Training in progress, step 360

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f783b68bc77d003b2ec2afb55e3fb0efe7ee75df1d06ba594d78823f698ccfe
+oid sha256:e02434f63bb76768d0764fb21761fc6bc5a8c5697635718d6ef1c79a814a08e1
 size 8077608

runs/Apr12_07-35-52_e5a48bec8248/events.out.tfevents.1712907354.e5a48bec8248.289.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fa9c1629eaac3b4aa7e3d18636a184dff31921f4ce135ec381c222922de6ba4
-size 8634
+oid sha256:2aac56b8ba2fcb1082cc0618c10b7f72fb3537a527bfd2ef5a173483ed4ae540
+size 9056

wandb/debug-internal.log

@@ -209,3 +209,22 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 07:38:00,978 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
 2024-04-12 07:38:00,980 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 07:38:01,357 INFO    Thread-12 :334 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/wandb-summary.json
+2024-04-12 07:38:03,358 INFO    Thread-12 :334 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/output.log
+2024-04-12 07:38:05,666 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:38:08,120 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:38:08,121 DEBUG   SenderThread:334 [sender.py:send():379] send: history
+2024-04-12 07:38:08,121 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:38:08,121 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:38:08,360 INFO    Thread-12 :334 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/wandb-summary.json
+2024-04-12 07:38:09,361 INFO    Thread-12 :334 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/output.log
+2024-04-12 07:38:11,565 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:38:12,513 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:38:12,513 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:38:12,514 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:38:15,302 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:38:15,303 DEBUG   SenderThread:334 [sender.py:send():379] send: history
+2024-04-12 07:38:15,303 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:38:15,305 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:38:15,363 INFO    Thread-12 :334 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/wandb-summary.json
+2024-04-12 07:38:16,980 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:38:17,364 INFO    Thread-12 :334 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/output.log

wandb/run-20240412_073555-bw7oy9ix/files/output.log

@@ -28,4 +28,10 @@
   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.
+  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_073555-bw7oy9ix/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 4.5021, "train/grad_norm": 38.77900695800781, "train/learning_rate": 1.6e-05, "train/epoch": 0.01, "train/global_step": 320, "_timestamp": 1712907480.9764044, "_runtime": 125.22751832008362, "_step": 15}
+{"train/loss": 4.3795, "train/grad_norm": 78.24981689453125, "train/learning_rate": 1.8e-05, "train/epoch": 0.01, "train/global_step": 360, "_timestamp": 1712907495.3015952, "_runtime": 139.55270910263062, "_step": 17}

wandb/run-20240412_073555-bw7oy9ix/logs/debug-internal.log

@@ -209,3 +209,22 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 07:38:00,978 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
 2024-04-12 07:38:00,980 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 07:38:01,357 INFO    Thread-12 :334 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/wandb-summary.json
+2024-04-12 07:38:03,358 INFO    Thread-12 :334 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/output.log
+2024-04-12 07:38:05,666 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:38:08,120 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:38:08,121 DEBUG   SenderThread:334 [sender.py:send():379] send: history
+2024-04-12 07:38:08,121 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:38:08,121 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:38:08,360 INFO    Thread-12 :334 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/wandb-summary.json
+2024-04-12 07:38:09,361 INFO    Thread-12 :334 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/output.log
+2024-04-12 07:38:11,565 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:38:12,513 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 07:38:12,513 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 07:38:12,514 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:38:15,302 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:38:15,303 DEBUG   SenderThread:334 [sender.py:send():379] send: history
+2024-04-12 07:38:15,303 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:38:15,305 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:38:15,363 INFO    Thread-12 :334 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/wandb-summary.json
+2024-04-12 07:38:16,980 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:38:17,364 INFO    Thread-12 :334 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/output.log