Training in progress, step 60

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa87f9a0408e652f2cd82092e72ff2e96f13f4b26866f97fa213ccfcfd1875e7
+oid sha256:2c298b8d29721f1a4fd059d2f89a9b9fa32c198dfd1c61a543ce2528f1633521
 size 4725640

runs/Apr14_08-02-48_22f82e031f6d/events.out.tfevents.1713081770.22f82e031f6d.90.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85f3107d9526ad29bd5dbe6f0c6c5c7a3aed7d74d0a40585b784be57800a7094
-size 21473
+oid sha256:15ac5573e3832a094ec8c3fe900120620377d72d808c3e715e197b76ff02146b
+size 21680

wandb/debug-internal.log

@@ -138,3 +138,17 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-14 08:11:03,944 DEBUG   SenderThread:143 [sender.py:send_request():406] send_request: summary_record
 2024-04-14 08:11:03,944 INFO    SenderThread:143 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-14 08:11:04,511 INFO    Thread-12 :143 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240414_080844-fw7v7n5v/files/wandb-summary.json
+2024-04-14 08:11:07,512 INFO    Thread-12 :143 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240414_080844-fw7v7n5v/files/output.log
+2024-04-14 08:11:08,648 DEBUG   HandlerThread:143 [handler.py:handle_request():146] handle_request: status_report
+2024-04-14 08:11:13,649 DEBUG   HandlerThread:143 [handler.py:handle_request():146] handle_request: status_report
+2024-04-14 08:11:15,575 DEBUG   SenderThread:143 [sender.py:send():379] send: stats
+2024-04-14 08:11:16,717 DEBUG   HandlerThread:143 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-14 08:11:16,717 DEBUG   HandlerThread:143 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-14 08:11:16,718 DEBUG   SenderThread:143 [sender.py:send_request():406] send_request: stop_status
+2024-04-14 08:11:18,816 DEBUG   HandlerThread:143 [handler.py:handle_request():146] handle_request: status_report
+2024-04-14 08:11:23,817 DEBUG   HandlerThread:143 [handler.py:handle_request():146] handle_request: status_report
+2024-04-14 08:11:24,756 DEBUG   HandlerThread:143 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-14 08:11:24,757 DEBUG   SenderThread:143 [sender.py:send():379] send: history
+2024-04-14 08:11:24,757 DEBUG   SenderThread:143 [sender.py:send_request():406] send_request: summary_record
+2024-04-14 08:11:24,759 INFO    SenderThread:143 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-14 08:11:25,520 INFO    Thread-12 :143 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240414_080844-fw7v7n5v/files/wandb-summary.json

wandb/run-20240414_080844-fw7v7n5v/files/output.log

@@ -1,3 +1,7 @@
+/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.
   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-20240414_080844-fw7v7n5v/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 3.6917, "train/grad_norm": 2.218903064727783, "train/learning_rate": 6.666666666666667e-06, "train/epoch": 0.0, "train/global_step": 40, "_timestamp": 1713082263.942358, "_runtime": 139.18560004234314, "_step": 2}
+{"train/loss": 3.5828, "train/grad_norm": 0.9262466430664062, "train/learning_rate": 1e-05, "train/epoch": 0.0, "train/global_step": 60, "_timestamp": 1713082284.7554557, "_runtime": 159.99869775772095, "_step": 3}

wandb/run-20240414_080844-fw7v7n5v/logs/debug-internal.log

@@ -138,3 +138,17 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-14 08:11:03,944 DEBUG   SenderThread:143 [sender.py:send_request():406] send_request: summary_record
 2024-04-14 08:11:03,944 INFO    SenderThread:143 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-14 08:11:04,511 INFO    Thread-12 :143 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240414_080844-fw7v7n5v/files/wandb-summary.json
+2024-04-14 08:11:07,512 INFO    Thread-12 :143 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240414_080844-fw7v7n5v/files/output.log
+2024-04-14 08:11:08,648 DEBUG   HandlerThread:143 [handler.py:handle_request():146] handle_request: status_report
+2024-04-14 08:11:13,649 DEBUG   HandlerThread:143 [handler.py:handle_request():146] handle_request: status_report
+2024-04-14 08:11:15,575 DEBUG   SenderThread:143 [sender.py:send():379] send: stats
+2024-04-14 08:11:16,717 DEBUG   HandlerThread:143 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-14 08:11:16,717 DEBUG   HandlerThread:143 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-14 08:11:16,718 DEBUG   SenderThread:143 [sender.py:send_request():406] send_request: stop_status
+2024-04-14 08:11:18,816 DEBUG   HandlerThread:143 [handler.py:handle_request():146] handle_request: status_report
+2024-04-14 08:11:23,817 DEBUG   HandlerThread:143 [handler.py:handle_request():146] handle_request: status_report
+2024-04-14 08:11:24,756 DEBUG   HandlerThread:143 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-14 08:11:24,757 DEBUG   SenderThread:143 [sender.py:send():379] send: history
+2024-04-14 08:11:24,757 DEBUG   SenderThread:143 [sender.py:send_request():406] send_request: summary_record
+2024-04-14 08:11:24,759 INFO    SenderThread:143 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-14 08:11:25,520 INFO    Thread-12 :143 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240414_080844-fw7v7n5v/files/wandb-summary.json