Training in progress, step 8960

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a9af64ab1559fcaab9589d8b574c2421e411e125c9460216500726ffa65a931
+oid sha256:b67cfb334f553e5fa2e5680a958299e8e3cfb8a501013766061595a741a2b198
 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 sha256:49ef6a1e62fc37f8fefa4e4599a33b81a6264de4dc97b9893df9143c73524531
-size 99364
+oid sha256:9ffcc6fa0d4a318db3f21dd6896be34f136ab66901fb9882e95fa8aac0745499
+size 99786

wandb/debug-internal.log

@@ -7364,3 +7364,34 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 10:42:47,949 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
 2024-04-12 10:42:48,082 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
 2024-04-12 10:42:48,470 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 10:42:50,471 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 10:42:53,560 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:42:58,561 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:43:02,626 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:43:02,949 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:43:02,950 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:43:03,848 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:43:08,850 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:43:11,401 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 10:43:11,402 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 10:43:11,402 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 10:43:11,403 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 10:43:11,479 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 10:43:13,978 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:43:14,481 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 10:43:15,400 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 10:43:17,626 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:43:17,949 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:43:17,949 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:43:19,058 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:43:24,059 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:43:29,061 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:43:32,626 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:43:32,949 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:43:32,950 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:43:34,081 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:43:34,705 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 10:43:34,706 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 10:43:34,707 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 10:43:34,707 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 10:43:35,488 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

@@ -888,4 +888,8 @@
   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": 3.3931, "train/grad_norm": 25.6701602935791, "train/learning_rate": 1.8324280212401316e-05, "train/epoch": 0.71, "train/global_step": 8920, "_timestamp": 1712918567.7775002, "_runtime": 10923.269782066345, "_step": 445}
+{"train/loss": 3.4074, "train/grad_norm": 26.73450469970703, "train/learning_rate": 1.8229464579868124e-05, "train/epoch": 0.72, "train/global_step": 8960, "_timestamp": 1712918614.7049577, "_runtime": 10970.197239637375, "_step": 447}

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

@@ -7364,3 +7364,34 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 10:42:47,949 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
 2024-04-12 10:42:48,082 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
 2024-04-12 10:42:48,470 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 10:42:50,471 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 10:42:53,560 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:42:58,561 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:43:02,626 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:43:02,949 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:43:02,950 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:43:03,848 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:43:08,850 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:43:11,401 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 10:43:11,402 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 10:43:11,402 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 10:43:11,403 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 10:43:11,479 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 10:43:13,978 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:43:14,481 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 10:43:15,400 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 10:43:17,626 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:43:17,949 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:43:17,949 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:43:19,058 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:43:24,059 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:43:29,061 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:43:32,626 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:43:32,949 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:43:32,950 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:43:34,081 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:43:34,705 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 10:43:34,706 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 10:43:34,707 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 10:43:34,707 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 10:43:35,488 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