Training in progress, step 340

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:364f6da3a4ebddec454e8c37aa50aa9c92120309c0c99ba6b58ce7277c88d74e
+oid sha256:6b7ec6cf301def100707e361a4e6c1db2db1aa3990c9cef234399996a58cfb97
 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 sha256:336f0fec34190fab0f3e6660a6578e58cfdffb17d0039d3a103bb83a98c9c2f9
-size 8634
+oid sha256:279e897ef3e73075bde5b841b5ba2572e60217f7dec04ee77ad12ac20d324c63
+size 8845

wandb/debug-internal.log

@@ -331,3 +331,22 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 07:47:35,138 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
 2024-04-12 07:47:35,139 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 07:47:36,075 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 07:47:37,863 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:47:38,076 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 07:47:42,864 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:47:45,029 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 07:47:46,042 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:47:46,044 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:47:46,044 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:47:48,168 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:47:53,169 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:47:58,170 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:48:00,044 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:48:00,045 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 07:48:00,046 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:48:00,046 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:48:00,086 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 07:48:01,050 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:48:01,050 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:48:01,051 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:48:02,087 INFO    Thread-12 :485 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_074044-widovcn3/files/output.log

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

@@ -28,4 +28,8 @@
   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": 4.0958, "train/grad_norm": 34.03230285644531, "train/learning_rate": 1.6e-05, "train/epoch": 0.03, "train/global_step": 320, "_timestamp": 1712908055.1366203, "_runtime": 410.62890219688416, "_step": 15}
+{"train/loss": 4.024, "train/grad_norm": 29.786975860595703, "train/learning_rate": 1.7e-05, "train/epoch": 0.03, "train/global_step": 340, "_timestamp": 1712908080.0437582, "_runtime": 435.53604006767273, "_step": 16}

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

@@ -331,3 +331,22 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 07:47:35,138 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
 2024-04-12 07:47:35,139 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 07:47:36,075 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 07:47:37,863 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:47:38,076 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 07:47:42,864 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:47:45,029 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 07:47:46,042 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:47:46,044 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:47:46,044 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:47:48,168 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:47:53,169 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:47:58,170 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:48:00,044 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:48:00,045 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 07:48:00,046 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:48:00,046 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:48:00,086 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 07:48:01,050 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:48:01,050 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:48:01,051 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:48:02,087 INFO    Thread-12 :485 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_074044-widovcn3/files/output.log