Training in progress, step 60

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d1b8936336ff610c11541b9799877d17a6fd74ef7458f9355dbb1999c703751
+oid sha256:4c13c1fb05d548b619e4ea3b6565286621267c5c8ce62890c4968c123b771070
 size 12803224

runs/Apr14_07-30-34_f694866fb244/events.out.tfevents.1713079834.f694866fb244.141.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb8d399141c20a86ee377255e55772bfce1bb01815ec3897356ebf21a3e1c1fd
-size 5694
+oid sha256:d05fa45d37933ab2faaad0da4cafab1afede4c1d758ab38535eda372c0c60116
+size 5901

wandb/debug-internal.log

@@ -96,3 +96,20 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-14 07:32:18,137 INFO    Thread-12 :183 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240414_073117-xuqlocdo/files/wandb-summary.json
 2024-04-14 07:32:18,235 DEBUG   SystemMonitor:183 [system_monitor.py:_start():172] Starting system metrics aggregation loop
 2024-04-14 07:32:18,237 DEBUG   SenderThread:183 [sender.py:send():379] send: stats
+2024-04-14 07:32:19,298 DEBUG   HandlerThread:183 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-14 07:32:19,298 DEBUG   SenderThread:183 [sender.py:send_request():406] send_request: stop_status
+2024-04-14 07:32:19,301 DEBUG   HandlerThread:183 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-14 07:32:20,138 INFO    Thread-12 :183 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240414_073117-xuqlocdo/files/output.log
+2024-04-14 07:32:20,418 DEBUG   HandlerThread:183 [handler.py:handle_request():146] handle_request: status_report
+2024-04-14 07:32:21,138 INFO    Thread-12 :183 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240414_073117-xuqlocdo/files/config.yaml
+2024-04-14 07:32:25,504 DEBUG   HandlerThread:183 [handler.py:handle_request():146] handle_request: status_report
+2024-04-14 07:32:30,505 DEBUG   HandlerThread:183 [handler.py:handle_request():146] handle_request: status_report
+2024-04-14 07:32:34,298 DEBUG   HandlerThread:183 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-14 07:32:34,299 DEBUG   SenderThread:183 [sender.py:send_request():406] send_request: stop_status
+2024-04-14 07:32:34,338 DEBUG   HandlerThread:183 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-14 07:32:36,378 DEBUG   HandlerThread:183 [handler.py:handle_request():146] handle_request: status_report
+2024-04-14 07:32:38,751 DEBUG   HandlerThread:183 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-14 07:32:38,753 DEBUG   SenderThread:183 [sender.py:send():379] send: history
+2024-04-14 07:32:38,753 DEBUG   SenderThread:183 [sender.py:send_request():406] send_request: summary_record
+2024-04-14 07:32:38,753 INFO    SenderThread:183 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-14 07:32:39,145 INFO    Thread-12 :183 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240414_073117-xuqlocdo/files/wandb-summary.json

wandb/run-20240414_073117-xuqlocdo/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-20240414_073117-xuqlocdo/files/output.log

@@ -1,3 +1,5 @@
+/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_073117-xuqlocdo/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 3.7962, "train/grad_norm": 90.38651275634766, "train/learning_rate": 5.333333333333334e-06, "train/epoch": 0.0, "train/global_step": 40, "_timestamp": 1713079937.4737687, "_runtime": 60.03454566001892, "_step": 1}
+{"train/loss": 3.5164, "train/grad_norm": 108.40189361572266, "train/learning_rate": 8.666666666666668e-06, "train/epoch": 0.0, "train/global_step": 60, "_timestamp": 1713079958.7512317, "_runtime": 81.31200861930847, "_step": 2}

wandb/run-20240414_073117-xuqlocdo/logs/debug-internal.log

@@ -96,3 +96,20 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-14 07:32:18,137 INFO    Thread-12 :183 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240414_073117-xuqlocdo/files/wandb-summary.json
 2024-04-14 07:32:18,235 DEBUG   SystemMonitor:183 [system_monitor.py:_start():172] Starting system metrics aggregation loop
 2024-04-14 07:32:18,237 DEBUG   SenderThread:183 [sender.py:send():379] send: stats
+2024-04-14 07:32:19,298 DEBUG   HandlerThread:183 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-14 07:32:19,298 DEBUG   SenderThread:183 [sender.py:send_request():406] send_request: stop_status
+2024-04-14 07:32:19,301 DEBUG   HandlerThread:183 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-14 07:32:20,138 INFO    Thread-12 :183 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240414_073117-xuqlocdo/files/output.log
+2024-04-14 07:32:20,418 DEBUG   HandlerThread:183 [handler.py:handle_request():146] handle_request: status_report
+2024-04-14 07:32:21,138 INFO    Thread-12 :183 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240414_073117-xuqlocdo/files/config.yaml
+2024-04-14 07:32:25,504 DEBUG   HandlerThread:183 [handler.py:handle_request():146] handle_request: status_report
+2024-04-14 07:32:30,505 DEBUG   HandlerThread:183 [handler.py:handle_request():146] handle_request: status_report
+2024-04-14 07:32:34,298 DEBUG   HandlerThread:183 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-14 07:32:34,299 DEBUG   SenderThread:183 [sender.py:send_request():406] send_request: stop_status
+2024-04-14 07:32:34,338 DEBUG   HandlerThread:183 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-14 07:32:36,378 DEBUG   HandlerThread:183 [handler.py:handle_request():146] handle_request: status_report
+2024-04-14 07:32:38,751 DEBUG   HandlerThread:183 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-14 07:32:38,753 DEBUG   SenderThread:183 [sender.py:send():379] send: history
+2024-04-14 07:32:38,753 DEBUG   SenderThread:183 [sender.py:send_request():406] send_request: summary_record
+2024-04-14 07:32:38,753 INFO    SenderThread:183 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-14 07:32:39,145 INFO    Thread-12 :183 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240414_073117-xuqlocdo/files/wandb-summary.json