Training in progress, step 20

adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query_key_valuelm_head",
-    "word_embeddings"
+    "word_embeddings",
+    "query_key_valuelm_head"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de52612f18d94eb85267cdbaa87cfac914b5a3415370220f048ff6627b5dc973
+oid sha256:4f5b4211357ffac39570b1f6e86556f478b9274661061048dc057539e048d76a
 size 8077608

runs/Apr12_07-35-52_e5a48bec8248/events.out.tfevents.1712907354.e5a48bec8248.289.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a24bc3f89fa8d99361dc24608208c2de729e4866df68e8d394ffeac11a1e43
+size 5489

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83256b55088d45d0ebeda1319a91e9b247c70b5f4d82cb04a018aa4a684554bc
+oid sha256:32e994f25267341e613f4d352977cc7a2847de358db5ece7a60fcf21be944170
 size 4984

wandb/debug-internal.log

@@ -1,32 +1,32 @@
-2024-04-12 07:27:36,633 INFO    StreamThr :216 [internal.py:wandb_internal():86] W&B internal server running at pid: 216, started at: 2024-04-12 07:27:36.632321
-2024-04-12 07:27:36,634 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status
-2024-04-12 07:27:36,923 INFO    WriterThread:216 [datastore.py:open_for_write():87] open: /kaggle/working/wandb/run-20240412_072736-gyl3aena/run-gyl3aena.wandb
-2024-04-12 07:27:36,923 DEBUG   SenderThread:216 [sender.py:send():379] send: header
-2024-04-12 07:27:36,926 DEBUG   SenderThread:216 [sender.py:send():379] send: run
-2024-04-12 07:27:37,028 INFO    SenderThread:216 [dir_watcher.py:__init__():211] watching files in: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files
-2024-04-12 07:27:37,029 INFO    SenderThread:216 [sender.py:_start_run_threads():1124] run started: gyl3aena with start time 1712906856.632079
-2024-04-12 07:27:37,038 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: check_version
-2024-04-12 07:27:37,038 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: check_version
-2024-04-12 07:27:37,127 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: run_start
-2024-04-12 07:27:37,138 DEBUG   HandlerThread:216 [system_info.py:__init__():26] System info init
-2024-04-12 07:27:37,139 DEBUG   HandlerThread:216 [system_info.py:__init__():41] System info init done
-2024-04-12 07:27:37,139 INFO    HandlerThread:216 [system_monitor.py:start():194] Starting system monitor
-2024-04-12 07:27:37,139 INFO    SystemMonitor:216 [system_monitor.py:_start():158] Starting system asset monitoring threads
-2024-04-12 07:27:37,139 INFO    HandlerThread:216 [system_monitor.py:probe():214] Collecting system info
-2024-04-12 07:27:37,140 INFO    SystemMonitor:216 [interfaces.py:start():190] Started cpu monitoring
-2024-04-12 07:27:37,140 INFO    SystemMonitor:216 [interfaces.py:start():190] Started disk monitoring
-2024-04-12 07:27:37,141 INFO    SystemMonitor:216 [interfaces.py:start():190] Started gpu monitoring
-2024-04-12 07:27:37,142 INFO    SystemMonitor:216 [interfaces.py:start():190] Started memory monitoring
-2024-04-12 07:27:37,144 INFO    SystemMonitor:216 [interfaces.py:start():190] Started network monitoring
-2024-04-12 07:27:37,154 DEBUG   HandlerThread:216 [system_info.py:probe():150] Probing system
-2024-04-12 07:27:37,156 DEBUG   HandlerThread:216 [gitlib.py:_init_repo():56] git repository is invalid
-2024-04-12 07:27:37,156 DEBUG   HandlerThread:216 [system_info.py:probe():198] Probing system done
-2024-04-12 07:27:37,156 DEBUG   HandlerThread:216 [system_monitor.py:probe():223] {'os': 'Linux-5.15.133+-x86_64-with-glibc2.31', 'python': '3.10.13', 'heartbeatAt': '2024-04-12T07:27:37.154498', 'startedAt': '2024-04-12T07:27:36.625772', 'docker': None, 'cuda': None, 'args': (), 'state': 'running', 'program': 'kaggle.ipynb', 'codePathLocal': None, 'root': '/kaggle/working', 'host': 'e5a48bec8248', 'username': 'root', 'executable': '/opt/conda/bin/python3.10', 'cpu_count': 2, 'cpu_count_logical': 4, 'cpu_freq': {'current': 2000.138, 'min': 0.0, 'max': 0.0}, 'cpu_freq_per_core': [{'current': 2000.138, 'min': 0.0, 'max': 0.0}, {'current': 2000.138, 'min': 0.0, 'max': 0.0}, {'current': 2000.138, 'min': 0.0, 'max': 0.0}, {'current': 2000.138, 'min': 0.0, 'max': 0.0}], 'disk': {'/': {'total': 8062.387607574463, 'used': 5565.782409667969}}, 'gpu': 'Tesla T4', 'gpu_count': 2, 'gpu_devices': [{'name': 'Tesla T4', 'memory_total': 16106127360}, {'name': 'Tesla T4', 'memory_total': 16106127360}], 'memory': {'total': 31.357559204101562}}
-2024-04-12 07:27:37,156 INFO    HandlerThread:216 [system_monitor.py:probe():224] Finished collecting system info
-2024-04-12 07:27:37,156 INFO    HandlerThread:216 [system_monitor.py:probe():227] Publishing system info
-2024-04-12 07:27:37,156 DEBUG   HandlerThread:216 [system_info.py:_save_conda():207] Saving list of conda packages installed into the current environment
-2024-04-12 07:27:38,030 INFO    Thread-12 :216 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/conda-environment.yaml
-2024-04-12 07:27:52,171 ERROR   HandlerThread:216 [system_info.py:_save_conda():221] Error saving conda packages: Command '['conda', 'env', 'export']' timed out after 15 seconds
+2024-04-12 07:35:55,749 INFO    StreamThr :334 [internal.py:wandb_internal():86] W&B internal server running at pid: 334, started at: 2024-04-12 07:35:55.748821
+2024-04-12 07:35:55,751 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status
+2024-04-12 07:35:56,159 INFO    WriterThread:334 [datastore.py:open_for_write():87] open: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/run-bw7oy9ix.wandb
+2024-04-12 07:35:56,160 DEBUG   SenderThread:334 [sender.py:send():379] send: header
+2024-04-12 07:35:56,163 DEBUG   SenderThread:334 [sender.py:send():379] send: run
+2024-04-12 07:35:56,307 INFO    SenderThread:334 [dir_watcher.py:__init__():211] watching files in: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files
+2024-04-12 07:35:56,307 INFO    SenderThread:334 [sender.py:_start_run_threads():1124] run started: bw7oy9ix with start time 1712907355.748886
+2024-04-12 07:35:56,317 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: check_version
+2024-04-12 07:35:56,317 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: check_version
+2024-04-12 07:35:56,409 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: run_start
+2024-04-12 07:35:56,421 DEBUG   HandlerThread:334 [system_info.py:__init__():26] System info init
+2024-04-12 07:35:56,421 DEBUG   HandlerThread:334 [system_info.py:__init__():41] System info init done
+2024-04-12 07:35:56,422 INFO    HandlerThread:334 [system_monitor.py:start():194] Starting system monitor
+2024-04-12 07:35:56,422 INFO    SystemMonitor:334 [system_monitor.py:_start():158] Starting system asset monitoring threads
+2024-04-12 07:35:56,422 INFO    HandlerThread:334 [system_monitor.py:probe():214] Collecting system info
+2024-04-12 07:35:56,423 INFO    SystemMonitor:334 [interfaces.py:start():190] Started cpu monitoring
+2024-04-12 07:35:56,423 INFO    SystemMonitor:334 [interfaces.py:start():190] Started disk monitoring
+2024-04-12 07:35:56,424 INFO    SystemMonitor:334 [interfaces.py:start():190] Started gpu monitoring
+2024-04-12 07:35:56,425 INFO    SystemMonitor:334 [interfaces.py:start():190] Started memory monitoring
+2024-04-12 07:35:56,426 INFO    SystemMonitor:334 [interfaces.py:start():190] Started network monitoring
+2024-04-12 07:35:56,437 DEBUG   HandlerThread:334 [system_info.py:probe():150] Probing system
+2024-04-12 07:35:56,439 DEBUG   HandlerThread:334 [gitlib.py:_init_repo():56] git repository is invalid
+2024-04-12 07:35:56,439 DEBUG   HandlerThread:334 [system_info.py:probe():198] Probing system done
+2024-04-12 07:35:56,439 DEBUG   HandlerThread:334 [system_monitor.py:probe():223] {'os': 'Linux-5.15.133+-x86_64-with-glibc2.31', 'python': '3.10.13', 'heartbeatAt': '2024-04-12T07:35:56.437403', 'startedAt': '2024-04-12T07:35:55.741618', 'docker': None, 'cuda': None, 'args': (), 'state': 'running', 'program': 'kaggle.ipynb', 'codePathLocal': None, 'root': '/kaggle/working', 'host': 'e5a48bec8248', 'username': 'root', 'executable': '/opt/conda/bin/python3.10', 'cpu_count': 2, 'cpu_count_logical': 4, 'cpu_freq': {'current': 2000.138, 'min': 0.0, 'max': 0.0}, 'cpu_freq_per_core': [{'current': 2000.138, 'min': 0.0, 'max': 0.0}, {'current': 2000.138, 'min': 0.0, 'max': 0.0}, {'current': 2000.138, 'min': 0.0, 'max': 0.0}, {'current': 2000.138, 'min': 0.0, 'max': 0.0}], 'disk': {'/': {'total': 8062.387607574463, 'used': 5565.782459259033}}, 'gpu': 'Tesla T4', 'gpu_count': 2, 'gpu_devices': [{'name': 'Tesla T4', 'memory_total': 16106127360}, {'name': 'Tesla T4', 'memory_total': 16106127360}], 'memory': {'total': 31.357559204101562}}
+2024-04-12 07:35:56,440 INFO    HandlerThread:334 [system_monitor.py:probe():224] Finished collecting system info
+2024-04-12 07:35:56,440 INFO    HandlerThread:334 [system_monitor.py:probe():227] Publishing system info
+2024-04-12 07:35:56,440 DEBUG   HandlerThread:334 [system_info.py:_save_conda():207] Saving list of conda packages installed into the current environment
+2024-04-12 07:35:57,309 INFO    Thread-12 :334 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/conda-environment.yaml
+2024-04-12 07:36:11,455 ERROR   HandlerThread:334 [system_info.py:_save_conda():221] Error saving conda packages: Command '['conda', 'env', 'export']' timed out after 15 seconds
 Traceback (most recent call last):
   File "/opt/conda/lib/python3.10/site-packages/wandb/sdk/internal/system/system_info.py", line 214, in _save_conda
     subprocess.call(
@@ -37,276 +37,41 @@ Traceback (most recent call last):
   File "/opt/conda/lib/python3.10/subprocess.py", line 1951, in _wait
     raise TimeoutExpired(self.args, timeout)
 subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after 15 seconds
-2024-04-12 07:27:52,172 DEBUG   HandlerThread:216 [system_info.py:_save_conda():222] Saving conda packages done
-2024-04-12 07:27:52,173 INFO    HandlerThread:216 [system_monitor.py:probe():229] Finished publishing system info
-2024-04-12 07:27:52,178 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:27:52,178 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: keepalive
-2024-04-12 07:27:52,178 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:27:52,178 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: keepalive
-2024-04-12 07:27:52,178 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:27:52,178 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: keepalive
-2024-04-12 07:27:52,179 DEBUG   SenderThread:216 [sender.py:send():379] send: files
-2024-04-12 07:27:52,179 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-metadata.json with policy now
-2024-04-12 07:27:52,388 INFO    wandb-upload_0:216 [upload_job.py:push():131] Uploaded file /tmp/tmpysomol4ewandb/y0nsu16m-wandb-metadata.json
-2024-04-12 07:27:53,034 INFO    Thread-12 :216 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/wandb-metadata.json
-2024-04-12 07:27:53,192 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: python_packages
-2024-04-12 07:27:53,193 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: python_packages
-2024-04-12 07:27:53,196 DEBUG   SenderThread:216 [sender.py:send():379] send: telemetry
-2024-04-12 07:27:53,207 DEBUG   SenderThread:216 [sender.py:send():379] send: config
-2024-04-12 07:27:53,209 DEBUG   SenderThread:216 [sender.py:send():379] send: metric
-2024-04-12 07:27:53,210 DEBUG   SenderThread:216 [sender.py:send():379] send: telemetry
-2024-04-12 07:27:53,210 DEBUG   SenderThread:216 [sender.py:send():379] send: metric
-2024-04-12 07:27:53,210 WARNING SenderThread:216 [sender.py:send_metric():1341] Seen metric with glob (shouldn't happen)
-2024-04-12 07:27:53,211 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:27:53,211 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:27:53,211 DEBUG   SenderThread:216 [sender.py:send():379] send: telemetry
-2024-04-12 07:27:53,212 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:27:54,034 INFO    Thread-12 :216 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/requirements.txt
-2024-04-12 07:27:54,035 INFO    Thread-12 :216 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/output.log
-2024-04-12 07:27:56,035 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/output.log
-2024-04-12 07:27:57,730 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:28:00,302 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: partial_history
-2024-04-12 07:28:00,305 DEBUG   SenderThread:216 [sender.py:send():379] send: metric
-2024-04-12 07:28:00,305 DEBUG   SenderThread:216 [sender.py:send():379] send: metric
-2024-04-12 07:28:00,306 DEBUG   SenderThread:216 [sender.py:send():379] send: metric
-2024-04-12 07:28:00,306 DEBUG   SenderThread:216 [sender.py:send():379] send: metric
-2024-04-12 07:28:00,306 DEBUG   SenderThread:216 [sender.py:send():379] send: history
-2024-04-12 07:28:00,306 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
-2024-04-12 07:28:00,308 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
-2024-04-12 07:28:01,037 INFO    Thread-12 :216 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/wandb-summary.json
-2024-04-12 07:28:02,038 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/output.log
-2024-04-12 07:28:03,008 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:28:06,847 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: partial_history
-2024-04-12 07:28:06,848 DEBUG   SenderThread:216 [sender.py:send():379] send: history
-2024-04-12 07:28:06,849 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
-2024-04-12 07:28:06,851 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
-2024-04-12 07:28:07,040 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/wandb-summary.json
-2024-04-12 07:28:08,201 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:28:08,201 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:28:08,202 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:28:08,314 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:28:09,041 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/config.yaml
-2024-04-12 07:28:10,041 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/output.log
-2024-04-12 07:28:13,125 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: partial_history
-2024-04-12 07:28:13,126 DEBUG   SenderThread:216 [sender.py:send():379] send: history
-2024-04-12 07:28:13,126 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
-2024-04-12 07:28:13,128 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
-2024-04-12 07:28:13,806 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: partial_history
-2024-04-12 07:28:13,807 DEBUG   SenderThread:216 [sender.py:send():379] send: telemetry
-2024-04-12 07:28:13,807 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
-2024-04-12 07:28:13,807 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:28:13,808 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
-2024-04-12 07:28:13,809 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
-2024-04-12 07:28:13,809 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
-2024-04-12 07:28:13,809 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
-2024-04-12 07:28:13,810 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
-2024-04-12 07:28:13,810 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
-2024-04-12 07:28:13,810 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
-2024-04-12 07:28:13,811 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
-2024-04-12 07:28:13,811 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
-2024-04-12 07:28:13,812 DEBUG   SenderThread:216 [sender.py:send():379] send: history
-2024-04-12 07:28:13,812 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
-2024-04-12 07:28:13,812 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
-2024-04-12 07:28:14,043 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/wandb-summary.json
-2024-04-12 07:28:18,814 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:28:23,193 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:28:23,194 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:28:23,194 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:28:24,273 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:28:26,760 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: pause
-2024-04-12 07:28:26,760 INFO    HandlerThread:216 [handler.py:handle_request_pause():708] stopping system metrics thread
-2024-04-12 07:28:26,760 INFO    HandlerThread:216 [system_monitor.py:finish():203] Stopping system monitor
-2024-04-12 07:28:26,761 INFO    HandlerThread:216 [interfaces.py:finish():202] Joined cpu monitor
-2024-04-12 07:28:26,761 INFO    HandlerThread:216 [interfaces.py:finish():202] Joined disk monitor
-2024-04-12 07:28:26,761 DEBUG   SystemMonitor:216 [system_monitor.py:_start():172] Starting system metrics aggregation loop
-2024-04-12 07:28:26,761 DEBUG   SystemMonitor:216 [system_monitor.py:_start():179] Finished system metrics aggregation loop
-2024-04-12 07:28:26,762 DEBUG   SystemMonitor:216 [system_monitor.py:_start():183] Publishing last batch of metrics
-2024-04-12 07:28:26,774 INFO    HandlerThread:216 [interfaces.py:finish():202] Joined gpu monitor
-2024-04-12 07:28:26,774 INFO    HandlerThread:216 [interfaces.py:finish():202] Joined memory monitor
-2024-04-12 07:28:26,774 INFO    HandlerThread:216 [interfaces.py:finish():202] Joined network monitor
-2024-04-12 07:28:26,775 DEBUG   SenderThread:216 [sender.py:send():379] send: stats
-2024-04-12 07:28:29,776 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:28:34,777 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:28:38,193 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:28:38,194 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:28:38,197 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:28:40,261 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:28:41,053 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/config.yaml
-2024-04-12 07:28:45,363 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:28:50,364 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:28:53,193 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:28:53,194 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:28:53,234 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:28:56,263 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:29:01,264 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:29:06,266 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:29:08,194 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:29:08,194 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:29:08,235 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:29:12,239 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:29:17,240 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:29:22,241 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:29:23,194 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:29:23,194 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:29:23,235 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:29:27,289 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:29:32,290 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:29:37,291 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:29:38,194 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:29:38,195 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:29:38,235 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:29:42,325 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:29:47,326 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:29:52,327 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:29:53,194 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:29:53,195 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:29:53,235 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:29:58,280 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:30:03,281 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:30:08,194 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:30:08,195 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:30:08,235 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:30:09,269 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:30:14,270 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:30:19,271 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:30:23,195 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:30:23,195 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:30:23,235 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:30:24,322 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:30:29,323 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:30:34,324 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:30:38,195 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:30:38,195 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:30:38,236 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:30:39,325 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:30:44,326 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:30:49,327 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:30:53,195 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:30:53,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:30:53,236 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:30:55,310 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:31:00,311 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:31:05,312 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:31:08,195 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:31:08,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:31:08,236 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:31:11,254 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:31:16,255 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:31:21,256 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:31:23,195 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:31:23,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:31:23,236 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:31:26,273 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:31:31,274 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:31:36,275 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:31:38,195 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:31:38,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:31:38,236 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:31:41,323 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:31:46,325 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:31:51,326 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:31:53,196 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:31:53,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:31:53,236 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:31:57,277 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:32:02,278 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:32:07,279 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:32:08,196 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:32:08,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:32:08,237 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:32:12,341 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:32:17,342 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:32:22,343 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:32:23,196 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:32:23,196 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:32:23,237 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:32:28,314 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:32:33,315 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:32:38,196 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:32:38,197 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:32:38,237 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:32:39,296 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:32:44,297 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:32:49,299 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:32:53,196 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:32:53,197 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:32:53,237 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:32:55,259 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:33:00,260 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:33:05,261 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:33:08,196 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:33:08,197 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:33:08,237 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:33:10,292 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:33:15,293 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:33:20,294 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:33:23,197 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:33:23,197 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:33:23,237 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:33:26,254 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:33:31,255 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:33:36,256 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:33:38,197 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:33:38,197 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:33:38,238 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:33:41,304 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:33:46,269 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: resume
-2024-04-12 07:33:46,269 INFO    HandlerThread:216 [handler.py:handle_request_resume():699] starting system metrics thread
-2024-04-12 07:33:46,269 INFO    HandlerThread:216 [system_monitor.py:start():194] Starting system monitor
-2024-04-12 07:33:46,269 INFO    SystemMonitor:216 [system_monitor.py:_start():158] Starting system asset monitoring threads
-2024-04-12 07:33:46,270 INFO    SystemMonitor:216 [interfaces.py:start():190] Started cpu monitoring
-2024-04-12 07:33:46,271 INFO    SystemMonitor:216 [interfaces.py:start():190] Started disk monitoring
-2024-04-12 07:33:46,271 INFO    SystemMonitor:216 [interfaces.py:start():190] Started gpu monitoring
-2024-04-12 07:33:46,272 INFO    SystemMonitor:216 [interfaces.py:start():190] Started memory monitoring
-2024-04-12 07:33:46,273 INFO    SystemMonitor:216 [interfaces.py:start():190] Started network monitoring
-2024-04-12 07:33:46,304 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:33:50,616 DEBUG   SenderThread:216 [sender.py:send():379] send: config
-2024-04-12 07:33:50,617 DEBUG   SenderThread:216 [sender.py:send():379] send: metric
-2024-04-12 07:33:50,617 DEBUG   SenderThread:216 [sender.py:send():379] send: metric
-2024-04-12 07:33:50,617 WARNING SenderThread:216 [sender.py:send_metric():1341] Seen metric with glob (shouldn't happen)
-2024-04-12 07:33:51,634 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:33:52,173 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/config.yaml
-2024-04-12 07:33:52,173 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/output.log
-2024-04-12 07:33:53,197 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:33:53,197 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:33:53,200 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:33:57,222 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: partial_history
-2024-04-12 07:33:57,224 DEBUG   SenderThread:216 [sender.py:send():379] send: history
-2024-04-12 07:33:57,224 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
-2024-04-12 07:33:57,224 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:33:57,225 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
-2024-04-12 07:33:58,175 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/wandb-summary.json
-2024-04-12 07:34:00,176 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/output.log
-2024-04-12 07:34:03,010 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:34:04,112 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: partial_history
-2024-04-12 07:34:04,114 DEBUG   SenderThread:216 [sender.py:send():379] send: history
-2024-04-12 07:34:04,114 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
-2024-04-12 07:34:04,114 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
-2024-04-12 07:34:04,178 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/wandb-summary.json
-2024-04-12 07:34:06,179 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/output.log
-2024-04-12 07:34:08,197 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
-2024-04-12 07:34:08,198 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
-2024-04-12 07:34:08,201 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
-2024-04-12 07:34:08,317 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:34:10,454 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: partial_history
-2024-04-12 07:34:10,455 DEBUG   SenderThread:216 [sender.py:send():379] send: history
-2024-04-12 07:34:10,455 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
-2024-04-12 07:34:10,456 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
-2024-04-12 07:34:11,182 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
-2024-04-12 07:34:11,184 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: partial_history
-2024-04-12 07:34:11,185 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
-2024-04-12 07:34:11,185 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
-2024-04-12 07:34:11,186 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
-2024-04-12 07:34:11,187 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
-2024-04-12 07:34:11,187 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/wandb-summary.json
-2024-04-12 07:34:11,188 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
-2024-04-12 07:34:11,188 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
-2024-04-12 07:34:11,188 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
-2024-04-12 07:34:11,189 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
-2024-04-12 07:34:11,189 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
-2024-04-12 07:34:11,189 DEBUG   SenderThread:216 [sender.py:send():379] send: history
-2024-04-12 07:34:11,189 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
-2024-04-12 07:34:11,190 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
-2024-04-12 07:34:12,187 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/wandb-summary.json
-2024-04-12 07:34:14,191 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
-2024-04-12 07:34:19,191 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:36:11,456 DEBUG   HandlerThread:334 [system_info.py:_save_conda():222] Saving conda packages done
+2024-04-12 07:36:11,456 INFO    HandlerThread:334 [system_monitor.py:probe():229] Finished publishing system info
+2024-04-12 07:36:11,462 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:36:11,462 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: keepalive
+2024-04-12 07:36:11,462 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:36:11,462 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: keepalive
+2024-04-12 07:36:11,462 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:36:11,462 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: keepalive
+2024-04-12 07:36:11,463 DEBUG   SenderThread:334 [sender.py:send():379] send: files
+2024-04-12 07:36:11,463 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-metadata.json with policy now
+2024-04-12 07:36:11,664 INFO    wandb-upload_0:334 [upload_job.py:push():131] Uploaded file /tmp/tmpjph8qv3dwandb/f1up76ir-wandb-metadata.json
+2024-04-12 07:36:12,312 INFO    Thread-12 :334 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/wandb-metadata.json
+2024-04-12 07:36:12,509 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: python_packages
+2024-04-12 07:36:12,509 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: python_packages
+2024-04-12 07:36:12,512 DEBUG   SenderThread:334 [sender.py:send():379] send: telemetry
+2024-04-12 07:36:12,523 DEBUG   SenderThread:334 [sender.py:send():379] send: config
+2024-04-12 07:36:12,525 DEBUG   SenderThread:334 [sender.py:send():379] send: metric
+2024-04-12 07:36:12,534 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:36:12,535 DEBUG   SenderThread:334 [sender.py:send():379] send: telemetry
+2024-04-12 07:36:12,535 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:36:12,535 DEBUG   SenderThread:334 [sender.py:send():379] send: metric
+2024-04-12 07:36:12,536 WARNING SenderThread:334 [sender.py:send_metric():1341] Seen metric with glob (shouldn't happen)
+2024-04-12 07:36:12,536 DEBUG   SenderThread:334 [sender.py:send():379] send: telemetry
+2024-04-12 07:36:12,536 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:36:13,313 INFO    Thread-12 :334 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/requirements.txt
+2024-04-12 07:36:13,313 INFO    Thread-12 :334 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/output.log
+2024-04-12 07:36:15,314 INFO    Thread-12 :334 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/output.log
+2024-04-12 07:36:17,014 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:36:19,589 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:36:19,592 DEBUG   SenderThread:334 [sender.py:send():379] send: metric
+2024-04-12 07:36:19,593 DEBUG   SenderThread:334 [sender.py:send():379] send: metric
+2024-04-12 07:36:19,593 DEBUG   SenderThread:334 [sender.py:send():379] send: metric
+2024-04-12 07:36:19,593 DEBUG   SenderThread:334 [sender.py:send():379] send: metric
+2024-04-12 07:36:19,593 DEBUG   SenderThread:334 [sender.py:send():379] send: history
+2024-04-12 07:36:19,593 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:36:19,595 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:36:20,316 INFO    Thread-12 :334 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/wandb-summary.json
+2024-04-12 07:36:21,316 INFO    Thread-12 :334 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/output.log

wandb/debug.log

@@ -1,35 +1,31 @@
-2024-04-12 07:27:36,627 INFO    MainThread:174 [wandb_setup.py:_flush():76] Current SDK version is 0.16.5
-2024-04-12 07:27:36,627 INFO    MainThread:174 [wandb_setup.py:_flush():76] Configure stats pid to 174
-2024-04-12 07:27:36,627 INFO    MainThread:174 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings
-2024-04-12 07:27:36,627 INFO    MainThread:174 [wandb_setup.py:_flush():76] Loading settings from /kaggle/working/wandb/settings
-2024-04-12 07:27:36,627 INFO    MainThread:174 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
-2024-04-12 07:27:36,627 INFO    MainThread:174 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
-2024-04-12 07:27:36,628 INFO    MainThread:174 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': '<python with no main file>'}
-2024-04-12 07:27:36,628 INFO    MainThread:174 [wandb_setup.py:_flush():76] Applying login settings: {}
-2024-04-12 07:27:36,628 INFO    MainThread:174 [wandb_init.py:_log_setup():527] Logging user logs to /kaggle/working/wandb/run-20240412_072736-gyl3aena/logs/debug.log
-2024-04-12 07:27:36,628 INFO    MainThread:174 [wandb_init.py:_log_setup():528] Logging internal logs to /kaggle/working/wandb/run-20240412_072736-gyl3aena/logs/debug-internal.log
-2024-04-12 07:27:36,628 INFO    MainThread:174 [wandb_init.py:_jupyter_setup():473] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x7db4ec9acdf0>
-2024-04-12 07:27:36,628 INFO    MainThread:174 [wandb_init.py:init():567] calling init triggers
-2024-04-12 07:27:36,628 INFO    MainThread:174 [wandb_init.py:init():574] wandb.init called with sweep_config: {}
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_setup.py:_flush():76] Current SDK version is 0.16.5
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_setup.py:_flush():76] Configure stats pid to 289
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_setup.py:_flush():76] Loading settings from /kaggle/working/wandb/settings
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': '<python with no main file>'}
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_setup.py:_flush():76] Applying login settings: {}
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_init.py:_log_setup():527] Logging user logs to /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/logs/debug.log
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_init.py:_log_setup():528] Logging internal logs to /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/logs/debug-internal.log
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_init.py:_jupyter_setup():473] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x7c2cd1fccd60>
+2024-04-12 07:35:55,745 INFO    MainThread:289 [wandb_init.py:init():567] calling init triggers
+2024-04-12 07:35:55,745 INFO    MainThread:289 [wandb_init.py:init():574] wandb.init called with sweep_config: {}
 config: {}
-2024-04-12 07:27:36,628 INFO    MainThread:174 [wandb_init.py:init():617] starting backend
-2024-04-12 07:27:36,628 INFO    MainThread:174 [wandb_init.py:init():621] setting up manager
-2024-04-12 07:27:36,630 INFO    MainThread:174 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
-2024-04-12 07:27:36,631 INFO    MainThread:174 [wandb_init.py:init():629] backend started and connected
-2024-04-12 07:27:36,644 INFO    MainThread:174 [wandb_run.py:_label_probe_notebook():1299] probe notebook
-2024-04-12 07:27:36,922 INFO    MainThread:174 [wandb_init.py:init():721] updated telemetry
-2024-04-12 07:27:36,925 INFO    MainThread:174 [wandb_init.py:init():754] communicating run to backend with 90.0 second timeout
-2024-04-12 07:27:37,037 INFO    MainThread:174 [wandb_run.py:_on_init():2344] communicating current version
-2024-04-12 07:27:37,121 INFO    MainThread:174 [wandb_run.py:_on_init():2353] got version response upgrade_message: "wandb version 0.16.6 is available!  To upgrade, please run:\n $ pip install wandb --upgrade"
+2024-04-12 07:35:55,745 INFO    MainThread:289 [wandb_init.py:init():617] starting backend
+2024-04-12 07:35:55,745 INFO    MainThread:289 [wandb_init.py:init():621] setting up manager
+2024-04-12 07:35:55,747 INFO    MainThread:289 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-04-12 07:35:55,748 INFO    MainThread:289 [wandb_init.py:init():629] backend started and connected
+2024-04-12 07:35:55,761 INFO    MainThread:289 [wandb_run.py:_label_probe_notebook():1299] probe notebook
+2024-04-12 07:35:56,159 INFO    MainThread:289 [wandb_init.py:init():721] updated telemetry
+2024-04-12 07:35:56,162 INFO    MainThread:289 [wandb_init.py:init():754] communicating run to backend with 90.0 second timeout
+2024-04-12 07:35:56,316 INFO    MainThread:289 [wandb_run.py:_on_init():2344] communicating current version
+2024-04-12 07:35:56,402 INFO    MainThread:289 [wandb_run.py:_on_init():2353] got version response upgrade_message: "wandb version 0.16.6 is available!  To upgrade, please run:\n $ pip install wandb --upgrade"
 
-2024-04-12 07:27:37,121 INFO    MainThread:174 [wandb_init.py:init():805] starting run threads in backend
-2024-04-12 07:27:53,193 INFO    MainThread:174 [wandb_run.py:_console_start():2323] atexit reg
-2024-04-12 07:27:53,194 INFO    MainThread:174 [wandb_run.py:_redirect():2178] redirect: wrap_raw
-2024-04-12 07:27:53,194 INFO    MainThread:174 [wandb_run.py:_redirect():2243] Wrapping output streams.
-2024-04-12 07:27:53,194 INFO    MainThread:174 [wandb_run.py:_redirect():2268] Redirects installed.
-2024-04-12 07:27:53,195 INFO    MainThread:174 [wandb_init.py:init():848] run started, returning control to user process
-2024-04-12 07:27:53,201 INFO    MainThread:174 [wandb_run.py:_config_callback():1347] config_cb None None {'vocab_size': 250880, 'hidden_size': 1536, 'n_layer': 24, 'n_head': 16, 'layer_norm_epsilon': 1e-05, 'initializer_range': 0.02, 'use_cache': False, 'pretraining_tp': 1, 'apply_residual_connection_post_layernorm': False, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'bos_token_id': 1, 'eos_token_id': 2, 'slow_but_exact': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['BloomForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'pad_token_id': 3, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'bigscience/bloomz-1b1', 'transformers_version': '4.39.3', 'attention_softmax_in_fp32': True, 'bias_dropout_fusion': True, 'unk_token_id': 0, 'masked_softmax_fusion': True, 'model_type': 'bloom', 'n_inner': None, 'offset_alibi': 100, 'seq_length': 2048, 'skip_bias_add': True, 'skip_bias_add_qkv': False, 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', '_load_in_8bit': False, '_load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'float16', 'bnb_4bit_quant_storage': 'uint8', 'load_in_4bit': True, 'load_in_8bit': False}, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 3e-05, 'weight_decay': 0.0001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.3, 'num_train_epochs': 5, 'max_steps': 60, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/Apr12_07-27-33_e5a48bec8248', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 20, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 20, 'save_total_limit': 1, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': 'Femboyuwu2000/bloomz-1b1-vn-chat', 'hub_strategy': 'checkpoint', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
-2024-04-12 07:28:26,759 INFO    MainThread:174 [jupyter.py:save_ipynb():373] not saving jupyter notebook
-2024-04-12 07:28:26,759 INFO    MainThread:174 [wandb_init.py:_pause_backend():438] pausing backend
-2024-04-12 07:33:46,268 INFO    MainThread:174 [wandb_init.py:_resume_backend():443] resuming backend
-2024-04-12 07:33:50,610 INFO    MainThread:174 [wandb_run.py:_config_callback():1347] config_cb None None {'vocab_size': 250880, 'hidden_size': 1536, 'n_layer': 24, 'n_head': 16, 'layer_norm_epsilon': 1e-05, 'initializer_range': 0.02, 'use_cache': False, 'pretraining_tp': 1, 'apply_residual_connection_post_layernorm': False, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'bos_token_id': 1, 'eos_token_id': 2, 'slow_but_exact': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['BloomForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'pad_token_id': 3, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'bigscience/bloomz-1b1', 'transformers_version': '4.39.3', 'attention_softmax_in_fp32': True, 'bias_dropout_fusion': True, 'unk_token_id': 0, 'masked_softmax_fusion': True, 'model_type': 'bloom', 'n_inner': None, 'offset_alibi': 100, 'seq_length': 2048, 'skip_bias_add': True, 'skip_bias_add_qkv': False, 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', '_load_in_8bit': False, '_load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'float16', 'bnb_4bit_quant_storage': 'uint8', 'load_in_4bit': True, 'load_in_8bit': False}, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 3e-05, 'weight_decay': 0.0001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.3, 'num_train_epochs': 5, 'max_steps': 60, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/Apr12_07-33-49_e5a48bec8248', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 20, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 20, 'save_total_limit': 1, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': 'Femboyuwu2000/bloomz-1b1-vn-chat', 'hub_strategy': 'checkpoint', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
+2024-04-12 07:35:56,403 INFO    MainThread:289 [wandb_init.py:init():805] starting run threads in backend
+2024-04-12 07:36:12,510 INFO    MainThread:289 [wandb_run.py:_console_start():2323] atexit reg
+2024-04-12 07:36:12,510 INFO    MainThread:289 [wandb_run.py:_redirect():2178] redirect: wrap_raw
+2024-04-12 07:36:12,511 INFO    MainThread:289 [wandb_run.py:_redirect():2243] Wrapping output streams.
+2024-04-12 07:36:12,511 INFO    MainThread:289 [wandb_run.py:_redirect():2268] Redirects installed.
+2024-04-12 07:36:12,512 INFO    MainThread:289 [wandb_init.py:init():848] run started, returning control to user process
+2024-04-12 07:36:12,518 INFO    MainThread:289 [wandb_run.py:_config_callback():1347] config_cb None None {'vocab_size': 250880, 'hidden_size': 1536, 'n_layer': 24, 'n_head': 16, 'layer_norm_epsilon': 1e-05, 'initializer_range': 0.02, 'use_cache': False, 'pretraining_tp': 1, 'apply_residual_connection_post_layernorm': False, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'bos_token_id': 1, 'eos_token_id': 2, 'slow_but_exact': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['BloomForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'pad_token_id': 3, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'bigscience/bloomz-1b1', 'transformers_version': '4.39.3', 'attention_softmax_in_fp32': True, 'bias_dropout_fusion': True, 'unk_token_id': 0, 'masked_softmax_fusion': True, 'model_type': 'bloom', 'n_inner': None, 'offset_alibi': 100, 'seq_length': 2048, 'skip_bias_add': True, 'skip_bias_add_qkv': False, 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', '_load_in_8bit': False, '_load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'float16', 'bnb_4bit_quant_storage': 'uint8', 'load_in_4bit': True, 'load_in_8bit': False}, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 3e-05, 'weight_decay': 0.0001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.3, 'num_train_epochs': 5, 'max_steps': 20000, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/Apr12_07-35-52_e5a48bec8248', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 20, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 20, 'save_total_limit': 1, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': 'Femboyuwu2000/bloomz-1b1-vn-chat', 'hub_strategy': 'checkpoint', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}

wandb/run-20240412_072736-gyl3aena/files/output.log

@@ -13,3 +13,4 @@ dataloader_config = DataLoaderConfiguration(dispatch_batches=None, split_batches
 /opt/conda/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
   warnings.warn(
 /opt/conda/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
+  warnings.warn(

wandb/run-20240412_072736-gyl3aena/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 4.8834, "train/grad_norm": 86.45769500732422, "train/learning_rate": 0.0, "train/epoch": 0.0, "train/global_step": 60, "_timestamp": 1712907251.181722, "_runtime": 394.54964303970337, "_step": 7, "train_runtime": 20.5872, "train_samples_per_second": 5.829, "train_steps_per_second": 2.914, "total_flos": 19812939669504.0, "train_loss": 4.715130106608073}
+{"train/loss": 4.8834, "train/grad_norm": 86.45769500732422, "train/learning_rate": 0.0, "train/epoch": 0.0, "train/global_step": 60, "_timestamp": 1712907251.181722, "_runtime": 394.54964303970337, "_step": 7, "train_runtime": 20.5872, "train_samples_per_second": 5.829, "train_steps_per_second": 2.914, "total_flos": 19812939669504.0, "train_loss": 4.715130106608073, "_wandb": {"runtime": 86}}

wandb/run-20240412_072736-gyl3aena/logs/debug-internal.log

@@ -310,3 +310,124 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 07:34:12,187 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/wandb-summary.json
 2024-04-12 07:34:14,191 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
 2024-04-12 07:34:19,191 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:34:22,622 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: pause
+2024-04-12 07:34:22,622 INFO    HandlerThread:216 [handler.py:handle_request_pause():708] stopping system metrics thread
+2024-04-12 07:34:22,622 INFO    HandlerThread:216 [system_monitor.py:finish():203] Stopping system monitor
+2024-04-12 07:34:22,623 DEBUG   SystemMonitor:216 [system_monitor.py:_start():172] Starting system metrics aggregation loop
+2024-04-12 07:34:22,623 INFO    HandlerThread:216 [interfaces.py:finish():202] Joined cpu monitor
+2024-04-12 07:34:22,623 DEBUG   SystemMonitor:216 [system_monitor.py:_start():179] Finished system metrics aggregation loop
+2024-04-12 07:34:22,624 INFO    HandlerThread:216 [interfaces.py:finish():202] Joined disk monitor
+2024-04-12 07:34:22,624 DEBUG   SystemMonitor:216 [system_monitor.py:_start():183] Publishing last batch of metrics
+2024-04-12 07:34:22,634 INFO    HandlerThread:216 [interfaces.py:finish():202] Joined gpu monitor
+2024-04-12 07:34:22,635 INFO    HandlerThread:216 [interfaces.py:finish():202] Joined memory monitor
+2024-04-12 07:34:22,635 INFO    HandlerThread:216 [interfaces.py:finish():202] Joined network monitor
+2024-04-12 07:34:22,635 DEBUG   SenderThread:216 [sender.py:send():379] send: stats
+2024-04-12 07:34:23,197 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:34:23,198 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:34:23,198 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:34:24,309 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:34:29,310 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:34:34,311 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:34:38,197 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:34:38,198 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:34:38,238 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:34:40,296 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:34:45,297 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:34:50,298 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:34:53,198 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:34:53,198 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:34:53,238 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:34:56,282 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:35:01,283 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:35:06,284 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:35:08,198 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:35:08,198 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:35:08,238 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:35:11,071 DEBUG   SenderThread:216 [sender.py:send():379] send: exit
+2024-04-12 07:35:11,071 INFO    SenderThread:216 [sender.py:send_exit():586] handling exit code: 0
+2024-04-12 07:35:11,071 INFO    SenderThread:216 [sender.py:send_exit():588] handling runtime: 86
+2024-04-12 07:35:11,073 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:35:11,074 INFO    SenderThread:216 [sender.py:send_exit():594] send defer
+2024-04-12 07:35:11,074 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: defer
+2024-04-12 07:35:11,074 INFO    HandlerThread:216 [handler.py:handle_request_defer():172] handle defer: 0
+2024-04-12 07:35:11,074 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: defer
+2024-04-12 07:35:11,074 INFO    SenderThread:216 [sender.py:send_request_defer():610] handle sender defer: 0
+2024-04-12 07:35:11,074 INFO    SenderThread:216 [sender.py:transition_state():614] send defer: 1
+2024-04-12 07:35:11,074 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: defer
+2024-04-12 07:35:11,074 INFO    HandlerThread:216 [handler.py:handle_request_defer():172] handle defer: 1
+2024-04-12 07:35:11,075 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: defer
+2024-04-12 07:35:11,075 INFO    SenderThread:216 [sender.py:send_request_defer():610] handle sender defer: 1
+2024-04-12 07:35:11,075 INFO    SenderThread:216 [sender.py:transition_state():614] send defer: 2
+2024-04-12 07:35:11,075 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: defer
+2024-04-12 07:35:11,075 INFO    HandlerThread:216 [handler.py:handle_request_defer():172] handle defer: 2
+2024-04-12 07:35:11,075 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: defer
+2024-04-12 07:35:11,075 INFO    SenderThread:216 [sender.py:send_request_defer():610] handle sender defer: 2
+2024-04-12 07:35:11,075 INFO    SenderThread:216 [sender.py:transition_state():614] send defer: 3
+2024-04-12 07:35:11,075 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: defer
+2024-04-12 07:35:11,075 INFO    HandlerThread:216 [handler.py:handle_request_defer():172] handle defer: 3
+2024-04-12 07:35:11,076 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: defer
+2024-04-12 07:35:11,076 INFO    SenderThread:216 [sender.py:send_request_defer():610] handle sender defer: 3
+2024-04-12 07:35:11,076 INFO    SenderThread:216 [sender.py:transition_state():614] send defer: 4
+2024-04-12 07:35:11,076 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: defer
+2024-04-12 07:35:11,076 INFO    HandlerThread:216 [handler.py:handle_request_defer():172] handle defer: 4
+2024-04-12 07:35:11,076 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: defer
+2024-04-12 07:35:11,076 INFO    SenderThread:216 [sender.py:send_request_defer():610] handle sender defer: 4
+2024-04-12 07:35:11,076 INFO    SenderThread:216 [sender.py:transition_state():614] send defer: 5
+2024-04-12 07:35:11,076 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: defer
+2024-04-12 07:35:11,077 INFO    HandlerThread:216 [handler.py:handle_request_defer():172] handle defer: 5
+2024-04-12 07:35:11,077 DEBUG   SenderThread:216 [sender.py:send():379] send: summary
+2024-04-12 07:35:11,077 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:35:11,078 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: defer
+2024-04-12 07:35:11,078 INFO    SenderThread:216 [sender.py:send_request_defer():610] handle sender defer: 5
+2024-04-12 07:35:11,078 INFO    SenderThread:216 [sender.py:transition_state():614] send defer: 6
+2024-04-12 07:35:11,078 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: defer
+2024-04-12 07:35:11,078 INFO    HandlerThread:216 [handler.py:handle_request_defer():172] handle defer: 6
+2024-04-12 07:35:11,078 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: defer
+2024-04-12 07:35:11,078 INFO    SenderThread:216 [sender.py:send_request_defer():610] handle sender defer: 6
+2024-04-12 07:35:11,078 INFO    SenderThread:216 [sender.py:transition_state():614] send defer: 7
+2024-04-12 07:35:11,078 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:35:11,079 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: defer
+2024-04-12 07:35:11,079 INFO    HandlerThread:216 [handler.py:handle_request_defer():172] handle defer: 7
+2024-04-12 07:35:11,079 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: defer
+2024-04-12 07:35:11,079 INFO    SenderThread:216 [sender.py:send_request_defer():610] handle sender defer: 7
+2024-04-12 07:35:11,209 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/wandb-summary.json
+2024-04-12 07:35:12,071 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: poll_exit
+2024-04-12 07:35:13,826 INFO    SenderThread:216 [sender.py:transition_state():614] send defer: 8
+2024-04-12 07:35:13,826 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: poll_exit
+2024-04-12 07:35:13,827 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: defer
+2024-04-12 07:35:13,827 INFO    HandlerThread:216 [handler.py:handle_request_defer():172] handle defer: 8
+2024-04-12 07:35:13,827 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: defer
+2024-04-12 07:35:13,827 INFO    SenderThread:216 [sender.py:send_request_defer():610] handle sender defer: 8
+2024-04-12 07:35:13,827 INFO    SenderThread:216 [job_builder.py:build():318] Attempting to build job artifact
+2024-04-12 07:35:13,830 INFO    SenderThread:216 [job_builder.py:_get_source_type():466] no source found
+2024-04-12 07:35:13,830 INFO    SenderThread:216 [sender.py:transition_state():614] send defer: 9
+2024-04-12 07:35:13,830 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: defer
+2024-04-12 07:35:13,830 INFO    HandlerThread:216 [handler.py:handle_request_defer():172] handle defer: 9
+2024-04-12 07:35:13,830 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: defer
+2024-04-12 07:35:13,830 INFO    SenderThread:216 [sender.py:send_request_defer():610] handle sender defer: 9
+2024-04-12 07:35:13,830 INFO    SenderThread:216 [dir_watcher.py:finish():358] shutting down directory watcher
+2024-04-12 07:35:14,073 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: poll_exit
+2024-04-12 07:35:14,124 WARNING StreamThr :216 [internal.py:is_dead():414] Internal process exiting, parent pid 174 disappeared
+2024-04-12 07:35:14,125 ERROR   StreamThr :216 [internal.py:wandb_internal():152] Internal process shutdown.
+2024-04-12 07:35:14,210 INFO    SenderThread:216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/output.log
+2024-04-12 07:35:14,211 INFO    SenderThread:216 [dir_watcher.py:finish():388] scan: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files
+2024-04-12 07:35:14,211 INFO    SenderThread:216 [dir_watcher.py:finish():402] scan save: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/conda-environment.yaml conda-environment.yaml
+2024-04-12 07:35:14,212 INFO    SenderThread:216 [dir_watcher.py:finish():402] scan save: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/requirements.txt requirements.txt
+2024-04-12 07:35:14,212 INFO    SenderThread:216 [dir_watcher.py:finish():402] scan save: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/output.log output.log
+2024-04-12 07:35:14,213 INFO    SenderThread:216 [dir_watcher.py:finish():402] scan save: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/wandb-summary.json wandb-summary.json
+2024-04-12 07:35:14,219 INFO    SenderThread:216 [dir_watcher.py:finish():402] scan save: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/config.yaml config.yaml
+2024-04-12 07:35:14,225 INFO    SenderThread:216 [dir_watcher.py:finish():402] scan save: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/wandb-metadata.json wandb-metadata.json
+2024-04-12 07:35:14,225 INFO    SenderThread:216 [sender.py:transition_state():614] send defer: 10
+2024-04-12 07:35:14,226 INFO    SenderThread:216 [sender.py:finish():1546] shutting down sender
+2024-04-12 07:35:14,226 INFO    SenderThread:216 [file_pusher.py:finish():172] shutting down file pusher
+2024-04-12 07:35:14,226 INFO    SenderThread:216 [file_pusher.py:join():178] waiting for file pusher
+2024-04-12 07:35:14,226 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: defer
+2024-04-12 07:35:14,226 INFO    HandlerThread:216 [handler.py:handle_request_defer():172] handle defer: 10
+2024-04-12 07:35:14,226 INFO    HandlerThread:216 [handler.py:finish():866] shutting down handler
+2024-04-12 07:35:14,227 INFO    WriterThread:216 [datastore.py:close():296] close: /kaggle/working/wandb/run-20240412_072736-gyl3aena/run-gyl3aena.wandb
+2024-04-12 07:35:14,441 INFO    wandb-upload_1:216 [upload_job.py:push():131] Uploaded file /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/output.log
+2024-04-12 07:35:14,519 INFO    wandb-upload_2:216 [upload_job.py:push():131] Uploaded file /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/wandb-summary.json
+2024-04-12 07:35:14,520 INFO    wandb-upload_3:216 [upload_job.py:push():131] Uploaded file /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/config.yaml
+2024-04-12 07:35:14,521 INFO    wandb-upload_0:216 [upload_job.py:push():131] Uploaded file /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/requirements.txt
+2024-04-12 07:35:14,727 INFO    SenderThread:216 [file_stream.py:finish():614] file stream finish called
+2024-04-12 07:35:14,790 INFO    SenderThread:216 [file_stream.py:finish():618] file stream finish is done

wandb/run-20240412_072736-gyl3aena/logs/debug.log

@@ -33,3 +33,5 @@ config: {}
 2024-04-12 07:28:26,759 INFO    MainThread:174 [wandb_init.py:_pause_backend():438] pausing backend
 2024-04-12 07:33:46,268 INFO    MainThread:174 [wandb_init.py:_resume_backend():443] resuming backend
 2024-04-12 07:33:50,610 INFO    MainThread:174 [wandb_run.py:_config_callback():1347] config_cb None None {'vocab_size': 250880, 'hidden_size': 1536, 'n_layer': 24, 'n_head': 16, 'layer_norm_epsilon': 1e-05, 'initializer_range': 0.02, 'use_cache': False, 'pretraining_tp': 1, 'apply_residual_connection_post_layernorm': False, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'bos_token_id': 1, 'eos_token_id': 2, 'slow_but_exact': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['BloomForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'pad_token_id': 3, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'bigscience/bloomz-1b1', 'transformers_version': '4.39.3', 'attention_softmax_in_fp32': True, 'bias_dropout_fusion': True, 'unk_token_id': 0, 'masked_softmax_fusion': True, 'model_type': 'bloom', 'n_inner': None, 'offset_alibi': 100, 'seq_length': 2048, 'skip_bias_add': True, 'skip_bias_add_qkv': False, 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', '_load_in_8bit': False, '_load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'float16', 'bnb_4bit_quant_storage': 'uint8', 'load_in_4bit': True, 'load_in_8bit': False}, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 3e-05, 'weight_decay': 0.0001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.3, 'num_train_epochs': 5, 'max_steps': 60, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/Apr12_07-33-49_e5a48bec8248', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 20, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 20, 'save_total_limit': 1, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': 'Femboyuwu2000/bloomz-1b1-vn-chat', 'hub_strategy': 'checkpoint', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
+2024-04-12 07:34:22,621 INFO    MainThread:174 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-04-12 07:34:22,621 INFO    MainThread:174 [wandb_init.py:_pause_backend():438] pausing backend

wandb/run-20240412_073555-bw7oy9ix/files/config.yaml

@@ -0,0 +1,38 @@
+wandb_version: 1
+
+_wandb:
+  desc: null
+  value:
+    python_version: 3.10.13
+    cli_version: 0.16.5
+    framework: huggingface
+    huggingface_version: 4.39.3
+    is_jupyter_run: true
+    is_kaggle_kernel: true
+    start_time: 1712907355.0
+    t:
+      1:
+      - 1
+      - 2
+      - 3
+      - 5
+      - 11
+      - 12
+      - 49
+      - 51
+      - 53
+      - 55
+      - 71
+      - 84
+      - 98
+      - 105
+      3:
+      - 23
+      4: 3.10.13
+      5: 0.16.5
+      6: 4.39.3
+      8:
+      - 1
+      - 2
+      - 5
+      13: linux-x86_64

wandb/run-20240412_073555-bw7oy9ix/files/output.log

@@ -0,0 +1,3 @@
+/opt/conda/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
+  warnings.warn(
+/opt/conda/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.

wandb/run-20240412_073555-bw7oy9ix/files/requirements.txt

@@ -0,0 +1,864 @@
+Babel==2.14.0
+Boruta==0.3
+Brotli==1.0.9
+CVXcanon==0.1.2
+Cartopy==0.22.0
+Cython==3.0.8
+Deprecated==1.2.14
+Farama-Notifications==0.0.4
+Flask==3.0.2
+Geohash==1.0
+GitPython==3.1.41
+ImageHash==4.3.1
+Janome==0.5.0
+Jinja2==3.1.2
+LunarCalendar==0.0.9
+Mako==1.3.2
+Markdown==3.5.2
+MarkupSafe==2.1.3
+MarkupSafe==2.1.5
+Pillow==9.5.0
+PuLP==2.8.0
+PyArabic==0.6.15
+PyJWT==2.8.0
+PyMeeus==0.5.12
+PySocks==1.7.1
+PyUpSet==0.1.1.post7
+PyWavelets==1.5.0
+PyYAML==6.0.1
+Pygments==2.17.2
+Pympler==1.0.1
+QtPy==2.4.1
+Rtree==1.2.0
+SQLAlchemy==2.0.25
+SecretStorage==3.3.3
+Send2Trash==1.8.2
+Shapely==1.8.5.post1
+Shimmy==1.3.0
+SimpleITK==2.3.1
+TPOT==0.12.1
+Theano-PyMC==1.1.2
+Theano==1.0.5
+Wand==0.6.13
+Werkzeug==3.0.2
+absl-py==1.4.0
+accelerate==0.28.0
+access==1.1.9
+affine==2.4.0
+aiobotocore==2.12.2
+aiofiles==22.1.0
+aiohttp-cors==0.7.0
+aiohttp==3.9.1
+aioitertools==0.11.0
+aiorwlock==1.3.0
+aiosignal==1.3.1
+aiosqlite==0.19.0
+albumentations==1.4.0
+alembic==1.13.1
+altair==5.3.0
+annotated-types==0.6.0
+annoy==1.17.3
+anyio==4.2.0
+apache-beam==2.46.0
+aplus==0.11.0
+appdirs==1.4.4
+archspec==0.2.3
+argon2-cffi-bindings==21.2.0
+argon2-cffi==23.1.0
+array-record==0.5.0
+arrow==1.3.0
+arviz==0.17.1
+astroid==3.1.0
+astropy-iers-data==0.2024.4.1.0.33.14
+astropy==6.0.1
+asttokens==2.4.1
+astunparse==1.6.3
+async-lru==2.0.4
+async-timeout==4.0.3
+attrs==23.2.0
+audioread==3.0.1
+autopep8==2.0.4
+backoff==2.2.1
+bayesian-optimization==1.4.3
+beatrix_jupyterlab==2023.128.151533
+beautifulsoup4==4.12.2
+bitsandbytes==0.43.1
+blake3==0.2.1
+bleach==6.1.0
+blessed==1.20.0
+blinker==1.7.0
+blis==0.7.10
+blosc2==2.6.0
+bokeh==3.3.4
+boltons==23.1.1
+boto3==1.26.100
+botocore==1.34.51
+bq_helper==0.4.1
+bqplot==0.12.43
+branca==0.7.1
+brewer2mpl==1.4.1
+brotlipy==0.7.0
+cached-property==1.5.2
+cachetools==4.2.4
+cachetools==5.3.2
+catalogue==2.0.10
+catalyst==22.4
+catboost==1.2.3
+category-encoders==2.6.3
+certifi==2024.2.2
+cesium==0.12.1
+cffi==1.16.0
+charset-normalizer==3.3.2
+chex==0.1.86
+cleverhans==4.0.0
+click-plugins==1.1.1
+click==8.1.7
+cligj==0.7.2
+cloud-tpu-client==0.10
+cloud-tpu-profiler==2.4.0
+cloudpathlib==0.16.0
+cloudpickle==2.2.1
+cloudpickle==3.0.0
+cmdstanpy==1.2.2
+colorama==0.4.6
+colorcet==3.1.0
+colorful==0.5.6
+colorlog==6.8.2
+colorlover==0.3.0
+comm==0.2.1
+conda-libmamba-solver==23.7.0
+conda-package-handling==2.2.0
+conda==23.7.4
+conda_package_streaming==0.9.0
+confection==0.1.4
+contextily==1.6.0
+contourpy==1.2.0
+convertdate==2.4.0
+crcmod==1.7
+cryptography==41.0.7
+cuda-python==12.4.0
+cudf==23.8.0
+cufflinks==0.17.3
+cuml==23.8.0
+cupy==13.0.0
+cycler==0.12.1
+cymem==2.0.8
+cytoolz==0.12.3
+daal4py==2024.2.0
+daal==2024.2.0
+dacite==1.8.1
+dask-cuda==23.8.0
+dask-cudf==23.8.0
+dask-expr==1.0.9
+dask==2024.4.0
+dataclasses-json==0.6.4
+dataproc_jupyter_plugin==0.1.66
+datasets==2.16.0
+datashader==0.16.0
+datatile==1.0.3
+db-dtypes==1.2.0
+deap==1.4.1
+debugpy==1.8.0
+decorator==5.1.1
+deepdiff==6.7.1
+defusedxml==0.7.1
+deprecation==2.1.0
+descartes==1.1.0
+dill==0.3.7
+dipy==1.9.0
+distlib==0.3.8
+distributed==2023.7.1
+distro==1.9.0
+dm-tree==0.1.8
+docker-pycreds==0.4.0
+docker==7.0.0
+docopt==0.6.2
+docstring-parser==0.15
+docstring-to-markdown==0.15
+docutils==0.20.1
+earthengine-api==0.1.395
+easydict==1.13
+easyocr==1.7.1
+ecos==2.0.13
+eli5==0.13.0
+emoji==2.11.0
+en-core-web-lg==3.7.1
+en-core-web-sm==3.7.1
+entrypoints==0.4
+ephem==4.1.5
+esda==2.5.1
+essentia==2.1b6.dev1110
+et-xmlfile==1.1.0
+etils==1.6.0
+exceptiongroup==1.2.0
+executing==2.0.1
+explainable-ai-sdk==1.3.3
+fastai==2.7.14
+fastapi==0.108.0
+fastavro==1.9.3
+fastcore==1.5.29
+fastdownload==0.0.7
+fasteners==0.19
+fastjsonschema==2.19.1
+fastprogress==1.0.3
+fastrlock==0.8.2
+fasttext==0.9.2
+feather-format==0.4.1
+featuretools==1.30.0
+filelock==3.13.1
+fiona==1.9.6
+fitter==1.7.0
+flake8==7.0.0
+flashtext==2.7
+flatbuffers==23.5.26
+flax==0.8.2
+folium==0.16.0
+fonttools==4.47.0
+fonttools==4.50.0
+fqdn==1.5.1
+frozendict==2.4.1
+frozenlist==1.4.1
+fsspec==2023.10.0
+fsspec==2024.3.1
+funcy==2.0
+fury==0.10.0
+future==1.0.0
+fuzzywuzzy==0.18.0
+gast==0.5.4
+gatspy==0.3
+gcsfs==2024.2.0
+gensim==4.3.2
+geographiclib==2.0
+geojson==3.1.0
+geopandas==0.14.3
+geoplot==0.5.1
+geopy==2.4.1
+geoviews==1.11.1
+ggplot==0.11.5
+giddy==2.3.5
+gitdb==4.0.11
+google-ai-generativelanguage==0.4.0
+google-api-core==2.11.1
+google-api-core==2.18.0
+google-api-python-client==2.125.0
+google-apitools==0.5.31
+google-auth-httplib2==0.2.0
+google-auth-oauthlib==1.2.0
+google-auth==2.26.1
+google-cloud-aiplatform==0.6.0a1
+google-cloud-artifact-registry==1.10.0
+google-cloud-automl==1.0.1
+google-cloud-bigquery==2.34.4
+google-cloud-bigtable==1.7.3
+google-cloud-core==2.4.1
+google-cloud-datastore==2.19.0
+google-cloud-dlp==3.14.0
+google-cloud-jupyter-config==0.0.5
+google-cloud-language==2.13.3
+google-cloud-monitoring==2.18.0
+google-cloud-pubsub==2.19.0
+google-cloud-pubsublite==1.9.0
+google-cloud-recommendations-ai==0.7.1
+google-cloud-resource-manager==1.11.0
+google-cloud-spanner==3.40.1
+google-cloud-storage==1.44.0
+google-cloud-translate==3.12.1
+google-cloud-videointelligence==2.13.3
+google-cloud-vision==2.8.0
+google-crc32c==1.5.0
+google-generativeai==0.4.1
+google-pasta==0.2.0
+google-resumable-media==2.7.0
+googleapis-common-protos==1.62.0
+gplearn==0.4.2
+gpustat==1.0.0
+gpxpy==1.6.2
+graphviz==0.20.3
+greenlet==3.0.3
+grpc-google-iam-v1==0.12.7
+grpcio-status==1.48.1
+grpcio-status==1.48.2
+grpcio==1.51.1
+grpcio==1.60.0
+gviz-api==1.10.0
+gym-notices==0.0.8
+gym==0.26.2
+gymnasium==0.29.0
+h11==0.14.0
+h2o==3.46.0.1
+h5netcdf==1.3.0
+h5py==3.10.0
+haversine==2.8.1
+hdfs==2.7.3
+hep-ml==0.7.2
+hijri-converter==2.3.1
+hmmlearn==0.3.2
+holidays==0.24
+holoviews==1.18.3
+hpsklearn==0.1.0
+html5lib==1.1
+htmlmin==0.1.12
+httpcore==1.0.5
+httplib2==0.21.0
+httptools==0.6.1
+httpx==0.27.0
+huggingface-hub==0.22.2
+hunspell==0.5.5
+hydra-slayer==0.5.0
+hyperopt==0.2.7
+hypertools==0.8.0
+idna==3.6
+igraph==0.11.4
+imagecodecs==2024.1.1
+imageio==2.33.1
+imbalanced-learn==0.12.2
+imgaug==0.4.0
+importlib-metadata==6.11.0
+importlib-metadata==7.0.1
+importlib-resources==6.1.1
+inequality==1.0.1
+iniconfig==2.0.0
+ipydatawidgets==4.3.5
+ipykernel==6.28.0
+ipyleaflet==0.18.2
+ipympl==0.7.0
+ipython-genutils==0.2.0
+ipython-genutils==0.2.0
+ipython-sql==0.5.0
+ipython==8.20.0
+ipyvolume==0.6.3
+ipyvue==1.10.2
+ipyvuetify==1.9.3
+ipywebrtc==0.6.0
+ipywidgets==7.7.1
+isoduration==20.11.0
+isort==5.13.2
+isoweek==1.3.3
+itsdangerous==2.1.2
+jaraco.classes==3.3.0
+jax-jumpy==1.0.0
+jax==0.4.23
+jaxlib==0.4.23.dev20240116
+jedi==0.19.1
+jeepney==0.8.0
+jieba==0.42.1
+jmespath==1.0.1
+joblib==1.3.2
+json5==0.9.14
+jsonpatch==1.33
+jsonpointer==2.4
+jsonschema-specifications==2023.12.1
+jsonschema==4.20.0
+jupyter-console==6.6.3
+jupyter-events==0.9.0
+jupyter-http-over-ws==0.0.8
+jupyter-lsp==1.5.1
+jupyter-server-mathjax==0.2.6
+jupyter-ydoc==0.2.5
+jupyter_client==7.4.9
+jupyter_client==8.6.0
+jupyter_core==5.7.1
+jupyter_server==2.13.0
+jupyter_server_fileid==0.9.1
+jupyter_server_proxy==4.1.0
+jupyter_server_terminals==0.5.1
+jupyter_server_ydoc==0.8.0
+jupyterlab-lsp==5.1.0
+jupyterlab-widgets==3.0.9
+jupyterlab==4.1.5
+jupyterlab_git==0.44.0
+jupyterlab_pygments==0.3.0
+jupyterlab_server==2.25.2
+jupytext==1.16.0
+kaggle-environments==1.14.3
+kaggle==1.6.8
+kagglehub==0.2.2
+keras-cv==0.8.2
+keras-nlp==0.8.2
+keras-tuner==1.4.6
+keras==3.1.1
+kernels-mixer==0.0.7
+keyring==24.3.0
+keyrings.google-artifactregistry-auth==1.1.2
+kfp-pipeline-spec==0.2.2
+kfp-server-api==2.0.5
+kfp==2.5.0
+kiwisolver==1.4.5
+kmapper==2.0.1
+kmodes==0.12.2
+korean-lunar-calendar==0.3.1
+kornia==0.7.2
+kornia_rs==0.1.3
+kt-legacy==1.0.5
+kubernetes==26.1.0
+langcodes==3.3.0
+langid==1.1.6
+lazy_loader==0.3
+learntools==0.3.4
+leven==1.0.4
+libclang==16.0.6
+libmambapy==1.5.0
+libpysal==4.9.2
+librosa==0.10.1
+lightgbm==4.2.0
+lightning-utilities==0.11.2
+lime==0.2.0.1
+line-profiler==4.1.2
+linkify-it-py==2.0.3
+llvmlite==0.41.1
+llvmlite==0.42.0
+lml==0.1.0
+locket==1.0.0
+loguru==0.7.2
+lxml==5.2.1
+lz4==4.3.3
+mamba==1.5.0
+mapclassify==2.6.1
+markdown-it-py==3.0.0
+marshmallow==3.21.1
+matplotlib-inline==0.1.6
+matplotlib-venn==0.11.10
+matplotlib==3.7.5
+matplotlib==3.8.3
+mccabe==0.7.0
+mdit-py-plugins==0.4.0
+mdurl==0.1.2
+memory-profiler==0.61.0
+menuinst==2.0.1
+mercantile==1.2.1
+mgwr==2.2.1
+missingno==0.5.2
+mistune==0.8.4
+mizani==0.11.1
+ml-dtypes==0.2.0
+mlcrate==0.2.0
+mlens==0.2.3
+mlxtend==0.23.1
+mne==1.6.1
+mnist==0.2.2
+momepy==0.7.0
+more-itertools==10.2.0
+mpld3==0.5.10
+mpmath==1.3.0
+msgpack==1.0.7
+multidict==6.0.4
+multimethod==1.10
+multipledispatch==1.0.0
+multiprocess==0.70.15
+munkres==1.1.4
+murmurhash==1.0.10
+mypy-extensions==1.0.0
+namex==0.0.7
+nb-conda-kernels==2.3.1
+nb_conda==2.2.1
+nbclassic==1.0.0
+nbclient==0.5.13
+nbconvert==6.4.5
+nbdime==3.2.0
+nbformat==5.9.2
+ndindex==1.8
+nest-asyncio==1.5.8
+networkx==3.2.1
+nibabel==5.2.1
+nilearn==0.10.3
+ninja==1.11.1.1
+nltk==3.2.4
+nose==1.3.7
+notebook==6.5.4
+notebook==6.5.6
+notebook_executor==0.2
+notebook_shim==0.2.3
+numba==0.58.1
+numba==0.59.1
+numexpr==2.10.0
+numpy==1.26.4
+nvidia-ml-py==11.495.46
+nvtx==0.2.10
+oauth2client==4.1.3
+oauthlib==3.2.2
+objsize==0.6.1
+odfpy==1.4.1
+olefile==0.47
+onnx==1.16.0
+opencensus-context==0.1.3
+opencensus==0.11.4
+opencv-contrib-python==4.9.0.80
+opencv-python-headless==4.9.0.80
+opencv-python==4.9.0.80
+openpyxl==3.1.2
+openslide-python==1.3.1
+opentelemetry-api==1.22.0
+opentelemetry-exporter-otlp-proto-common==1.22.0
+opentelemetry-exporter-otlp-proto-grpc==1.22.0
+opentelemetry-exporter-otlp-proto-http==1.22.0
+opentelemetry-exporter-otlp==1.22.0
+opentelemetry-proto==1.22.0
+opentelemetry-sdk==1.22.0
+opentelemetry-semantic-conventions==0.43b0
+opt-einsum==3.3.0
+optax==0.2.2
+optree==0.11.0
+optuna==3.6.1
+orbax-checkpoint==0.5.7
+ordered-set==4.1.0
+orjson==3.9.10
+ortools==9.4.1874
+osmnx==1.9.2
+overrides==7.4.0
+packaging==21.3
+pandas-datareader==0.10.0
+pandas-profiling==3.6.6
+pandas-summary==0.2.0
+pandas==2.1.4
+pandas==2.2.1
+pandasql==0.7.3
+pandocfilters==1.5.0
+panel==1.3.8
+papermill==2.5.0
+param==2.1.0
+parso==0.8.3
+partd==1.4.1
+path.py==12.5.0
+path==16.10.0
+pathos==0.3.2
+pathy==0.10.3
+patsy==0.5.6
+pdf2image==1.17.0
+peft==0.10.0
+pettingzoo==1.24.0
+pexpect==4.8.0
+pexpect==4.9.0
+phik==0.12.4
+pickleshare==0.7.5
+pillow==10.3.0
+pip==23.3.2
+pkgutil_resolve_name==1.3.10
+platformdirs==4.2.0
+plotly-express==0.4.1
+plotly==5.18.0
+plotnine==0.13.4
+pluggy==1.4.0
+pointpats==2.4.0
+polars==0.20.18
+polyglot==16.7.4
+pooch==1.8.1
+pox==0.3.4
+ppca==0.0.4
+ppft==1.7.6.8
+preprocessing==0.1.13
+preshed==3.0.9
+prettytable==3.9.0
+progressbar2==4.4.2
+prometheus-client==0.19.0
+promise==2.3
+prompt-toolkit==3.0.42
+prompt-toolkit==3.0.43
+prophet==1.1.1
+proto-plus==1.23.0
+protobuf==3.20.3
+protobuf==4.21.12
+psutil==5.9.3
+psutil==5.9.7
+ptyprocess==0.7.0
+pudb==2024.1
+pure-eval==0.2.2
+py-cpuinfo==9.0.0
+py-spy==0.3.14
+py4j==0.10.9.7
+pyLDAvis==3.4.1
+pyOpenSSL==23.3.0
+pyaml==23.12.0
+pyarrow-hotfix==0.6
+pyarrow==15.0.2
+pyasn1-modules==0.3.0
+pyasn1==0.5.1
+pybind11==2.12.0
+pyclipper==1.3.0.post5
+pycodestyle==2.11.1
+pycosat==0.6.6
+pycparser==2.21
+pycryptodome==3.20.0
+pyct==0.5.0
+pycuda==2024.1
+pydantic==2.5.3
+pydantic==2.6.4
+pydantic_core==2.14.6
+pydantic_core==2.16.3
+pydegensac==0.1.2
+pydicom==2.4.4
+pydocstyle==6.3.0
+pydot==1.4.2
+pydub==0.25.1
+pyemd==1.0.0
+pyerfa==2.0.1.1
+pyexcel-io==0.6.6
+pyexcel-ods==0.6.0
+pyflakes==3.2.0
+pygltflib==1.16.2
+pykalman==0.9.7
+pylibraft==23.8.0
+pylint==3.1.0
+pymc3==3.11.4
+pymongo==3.13.0
+pynndescent==0.5.12
+pynvml==11.4.1
+pynvrtc==9.2
+pyparsing==3.1.1
+pyparsing==3.1.2
+pypdf==4.1.0
+pyproj==3.6.1
+pysal==24.1
+pyshp==2.3.1
+pytesseract==0.3.10
+pytest==8.1.1
+python-bidi==0.4.2
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.0
+python-json-logger==2.0.7
+python-louvain==0.16
+python-lsp-jsonrpc==1.1.2
+python-lsp-server==1.11.0
+python-slugify==8.0.4
+python-utils==3.8.2
+pythreejs==2.4.2
+pytoolconfig==1.3.1
+pytools==2024.1.1
+pytorch-ignite==0.5.0.post2
+pytorch-lightning==2.2.1
+pytz==2023.3.post1
+pytz==2024.1
+pyu2f==0.1.5
+pyviz_comms==3.0.2
+pyzmq==24.0.1
+pyzmq==25.1.2
+qgrid==1.3.1
+qtconsole==5.5.1
+quantecon==0.7.2
+qudida==0.0.4
+raft-dask==23.8.0
+rasterio==1.3.9
+rasterstats==0.19.0
+ray-cpp==2.9.0
+ray==2.9.0
+referencing==0.32.1
+regex==2023.12.25
+requests-oauthlib==1.3.1
+requests-toolbelt==0.10.1
+requests==2.31.0
+retrying==1.3.3
+retrying==1.3.4
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
+rgf-python==3.12.0
+rich-click==1.7.4
+rich==13.7.0
+rich==13.7.1
+rmm==23.8.0
+rope==1.13.0
+rpds-py==0.16.2
+rsa==4.9
+ruamel-yaml-conda==0.15.100
+ruamel.yaml.clib==0.2.7
+ruamel.yaml==0.17.40
+s2sphere==0.2.5
+s3fs==2024.2.0
+s3transfer==0.6.2
+safetensors==0.4.2
+scattertext==0.1.19
+scikit-image==0.22.0
+scikit-learn-intelex==2024.2.0
+scikit-learn==1.2.2
+scikit-multilearn==0.2.0
+scikit-optimize==0.10.1
+scikit-plot==0.3.7
+scikit-surprise==1.1.3
+scipy==1.11.4
+scipy==1.12.0
+seaborn==0.12.2
+segment_anything==1.0
+segregation==2.5
+semver==3.0.2
+sentencepiece==0.2.0
+sentry-sdk==1.44.1
+setproctitle==1.3.3
+setuptools-git==1.2
+setuptools-scm==8.0.4
+setuptools==69.0.3
+shap==0.44.1
+shapely==2.0.3
+shellingham==1.5.4
+shtab==1.7.1
+simpervisor==1.0.0
+simplejson==3.19.2
+six==1.16.0
+sklearn-pandas==2.2.0
+slicer==0.0.7
+smart-open==6.4.0
+smmap==5.0.1
+sniffio==1.3.0
+snowballstemmer==2.2.0
+snuggs==1.4.7
+sortedcontainers==2.4.0
+soundfile==0.12.1
+soupsieve==2.5
+soxr==0.3.7
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+spacy==3.7.2
+spaghetti==1.7.5.post1
+spectral==0.23.1
+spglm==1.1.0
+sphinx-rtd-theme==0.2.4
+spint==1.0.7
+splot==1.1.5.post1
+spopt==0.6.0
+spreg==1.4.2
+spvcm==0.3.0
+sqlparse==0.4.4
+squarify==0.4.3
+srsly==2.4.8
+stable-baselines3==2.1.0
+stack-data==0.6.2
+stack-data==0.6.3
+stanio==0.5.0
+starlette==0.32.0.post1
+statsmodels==0.14.1
+stemming==1.0.1
+stop-words==2018.7.23
+stopit==1.1.2
+stumpy==1.12.0
+sympy==1.12
+tables==3.9.2
+tabulate==0.9.0
+tangled-up-in-unicode==0.2.0
+tbb==2021.12.0
+tblib==3.0.0
+tenacity==8.2.3
+tensorboard-data-server==0.7.2
+tensorboard-plugin-profile==2.15.0
+tensorboard==2.15.1
+tensorboardX==2.6.2.2
+tensorflow-cloud==0.1.16
+tensorflow-datasets==4.9.4
+tensorflow-decision-forests==1.8.1
+tensorflow-estimator==2.15.0
+tensorflow-hub==0.16.1
+tensorflow-io-gcs-filesystem==0.35.0
+tensorflow-io==0.35.0
+tensorflow-metadata==0.14.0
+tensorflow-probability==0.23.0
+tensorflow-serving-api==2.14.1
+tensorflow-text==2.15.0
+tensorflow-transform==0.14.0
+tensorflow==2.15.0
+tensorstore==0.1.56
+termcolor==2.4.0
+terminado==0.18.0
+testpath==0.6.0
+text-unidecode==1.3
+textblob==0.18.0.post0
+texttable==1.7.0
+tf_keras==2.15.1
+tfp-nightly==0.24.0.dev0
+thinc==8.2.2
+threadpoolctl==3.2.0
+tifffile==2023.12.9
+timm==0.9.16
+tinycss2==1.2.1
+tobler==0.11.2
+tokenizers==0.15.2
+toml==0.10.2
+tomli==2.0.1
+tomlkit==0.12.4
+toolz==0.12.1
+torch==2.1.2
+torchaudio==2.1.2
+torchdata==0.7.1
+torchinfo==1.8.0
+torchmetrics==1.3.2
+torchtext==0.16.2
+torchvision==0.16.2
+tornado==6.3.3
+tqdm==4.66.1
+traceml==1.0.8
+traitlets==5.9.0
+traittypes==0.2.1
+transformers==4.39.3
+treelite-runtime==3.2.0
+treelite==3.2.0
+trl==0.8.2
+truststore==0.8.0
+trx-python==0.2.9
+tsfresh==0.20.2
+typeguard==4.1.5
+typer==0.9.0
+typer==0.9.4
+types-python-dateutil==2.8.19.20240106
+typing-inspect==0.9.0
+typing-utils==0.1.0
+typing_extensions==4.9.0
+tyro==0.8.3
+tzdata==2023.4
+uc-micro-py==1.0.3
+ucx-py==0.33.0
+ujson==5.9.0
+umap-learn==0.5.5
+unicodedata2==15.1.0
+update-checker==0.18.0
+uri-template==1.3.0
+uritemplate==3.0.1
+urllib3==1.26.18
+urllib3==2.1.0
+urwid==2.6.10
+urwid_readline==0.14
+uvicorn==0.25.0
+uvloop==0.19.0
+vaex-astro==0.9.3
+vaex-core==4.17.1
+vaex-hdf5==0.14.1
+vaex-jupyter==0.8.2
+vaex-ml==0.18.3
+vaex-server==0.9.0
+vaex-viz==0.5.4
+vaex==4.17.0
+vec_noise==1.1.4
+vecstack==0.4.0
+virtualenv==20.21.0
+visions==0.7.5
+vowpalwabbit==9.9.0
+vtk==9.3.0
+wandb==0.16.5
+wasabi==1.1.2
+watchfiles==0.21.0
+wavio==0.0.8
+wcwidth==0.2.13
+weasel==0.3.4
+webcolors==1.13
+webencodings==0.5.1
+websocket-client==1.7.0
+websockets==12.0
+wfdb==4.1.2
+whatthepatch==1.0.5
+wheel==0.42.0
+widgetsnbextension==3.6.6
+witwidget==1.8.1
+woodwork==0.29.0
+wordcloud==1.9.3
+wordsegment==1.3.1
+wrapt==1.14.1
+xarray-einstats==0.7.0
+xarray==2024.3.0
+xgboost==2.0.3
+xvfbwrapper==0.2.9
+xxhash==3.4.1
+xyzservices==2023.10.1
+y-py==0.6.2
+yapf==0.40.2
+yarl==1.9.3
+yarl==1.9.4
+ydata-profiling==4.6.4
+yellowbrick==1.5
+ypy-websocket==0.8.4
+zict==3.0.0
+zipp==3.17.0
+zstandard==0.22.0

wandb/run-20240412_073555-bw7oy9ix/files/wandb-metadata.json

@@ -0,0 +1,66 @@
+{
+    "os": "Linux-5.15.133+-x86_64-with-glibc2.31",
+    "python": "3.10.13",
+    "heartbeatAt": "2024-04-12T07:35:56.437403",
+    "startedAt": "2024-04-12T07:35:55.741618",
+    "docker": null,
+    "cuda": null,
+    "args": [],
+    "state": "running",
+    "program": "kaggle.ipynb",
+    "codePathLocal": null,
+    "root": "/kaggle/working",
+    "host": "e5a48bec8248",
+    "username": "root",
+    "executable": "/opt/conda/bin/python3.10",
+    "cpu_count": 2,
+    "cpu_count_logical": 4,
+    "cpu_freq": {
+        "current": 2000.138,
+        "min": 0.0,
+        "max": 0.0
+    },
+    "cpu_freq_per_core": [
+        {
+            "current": 2000.138,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2000.138,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2000.138,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2000.138,
+            "min": 0.0,
+            "max": 0.0
+        }
+    ],
+    "disk": {
+        "/": {
+            "total": 8062.387607574463,
+            "used": 5565.782459259033
+        }
+    },
+    "gpu": "Tesla T4",
+    "gpu_count": 2,
+    "gpu_devices": [
+        {
+            "name": "Tesla T4",
+            "memory_total": 16106127360
+        },
+        {
+            "name": "Tesla T4",
+            "memory_total": 16106127360
+        }
+    ],
+    "memory": {
+        "total": 31.357559204101562
+    }
+}

wandb/run-20240412_073555-bw7oy9ix/files/wandb-summary.json

@@ -0,0 +1 @@
+{"train/loss": 4.6771, "train/grad_norm": 79.12922668457031, "train/learning_rate": 1e-06, "train/epoch": 0.0, "train/global_step": 20, "_timestamp": 1712907379.5892065, "_runtime": 23.840320348739624, "_step": 0}

wandb/run-20240412_073555-bw7oy9ix/logs/debug-internal.log

@@ -0,0 +1,77 @@
+2024-04-12 07:35:55,749 INFO    StreamThr :334 [internal.py:wandb_internal():86] W&B internal server running at pid: 334, started at: 2024-04-12 07:35:55.748821
+2024-04-12 07:35:55,751 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status
+2024-04-12 07:35:56,159 INFO    WriterThread:334 [datastore.py:open_for_write():87] open: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/run-bw7oy9ix.wandb
+2024-04-12 07:35:56,160 DEBUG   SenderThread:334 [sender.py:send():379] send: header
+2024-04-12 07:35:56,163 DEBUG   SenderThread:334 [sender.py:send():379] send: run
+2024-04-12 07:35:56,307 INFO    SenderThread:334 [dir_watcher.py:__init__():211] watching files in: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files
+2024-04-12 07:35:56,307 INFO    SenderThread:334 [sender.py:_start_run_threads():1124] run started: bw7oy9ix with start time 1712907355.748886
+2024-04-12 07:35:56,317 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: check_version
+2024-04-12 07:35:56,317 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: check_version
+2024-04-12 07:35:56,409 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: run_start
+2024-04-12 07:35:56,421 DEBUG   HandlerThread:334 [system_info.py:__init__():26] System info init
+2024-04-12 07:35:56,421 DEBUG   HandlerThread:334 [system_info.py:__init__():41] System info init done
+2024-04-12 07:35:56,422 INFO    HandlerThread:334 [system_monitor.py:start():194] Starting system monitor
+2024-04-12 07:35:56,422 INFO    SystemMonitor:334 [system_monitor.py:_start():158] Starting system asset monitoring threads
+2024-04-12 07:35:56,422 INFO    HandlerThread:334 [system_monitor.py:probe():214] Collecting system info
+2024-04-12 07:35:56,423 INFO    SystemMonitor:334 [interfaces.py:start():190] Started cpu monitoring
+2024-04-12 07:35:56,423 INFO    SystemMonitor:334 [interfaces.py:start():190] Started disk monitoring
+2024-04-12 07:35:56,424 INFO    SystemMonitor:334 [interfaces.py:start():190] Started gpu monitoring
+2024-04-12 07:35:56,425 INFO    SystemMonitor:334 [interfaces.py:start():190] Started memory monitoring
+2024-04-12 07:35:56,426 INFO    SystemMonitor:334 [interfaces.py:start():190] Started network monitoring
+2024-04-12 07:35:56,437 DEBUG   HandlerThread:334 [system_info.py:probe():150] Probing system
+2024-04-12 07:35:56,439 DEBUG   HandlerThread:334 [gitlib.py:_init_repo():56] git repository is invalid
+2024-04-12 07:35:56,439 DEBUG   HandlerThread:334 [system_info.py:probe():198] Probing system done
+2024-04-12 07:35:56,439 DEBUG   HandlerThread:334 [system_monitor.py:probe():223] {'os': 'Linux-5.15.133+-x86_64-with-glibc2.31', 'python': '3.10.13', 'heartbeatAt': '2024-04-12T07:35:56.437403', 'startedAt': '2024-04-12T07:35:55.741618', 'docker': None, 'cuda': None, 'args': (), 'state': 'running', 'program': 'kaggle.ipynb', 'codePathLocal': None, 'root': '/kaggle/working', 'host': 'e5a48bec8248', 'username': 'root', 'executable': '/opt/conda/bin/python3.10', 'cpu_count': 2, 'cpu_count_logical': 4, 'cpu_freq': {'current': 2000.138, 'min': 0.0, 'max': 0.0}, 'cpu_freq_per_core': [{'current': 2000.138, 'min': 0.0, 'max': 0.0}, {'current': 2000.138, 'min': 0.0, 'max': 0.0}, {'current': 2000.138, 'min': 0.0, 'max': 0.0}, {'current': 2000.138, 'min': 0.0, 'max': 0.0}], 'disk': {'/': {'total': 8062.387607574463, 'used': 5565.782459259033}}, 'gpu': 'Tesla T4', 'gpu_count': 2, 'gpu_devices': [{'name': 'Tesla T4', 'memory_total': 16106127360}, {'name': 'Tesla T4', 'memory_total': 16106127360}], 'memory': {'total': 31.357559204101562}}
+2024-04-12 07:35:56,440 INFO    HandlerThread:334 [system_monitor.py:probe():224] Finished collecting system info
+2024-04-12 07:35:56,440 INFO    HandlerThread:334 [system_monitor.py:probe():227] Publishing system info
+2024-04-12 07:35:56,440 DEBUG   HandlerThread:334 [system_info.py:_save_conda():207] Saving list of conda packages installed into the current environment
+2024-04-12 07:35:57,309 INFO    Thread-12 :334 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/conda-environment.yaml
+2024-04-12 07:36:11,455 ERROR   HandlerThread:334 [system_info.py:_save_conda():221] Error saving conda packages: Command '['conda', 'env', 'export']' timed out after 15 seconds
+Traceback (most recent call last):
+  File "/opt/conda/lib/python3.10/site-packages/wandb/sdk/internal/system/system_info.py", line 214, in _save_conda
+    subprocess.call(
+  File "/opt/conda/lib/python3.10/subprocess.py", line 347, in call
+    return p.wait(timeout=timeout)
+  File "/opt/conda/lib/python3.10/subprocess.py", line 1209, in wait
+    return self._wait(timeout=timeout)
+  File "/opt/conda/lib/python3.10/subprocess.py", line 1951, in _wait
+    raise TimeoutExpired(self.args, timeout)
+subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after 15 seconds
+2024-04-12 07:36:11,456 DEBUG   HandlerThread:334 [system_info.py:_save_conda():222] Saving conda packages done
+2024-04-12 07:36:11,456 INFO    HandlerThread:334 [system_monitor.py:probe():229] Finished publishing system info
+2024-04-12 07:36:11,462 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:36:11,462 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: keepalive
+2024-04-12 07:36:11,462 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:36:11,462 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: keepalive
+2024-04-12 07:36:11,462 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:36:11,462 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: keepalive
+2024-04-12 07:36:11,463 DEBUG   SenderThread:334 [sender.py:send():379] send: files
+2024-04-12 07:36:11,463 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-metadata.json with policy now
+2024-04-12 07:36:11,664 INFO    wandb-upload_0:334 [upload_job.py:push():131] Uploaded file /tmp/tmpjph8qv3dwandb/f1up76ir-wandb-metadata.json
+2024-04-12 07:36:12,312 INFO    Thread-12 :334 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/wandb-metadata.json
+2024-04-12 07:36:12,509 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: python_packages
+2024-04-12 07:36:12,509 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: python_packages
+2024-04-12 07:36:12,512 DEBUG   SenderThread:334 [sender.py:send():379] send: telemetry
+2024-04-12 07:36:12,523 DEBUG   SenderThread:334 [sender.py:send():379] send: config
+2024-04-12 07:36:12,525 DEBUG   SenderThread:334 [sender.py:send():379] send: metric
+2024-04-12 07:36:12,534 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:36:12,535 DEBUG   SenderThread:334 [sender.py:send():379] send: telemetry
+2024-04-12 07:36:12,535 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:36:12,535 DEBUG   SenderThread:334 [sender.py:send():379] send: metric
+2024-04-12 07:36:12,536 WARNING SenderThread:334 [sender.py:send_metric():1341] Seen metric with glob (shouldn't happen)
+2024-04-12 07:36:12,536 DEBUG   SenderThread:334 [sender.py:send():379] send: telemetry
+2024-04-12 07:36:12,536 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:36:13,313 INFO    Thread-12 :334 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/requirements.txt
+2024-04-12 07:36:13,313 INFO    Thread-12 :334 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/output.log
+2024-04-12 07:36:15,314 INFO    Thread-12 :334 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/output.log
+2024-04-12 07:36:17,014 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:36:19,589 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:36:19,592 DEBUG   SenderThread:334 [sender.py:send():379] send: metric
+2024-04-12 07:36:19,593 DEBUG   SenderThread:334 [sender.py:send():379] send: metric
+2024-04-12 07:36:19,593 DEBUG   SenderThread:334 [sender.py:send():379] send: metric
+2024-04-12 07:36:19,593 DEBUG   SenderThread:334 [sender.py:send():379] send: metric
+2024-04-12 07:36:19,593 DEBUG   SenderThread:334 [sender.py:send():379] send: history
+2024-04-12 07:36:19,593 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:36:19,595 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:36:20,316 INFO    Thread-12 :334 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/wandb-summary.json
+2024-04-12 07:36:21,316 INFO    Thread-12 :334 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/output.log

wandb/run-20240412_073555-bw7oy9ix/logs/debug.log

@@ -0,0 +1,31 @@
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_setup.py:_flush():76] Current SDK version is 0.16.5
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_setup.py:_flush():76] Configure stats pid to 289
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_setup.py:_flush():76] Loading settings from /kaggle/working/wandb/settings
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': '<python with no main file>'}
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_setup.py:_flush():76] Applying login settings: {}
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_init.py:_log_setup():527] Logging user logs to /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/logs/debug.log
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_init.py:_log_setup():528] Logging internal logs to /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/logs/debug-internal.log
+2024-04-12 07:35:55,744 INFO    MainThread:289 [wandb_init.py:_jupyter_setup():473] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x7c2cd1fccd60>
+2024-04-12 07:35:55,745 INFO    MainThread:289 [wandb_init.py:init():567] calling init triggers
+2024-04-12 07:35:55,745 INFO    MainThread:289 [wandb_init.py:init():574] wandb.init called with sweep_config: {}
+config: {}
+2024-04-12 07:35:55,745 INFO    MainThread:289 [wandb_init.py:init():617] starting backend
+2024-04-12 07:35:55,745 INFO    MainThread:289 [wandb_init.py:init():621] setting up manager
+2024-04-12 07:35:55,747 INFO    MainThread:289 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-04-12 07:35:55,748 INFO    MainThread:289 [wandb_init.py:init():629] backend started and connected
+2024-04-12 07:35:55,761 INFO    MainThread:289 [wandb_run.py:_label_probe_notebook():1299] probe notebook
+2024-04-12 07:35:56,159 INFO    MainThread:289 [wandb_init.py:init():721] updated telemetry
+2024-04-12 07:35:56,162 INFO    MainThread:289 [wandb_init.py:init():754] communicating run to backend with 90.0 second timeout
+2024-04-12 07:35:56,316 INFO    MainThread:289 [wandb_run.py:_on_init():2344] communicating current version
+2024-04-12 07:35:56,402 INFO    MainThread:289 [wandb_run.py:_on_init():2353] got version response upgrade_message: "wandb version 0.16.6 is available!  To upgrade, please run:\n $ pip install wandb --upgrade"
+
+2024-04-12 07:35:56,403 INFO    MainThread:289 [wandb_init.py:init():805] starting run threads in backend
+2024-04-12 07:36:12,510 INFO    MainThread:289 [wandb_run.py:_console_start():2323] atexit reg
+2024-04-12 07:36:12,510 INFO    MainThread:289 [wandb_run.py:_redirect():2178] redirect: wrap_raw
+2024-04-12 07:36:12,511 INFO    MainThread:289 [wandb_run.py:_redirect():2243] Wrapping output streams.
+2024-04-12 07:36:12,511 INFO    MainThread:289 [wandb_run.py:_redirect():2268] Redirects installed.
+2024-04-12 07:36:12,512 INFO    MainThread:289 [wandb_init.py:init():848] run started, returning control to user process
+2024-04-12 07:36:12,518 INFO    MainThread:289 [wandb_run.py:_config_callback():1347] config_cb None None {'vocab_size': 250880, 'hidden_size': 1536, 'n_layer': 24, 'n_head': 16, 'layer_norm_epsilon': 1e-05, 'initializer_range': 0.02, 'use_cache': False, 'pretraining_tp': 1, 'apply_residual_connection_post_layernorm': False, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'bos_token_id': 1, 'eos_token_id': 2, 'slow_but_exact': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['BloomForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'pad_token_id': 3, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'bigscience/bloomz-1b1', 'transformers_version': '4.39.3', 'attention_softmax_in_fp32': True, 'bias_dropout_fusion': True, 'unk_token_id': 0, 'masked_softmax_fusion': True, 'model_type': 'bloom', 'n_inner': None, 'offset_alibi': 100, 'seq_length': 2048, 'skip_bias_add': True, 'skip_bias_add_qkv': False, 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', '_load_in_8bit': False, '_load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'float16', 'bnb_4bit_quant_storage': 'uint8', 'load_in_4bit': True, 'load_in_8bit': False}, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 3e-05, 'weight_decay': 0.0001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.3, 'num_train_epochs': 5, 'max_steps': 20000, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/Apr12_07-35-52_e5a48bec8248', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 20, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 20, 'save_total_limit': 1, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_8bit', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': 'Femboyuwu2000/bloomz-1b1-vn-chat', 'hub_strategy': 'checkpoint', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}