Training in progress, step 160

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50c0bb52227566fdedffa529ef2d112337892b1e2363fcc0565a80cbf56fd4e9
+oid sha256:7ef52118b7358bdb0aa0f0554808f11d96b38076a0b9d7546a83421a5f489428
 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:cdf267dbf8f30ea76b0171d24899d6d6c8b49ab89a0f3f2d2ff83e1959698d0a
-size 6735
+oid sha256:7882bd3e3015e5bd3b4fff0f7eed55da8864fe7543de6e54db827f2808722029
+size 6946

wandb/debug-internal.log

@@ -130,3 +130,10 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 07:36:59,729 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
 2024-04-12 07:36:59,729 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 07:37:00,332 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 07:37:03,333 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 07:37:04,722 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:37:06,767 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:37:06,769 DEBUG   SenderThread:334 [sender.py:send():379] send: history
+2024-04-12 07:37:06,769 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:37:06,772 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:37:07,335 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

@@ -10,4 +10,6 @@
   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": 5.0142, "train/grad_norm": 43.68627166748047, "train/learning_rate": 7e-06, "train/epoch": 0.0, "train/global_step": 140, "_timestamp": 1712907419.7269895, "_runtime": 63.97810339927673, "_step": 6}
+{"train/loss": 4.8572, "train/grad_norm": 37.58155059814453, "train/learning_rate": 8e-06, "train/epoch": 0.0, "train/global_step": 160, "_timestamp": 1712907426.7673645, "_runtime": 71.01847839355469, "_step": 7}

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

@@ -130,3 +130,10 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 07:36:59,729 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
 2024-04-12 07:36:59,729 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 07:37:00,332 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 07:37:03,333 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 07:37:04,722 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:37:06,767 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:37:06,769 DEBUG   SenderThread:334 [sender.py:send():379] send: history
+2024-04-12 07:37:06,769 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:37:06,772 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:37:07,335 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