sharukat commited on
Commit
a57c9b2
·
verified ·
1 Parent(s): b341324

Training in progress, epoch 5

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a22a4c92bbf3913b0c34c960c4459c97dcd8c04f67f6b1ce1e321329097633e7
3
  size 502675828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9447ecdb08c2719f42af83b0d505b8d1d0ad1d2c0029dfcf82cc87a88e9f300e
3
  size 502675828
runs/Mar06_14-59-58_41759fa8e6ad/events.out.tfevents.1709737199.41759fa8e6ad.34.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c13270d753577a6b526afe9d18f1a90d706f21e6e8131ba9f2e77ded1722f291
3
- size 7874
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49645dcae605860e30db72adaeaa0966d4bae72b1ce9c5de95f727bdc4c250c1
3
+ size 8557
wandb/debug-internal.log CHANGED
@@ -465,3 +465,34 @@
465
  2024-03-06 15:02:28,791 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
466
  2024-03-06 15:02:30,283 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
467
  2024-03-06 15:02:31,123 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
465
  2024-03-06 15:02:28,791 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
466
  2024-03-06 15:02:30,283 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
467
  2024-03-06 15:02:31,123 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
468
+ 2024-03-06 15:02:33,792 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
469
+ 2024-03-06 15:02:35,284 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
470
+ 2024-03-06 15:02:36,124 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
471
+ 2024-03-06 15:02:38,793 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
472
+ 2024-03-06 15:02:40,285 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
473
+ 2024-03-06 15:02:41,126 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
474
+ 2024-03-06 15:02:41,912 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: partial_history
475
+ 2024-03-06 15:02:41,913 DEBUG SenderThread:137 [sender.py:send():382] send: history
476
+ 2024-03-06 15:02:41,914 DEBUG SenderThread:137 [sender.py:send_request():409] send_request: summary_record
477
+ 2024-03-06 15:02:41,914 INFO SenderThread:137 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
478
+ 2024-03-06 15:02:41,917 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
479
+ 2024-03-06 15:02:43,028 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: partial_history
480
+ 2024-03-06 15:02:43,029 DEBUG SenderThread:137 [sender.py:send():382] send: history
481
+ 2024-03-06 15:02:43,029 DEBUG SenderThread:137 [sender.py:send_request():409] send_request: summary_record
482
+ 2024-03-06 15:02:43,030 INFO SenderThread:137 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
483
+ 2024-03-06 15:02:43,918 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
484
+ 2024-03-06 15:02:44,031 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
485
+ 2024-03-06 15:02:45,286 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
486
+ 2024-03-06 15:02:45,919 INFO Thread-18 :137 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240306_145455-h1uv5tyi/files/output.log
487
+ 2024-03-06 15:02:46,341 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
488
+ 2024-03-06 15:02:46,342 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
489
+ 2024-03-06 15:02:49,032 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
490
+ 2024-03-06 15:02:50,286 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
491
+ 2024-03-06 15:02:51,344 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
492
+ 2024-03-06 15:02:54,033 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
493
+ 2024-03-06 15:02:55,287 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
494
+ 2024-03-06 15:02:56,345 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
495
+ 2024-03-06 15:02:56,791 DEBUG SenderThread:137 [sender.py:send():382] send: stats
496
+ 2024-03-06 15:02:59,792 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
497
+ 2024-03-06 15:03:00,288 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
498
+ 2024-03-06 15:03:01,347 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
wandb/run-20240306_145424-trm7fvg4/logs/debug-internal.log CHANGED
@@ -516,3 +516,34 @@ wandb.errors.AuthenticationError: The API key you provided is either invalid or
516
  2024-03-06 15:02:28,791 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
517
  2024-03-06 15:02:30,283 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
518
  2024-03-06 15:02:31,123 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
516
  2024-03-06 15:02:28,791 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
517
  2024-03-06 15:02:30,283 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
518
  2024-03-06 15:02:31,123 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
519
+ 2024-03-06 15:02:33,792 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
520
+ 2024-03-06 15:02:35,284 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
521
+ 2024-03-06 15:02:36,124 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
522
+ 2024-03-06 15:02:38,793 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
523
+ 2024-03-06 15:02:40,285 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
524
+ 2024-03-06 15:02:41,126 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
525
+ 2024-03-06 15:02:41,912 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: partial_history
526
+ 2024-03-06 15:02:41,913 DEBUG SenderThread:137 [sender.py:send():382] send: history
527
+ 2024-03-06 15:02:41,914 DEBUG SenderThread:137 [sender.py:send_request():409] send_request: summary_record
528
+ 2024-03-06 15:02:41,914 INFO SenderThread:137 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
529
+ 2024-03-06 15:02:41,917 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
530
+ 2024-03-06 15:02:43,028 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: partial_history
531
+ 2024-03-06 15:02:43,029 DEBUG SenderThread:137 [sender.py:send():382] send: history
532
+ 2024-03-06 15:02:43,029 DEBUG SenderThread:137 [sender.py:send_request():409] send_request: summary_record
533
+ 2024-03-06 15:02:43,030 INFO SenderThread:137 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
534
+ 2024-03-06 15:02:43,918 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
535
+ 2024-03-06 15:02:44,031 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
536
+ 2024-03-06 15:02:45,286 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
537
+ 2024-03-06 15:02:45,919 INFO Thread-18 :137 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240306_145455-h1uv5tyi/files/output.log
538
+ 2024-03-06 15:02:46,341 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
539
+ 2024-03-06 15:02:46,342 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
540
+ 2024-03-06 15:02:49,032 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
541
+ 2024-03-06 15:02:50,286 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
542
+ 2024-03-06 15:02:51,344 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
543
+ 2024-03-06 15:02:54,033 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
544
+ 2024-03-06 15:02:55,287 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
545
+ 2024-03-06 15:02:56,345 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
546
+ 2024-03-06 15:02:56,791 DEBUG SenderThread:137 [sender.py:send():382] send: stats
547
+ 2024-03-06 15:02:59,792 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
548
+ 2024-03-06 15:03:00,288 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
549
+ 2024-03-06 15:03:01,347 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
wandb/run-20240306_145455-h1uv5tyi/files/output.log CHANGED
@@ -23,3 +23,6 @@ Checkpoint destination directory /kaggle/working/checkpoint-124 already exists a
23
  Checkpoint destination directory /kaggle/working/checkpoint-186 already exists and is non-empty. Saving will proceed but saved results may be invalid.
24
  /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.
25
  _warn_prf(average, modifier, msg_start, len(result))
 
 
 
 
23
  Checkpoint destination directory /kaggle/working/checkpoint-186 already exists and is non-empty. Saving will proceed but saved results may be invalid.
24
  /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.
25
  _warn_prf(average, modifier, msg_start, len(result))
26
+ Checkpoint destination directory /kaggle/working/checkpoint-248 already exists and is non-empty. Saving will proceed but saved results may be invalid.
27
+ /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.
28
+ _warn_prf(average, modifier, msg_start, len(result))
wandb/run-20240306_145455-h1uv5tyi/files/wandb-summary.json CHANGED
@@ -1 +1 @@
1
- {"train/loss": 1.6957, "train/grad_norm": 11.199089050292969, "train/learning_rate": 6.016129032258065e-06, "train/epoch": 4.0, "train/global_step": 248, "_timestamp": 1709737329.7935672, "_runtime": 434.07481026649475, "_step": 19, "eval/loss": 1.7372241020202637, "eval/accuracy": 0.36363636363636365, "eval/precision": 0.2310160427807487, "eval/recall": 0.36363636363636365, "eval/f1": 0.23220779220779222, "eval/runtime": 1.1099, "eval/samples_per_second": 49.555, "eval/steps_per_second": 6.307, "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}
 
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}
wandb/run-20240306_145455-h1uv5tyi/logs/debug-internal.log CHANGED
@@ -465,3 +465,34 @@
465
  2024-03-06 15:02:28,791 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
466
  2024-03-06 15:02:30,283 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
467
  2024-03-06 15:02:31,123 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
465
  2024-03-06 15:02:28,791 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
466
  2024-03-06 15:02:30,283 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
467
  2024-03-06 15:02:31,123 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
468
+ 2024-03-06 15:02:33,792 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
469
+ 2024-03-06 15:02:35,284 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
470
+ 2024-03-06 15:02:36,124 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
471
+ 2024-03-06 15:02:38,793 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
472
+ 2024-03-06 15:02:40,285 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
473
+ 2024-03-06 15:02:41,126 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
474
+ 2024-03-06 15:02:41,912 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: partial_history
475
+ 2024-03-06 15:02:41,913 DEBUG SenderThread:137 [sender.py:send():382] send: history
476
+ 2024-03-06 15:02:41,914 DEBUG SenderThread:137 [sender.py:send_request():409] send_request: summary_record
477
+ 2024-03-06 15:02:41,914 INFO SenderThread:137 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
478
+ 2024-03-06 15:02:41,917 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
479
+ 2024-03-06 15:02:43,028 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: partial_history
480
+ 2024-03-06 15:02:43,029 DEBUG SenderThread:137 [sender.py:send():382] send: history
481
+ 2024-03-06 15:02:43,029 DEBUG SenderThread:137 [sender.py:send_request():409] send_request: summary_record
482
+ 2024-03-06 15:02:43,030 INFO SenderThread:137 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
483
+ 2024-03-06 15:02:43,918 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
484
+ 2024-03-06 15:02:44,031 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
485
+ 2024-03-06 15:02:45,286 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
486
+ 2024-03-06 15:02:45,919 INFO Thread-18 :137 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240306_145455-h1uv5tyi/files/output.log
487
+ 2024-03-06 15:02:46,341 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
488
+ 2024-03-06 15:02:46,342 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
489
+ 2024-03-06 15:02:49,032 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
490
+ 2024-03-06 15:02:50,286 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
491
+ 2024-03-06 15:02:51,344 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
492
+ 2024-03-06 15:02:54,033 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
493
+ 2024-03-06 15:02:55,287 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
494
+ 2024-03-06 15:02:56,345 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive
495
+ 2024-03-06 15:02:56,791 DEBUG SenderThread:137 [sender.py:send():382] send: stats
496
+ 2024-03-06 15:02:59,792 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
497
+ 2024-03-06 15:03:00,288 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: status_report
498
+ 2024-03-06 15:03:01,347 DEBUG HandlerThread:137 [handler.py:handle_request():146] handle_request: keepalive