Training in progress, step 60

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7598e4d11a7e88a2cd048c7d81b03a00065ebccc133982b8a62f1502da78a828
+oid sha256:1a36d600cb075593139b01f4d1f27775faa37b77eacaf43dd2393c880d628c4e
 size 12803224

runs/Apr13_02-50-02_4be9d1bc899e/events.out.tfevents.1712977457.4be9d1bc899e.109.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce87010a8fba3aeaebae80900ef8dc44dbc7334adfc638b206adfd2654ee5d75
-size 5696
+oid sha256:dd370b2c26a46764d523161c85eb3e4767bc47063c6a9a4f6b8a7baa057e2365
+size 5903

wandb/debug-internal.log

@@ -108,3 +108,29 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-13 03:08:45,116 DEBUG   SenderThread:162 [sender.py:send_request():406] send_request: summary_record
 2024-04-13 03:08:45,118 INFO    SenderThread:162 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-13 03:08:45,409 INFO    Thread-12 :162 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240413_030720-hqqism3w/files/wandb-summary.json
+2024-04-13 03:08:47,410 INFO    Thread-12 :162 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240413_030720-hqqism3w/files/output.log
+2024-04-13 03:08:49,876 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:08:51,493 DEBUG   SenderThread:162 [sender.py:send():379] send: stats
+2024-04-13 03:08:52,562 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-13 03:08:52,562 DEBUG   SenderThread:162 [sender.py:send_request():406] send_request: stop_status
+2024-04-13 03:08:52,565 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-13 03:08:55,643 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:09:00,644 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:09:05,644 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:09:07,562 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-13 03:09:07,562 DEBUG   SenderThread:162 [sender.py:send_request():406] send_request: stop_status
+2024-04-13 03:09:07,603 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-13 03:09:10,690 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:09:15,691 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:09:20,692 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:09:21,494 DEBUG   SenderThread:162 [sender.py:send():379] send: stats
+2024-04-13 03:09:22,562 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-13 03:09:22,563 DEBUG   SenderThread:162 [sender.py:send_request():406] send_request: stop_status
+2024-04-13 03:09:22,603 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-13 03:09:26,621 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:09:31,010 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-13 03:09:31,012 DEBUG   SenderThread:162 [sender.py:send():379] send: history
+2024-04-13 03:09:31,012 DEBUG   SenderThread:162 [sender.py:send_request():406] send_request: summary_record
+2024-04-13 03:09:31,012 INFO    SenderThread:162 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-13 03:09:31,427 INFO    Thread-12 :162 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240413_030720-hqqism3w/files/wandb-summary.json
+2024-04-13 03:09:31,740 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report

wandb/run-20240413_030720-hqqism3w/files/output.log

@@ -1,3 +1,5 @@
+/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-20240413_030720-hqqism3w/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 3.7271, "train/grad_norm": 90.37364196777344, "train/learning_rate": 3.3333333333333333e-06, "train/epoch": 0.0, "train/global_step": 40, "_timestamp": 1712977725.1147408, "_runtime": 84.30216884613037, "_step": 1}
+{"train/loss": 3.5867, "train/grad_norm": 47.56499481201172, "train/learning_rate": 5e-06, "train/epoch": 0.0, "train/global_step": 60, "_timestamp": 1712977771.010329, "_runtime": 130.19775700569153, "_step": 2}

wandb/run-20240413_030720-hqqism3w/logs/debug-internal.log

@@ -108,3 +108,29 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-13 03:08:45,116 DEBUG   SenderThread:162 [sender.py:send_request():406] send_request: summary_record
 2024-04-13 03:08:45,118 INFO    SenderThread:162 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-13 03:08:45,409 INFO    Thread-12 :162 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240413_030720-hqqism3w/files/wandb-summary.json
+2024-04-13 03:08:47,410 INFO    Thread-12 :162 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240413_030720-hqqism3w/files/output.log
+2024-04-13 03:08:49,876 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:08:51,493 DEBUG   SenderThread:162 [sender.py:send():379] send: stats
+2024-04-13 03:08:52,562 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-13 03:08:52,562 DEBUG   SenderThread:162 [sender.py:send_request():406] send_request: stop_status
+2024-04-13 03:08:52,565 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-13 03:08:55,643 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:09:00,644 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:09:05,644 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:09:07,562 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-13 03:09:07,562 DEBUG   SenderThread:162 [sender.py:send_request():406] send_request: stop_status
+2024-04-13 03:09:07,603 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-13 03:09:10,690 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:09:15,691 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:09:20,692 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:09:21,494 DEBUG   SenderThread:162 [sender.py:send():379] send: stats
+2024-04-13 03:09:22,562 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-13 03:09:22,563 DEBUG   SenderThread:162 [sender.py:send_request():406] send_request: stop_status
+2024-04-13 03:09:22,603 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-13 03:09:26,621 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:09:31,010 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-13 03:09:31,012 DEBUG   SenderThread:162 [sender.py:send():379] send: history
+2024-04-13 03:09:31,012 DEBUG   SenderThread:162 [sender.py:send_request():406] send_request: summary_record
+2024-04-13 03:09:31,012 INFO    SenderThread:162 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-13 03:09:31,427 INFO    Thread-12 :162 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240413_030720-hqqism3w/files/wandb-summary.json
+2024-04-13 03:09:31,740 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report