Training in progress, step 120

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79d9c815d4c43548c4c0ce822c3f1c0ee1bdede2f9fab3ab3cfa6a4b4da825c8
+oid sha256:c38bdb0979c928e502c97dd82b769114b80aa32487f2fa00dc25b698969b75a2
 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 sha256:362c44eff627365de274f8ddfeaefdcd5b5b48cbcf7ca4b32147dbb13fa8c0ab
-size 6317
+oid sha256:c82f06668489a1c84d23a53ad8c6ad5f5ccbe7487f4b903cddcf47c080541d22
+size 6524

wandb/debug-internal.log

@@ -110,3 +110,11 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 07:36:46,422 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
 2024-04-12 07:36:46,424 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 07:36:47,326 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 07:36:49,121 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:36:49,327 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 07:36:53,592 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:36:53,593 DEBUG   SenderThread:334 [sender.py:send():379] send: history
+2024-04-12 07:36:53,593 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:36:53,595 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:36:54,299 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:36:54,329 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

@@ -6,4 +6,8 @@
   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.
+  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": 4.7237, "train/grad_norm": 147.12461853027344, "train/learning_rate": 4.9999999999999996e-06, "train/epoch": 0.0, "train/global_step": 100, "_timestamp": 1712907406.4197586, "_runtime": 50.67087244987488, "_step": 4}
+{"train/loss": 4.4426, "train/grad_norm": 115.61023712158203, "train/learning_rate": 6e-06, "train/epoch": 0.0, "train/global_step": 120, "_timestamp": 1712907413.591552, "_runtime": 57.842665910720825, "_step": 5}

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

@@ -110,3 +110,11 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 07:36:46,422 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
 2024-04-12 07:36:46,424 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-12 07:36:47,326 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 07:36:49,121 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:36:49,327 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 07:36:53,592 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:36:53,593 DEBUG   SenderThread:334 [sender.py:send():379] send: history
+2024-04-12 07:36:53,593 DEBUG   SenderThread:334 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:36:53,595 INFO    SenderThread:334 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:36:54,299 DEBUG   HandlerThread:334 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:36:54,329 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