Training in progress, step 6240

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1473b98008a7f35dc7965737a1e130bdcd8e0826db630ae5819b00c7608d4429
+oid sha256:21a654a2c630a4be80136d7033c71365f7cc824c88608bee2bcde6cc3fbbc733
 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 sha256:8a8cab6f0f94bf915e8bb10b0a4c647eb657c1bc0450cdf3e6c472189c398eb0
-size 70668
+oid sha256:f823d496e67aafb4d85a3345452041eaf4649f53fd7ba4311c77f77c21af4710
+size 71090

wandb/debug-internal.log

@@ -5140,3 +5140,32 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 09:47:19,061 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 09:47:20,302 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
 2024-04-12 09:47:21,062 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 09:47:25,304 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:47:30,305 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:47:32,134 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 09:47:32,406 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 09:47:32,407 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 09:47:35,449 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:47:40,450 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:47:41,802 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 09:47:41,803 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 09:47:41,803 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 09:47:41,804 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 09:47:42,071 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 09:47:45,072 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 09:47:45,290 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 09:47:46,291 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:47:47,134 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 09:47:47,406 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 09:47:47,407 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 09:47:51,457 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:47:56,459 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:01,460 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:02,134 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 09:48:02,406 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 09:48:02,407 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 09:48:04,131 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 09:48:04,132 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+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

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

@@ -618,4 +618,6 @@
   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": 3.4539, "train/grad_norm": 31.746124267578125, "train/learning_rate": 2.424342698401391e-05, "train/epoch": 0.5, "train/global_step": 6200, "_timestamp": 1712915238.5600345, "_runtime": 7594.052316427231, "_step": 309}
+{"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}

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

@@ -5140,3 +5140,32 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 09:47:19,061 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 09:47:20,302 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
 2024-04-12 09:47:21,062 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 09:47:25,304 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:47:30,305 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:47:32,134 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 09:47:32,406 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 09:47:32,407 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 09:47:35,449 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:47:40,450 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:47:41,802 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 09:47:41,803 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 09:47:41,803 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 09:47:41,804 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 09:47:42,071 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 09:47:45,072 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 09:47:45,290 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 09:47:46,291 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:47:47,134 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 09:47:47,406 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 09:47:47,407 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 09:47:51,457 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:47:56,459 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:01,460 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:48:02,134 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 09:48:02,406 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 09:48:02,407 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 09:48:04,131 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 09:48:04,132 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+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