Training in progress, step 40

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:533927acb55df80e6c77c4e44b5e95d6906f3b0015497942bec83230a6f3834f
+oid sha256:7598e4d11a7e88a2cd048c7d81b03a00065ebccc133982b8a62f1502da78a828
 size 12803224

runs/Apr13_02-50-02_4be9d1bc899e/events.out.tfevents.1712977457.4be9d1bc899e.109.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3adee0ee0d08dba60751b060411dc51828927959bb02ef8971a768562bf70d2c
-size 5489
+oid sha256:ce87010a8fba3aeaebae80900ef8dc44dbc7334adfc638b206adfd2654ee5d75
+size 5696

wandb/debug-internal.log

@@ -86,3 +86,25 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-13 03:08:10,148 DEBUG   SenderThread:162 [sender.py:send_request():406] send_request: summary_record
 2024-04-13 03:08:10,150 INFO    SenderThread:162 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-13 03:08:10,396 INFO    Thread-12 :162 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240413_030720-hqqism3w/files/wandb-summary.json
+2024-04-13 03:08:12,938 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:08:13,397 INFO    Thread-12 :162 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240413_030720-hqqism3w/files/output.log
+2024-04-13 03:08:17,938 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:08:21,491 DEBUG   SystemMonitor:162 [system_monitor.py:_start():172] Starting system metrics aggregation loop
+2024-04-13 03:08:21,492 DEBUG   SenderThread:162 [sender.py:send():379] send: stats
+2024-04-13 03:08:22,561 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-13 03:08:22,562 DEBUG   SenderThread:162 [sender.py:send_request():406] send_request: stop_status
+2024-04-13 03:08:22,566 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-13 03:08:23,629 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:08:24,401 INFO    Thread-12 :162 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240413_030720-hqqism3w/files/config.yaml
+2024-04-13 03:08:28,735 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:08:33,736 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:08:37,561 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-13 03:08:37,562 DEBUG   SenderThread:162 [sender.py:send_request():406] send_request: stop_status
+2024-04-13 03:08:37,602 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-13 03:08:39,617 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:08:44,618 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:08:45,115 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-13 03:08:45,116 DEBUG   SenderThread:162 [sender.py:send():379] send: history
+2024-04-13 03:08:45,116 DEBUG   SenderThread:162 [sender.py:send_request():406] send_request: summary_record
+2024-04-13 03:08:45,118 INFO    SenderThread:162 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-13 03:08:45,409 INFO    Thread-12 :162 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240413_030720-hqqism3w/files/wandb-summary.json

wandb/run-20240413_030720-hqqism3w/files/config.yaml

@@ -58,6 +58,22 @@ _wandb:
     - 1: train/global_step
       6:
       - 3
+    - 1: train/loss
+      5: 1
+      6:
+      - 1
+    - 1: train/grad_norm
+      5: 1
+      6:
+      - 1
+    - 1: train/learning_rate
+      5: 1
+      6:
+      - 1
+    - 1: train/epoch
+      5: 1
+      6:
+      - 1
 vocab_size:
   desc: null
   value: 250880

wandb/run-20240413_030720-hqqism3w/files/output.log

@@ -1 +1,3 @@
+/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-20240413_030720-hqqism3w/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 3.6651, "train/grad_norm": 75.3083267211914, "train/learning_rate": 1.6666666666666667e-06, "train/epoch": 0.0, "train/global_step": 20, "_timestamp": 1712977690.1454391, "_runtime": 49.33286714553833, "_step": 0}
+{"train/loss": 3.7271, "train/grad_norm": 90.37364196777344, "train/learning_rate": 3.3333333333333333e-06, "train/epoch": 0.0, "train/global_step": 40, "_timestamp": 1712977725.1147408, "_runtime": 84.30216884613037, "_step": 1}

wandb/run-20240413_030720-hqqism3w/logs/debug-internal.log

@@ -86,3 +86,25 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-13 03:08:10,148 DEBUG   SenderThread:162 [sender.py:send_request():406] send_request: summary_record
 2024-04-13 03:08:10,150 INFO    SenderThread:162 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
 2024-04-13 03:08:10,396 INFO    Thread-12 :162 [dir_watcher.py:_on_file_created():271] file/dir created: /kaggle/working/wandb/run-20240413_030720-hqqism3w/files/wandb-summary.json
+2024-04-13 03:08:12,938 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:08:13,397 INFO    Thread-12 :162 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240413_030720-hqqism3w/files/output.log
+2024-04-13 03:08:17,938 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:08:21,491 DEBUG   SystemMonitor:162 [system_monitor.py:_start():172] Starting system metrics aggregation loop
+2024-04-13 03:08:21,492 DEBUG   SenderThread:162 [sender.py:send():379] send: stats
+2024-04-13 03:08:22,561 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-13 03:08:22,562 DEBUG   SenderThread:162 [sender.py:send_request():406] send_request: stop_status
+2024-04-13 03:08:22,566 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-13 03:08:23,629 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:08:24,401 INFO    Thread-12 :162 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240413_030720-hqqism3w/files/config.yaml
+2024-04-13 03:08:28,735 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:08:33,736 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:08:37,561 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-13 03:08:37,562 DEBUG   SenderThread:162 [sender.py:send_request():406] send_request: stop_status
+2024-04-13 03:08:37,602 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-13 03:08:39,617 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:08:44,618 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: status_report
+2024-04-13 03:08:45,115 DEBUG   HandlerThread:162 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-13 03:08:45,116 DEBUG   SenderThread:162 [sender.py:send():379] send: history
+2024-04-13 03:08:45,116 DEBUG   SenderThread:162 [sender.py:send_request():406] send_request: summary_record
+2024-04-13 03:08:45,118 INFO    SenderThread:162 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-13 03:08:45,409 INFO    Thread-12 :162 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240413_030720-hqqism3w/files/wandb-summary.json