Training in progress, step 6280

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21a654a2c630a4be80136d7033c71365f7cc824c88608bee2bcde6cc3fbbc733
+oid sha256:4952d07d35404125ac82a69ff1d2b691b555ce36f8f5e2491332621aa761003d
 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:f823d496e67aafb4d85a3345452041eaf4649f53fd7ba4311c77f77c21af4710
-size 71090
+oid sha256:eae5cf9b7f19e4d620f566f3c220b67be60268ea84f3ad533257770b5c7395fc
+size 71512

wandb/debug-internal.log

@@ -5169,3 +5169,35 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 09:48:04,132 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
 2024-04-12 09:48:04,133 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 09:48:05,079 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 09:48:06,876 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:07,080 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 09:48:11,877 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:15,291 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 09:48:17,134 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 09:48:17,292 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:17,406 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 09:48:17,407 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 09:48:22,518 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:24,214 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 09:48:24,215 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 09:48:24,215 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 09:48:24,216 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 09:48:25,087 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 09:48:27,088 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 09:48:27,686 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:32,134 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 09:48:32,407 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 09:48:32,407 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 09:48:33,462 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:38,463 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:43,464 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:45,293 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 09:48:47,134 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 09:48:47,407 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 09:48:47,407 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 09:48:49,451 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:50,374 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 09:48:50,376 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 09:48:50,376 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 09:48:50,376 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 09:48:51,098 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

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

@@ -620,4 +620,10 @@
   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.
+  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": 3.4353, "train/grad_norm": 28.155752182006836, "train/learning_rate": 2.4166711454025754e-05, "train/epoch": 0.5, "train/global_step": 6240, "_timestamp": 1712915284.1308498, "_runtime": 7639.623131752014, "_step": 311}
+{"train/loss": 3.4637, "train/grad_norm": 44.352596282958984, "train/learning_rate": 2.408961130718405e-05, "train/epoch": 0.5, "train/global_step": 6280, "_timestamp": 1712915330.374364, "_runtime": 7685.866645812988, "_step": 313}

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

@@ -5169,3 +5169,35 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 09:48:04,132 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
 2024-04-12 09:48:04,133 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 09:48:05,079 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 09:48:06,876 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:07,080 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 09:48:11,877 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:15,291 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 09:48:17,134 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 09:48:17,292 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:17,406 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 09:48:17,407 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 09:48:22,518 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:24,214 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 09:48:24,215 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 09:48:24,215 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 09:48:24,216 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 09:48:25,087 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 09:48:27,088 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 09:48:27,686 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:32,134 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 09:48:32,407 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 09:48:32,407 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 09:48:33,462 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:38,463 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:43,464 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:45,293 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 09:48:47,134 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 09:48:47,407 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 09:48:47,407 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 09:48:49,451 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:50,374 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 09:48:50,376 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 09:48:50,376 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 09:48:50,376 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 09:48:51,098 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