Training in progress, step 18540

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ee3c331e12cc90d2109f4e1480b06ec8c2e15119b962650d98dc8e9275f0114
+oid sha256:f1a89e01452a1f4a07786e13815583895e60d58274777765962f66cefaa61094
 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 sha256:6ee9d53a8927d127dcbcdd7adda0c81b8ec82577095669e93f1c060abcd9b58b
-size 201072
+oid sha256:336c4d0fbaa9dbd78745cd950aef914551227a4a92299ebd04e9e9dcb3463dd5
+size 201287

wandb/debug-internal.log

@@ -13861,3 +13861,21 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 17:25:21,639 INFO    SenderThread:151 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 17:25:21,861 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 17:25:22,995 DEBUG   SenderThread:151 [sender.py:send():379] send: stats
+2024-04-12 17:25:23,862 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 17:25:23,996 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 17:25:27,510 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 17:25:27,511 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 17:25:27,511 DEBUG   SenderThread:151 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 17:25:29,650 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 17:25:34,651 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 17:25:39,652 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 17:25:42,510 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 17:25:42,511 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 17:25:42,512 DEBUG   SenderThread:151 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 17:25:44,083 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 17:25:44,084 DEBUG   SenderThread:151 [sender.py:send():379] send: history
+2024-04-12 17:25:44,084 DEBUG   SenderThread:151 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 17:25:44,085 INFO    SenderThread:151 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+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

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

@@ -1854,4 +1854,6 @@
   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": 3.5844, "train/grad_norm": 19.394601821899414, "train/learning_rate": 7.145784012061424e-07, "train/epoch": 0.26, "train/global_step": 18520, "_timestamp": 1712942721.6361759, "_runtime": 19530.045205831528, "_step": 925}
+{"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}

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

@@ -13861,3 +13861,21 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 17:25:21,639 INFO    SenderThread:151 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 17:25:21,861 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 17:25:22,995 DEBUG   SenderThread:151 [sender.py:send():379] send: stats
+2024-04-12 17:25:23,862 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 17:25:23,996 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 17:25:27,510 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 17:25:27,511 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 17:25:27,511 DEBUG   SenderThread:151 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 17:25:29,650 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 17:25:34,651 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 17:25:39,652 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 17:25:42,510 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 17:25:42,511 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 17:25:42,512 DEBUG   SenderThread:151 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 17:25:44,083 DEBUG   HandlerThread:151 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 17:25:44,084 DEBUG   SenderThread:151 [sender.py:send():379] send: history
+2024-04-12 17:25:44,084 DEBUG   SenderThread:151 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 17:25:44,085 INFO    SenderThread:151 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+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