Training in progress, step 8900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f73dcc6e7fa0fc227105e43f2e1eea3d45deccd0cda946455200eb5cc8da7c27
+oid sha256:630a910b2d5b8c9504add11b070a2b95445874621f6de2ea3077628d0553ffe3
 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 sha256:691a58e9e4f859c10b82cfc28e08720118e9a08be217b098918dcc3d8072d39e
-size 98731
+oid sha256:a6beb4b031c40676a52391d3dfcfbf6a83b8f9b9994d747ce903358a62a5050d
+size 99153

wandb/debug-internal.log

@@ -7314,3 +7314,35 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 10:41:35,070 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
 2024-04-12 10:41:35,070 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 10:41:35,443 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 10:41:38,445 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 10:41:39,890 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:41:44,891 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:41:45,397 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 10:41:47,625 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:41:47,949 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:41:47,950 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:41:50,020 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:41:55,021 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:41:57,394 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 10:41:57,395 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 10:41:57,395 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 10:41:57,396 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 10:41:57,451 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 10:42:00,452 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 10:42:00,944 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:42:02,625 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:42:02,949 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:42:02,949 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:42:05,980 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:42:10,981 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:42:15,398 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 10:42:16,399 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:42:17,625 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:42:17,949 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:42:17,949 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:42:21,566 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 10:42:21,567 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 10:42:21,567 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 10:42:21,568 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:42:21,568 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 10:42:22,461 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

@@ -884,4 +884,6 @@
   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": 3.4659, "train/grad_norm": 31.448450088500977, "train/learning_rate": 1.846624089432392e-05, "train/epoch": 0.71, "train/global_step": 8860, "_timestamp": 1712918495.067904, "_runtime": 10850.560185909271, "_step": 442}
+{"train/loss": 3.4938, "train/grad_norm": 65.90203857421875, "train/learning_rate": 1.8371635972030942e-05, "train/epoch": 0.71, "train/global_step": 8900, "_timestamp": 1712918541.5655575, "_runtime": 10897.057839393616, "_step": 444}

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

@@ -7314,3 +7314,35 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 10:41:35,070 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
 2024-04-12 10:41:35,070 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 10:41:35,443 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 10:41:38,445 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 10:41:39,890 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:41:44,891 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:41:45,397 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 10:41:47,625 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:41:47,949 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:41:47,950 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:41:50,020 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:41:55,021 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:41:57,394 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 10:41:57,395 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 10:41:57,395 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 10:41:57,396 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 10:41:57,451 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 10:42:00,452 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 10:42:00,944 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:42:02,625 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:42:02,949 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:42:02,949 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:42:05,980 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:42:10,981 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:42:15,398 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 10:42:16,399 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:42:17,625 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:42:17,949 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:42:17,949 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:42:21,566 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 10:42:21,567 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 10:42:21,567 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 10:42:21,568 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:42:21,568 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 10:42:22,461 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