Training in progress, step 60

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dfbc361c2b02f401e3f14648ec78d5e8d62997d071bdac4d7915200ce8f59a3
+oid sha256:7b5e1d7fec5642c5a7eebc261811b86c8379352efb270f0d53c3bdd0277083ab
 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 sha256:913bb113dda8007fe01268dd33a6a6f8abd869814e6e2426784ac3ea47929bf2
-size 5696
+oid sha256:6369dcc6e0a420f096623dd6414140e37237f2b8de9381a6432d557a75e720ac
+size 5903

wandb/debug-internal.log

@@ -85,3 +85,11 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 07:36:27,511 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: stop_status
 2024-04-12 07:36:27,511 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: internal_messages
 2024-04-12 07:36:27,582 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:36:28,319 INFO    Thread-12 :334 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/config.yaml
+2024-04-12 07:36:29,319 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 07:36:32,526 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:36:32,527 DEBUG   SenderThread:334 [sender.py:send():379] send: history
+2024-04-12 07:36:32,527 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:36:32,530 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:36:33,242 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:36:33,320 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

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

@@ -1,3 +1,5 @@
+/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": 4.5023, "train/grad_norm": 239.7991943359375, "train/learning_rate": 2e-06, "train/epoch": 0.0, "train/global_step": 40, "_timestamp": 1712907386.0967398, "_runtime": 30.347853660583496, "_step": 1}
+{"train/loss": 4.8171, "train/grad_norm": 77.5164794921875, "train/learning_rate": 3e-06, "train/epoch": 0.0, "train/global_step": 60, "_timestamp": 1712907392.5257075, "_runtime": 36.77682137489319, "_step": 2}

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

@@ -85,3 +85,11 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 07:36:27,511 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: stop_status
 2024-04-12 07:36:27,511 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: internal_messages
 2024-04-12 07:36:27,582 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:36:28,319 INFO    Thread-12 :334 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_073555-bw7oy9ix/files/config.yaml
+2024-04-12 07:36:29,319 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 07:36:32,526 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:36:32,527 DEBUG   SenderThread:334 [sender.py:send():379] send: history
+2024-04-12 07:36:32,527 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:36:32,530 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:36:33,242 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:36:33,320 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