args":  [
+    "--perturbation",
+    "shuffle_nondeterministic",
+    "--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":  "1753992269824"
+    }
+  },
+  "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_012734-m18lsdzn/logs/debug-internal.log

@@ -0,0 +1,8 @@
+{"time":"2024-11-01T01:27:34.136793008-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-11-01T01:27:34.136814509-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_012734-m18lsdzn/logs/debug-core.log"}
+{"time":"2024-11-01T01:27:34.243830731-04:00","level":"INFO","msg":"created new stream","id":"m18lsdzn"}
+{"time":"2024-11-01T01:27:34.243863612-04:00","level":"INFO","msg":"stream: started","id":"m18lsdzn"}
+{"time":"2024-11-01T01:27:34.244001533-04:00","level":"INFO","msg":"sender: started","stream_id":"m18lsdzn"}
+{"time":"2024-11-01T01:27:34.243939362-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"m18lsdzn"}}
+{"time":"2024-11-01T01:27:34.243890052-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"m18lsdzn"}}
+{"time":"2024-11-01T01:27:34.468881692-04:00","level":"INFO","msg":"Starting system monitor"}

wandb/run-20241101_200517-iopieyi0/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_nondeterministic
+seed:
+    value: 0
+train_set:
+    value: 10M

wandb/run-20241101_200517-iopieyi0/files/output.log

@@ -0,0 +1,42 @@
+Downloading shards:   0%|                                                                                                                                                               | 0/2 [00:07<?, ?it/s]
+Error in sys.excepthook:
+Traceback (most recent call last):
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/linecache.py", line 46, in getlines
+    return updatecache(filename, module_globals)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/linecache.py", line 136, in updatecache
+    with tokenize.open(fullname) as fp:
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/tokenize.py", line 394, in open
+    encoding, lines = detect_encoding(buffer.readline)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/tokenize.py", line 363, in detect_encoding
+    first = read_or_stop()
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/tokenize.py", line 321, in read_or_stop
+    return readline()
+KeyboardInterrupt
+
+Original exception was:
+Traceback (most recent call last):
+  File "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py", line 173, 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-20241101_200517-iopieyi0/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_200517-iopieyi0/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":  "2024-11-02T00:05:17.140953Z",
+  "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":  "1754801557504"
+    }
+  },
+  "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_200517-iopieyi0/files/wandb-summary.json

@@ -0,0 +1 @@
+{"_wandb":{"runtime":8}}

wandb/run-20241101_200517-iopieyi0/logs/debug-internal.log

@@ -0,0 +1,11 @@
+{"time":"2024-11-01T20:05:17.143962046-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-11-01T20:05:17.143982966-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_200517-iopieyi0/logs/debug-core.log"}
+{"time":"2024-11-01T20:05:17.249463211-04:00","level":"INFO","msg":"created new stream","id":"iopieyi0"}
+{"time":"2024-11-01T20:05:17.249485021-04:00","level":"INFO","msg":"stream: started","id":"iopieyi0"}
+{"time":"2024-11-01T20:05:17.249553251-04:00","level":"INFO","msg":"sender: started","stream_id":"iopieyi0"}
+{"time":"2024-11-01T20:05:17.249556141-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"iopieyi0"}}
+{"time":"2024-11-01T20:05:17.249534441-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"iopieyi0"}}
+{"time":"2024-11-01T20:05:17.488885363-04:00","level":"INFO","msg":"Starting system monitor"}
+{"time":"2024-11-01T20:05:25.263236061-04:00","level":"INFO","msg":"stream: closing","id":"iopieyi0"}
+{"time":"2024-11-01T20:05:25.263331811-04:00","level":"INFO","msg":"Stopping system monitor"}
+{"time":"2024-11-01T20:05:25.264008616-04:00","level":"INFO","msg":"Stopped system monitor"}

wandb/run-20241101_201927-8tmqrwpx/logs/debug-internal.log

@@ -0,0 +1,16 @@
+{"time":"2024-11-01T20:19:27.015302603-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-11-01T20:19:27.015321923-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_201927-8tmqrwpx/logs/debug-core.log"}
+{"time":"2024-11-01T20:19:27.121571158-04:00","level":"INFO","msg":"created new stream","id":"8tmqrwpx"}
+{"time":"2024-11-01T20:19:27.121598178-04:00","level":"INFO","msg":"stream: started","id":"8tmqrwpx"}
+{"time":"2024-11-01T20:19:27.121628798-04:00","level":"INFO","msg":"sender: started","stream_id":"8tmqrwpx"}
+{"time":"2024-11-01T20:19:27.121672758-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"8tmqrwpx"}}
+{"time":"2024-11-01T20:19:27.121613458-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"8tmqrwpx"}}
+{"time":"2024-11-01T20:19:27.355884937-04:00","level":"INFO","msg":"Starting system monitor"}
+{"time":"2024-11-01T20:20:25.212793119-04:00","level":"INFO","msg":"stream: closing","id":"8tmqrwpx"}
+{"time":"2024-11-01T20:20:25.212864349-04:00","level":"INFO","msg":"Stopping system monitor"}
+{"time":"2024-11-01T20:20:25.214203517-04:00","level":"INFO","msg":"Stopped system monitor"}
+{"time":"2024-11-01T20:20:25.558844402-04:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2024-11-01T20:20:25.688669501-04:00","level":"INFO","msg":"handler: closed","stream_id":{"value":"8tmqrwpx"}}
+{"time":"2024-11-01T20:20:25.688704032-04:00","level":"INFO","msg":"writer: Close: closed","stream_id":{"value":"8tmqrwpx"}}
+{"time":"2024-11-01T20:20:25.688738252-04:00","level":"INFO","msg":"sender: closed","stream_id":"8tmqrwpx"}
+{"time":"2024-11-01T20:20:25.688758612-04:00","level":"INFO","msg":"stream: closed","id":"8tmqrwpx"}

wandb/run-20241105_160059-czoj7ear/files/wandb-summary.json

@@ -0,0 +1 @@
+{"_wandb":{"runtime":5}}

wandb/run-20241105_160059-czoj7ear/logs/debug-internal.log

@@ -0,0 +1,17 @@
+{"time":"2024-11-05T16:00:59.421616162-05:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-11-05T16:00:59.421628512-05:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241105_160059-czoj7ear/logs/debug-core.log"}
+{"time":"2024-11-05T16:01:04.448895853-05:00","level":"INFO","msg":"created new stream","id":"czoj7ear"}
+{"time":"2024-11-05T16:01:04.448941013-05:00","level":"INFO","msg":"stream: started","id":"czoj7ear"}
+{"time":"2024-11-05T16:01:04.449026033-05:00","level":"INFO","msg":"sender: started","stream_id":"czoj7ear"}
+{"time":"2024-11-05T16:01:04.448975523-05:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"czoj7ear"}}
+{"time":"2024-11-05T16:01:04.449027943-05:00","level":"INFO","msg":"handler: started","stream_id":{"value":"czoj7ear"}}
+{"time":"2024-11-05T16:01:04.684712499-05:00","level":"INFO","msg":"Starting system monitor"}
+{"time":"2024-11-05T16:01:04.794485285-05:00","level":"INFO","msg":"stream: closing","id":"czoj7ear"}
+{"time":"2024-11-05T16:01:04.794512205-05:00","level":"INFO","msg":"Stopping system monitor"}
+{"time":"2024-11-05T16:01:04.794592695-05:00","level":"INFO","msg":"Stopped system monitor"}
+{"time":"2024-11-05T16:01:05.093812959-05:00","level":"ERROR","msg":"sender: sendDefer: failed to build job artifact","error":"failed to write data to file: write /tmp/tmpfile-3701223180: no space left on device"}
+{"time":"2024-11-05T16:01:05.340839422-05:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2024-11-05T16:01:05.518421834-05:00","level":"INFO","msg":"handler: closed","stream_id":{"value":"czoj7ear"}}
+{"time":"2024-11-05T16:01:05.518467794-05:00","level":"INFO","msg":"writer: Close: closed","stream_id":{"value":"czoj7ear"}}
+{"time":"2024-11-05T16:01:05.518480744-05:00","level":"INFO","msg":"sender: closed","stream_id":"czoj7ear"}
+{"time":"2024-11-05T16:01:05.518572734-05:00","level":"INFO","msg":"stream: closed","id":"czoj7ear"}

wandb/run-20241105_161832-c18fx9uc/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_162858-6py0unak/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_162858-6py0unak/files/output.log

@@ -0,0 +1,34 @@
+Downloading shards:   0%|                                                                                                                                        | 0/2 [00:00<?, ?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 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

wandb/run-20241105_162858-6py0unak/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_162858-6py0unak/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":  "2024-11-05T21:28:58.840904Z",
+  "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":  "1785811787776"
+    }
+  },
+  "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_162858-6py0unak/files/wandb-summary.json

@@ -0,0 +1 @@
+{"_wandb":{"runtime":23}}

wandb/run-20241105_162858-6py0unak/logs/debug-internal.log

@@ -0,0 +1,12 @@
+{"time":"2024-11-05T16:28:58.843383096-05:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-11-05T16:28:58.843400236-05:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241105_162858-6py0unak/logs/debug-core.log"}
+{"time":"2024-11-05T16:28:58.951956143-05:00","level":"INFO","msg":"created new stream","id":"6py0unak"}
+{"time":"2024-11-05T16:28:58.952002873-05:00","level":"INFO","msg":"stream: started","id":"6py0unak"}
+{"time":"2024-11-05T16:28:58.952045833-05:00","level":"INFO","msg":"sender: started","stream_id":"6py0unak"}
+{"time":"2024-11-05T16:28:58.952018493-05:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"6py0unak"}}
+{"time":"2024-11-05T16:28:58.952045693-05:00","level":"INFO","msg":"handler: started","stream_id":{"value":"6py0unak"}}
+{"time":"2024-11-05T16:28:59.159891406-05:00","level":"INFO","msg":"Starting system monitor"}
+{"time":"2024-11-05T16:29:22.458107091-05:00","level":"INFO","msg":"stream: closing","id":"6py0unak"}
+{"time":"2024-11-05T16:29:22.458143501-05:00","level":"INFO","msg":"Stopping system monitor"}
+{"time":"2024-11-05T16:29:22.458735014-05:00","level":"INFO","msg":"Stopped system monitor"}
+{"time":"2024-11-05T16:29:22.68105964-05:00","level":"INFO","msg":"api: retrying HTTP error","status":503,"url":"https://api.wandb.ai/graphql"}

wandb/run-20241105_162858-6py0unak/logs/debug.log

@@ -0,0 +1,27 @@
+2024-11-05 16:28:58,838 INFO    MainThread:1778375 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
+2024-11-05 16:28:58,838 INFO    MainThread:1778375 [wandb_setup.py:_flush():79] Configure stats pid to 1778375
+2024-11-05 16:28:58,838 INFO    MainThread:1778375 [wandb_setup.py:_flush():79] Loading settings from /home/chunhui/.config/wandb/settings
+2024-11-05 16:28:58,838 INFO    MainThread:1778375 [wandb_setup.py:_flush():79] Loading settings from /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/settings
+2024-11-05 16:28:58,838 INFO    MainThread:1778375 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2024-11-05 16:28:58,838 INFO    MainThread:1778375 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
+2024-11-05 16:28:58,838 INFO    MainThread:1778375 [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 16:28:58,838 INFO    MainThread:1778375 [wandb_setup.py:_flush():79] Applying login settings: {}
+2024-11-05 16:28:58,839 INFO    MainThread:1778375 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241105_162858-6py0unak/logs/debug.log
+2024-11-05 16:28:58,839 INFO    MainThread:1778375 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241105_162858-6py0unak/logs/debug-internal.log
+2024-11-05 16:28:58,839 INFO    MainThread:1778375 [wandb_init.py:init():621] calling init triggers
+2024-11-05 16:28:58,839 INFO    MainThread:1778375 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
+config: {}
+2024-11-05 16:28:58,839 INFO    MainThread:1778375 [wandb_init.py:init():671] starting backend
+2024-11-05 16:28:58,839 INFO    MainThread:1778375 [wandb_init.py:init():675] sending inform_init request
+2024-11-05 16:28:58,840 INFO    MainThread:1778375 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-11-05 16:28:58,840 INFO    MainThread:1778375 [wandb_init.py:init():688] backend started and connected
+2024-11-05 16:28:58,844 INFO    MainThread:1778375 [wandb_init.py:init():783] updated telemetry
+2024-11-05 16:28:58,865 INFO    MainThread:1778375 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
+2024-11-05 16:28:59,157 INFO    MainThread:1778375 [wandb_init.py:init():867] starting run threads in backend
+2024-11-05 16:28:59,247 INFO    MainThread:1778375 [wandb_run.py:_console_start():2463] atexit reg
+2024-11-05 16:28:59,247 INFO    MainThread:1778375 [wandb_run.py:_redirect():2311] redirect: wrap_raw
+2024-11-05 16:28:59,247 INFO    MainThread:1778375 [wandb_run.py:_redirect():2376] Wrapping output streams.
+2024-11-05 16:28:59,247 INFO    MainThread:1778375 [wandb_run.py:_redirect():2401] Redirects installed.
+2024-11-05 16:28:59,249 INFO    MainThread:1778375 [wandb_init.py:init():911] run started, returning control to user process
+2024-11-05 16:28:59,249 INFO    MainThread:1778375 [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 16:29:22,458 WARNING MsgRouterThr:1778375 [router.py:message_loop():77] message_loop has been closed