Training in progress, step 60

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74b7042625fdf29a6faf48f0128dac77e815518769da2c364416136e5fdbde7b
+oid sha256:270f7a985c38ef87d3b0c62d407b8c8e1e8a69c4b0b3fcff9cbdaefb08b99e6e
 size 8077608

runs/Apr12_07-27-33_e5a48bec8248/events.out.tfevents.1712906854.e5a48bec8248.174.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1d75a3b7bbc52718236b34de3263fa30c63c7a56375f0130decebec5810d44f
-size 5693
+oid sha256:c80e9ac1748eb532a27799485f3445ff2306a8a9053c07297abe76ca727a053a
+size 6248

wandb/debug-internal.log

@@ -85,3 +85,26 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 07:28:08,201 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
 2024-04-12 07:28:08,202 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
 2024-04-12 07:28:08,314 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:28:09,041 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/config.yaml
+2024-04-12 07:28:10,041 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/output.log
+2024-04-12 07:28:13,125 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:28:13,126 DEBUG   SenderThread:216 [sender.py:send():379] send: history
+2024-04-12 07:28:13,126 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:28:13,128 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:28:13,806 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:28:13,807 DEBUG   SenderThread:216 [sender.py:send():379] send: telemetry
+2024-04-12 07:28:13,807 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:28:13,807 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:28:13,808 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:28:13,809 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:28:13,809 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:28:13,809 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:28:13,810 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:28:13,810 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:28:13,810 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:28:13,811 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:28:13,811 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:28:13,812 DEBUG   SenderThread:216 [sender.py:send():379] send: history
+2024-04-12 07:28:13,812 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:28:13,812 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:28:14,043 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/wandb-summary.json

wandb/run-20240412_072736-gyl3aena/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-20240412_072736-gyl3aena/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 4.5269, "train/grad_norm": 248.84193420410156, "train/learning_rate": 7.97387338950315e-06, "train/epoch": 0.0, "train/global_step": 40, "_timestamp": 1712906886.8470142, "_runtime": 30.214935302734375, "_step": 1}
+{"train/loss": 4.8386, "train/grad_norm": 73.25434112548828, "train/learning_rate": 0.0, "train/epoch": 0.0, "train/global_step": 60, "_timestamp": 1712906893.8035388, "_runtime": 37.171459913253784, "_step": 3, "train_runtime": 39.0078, "train_samples_per_second": 3.076, "train_steps_per_second": 1.538, "total_flos": 19812939669504.0, "train_loss": 4.6811678568522135}

wandb/run-20240412_072736-gyl3aena/logs/debug-internal.log

@@ -85,3 +85,26 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-12 07:28:08,201 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: stop_status
 2024-04-12 07:28:08,202 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: internal_messages
 2024-04-12 07:28:08,314 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: stop_status
+2024-04-12 07:28:09,041 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/config.yaml
+2024-04-12 07:28:10,041 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/output.log
+2024-04-12 07:28:13,125 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:28:13,126 DEBUG   SenderThread:216 [sender.py:send():379] send: history
+2024-04-12 07:28:13,126 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:28:13,128 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:28:13,806 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-12 07:28:13,807 DEBUG   SenderThread:216 [sender.py:send():379] send: telemetry
+2024-04-12 07:28:13,807 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:28:13,807 DEBUG   HandlerThread:216 [handler.py:handle_request():146] handle_request: status_report
+2024-04-12 07:28:13,808 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:28:13,809 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:28:13,809 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:28:13,809 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:28:13,810 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:28:13,810 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:28:13,810 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:28:13,811 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:28:13,811 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:28:13,812 DEBUG   SenderThread:216 [sender.py:send():379] send: history
+2024-04-12 07:28:13,812 DEBUG   SenderThread:216 [sender.py:send_request():406] send_request: summary_record
+2024-04-12 07:28:13,812 INFO    SenderThread:216 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-12 07:28:14,043 INFO    Thread-12 :216 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240412_072736-gyl3aena/files/wandb-summary.json