Training in progress, step 18560

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1a89e01452a1f4a07786e13815583895e60d58274777765962f66cefaa61094
+oid sha256:f3ead06ca64c097b468e4848a48dfe313e10e066882daadec4733b392f7d027f
 size 13982248

runs/Apr12_11-58-09_f044666cc877/events.out.tfevents.1712923163.f044666cc877.110.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:336c4d0fbaa9dbd78745cd950aef914551227a4a92299ebd04e9e9dcb3463dd5
-size 201287
+oid sha256:d903f74c6c3b2a17c0879b3a1cec6a2056893f8043ad1d9d0ebbd7ffc341750d
+size 201502

wandb/debug-internal.log

@@ -13879,3 +13879,16 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 17:25:44,869 INFO    Thread-12 :151 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_115951-o0z5y86z/files/wandb-summary.json
 2024-04-12 17:25:44,919 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: status_report
 2024-04-12 17:25:45,870 INFO    Thread-12 :151 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_115951-o0z5y86z/files/output.log
+2024-04-12 17:25:49,920 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 17:25:52,996 DEBUG   SenderThread:151 [sender.py:send():379] send: stats
+2024-04-12 17:25:54,997 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 17:25:57,510 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 17:25:57,511 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 17:25:57,512 DEBUG   SenderThread:151 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 17:26:00,615 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 17:26:05,616 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 17:26:06,123 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 17:26:06,124 DEBUG   SenderThread:151 [sender.py:send():379] send: history
+2024-04-12 17:26:06,124 DEBUG   SenderThread:151 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 17:26:06,125 INFO    SenderThread:151 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 17:26:06,878 INFO    Thread-12 :151 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_115951-o0z5y86z/files/wandb-summary.json

wandb/run-20240412_115951-o0z5y86z/files/output.log

@@ -1856,4 +1856,6 @@
   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_115951-o0z5y86z/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 3.5348, "train/grad_norm": 22.156579971313477, "train/learning_rate": 6.954854106421715e-07, "train/epoch": 0.26, "train/global_step": 18540, "_timestamp": 1712942744.08272, "_runtime": 19552.491750001907, "_step": 926}
+{"train/loss": 3.5451, "train/grad_norm": 28.641721725463867, "train/learning_rate": 6.766473629355452e-07, "train/epoch": 0.26, "train/global_step": 18560, "_timestamp": 1712942766.1225753, "_runtime": 19574.531605243683, "_step": 927}

wandb/run-20240412_115951-o0z5y86z/logs/debug-internal.log

@@ -13879,3 +13879,16 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 17:25:44,869 INFO    Thread-12 :151 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_115951-o0z5y86z/files/wandb-summary.json
 2024-04-12 17:25:44,919 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: status_report
 2024-04-12 17:25:45,870 INFO    Thread-12 :151 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_115951-o0z5y86z/files/output.log
+2024-04-12 17:25:49,920 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 17:25:52,996 DEBUG   SenderThread:151 [sender.py:send():379] send: stats
+2024-04-12 17:25:54,997 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 17:25:57,510 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 17:25:57,511 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 17:25:57,512 DEBUG   SenderThread:151 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 17:26:00,615 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 17:26:05,616 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 17:26:06,123 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 17:26:06,124 DEBUG   SenderThread:151 [sender.py:send():379] send: history
+2024-04-12 17:26:06,124 DEBUG   SenderThread:151 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 17:26:06,125 INFO    SenderThread:151 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 17:26:06,878 INFO    Thread-12 :151 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_115951-o0z5y86z/files/wandb-summary.json