Training in progress, step 6740

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baab6ce921f1613f657e84693cedae976231955db151735d337f863663c7e95d
+oid sha256:7bb5fc18755b1bc902fa960b0f60645e025420e2f705caa8dd38fa32ba2a515f
 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 sha256:748ff77aac6a40f29dc4738f0c4853f2de9644ac0dbce69f19849178aeab0ed1
-size 75943
+oid sha256:77811c0aeadea0ef1b4e560da79568bd30427837490fc86698dd7b730f6c1bbe
+size 76365

wandb/debug-internal.log

@@ -5542,3 +5542,35 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 09:57:17,795 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
 2024-04-12 09:57:17,795 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 09:57:18,308 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 09:57:21,310 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 09:57:22,605 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:57:27,606 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:57:32,139 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 09:57:32,607 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:57:32,610 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 09:57:32,611 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 09:57:37,653 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:57:42,513 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 09:57:42,514 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 09:57:42,514 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 09:57:42,515 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 09:57:43,029 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:57:43,318 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 09:57:45,312 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 09:57:45,318 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 09:57:47,139 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 09:57:47,611 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 09:57:47,611 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 09:57:48,733 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:57:53,734 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:57:58,735 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:58:02,140 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 09:58:02,611 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 09:58:02,611 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 09:58:04,727 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:58:07,958 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 09:58:07,960 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 09:58:07,960 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 09:58:07,960 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 09:58:08,327 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 09:58:09,743 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report

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

@@ -666,4 +666,8 @@
   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": 3.3443, "train/grad_norm": 21.337862014770508, "train/learning_rate": 2.3257661740587055e-05, "train/epoch": 0.54, "train/global_step": 6700, "_timestamp": 1712915837.7930465, "_runtime": 8193.285328388214, "_step": 334}
+{"train/loss": 3.4748, "train/grad_norm": 27.79935646057129, "train/learning_rate": 2.3176374956579525e-05, "train/epoch": 0.54, "train/global_step": 6740, "_timestamp": 1712915887.9583817, "_runtime": 8243.45066356659, "_step": 336}

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

@@ -5542,3 +5542,35 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 09:57:17,795 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
 2024-04-12 09:57:17,795 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 09:57:18,308 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 09:57:21,310 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 09:57:22,605 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:57:27,606 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:57:32,139 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 09:57:32,607 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:57:32,610 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 09:57:32,611 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 09:57:37,653 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:57:42,513 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 09:57:42,514 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 09:57:42,514 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 09:57:42,515 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 09:57:43,029 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:57:43,318 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 09:57:45,312 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 09:57:45,318 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 09:57:47,139 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 09:57:47,611 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 09:57:47,611 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 09:57:48,733 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:57:53,734 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:57:58,735 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:58:02,140 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 09:58:02,611 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 09:58:02,611 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 09:58:04,727 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 09:58:07,958 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 09:58:07,960 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 09:58:07,960 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 09:58:07,960 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 09:58:08,327 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 09:58:09,743 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report