Add files using upload-large-folder tool

wandb/run-20241030_010306-2i7gykhq/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_010306-2i7gykhq/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_010306-2i7gykhq/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":  "2024-10-30T05:03:06.008901Z",
+  "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":  "1719200055296"
+    }
+  },
+  "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_010306-2i7gykhq/files/wandb-summary.json

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

wandb/run-20241030_010306-2i7gykhq/logs/debug-internal.log

@@ -0,0 +1,16 @@
+{"time":"2024-10-30T01:03:06.0117365-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-10-30T01:03:06.01174823-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241030_010306-2i7gykhq/logs/debug-core.log"}
+{"time":"2024-10-30T01:03:06.120361557-04:00","level":"INFO","msg":"created new stream","id":"2i7gykhq"}
+{"time":"2024-10-30T01:03:06.120402537-04:00","level":"INFO","msg":"stream: started","id":"2i7gykhq"}
+{"time":"2024-10-30T01:03:06.120481838-04:00","level":"INFO","msg":"sender: started","stream_id":"2i7gykhq"}
+{"time":"2024-10-30T01:03:06.120465068-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"2i7gykhq"}}
+{"time":"2024-10-30T01:03:06.120437948-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"2i7gykhq"}}
+{"time":"2024-10-30T01:03:06.343082168-04:00","level":"INFO","msg":"Starting system monitor"}
+{"time":"2024-10-30T01:03:06.442934695-04:00","level":"INFO","msg":"stream: closing","id":"2i7gykhq"}
+{"time":"2024-10-30T01:03:06.442971726-04:00","level":"INFO","msg":"Stopping system monitor"}
+{"time":"2024-10-30T01:03:06.443431019-04:00","level":"INFO","msg":"Stopped system monitor"}
+{"time":"2024-10-30T01:03:08.147923119-04:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2024-10-30T01:03:08.245191018-04:00","level":"INFO","msg":"handler: closed","stream_id":{"value":"2i7gykhq"}}
+{"time":"2024-10-30T01:03:08.245294648-04:00","level":"INFO","msg":"writer: Close: closed","stream_id":{"value":"2i7gykhq"}}
+{"time":"2024-10-30T01:03:08.245303978-04:00","level":"INFO","msg":"sender: closed","stream_id":"2i7gykhq"}
+{"time":"2024-10-30T01:03:08.245465209-04:00","level":"INFO","msg":"stream: closed","id":"2i7gykhq"}

wandb/run-20241030_010306-2i7gykhq/logs/debug.log

@@ -0,0 +1,27 @@
+2024-10-30 01:03:06,006 INFO    MainThread:320661 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
+2024-10-30 01:03:06,006 INFO    MainThread:320661 [wandb_setup.py:_flush():79] Configure stats pid to 320661
+2024-10-30 01:03:06,006 INFO    MainThread:320661 [wandb_setup.py:_flush():79] Loading settings from /home/chunhui/.config/wandb/settings
+2024-10-30 01:03:06,006 INFO    MainThread:320661 [wandb_setup.py:_flush():79] Loading settings from /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/settings
+2024-10-30 01:03:06,006 INFO    MainThread:320661 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2024-10-30 01:03:06,006 INFO    MainThread:320661 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
+2024-10-30 01:03:06,006 INFO    MainThread:320661 [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 01:03:06,006 INFO    MainThread:320661 [wandb_setup.py:_flush():79] Applying login settings: {}
+2024-10-30 01:03:06,006 INFO    MainThread:320661 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241030_010306-2i7gykhq/logs/debug.log
+2024-10-30 01:03:06,006 INFO    MainThread:320661 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241030_010306-2i7gykhq/logs/debug-internal.log
+2024-10-30 01:03:06,006 INFO    MainThread:320661 [wandb_init.py:init():621] calling init triggers
+2024-10-30 01:03:06,007 INFO    MainThread:320661 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
+config: {}
+2024-10-30 01:03:06,007 INFO    MainThread:320661 [wandb_init.py:init():671] starting backend
+2024-10-30 01:03:06,007 INFO    MainThread:320661 [wandb_init.py:init():675] sending inform_init request
+2024-10-30 01:03:06,008 INFO    MainThread:320661 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-10-30 01:03:06,008 INFO    MainThread:320661 [wandb_init.py:init():688] backend started and connected
+2024-10-30 01:03:06,012 INFO    MainThread:320661 [wandb_init.py:init():783] updated telemetry
+2024-10-30 01:03:06,044 INFO    MainThread:320661 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
+2024-10-30 01:03:06,339 INFO    MainThread:320661 [wandb_init.py:init():867] starting run threads in backend
+2024-10-30 01:03:06,439 INFO    MainThread:320661 [wandb_run.py:_console_start():2463] atexit reg
+2024-10-30 01:03:06,439 INFO    MainThread:320661 [wandb_run.py:_redirect():2311] redirect: wrap_raw
+2024-10-30 01:03:06,439 INFO    MainThread:320661 [wandb_run.py:_redirect():2376] Wrapping output streams.
+2024-10-30 01:03:06,439 INFO    MainThread:320661 [wandb_run.py:_redirect():2401] Redirects installed.
+2024-10-30 01:03:06,441 INFO    MainThread:320661 [wandb_init.py:init():911] run started, returning control to user process
+2024-10-30 01:03:06,441 INFO    MainThread:320661 [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 01:03:06,443 WARNING MsgRouterThr:320661 [router.py:message_loop():77] message_loop has been closed

wandb/run-20241030_011509-3dp0dtmk/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_011509-3dp0dtmk/logs/debug-internal.log

@@ -0,0 +1,8 @@
+{"time":"2024-10-30T01:15:09.513233148-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-10-30T01:15:09.513243808-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241030_011509-3dp0dtmk/logs/debug-core.log"}
+{"time":"2024-10-30T01:15:09.61864921-04:00","level":"INFO","msg":"created new stream","id":"3dp0dtmk"}
+{"time":"2024-10-30T01:15:09.618680701-04:00","level":"INFO","msg":"stream: started","id":"3dp0dtmk"}
+{"time":"2024-10-30T01:15:09.618709051-04:00","level":"INFO","msg":"sender: started","stream_id":"3dp0dtmk"}
+{"time":"2024-10-30T01:15:09.618691701-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"3dp0dtmk"}}
+{"time":"2024-10-30T01:15:09.618713711-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"3dp0dtmk"}}
+{"time":"2024-10-30T01:15:09.827809374-04:00","level":"INFO","msg":"Starting system monitor"}

wandb/run-20241030_011509-cqcwsj7s/files/output.log

@@ -0,0 +1,15 @@
+Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:04<00:00,  2.30s/it]
+Map: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 17519/17519 [00:52<00:00, 334.96 examples/s]
+Map: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 18140/18140 [00:52<00:00, 343.59 examples/s]
+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(
+[2024-10-30 01:17:00,868] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2024-10-30 01:17:07,837] [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: 4.274901390075684 seconds

wandb/run-20241030_011509-cqcwsj7s/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_011509-cqcwsj7s/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":  "2024-10-30T05:15:09.348320Z",
+  "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":  "1719287033856"
+    }
+  },
+  "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_011509-cqcwsj7s/logs/debug-internal.log

@@ -0,0 +1,8 @@
+{"time":"2024-10-30T01:15:09.350927711-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-10-30T01:15:09.350949441-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241030_011509-cqcwsj7s/logs/debug-core.log"}
+{"time":"2024-10-30T01:15:09.4574055-04:00","level":"INFO","msg":"created new stream","id":"cqcwsj7s"}
+{"time":"2024-10-30T01:15:09.457454561-04:00","level":"INFO","msg":"stream: started","id":"cqcwsj7s"}
+{"time":"2024-10-30T01:15:09.457507131-04:00","level":"INFO","msg":"sender: started","stream_id":"cqcwsj7s"}
+{"time":"2024-10-30T01:15:09.457476101-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"cqcwsj7s"}}
+{"time":"2024-10-30T01:15:09.457490051-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"cqcwsj7s"}}
+{"time":"2024-10-30T01:15:09.678893618-04:00","level":"INFO","msg":"Starting system monitor"}

wandb/run-20241030_222932-l8nv7d2l/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":  "2024-10-31T02:29:32.386006Z",
+  "args":  [
+    "--perturbation",
+    "reverse_control",
+    "--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":  "1710969503744"
+    }
+  },
+  "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_222932-lsfm0d2q/files/output.log

@@ -0,0 +1,43 @@
+Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:18<00:00,  9.35s/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(
+[2024-10-30 22:29:54,126] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2024-10-30 22:30:03,508] [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...
+Emitting ninja build file /home/chunhui/.cache/torch_extensions/py39_cu117/cpu_adam/build.ninja...
+Building extension module cpu_adam...
+Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
+Loading extension module cpu_adam...
+Time to load cpu_adam op: 5.208661794662476 seconds
+wandb: WARNING Fatal error while uploading data. Some run data will not be synced, but it will still be written to disk. Use `wandb sync` at the end of the run to try uploading.
+Traceback (most recent call last):
+  File "/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/train_deep_wandb.py", line 219, in <module>
+    trainer.train()
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/transformers/trainer.py", line 2052, in train
+    return inner_training_loop(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/transformers/trainer.py", line 2388, in _inner_training_loop
+    tr_loss_step = self.training_step(model, inputs)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/transformers/trainer.py", line 3518, in training_step
+    self.accelerator.backward(loss, **kwargs)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/accelerate/accelerator.py", line 2238, in backward
+    self.deepspeed_engine_wrapped.backward(loss, **kwargs)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/accelerate/utils/deepspeed.py", line 186, in backward
+    self.engine.backward(loss, **kwargs)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/deepspeed/utils/nvtx.py", line 18, in wrapped_fn
+    ret_val = func(*args, **kwargs)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/deepspeed/runtime/engine.py", line 2020, in backward
+    self.optimizer.backward(loss, retain_graph=retain_graph)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/deepspeed/runtime/zero/stage_1_and_2.py", line 2063, in backward
+    self.loss_scaler.backward(loss.float(), retain_graph=retain_graph)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/deepspeed/runtime/fp16/loss_scaler.py", line 63, in backward
+    scaled_loss.backward(retain_graph=retain_graph)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/torch/_tensor.py", line 487, in backward
+    torch.autograd.backward(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/torch/autograd/__init__.py", line 200, in backward
+    Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
+KeyboardInterrupt

wandb/run-20241030_231835-i7aqcsql/files/output.log

@@ -0,0 +1,13 @@
+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(
+[2024-10-30 23:18:43,451] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2024-10-30 23:18:52,678] [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: 5.939827919006348 seconds

wandb/run-20241030_231835-i7aqcsql/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_231835-i7aqcsql/logs/debug.log

@@ -0,0 +1,26 @@
+2024-10-30 23:18:35,491 INFO    MainThread:457828 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
+2024-10-30 23:18:35,491 INFO    MainThread:457828 [wandb_setup.py:_flush():79] Configure stats pid to 457828
+2024-10-30 23:18:35,491 INFO    MainThread:457828 [wandb_setup.py:_flush():79] Loading settings from /home/chunhui/.config/wandb/settings
+2024-10-30 23:18:35,491 INFO    MainThread:457828 [wandb_setup.py:_flush():79] Loading settings from /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/settings
+2024-10-30 23:18:35,491 INFO    MainThread:457828 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2024-10-30 23:18:35,491 INFO    MainThread:457828 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
+2024-10-30 23:18:35,491 INFO    MainThread:457828 [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 23:18:35,492 INFO    MainThread:457828 [wandb_setup.py:_flush():79] Applying login settings: {}
+2024-10-30 23:18:35,492 INFO    MainThread:457828 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241030_231835-i7aqcsql/logs/debug.log
+2024-10-30 23:18:35,492 INFO    MainThread:457828 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241030_231835-i7aqcsql/logs/debug-internal.log
+2024-10-30 23:18:35,492 INFO    MainThread:457828 [wandb_init.py:init():621] calling init triggers
+2024-10-30 23:18:35,492 INFO    MainThread:457828 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
+config: {}
+2024-10-30 23:18:35,492 INFO    MainThread:457828 [wandb_init.py:init():671] starting backend
+2024-10-30 23:18:35,492 INFO    MainThread:457828 [wandb_init.py:init():675] sending inform_init request
+2024-10-30 23:18:35,493 INFO    MainThread:457828 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-10-30 23:18:35,493 INFO    MainThread:457828 [wandb_init.py:init():688] backend started and connected
+2024-10-30 23:18:35,496 INFO    MainThread:457828 [wandb_init.py:init():783] updated telemetry
+2024-10-30 23:18:35,522 INFO    MainThread:457828 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
+2024-10-30 23:18:35,838 INFO    MainThread:457828 [wandb_init.py:init():867] starting run threads in backend
+2024-10-30 23:18:35,950 INFO    MainThread:457828 [wandb_run.py:_console_start():2463] atexit reg
+2024-10-30 23:18:35,950 INFO    MainThread:457828 [wandb_run.py:_redirect():2311] redirect: wrap_raw
+2024-10-30 23:18:35,950 INFO    MainThread:457828 [wandb_run.py:_redirect():2376] Wrapping output streams.
+2024-10-30 23:18:35,950 INFO    MainThread:457828 [wandb_run.py:_redirect():2401] Redirects installed.
+2024-10-30 23:18:35,952 INFO    MainThread:457828 [wandb_init.py:init():911] run started, returning control to user process
+2024-10-30 23:18:35,952 INFO    MainThread:457828 [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-mehxid7z/files/output.log

@@ -0,0 +1,13 @@
+Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:18<00:00,  9.31s/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 00:09:00,064] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2024-10-31 00:09:09,744] [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: 5.402003526687622 seconds

wandb/run-20241031_122114-2k9672ya/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: 5e-06
+perturbation:
+    value: reverse_full
+seed:
+    value: 0
+train_set:
+    value: 10M

wandb/run-20241031_122114-2k9672ya/files/output.log

@@ -0,0 +1,17 @@
+Downloading shards: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [02:08<00:00, 64.47s/it]
+Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:05<00:00,  2.61s/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 12:23:30,593] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2024-10-31 12:23:38,777] [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...
+Emitting ninja build file /home/chunhui/.cache/torch_extensions/py39_cu117/cpu_adam/build.ninja...
+Building extension module cpu_adam...
+Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
+Loading extension module cpu_adam...
+Time to load cpu_adam op: 5.0573859214782715 seconds

wandb/run-20241031_122114-2k9672ya/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":  "2024-10-31T16:21:14.171538Z",
+  "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":  "1753159966720"
+    }
+  },
+  "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_122114-2k9672ya/files/wandb-summary.json

@@ -0,0 +1 @@
+{"_wandb":{"runtime":32015}}

wandb/run-20241031_122114-2k9672ya/logs/debug-internal.log

@@ -0,0 +1,22 @@
+{"time":"2024-10-31T12:21:14.17421403-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-10-31T12:21:14.17422767-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241031_122114-2k9672ya/logs/debug-core.log"}
+{"time":"2024-10-31T12:21:14.283263175-04:00","level":"INFO","msg":"created new stream","id":"2k9672ya"}
+{"time":"2024-10-31T12:21:14.283309355-04:00","level":"INFO","msg":"stream: started","id":"2k9672ya"}
+{"time":"2024-10-31T12:21:14.283383545-04:00","level":"INFO","msg":"sender: started","stream_id":"2k9672ya"}
+{"time":"2024-10-31T12:21:14.283382385-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"2k9672ya"}}
+{"time":"2024-10-31T12:21:14.283377385-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"2k9672ya"}}
+{"time":"2024-10-31T12:21:14.488458951-04:00","level":"INFO","msg":"Starting system monitor"}
+{"time":"2024-10-31T15:06:23.896231311-04:00","level":"INFO","msg":"api: retrying HTTP error","status":502,"url":"https://api.wandb.ai/files/yaning1001-dartmouth-college/impossible_llm_reverse/2k9672ya/file_stream"}
+{"time":"2024-10-31T16:36:28.430733687-04:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2024-10-31T17:53:37.431874892-04:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2024-10-31T18:43:04.954227971-04:00","level":"INFO","msg":"api: retrying error","error":"Post \"https://api.wandb.ai/graphql\": context deadline exceeded (Client.Timeout exceeded while awaiting headers)"}
+{"time":"2024-10-31T18:47:37.271013751-04:00","level":"INFO","msg":"api: retrying HTTP error","status":502,"url":"https://api.wandb.ai/files/yaning1001-dartmouth-college/impossible_llm_reverse/2k9672ya/file_stream"}
+{"time":"2024-10-31T21:14:49.439472129-04:00","level":"INFO","msg":"Stopping system monitor"}
+{"time":"2024-10-31T21:14:49.51063436-04:00","level":"INFO","msg":"Stopped system monitor"}
+{"time":"2024-10-31T21:14:50.160847475-04:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2024-10-31T21:14:50.291547228-04:00","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2024-10-31T21:14:51.421940751-04:00","level":"INFO","msg":"stream: closing","id":"2k9672ya"}
+{"time":"2024-10-31T21:14:51.421967541-04:00","level":"INFO","msg":"handler: closed","stream_id":{"value":"2k9672ya"}}
+{"time":"2024-10-31T21:14:51.421996271-04:00","level":"INFO","msg":"writer: Close: closed","stream_id":{"value":"2k9672ya"}}
+{"time":"2024-10-31T21:14:51.422018811-04:00","level":"INFO","msg":"sender: closed","stream_id":"2k9672ya"}
+{"time":"2024-10-31T21:14:51.422075131-04:00","level":"INFO","msg":"stream: closed","id":"2k9672ya"}

wandb/run-20241031_122114-2k9672ya/logs/debug.log

@@ -0,0 +1,33 @@
+2024-10-31 12:21:14,168 INFO    MainThread:558434 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
+2024-10-31 12:21:14,168 INFO    MainThread:558434 [wandb_setup.py:_flush():79] Configure stats pid to 558434
+2024-10-31 12:21:14,168 INFO    MainThread:558434 [wandb_setup.py:_flush():79] Loading settings from /home/chunhui/.config/wandb/settings
+2024-10-31 12:21:14,168 INFO    MainThread:558434 [wandb_setup.py:_flush():79] Loading settings from /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/settings
+2024-10-31 12:21:14,168 INFO    MainThread:558434 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2024-10-31 12:21:14,168 INFO    MainThread:558434 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
+2024-10-31 12:21:14,168 INFO    MainThread:558434 [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 12:21:14,168 INFO    MainThread:558434 [wandb_setup.py:_flush():79] Applying login settings: {}
+2024-10-31 12:21:14,168 INFO    MainThread:558434 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241031_122114-2k9672ya/logs/debug.log
+2024-10-31 12:21:14,168 INFO    MainThread:558434 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241031_122114-2k9672ya/logs/debug-internal.log
+2024-10-31 12:21:14,168 INFO    MainThread:558434 [wandb_init.py:init():621] calling init triggers
+2024-10-31 12:21:14,169 INFO    MainThread:558434 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
+config: {}
+2024-10-31 12:21:14,169 INFO    MainThread:558434 [wandb_init.py:init():671] starting backend
+2024-10-31 12:21:14,169 INFO    MainThread:558434 [wandb_init.py:init():675] sending inform_init request
+2024-10-31 12:21:14,170 INFO    MainThread:558434 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-10-31 12:21:14,171 INFO    MainThread:558434 [wandb_init.py:init():688] backend started and connected
+2024-10-31 12:21:14,173 INFO    MainThread:558434 [wandb_init.py:init():783] updated telemetry
+2024-10-31 12:21:14,203 INFO    MainThread:558434 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
+2024-10-31 12:21:14,485 INFO    MainThread:558434 [wandb_init.py:init():867] starting run threads in backend
+2024-10-31 12:21:14,573 INFO    MainThread:558434 [wandb_run.py:_console_start():2463] atexit reg
+2024-10-31 12:21:14,573 INFO    MainThread:558434 [wandb_run.py:_redirect():2311] redirect: wrap_raw
+2024-10-31 12:21:14,573 INFO    MainThread:558434 [wandb_run.py:_redirect():2376] Wrapping output streams.
+2024-10-31 12:21:14,573 INFO    MainThread:558434 [wandb_run.py:_redirect():2401] Redirects installed.
+2024-10-31 12:21:14,575 INFO    MainThread:558434 [wandb_init.py:init():911] run started, returning control to user process
+2024-10-31 12:21:14,575 INFO    MainThread:558434 [wandb_run.py:_config_callback():1390] config_cb None None {'perturbation': 'reverse_full', 'train_set': '10M', 'batch_size': 3, 'epoch': 6, 'seed': 0, 'lr': 5e-06}
+2024-10-31 21:14:49,288 INFO    MainThread:558434 [wandb_run.py:_finish():2158] finishing run yaning1001-dartmouth-college/impossible_llm_reverse/2k9672ya
+2024-10-31 21:14:49,400 INFO    MainThread:558434 [wandb_run.py:_atexit_cleanup():2426] got exitcode: 0
+2024-10-31 21:14:49,400 INFO    MainThread:558434 [wandb_run.py:_restore():2408] restore
+2024-10-31 21:14:49,400 INFO    MainThread:558434 [wandb_run.py:_restore():2414] restore done
+2024-10-31 21:14:51,293 INFO    MainThread:558434 [wandb_run.py:_footer_history_summary_info():3975] rendering history
+2024-10-31 21:14:51,293 INFO    MainThread:558434 [wandb_run.py:_footer_history_summary_info():4007] rendering summary
+2024-10-31 21:14:51,421 INFO    MainThread:558434 [wandb_run.py:_footer_sync_info():3934] logging synced files

wandb/run-20241101_012438-tr39r2kv/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-tr39r2kv/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-tr39r2kv/files/wandb-summary.json

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

wandb/run-20241101_012438-tr39r2kv/logs/debug-internal.log

@@ -0,0 +1,16 @@
+{"time":"2024-11-01T01:24:38.169173693-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-11-01T01:24:38.169187803-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_012438-tr39r2kv/logs/debug-core.log"}
+{"time":"2024-11-01T01:24:38.280395547-04:00","level":"INFO","msg":"created new stream","id":"tr39r2kv"}
+{"time":"2024-11-01T01:24:38.280440227-04:00","level":"INFO","msg":"stream: started","id":"tr39r2kv"}
+{"time":"2024-11-01T01:24:38.280482807-04:00","level":"INFO","msg":"sender: started","stream_id":"tr39r2kv"}
+{"time":"2024-11-01T01:24:38.280484247-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"tr39r2kv"}}
+{"time":"2024-11-01T01:24:38.280477617-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"tr39r2kv"}}
+{"time":"2024-11-01T01:24:38.465343943-04:00","level":"INFO","msg":"Starting system monitor"}
+{"time":"2024-11-01T01:24:38.590950117-04:00","level":"INFO","msg":"stream: closing","id":"tr39r2kv"}
+{"time":"2024-11-01T01:24:38.590992697-04:00","level":"INFO","msg":"Stopping system monitor"}
+{"time":"2024-11-01T01:24:38.63883528-04:00","level":"INFO","msg":"Stopped system monitor"}
+{"time":"2024-11-01T01:24:39.16923887-04:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2024-11-01T01:24:39.290094771-04:00","level":"INFO","msg":"handler: closed","stream_id":{"value":"tr39r2kv"}}
+{"time":"2024-11-01T01:24:39.290144111-04:00","level":"INFO","msg":"writer: Close: closed","stream_id":{"value":"tr39r2kv"}}
+{"time":"2024-11-01T01:24:39.290152561-04:00","level":"INFO","msg":"sender: closed","stream_id":"tr39r2kv"}
+{"time":"2024-11-01T01:24:39.290211281-04:00","level":"INFO","msg":"stream: closed","id":"tr39r2kv"}

wandb/run-20241101_012733-4u8e027p/logs/debug-internal.log

@@ -0,0 +1,8 @@
+{"time":"2024-11-01T01:27:33.995935712-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-11-01T01:27:33.995950772-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_012733-4u8e027p/logs/debug-core.log"}
+{"time":"2024-11-01T01:27:34.10392569-04:00","level":"INFO","msg":"created new stream","id":"4u8e027p"}
+{"time":"2024-11-01T01:27:34.103978121-04:00","level":"INFO","msg":"stream: started","id":"4u8e027p"}
+{"time":"2024-11-01T01:27:34.104114652-04:00","level":"INFO","msg":"sender: started","stream_id":"4u8e027p"}
+{"time":"2024-11-01T01:27:34.104042611-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"4u8e027p"}}
+{"time":"2024-11-01T01:27:34.104027311-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"4u8e027p"}}
+{"time":"2024-11-01T01:27:34.323754805-04:00","level":"INFO","msg":"Starting system monitor"}

wandb/run-20241101_012733-e3zsr634/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_012733-e3zsr634/logs/debug-internal.log

@@ -0,0 +1,8 @@
+{"time":"2024-11-01T01:27:33.960171934-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-11-01T01:27:33.960186144-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_012733-e3zsr634/logs/debug-core.log"}
+{"time":"2024-11-01T01:27:34.065020141-04:00","level":"INFO","msg":"created new stream","id":"e3zsr634"}
+{"time":"2024-11-01T01:27:34.065052661-04:00","level":"INFO","msg":"stream: started","id":"e3zsr634"}
+{"time":"2024-11-01T01:27:34.065102351-04:00","level":"INFO","msg":"sender: started","stream_id":"e3zsr634"}
+{"time":"2024-11-01T01:27:34.065089571-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"e3zsr634"}}
+{"time":"2024-11-01T01:27:34.065106681-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"e3zsr634"}}
+{"time":"2024-11-01T01:27:34.21774298-04:00","level":"INFO","msg":"Starting system monitor"}

wandb/run-20241101_012733-e3zsr634/logs/debug.log

@@ -0,0 +1,26 @@
+2024-11-01 01:27:33,956 INFO    MainThread:678554 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
+2024-11-01 01:27:33,956 INFO    MainThread:678554 [wandb_setup.py:_flush():79] Configure stats pid to 678554
+2024-11-01 01:27:33,956 INFO    MainThread:678554 [wandb_setup.py:_flush():79] Loading settings from /home/chunhui/.config/wandb/settings
+2024-11-01 01:27:33,956 INFO    MainThread:678554 [wandb_setup.py:_flush():79] Loading settings from /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/settings
+2024-11-01 01:27:33,956 INFO    MainThread:678554 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2024-11-01 01:27:33,956 INFO    MainThread:678554 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
+2024-11-01 01:27:33,956 INFO    MainThread:678554 [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 01:27:33,956 INFO    MainThread:678554 [wandb_setup.py:_flush():79] Applying login settings: {}
+2024-11-01 01:27:33,956 INFO    MainThread:678554 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_012733-e3zsr634/logs/debug.log
+2024-11-01 01:27:33,956 INFO    MainThread:678554 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_012733-e3zsr634/logs/debug-internal.log
+2024-11-01 01:27:33,956 INFO    MainThread:678554 [wandb_init.py:init():621] calling init triggers
+2024-11-01 01:27:33,956 INFO    MainThread:678554 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
+config: {}
+2024-11-01 01:27:33,956 INFO    MainThread:678554 [wandb_init.py:init():671] starting backend
+2024-11-01 01:27:33,956 INFO    MainThread:678554 [wandb_init.py:init():675] sending inform_init request
+2024-11-01 01:27:33,957 INFO    MainThread:678554 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-11-01 01:27:33,958 INFO    MainThread:678554 [wandb_init.py:init():688] backend started and connected
+2024-11-01 01:27:33,961 INFO    MainThread:678554 [wandb_init.py:init():783] updated telemetry
+2024-11-01 01:27:33,985 INFO    MainThread:678554 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
+2024-11-01 01:27:34,215 INFO    MainThread:678554 [wandb_init.py:init():867] starting run threads in backend
+2024-11-01 01:27:34,304 INFO    MainThread:678554 [wandb_run.py:_console_start():2463] atexit reg
+2024-11-01 01:27:34,304 INFO    MainThread:678554 [wandb_run.py:_redirect():2311] redirect: wrap_raw
+2024-11-01 01:27:34,305 INFO    MainThread:678554 [wandb_run.py:_redirect():2376] Wrapping output streams.
+2024-11-01 01:27:34,305 INFO    MainThread:678554 [wandb_run.py:_redirect():2401] Redirects installed.
+2024-11-01 01:27:34,306 INFO    MainThread:678554 [wandb_init.py:init():911] run started, returning control to user process
+2024-11-01 01:27:34,306 INFO    MainThread:678554 [wandb_run.py:_config_callback():1390] config_cb None None {'perturbation': 'shuffle_nondeterministic', 'train_set': '10M', 'batch_size': 3, 'epoch': 6, 'seed': 0, 'lr': 5e-06}

wandb/run-20241101_200502-28ivel81/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_200502-28ivel81/logs/debug-internal.log

@@ -0,0 +1,8 @@
+{"time":"2024-11-01T20:05:02.696528925-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-11-01T20:05:02.696551646-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_200502-28ivel81/logs/debug-core.log"}
+{"time":"2024-11-01T20:05:02.804187905-04:00","level":"INFO","msg":"created new stream","id":"28ivel81"}
+{"time":"2024-11-01T20:05:02.804240726-04:00","level":"INFO","msg":"stream: started","id":"28ivel81"}
+{"time":"2024-11-01T20:05:02.804338597-04:00","level":"INFO","msg":"sender: started","stream_id":"28ivel81"}
+{"time":"2024-11-01T20:05:02.804329676-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"28ivel81"}}
+{"time":"2024-11-01T20:05:02.804273736-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"28ivel81"}}
+{"time":"2024-11-01T20:05:03.033544975-04:00","level":"INFO","msg":"Starting system monitor"}

wandb/run-20241101_200502-28ivel81/logs/debug.log

@@ -0,0 +1,26 @@
+2024-11-01 20:05:02,690 INFO    MainThread:869511 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
+2024-11-01 20:05:02,690 INFO    MainThread:869511 [wandb_setup.py:_flush():79] Configure stats pid to 869511
+2024-11-01 20:05:02,690 INFO    MainThread:869511 [wandb_setup.py:_flush():79] Loading settings from /home/chunhui/.config/wandb/settings
+2024-11-01 20:05:02,690 INFO    MainThread:869511 [wandb_setup.py:_flush():79] Loading settings from /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/settings
+2024-11-01 20:05:02,690 INFO    MainThread:869511 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2024-11-01 20:05:02,690 INFO    MainThread:869511 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
+2024-11-01 20:05:02,690 INFO    MainThread:869511 [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 20:05:02,690 INFO    MainThread:869511 [wandb_setup.py:_flush():79] Applying login settings: {}
+2024-11-01 20:05:02,690 INFO    MainThread:869511 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_200502-28ivel81/logs/debug.log
+2024-11-01 20:05:02,691 INFO    MainThread:869511 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_200502-28ivel81/logs/debug-internal.log
+2024-11-01 20:05:02,691 INFO    MainThread:869511 [wandb_init.py:init():621] calling init triggers
+2024-11-01 20:05:02,691 INFO    MainThread:869511 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
+config: {}
+2024-11-01 20:05:02,691 INFO    MainThread:869511 [wandb_init.py:init():671] starting backend
+2024-11-01 20:05:02,691 INFO    MainThread:869511 [wandb_init.py:init():675] sending inform_init request
+2024-11-01 20:05:02,693 INFO    MainThread:869511 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-11-01 20:05:02,693 INFO    MainThread:869511 [wandb_init.py:init():688] backend started and connected
+2024-11-01 20:05:02,698 INFO    MainThread:869511 [wandb_init.py:init():783] updated telemetry
+2024-11-01 20:05:02,727 INFO    MainThread:869511 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
+2024-11-01 20:05:03,030 INFO    MainThread:869511 [wandb_init.py:init():867] starting run threads in backend
+2024-11-01 20:05:03,121 INFO    MainThread:869511 [wandb_run.py:_console_start():2463] atexit reg
+2024-11-01 20:05:03,121 INFO    MainThread:869511 [wandb_run.py:_redirect():2311] redirect: wrap_raw
+2024-11-01 20:05:03,121 INFO    MainThread:869511 [wandb_run.py:_redirect():2376] Wrapping output streams.
+2024-11-01 20:05:03,121 INFO    MainThread:869511 [wandb_run.py:_redirect():2401] Redirects installed.
+2024-11-01 20:05:03,123 INFO    MainThread:869511 [wandb_init.py:init():911] run started, returning control to user process
+2024-11-01 20:05:03,123 INFO    MainThread:869511 [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-20241101_200517-f3b150ss/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-f3b150ss/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-f3b150ss/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-f3b150ss/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":  "2024-11-02T00:05:17.187494Z",
+  "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-f3b150ss/files/wandb-summary.json

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

wandb/run-20241101_200517-f3b150ss/logs/debug-internal.log

@@ -0,0 +1,11 @@
+{"time":"2024-11-01T20:05:17.189781964-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-11-01T20:05:17.189800414-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_200517-f3b150ss/logs/debug-core.log"}
+{"time":"2024-11-01T20:05:17.295261458-04:00","level":"INFO","msg":"created new stream","id":"f3b150ss"}
+{"time":"2024-11-01T20:05:17.295289028-04:00","level":"INFO","msg":"stream: started","id":"f3b150ss"}
+{"time":"2024-11-01T20:05:17.295344069-04:00","level":"INFO","msg":"sender: started","stream_id":"f3b150ss"}
+{"time":"2024-11-01T20:05:17.295315769-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"f3b150ss"}}
+{"time":"2024-11-01T20:05:17.295333749-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"f3b150ss"}}
+{"time":"2024-11-01T20:05:17.655340154-04:00","level":"INFO","msg":"Starting system monitor"}
+{"time":"2024-11-01T20:05:25.26316459-04:00","level":"INFO","msg":"stream: closing","id":"f3b150ss"}
+{"time":"2024-11-01T20:05:25.263209061-04:00","level":"INFO","msg":"Stopping system monitor"}
+{"time":"2024-11-01T20:05:25.263959546-04:00","level":"INFO","msg":"Stopped system monitor"}

wandb/run-20241101_200517-f3b150ss/logs/debug.log

@@ -0,0 +1,27 @@
+2024-11-01 20:05:17,184 INFO    MainThread:870385 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
+2024-11-01 20:05:17,184 INFO    MainThread:870385 [wandb_setup.py:_flush():79] Configure stats pid to 870385
+2024-11-01 20:05:17,184 INFO    MainThread:870385 [wandb_setup.py:_flush():79] Loading settings from /home/chunhui/.config/wandb/settings
+2024-11-01 20:05:17,184 INFO    MainThread:870385 [wandb_setup.py:_flush():79] Loading settings from /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/settings
+2024-11-01 20:05:17,184 INFO    MainThread:870385 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2024-11-01 20:05:17,184 INFO    MainThread:870385 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
+2024-11-01 20:05:17,185 INFO    MainThread:870385 [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 20:05:17,185 INFO    MainThread:870385 [wandb_setup.py:_flush():79] Applying login settings: {}
+2024-11-01 20:05:17,185 INFO    MainThread:870385 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_200517-f3b150ss/logs/debug.log
+2024-11-01 20:05:17,185 INFO    MainThread:870385 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_200517-f3b150ss/logs/debug-internal.log
+2024-11-01 20:05:17,185 INFO    MainThread:870385 [wandb_init.py:init():621] calling init triggers
+2024-11-01 20:05:17,185 INFO    MainThread:870385 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
+config: {}
+2024-11-01 20:05:17,185 INFO    MainThread:870385 [wandb_init.py:init():671] starting backend
+2024-11-01 20:05:17,185 INFO    MainThread:870385 [wandb_init.py:init():675] sending inform_init request
+2024-11-01 20:05:17,186 INFO    MainThread:870385 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-11-01 20:05:17,187 INFO    MainThread:870385 [wandb_init.py:init():688] backend started and connected
+2024-11-01 20:05:17,191 INFO    MainThread:870385 [wandb_init.py:init():783] updated telemetry
+2024-11-01 20:05:17,223 INFO    MainThread:870385 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
+2024-11-01 20:05:17,652 INFO    MainThread:870385 [wandb_init.py:init():867] starting run threads in backend
+2024-11-01 20:05:17,739 INFO    MainThread:870385 [wandb_run.py:_console_start():2463] atexit reg
+2024-11-01 20:05:17,739 INFO    MainThread:870385 [wandb_run.py:_redirect():2311] redirect: wrap_raw
+2024-11-01 20:05:17,739 INFO    MainThread:870385 [wandb_run.py:_redirect():2376] Wrapping output streams.
+2024-11-01 20:05:17,739 INFO    MainThread:870385 [wandb_run.py:_redirect():2401] Redirects installed.
+2024-11-01 20:05:17,741 INFO    MainThread:870385 [wandb_init.py:init():911] run started, returning control to user process
+2024-11-01 20:05:17,741 INFO    MainThread:870385 [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}
+2024-11-01 20:05:25,263 WARNING MsgRouterThr:870385 [router.py:message_loop():77] message_loop has been closed

wandb/run-20241101_201926-5y6ulxig/logs/debug-internal.log

@@ -0,0 +1,8 @@
+{"time":"2024-11-01T20:19:26.872916513-04:00","level":"INFO","msg":"using version","core version":"0.18.5"}
+{"time":"2024-11-01T20:19:26.872928923-04:00","level":"INFO","msg":"created symlink","path":"/mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241101_201926-5y6ulxig/logs/debug-core.log"}
+{"time":"2024-11-01T20:19:26.979140297-04:00","level":"INFO","msg":"created new stream","id":"5y6ulxig"}
+{"time":"2024-11-01T20:19:26.979176487-04:00","level":"INFO","msg":"stream: started","id":"5y6ulxig"}
+{"time":"2024-11-01T20:19:26.979208097-04:00","level":"INFO","msg":"sender: started","stream_id":"5y6ulxig"}
+{"time":"2024-11-01T20:19:26.979191997-04:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"5y6ulxig"}}
+{"time":"2024-11-01T20:19:26.979249518-04:00","level":"INFO","msg":"handler: started","stream_id":{"value":"5y6ulxig"}}
+{"time":"2024-11-01T20:19:27.191677696-04:00","level":"INFO","msg":"Starting system monitor"}

wandb/run-20241105_155905-e2ilsfdb/files/output.log

@@ -0,0 +1,19 @@
+Traceback (most recent call last):
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/pathlib.py", line 1323, in mkdir
+    self._accessor.mkdir(self, mode)
+FileNotFoundError: [Errno 2] No such file or directory: '/home/chunhui/.cache/huggingface/datasets/babylm_dataset_test/babylm_shuffle_deterministic21_10M_seed0/0.0.0'
+
+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 165, 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 2096, in load_dataset
+    builder_instance.download_and_prepare(
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/site-packages/datasets/builder.py", line 855, in download_and_prepare
+    Path(self._output_dir).parent.mkdir(parents=True, exist_ok=True)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/pathlib.py", line 1327, in mkdir
+    self.parent.mkdir(parents=True, exist_ok=True)
+  File "/mnt/ssd3/chunhui/miniconda/envs/impossible_llm/lib/python3.9/pathlib.py", line 1323, in mkdir
+    self._accessor.mkdir(self, mode)
+OSError: [Errno 28] No space left on device: '/home/chunhui/.cache/huggingface/datasets/babylm_dataset_test/babylm_shuffle_deterministic21_10M_seed0'

wandb/run-20241105_160217-dgnjdt5g/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_160217-dgnjdt5g/logs/debug.log

@@ -0,0 +1,27 @@
+2024-11-05 16:02:17,745 INFO    MainThread:1770493 [wandb_setup.py:_flush():79] Current SDK version is 0.18.5
+2024-11-05 16:02:17,745 INFO    MainThread:1770493 [wandb_setup.py:_flush():79] Configure stats pid to 1770493
+2024-11-05 16:02:17,745 INFO    MainThread:1770493 [wandb_setup.py:_flush():79] Loading settings from /home/chunhui/.config/wandb/settings
+2024-11-05 16:02:17,745 INFO    MainThread:1770493 [wandb_setup.py:_flush():79] Loading settings from /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/settings
+2024-11-05 16:02:17,745 INFO    MainThread:1770493 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2024-11-05 16:02:17,745 INFO    MainThread:1770493 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': None, '_disable_service': None}
+2024-11-05 16:02:17,745 INFO    MainThread:1770493 [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 16:02:17,746 INFO    MainThread:1770493 [wandb_setup.py:_flush():79] Applying login settings: {}
+2024-11-05 16:02:17,746 INFO    MainThread:1770493 [wandb_init.py:_log_setup():534] Logging user logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241105_160217-dgnjdt5g/logs/debug.log
+2024-11-05 16:02:17,746 INFO    MainThread:1770493 [wandb_init.py:_log_setup():535] Logging internal logs to /mnt/ssd3/chunhui/yaning/project/impossible_llm/train/wandb/run-20241105_160217-dgnjdt5g/logs/debug-internal.log
+2024-11-05 16:02:17,746 INFO    MainThread:1770493 [wandb_init.py:init():621] calling init triggers
+2024-11-05 16:02:17,746 INFO    MainThread:1770493 [wandb_init.py:init():628] wandb.init called with sweep_config: {}
+config: {}
+2024-11-05 16:02:17,746 INFO    MainThread:1770493 [wandb_init.py:init():671] starting backend
+2024-11-05 16:02:17,746 INFO    MainThread:1770493 [wandb_init.py:init():675] sending inform_init request
+2024-11-05 16:02:17,748 INFO    MainThread:1770493 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-11-05 16:02:17,748 INFO    MainThread:1770493 [wandb_init.py:init():688] backend started and connected
+2024-11-05 16:02:17,753 INFO    MainThread:1770493 [wandb_init.py:init():783] updated telemetry
+2024-11-05 16:02:17,779 INFO    MainThread:1770493 [wandb_init.py:init():816] communicating run to backend with 90.0 second timeout
+2024-11-05 16:02:22,979 INFO    MainThread:1770493 [wandb_init.py:init():867] starting run threads in backend
+2024-11-05 16:02:23,067 INFO    MainThread:1770493 [wandb_run.py:_console_start():2463] atexit reg
+2024-11-05 16:02:23,067 INFO    MainThread:1770493 [wandb_run.py:_redirect():2311] redirect: wrap_raw
+2024-11-05 16:02:23,067 INFO    MainThread:1770493 [wandb_run.py:_redirect():2376] Wrapping output streams.
+2024-11-05 16:02:23,067 INFO    MainThread:1770493 [wandb_run.py:_redirect():2401] Redirects installed.
+2024-11-05 16:02:23,068 INFO    MainThread:1770493 [wandb_init.py:init():911] run started, returning control to user process
+2024-11-05 16:02:23,068 INFO    MainThread:1770493 [wandb_run.py:_config_callback():1390] config_cb None None {'perturbation': 'shuffle_deterministic21', 'train_set': '10M', 'batch_size': 3, 'epoch': 3, 'seed': 0, 'lr': 5e-06}
+2024-11-05 16:02:23,092 WARNING MsgRouterThr:1770493 [router.py:message_loop():77] message_loop has been closed

wandb/run-20241105_162858-1nu0waui/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