Training in progress, step 7220

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d33ad5ad7297a3474565ac786f8f9d70a33eb5627d08f5a697c138ffc15d88d1
+oid sha256:04106cea74c9b7217608ed5335434aec139928b980a1d98f13c1d65ad9a2757e
 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 sha256:77935b310b7dc668fa40971d7f9175b955e8c24306f9eee262205ae0bb2105dd
-size 81218
+oid sha256:685a442f340384f8f0c2f4017750b33a7b6cf8cb85bca6e36119662c991f7791
+size 81429

wandb/debug-internal.log

@@ -5948,3 +5948,20 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 10:07:29,187 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 10:07:29,605 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 10:07:30,007 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:07:31,606 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 10:07:32,146 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:07:32,721 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:07:32,722 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:07:35,831 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:07:40,832 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:07:45,332 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 10:07:46,333 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:07:47,146 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:07:47,721 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:07:47,722 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:07:51,812 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:07:54,959 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 10:07:54,960 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 10:07:54,961 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 10:07:54,961 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 10:07:55,615 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

@@ -716,4 +716,6 @@
   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": 3.4405, "train/grad_norm": 25.721759796142578, "train/learning_rate": 2.2217789167362078e-05, "train/epoch": 0.58, "train/global_step": 7200, "_timestamp": 1712916449.18498, "_runtime": 8804.677261829376, "_step": 359}
+{"train/loss": 3.5408, "train/grad_norm": 34.66562271118164, "train/learning_rate": 2.217516409129699e-05, "train/epoch": 0.58, "train/global_step": 7220, "_timestamp": 1712916474.9589913, "_runtime": 8830.451273202896, "_step": 360}

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

@@ -5948,3 +5948,20 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 10:07:29,187 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 10:07:29,605 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 10:07:30,007 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:07:31,606 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 10:07:32,146 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:07:32,721 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:07:32,722 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:07:35,831 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:07:40,832 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:07:45,332 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 10:07:46,333 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:07:47,146 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:07:47,721 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:07:47,722 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:07:51,812 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:07:54,959 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 10:07:54,960 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 10:07:54,961 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 10:07:54,961 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 10:07:55,615 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