Training in progress, step 9220

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1191e15f1f075f04e1758ba87cec35bdffa2da050944d1bbd85df57885868d03
+oid sha256:32794401cb308b267d0bd79030d66e61135ddaadf4fd04203a94ef1dc084f749
 size 13982248

runs/Apr12_07-40-41_e5a48bec8248/events.out.tfevents.1712907642.e5a48bec8248.443.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a28ffd7e6912f9e06adba14afb9efc2069ea27a1057bb54eade39cba05e11ed
-size 102318
+oid sha256:19ef8459a8e17cd5878247cc04cdab06274675766f0ad23666fd73e4455e10f5
+size 102529

wandb/debug-internal.log

@@ -7593,3 +7593,18 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 10:48:32,741 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
 2024-04-12 10:48:32,994 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
 2024-04-12 10:48:32,994 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:48:34,617 INFO    Thread-12 :485 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_074044-widovcn3/files/output.log
+2024-04-12 10:48:35,125 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:48:40,126 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:48:45,127 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:48:45,412 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 10:48:47,689 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:48:47,992 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:48:47,993 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:48:51,098 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:48:53,532 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 10:48:53,533 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 10:48:53,533 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 10:48:53,534 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 10:48:53,625 INFO    Thread-12 :485 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_074044-widovcn3/files/wandb-summary.json
+2024-04-12 10:48:56,334 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report

wandb/run-20240412_074044-widovcn3/files/output.log

@@ -916,4 +916,8 @@
   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(
+/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(
 /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_074044-widovcn3/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 3.4515, "train/grad_norm": 29.5195369720459, "train/learning_rate": 1.7657864873688343e-05, "train/epoch": 0.74, "train/global_step": 9200, "_timestamp": 1712918912.2451706, "_runtime": 11267.737452507019, "_step": 459}
+{"train/loss": 3.4684, "train/grad_norm": 41.386260986328125, "train/learning_rate": 1.761003841513674e-05, "train/epoch": 0.74, "train/global_step": 9220, "_timestamp": 1712918933.531621, "_runtime": 11289.023902893066, "_step": 460}

wandb/run-20240412_074044-widovcn3/logs/debug-internal.log

@@ -7593,3 +7593,18 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 10:48:32,741 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
 2024-04-12 10:48:32,994 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
 2024-04-12 10:48:32,994 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:48:34,617 INFO    Thread-12 :485 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_074044-widovcn3/files/output.log
+2024-04-12 10:48:35,125 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:48:40,126 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:48:45,127 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:48:45,412 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 10:48:47,689 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:48:47,992 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:48:47,993 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:48:51,098 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:48:53,532 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 10:48:53,533 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 10:48:53,533 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 10:48:53,534 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 10:48:53,625 INFO    Thread-12 :485 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_074044-widovcn3/files/wandb-summary.json
+2024-04-12 10:48:56,334 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report