Training in progress, step 3800

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4223f69fa5c4d343cdb0daf20def262d26468340b68b3012ba5b5bf860add746
+oid sha256:36ac2a87ab309a324156770cff23fbcfbbf432e170a53864d6322a1b4b0f07fa
 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 sha256:09b6d5565c15349a6343ff5a9e4f0409b733a1c43442276635922fe6995b83ca
-size 45137
+oid sha256:8d859358ef445d8eb443d6c9d0825ba927bd193cb49b44b8e6c318a529c26c61
+size 45348

wandb/debug-internal.log

@@ -3155,3 +3155,21 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 08:57:53,788 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
 2024-04-12 08:57:53,788 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 08:57:53,867 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 08:57:56,544 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 08:57:56,868 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 08:58:01,545 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 08:58:01,917 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 08:58:02,158 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 08:58:02,158 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 08:58:07,279 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 08:58:12,280 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 08:58:15,187 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 08:58:15,458 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 08:58:15,459 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 08:58:15,459 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 08:58:15,460 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 08:58:15,876 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 08:58:16,877 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 08:58:16,917 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 08:58:17,160 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 08:58:17,160 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status

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

@@ -374,4 +374,8 @@
   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": 3.4905, "train/grad_norm": 28.02115821838379, "train/learning_rate": 2.805467086984027e-05, "train/epoch": 0.3, "train/global_step": 3780, "_timestamp": 1712912273.7863293, "_runtime": 4629.2786111831665, "_step": 188}
+{"train/loss": 3.5289, "train/grad_norm": 41.776817321777344, "train/learning_rate": 2.803067604777227e-05, "train/epoch": 0.3, "train/global_step": 3800, "_timestamp": 1712912295.4576507, "_runtime": 4650.949932575226, "_step": 189}

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

@@ -3155,3 +3155,21 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 08:57:53,788 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
 2024-04-12 08:57:53,788 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 08:57:53,867 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 08:57:56,544 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 08:57:56,868 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 08:58:01,545 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 08:58:01,917 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 08:58:02,158 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 08:58:02,158 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 08:58:07,279 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 08:58:12,280 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 08:58:15,187 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 08:58:15,458 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 08:58:15,459 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 08:58:15,459 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 08:58:15,460 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 08:58:15,876 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 08:58:16,877 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 08:58:16,917 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 08:58:17,160 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 08:58:17,160 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status