Training in progress, step 200

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a9867f99c80185e1b8d0dfbd9cde47afb3cd72d5abadb57ea7445d0a73daca2
+oid sha256:1cc7b9a48572694fd3b1c4f08ce5b23be1097c9f79ab4aee497359e8137b0686
 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:fdd6987bbbf5bcb819fb8087f8dd751750bd394578a44ff9cdbe328484be8003
-size 7157
+oid sha256:b8b568b7a5c5a6c9c1cd726f8371d50efdd41fce018d790f487e866997d4f294
+size 7368

wandb/debug-internal.log

@@ -147,3 +147,10 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 07:37:13,356 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
 2024-04-12 07:37:13,356 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 07:37:14,338 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 07:37:15,338 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 07:37:16,091 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:37:20,246 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:37:20,247 DEBUG   SenderThread:334 [sender.py:send():379] send: history
+2024-04-12 07:37:20,247 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:37:20,250 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:37:20,340 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

@@ -14,4 +14,6 @@
   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_073555-bw7oy9ix/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 4.6848, "train/grad_norm": 86.82076263427734, "train/learning_rate": 9e-06, "train/epoch": 0.0, "train/global_step": 180, "_timestamp": 1712907433.3538334, "_runtime": 77.6049473285675, "_step": 8}
+{"train/loss": 4.6474, "train/grad_norm": 289.0603332519531, "train/learning_rate": 9.999999999999999e-06, "train/epoch": 0.0, "train/global_step": 200, "_timestamp": 1712907440.2455006, "_runtime": 84.49661445617676, "_step": 9}

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

@@ -147,3 +147,10 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 07:37:13,356 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
 2024-04-12 07:37:13,356 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 07:37:14,338 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 07:37:15,338 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 07:37:16,091 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:37:20,246 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:37:20,247 DEBUG   SenderThread:334 [sender.py:send():379] send: history
+2024-04-12 07:37:20,247 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:37:20,250 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:37:20,340 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