Training in progress, epoch 6

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9447ecdb08c2719f42af83b0d505b8d1d0ad1d2c0029dfcf82cc87a88e9f300e
+oid sha256:aa4e636578a89d52fa8a79b790d5fbae475d52c5002e01cc9ca1bad925a5a52a
 size 502675828

runs/Mar06_14-59-58_41759fa8e6ad/events.out.tfevents.1709737199.41759fa8e6ad.34.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49645dcae605860e30db72adaeaa0966d4bae72b1ce9c5de95f727bdc4c250c1
-size 8557
+oid sha256:b50afec718284985d69f44e0a7adf4cd6aebf6a9d3c4d4b7f24370571c666aa7
+size 9240

wandb/debug-internal.log

@@ -496,3 +496,33 @@
 2024-03-06 15:02:59,792 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
 2024-03-06 15:03:00,288 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
 2024-03-06 15:03:01,347 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:03:04,793 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:05,289 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:06,347 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:03:09,794 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:10,290 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:11,349 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:03:14,795 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:15,152 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: partial_history
+2024-03-06 15:03:15,153 DEBUG   SenderThread:137 [sender.py:send():382] send: history
+2024-03-06 15:03:15,154 DEBUG   SenderThread:137 [sender.py:send_request():409] send_request: summary_record
+2024-03-06 15:03:15,154 INFO    SenderThread:137 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
+2024-03-06 15:03:15,291 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:15,931 INFO    Thread-18 :137 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240306_145455-h1uv5tyi/files/wandb-summary.json
+2024-03-06 15:03:16,264 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: partial_history
+2024-03-06 15:03:16,265 DEBUG   SenderThread:137 [sender.py:send():382] send: history
+2024-03-06 15:03:16,266 DEBUG   SenderThread:137 [sender.py:send_request():409] send_request: summary_record
+2024-03-06 15:03:16,267 INFO    SenderThread:137 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
+2024-03-06 15:03:16,350 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:03:16,931 INFO    Thread-18 :137 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240306_145455-h1uv5tyi/files/wandb-summary.json
+2024-03-06 15:03:17,931 INFO    Thread-18 :137 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240306_145455-h1uv5tyi/files/output.log
+2024-03-06 15:03:20,268 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:20,291 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:21,486 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:03:25,269 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:25,292 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:26,487 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:03:26,792 DEBUG   SenderThread:137 [sender.py:send():382] send: stats
+2024-03-06 15:03:30,293 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:30,793 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:31,488 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive

wandb/run-20240306_145424-trm7fvg4/logs/debug-internal.log

@@ -547,3 +547,33 @@ wandb.errors.AuthenticationError: The API key you provided is either invalid or
 2024-03-06 15:02:59,792 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
 2024-03-06 15:03:00,288 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
 2024-03-06 15:03:01,347 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:03:04,793 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:05,289 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:06,347 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:03:09,794 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:10,290 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:11,349 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:03:14,795 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:15,152 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: partial_history
+2024-03-06 15:03:15,153 DEBUG   SenderThread:137 [sender.py:send():382] send: history
+2024-03-06 15:03:15,154 DEBUG   SenderThread:137 [sender.py:send_request():409] send_request: summary_record
+2024-03-06 15:03:15,154 INFO    SenderThread:137 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
+2024-03-06 15:03:15,291 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:15,931 INFO    Thread-18 :137 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240306_145455-h1uv5tyi/files/wandb-summary.json
+2024-03-06 15:03:16,264 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: partial_history
+2024-03-06 15:03:16,265 DEBUG   SenderThread:137 [sender.py:send():382] send: history
+2024-03-06 15:03:16,266 DEBUG   SenderThread:137 [sender.py:send_request():409] send_request: summary_record
+2024-03-06 15:03:16,267 INFO    SenderThread:137 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
+2024-03-06 15:03:16,350 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:03:16,931 INFO    Thread-18 :137 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240306_145455-h1uv5tyi/files/wandb-summary.json
+2024-03-06 15:03:17,931 INFO    Thread-18 :137 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240306_145455-h1uv5tyi/files/output.log
+2024-03-06 15:03:20,268 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:20,291 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:21,486 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:03:25,269 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:25,292 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:26,487 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:03:26,792 DEBUG   SenderThread:137 [sender.py:send():382] send: stats
+2024-03-06 15:03:30,293 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:30,793 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:31,488 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive

wandb/run-20240306_145455-h1uv5tyi/files/output.log

@@ -26,3 +26,5 @@ Checkpoint destination directory /kaggle/working/checkpoint-186 already exists a
 Checkpoint destination directory /kaggle/working/checkpoint-248 already exists and is non-empty. Saving will proceed but saved results may be invalid.
 /opt/conda/lib/python3.10/site-packages/sklearn/metrics/_classification.py:1344: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
   _warn_prf(average, modifier, msg_start, len(result))
+Checkpoint destination directory /kaggle/working/checkpoint-310 already exists and is non-empty. Saving will proceed but saved results may be invalid.
+/opt/conda/lib/python3.10/site-packages/sklearn/metrics/_classification.py:1344: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.

wandb/run-20240306_145455-h1uv5tyi/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 1.662, "train/grad_norm": 10.58697509765625, "train/learning_rate": 5.032258064516129e-06, "train/epoch": 5.0, "train/global_step": 310, "_timestamp": 1709737363.0277505, "_runtime": 467.30899357795715, "_step": 21, "eval/loss": 1.7386547327041626, "eval/accuracy": 0.32727272727272727, "eval/precision": 0.17372627372627372, "eval/recall": 0.32727272727272727, "eval/f1": 0.22225931445603578, "eval/runtime": 1.1117, "eval/samples_per_second": 49.474, "eval/steps_per_second": 6.297, "train/train_runtime": 237.4526, "train/train_samples_per_second": 10.339, "train/train_steps_per_second": 1.306, "train/total_flos": 645966638976000.0, "train/train_loss": 1.7031736066264491}
+{"train/loss": 1.6727, "train/grad_norm": 14.989230155944824, "train/learning_rate": 4.032258064516129e-06, "train/epoch": 6.0, "train/global_step": 372, "_timestamp": 1709737396.2640631, "_runtime": 500.5453062057495, "_step": 23, "eval/loss": 1.7222378253936768, "eval/accuracy": 0.38181818181818183, "eval/precision": 0.2246376811594203, "eval/recall": 0.38181818181818183, "eval/f1": 0.2638161838161838, "eval/runtime": 1.1081, "eval/samples_per_second": 49.633, "eval/steps_per_second": 6.317, "train/train_runtime": 237.4526, "train/train_samples_per_second": 10.339, "train/train_steps_per_second": 1.306, "train/total_flos": 645966638976000.0, "train/train_loss": 1.7031736066264491}

wandb/run-20240306_145455-h1uv5tyi/logs/debug-internal.log

@@ -496,3 +496,33 @@
 2024-03-06 15:02:59,792 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
 2024-03-06 15:03:00,288 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
 2024-03-06 15:03:01,347 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:03:04,793 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:05,289 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:06,347 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:03:09,794 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:10,290 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:11,349 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:03:14,795 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:15,152 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: partial_history
+2024-03-06 15:03:15,153 DEBUG   SenderThread:137 [sender.py:send():382] send: history
+2024-03-06 15:03:15,154 DEBUG   SenderThread:137 [sender.py:send_request():409] send_request: summary_record
+2024-03-06 15:03:15,154 INFO    SenderThread:137 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
+2024-03-06 15:03:15,291 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:15,931 INFO    Thread-18 :137 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240306_145455-h1uv5tyi/files/wandb-summary.json
+2024-03-06 15:03:16,264 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: partial_history
+2024-03-06 15:03:16,265 DEBUG   SenderThread:137 [sender.py:send():382] send: history
+2024-03-06 15:03:16,266 DEBUG   SenderThread:137 [sender.py:send_request():409] send_request: summary_record
+2024-03-06 15:03:16,267 INFO    SenderThread:137 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
+2024-03-06 15:03:16,350 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:03:16,931 INFO    Thread-18 :137 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240306_145455-h1uv5tyi/files/wandb-summary.json
+2024-03-06 15:03:17,931 INFO    Thread-18 :137 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240306_145455-h1uv5tyi/files/output.log
+2024-03-06 15:03:20,268 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:20,291 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:21,486 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:03:25,269 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:25,292 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:26,487 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:03:26,792 DEBUG   SenderThread:137 [sender.py:send():382] send: stats
+2024-03-06 15:03:30,293 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:30,793 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:03:31,488 DEBUG   HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive