Upload folder using huggingface_hub

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 unselective_run_1_restarted_with_ko_zero/wandb/run-20250213_072801-crz42i9y/run-crz42i9y.wandb filter=lfs diff=lfs merge=lfs -text
 unselective_run_1_restarted/wandb/run-20250213_073721-bd672vnz/run-bd672vnz.wandb filter=lfs diff=lfs merge=lfs -text
+unselective_run_1_restarted_with_o_rescaled/wandb/run-20250213_072314-jkzpfmgd/run-jkzpfmgd.wandb filter=lfs diff=lfs merge=lfs -text

unselective_run_1_restarted_with_o_rescaled/args.json

@@ -0,0 +1 @@
+{"hellaswag": true, "attention_kind": "self", "log_dir": "unselective_run_1_restarted_with_o_rescaled", "resume_checkpoint": "hf://andrew-healey/context-compression/unselective_run_0/model_07500.pt", "resume_optimizer": false, "add_a_head": true, "add_head_to_start": true, "new_head_init": "o_rescaled", "max_steps": 2500, "group": "selective_surgery_2", "use_wandb": true, "kill_self_after_run": false}

unselective_run_1_restarted_with_o_rescaled/dataloader_02499.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cefbc0ab907c6a30382d71f16b47450e3533ee64ae273fcfa46862dc62ec8a7
+size 964

unselective_run_1_restarted_with_o_rescaled/model_02499.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1a7d74841e37f47c82ed1c8aa839fac5d31adff4a50454dbdf85b6eed10184e
+size 507404522

unselective_run_1_restarted_with_o_rescaled/optimizer_02499.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9eed248b9dff2148b3c4373f271ab6fb2f91a80109560f33851980b9b406344
+size 1014834310

unselective_run_1_restarted_with_o_rescaled/wandb/debug-internal.log

@@ -0,0 +1,7 @@
+{"time":"2025-02-13T07:23:14.362440989Z","level":"INFO","msg":"stream: starting","core version":"0.19.6","symlink path":"unselective_run_1_restarted_with_o_rescaled/wandb/run-20250213_072314-jkzpfmgd/logs/debug-core.log"}
+{"time":"2025-02-13T07:23:14.581470737Z","level":"INFO","msg":"created new stream","id":"jkzpfmgd"}
+{"time":"2025-02-13T07:23:14.581503917Z","level":"INFO","msg":"stream: started","id":"jkzpfmgd"}
+{"time":"2025-02-13T07:23:14.581523127Z","level":"INFO","msg":"writer: Do: started","stream_id":"jkzpfmgd"}
+{"time":"2025-02-13T07:23:14.581605127Z","level":"INFO","msg":"sender: started","stream_id":"jkzpfmgd"}
+{"time":"2025-02-13T07:23:14.581655667Z","level":"INFO","msg":"handler: started","stream_id":"jkzpfmgd"}
+{"time":"2025-02-13T07:23:14.820664913Z","level":"INFO","msg":"Starting system monitor"}

unselective_run_1_restarted_with_o_rescaled/wandb/debug.log

@@ -0,0 +1,22 @@
+2025-02-13 07:23:14,140 INFO    MainThread:2405 [wandb_setup.py:_flush():68] Current SDK version is 0.19.6
+2025-02-13 07:23:14,140 INFO    MainThread:2405 [wandb_setup.py:_flush():68] Configure stats pid to 2405
+2025-02-13 07:23:14,140 INFO    MainThread:2405 [wandb_setup.py:_flush():68] Loading settings from /root/.config/wandb/settings
+2025-02-13 07:23:14,140 INFO    MainThread:2405 [wandb_setup.py:_flush():68] Loading settings from /workspace/context-compression/wandb/settings
+2025-02-13 07:23:14,140 INFO    MainThread:2405 [wandb_setup.py:_flush():68] Loading settings from environment variables
+2025-02-13 07:23:14,140 INFO    MainThread:2405 [wandb_init.py:setup_run_log_directory():637] Logging user logs to unselective_run_1_restarted_with_o_rescaled/wandb/run-20250213_072314-jkzpfmgd/logs/debug.log
+2025-02-13 07:23:14,140 INFO    MainThread:2405 [wandb_init.py:setup_run_log_directory():638] Logging internal logs to unselective_run_1_restarted_with_o_rescaled/wandb/run-20250213_072314-jkzpfmgd/logs/debug-internal.log
+2025-02-13 07:23:14,140 INFO    MainThread:2405 [wandb_init.py:init():756] calling init triggers
+2025-02-13 07:23:14,140 INFO    MainThread:2405 [wandb_init.py:init():761] wandb.init called with sweep_config: {}
+config: {'hellaswag': True, 'attention_kind': <AttentionKind.SELF: 'self'>, 'log_dir': 'unselective_run_1_restarted_with_o_rescaled', 'resume_checkpoint': 'hf://andrew-healey/context-compression/unselective_run_0/model_07500.pt', 'resume_optimizer': False, 'add_a_head': True, 'add_head_to_start': True, 'new_head_init': <NewHeadInit.O_RESCALED: 'o_rescaled'>, 'max_steps': 2500, 'group': 'selective_surgery_2', 'use_wandb': True, 'kill_self_after_run': False, '_wandb': {}}
+2025-02-13 07:23:14,140 INFO    MainThread:2405 [wandb_init.py:init():789] starting backend
+2025-02-13 07:23:14,350 INFO    MainThread:2405 [wandb_init.py:init():793] sending inform_init request
+2025-02-13 07:23:14,358 INFO    MainThread:2405 [backend.py:_multiprocessing_setup():97] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2025-02-13 07:23:14,359 INFO    MainThread:2405 [wandb_init.py:init():808] backend started and connected
+2025-02-13 07:23:14,367 INFO    MainThread:2405 [wandb_init.py:init():901] updated telemetry
+2025-02-13 07:23:14,376 INFO    MainThread:2405 [wandb_init.py:init():936] communicating run to backend with 90.0 second timeout
+2025-02-13 07:23:14,816 INFO    MainThread:2405 [wandb_init.py:init():994] starting run threads in backend
+2025-02-13 07:23:14,943 INFO    MainThread:2405 [wandb_run.py:_console_start():2385] atexit reg
+2025-02-13 07:23:14,943 INFO    MainThread:2405 [wandb_run.py:_redirect():2235] redirect: wrap_raw
+2025-02-13 07:23:14,944 INFO    MainThread:2405 [wandb_run.py:_redirect():2300] Wrapping output streams.
+2025-02-13 07:23:14,944 INFO    MainThread:2405 [wandb_run.py:_redirect():2325] Redirects installed.
+2025-02-13 07:23:14,945 INFO    MainThread:2405 [wandb_init.py:init():1036] run started, returning control to user process

unselective_run_1_restarted_with_o_rescaled/wandb/run-20250213_072314-jkzpfmgd/files/requirements.txt

@@ -0,0 +1,217 @@
+Brotli==1.1.0
+MarkupSafe==3.0.2
+PySocks==1.7.1
+PyYAML==6.0.2
+archspec==0.2.3
+asttokens==2.4.1
+astunparse==1.6.3
+attrs==24.2.0
+beautifulsoup4==4.12.3
+boltons==24.0.0
+certifi==2024.8.30
+cffi==1.17.1
+chardet==5.2.0
+charset-normalizer==3.4.0
+click==8.1.7
+colorama==0.4.6
+conda==24.9.2
+conda-build==24.9.0
+conda_index==0.5.0
+conda-libmamba-solver==24.9.0
+conda-package-handling==2.4.0
+conda_package_streaming==0.11.0
+decorator==5.1.1
+distro==1.9.0
+dnspython==2.7.0
+exceptiongroup==1.2.2
+executing==2.1.0
+expecttest==0.2.1
+filelock==3.16.1
+frozendict==2.4.6
+h2==4.1.0
+hpack==4.0.0
+hyperframe==6.0.1
+hypothesis==6.115.5
+idna==3.10
+importlib_resources==6.4.5
+ipython==8.29.0
+jedi==0.19.1
+Jinja2==3.1.4
+jsonpatch==1.33
+jsonpointer==3.0.0
+jsonschema==4.23.0
+jsonschema-specifications==2024.10.1
+libarchive-c==5.1
+libmambapy==1.5.10
+lief==0.14.1
+lintrunner==0.12.5
+mamba==1.5.10
+matplotlib-inline==0.1.7
+menuinst==2.1.2
+more-itertools==10.5.0
+mpmath==1.3.0
+networkx==3.4.2
+ninja==1.11.1.1
+numpy==2.1.2
+nvidia-cublas-cu12==12.4.5.8
+nvidia-cuda-cupti-cu12==12.4.127
+nvidia-cuda-nvrtc-cu12==12.4.127
+nvidia-cuda-runtime-cu12==12.4.127
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.2.1.3
+nvidia-curand-cu12==10.3.5.147
+nvidia-cusolver-cu12==11.6.1.9
+nvidia-cusparse-cu12==12.3.1.170
+nvidia-nccl-cu12==2.21.5
+nvidia-nvjitlink-cu12==12.4.127
+nvidia-nvtx-cu12==12.4.127
+optree==0.13.0
+packaging==24.1
+parso==0.8.4
+pexpect==4.9.0
+pickleshare==0.7.5
+pillow==10.2.0
+pip==24.2
+pkginfo==1.11.2
+pkgutil_resolve_name==1.3.10
+platformdirs==4.3.6
+pluggy==1.5.0
+prompt_toolkit==3.0.48
+psutil==6.1.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pycosat==0.6.6
+pycparser==2.22
+Pygments==2.18.0
+python-etcd==0.4.5
+pytz==2024.2
+referencing==0.35.1
+requests==2.32.3
+rpds-py==0.20.0
+ruamel.yaml==0.18.6
+ruamel.yaml.clib==0.2.8
+setuptools==72.1.0
+six==1.16.0
+sortedcontainers==2.4.0
+soupsieve==2.5
+stack-data==0.6.2
+sympy==1.13.1
+torch==2.5.1+cu124
+torchaudio==2.5.1+cu124
+torchelastic==0.2.2
+torchvision==0.20.1+cu124
+tqdm==4.66.5
+traitlets==5.14.3
+triton==3.1.0
+truststore==0.9.2
+types-dataclasses==0.6.6
+typing_extensions==4.12.2
+urllib3==2.2.3
+wcwidth==0.2.13
+wheel==0.44.0
+zipp==3.20.2
+zstandard==0.23.0
+smmap==5.0.2
+setproctitle==1.3.4
+sentry-sdk==2.21.0
+pydantic_core==2.27.2
+protobuf==5.29.3
+docker-pycreds==0.4.0
+annotated-types==0.7.0
+pydantic==2.10.6
+gitdb==4.0.12
+GitPython==3.1.44
+wandb==0.19.6
+iniconfig==2.0.0
+pytest==8.3.4
+jupyter-archive==3.4.0
+nbzip==0.1.0
+webencodings==0.5.1
+filetype==1.2.0
+fastjsonschema==2.21.1
+widgetsnbextension==4.0.13
+websocket-client==1.8.0
+webcolors==24.11.1
+uri-template==1.3.0
+types-python-dateutil==2.9.0.20241206
+tornado==6.4.2
+tinycss2==1.4.0
+sniffio==1.3.1
+Send2Trash==1.8.3
+rfc3986-validator==0.1.1
+rfc3339-validator==0.1.4
+pyzmq==26.2.1
+python-json-logger==3.2.1
+prometheus_client==0.21.1
+pandocfilters==1.5.1
+overrides==7.7.0
+nest-asyncio==1.6.0
+mistune==3.1.1
+jupyterlab_widgets==3.0.13
+jupyterlab_pygments==0.3.0
+jupyter_core==5.7.2
+json5==0.10.0
+h11==0.14.0
+fqdn==1.5.1
+defusedxml==0.7.1
+debugpy==1.8.12
+comm==0.2.2
+bleach==6.2.0
+babel==2.17.0
+async-lru==2.0.4
+terminado==0.18.1
+jupyter_client==8.6.3
+httpcore==1.0.7
+arrow==1.3.0
+argon2-cffi-bindings==21.2.0
+anyio==4.8.0
+jupyter_server_terminals==0.5.3
+isoduration==20.11.0
+httpx==0.28.1
+argon2-cffi==23.1.0
+nbformat==5.10.4
+ipywidgets==8.1.5
+ipykernel==6.29.5
+nbclient==0.10.2
+jupyter-events==0.12.0
+jupyter-console==6.6.3
+bash_kernel==0.10.0
+nbconvert==7.16.6
+jupyter_server==2.15.0
+notebook_shim==0.2.4
+jupyterlab_server==2.27.3
+jupyter-lsp==2.2.5
+jupyterlab==4.3.5
+notebook==7.3.2
+jupyter-http-over-ws==0.0.8
+jupyter==1.1.1
+aiohappyeyeballs==2.4.6
+aiohttp==3.11.12
+aiosignal==1.3.2
+contourpy==1.3.1
+cycler==0.12.1
+datasets==3.2.0
+dill==0.3.8
+fonttools==4.56.0
+frozenlist==1.5.0
+fsspec==2024.9.0
+huggingface-hub==0.28.1
+kiwisolver==1.4.8
+matplotlib==3.10.0
+multidict==6.1.0
+multiprocess==0.70.16
+pandas==2.2.3
+propcache==0.2.1
+pyarrow==19.0.0
+pyparsing==3.2.1
+python-dateutil==2.9.0.post0
+regex==2024.11.6
+safetensors==0.5.2
+sentencepiece==0.2.0
+tiktoken==0.8.0
+tokenizers==0.21.0
+transformers==4.48.3
+tzdata==2025.1
+vastai==0.2.8
+xxhash==3.5.0
+yarl==1.18.3

unselective_run_1_restarted_with_o_rescaled/wandb/run-20250213_072314-jkzpfmgd/files/wandb-metadata.json

@@ -0,0 +1,98 @@
+{
+  "os":  "Linux-5.15.0-130-generic-x86_64-with-glibc2.35",
+  "python":  "CPython 3.11.10",
+  "startedAt":  "2025-02-13T07:23:14.359620Z",
+  "args":  [
+    "--group",
+    "selective_surgery_2",
+    "--resume_checkpoint",
+    "hf://andrew-healey/context-compression/unselective_run_0/model_07500.pt",
+    "--max_steps",
+    "2500",
+    "--attention_kind",
+    "self",
+    "--log_dir",
+    "unselective_run_1_restarted_with_o_rescaled",
+    "--add_a_head",
+    "--add_head_to_start",
+    "--new_head_init",
+    "o_rescaled"
+  ],
+  "program":  "-m context_compression.train",
+  "git":  {
+    "remote":  "https://github.com/andrew-healey/context-compression",
+    "commit":  "303eb3f2a5dab5fe30125c9ccc545fc206daf467"
+  },
+  "email":  "doolie.healey@gmail.com",
+  "root":  "unselective_run_1_restarted_with_o_rescaled",
+  "host":  "545c49c08c4a",
+  "executable":  "/opt/conda/bin/python3.11",
+  "cpu_count":  128,
+  "cpu_count_logical":  256,
+  "gpu":  "NVIDIA GeForce RTX 4090",
+  "gpu_count":  8,
+  "disk":  {
+    "/":  {
+      "total":  "222264557568",
+      "used":  "966045696"
+    }
+  },
+  "memory":  {
+    "total":  "540812591104"
+  },
+  "cpu":  {
+    "count":  128,
+    "countLogical":  256
+  },
+  "gpu_nvidia":  [
+    {
+      "name":  "NVIDIA GeForce RTX 4090",
+      "memoryTotal":  "25757220864",
+      "cudaCores":  16384,
+      "architecture":  "Ada"
+    },
+    {
+      "name":  "NVIDIA GeForce RTX 4090",
+      "memoryTotal":  "25757220864",
+      "cudaCores":  16384,
+      "architecture":  "Ada"
+    },
+    {
+      "name":  "NVIDIA GeForce RTX 4090",
+      "memoryTotal":  "25757220864",
+      "cudaCores":  16384,
+      "architecture":  "Ada"
+    },
+    {
+      "name":  "NVIDIA GeForce RTX 4090",
+      "memoryTotal":  "25757220864",
+      "cudaCores":  16384,
+      "architecture":  "Ada"
+    },
+    {
+      "name":  "NVIDIA GeForce RTX 4090",
+      "memoryTotal":  "25757220864",
+      "cudaCores":  16384,
+      "architecture":  "Ada"
+    },
+    {
+      "name":  "NVIDIA GeForce RTX 4090",
+      "memoryTotal":  "25757220864",
+      "cudaCores":  16384,
+      "architecture":  "Ada"
+    },
+    {
+      "name":  "NVIDIA GeForce RTX 4090",
+      "memoryTotal":  "25757220864",
+      "cudaCores":  16384,
+      "architecture":  "Ada"
+    },
+    {
+      "name":  "NVIDIA GeForce RTX 4090",
+      "memoryTotal":  "25757220864",
+      "cudaCores":  16384,
+      "architecture":  "Ada"
+    }
+  ],
+  "cudaVersion":  "12.6"
+}

unselective_run_1_restarted_with_o_rescaled/wandb/run-20250213_072314-jkzpfmgd/logs/debug-core.log

@@ -0,0 +1,6 @@
+{"time":"2025-02-13T07:23:14.183673864Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpkbqz87_y/port-2405.txt","pid":2405,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false}
+{"time":"2025-02-13T07:23:14.194851309Z","level":"INFO","msg":"Will exit if parent process dies.","ppid":2405}
+{"time":"2025-02-13T07:23:14.194758999Z","level":"INFO","msg":"server is running","addr":{"IP":"127.0.0.1","Port":38973,"Zone":""}}
+{"time":"2025-02-13T07:23:14.350871935Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"127.0.0.1:57822"}
+{"time":"2025-02-13T07:23:14.362170889Z","level":"INFO","msg":"handleInformInit: received","streamId":"jkzpfmgd","id":"127.0.0.1:57822"}
+{"time":"2025-02-13T07:23:14.581509397Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"jkzpfmgd","id":"127.0.0.1:57822"}

unselective_run_1_restarted_with_o_rescaled/wandb/run-20250213_072314-jkzpfmgd/logs/debug-internal.log

@@ -0,0 +1,7 @@
+{"time":"2025-02-13T07:23:14.362440989Z","level":"INFO","msg":"stream: starting","core version":"0.19.6","symlink path":"unselective_run_1_restarted_with_o_rescaled/wandb/run-20250213_072314-jkzpfmgd/logs/debug-core.log"}
+{"time":"2025-02-13T07:23:14.581470737Z","level":"INFO","msg":"created new stream","id":"jkzpfmgd"}
+{"time":"2025-02-13T07:23:14.581503917Z","level":"INFO","msg":"stream: started","id":"jkzpfmgd"}
+{"time":"2025-02-13T07:23:14.581523127Z","level":"INFO","msg":"writer: Do: started","stream_id":"jkzpfmgd"}
+{"time":"2025-02-13T07:23:14.581605127Z","level":"INFO","msg":"sender: started","stream_id":"jkzpfmgd"}
+{"time":"2025-02-13T07:23:14.581655667Z","level":"INFO","msg":"handler: started","stream_id":"jkzpfmgd"}
+{"time":"2025-02-13T07:23:14.820664913Z","level":"INFO","msg":"Starting system monitor"}

unselective_run_1_restarted_with_o_rescaled/wandb/run-20250213_072314-jkzpfmgd/logs/debug.log

@@ -0,0 +1,22 @@
+2025-02-13 07:23:14,140 INFO    MainThread:2405 [wandb_setup.py:_flush():68] Current SDK version is 0.19.6
+2025-02-13 07:23:14,140 INFO    MainThread:2405 [wandb_setup.py:_flush():68] Configure stats pid to 2405
+2025-02-13 07:23:14,140 INFO    MainThread:2405 [wandb_setup.py:_flush():68] Loading settings from /root/.config/wandb/settings
+2025-02-13 07:23:14,140 INFO    MainThread:2405 [wandb_setup.py:_flush():68] Loading settings from /workspace/context-compression/wandb/settings
+2025-02-13 07:23:14,140 INFO    MainThread:2405 [wandb_setup.py:_flush():68] Loading settings from environment variables
+2025-02-13 07:23:14,140 INFO    MainThread:2405 [wandb_init.py:setup_run_log_directory():637] Logging user logs to unselective_run_1_restarted_with_o_rescaled/wandb/run-20250213_072314-jkzpfmgd/logs/debug.log
+2025-02-13 07:23:14,140 INFO    MainThread:2405 [wandb_init.py:setup_run_log_directory():638] Logging internal logs to unselective_run_1_restarted_with_o_rescaled/wandb/run-20250213_072314-jkzpfmgd/logs/debug-internal.log
+2025-02-13 07:23:14,140 INFO    MainThread:2405 [wandb_init.py:init():756] calling init triggers
+2025-02-13 07:23:14,140 INFO    MainThread:2405 [wandb_init.py:init():761] wandb.init called with sweep_config: {}
+config: {'hellaswag': True, 'attention_kind': <AttentionKind.SELF: 'self'>, 'log_dir': 'unselective_run_1_restarted_with_o_rescaled', 'resume_checkpoint': 'hf://andrew-healey/context-compression/unselective_run_0/model_07500.pt', 'resume_optimizer': False, 'add_a_head': True, 'add_head_to_start': True, 'new_head_init': <NewHeadInit.O_RESCALED: 'o_rescaled'>, 'max_steps': 2500, 'group': 'selective_surgery_2', 'use_wandb': True, 'kill_self_after_run': False, '_wandb': {}}
+2025-02-13 07:23:14,140 INFO    MainThread:2405 [wandb_init.py:init():789] starting backend
+2025-02-13 07:23:14,350 INFO    MainThread:2405 [wandb_init.py:init():793] sending inform_init request
+2025-02-13 07:23:14,358 INFO    MainThread:2405 [backend.py:_multiprocessing_setup():97] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2025-02-13 07:23:14,359 INFO    MainThread:2405 [wandb_init.py:init():808] backend started and connected
+2025-02-13 07:23:14,367 INFO    MainThread:2405 [wandb_init.py:init():901] updated telemetry
+2025-02-13 07:23:14,376 INFO    MainThread:2405 [wandb_init.py:init():936] communicating run to backend with 90.0 second timeout
+2025-02-13 07:23:14,816 INFO    MainThread:2405 [wandb_init.py:init():994] starting run threads in backend
+2025-02-13 07:23:14,943 INFO    MainThread:2405 [wandb_run.py:_console_start():2385] atexit reg
+2025-02-13 07:23:14,943 INFO    MainThread:2405 [wandb_run.py:_redirect():2235] redirect: wrap_raw
+2025-02-13 07:23:14,944 INFO    MainThread:2405 [wandb_run.py:_redirect():2300] Wrapping output streams.
+2025-02-13 07:23:14,944 INFO    MainThread:2405 [wandb_run.py:_redirect():2325] Redirects installed.
+2025-02-13 07:23:14,945 INFO    MainThread:2405 [wandb_init.py:init():1036] run started, returning control to user process

unselective_run_1_restarted_with_o_rescaled/wandb/run-20250213_072314-jkzpfmgd/run-jkzpfmgd.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:017de5a052607dce97dc3d4061e75956874d7e7450c9b1edb79a288f668807ab
+size 3506176