Training in progress, step 9060

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba139240646f433f9f0106d855aea9e350f07f031693b316743dd388f006a45a
+oid sha256:b0bac75f5d24a596f406e46fc168b931d808d6267d31438980869f07fbf3a128
 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:d2f229b0ff58ad3c7398f80c3698a6cf6357a6eab2eaddf535b2f272e8058080
-size 100630
+oid sha256:08d02f2583e07de081efa567b8092e11e12838ef6766ab641d4adc1d3fc872a2
+size 100841

wandb/debug-internal.log

@@ -7460,3 +7460,20 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 10:45:14,211 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 10:45:14,527 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 10:45:15,405 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 10:45:16,528 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 10:45:17,627 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:45:17,951 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:45:17,951 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:45:19,085 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:45:24,086 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:45:29,087 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:45:32,627 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:45:32,951 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:45:32,951 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:45:35,032 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:45:40,033 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:45:42,445 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 10:45:42,446 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 10:45:42,446 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 10:45:42,447 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 10:45:42,537 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

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

@@ -902,4 +902,6 @@
   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_074044-widovcn3/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 3.5014, "train/grad_norm": 26.23653793334961, "train/learning_rate": 1.8039430793163753e-05, "train/epoch": 0.72, "train/global_step": 9040, "_timestamp": 1712918714.2085314, "_runtime": 11069.700813293457, "_step": 451}
+{"train/loss": 3.4575, "train/grad_norm": 21.284992218017578, "train/learning_rate": 1.7991841394296962e-05, "train/epoch": 0.72, "train/global_step": 9060, "_timestamp": 1712918742.444912, "_runtime": 11097.937193870544, "_step": 452}

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

@@ -7460,3 +7460,20 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 10:45:14,211 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 10:45:14,527 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 10:45:15,405 DEBUG   SenderThread:485 [sender.py:send():379] send: stats
+2024-04-12 10:45:16,528 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 10:45:17,627 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:45:17,951 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:45:17,951 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:45:19,085 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:45:24,086 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:45:29,087 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:45:32,627 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-12 10:45:32,951 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-12 10:45:32,951 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 10:45:35,032 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:45:40,033 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 10:45:42,445 DEBUG   HandlerThread:485 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 10:45:42,446 DEBUG   SenderThread:485 [sender.py:send():379] send: history
+2024-04-12 10:45:42,446 DEBUG   SenderThread:485 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 10:45:42,447 INFO    SenderThread:485 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 10:45:42,537 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