Auto upload zain 2026-08-12T22:45:12.055248 (part 3)

.gitattributes

@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 zain/Activation/wandb/run-20260812_213624-1sryr5l2/run-1sryr5l2.wandb filter=lfs diff=lfs merge=lfs -text
 zain/Activation/wandb/run-20260812_220132-25l266uo/run-25l266uo.wandb filter=lfs diff=lfs merge=lfs -text
 zain/Activation/wandb/run-20260812_222758-48ajimfv/run-48ajimfv.wandb filter=lfs diff=lfs merge=lfs -text
+zain/Activation/wandb/run-20260812_224111-g6mesp08/run-g6mesp08.wandb filter=lfs diff=lfs merge=lfs -text

zain/Activation/wandb/debug-internal.log

@@ -1,105 +1,41 @@
-{"time":"2026-08-12T22:27:58.581647086Z","level":"INFO","msg":"wandb-core"}
-{"time":"2026-08-12T22:27:58.581784642Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
-{"time":"2026-08-12T22:27:58.842385208Z","level":"INFO","msg":"stream: created new stream","id":"48ajimfv"}
-{"time":"2026-08-12T22:27:58.842475883Z","level":"INFO","msg":"handler: started"}
-{"time":"2026-08-12T22:27:58.842569075Z","level":"INFO","msg":"stream: started"}
-{"time":"2026-08-12T22:27:58.842581831Z","level":"INFO","msg":"writer: started","stream_id":"48ajimfv"}
-{"time":"2026-08-12T22:27:58.842610731Z","level":"INFO","msg":"sender: started"}
-{"time":"2026-08-12T22:27:59.429967503Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
-{"time":"2026-08-12T22:27:59.538155968Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:28:14.430500858Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":2,"events_offset":0,"events_lines":2,"console_offset":1,"console_lines":4,"uploaded_len":2}
-{"time":"2026-08-12T22:28:14.590492483Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:28:29.430749436Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":2,"history_lines":3,"events_offset":2,"events_lines":2,"console_offset":2,"console_lines":1}
-{"time":"2026-08-12T22:28:29.675445625Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:28:44.430753756Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":5,"history_lines":2,"events_offset":4,"events_lines":2,"console_offset":5,"console_lines":10}
-{"time":"2026-08-12T22:28:44.557251158Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:28:59.430449719Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":7,"history_lines":3,"events_offset":6,"events_lines":2,"console_offset":12,"console_lines":1}
-{"time":"2026-08-12T22:28:59.594468323Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:29:14.430319434Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":10,"history_lines":2,"events_offset":8,"events_lines":2,"console_offset":15,"console_lines":10}
-{"time":"2026-08-12T22:29:14.600270868Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:29:29.430789603Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":12,"history_lines":3,"events_offset":10,"events_lines":2,"console_offset":22,"console_lines":1}
-{"time":"2026-08-12T22:29:29.570324278Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:29:44.430836772Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":15,"history_lines":2,"events_offset":12,"events_lines":2,"console_offset":25,"console_lines":10}
-{"time":"2026-08-12T22:29:44.551059141Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:29:59.430699061Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":17,"history_lines":3,"events_offset":14,"events_lines":2,"console_offset":32,"console_lines":1}
-{"time":"2026-08-12T22:29:59.602847748Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:30:14.430251686Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":20,"history_lines":2,"events_offset":16,"events_lines":2,"console_offset":35,"console_lines":10}
-{"time":"2026-08-12T22:30:14.629116836Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:30:29.430421653Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":22,"history_lines":3,"events_offset":18,"events_lines":2,"console_offset":42,"console_lines":1}
-{"time":"2026-08-12T22:30:29.610315234Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:30:44.431117557Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":25,"history_lines":2,"events_offset":20,"events_lines":2,"console_offset":45,"console_lines":10}
-{"time":"2026-08-12T22:30:44.558198864Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:30:59.430060367Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":27,"history_lines":3,"events_offset":22,"events_lines":2,"console_offset":52,"console_lines":1}
-{"time":"2026-08-12T22:30:59.630889644Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:31:14.431923193Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":30,"history_lines":2,"events_offset":24,"events_lines":2,"console_offset":55,"console_lines":10}
-{"time":"2026-08-12T22:31:14.604177028Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:31:29.430439724Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":32,"history_lines":3,"events_offset":26,"events_lines":2,"console_offset":62,"console_lines":1}
-{"time":"2026-08-12T22:31:29.586624722Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:31:44.430331188Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":35,"history_lines":3,"events_offset":28,"events_lines":2,"console_offset":65,"console_lines":11}
-{"time":"2026-08-12T22:31:44.559438165Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:31:59.430802062Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":38,"history_lines":2,"events_offset":30,"events_lines":2,"console_offset":72,"console_lines":1}
-{"time":"2026-08-12T22:31:59.603175279Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:32:14.430686862Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":40,"history_lines":3,"events_offset":32,"events_lines":2,"console_offset":76,"console_lines":10}
-{"time":"2026-08-12T22:32:14.700048748Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:32:29.43068693Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":43,"history_lines":2,"events_offset":34,"events_lines":2,"console_offset":82,"console_lines":1}
-{"time":"2026-08-12T22:32:29.663608478Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:32:44.430687397Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":45,"history_lines":3,"events_offset":36,"events_lines":2,"console_offset":86,"console_lines":10}
-{"time":"2026-08-12T22:32:44.567924744Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:32:59.431036431Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":48,"history_lines":2,"events_offset":38,"events_lines":2,"console_offset":92,"console_lines":1}
-{"time":"2026-08-12T22:32:59.599734812Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:33:14.43031999Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":50,"history_lines":3,"events_offset":40,"events_lines":2,"console_offset":96,"console_lines":10}
-{"time":"2026-08-12T22:33:14.631805831Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:33:29.430807862Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":53,"history_lines":2,"events_offset":42,"events_lines":2,"console_offset":102,"console_lines":1}
-{"time":"2026-08-12T22:33:29.654336317Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:33:44.431064377Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":55,"history_lines":3,"events_offset":44,"events_lines":2,"console_offset":106,"console_lines":10}
-{"time":"2026-08-12T22:33:44.557936576Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:33:59.430970703Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":58,"history_lines":2,"events_offset":46,"events_lines":2,"console_offset":112,"console_lines":1}
-{"time":"2026-08-12T22:33:59.610842304Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:34:14.430943029Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":60,"history_lines":3,"events_offset":48,"events_lines":2,"console_offset":116,"console_lines":10}
-{"time":"2026-08-12T22:34:14.712593897Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:34:29.430284726Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":63,"history_lines":3,"events_offset":50,"events_lines":2,"console_offset":122,"console_lines":1}
-{"time":"2026-08-12T22:34:29.567234039Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:34:44.430996463Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":66,"history_lines":2,"events_offset":52,"events_lines":2,"console_offset":126,"console_lines":10}
-{"time":"2026-08-12T22:34:44.686780359Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:34:59.430551639Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":68,"history_lines":3,"events_offset":54,"events_lines":2,"console_offset":132,"console_lines":1}
-{"time":"2026-08-12T22:34:59.544787249Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:35:14.430617626Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":71,"history_lines":2,"events_offset":56,"events_lines":2,"console_offset":136,"console_lines":10}
-{"time":"2026-08-12T22:35:14.666107485Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:35:29.431525173Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":73,"history_lines":3,"events_offset":58,"events_lines":2,"console_offset":142,"console_lines":1}
-{"time":"2026-08-12T22:35:29.56558724Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:35:44.430379118Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":76,"history_lines":2,"events_offset":60,"events_lines":2,"console_offset":146,"console_lines":10}
-{"time":"2026-08-12T22:35:44.559977178Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:35:59.431032641Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":78,"history_lines":3,"events_offset":62,"events_lines":2,"console_offset":152,"console_lines":1}
-{"time":"2026-08-12T22:35:59.714328043Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:36:14.431039076Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":81,"history_lines":2,"events_offset":64,"events_lines":2,"console_offset":156,"console_lines":10}
-{"time":"2026-08-12T22:36:14.732414261Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:36:29.430999309Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":83,"history_lines":3,"events_offset":66,"events_lines":2,"console_offset":162,"console_lines":1}
-{"time":"2026-08-12T22:36:29.553153666Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:36:44.430730505Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":86,"history_lines":2,"events_offset":68,"events_lines":2,"console_offset":166,"console_lines":10}
-{"time":"2026-08-12T22:36:44.621594715Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:36:59.430441228Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":88,"history_lines":3,"events_offset":70,"events_lines":2,"console_offset":172,"console_lines":1}
-{"time":"2026-08-12T22:36:59.560670992Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:37:14.430659368Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":91,"history_lines":2,"events_offset":72,"events_lines":2,"console_offset":176,"console_lines":10}
-{"time":"2026-08-12T22:37:14.646954413Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:37:29.430134791Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":93,"history_lines":3,"events_offset":74,"events_lines":2,"console_offset":182,"console_lines":1}
-{"time":"2026-08-12T22:37:29.561119001Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:37:44.430646454Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":96,"history_lines":2,"events_offset":76,"events_lines":2,"console_offset":186,"console_lines":10}
-{"time":"2026-08-12T22:37:44.743578441Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:37:59.430259631Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":98,"history_lines":3,"events_offset":78,"events_lines":2,"console_offset":192,"console_lines":1}
-{"time":"2026-08-12T22:37:59.72116865Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:38:14.430863751Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":101,"history_lines":2,"events_offset":80,"events_lines":2,"console_offset":196,"console_lines":10}
-{"time":"2026-08-12T22:38:14.844933267Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:38:29.430786733Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":103,"history_lines":3,"events_offset":82,"events_lines":2,"console_offset":202,"console_lines":1}
-{"time":"2026-08-12T22:38:29.717980384Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:38:44.430325914Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":106,"history_lines":2,"events_offset":84,"events_lines":2,"console_offset":206,"console_lines":10}
-{"time":"2026-08-12T22:38:44.644908382Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:38:59.430622651Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":108,"history_lines":3,"events_offset":86,"events_lines":2,"console_offset":212,"console_lines":1}
-{"time":"2026-08-12T22:38:59.755414674Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:39:14.430626349Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":111,"history_lines":2,"events_offset":88,"events_lines":2,"console_offset":216,"console_lines":10}
-{"time":"2026-08-12T22:39:14.69724536Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:39:29.430519211Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":113,"history_lines":3,"events_offset":90,"events_lines":2,"console_offset":222,"console_lines":1}
-{"time":"2026-08-12T22:39:29.708983107Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:39:44.430486853Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":116,"history_lines":2,"events_offset":92,"events_lines":2,"console_offset":226,"console_lines":10}
-{"time":"2026-08-12T22:39:44.740657985Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-12T22:39:59.430983472Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":118,"history_lines":3,"events_offset":94,"events_lines":2,"console_offset":232,"console_lines":1}
-{"time":"2026-08-12T22:39:59.794369716Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:41:11.169747831Z","level":"INFO","msg":"wandb-core"}
+{"time":"2026-08-12T22:41:11.169891384Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
+{"time":"2026-08-12T22:41:11.430196954Z","level":"INFO","msg":"stream: created new stream","id":"g6mesp08"}
+{"time":"2026-08-12T22:41:11.430285757Z","level":"INFO","msg":"handler: started"}
+{"time":"2026-08-12T22:41:11.430381897Z","level":"INFO","msg":"stream: started"}
+{"time":"2026-08-12T22:41:11.430391581Z","level":"INFO","msg":"writer: started","stream_id":"g6mesp08"}
+{"time":"2026-08-12T22:41:11.430426905Z","level":"INFO","msg":"sender: started"}
+{"time":"2026-08-12T22:41:12.662303161Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
+{"time":"2026-08-12T22:41:12.751702232Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:41:27.663146362Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":2,"events_offset":0,"events_lines":2,"console_offset":0,"console_lines":3,"uploaded_len":2}
+{"time":"2026-08-12T22:41:27.775246965Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:41:42.662511534Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":2,"history_lines":2,"events_offset":2,"events_lines":2,"console_offset":0,"console_lines":1}
+{"time":"2026-08-12T22:41:42.783128036Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:41:57.662469694Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":4,"history_lines":3,"events_offset":4,"events_lines":2,"console_offset":0,"console_lines":1}
+{"time":"2026-08-12T22:41:57.779250604Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:42:12.663142839Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":7,"history_lines":2,"events_offset":6,"events_lines":2,"console_offset":3,"console_lines":12}
+{"time":"2026-08-12T22:42:12.847678714Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:42:27.662713702Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":9,"history_lines":2,"events_offset":8,"events_lines":2,"console_offset":10,"console_lines":1}
+{"time":"2026-08-12T22:42:27.802355946Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:42:42.663234627Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":11,"history_lines":3,"events_offset":10,"events_lines":2,"console_offset":15,"console_lines":10}
+{"time":"2026-08-12T22:42:42.77804022Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:42:57.66297082Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":14,"history_lines":2,"events_offset":12,"events_lines":2,"console_offset":20,"console_lines":1}
+{"time":"2026-08-12T22:42:57.799831047Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:43:12.662546129Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":16,"history_lines":2,"events_offset":14,"events_lines":2,"console_offset":25,"console_lines":9}
+{"time":"2026-08-12T22:43:12.83962087Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:43:27.66341876Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":18,"history_lines":3,"events_offset":16,"events_lines":2,"console_offset":30,"console_lines":1}
+{"time":"2026-08-12T22:43:27.792335861Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:43:42.663310497Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":21,"history_lines":2,"events_offset":18,"events_lines":2,"console_offset":34,"console_lines":10}
+{"time":"2026-08-12T22:43:42.799978026Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:43:57.662859749Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":23,"history_lines":2,"events_offset":20,"events_lines":2,"console_offset":40,"console_lines":1}
+{"time":"2026-08-12T22:43:57.805772287Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:44:12.663349352Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":25,"history_lines":3,"events_offset":22,"events_lines":2,"console_offset":44,"console_lines":10}
+{"time":"2026-08-12T22:44:12.808003723Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:44:27.66277157Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":28,"history_lines":2,"events_offset":24,"events_lines":2,"console_offset":50,"console_lines":1}
+{"time":"2026-08-12T22:44:27.784839934Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:44:42.662822837Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":30,"history_lines":2,"events_offset":26,"events_lines":2,"console_offset":54,"console_lines":9}
+{"time":"2026-08-12T22:44:42.814831858Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:44:57.663067595Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":32,"history_lines":3,"events_offset":28,"events_lines":2,"console_offset":60,"console_lines":1}
+{"time":"2026-08-12T22:44:57.806264315Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:45:12.66281333Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":35,"history_lines":2,"events_offset":30,"events_lines":2,"console_offset":63,"console_lines":10}
+{"time":"2026-08-12T22:45:12.810852756Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}

zain/Activation/wandb/debug.log

@@ -1,23 +1,20 @@
-2026-08-12 22:27:58,579 INFO    MainThread:3978000 [wandb_setup.py:_flush():81] Current SDK version is 0.28.1
-2026-08-12 22:27:58,580 INFO    MainThread:3978000 [wandb_setup.py:_flush():81] Configure stats pid to 3978000
-2026-08-12 22:27:58,580 INFO    MainThread:3978000 [wandb_setup.py:_flush():81] Loading settings from environment variables
-2026-08-12 22:27:58,580 INFO    MainThread:3978000 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_222758-48ajimfv/logs/debug.log
-2026-08-12 22:27:58,580 INFO    MainThread:3978000 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_222758-48ajimfv/logs/debug-internal.log
-2026-08-12 22:27:58,580 INFO    MainThread:3978000 [wandb_init.py:init():772] calling init triggers
-2026-08-12 22:27:58,580 INFO    MainThread:3978000 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
+2026-08-12 22:41:11,168 INFO    MainThread:3978000 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_224111-g6mesp08/logs/debug.log
+2026-08-12 22:41:11,168 INFO    MainThread:3978000 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_224111-g6mesp08/logs/debug-internal.log
+2026-08-12 22:41:11,168 INFO    MainThread:3978000 [wandb_init.py:init():772] calling init triggers
+2026-08-12 22:41:11,168 INFO    MainThread:3978000 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
 config: {'_wandb': {}}
-2026-08-12 22:27:58,580 INFO    MainThread:3978000 [wandb_init.py:init():820] starting backend
-2026-08-12 22:27:58,580 INFO    MainThread:3978000 [wandb_init.py:init():826] Connected to an existing wandb-core service via WANDB_SERVICE
-2026-08-12 22:27:58,580 INFO    MainThread:3978000 [wandb_init.py:init():835] sending inform_init request
-2026-08-12 22:27:58,843 INFO    MainThread:3978000 [wandb_init.py:init():840] backend started and connected
-2026-08-12 22:27:58,846 INFO    MainThread:3978000 [wandb_init.py:init():910] updated telemetry
-2026-08-12 22:27:58,853 INFO    MainThread:3978000 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
-2026-08-12 22:27:59,154 INFO    MainThread:3978000 [wandb_init.py:init():978] starting run threads in backend
-2026-08-12 22:27:59,228 INFO    MainThread:3978000 [wandb_run.py:_console_start():2621] atexit reg
-2026-08-12 22:27:59,228 INFO    MainThread:3978000 [wandb_run.py:_redirect():2471] redirect: wrap_raw
-2026-08-12 22:27:59,228 INFO    MainThread:3978000 [wandb_run.py:_redirect():2540] Wrapping output streams.
-2026-08-12 22:27:59,228 INFO    MainThread:3978000 [wandb_run.py:_redirect():2563] Redirects installed.
-2026-08-12 22:27:59,231 INFO    MainThread:3978000 [wandb_init.py:init():1016] run started, returning control to user process
-2026-08-12 22:27:59,232 INFO    MainThread:3978000 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.16.0.dev0', 'architectures': None, 'output_hidden_states': False, 'return_dict': True, 'dtype': None, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, 'vocab_size': 4096, 'hidden_size': 128, 'intermediate_size': 256, 'num_hidden_layers': 100, 'num_attention_heads': 4, 'num_key_value_heads': 4, 'hidden_act': 'silu', 'max_position_embeddings': 512, 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'pad_token_id': 0, 'bos_token_id': 1, 'eos_token_id': 2, 'pretraining_tp': 1, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 10000.0, 'rope_type': 'default'}, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'head_dim': 32, '_name_or_path': '', 'tokenizer_name': 'w-ahmad/tiny-stories-tokenizer', 'mlp_type': 'glu', 'activation': 'silu-waleed10', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-silu-waleed10-100L_run', 'per_device_train_batch_size': 64, 'num_train_epochs': 1, 'max_steps': 2500, 'learning_rate': 0.0007, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 500, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 1.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-silu-waleed10-100L-16.9M-20260812-222757', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 2498, 'eval_delay': 0, 'per_device_eval_batch_size': 1024, 'prediction_loss_only': False, 'eval_on_start': False, 'eval_do_concat_batches': True, 'eval_use_gather_object': False, 'eval_accumulation_steps': None, 'include_for_metrics': [], 'batch_eval_metrics': False, 'save_only_model': False, 'save_strategy': 'steps', 'save_steps': 100, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/6L-glu-silu-waleed10-100L', 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': None, 'dataloader_multiprocessing_context': None, 'dataloader_in_order': True, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_static_graph': None, 'ddp_backend': None, 'ddp_timeout': 1800, 'fsdp': None, 'fsdp_config': None, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'local_rank': -1}
-2026-08-12 22:27:59,236 INFO    MainThread:3978000 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 16934016 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x14d922561cd0>>
-2026-08-12 22:27:59,236 INFO    MainThread:3978000 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 16934016 None
+2026-08-12 22:41:11,168 INFO    MainThread:3978000 [wandb_init.py:init():820] starting backend
+2026-08-12 22:41:11,168 INFO    MainThread:3978000 [wandb_init.py:init():826] Connected to an existing wandb-core service via WANDB_SERVICE
+2026-08-12 22:41:11,168 INFO    MainThread:3978000 [wandb_init.py:init():835] sending inform_init request
+2026-08-12 22:41:11,430 INFO    MainThread:3978000 [wandb_init.py:init():840] backend started and connected
+2026-08-12 22:41:11,431 INFO    MainThread:3978000 [wandb_init.py:init():910] updated telemetry
+2026-08-12 22:41:11,438 INFO    MainThread:3978000 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
+2026-08-12 22:41:11,946 INFO    MainThread:3978000 [wandb_init.py:init():978] starting run threads in backend
+2026-08-12 22:41:12,023 INFO    MainThread:3978000 [wandb_run.py:_console_start():2621] atexit reg
+2026-08-12 22:41:12,023 INFO    MainThread:3978000 [wandb_run.py:_redirect():2471] redirect: wrap_raw
+2026-08-12 22:41:12,023 INFO    MainThread:3978000 [wandb_run.py:_redirect():2540] Wrapping output streams.
+2026-08-12 22:41:12,023 INFO    MainThread:3978000 [wandb_run.py:_redirect():2563] Redirects installed.
+2026-08-12 22:41:12,024 INFO    MainThread:3978000 [wandb_init.py:init():1016] run started, returning control to user process
+2026-08-12 22:41:12,025 INFO    MainThread:3978000 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.16.0.dev0', 'architectures': None, 'output_hidden_states': False, 'return_dict': True, 'dtype': None, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, 'vocab_size': 4096, 'hidden_size': 128, 'intermediate_size': 256, 'num_hidden_layers': 100, 'num_attention_heads': 4, 'num_key_value_heads': 4, 'hidden_act': 'silu', 'max_position_embeddings': 512, 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'pad_token_id': 0, 'bos_token_id': 1, 'eos_token_id': 2, 'pretraining_tp': 1, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 10000.0, 'rope_type': 'default'}, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'head_dim': 32, '_name_or_path': '', 'tokenizer_name': 'w-ahmad/tiny-stories-tokenizer', 'mlp_type': 'glu', 'activation': 'situglu', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-situglu-100L_run', 'per_device_train_batch_size': 64, 'num_train_epochs': 1, 'max_steps': 2500, 'learning_rate': 0.0007, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 500, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 1.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-situglu-100L-16.9M-20260812-224110', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 2498, 'eval_delay': 0, 'per_device_eval_batch_size': 1024, 'prediction_loss_only': False, 'eval_on_start': False, 'eval_do_concat_batches': True, 'eval_use_gather_object': False, 'eval_accumulation_steps': None, 'include_for_metrics': [], 'batch_eval_metrics': False, 'save_only_model': False, 'save_strategy': 'steps', 'save_steps': 100, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/6L-glu-situglu-100L', 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': None, 'dataloader_multiprocessing_context': None, 'dataloader_in_order': True, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_static_graph': None, 'ddp_backend': None, 'ddp_timeout': 1800, 'fsdp': None, 'fsdp_config': None, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'local_rank': -1}
+2026-08-12 22:41:12,030 INFO    MainThread:3978000 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 16934016 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x14d8f5c68f10>>
+2026-08-12 22:41:12,030 INFO    MainThread:3978000 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 16934016 None

zain/Activation/wandb/run-20260812_213354-drnrn7sc/logs/debug-core.log

@@ -55,3 +55,10 @@
 {"time":"2026-08-12T22:27:58.581475059Z","level":"INFO","msg":"handleInformInit: received","streamId":"48ajimfv","id":"5(@)"}
 {"time":"2026-08-12T22:27:58.842579591Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"48ajimfv","id":"5(@)"}
 {"time":"2026-08-12T22:28:04.247449735Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:09.454807185Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:10.177269679Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:10.178867577Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"48ajimfv","id":"5(@)"}
+{"time":"2026-08-12T22:41:10.179515406Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"48ajimfv","id":"5(@)"}
+{"time":"2026-08-12T22:41:11.169574197Z","level":"INFO","msg":"handleInformInit: received","streamId":"g6mesp08","id":"5(@)"}
+{"time":"2026-08-12T22:41:11.430389293Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"g6mesp08","id":"5(@)"}
+{"time":"2026-08-12T22:41:17.032077408Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"uc88v5r6gnic"}

zain/Activation/wandb/run-20260812_213440-m4b216ej/logs/debug-core.log

@@ -55,3 +55,10 @@
 {"time":"2026-08-12T22:27:58.581475059Z","level":"INFO","msg":"handleInformInit: received","streamId":"48ajimfv","id":"5(@)"}
 {"time":"2026-08-12T22:27:58.842579591Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"48ajimfv","id":"5(@)"}
 {"time":"2026-08-12T22:28:04.247449735Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:09.454807185Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:10.177269679Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:10.178867577Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"48ajimfv","id":"5(@)"}
+{"time":"2026-08-12T22:41:10.179515406Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"48ajimfv","id":"5(@)"}
+{"time":"2026-08-12T22:41:11.169574197Z","level":"INFO","msg":"handleInformInit: received","streamId":"g6mesp08","id":"5(@)"}
+{"time":"2026-08-12T22:41:11.430389293Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"g6mesp08","id":"5(@)"}
+{"time":"2026-08-12T22:41:17.032077408Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"uc88v5r6gnic"}

zain/Activation/wandb/run-20260812_213624-1sryr5l2/logs/debug-core.log

@@ -55,3 +55,10 @@
 {"time":"2026-08-12T22:27:58.581475059Z","level":"INFO","msg":"handleInformInit: received","streamId":"48ajimfv","id":"5(@)"}
 {"time":"2026-08-12T22:27:58.842579591Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"48ajimfv","id":"5(@)"}
 {"time":"2026-08-12T22:28:04.247449735Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:09.454807185Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:10.177269679Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:10.178867577Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"48ajimfv","id":"5(@)"}
+{"time":"2026-08-12T22:41:10.179515406Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"48ajimfv","id":"5(@)"}
+{"time":"2026-08-12T22:41:11.169574197Z","level":"INFO","msg":"handleInformInit: received","streamId":"g6mesp08","id":"5(@)"}
+{"time":"2026-08-12T22:41:11.430389293Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"g6mesp08","id":"5(@)"}
+{"time":"2026-08-12T22:41:17.032077408Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"uc88v5r6gnic"}

zain/Activation/wandb/run-20260812_220132-25l266uo/logs/debug-core.log

@@ -55,3 +55,10 @@
 {"time":"2026-08-12T22:27:58.581475059Z","level":"INFO","msg":"handleInformInit: received","streamId":"48ajimfv","id":"5(@)"}
 {"time":"2026-08-12T22:27:58.842579591Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"48ajimfv","id":"5(@)"}
 {"time":"2026-08-12T22:28:04.247449735Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:09.454807185Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:10.177269679Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:10.178867577Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"48ajimfv","id":"5(@)"}
+{"time":"2026-08-12T22:41:10.179515406Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"48ajimfv","id":"5(@)"}
+{"time":"2026-08-12T22:41:11.169574197Z","level":"INFO","msg":"handleInformInit: received","streamId":"g6mesp08","id":"5(@)"}
+{"time":"2026-08-12T22:41:11.430389293Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"g6mesp08","id":"5(@)"}
+{"time":"2026-08-12T22:41:17.032077408Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"uc88v5r6gnic"}

zain/Activation/wandb/run-20260812_222706-8exldg55/logs/debug-core.log

@@ -55,3 +55,10 @@
 {"time":"2026-08-12T22:27:58.581475059Z","level":"INFO","msg":"handleInformInit: received","streamId":"48ajimfv","id":"5(@)"}
 {"time":"2026-08-12T22:27:58.842579591Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"48ajimfv","id":"5(@)"}
 {"time":"2026-08-12T22:28:04.247449735Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:09.454807185Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:10.177269679Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:10.178867577Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"48ajimfv","id":"5(@)"}
+{"time":"2026-08-12T22:41:10.179515406Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"48ajimfv","id":"5(@)"}
+{"time":"2026-08-12T22:41:11.169574197Z","level":"INFO","msg":"handleInformInit: received","streamId":"g6mesp08","id":"5(@)"}
+{"time":"2026-08-12T22:41:11.430389293Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"g6mesp08","id":"5(@)"}
+{"time":"2026-08-12T22:41:17.032077408Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"uc88v5r6gnic"}

zain/Activation/wandb/run-20260812_222758-48ajimfv/files/config.yaml

@@ -0,0 +1,438 @@
+_name_or_path:
+    value: ""
+_wandb:
+    value:
+        cli_version: 0.28.1
+        e:
+            cfscnetz4f3lmpfii83429a44mkzi20a:
+                args:
+                    - --config
+                    - /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/configs/baseline100L.yaml
+                    - --variants
+                    - glu-silu-waleed10
+                    - glu-situglu
+                    - glu-waleed
+                    - glu-situglu_low
+                    - glu-waleedglu_low
+                    - glu-linear
+                codePath: sweep.py
+                codePathLocal: sweep.py
+                cpu_count: 112
+                cpu_count_logical: 224
+                cudaVersion: "12.4"
+                disk:
+                    /:
+                        total: "1560765693952"
+                        used: "716399116288"
+                email: deepnevro@gmail.com
+                executable: /mnt/data/zainulabideen/zain-exp/notebooks/my_env/bin/python
+                git:
+                    commit: 26a43c7dee7982e610a25ac78443de9ce18f5077
+                    remote: https://github.com/w-ahmad1a10/Activation.git
+                gpu: NVIDIA H100 80GB HBM3
+                gpu_count: 8
+                gpu_nvidia:
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-39c684a5-fde6-83d7-1663-0859795881ae
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-68012e5a-38b6-b643-0ca6-62fb66720bf3
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-132944c4-b689-2b5f-89a4-d730401677ab
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-2df386cc-6d26-d0e2-7a2d-a057b0d95864
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-bfa16575-1d94-1aa2-4537-2c93433f42ef
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-bc6c3e3c-9b90-09ca-c034-774961847c54
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-00a441e1-7c95-e7d6-4c35-43d6b291aea9
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-1c4d29a2-4647-6fce-d8fc-0c5ecfbbd6ea
+                host: deeplens-k3s-node1
+                memory:
+                    total: "2164089937920"
+                os: Linux-5.15.0-126-generic-x86_64-with-glibc2.35
+                program: /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/sweep.py
+                python: CPython 3.11.15
+                root: /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation
+                startedAt: "2026-08-12T22:27:58.578801Z"
+                writerId: cfscnetz4f3lmpfii83429a44mkzi20a
+        m:
+            - "1": train/global_step
+              "6":
+                - 3
+              "7": []
+            - "2": '*'
+              "5": 1
+              "6":
+                - 1
+              "7": []
+        python_version: 3.11.15
+        t:
+            "1":
+                - 1
+                - 5
+                - 11
+                - 41
+                - 49
+                - 51
+                - 53
+                - 71
+            "2":
+                - 1
+                - 5
+                - 11
+                - 41
+                - 49
+                - 51
+                - 53
+                - 71
+            "3":
+                - 2
+                - 7
+                - 13
+                - 19
+                - 62
+                - 66
+            "4": 3.11.15
+            "5": 0.28.1
+            "6": 5.16.0.dev0
+            "9":
+                "1": transformers_trainer
+            "12": 0.28.1
+            "13": linux-x86_64
+accelerator_config:
+    value:
+        dispatch_batches: null
+        even_batches: true
+        gradient_accumulation_kwargs: null
+        non_blocking: false
+        split_batches: false
+        use_seedable_sampler: true
+activation:
+    value: silu-waleed10
+adam_beta1:
+    value: 0.9
+adam_beta2:
+    value: 0.999
+adam_epsilon:
+    value: 1e-08
+architectures:
+    value: null
+attention_bias:
+    value: false
+attention_dropout:
+    value: 0
+auto_find_batch_size:
+    value: false
+average_tokens_across_devices:
+    value: true
+batch_eval_metrics:
+    value: false
+bf16:
+    value: true
+bf16_full_eval:
+    value: false
+bos_token_id:
+    value: 1
+chunk_size_feed_forward:
+    value: 0
+data_seed:
+    value: 42
+dataloader_drop_last:
+    value: false
+dataloader_in_order:
+    value: true
+dataloader_multiprocessing_context:
+    value: null
+dataloader_num_workers:
+    value: 0
+dataloader_persistent_workers:
+    value: false
+dataloader_pin_memory:
+    value: true
+dataloader_prefetch_factor:
+    value: null
+ddp_backend:
+    value: null
+ddp_broadcast_buffers:
+    value: null
+ddp_bucket_cap_mb:
+    value: null
+ddp_find_unused_parameters:
+    value: null
+ddp_static_graph:
+    value: null
+ddp_timeout:
+    value: 1800
+debug:
+    value: []
+deepspeed:
+    value: null
+disable_tqdm:
+    value: false
+do_eval:
+    value: true
+do_predict:
+    value: false
+do_train:
+    value: false
+dtype:
+    value: null
+enable_jit_checkpoint:
+    value: false
+eos_token_id:
+    value: 2
+eval_accumulation_steps:
+    value: null
+eval_delay:
+    value: 0
+eval_do_concat_batches:
+    value: true
+eval_on_start:
+    value: false
+eval_steps:
+    value: 2498
+eval_strategy:
+    value: steps
+eval_use_gather_object:
+    value: false
+fp16:
+    value: false
+fp16_full_eval:
+    value: false
+fsdp:
+    value: null
+fsdp_config:
+    value: null
+full_determinism:
+    value: false
+gradient_accumulation_steps:
+    value: 1
+gradient_checkpointing:
+    value: false
+gradient_checkpointing_kwargs:
+    value: null
+greater_is_better:
+    value: null
+head_dim:
+    value: 32
+hidden_act:
+    value: silu
+hidden_size:
+    value: 128
+hub_always_push:
+    value: false
+hub_model_id:
+    value: w-ahmad/6L-glu-silu-waleed10-100L
+hub_private_repo:
+    value: null
+hub_revision:
+    value: null
+hub_strategy:
+    value: every_save
+hub_token:
+    value: <HUB_TOKEN>
+id2label:
+    value:
+        "0": LABEL_0
+        "1": LABEL_1
+ignore_data_skip:
+    value: false
+include_for_metrics:
+    value: []
+include_num_input_tokens_seen:
+    value: "no"
+initializer_range:
+    value: 0.02
+intermediate_size:
+    value: 256
+is_encoder_decoder:
+    value: false
+label_names:
+    value: null
+label_smoothing_factor:
+    value: 0
+label2id:
+    value:
+        LABEL_0: 0
+        LABEL_1: 1
+learning_rate:
+    value: 0.0007
+length_column_name:
+    value: length
+liger_kernel_config:
+    value: null
+load_best_model_at_end:
+    value: false
+local_rank:
+    value: -1
+log_level:
+    value: passive
+log_level_replica:
+    value: warning
+log_on_each_node:
+    value: true
+logging_first_step:
+    value: false
+logging_nan_inf_filter:
+    value: true
+logging_steps:
+    value: 20
+logging_strategy:
+    value: steps
+lr_scheduler_kwargs:
+    value: null
+lr_scheduler_type:
+    value: constant_with_warmup
+max_grad_norm:
+    value: 1
+max_position_embeddings:
+    value: 512
+max_steps:
+    value: 2500
+metric_for_best_model:
+    value: null
+mlp_bias:
+    value: false
+mlp_type:
+    value: glu
+model/num_parameters:
+    value: 16934016
+model_type:
+    value: tiny_llama
+neftune_noise_alpha:
+    value: null
+num_attention_heads:
+    value: 4
+num_hidden_layers:
+    value: 100
+num_key_value_heads:
+    value: 4
+num_train_epochs:
+    value: 1
+optim:
+    value: adamw_torch_fused
+optim_args:
+    value: null
+optim_target_modules:
+    value: null
+output_attentions:
+    value: false
+output_dir:
+    value: out/glu-silu-waleed10-100L_run
+output_hidden_states:
+    value: false
+pad_token_id:
+    value: 0
+parallelism_config:
+    value: null
+per_device_eval_batch_size:
+    value: 1024
+per_device_train_batch_size:
+    value: 64
+prediction_loss_only:
+    value: false
+pretraining_tp:
+    value: 1
+problem_type:
+    value: null
+project:
+    value: huggingface
+push_to_hub:
+    value: false
+remove_unused_columns:
+    value: false
+report_to:
+    value:
+        - wandb
+restore_callback_states_from_checkpoint:
+    value: false
+resume_from_checkpoint:
+    value: null
+return_dict:
+    value: true
+rms_norm_eps:
+    value: 1e-06
+rope_parameters:
+    value:
+        rope_theta: 10000
+        rope_type: default
+run_name:
+    value: LM-glu-silu-waleed10-100L-16.9M-20260812-222757
+save_on_each_node:
+    value: false
+save_only_model:
+    value: false
+save_steps:
+    value: 100
+save_strategy:
+    value: steps
+save_total_limit:
+    value: null
+seed:
+    value: 42
+skip_memory_metrics:
+    value: true
+tf32:
+    value: null
+tie_word_embeddings:
+    value: true
+tokenizer_name:
+    value: w-ahmad/tiny-stories-tokenizer
+torch_compile:
+    value: false
+torch_compile_backend:
+    value: null
+torch_compile_mode:
+    value: null
+torch_empty_cache_steps:
+    value: null
+trackio_bucket_id:
+    value: null
+trackio_space_id:
+    value: null
+trackio_static_space_id:
+    value: null
+train_sampling_strategy:
+    value: random
+transformers_version:
+    value: 5.16.0.dev0
+use_cache:
+    value: false
+use_cpu:
+    value: false
+use_liger_kernel:
+    value: false
+vocab_size:
+    value: 4096
+waleed_beta:
+    value: 10
+warmup_steps:
+    value: 500
+weight_decay:
+    value: 0

zain/Activation/wandb/run-20260812_222758-48ajimfv/files/output.log

@@ -240,6 +240,23 @@ Writing model shards: 100%|██████████| 1/1 [00:00<00:00, 15.
   - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
   - If you are not the owner of the model architecture class, please contact the model code owner to update it.
 Writing model shards: 100%|██████████| 1/1 [00:00<00:00, 16.58it/s]
- 98%|█████████▊| 2458/2500 [12:10<00:13,  3.14it/s], ?it/s]
+100%|██████████| 2500/2500 [12:54<00:00,  3.60s[transformers] TinyLlamaForCausalLM has generative capabilities, as `prepare_inputs_for_generation` is explicitly defined. However, it doesn't directly inherit from `GenerationMixin`. From 👉v4.50👈 onwards, `PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions.
 {'loss': '2.131', 'grad_norm': '0.3359', 'learning_rate': '0.0007', 'epoch': '0.1631', 'train/total_time_seconds': '590.2', 'train/time_per_step_avg': '0.2485', 'train/epoch_time_elapsed': '718.7', 'train/estimated_remaining_minutes': '0.3252'}
 {'loss': '2.118', 'grad_norm': '0.3398', 'learning_rate': '0.0007', 'epoch': '0.1645', 'train/total_time_seconds': '595.1', 'train/time_per_step_avg': '0.2475', 'train/epoch_time_elapsed': '724.6', 'train/estimated_remaining_minutes': '0.2439'}
+{'loss': '2.13', 'grad_norm': '0.3281', 'learning_rate': '0.0007', 'epoch': '0.1658', 'train/total_time_seconds': '600.2', 'train/time_per_step_avg': '0.2488', 'train/epoch_time_elapsed': '730.8', 'train/estimated_remaining_minutes': '0.1627'}
+{'loss': '2.129', 'grad_norm': '0.3418', 'learning_rate': '0.0007', 'epoch': '0.1672', 'train/total_time_seconds': '605.1', 'train/time_per_step_avg': '0.2487', 'train/epoch_time_elapsed': '736.8', 'train/estimated_remaining_minutes': '0.08134'}
+  - If you're using `trust_remote_code=True`, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
+{'eval_loss': '2.122', 'eval_runtime': '15.73', 'eval_samples_per_second': '605.6', 'eval_steps_per_second': '0.636', 'epoch': '0.1684', 'train/total_time_seconds': '609.6', 'train/time_per_step_avg': '0.2489', 'train/epoch_time_elapsed': '757.9', 'train/estimated_remaining_minutes': '0.008135'}
+{'loss': '2.112', 'grad_norm': '0.3301', 'learning_rate': '0.0007', 'epoch': '0.1685', 'train/total_time_seconds': '610.1', 'train/time_per_step_avg': '0.2488', 'train/epoch_time_elapsed': '758.5', 'train/estimated_remaining_minutes': '0'}
+{'eval_loss': '2.123', 'eval_runtime': '15.66', 'eval_samples_per_second': '608.5', 'eval_steps_per_second': '0.639', 'epoch': '0.1685', 'train/total_time_seconds': '610.1', 'train/time_per_step_avg': '0.2488', 'train/epoch_time_elapsed': '774.1', 'train/estimated_remaining_minutes': '0'}
+  - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
+  - If you are not the owner of the model architecture class, please contact the model code owner to update it.
+Writing model shards: 100%|██████████| 1/1 [00:00<00:00, 16.21it/s]
+100%|██████████| 2500/2500 [12:55<00:00,  3.22it/s], ?it/s]
+{'train_runtime': '775.2', 'train_samples_per_second': '206.4', 'train_steps_per_second': '3.225', 'train_loss': '3.076', 'epoch': '0.1685', 'train/total_time_seconds': '610.1', 'train/time_per_step_avg': '0.2488', 'train/epoch_time_elapsed': '774.4', 'train/estimated_remaining_minutes': '0'}
+100%|██████████| 10/10 [00:13<00:00,  1.35s/it]
+[transformers] TinyLlamaForCausalLM has generative capabilities, as `prepare_inputs_for_generation` is explicitly defined. However, it doesn't directly inherit from `GenerationMixin`. From 👉v4.50👈 onwards, `PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions.
+  - If you're using `trust_remote_code=True`, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
+  - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
+  - If you are not the owner of the model architecture class, please contact the model code owner to update it.
+Writing model shards: 100%|██████████| 1/1 [00:00<00:00, 14.81it/s]

zain/Activation/wandb/run-20260812_222758-48ajimfv/files/wandb-summary.json

@@ -0,0 +1 @@
+{"eval/loss":2.122779130935669,"train_runtime":775.1939,"_runtime":790,"_step":128,"_wandb":{"runtime":790},"total_flos":8.06570950656e+15,"train/train/time_per_step_avg":0.24884768467396498,"eval/runtime":15.6769,"train/grad_norm":0.330078125,"train_samples_per_second":206.4,"eval/steps_per_second":0.638,"train/loss":2.1122053146362303,"train/learning_rate":0.0007,"train/global_step":2500,"train/epoch":0.16852039096730703,"train_loss":3.075678741455078,"train/train/epoch_time_elapsed":790.1192352175713,"train/train/total_time_seconds":610.1298802383244,"eval/samples_per_second":607.708,"train_steps_per_second":3.225,"train/train/estimated_remaining_minutes":0,"_timestamp":1.7865744693563404e+09}

zain/Activation/wandb/run-20260812_222758-48ajimfv/logs/debug-core.log

@@ -55,3 +55,10 @@
 {"time":"2026-08-12T22:27:58.581475059Z","level":"INFO","msg":"handleInformInit: received","streamId":"48ajimfv","id":"5(@)"}
 {"time":"2026-08-12T22:27:58.842579591Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"48ajimfv","id":"5(@)"}
 {"time":"2026-08-12T22:28:04.247449735Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:09.454807185Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:10.177269679Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:10.178867577Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"48ajimfv","id":"5(@)"}
+{"time":"2026-08-12T22:41:10.179515406Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"48ajimfv","id":"5(@)"}
+{"time":"2026-08-12T22:41:11.169574197Z","level":"INFO","msg":"handleInformInit: received","streamId":"g6mesp08","id":"5(@)"}
+{"time":"2026-08-12T22:41:11.430389293Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"g6mesp08","id":"5(@)"}
+{"time":"2026-08-12T22:41:17.032077408Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"uc88v5r6gnic"}

zain/Activation/wandb/run-20260812_222758-48ajimfv/logs/debug-internal.log

@@ -103,3 +103,19 @@
 {"time":"2026-08-12T22:39:44.740657985Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
 {"time":"2026-08-12T22:39:59.430983472Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":118,"history_lines":3,"events_offset":94,"events_lines":2,"console_offset":232,"console_lines":1}
 {"time":"2026-08-12T22:39:59.794369716Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:40:14.431022343Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":121,"history_lines":2,"events_offset":96,"events_lines":2,"console_offset":236,"console_lines":10}
+{"time":"2026-08-12T22:40:14.741497229Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:40:29.4302943Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":123,"history_lines":1,"events_offset":98,"events_lines":2,"console_offset":242,"console_lines":1}
+{"time":"2026-08-12T22:40:29.57795897Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:40:44.430823678Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":124,"history_lines":2,"events_offset":100,"events_lines":2,"console_offset":242,"console_lines":1}
+{"time":"2026-08-12T22:40:44.66808462Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:40:59.431034803Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":126,"history_lines":2,"events_offset":102,"events_lines":2,"console_offset":242,"console_lines":1}
+{"time":"2026-08-12T22:40:59.69351984Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:41:10.034164126Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2026-08-12T22:41:10.034383941Z","level":"INFO","msg":"filestream: sending request","total_files":3,"history_offset":128,"history_lines":1,"console_offset":246,"console_lines":16,"uploaded_len":3,"complete":true,"exit_code":0}
+{"time":"2026-08-12T22:41:10.174833199Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:41:10.176011934Z","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2026-08-12T22:41:10.178895759Z","level":"INFO","msg":"stream: finishing up"}
+{"time":"2026-08-12T22:41:10.178925693Z","level":"INFO","msg":"handler: closed"}
+{"time":"2026-08-12T22:41:10.178979601Z","level":"INFO","msg":"sender: closed"}
+{"time":"2026-08-12T22:41:10.178984229Z","level":"INFO","msg":"stream: all finished"}

zain/Activation/wandb/run-20260812_222758-48ajimfv/logs/debug.log

@@ -21,3 +21,8 @@ config: {'_wandb': {}}
 2026-08-12 22:27:59,232 INFO    MainThread:3978000 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.16.0.dev0', 'architectures': None, 'output_hidden_states': False, 'return_dict': True, 'dtype': None, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, 'vocab_size': 4096, 'hidden_size': 128, 'intermediate_size': 256, 'num_hidden_layers': 100, 'num_attention_heads': 4, 'num_key_value_heads': 4, 'hidden_act': 'silu', 'max_position_embeddings': 512, 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'pad_token_id': 0, 'bos_token_id': 1, 'eos_token_id': 2, 'pretraining_tp': 1, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 10000.0, 'rope_type': 'default'}, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'head_dim': 32, '_name_or_path': '', 'tokenizer_name': 'w-ahmad/tiny-stories-tokenizer', 'mlp_type': 'glu', 'activation': 'silu-waleed10', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-silu-waleed10-100L_run', 'per_device_train_batch_size': 64, 'num_train_epochs': 1, 'max_steps': 2500, 'learning_rate': 0.0007, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 500, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 1.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-silu-waleed10-100L-16.9M-20260812-222757', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 2498, 'eval_delay': 0, 'per_device_eval_batch_size': 1024, 'prediction_loss_only': False, 'eval_on_start': False, 'eval_do_concat_batches': True, 'eval_use_gather_object': False, 'eval_accumulation_steps': None, 'include_for_metrics': [], 'batch_eval_metrics': False, 'save_only_model': False, 'save_strategy': 'steps', 'save_steps': 100, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/6L-glu-silu-waleed10-100L', 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': None, 'dataloader_multiprocessing_context': None, 'dataloader_in_order': True, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_static_graph': None, 'ddp_backend': None, 'ddp_timeout': 1800, 'fsdp': None, 'fsdp_config': None, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'local_rank': -1}
 2026-08-12 22:27:59,236 INFO    MainThread:3978000 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 16934016 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x14d922561cd0>>
 2026-08-12 22:27:59,236 INFO    MainThread:3978000 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 16934016 None
+2026-08-12 22:41:09,454 INFO    MainThread:3978000 [wandb_run.py:_finish():2383] finishing run deepnevro-deepnevro/research3/48ajimfv
+2026-08-12 22:41:09,454 INFO    MainThread:3978000 [wandb_run.py:_atexit_cleanup():2588] got exitcode: 0
+2026-08-12 22:41:09,454 INFO    MainThread:3978000 [wandb_run.py:_restore():2570] restore
+2026-08-12 22:41:09,454 INFO    MainThread:3978000 [wandb_run.py:_restore():2576] restore done
+2026-08-12 22:41:10,178 INFO    MainThread:3978000 [wandb_run.py:_footer_sync_info():3993] logging synced files

zain/Activation/wandb/run-20260812_222758-48ajimfv/run-48ajimfv.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c119ab43d6013cdea8e472e2792a58f89e507a70f48e3d1a43f2398fb13c32c4
-size 819200
+oid sha256:782069f5b0689421c66343dfee30af8bb2c2a59e827ba6b733ec42356227a4a9
+size 893957

zain/Activation/wandb/run-20260812_224111-g6mesp08/files/output.log

@@ -0,0 +1,74 @@
+  4%|▍         | 100/2500 [00:32<12:31,  3.19it/s][transformers] TinyLlamaForCausalLM has generative capabilities, as `prepare_inputs_for_generation` is explicitly defined. However, it doesn't directly inherit from `GenerationMixin`. From 👉v4.50👈 onwards, `PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions.
+{'loss': '8.3', 'grad_norm': '2.078', 'learning_rate': '2.66e-05', 'epoch': '0.001348', 'train/total_time_seconds': '5.534', 'train/time_per_step_avg': '0.2767', 'train/epoch_time_elapsed': '6.577', 'train/estimated_remaining_minutes': '11.44'}
+{'loss': '8.048', 'grad_norm': '1.352', 'learning_rate': '5.46e-05', 'epoch': '0.002696', 'train/total_time_seconds': '10.85', 'train/time_per_step_avg': '0.2713', 'train/epoch_time_elapsed': '12.85', 'train/estimated_remaining_minutes': '11.12'}
+{'loss': '7.838', 'grad_norm': '1.273', 'learning_rate': '8.26e-05', 'epoch': '0.004044', 'train/total_time_seconds': '16.14', 'train/time_per_step_avg': '0.2691', 'train/epoch_time_elapsed': '19.09', 'train/estimated_remaining_minutes': '10.94'}
+{'loss': '7.573', 'grad_norm': '1.266', 'learning_rate': '0.0001106', 'epoch': '0.005393', 'train/total_time_seconds': '21.44', 'train/time_per_step_avg': '0.268', 'train/epoch_time_elapsed': '25.35', 'train/estimated_remaining_minutes': '10.81'}
+{'loss': '7.233', 'grad_norm': '1.195', 'learning_rate': '0.0001386', 'epoch': '0.006741', 'train/total_time_seconds': '26.75', 'train/time_per_step_avg': '0.2675', 'train/epoch_time_elapsed': '31.66', 'train/estimated_remaining_minutes': '10.7'}
+  - If you're using `trust_remote_code=True`, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
+  - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
+  - If you are not the owner of the model architecture class, please contact the model code owner to update it.
+Writing model shards: 100%|██████████| 1/1 [00:00<00:00, 12.84it/s]
+  8%|▊         | 200/2500 [01:04<12:11,  3.14it/s][transformers] TinyLlamaForCausalLM has generative capabilities, as `prepare_inputs_for_generation` is explicitly defined. However, it doesn't directly inherit from `GenerationMixin`. From 👉v4.50👈 onwards, `PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions.
+{'loss': '6.861', 'grad_norm': '1.133', 'learning_rate': '0.0001666', 'epoch': '0.008089', 'train/total_time_seconds': '32.1', 'train/time_per_step_avg': '0.2657', 'train/epoch_time_elapsed': '38.29', 'train/estimated_remaining_minutes': '10.61'}
+{'loss': '6.518', 'grad_norm': '0.9492', 'learning_rate': '0.0001946', 'epoch': '0.009437', 'train/total_time_seconds': '37.41', 'train/time_per_step_avg': '0.2655', 'train/epoch_time_elapsed': '44.55', 'train/estimated_remaining_minutes': '10.51'}
+{'loss': '6.24', 'grad_norm': '0.8047', 'learning_rate': '0.0002226', 'epoch': '0.01079', 'train/total_time_seconds': '42.7', 'train/time_per_step_avg': '0.2655', 'train/epoch_time_elapsed': '50.81', 'train/estimated_remaining_minutes': '10.41'}
+{'loss': '6.041', 'grad_norm': '0.6641', 'learning_rate': '0.0002506', 'epoch': '0.01213', 'train/total_time_seconds': '48.07', 'train/time_per_step_avg': '0.2663', 'train/epoch_time_elapsed': '57.15', 'train/estimated_remaining_minutes': '10.33'}
+{'loss': '5.864', 'grad_norm': '0.5234', 'learning_rate': '0.0002786', 'epoch': '0.01348', 'train/total_time_seconds': '53.63', 'train/time_per_step_avg': '0.2688', 'train/epoch_time_elapsed': '63.68', 'train/estimated_remaining_minutes': '10.28'}
+  - If you're using `trust_remote_code=True`, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
+  - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
+  - If you are not the owner of the model architecture class, please contact the model code owner to update it.
+Writing model shards: 100%|██████████| 1/1 [00:00<00:00, 16.56it/s]
+ 12%|█▏        | 300/2500 [01:36<11:42,  3.13it/s][transformers] TinyLlamaForCausalLM has generative capabilities, as `prepare_inputs_for_generation` is explicitly defined. However, it doesn't directly inherit from `GenerationMixin`. From 👉v4.50👈 onwards, `PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions.
+{'loss': '5.693', 'grad_norm': '1.375', 'learning_rate': '0.0003066', 'epoch': '0.01483', 'train/total_time_seconds': '59.31', 'train/time_per_step_avg': '0.272', 'train/epoch_time_elapsed': '70.65', 'train/estimated_remaining_minutes': '10.24'}
+{'loss': '5.484', 'grad_norm': '0.875', 'learning_rate': '0.0003346', 'epoch': '0.01618', 'train/total_time_seconds': '64.62', 'train/time_per_step_avg': '0.2722', 'train/epoch_time_elapsed': '76.93', 'train/estimated_remaining_minutes': '10.14'}
+{'loss': '5.257', 'grad_norm': '1.25', 'learning_rate': '0.0003626', 'epoch': '0.01753', 'train/total_time_seconds': '69.94', 'train/time_per_step_avg': '0.2724', 'train/epoch_time_elapsed': '83.23', 'train/estimated_remaining_minutes': '10.04'}
+{'loss': '5.029', 'grad_norm': '0.8125', 'learning_rate': '0.0003906', 'epoch': '0.01887', 'train/total_time_seconds': '75.28', 'train/time_per_step_avg': '0.2721', 'train/epoch_time_elapsed': '89.55', 'train/estimated_remaining_minutes': '9.948'}
+{'loss': '4.792', 'grad_norm': '0.7539', 'learning_rate': '0.0004186', 'epoch': '0.02022', 'train/total_time_seconds': '80.61', 'train/time_per_step_avg': '0.2698', 'train/epoch_time_elapsed': '95.88', 'train/estimated_remaining_minutes': '9.852'}
+  - If you're using `trust_remote_code=True`, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
+  - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
+  - If you are not the owner of the model architecture class, please contact the model code owner to update it.
+Writing model shards: 100%|██████████| 1/1 [00:00<00:00, 15.24it/s]
+ 16%|█▌        | 400/2500 [02:08<11:29,  3.04it/s][transformers] TinyLlamaForCausalLM has generative capabilities, as `prepare_inputs_for_generation` is explicitly defined. However, it doesn't directly inherit from `GenerationMixin`. From 👉v4.50👈 onwards, `PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions.
+{'loss': '4.599', 'grad_norm': '0.875', 'learning_rate': '0.0004466', 'epoch': '0.02157', 'train/total_time_seconds': '85.99', 'train/time_per_step_avg': '0.2668', 'train/epoch_time_elapsed': '102.5', 'train/estimated_remaining_minutes': '9.763'}
+{'loss': '4.419', 'grad_norm': '0.8125', 'learning_rate': '0.0004746', 'epoch': '0.02292', 'train/total_time_seconds': '91.31', 'train/time_per_step_avg': '0.2669', 'train/epoch_time_elapsed': '108.8', 'train/estimated_remaining_minutes': '9.668'}
+{'loss': '4.273', 'grad_norm': '0.8906', 'learning_rate': '0.0005026', 'epoch': '0.02427', 'train/total_time_seconds': '96.65', 'train/time_per_step_avg': '0.267', 'train/epoch_time_elapsed': '115.1', 'train/estimated_remaining_minutes': '9.575'}
+{'loss': '4.128', 'grad_norm': '1.273', 'learning_rate': '0.0005306', 'epoch': '0.02562', 'train/total_time_seconds': '102', 'train/time_per_step_avg': '0.2668', 'train/epoch_time_elapsed': '121.4', 'train/estimated_remaining_minutes': '9.481'}
+{'loss': '3.994', 'grad_norm': '0.543', 'learning_rate': '0.0005586', 'epoch': '0.02696', 'train/total_time_seconds': '107.5', 'train/time_per_step_avg': '0.2693', 'train/epoch_time_elapsed': '128', 'train/estimated_remaining_minutes': '9.409'}
+  - If you're using `trust_remote_code=True`, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
+  - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
+  - If you are not the owner of the model architecture class, please contact the model code owner to update it.
+Writing model shards: 100%|██████████| 1/1 [00:00<00:00, 15.90it/s]
+ 20%|██        | 500/2500 [02:40<10:29,  3.18it/s][transformers] TinyLlamaForCausalLM has generative capabilities, as `prepare_inputs_for_generation` is explicitly defined. However, it doesn't directly inherit from `GenerationMixin`. From 👉v4.50👈 onwards, `PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions.
+{'loss': '3.885', 'grad_norm': '0.5469', 'learning_rate': '0.0005866', 'epoch': '0.02831', 'train/total_time_seconds': '112.9', 'train/time_per_step_avg': '0.269', 'train/epoch_time_elapsed': '134.6', 'train/estimated_remaining_minutes': '9.318'}
+{'loss': '3.822', 'grad_norm': '0.7891', 'learning_rate': '0.0006146', 'epoch': '0.02966', 'train/total_time_seconds': '118.3', 'train/time_per_step_avg': '0.2694', 'train/epoch_time_elapsed': '141', 'train/estimated_remaining_minutes': '9.227'}
+{'loss': '3.707', 'grad_norm': '0.5273', 'learning_rate': '0.0006426', 'epoch': '0.03101', 'train/total_time_seconds': '123.6', 'train/time_per_step_avg': '0.2695', 'train/epoch_time_elapsed': '147.4', 'train/estimated_remaining_minutes': '9.136'}
+{'loss': '3.637', 'grad_norm': '0.6328', 'learning_rate': '0.0006706', 'epoch': '0.03236', 'train/total_time_seconds': '129', 'train/time_per_step_avg': '0.2701', 'train/epoch_time_elapsed': '153.7', 'train/estimated_remaining_minutes': '9.046'}
+{'loss': '3.555', 'grad_norm': '0.5625', 'learning_rate': '0.0006986', 'epoch': '0.0337', 'train/total_time_seconds': '134.3', 'train/time_per_step_avg': '0.2678', 'train/epoch_time_elapsed': '160', 'train/estimated_remaining_minutes': '8.954'}
+  - If you're using `trust_remote_code=True`, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
+  - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
+  - If you are not the owner of the model architecture class, please contact the model code owner to update it.
+Writing model shards: 100%|██████████| 1/1 [00:00<00:00, 14.93it/s]
+ 24%|██▍       | 600/2500 [03:13<10:19,  3.07it/s][transformers] TinyLlamaForCausalLM has generative capabilities, as `prepare_inputs_for_generation` is explicitly defined. However, it doesn't directly inherit from `GenerationMixin`. From 👉v4.50👈 onwards, `PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions.
+{'loss': '3.487', 'grad_norm': '0.4727', 'learning_rate': '0.0007', 'epoch': '0.03505', 'train/total_time_seconds': '139.7', 'train/time_per_step_avg': '0.2678', 'train/epoch_time_elapsed': '166.7', 'train/estimated_remaining_minutes': '8.864'}
+{'loss': '3.415', 'grad_norm': '0.6328', 'learning_rate': '0.0007', 'epoch': '0.0364', 'train/total_time_seconds': '145', 'train/time_per_step_avg': '0.2676', 'train/epoch_time_elapsed': '173', 'train/estimated_remaining_minutes': '8.772'}
+{'loss': '3.362', 'grad_norm': '0.4785', 'learning_rate': '0.0007', 'epoch': '0.03775', 'train/total_time_seconds': '150.3', 'train/time_per_step_avg': '0.2673', 'train/epoch_time_elapsed': '179.3', 'train/estimated_remaining_minutes': '8.68'}
+{'loss': '3.301', 'grad_norm': '0.4785', 'learning_rate': '0.0007', 'epoch': '0.0391', 'train/total_time_seconds': '155.7', 'train/time_per_step_avg': '0.267', 'train/epoch_time_elapsed': '185.6', 'train/estimated_remaining_minutes': '8.589'}
+{'loss': '3.266', 'grad_norm': '0.4414', 'learning_rate': '0.0007', 'epoch': '0.04044', 'train/total_time_seconds': '161.2', 'train/time_per_step_avg': '0.2694', 'train/epoch_time_elapsed': '192.2', 'train/estimated_remaining_minutes': '8.51'}
+  - If you're using `trust_remote_code=True`, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
+  - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
+  - If you are not the owner of the model architecture class, please contact the model code owner to update it.
+Writing model shards: 100%|██████████| 1/1 [00:00<00:00, 13.94it/s]
+ 28%|██▊       | 700/2500 [03:45<09:40,  3.10it/s][transformers] TinyLlamaForCausalLM has generative capabilities, as `prepare_inputs_for_generation` is explicitly defined. However, it doesn't directly inherit from `GenerationMixin`. From 👉v4.50👈 onwards, `PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions.
+{'loss': '3.199', 'grad_norm': '0.582', 'learning_rate': '0.0007', 'epoch': '0.04179', 'train/total_time_seconds': '166.6', 'train/time_per_step_avg': '0.2696', 'train/epoch_time_elapsed': '198.9', 'train/estimated_remaining_minutes': '8.421'}
+{'loss': '3.175', 'grad_norm': '0.5195', 'learning_rate': '0.0007', 'epoch': '0.04314', 'train/total_time_seconds': '172', 'train/time_per_step_avg': '0.2696', 'train/epoch_time_elapsed': '205.2', 'train/estimated_remaining_minutes': '8.33'}
+{'loss': '3.119', 'grad_norm': '0.4434', 'learning_rate': '0.0007', 'epoch': '0.04449', 'train/total_time_seconds': '177.3', 'train/time_per_step_avg': '0.2697', 'train/epoch_time_elapsed': '211.5', 'train/estimated_remaining_minutes': '8.238'}
+{'loss': '3.091', 'grad_norm': '0.4473', 'learning_rate': '0.0007', 'epoch': '0.04584', 'train/total_time_seconds': '182.7', 'train/time_per_step_avg': '0.2702', 'train/epoch_time_elapsed': '217.9', 'train/estimated_remaining_minutes': '8.149'}
+{'loss': '3.048', 'grad_norm': '0.4004', 'learning_rate': '0.0007', 'epoch': '0.04719', 'train/total_time_seconds': '188', 'train/time_per_step_avg': '0.2678', 'train/epoch_time_elapsed': '224.3', 'train/estimated_remaining_minutes': '8.058'}
+  - If you're using `trust_remote_code=True`, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
+  - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
+  - If you are not the owner of the model architecture class, please contact the model code owner to update it.
+Writing model shards: 100%|██████████| 1/1 [00:00<00:00, 14.19it/s]
+ 31%|███       | 766/2500 [04:06<09:08,  3.16it/s]?, ?it/s]
+{'loss': '3.012', 'grad_norm': '0.3945', 'learning_rate': '0.0007', 'epoch': '0.04853', 'train/total_time_seconds': '193.4', 'train/time_per_step_avg': '0.2674', 'train/epoch_time_elapsed': '230.9', 'train/estimated_remaining_minutes': '7.968'}
+{'loss': '2.973', 'grad_norm': '0.4062', 'learning_rate': '0.0007', 'epoch': '0.04988', 'train/total_time_seconds': '198.7', 'train/time_per_step_avg': '0.2674', 'train/epoch_time_elapsed': '237.2', 'train/estimated_remaining_minutes': '7.877'}
+{'loss': '2.957', 'grad_norm': '0.4102', 'learning_rate': '0.0007', 'epoch': '0.05123', 'train/total_time_seconds': '204.1', 'train/time_per_step_avg': '0.2678', 'train/epoch_time_elapsed': '243.6', 'train/estimated_remaining_minutes': '7.787'}

zain/Activation/wandb/run-20260812_224111-g6mesp08/files/requirements.txt

@@ -0,0 +1,149 @@
+asttokens==3.0.1
+comm==0.2.3
+debugpy==1.8.21
+decorator==5.3.1
+executing==2.2.1
+nest-asyncio==1.6.0
+parso==0.8.7
+platformdirs==4.11.0
+psutil==7.2.2
+ptyprocess==0.7.0
+pure_eval==0.2.3
+Pygments==2.20.0
+pyzmq==27.1.0
+setuptools==83.0.0
+six==1.17.0
+tornado==6.5.7
+traitlets==5.15.0
+fsspec==2026.4.0
+wcwidth==0.8.2
+ipython_pygments_lexers==1.1.1
+jedi==0.20.0
+jupyter_core==5.9.1
+matplotlib-inline==0.2.2
+pexpect==4.9.0
+prompt_toolkit==3.0.53
+python-dateutil==2.9.0.post0
+stack_data==0.6.3
+wheel==0.47.0
+jupyter_client==8.9.1
+pip==26.1.2
+ipython==9.15.0
+ipykernel==7.2.0
+threadpoolctl==3.6.0
+pyparsing==3.3.2
+typing_extensions==4.15.0
+Jinja2==3.1.6
+narwhals==2.24.0
+kiwisolver==1.5.0
+joblib==1.5.3
+fonttools==4.63.0
+cycler==0.12.1
+scipy==1.17.1
+pandas==3.0.5
+contourpy==1.3.3
+scikit-learn==1.9.0
+matplotlib==3.11.1
+urllib3==2.7.0
+tqdm==4.70.0
+idna==3.18
+charset-normalizer==3.4.9
+certifi==2026.7.22
+requests==2.34.2
+seaborn==0.13.2
+uv==0.12.0
+shellingham==1.5.4
+mpmath==1.3.0
+attrs==26.1.0
+hf-xet==1.5.2
+nvidia-nccl-cu12==2.21.5
+MarkupSafe==3.0.3
+regex==2026.7.19
+importlib_metadata==9.0.0
+httpcore==1.0.9
+annotated-doc==0.0.5
+multidict==6.7.1
+aiohttp==3.14.3
+aiosignal==1.4.0
+xxhash==3.8.1
+aiohappyeyeballs==2.7.1
+mdurl==0.1.2
+cuda-toolkit==13.0.3.0
+networkx==3.6.1
+PyYAML==6.0.3
+nvidia-cufile==1.15.1.6
+typer==0.27.0
+torchaudio==2.6.0+cu124
+rich==15.0.0
+nvidia-cufft-cu12==11.2.1.3
+h11==0.16.0
+dill==0.4.1
+cuda-pathfinder==1.6.0
+filelock==3.29.0
+nvidia-nvtx-cu12==12.4.127
+httpx==0.28.1
+anyio==4.14.2
+numpy==2.4.4
+yarl==1.24.5
+click==8.4.2
+triton==3.2.0
+frozenlist==1.8.0
+zipp==4.1.0
+propcache==0.5.2
+tokenizers==0.22.2
+markdown-it-py==4.2.0
+nvidia-cuda-runtime==13.0.96
+cuda-bindings==13.3.1
+nvidia-cuda-cupti==13.0.85
+torch==2.6.0+cu124
+multiprocess==0.70.19
+pillow==12.2.0
+transformers==5.16.0.dev0
+wandb==0.28.1
+nvidia-curand==10.4.0.35
+sympy==1.13.1
+nvidia-cusparse==12.6.3.3
+nvidia-cuda-nvrtc==13.0.88
+typing-inspection==0.4.2
+nvidia-cusolver==12.0.4.66
+nvidia-cufft==12.0.0.61
+nvidia-cudnn-cu13==9.20.0.48
+nvidia-cublas==13.1.1.3
+pyarrow==25.0.0
+evaluate==0.4.6
+diffusers==0.39.0
+pydantic==2.13.4
+annotated-types==0.8.0
+protobuf==7.35.1
+sentry-sdk==2.66.1
+einops==0.8.2
+packaging==26.2
+nvidia-nvjitlink-cu12==12.4.127
+nvidia-curand-cu12==10.3.5.147
+nvidia-cusparselt-cu12==0.6.2
+nvidia-cusparse-cu12==12.3.1.170
+nvidia-cuda-runtime-cu12==12.4.127
+torchvision==0.21.0+cu124
+nvidia-cuda-nvrtc-cu12==12.4.127
+nvidia-cuda-cupti-cu12==12.4.127
+nvidia-cusolver-cu12==11.6.1.9
+nvidia-cublas-cu12==12.4.5.8
+nvidia-cudnn-cu12==9.1.0.70
+huggingface_hub==1.26.0
+datasets==5.0.1
+safetensors==0.8.0
+accelerate==1.14.0
+pydantic_core==2.46.4
+ninja==1.13.0
+autocommand==2.2.2
+backports.tarfile==1.2.0
+importlib_metadata==8.7.1
+jaraco.text==4.0.0
+jaraco.context==6.1.0
+jaraco.functools==4.4.0
+more-itertools==10.8.0
+packaging==26.0
+platformdirs==4.4.0
+tomli==2.4.0
+wheel==0.46.3
+zipp==3.23.0

zain/Activation/wandb/run-20260812_224111-g6mesp08/files/wandb-metadata.json

@@ -0,0 +1,100 @@
+{
+  "os":  "Linux-5.15.0-126-generic-x86_64-with-glibc2.35",
+  "python":  "CPython 3.11.15",
+  "startedAt":  "2026-08-12T22:41:11.167328Z",
+  "args":  [
+    "--config",
+    "/mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/configs/baseline100L.yaml",
+    "--variants",
+    "glu-silu-waleed10",
+    "glu-situglu",
+    "glu-waleed",
+    "glu-situglu_low",
+    "glu-waleedglu_low",
+    "glu-linear"
+  ],
+  "program":  "/mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/sweep.py",
+  "codePath":  "sweep.py",
+  "codePathLocal":  "sweep.py",
+  "git":  {
+    "remote":  "https://github.com/w-ahmad1a10/Activation.git",
+    "commit":  "26a43c7dee7982e610a25ac78443de9ce18f5077"
+  },
+  "email":  "deepnevro@gmail.com",
+  "root":  "/mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation",
+  "host":  "deeplens-k3s-node1",
+  "executable":  "/mnt/data/zainulabideen/zain-exp/notebooks/my_env/bin/python",
+  "cpu_count":  112,
+  "cpu_count_logical":  224,
+  "gpu":  "NVIDIA H100 80GB HBM3",
+  "gpu_count":  8,
+  "disk":  {
+    "/":  {
+      "total":  "1560765693952",
+      "used":  "716395634688"
+    }
+  },
+  "memory":  {
+    "total":  "2164089937920"
+  },
+  "gpu_nvidia":  [
+    {
+      "name":  "NVIDIA H100 80GB HBM3",
+      "memoryTotal":  "85520809984",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-39c684a5-fde6-83d7-1663-0859795881ae"
+    },
+    {
+      "name":  "NVIDIA H100 80GB HBM3",
+      "memoryTotal":  "85520809984",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-68012e5a-38b6-b643-0ca6-62fb66720bf3"
+    },
+    {
+      "name":  "NVIDIA H100 80GB HBM3",
+      "memoryTotal":  "85520809984",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-132944c4-b689-2b5f-89a4-d730401677ab"
+    },
+    {
+      "name":  "NVIDIA H100 80GB HBM3",
+      "memoryTotal":  "85520809984",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-2df386cc-6d26-d0e2-7a2d-a057b0d95864"
+    },
+    {
+      "name":  "NVIDIA H100 80GB HBM3",
+      "memoryTotal":  "85520809984",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-bfa16575-1d94-1aa2-4537-2c93433f42ef"
+    },
+    {
+      "name":  "NVIDIA H100 80GB HBM3",
+      "memoryTotal":  "85520809984",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-bc6c3e3c-9b90-09ca-c034-774961847c54"
+    },
+    {
+      "name":  "NVIDIA H100 80GB HBM3",
+      "memoryTotal":  "85520809984",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-00a441e1-7c95-e7d6-4c35-43d6b291aea9"
+    },
+    {
+      "name":  "NVIDIA H100 80GB HBM3",
+      "memoryTotal":  "85520809984",
+      "cudaCores":  16896,
+      "architecture":  "Hopper",
+      "uuid":  "GPU-1c4d29a2-4647-6fce-d8fc-0c5ecfbbd6ea"
+    }
+  ],
+  "cudaVersion":  "12.4",
+  "writerId":  "3cqy1hzjookbpfr002402bo7rd56tn3g"
+}

zain/Activation/wandb/run-20260812_224111-g6mesp08/logs/debug-core.log

@@ -0,0 +1,64 @@
+{"time":"2026-08-12T21:27:07.709800408Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpr5g1l2m_/port-3395538.txt","pid":3395538,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
+{"time":"2026-08-12T21:27:07.710342132Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":3395538}
+{"time":"2026-08-12T21:27:07.710337721Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-3395538-3401527-3744105281/socket","Net":"unix"}}
+{"time":"2026-08-12T21:27:07.887333699Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
+{"time":"2026-08-12T21:33:54.581320373Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"2(@)"}
+{"time":"2026-08-12T21:33:54.688909416Z","level":"INFO","msg":"handleInformInit: received","streamId":"drnrn7sc","id":"2(@)"}
+{"time":"2026-08-12T21:33:54.951896683Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"drnrn7sc","id":"2(@)"}
+{"time":"2026-08-12T21:34:00.556327076Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"ixm556fepihi"}
+{"time":"2026-08-12T21:34:10.171737115Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"ixm556fepihi"}
+{"time":"2026-08-12T21:34:11.895909974Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"ixm556fepihi"}
+{"time":"2026-08-12T21:34:11.897425638Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"drnrn7sc","id":"2(@)"}
+{"time":"2026-08-12T21:34:11.898049087Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"drnrn7sc","id":"2(@)"}
+{"time":"2026-08-12T21:34:13.578630946Z","level":"INFO","msg":"connection: closing","id":"2(@)"}
+{"time":"2026-08-12T21:34:13.57872317Z","level":"INFO","msg":"connection: closed successfully","id":"2(@)"}
+{"time":"2026-08-12T21:34:13.578646733Z","level":"INFO","msg":"processOutgoingData: finished","id":"2(@)"}
+{"time":"2026-08-12T21:34:13.578731041Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"2(@)"}
+{"time":"2026-08-12T21:34:40.817809433Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"3(@)"}
+{"time":"2026-08-12T21:34:40.893415954Z","level":"INFO","msg":"handleInformInit: received","streamId":"m4b216ej","id":"3(@)"}
+{"time":"2026-08-12T21:34:41.135313896Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"m4b216ej","id":"3(@)"}
+{"time":"2026-08-12T21:34:44.83192125Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"oh7mx3hrp202"}
+{"time":"2026-08-12T21:34:45.383336246Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"oh7mx3hrp202"}
+{"time":"2026-08-12T21:34:45.384332831Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"m4b216ej","id":"3(@)"}
+{"time":"2026-08-12T21:34:45.384892811Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"m4b216ej","id":"3(@)"}
+{"time":"2026-08-12T21:34:46.960734444Z","level":"INFO","msg":"connection: closing","id":"3(@)"}
+{"time":"2026-08-12T21:34:46.96082903Z","level":"INFO","msg":"connection: closed successfully","id":"3(@)"}
+{"time":"2026-08-12T21:34:46.960739226Z","level":"INFO","msg":"processOutgoingData: finished","id":"3(@)"}
+{"time":"2026-08-12T21:34:46.9608377Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"3(@)"}
+{"time":"2026-08-12T21:36:24.333479246Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"4(@)"}
+{"time":"2026-08-12T21:36:24.623681085Z","level":"INFO","msg":"handleInformInit: received","streamId":"1sryr5l2","id":"4(@)"}
+{"time":"2026-08-12T21:36:24.887624589Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"1sryr5l2","id":"4(@)"}
+{"time":"2026-08-12T21:36:30.334104214Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"uz9adtdly9x9"}
+{"time":"2026-08-12T22:01:30.787230204Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"uz9adtdly9x9"}
+{"time":"2026-08-12T22:01:31.351822304Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"uz9adtdly9x9"}
+{"time":"2026-08-12T22:01:31.353575322Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"1sryr5l2","id":"4(@)"}
+{"time":"2026-08-12T22:01:31.354164043Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"1sryr5l2","id":"4(@)"}
+{"time":"2026-08-12T22:01:32.229709771Z","level":"INFO","msg":"handleInformInit: received","streamId":"25l266uo","id":"4(@)"}
+{"time":"2026-08-12T22:01:32.488627418Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"25l266uo","id":"4(@)"}
+{"time":"2026-08-12T22:01:37.921838747Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"isui8l135tz1"}
+{"time":"2026-08-12T22:27:04.706825821Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"isui8l135tz1"}
+{"time":"2026-08-12T22:27:05.284617706Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"isui8l135tz1"}
+{"time":"2026-08-12T22:27:05.28630449Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"25l266uo","id":"4(@)"}
+{"time":"2026-08-12T22:27:05.306668573Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"25l266uo","id":"4(@)"}
+{"time":"2026-08-12T22:27:06.138572439Z","level":"INFO","msg":"handleInformInit: received","streamId":"8exldg55","id":"4(@)"}
+{"time":"2026-08-12T22:27:06.402135145Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"8exldg55","id":"4(@)"}
+{"time":"2026-08-12T22:27:11.79656888Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"pprgnnn1rakg"}
+{"time":"2026-08-12T22:27:27.947448187Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"pprgnnn1rakg"}
+{"time":"2026-08-12T22:27:28.405320179Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"pprgnnn1rakg"}
+{"time":"2026-08-12T22:27:28.406668119Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"8exldg55","id":"4(@)"}
+{"time":"2026-08-12T22:27:28.407546098Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"8exldg55","id":"4(@)"}
+{"time":"2026-08-12T22:27:29.871371448Z","level":"INFO","msg":"connection: closing","id":"4(@)"}
+{"time":"2026-08-12T22:27:29.871383033Z","level":"INFO","msg":"processOutgoingData: finished","id":"4(@)"}
+{"time":"2026-08-12T22:27:29.871449362Z","level":"INFO","msg":"connection: closed successfully","id":"4(@)"}
+{"time":"2026-08-12T22:27:29.871453424Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"4(@)"}
+{"time":"2026-08-12T22:27:58.491158261Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"5(@)"}
+{"time":"2026-08-12T22:27:58.581475059Z","level":"INFO","msg":"handleInformInit: received","streamId":"48ajimfv","id":"5(@)"}
+{"time":"2026-08-12T22:27:58.842579591Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"48ajimfv","id":"5(@)"}
+{"time":"2026-08-12T22:28:04.247449735Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:09.454807185Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:10.177269679Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"qhir5h2t5fy6"}
+{"time":"2026-08-12T22:41:10.178867577Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"48ajimfv","id":"5(@)"}
+{"time":"2026-08-12T22:41:10.179515406Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"48ajimfv","id":"5(@)"}
+{"time":"2026-08-12T22:41:11.169574197Z","level":"INFO","msg":"handleInformInit: received","streamId":"g6mesp08","id":"5(@)"}
+{"time":"2026-08-12T22:41:11.430389293Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"g6mesp08","id":"5(@)"}
+{"time":"2026-08-12T22:41:17.032077408Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"uc88v5r6gnic"}

zain/Activation/wandb/run-20260812_224111-g6mesp08/logs/debug-internal.log

@@ -0,0 +1,41 @@
+{"time":"2026-08-12T22:41:11.169747831Z","level":"INFO","msg":"wandb-core"}
+{"time":"2026-08-12T22:41:11.169891384Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
+{"time":"2026-08-12T22:41:11.430196954Z","level":"INFO","msg":"stream: created new stream","id":"g6mesp08"}
+{"time":"2026-08-12T22:41:11.430285757Z","level":"INFO","msg":"handler: started"}
+{"time":"2026-08-12T22:41:11.430381897Z","level":"INFO","msg":"stream: started"}
+{"time":"2026-08-12T22:41:11.430391581Z","level":"INFO","msg":"writer: started","stream_id":"g6mesp08"}
+{"time":"2026-08-12T22:41:11.430426905Z","level":"INFO","msg":"sender: started"}
+{"time":"2026-08-12T22:41:12.662303161Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
+{"time":"2026-08-12T22:41:12.751702232Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:41:27.663146362Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":2,"events_offset":0,"events_lines":2,"console_offset":0,"console_lines":3,"uploaded_len":2}
+{"time":"2026-08-12T22:41:27.775246965Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:41:42.662511534Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":2,"history_lines":2,"events_offset":2,"events_lines":2,"console_offset":0,"console_lines":1}
+{"time":"2026-08-12T22:41:42.783128036Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:41:57.662469694Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":4,"history_lines":3,"events_offset":4,"events_lines":2,"console_offset":0,"console_lines":1}
+{"time":"2026-08-12T22:41:57.779250604Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:42:12.663142839Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":7,"history_lines":2,"events_offset":6,"events_lines":2,"console_offset":3,"console_lines":12}
+{"time":"2026-08-12T22:42:12.847678714Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:42:27.662713702Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":9,"history_lines":2,"events_offset":8,"events_lines":2,"console_offset":10,"console_lines":1}
+{"time":"2026-08-12T22:42:27.802355946Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:42:42.663234627Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":11,"history_lines":3,"events_offset":10,"events_lines":2,"console_offset":15,"console_lines":10}
+{"time":"2026-08-12T22:42:42.77804022Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:42:57.66297082Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":14,"history_lines":2,"events_offset":12,"events_lines":2,"console_offset":20,"console_lines":1}
+{"time":"2026-08-12T22:42:57.799831047Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:43:12.662546129Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":16,"history_lines":2,"events_offset":14,"events_lines":2,"console_offset":25,"console_lines":9}
+{"time":"2026-08-12T22:43:12.83962087Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:43:27.66341876Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":18,"history_lines":3,"events_offset":16,"events_lines":2,"console_offset":30,"console_lines":1}
+{"time":"2026-08-12T22:43:27.792335861Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:43:42.663310497Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":21,"history_lines":2,"events_offset":18,"events_lines":2,"console_offset":34,"console_lines":10}
+{"time":"2026-08-12T22:43:42.799978026Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:43:57.662859749Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":23,"history_lines":2,"events_offset":20,"events_lines":2,"console_offset":40,"console_lines":1}
+{"time":"2026-08-12T22:43:57.805772287Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:44:12.663349352Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":25,"history_lines":3,"events_offset":22,"events_lines":2,"console_offset":44,"console_lines":10}
+{"time":"2026-08-12T22:44:12.808003723Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:44:27.66277157Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":28,"history_lines":2,"events_offset":24,"events_lines":2,"console_offset":50,"console_lines":1}
+{"time":"2026-08-12T22:44:27.784839934Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:44:42.662822837Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":30,"history_lines":2,"events_offset":26,"events_lines":2,"console_offset":54,"console_lines":9}
+{"time":"2026-08-12T22:44:42.814831858Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:44:57.663067595Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":32,"history_lines":3,"events_offset":28,"events_lines":2,"console_offset":60,"console_lines":1}
+{"time":"2026-08-12T22:44:57.806264315Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T22:45:12.66281333Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":35,"history_lines":2,"events_offset":30,"events_lines":2,"console_offset":63,"console_lines":10}
+{"time":"2026-08-12T22:45:12.810852756Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}

zain/Activation/wandb/run-20260812_224111-g6mesp08/logs/debug.log

@@ -0,0 +1,20 @@
+2026-08-12 22:41:11,168 INFO    MainThread:3978000 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_224111-g6mesp08/logs/debug.log
+2026-08-12 22:41:11,168 INFO    MainThread:3978000 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_224111-g6mesp08/logs/debug-internal.log
+2026-08-12 22:41:11,168 INFO    MainThread:3978000 [wandb_init.py:init():772] calling init triggers
+2026-08-12 22:41:11,168 INFO    MainThread:3978000 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
+config: {'_wandb': {}}
+2026-08-12 22:41:11,168 INFO    MainThread:3978000 [wandb_init.py:init():820] starting backend
+2026-08-12 22:41:11,168 INFO    MainThread:3978000 [wandb_init.py:init():826] Connected to an existing wandb-core service via WANDB_SERVICE
+2026-08-12 22:41:11,168 INFO    MainThread:3978000 [wandb_init.py:init():835] sending inform_init request
+2026-08-12 22:41:11,430 INFO    MainThread:3978000 [wandb_init.py:init():840] backend started and connected
+2026-08-12 22:41:11,431 INFO    MainThread:3978000 [wandb_init.py:init():910] updated telemetry
+2026-08-12 22:41:11,438 INFO    MainThread:3978000 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
+2026-08-12 22:41:11,946 INFO    MainThread:3978000 [wandb_init.py:init():978] starting run threads in backend
+2026-08-12 22:41:12,023 INFO    MainThread:3978000 [wandb_run.py:_console_start():2621] atexit reg
+2026-08-12 22:41:12,023 INFO    MainThread:3978000 [wandb_run.py:_redirect():2471] redirect: wrap_raw
+2026-08-12 22:41:12,023 INFO    MainThread:3978000 [wandb_run.py:_redirect():2540] Wrapping output streams.
+2026-08-12 22:41:12,023 INFO    MainThread:3978000 [wandb_run.py:_redirect():2563] Redirects installed.
+2026-08-12 22:41:12,024 INFO    MainThread:3978000 [wandb_init.py:init():1016] run started, returning control to user process
+2026-08-12 22:41:12,025 INFO    MainThread:3978000 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.16.0.dev0', 'architectures': None, 'output_hidden_states': False, 'return_dict': True, 'dtype': None, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, 'vocab_size': 4096, 'hidden_size': 128, 'intermediate_size': 256, 'num_hidden_layers': 100, 'num_attention_heads': 4, 'num_key_value_heads': 4, 'hidden_act': 'silu', 'max_position_embeddings': 512, 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'pad_token_id': 0, 'bos_token_id': 1, 'eos_token_id': 2, 'pretraining_tp': 1, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 10000.0, 'rope_type': 'default'}, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'head_dim': 32, '_name_or_path': '', 'tokenizer_name': 'w-ahmad/tiny-stories-tokenizer', 'mlp_type': 'glu', 'activation': 'situglu', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-situglu-100L_run', 'per_device_train_batch_size': 64, 'num_train_epochs': 1, 'max_steps': 2500, 'learning_rate': 0.0007, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 500, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 1.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-situglu-100L-16.9M-20260812-224110', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 2498, 'eval_delay': 0, 'per_device_eval_batch_size': 1024, 'prediction_loss_only': False, 'eval_on_start': False, 'eval_do_concat_batches': True, 'eval_use_gather_object': False, 'eval_accumulation_steps': None, 'include_for_metrics': [], 'batch_eval_metrics': False, 'save_only_model': False, 'save_strategy': 'steps', 'save_steps': 100, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/6L-glu-situglu-100L', 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': None, 'dataloader_multiprocessing_context': None, 'dataloader_in_order': True, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_static_graph': None, 'ddp_backend': None, 'ddp_timeout': 1800, 'fsdp': None, 'fsdp_config': None, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'local_rank': -1}
+2026-08-12 22:41:12,030 INFO    MainThread:3978000 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 16934016 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x14d8f5c68f10>>
+2026-08-12 22:41:12,030 INFO    MainThread:3978000 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 16934016 None

zain/Activation/wandb/run-20260812_224111-g6mesp08/run-g6mesp08.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e3697394f44baf30175c8c2f84ceee8ba4bb1f6d40e8044d211332b7f114694
+size 229376