Auto upload zain 2026-08-14T20:17:57.469534 (part 2)

zain/Activation/out/glu-waleed10-9L_run/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

zain/Activation/out/glu-waleed10-9L_run/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e444049d2d60784f1081894df74c28e3ed74440e02d01d5d83488b6f9d55a5f
+size 4920

zain/Activation/out/glu-waleed10-9L_run/training_log.jsonl

@@ -35,3 +35,19 @@
 {"step": 700, "epoch": 0.37735849056603776, "timestamp": 1786738348.3269963, "loss": 2.395576286315918, "grad_norm": 0.63671875, "learning_rate": 0.001, "train/total_time_seconds": 217.82805619761348, "train/time_per_step_avg": 0.31146045852452514, "train/epoch_time_elapsed": 482.2129458449781, "train/estimated_remaining_minutes": 1.5559146871258105}
 {"step": 720, "epoch": 0.3881401617250674, "timestamp": 1786738362.0518074, "loss": 2.3714391708374025, "grad_norm": 0.578125, "learning_rate": 0.001, "train/total_time_seconds": 224.04008734971285, "train/time_per_step_avg": 0.3116867682337761, "train/epoch_time_elapsed": 495.93775502964854, "train/estimated_remaining_minutes": 1.4521116772666574}
 {"step": 740, "epoch": 0.39892183288409705, "timestamp": 1786738375.7359393, "loss": 2.3693151473999023, "grad_norm": 0.59375, "learning_rate": 0.001, "train/total_time_seconds": 230.25869682058692, "train/time_per_step_avg": 0.31045090246945617, "train/epoch_time_elapsed": 509.62188804894686, "train/estimated_remaining_minutes": 1.348361738138572}
+{"step": 760, "epoch": 0.40970350404312667, "timestamp": 1786738389.2475324, "loss": 2.3519989013671876, "grad_norm": 0.53515625, "learning_rate": 0.001, "train/total_time_seconds": 236.25774824991822, "train/time_per_step_avg": 0.310084324143827, "train/epoch_time_elapsed": 523.1334819346666, "train/estimated_remaining_minutes": 1.2434618328943066}
+{"step": 780, "epoch": 0.42048517520215634, "timestamp": 1786738403.1076856, "loss": 2.346103858947754, "grad_norm": 0.78125, "learning_rate": 0.001, "train/total_time_seconds": 242.42881532013416, "train/time_per_step_avg": 0.3087368572130799, "train/epoch_time_elapsed": 536.9936351887882, "train/estimated_remaining_minutes": 1.139622636120289}
+{"step": 800, "epoch": 0.431266846361186, "timestamp": 1786738417.1171541, "loss": 2.328810119628906, "grad_norm": 0.5703125, "learning_rate": 0.001, "train/total_time_seconds": 248.85032514110208, "train/time_per_step_avg": 0.31022268943488596, "train/epoch_time_elapsed": 551.0031033791602, "train/estimated_remaining_minutes": 1.0368763547545918}
+{"step": 820, "epoch": 0.4420485175202156, "timestamp": 1786738430.8873918, "loss": 2.31988410949707, "grad_norm": 0.6171875, "learning_rate": 0.001, "train/total_time_seconds": 254.93540498241782, "train/time_per_step_avg": 0.3089531763270497, "train/epoch_time_elapsed": 564.7733410894871, "train/estimated_remaining_minutes": 0.9326905060332359}
+{"step": 840, "epoch": 0.4528301886792453, "timestamp": 1786738444.9400606, "loss": 2.3125839233398438, "grad_norm": 0.58984375, "learning_rate": 0.001, "train/total_time_seconds": 261.36890902742743, "train/time_per_step_avg": 0.31110212206840515, "train/epoch_time_elapsed": 578.8260099850595, "train/estimated_remaining_minutes": 0.8297425683410395}
+{"step": 860, "epoch": 0.4636118598382749, "timestamp": 1786738458.5670846, "loss": 2.29653263092041, "grad_norm": 0.796875, "learning_rate": 0.001, "train/total_time_seconds": 267.5220149643719, "train/time_per_step_avg": 0.312642667144537, "train/epoch_time_elapsed": 592.4530341215432, "train/estimated_remaining_minutes": 0.7258349243219393}
+{"step": 880, "epoch": 0.4743935309973046, "timestamp": 1786738472.4700503, "loss": 2.291933059692383, "grad_norm": 0.609375, "learning_rate": 0.001, "train/total_time_seconds": 273.8007878176868, "train/time_per_step_avg": 0.31371972497552636, "train/epoch_time_elapsed": 606.3559994921088, "train/estimated_remaining_minutes": 0.62227451776747}
+{"step": 900, "epoch": 0.48517520215633425, "timestamp": 1786738486.2694337, "loss": 2.280624008178711, "grad_norm": 0.64453125, "learning_rate": 0.001, "train/total_time_seconds": 279.88062911108136, "train/time_per_step_avg": 0.31030303969979284, "train/epoch_time_elapsed": 620.1553830169141, "train/estimated_remaining_minutes": 0.5182974613168173}
+{"step": 920, "epoch": 0.49595687331536387, "timestamp": 1786738500.1559243, "loss": 2.271377944946289, "grad_norm": 0.58203125, "learning_rate": 0.001, "train/total_time_seconds": 285.96561647206545, "train/time_per_step_avg": 0.31030211489647624, "train/epoch_time_elapsed": 634.0418738946319, "train/estimated_remaining_minutes": 0.41444292242328323}
+{"step": 940, "epoch": 0.5067385444743935, "timestamp": 1786738513.9616292, "loss": 2.2698923110961915, "grad_norm": 0.65234375, "learning_rate": 0.001, "train/total_time_seconds": 291.9561942741275, "train/time_per_step_avg": 0.30587285246700047, "train/epoch_time_elapsed": 647.8475783206522, "train/estimated_remaining_minutes": 0.3105916960363058}
+{"step": 960, "epoch": 0.5175202156334232, "timestamp": 1786738527.9307106, "loss": 2.2646963119506838, "grad_norm": 0.63671875, "learning_rate": 0.001, "train/total_time_seconds": 298.29048217087984, "train/time_per_step_avg": 0.3076846720650792, "train/epoch_time_elapsed": 661.8166598901153, "train/estimated_remaining_minutes": 0.2071461681742221}
+{"step": 980, "epoch": 0.5283018867924528, "timestamp": 1786738541.844498, "loss": 2.2574932098388674, "grad_norm": 0.8515625, "learning_rate": 0.001, "train/total_time_seconds": 304.56151608750224, "train/time_per_step_avg": 0.30760728269815446, "train/epoch_time_elapsed": 675.7304472476244, "train/estimated_remaining_minutes": 0.10359235241071504}
+{"step": 1000, "epoch": 0.5390835579514824, "timestamp": 1786738555.6450493, "loss": 2.251524543762207, "grad_norm": 0.65625, "learning_rate": 0.001, "train/total_time_seconds": 310.6948715560138, "train/time_per_step_avg": 0.3081424244493246, "train/epoch_time_elapsed": 689.5309977941215, "train/estimated_remaining_minutes": 0.0}
+{"step": 1000, "epoch": 0.5390835579514824, "timestamp": 1786738564.9100592, "eval_loss": 2.248227596282959, "eval_runtime": 9.2633, "eval_samples_per_second": 1028.467, "eval_steps_per_second": 2.051, "train/total_time_seconds": 310.6948715560138, "train/time_per_step_avg": 0.3081424244493246, "train/epoch_time_elapsed": 698.7960081025958, "train/estimated_remaining_minutes": 0.0}
+{"step": 1000, "epoch": 0.5390835579514824, "timestamp": 1786738564.9573493, "train_runtime": 699.9327, "train_samples_per_second": 731.499, "train_steps_per_second": 1.429, "total_flos": 2323107545088000.0, "train_loss": 2.965903495788574, "train/total_time_seconds": 310.6948715560138, "train/time_per_step_avg": 0.3081424244493246, "train/epoch_time_elapsed": 698.8432977646589, "train/estimated_remaining_minutes": 0.0}
+{"step": 1000, "epoch": 0.5390835579514824, "timestamp": 1786738574.5099926, "eval_loss": 2.248227596282959, "eval_runtime": 9.5496, "eval_samples_per_second": 997.637, "eval_steps_per_second": 1.99, "train/total_time_seconds": 310.6948715560138, "train/time_per_step_avg": 0.3081424244493246, "train/epoch_time_elapsed": 708.3959413841367, "train/estimated_remaining_minutes": 0.0}

zain/Activation/wandb/debug-internal.log

@@ -1,71 +1,23 @@
-{"time":"2026-08-14T20:05:03.038905839Z","level":"INFO","msg":"wandb-core"}
-{"time":"2026-08-14T20:05:03.039040293Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
-{"time":"2026-08-14T20:05:03.298949412Z","level":"INFO","msg":"stream: created new stream","id":"bdhnr27j"}
-{"time":"2026-08-14T20:05:03.299037569Z","level":"INFO","msg":"handler: started"}
-{"time":"2026-08-14T20:05:03.299125054Z","level":"INFO","msg":"stream: started"}
-{"time":"2026-08-14T20:05:03.299135696Z","level":"INFO","msg":"writer: started","stream_id":"bdhnr27j"}
-{"time":"2026-08-14T20:05:03.299170646Z","level":"INFO","msg":"sender: started"}
-{"time":"2026-08-14T20:05:03.650201569Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
-{"time":"2026-08-14T20:05:03.748251027Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:05:18.650428232Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":1,"events_offset":0,"events_lines":1,"console_offset":0,"console_lines":2,"uploaded_len":2}
-{"time":"2026-08-14T20:05:18.75376572Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:05:33.650669159Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":1,"history_lines":3,"events_offset":1,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-14T20:05:33.790832697Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:05:48.651007341Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":4,"history_lines":2,"events_offset":3,"events_lines":2,"console_offset":0,"console_lines":1}
-{"time":"2026-08-14T20:05:48.753491293Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:06:03.650618135Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":6,"history_lines":2,"events_offset":5,"events_lines":2,"console_offset":2,"console_lines":12}
-{"time":"2026-08-14T20:06:03.812307638Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:06:18.650895578Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":8,"history_lines":2,"events_offset":7,"events_lines":2,"console_offset":10,"console_lines":1}
-{"time":"2026-08-14T20:06:18.766396346Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:06:33.651030659Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":10,"history_lines":2,"events_offset":9,"events_lines":2,"console_offset":14,"console_lines":9}
-{"time":"2026-08-14T20:06:33.779793842Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:06:48.651185Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":12,"history_lines":2,"events_offset":11,"events_lines":2,"console_offset":20,"console_lines":1}
-{"time":"2026-08-14T20:06:48.793030243Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:07:03.650991232Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":14,"history_lines":2,"events_offset":13,"events_lines":2,"console_offset":20,"console_lines":1}
-{"time":"2026-08-14T20:07:03.813182818Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:07:18.650766634Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":16,"history_lines":2,"events_offset":15,"events_lines":2,"console_offset":23,"console_lines":11}
-{"time":"2026-08-14T20:07:18.771811803Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:07:33.650522671Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":18,"history_lines":2,"events_offset":17,"events_lines":2,"console_offset":30,"console_lines":1}
-{"time":"2026-08-14T20:07:33.796142744Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:07:48.650647629Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":20,"history_lines":2,"events_offset":19,"events_lines":2,"console_offset":34,"console_lines":9}
-{"time":"2026-08-14T20:07:48.758682405Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:08:03.650886242Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":22,"history_lines":2,"events_offset":21,"events_lines":2,"console_offset":40,"console_lines":1}
-{"time":"2026-08-14T20:08:03.798879176Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:08:18.650486756Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":24,"history_lines":2,"events_offset":23,"events_lines":2,"console_offset":40,"console_lines":1}
-{"time":"2026-08-14T20:08:18.791497653Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:08:33.650900222Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":26,"history_lines":2,"events_offset":25,"events_lines":2,"console_offset":43,"console_lines":11}
-{"time":"2026-08-14T20:08:33.773277171Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:08:48.650962861Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":28,"history_lines":2,"events_offset":27,"events_lines":2,"console_offset":50,"console_lines":1}
-{"time":"2026-08-14T20:08:48.762738006Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:09:03.65084968Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":30,"history_lines":2,"events_offset":29,"events_lines":2,"console_offset":54,"console_lines":9}
-{"time":"2026-08-14T20:09:03.767357796Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:09:18.650505208Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":32,"history_lines":2,"events_offset":31,"events_lines":2,"console_offset":60,"console_lines":1}
-{"time":"2026-08-14T20:09:18.793298146Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:09:33.650653733Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":34,"history_lines":2,"events_offset":33,"events_lines":2,"console_offset":60,"console_lines":1}
-{"time":"2026-08-14T20:09:33.787641662Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:09:48.65118706Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":36,"history_lines":2,"events_offset":35,"events_lines":2,"console_offset":63,"console_lines":11}
-{"time":"2026-08-14T20:09:48.778847856Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:10:03.650425411Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":38,"history_lines":2,"events_offset":37,"events_lines":2,"console_offset":70,"console_lines":1}
-{"time":"2026-08-14T20:10:03.932173776Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:10:18.651095565Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":40,"history_lines":2,"events_offset":39,"events_lines":2,"console_offset":74,"console_lines":9}
-{"time":"2026-08-14T20:10:18.863855648Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:10:33.650779894Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":42,"history_lines":2,"events_offset":41,"events_lines":2,"console_offset":80,"console_lines":1}
-{"time":"2026-08-14T20:10:33.794270018Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:10:48.651204914Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":44,"history_lines":2,"events_offset":43,"events_lines":2,"console_offset":80,"console_lines":1}
-{"time":"2026-08-14T20:10:48.761426246Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:11:03.651311162Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":46,"history_lines":2,"events_offset":45,"events_lines":2,"console_offset":83,"console_lines":11}
-{"time":"2026-08-14T20:11:03.762416483Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:11:18.650460962Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":48,"history_lines":2,"events_offset":47,"events_lines":2,"console_offset":90,"console_lines":1}
-{"time":"2026-08-14T20:11:18.761140037Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:11:33.650653569Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":50,"history_lines":2,"events_offset":49,"events_lines":2,"console_offset":94,"console_lines":9}
-{"time":"2026-08-14T20:11:33.768118914Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:11:48.650585968Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":52,"history_lines":2,"events_offset":51,"events_lines":2,"console_offset":100,"console_lines":1}
-{"time":"2026-08-14T20:11:48.766084818Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:12:03.650611562Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":54,"history_lines":2,"events_offset":53,"events_lines":2,"console_offset":100,"console_lines":1}
-{"time":"2026-08-14T20:12:03.785385371Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:12:18.650538964Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":56,"history_lines":2,"events_offset":55,"events_lines":2,"console_offset":103,"console_lines":11}
-{"time":"2026-08-14T20:12:18.772965979Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:12:33.650735231Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":58,"history_lines":2,"events_offset":57,"events_lines":2,"console_offset":110,"console_lines":1}
-{"time":"2026-08-14T20:12:33.807298622Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-14T20:12:48.650587497Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":60,"history_lines":2,"events_offset":59,"events_lines":2,"console_offset":114,"console_lines":9}
-{"time":"2026-08-14T20:12:48.778517356Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:16:15.759688663Z","level":"INFO","msg":"wandb-core"}
+{"time":"2026-08-14T20:16:15.75981584Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
+{"time":"2026-08-14T20:16:16.019892925Z","level":"INFO","msg":"stream: created new stream","id":"w8mr4w6k"}
+{"time":"2026-08-14T20:16:16.01997882Z","level":"INFO","msg":"handler: started"}
+{"time":"2026-08-14T20:16:16.020075043Z","level":"INFO","msg":"stream: started"}
+{"time":"2026-08-14T20:16:16.02008577Z","level":"INFO","msg":"writer: started","stream_id":"w8mr4w6k"}
+{"time":"2026-08-14T20:16:16.020113292Z","level":"INFO","msg":"sender: started"}
+{"time":"2026-08-14T20:16:16.531359023Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
+{"time":"2026-08-14T20:16:16.686067824Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:16:31.532246567Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":1,"events_offset":0,"events_lines":1,"console_offset":0,"console_lines":2,"uploaded_len":2}
+{"time":"2026-08-14T20:16:31.65014999Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:16:46.53154926Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":1,"history_lines":1,"events_offset":1,"events_lines":2,"console_offset":0,"console_lines":1}
+{"time":"2026-08-14T20:16:46.697907798Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:17:01.532416577Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":2,"history_lines":1,"events_offset":3,"events_lines":2,"console_offset":0,"console_lines":1}
+{"time":"2026-08-14T20:17:01.661940731Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:17:16.532407844Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3,"history_lines":1,"events_offset":5,"events_lines":2,"console_offset":0,"console_lines":1}
+{"time":"2026-08-14T20:17:16.655117007Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:17:31.531597694Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":4,"history_lines":1,"events_offset":7,"events_lines":2,"console_offset":0,"console_lines":1}
+{"time":"2026-08-14T20:17:31.671651312Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:17:46.532231919Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":5,"history_lines":1,"events_offset":9,"events_lines":2,"console_offset":2,"console_lines":10}
+{"time":"2026-08-14T20:17:46.65675743Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:18:01.532320003Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":6,"history_lines":1,"events_offset":11,"events_lines":2,"console_offset":10,"console_lines":1}
+{"time":"2026-08-14T20:18:01.703907556Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}

zain/Activation/wandb/debug.log

@@ -1,20 +1,19 @@
-2026-08-14 20:05:03,037 INFO    MainThread:171901 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260814_200503-bdhnr27j/logs/debug.log
-2026-08-14 20:05:03,037 INFO    MainThread:171901 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260814_200503-bdhnr27j/logs/debug-internal.log
-2026-08-14 20:05:03,037 INFO    MainThread:171901 [wandb_init.py:init():772] calling init triggers
-2026-08-14 20:05:03,037 INFO    MainThread:171901 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
+2026-08-14 20:16:15,758 INFO    MainThread:409188 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260814_201615-w8mr4w6k/logs/debug.log
+2026-08-14 20:16:15,758 INFO    MainThread:409188 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260814_201615-w8mr4w6k/logs/debug-internal.log
+2026-08-14 20:16:15,758 INFO    MainThread:409188 [wandb_init.py:init():772] calling init triggers
+2026-08-14 20:16:15,758 INFO    MainThread:409188 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
 config: {'_wandb': {}}
-2026-08-14 20:05:03,037 INFO    MainThread:171901 [wandb_init.py:init():820] starting backend
-2026-08-14 20:05:03,037 INFO    MainThread:171901 [wandb_init.py:init():826] Connected to an existing wandb-core service via WANDB_SERVICE
-2026-08-14 20:05:03,037 INFO    MainThread:171901 [wandb_init.py:init():835] sending inform_init request
-2026-08-14 20:05:03,299 INFO    MainThread:171901 [wandb_init.py:init():840] backend started and connected
-2026-08-14 20:05:03,300 INFO    MainThread:171901 [wandb_init.py:init():910] updated telemetry
-2026-08-14 20:05:03,307 INFO    MainThread:171901 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
-2026-08-14 20:05:03,564 INFO    MainThread:171901 [wandb_init.py:init():978] starting run threads in backend
-2026-08-14 20:05:03,641 INFO    MainThread:171901 [wandb_run.py:_console_start():2621] atexit reg
-2026-08-14 20:05:03,642 INFO    MainThread:171901 [wandb_run.py:_redirect():2471] redirect: wrap_raw
-2026-08-14 20:05:03,642 INFO    MainThread:171901 [wandb_run.py:_redirect():2540] Wrapping output streams.
-2026-08-14 20:05:03,642 INFO    MainThread:171901 [wandb_run.py:_redirect():2563] Redirects installed.
-2026-08-14 20:05:03,643 INFO    MainThread:171901 [wandb_init.py:init():1016] run started, returning control to user process
-2026-08-14 20:05:03,643 INFO    MainThread:171901 [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': 'sigmoid', 'waleed_beta': 4, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-sigmoid-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-sigmoid-100L-16.9M-20260814-200502', '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-sigmoid-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}
-2026-08-14 20:05:03,649 INFO    MainThread:171901 [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 0x1505b0258e90>>
-2026-08-14 20:05:03,649 INFO    MainThread:171901 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 16934016 None
+2026-08-14 20:16:15,758 INFO    MainThread:409188 [wandb_init.py:init():820] starting backend
+2026-08-14 20:16:15,758 INFO    MainThread:409188 [wandb_init.py:init():835] sending inform_init request
+2026-08-14 20:16:16,020 INFO    MainThread:409188 [wandb_init.py:init():840] backend started and connected
+2026-08-14 20:16:16,021 INFO    MainThread:409188 [wandb_init.py:init():910] updated telemetry
+2026-08-14 20:16:16,028 INFO    MainThread:409188 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
+2026-08-14 20:16:16,449 INFO    MainThread:409188 [wandb_init.py:init():978] starting run threads in backend
+2026-08-14 20:16:16,526 INFO    MainThread:409188 [wandb_run.py:_console_start():2621] atexit reg
+2026-08-14 20:16:16,526 INFO    MainThread:409188 [wandb_run.py:_redirect():2471] redirect: wrap_raw
+2026-08-14 20:16:16,526 INFO    MainThread:409188 [wandb_run.py:_redirect():2540] Wrapping output streams.
+2026-08-14 20:16:16,526 INFO    MainThread:409188 [wandb_run.py:_redirect():2563] Redirects installed.
+2026-08-14 20:16:16,527 INFO    MainThread:409188 [wandb_init.py:init():1016] run started, returning control to user process
+2026-08-14 20:16:16,528 INFO    MainThread:409188 [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': 9, '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-waleed10-9L_run', 'per_device_train_batch_size': 512, 'num_train_epochs': 1, 'max_steps': 1000, 'learning_rate': 0.001, 'lr_scheduler_type': 'constant', 'lr_scheduler_kwargs': None, 'warmup_steps': 0, 'optim': 'adamw_torch', 'optim_args': None, 'weight_decay': 0.01, '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-waleed10-9L-2.0M-20260814-201615', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 60000, 'eval_delay': 0, 'per_device_eval_batch_size': 512, '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/A-glu-silu-waleed10-9L', '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}
+2026-08-14 20:16:16,530 INFO    MainThread:409188 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 2001280 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x153f494c8950>>
+2026-08-14 20:16:16,530 INFO    MainThread:409188 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 2001280 None

zain/Activation/wandb/run-20260814_200425-npumf6lz/files/config.yaml

@@ -0,0 +1,439 @@
+_name_or_path:
+    value: ""
+_wandb:
+    value:
+        cli_version: 0.28.1
+        e:
+            alqerd29ipcqwhuzsiug6whawhrjqt6i:
+                args:
+                    - --config
+                    - /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/configs/baseline.yaml
+                    - --variants
+                    - glu-waleed10
+                    - glu-silu-waleed10
+                    - mlp-waleed10
+                    - mlp-silu-waleed10
+                    - glu-waleed
+                    - glu-situglu_low
+                    - glu-waleedglu_low
+                codePath: sweep.py
+                codePathLocal: sweep.py
+                cpu_count: 112
+                cpu_count_logical: 224
+                cudaVersion: "12.4"
+                disk:
+                    /:
+                        total: "1560765693952"
+                        used: "696150245376"
+                email: deepnevro@gmail.com
+                executable: /mnt/data/zainulabideen/zain-exp/notebooks/my_env/bin/python
+                git:
+                    commit: 3fb47c6943d6927eafc39bd399a3d3a520bae74a
+                    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: "2026-08-14T20:04:25.501406Z"
+                writerId: alqerd29ipcqwhuzsiug6whawhrjqt6i
+        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: 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: 60000
+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/A-glu-waleed10-9L
+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: 0.001
+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
+max_grad_norm:
+    value: 1
+max_position_embeddings:
+    value: 512
+max_steps:
+    value: 1000
+metric_for_best_model:
+    value: null
+mlp_bias:
+    value: false
+mlp_type:
+    value: glu
+model/num_parameters:
+    value: 2001280
+model_type:
+    value: tiny_llama
+neftune_noise_alpha:
+    value: null
+num_attention_heads:
+    value: 4
+num_hidden_layers:
+    value: 9
+num_key_value_heads:
+    value: 4
+num_train_epochs:
+    value: 1
+optim:
+    value: adamw_torch
+optim_args:
+    value: null
+optim_target_modules:
+    value: null
+output_attentions:
+    value: false
+output_dir:
+    value: out/glu-waleed10-9L_run
+output_hidden_states:
+    value: false
+pad_token_id:
+    value: 0
+parallelism_config:
+    value: null
+per_device_eval_batch_size:
+    value: 512
+per_device_train_batch_size:
+    value: 512
+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-waleed10-9L-2.0M-20260814-200424
+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: 0
+weight_decay:
+    value: 0.01

zain/Activation/wandb/run-20260814_200425-npumf6lz/files/output.log

@@ -70,5 +70,43 @@ Writing model shards: 100%|██████████| 1/1 [00:00<00:00, 168
   - 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, 171.17it/s]
- 73%|███████▎  | 733/1000 [08:24<03:04,  1.45it/s]?, ?it/s]
+ 80%|████████  | 800/1000 [09:11<02:20,  1.43it/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': '2.371', 'grad_norm': '0.5781', 'learning_rate': '0.001', 'epoch': '0.3881', 'train/total_time_seconds': '224', 'train/time_per_step_avg': '0.3117', 'train/epoch_time_elapsed': '495.9', 'train/estimated_remaining_minutes': '1.452'}
+{'loss': '2.369', 'grad_norm': '0.5938', 'learning_rate': '0.001', 'epoch': '0.3989', 'train/total_time_seconds': '230.3', 'train/time_per_step_avg': '0.3105', 'train/epoch_time_elapsed': '509.6', 'train/estimated_remaining_minutes': '1.348'}
+{'loss': '2.352', 'grad_norm': '0.5352', 'learning_rate': '0.001', 'epoch': '0.4097', 'train/total_time_seconds': '236.3', 'train/time_per_step_avg': '0.3101', 'train/epoch_time_elapsed': '523.1', 'train/estimated_remaining_minutes': '1.243'}
+{'loss': '2.346', 'grad_norm': '0.7812', 'learning_rate': '0.001', 'epoch': '0.4205', 'train/total_time_seconds': '242.4', 'train/time_per_step_avg': '0.3087', 'train/epoch_time_elapsed': '537', 'train/estimated_remaining_minutes': '1.14'}
+{'loss': '2.329', 'grad_norm': '0.5703', 'learning_rate': '0.001', 'epoch': '0.4313', 'train/total_time_seconds': '248.9', 'train/time_per_step_avg': '0.3102', 'train/epoch_time_elapsed': '551', 'train/estimated_remaining_minutes': '1.037'}
+  - 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, 161.49it/s]
+ 90%|█████████ | 900/1000 [10:20<01:06,  1.51it/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': '2.32', 'grad_norm': '0.6172', 'learning_rate': '0.001', 'epoch': '0.442', 'train/total_time_seconds': '254.9', 'train/time_per_step_avg': '0.309', 'train/epoch_time_elapsed': '564.8', 'train/estimated_remaining_minutes': '0.9327'}
+{'loss': '2.313', 'grad_norm': '0.5898', 'learning_rate': '0.001', 'epoch': '0.4528', 'train/total_time_seconds': '261.4', 'train/time_per_step_avg': '0.3111', 'train/epoch_time_elapsed': '578.8', 'train/estimated_remaining_minutes': '0.8297'}
+{'loss': '2.297', 'grad_norm': '0.7969', 'learning_rate': '0.001', 'epoch': '0.4636', 'train/total_time_seconds': '267.5', 'train/time_per_step_avg': '0.3126', 'train/epoch_time_elapsed': '592.5', 'train/estimated_remaining_minutes': '0.7258'}
+{'loss': '2.292', 'grad_norm': '0.6094', 'learning_rate': '0.001', 'epoch': '0.4744', 'train/total_time_seconds': '273.8', 'train/time_per_step_avg': '0.3137', 'train/epoch_time_elapsed': '606.4', 'train/estimated_remaining_minutes': '0.6223'}
+{'loss': '2.281', 'grad_norm': '0.6445', 'learning_rate': '0.001', 'epoch': '0.4852', 'train/total_time_seconds': '279.9', 'train/time_per_step_avg': '0.3103', 'train/epoch_time_elapsed': '620.2', 'train/estimated_remaining_minutes': '0.5183'}
+  - 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, 76.87it/s]
+100%|██████████| 1000/1000 [11:38<00:00,  1.48i[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': '2.271', 'grad_norm': '0.582', 'learning_rate': '0.001', 'epoch': '0.496', 'train/total_time_seconds': '286', 'train/time_per_step_avg': '0.3103', 'train/epoch_time_elapsed': '634', 'train/estimated_remaining_minutes': '0.4144'}
+{'loss': '2.27', 'grad_norm': '0.6523', 'learning_rate': '0.001', 'epoch': '0.5067', 'train/total_time_seconds': '292', 'train/time_per_step_avg': '0.3059', 'train/epoch_time_elapsed': '647.8', 'train/estimated_remaining_minutes': '0.3106'}
+{'loss': '2.265', 'grad_norm': '0.6367', 'learning_rate': '0.001', 'epoch': '0.5175', 'train/total_time_seconds': '298.3', 'train/time_per_step_avg': '0.3077', 'train/epoch_time_elapsed': '661.8', 'train/estimated_remaining_minutes': '0.2071'}
+{'loss': '2.257', 'grad_norm': '0.8516', 'learning_rate': '0.001', 'epoch': '0.5283', 'train/total_time_seconds': '304.6', 'train/time_per_step_avg': '0.3076', 'train/epoch_time_elapsed': '675.7', 'train/estimated_remaining_minutes': '0.1036'}
+{'loss': '2.252', 'grad_norm': '0.6562', 'learning_rate': '0.001', 'epoch': '0.5391', 'train/total_time_seconds': '310.7', 'train/time_per_step_avg': '0.3081', 'train/epoch_time_elapsed': '689.5', 'train/estimated_remaining_minutes': '0'}
+  - 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': '2.248', 'eval_runtime': '9.263', 'eval_samples_per_second': '1028', 'eval_steps_per_second': '2.051', 'epoch': '0.5391', 'train/total_time_seconds': '310.7', 'train/time_per_step_avg': '0.3081', 'train/epoch_time_elapsed': '698.8', '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, 162.67it/s]
+100%|██████████| 1000/1000 [11:38<00:00,  1.43it/s], ?it/s]
+{'train_runtime': '699.9', 'train_samples_per_second': '731.5', 'train_steps_per_second': '1.429', 'train_loss': '2.966', 'epoch': '0.5391', 'train/total_time_seconds': '310.7', 'train/time_per_step_avg': '0.3081', 'train/epoch_time_elapsed': '698.8', 'train/estimated_remaining_minutes': '0'}
+100%|██████████| 19/19 [00:08<00:00,  2.16it/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.
+  - 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, 148.63it/s]
+>>> FINISHED glu-waleed10-9L successfully

zain/Activation/wandb/run-20260814_200425-npumf6lz/files/wandb-summary.json

@@ -0,0 +1 @@
+{"eval/loss":2.248227596282959,"train/learning_rate":0.001,"eval/samples_per_second":997.637,"total_flos":2.323107545088e+15,"_runtime":708,"eval/runtime":9.5496,"train/epoch":0.5390835579514824,"_step":52,"_timestamp":1.7867385745094874e+09,"train/grad_norm":0.65625,"train_samples_per_second":731.499,"_wandb":{"runtime":708},"train_runtime":699.9327,"train_loss":2.965903495788574,"train/loss":2.251524543762207,"eval/steps_per_second":1.99,"train_steps_per_second":1.429,"train/global_step":1000}

zain/Activation/wandb/run-20260814_200425-npumf6lz/logs/debug-core.log

@@ -5,3 +5,10 @@
 {"time":"2026-08-14T20:04:25.504127391Z","level":"INFO","msg":"handleInformInit: received","streamId":"npumf6lz","id":"1(@)"}
 {"time":"2026-08-14T20:04:25.765319769Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"npumf6lz","id":"1(@)"}
 {"time":"2026-08-14T20:04:31.109816098Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"d0p7d03ygyti"}
+{"time":"2026-08-14T20:16:14.526898083Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"d0p7d03ygyti"}
+{"time":"2026-08-14T20:16:15.115854524Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"d0p7d03ygyti"}
+{"time":"2026-08-14T20:16:15.117591712Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"npumf6lz","id":"1(@)"}
+{"time":"2026-08-14T20:16:15.118263697Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"npumf6lz","id":"1(@)"}
+{"time":"2026-08-14T20:16:15.759561877Z","level":"INFO","msg":"handleInformInit: received","streamId":"w8mr4w6k","id":"1(@)"}
+{"time":"2026-08-14T20:16:16.020082435Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w8mr4w6k","id":"1(@)"}
+{"time":"2026-08-14T20:16:21.531557612Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"ewwa8fnip5gl"}

zain/Activation/wandb/run-20260814_200425-npumf6lz/logs/debug-internal.log

@@ -73,3 +73,39 @@
 {"time":"2026-08-14T20:12:26.378510776Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
 {"time":"2026-08-14T20:12:41.115319434Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":34,"history_lines":1,"events_offset":63,"events_lines":2,"console_offset":62,"console_lines":1}
 {"time":"2026-08-14T20:12:41.267342294Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:12:56.114920871Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":35,"history_lines":2,"events_offset":65,"events_lines":2,"console_offset":64,"console_lines":11}
+{"time":"2026-08-14T20:12:56.259763692Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:13:11.115344687Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":37,"history_lines":1,"events_offset":67,"events_lines":2,"console_offset":72,"console_lines":1}
+{"time":"2026-08-14T20:13:11.305643125Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:13:26.115288325Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":38,"history_lines":1,"events_offset":69,"events_lines":2,"console_offset":72,"console_lines":1}
+{"time":"2026-08-14T20:13:26.308670168Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:13:41.114999631Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":39,"history_lines":1,"events_offset":71,"events_lines":2,"console_offset":72,"console_lines":1}
+{"time":"2026-08-14T20:13:41.384462715Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:13:56.115351195Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":40,"history_lines":1,"events_offset":73,"events_lines":2,"console_offset":75,"console_lines":9}
+{"time":"2026-08-14T20:13:56.250188223Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:14:11.114660562Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":41,"history_lines":1,"events_offset":75,"events_lines":2,"console_offset":82,"console_lines":1}
+{"time":"2026-08-14T20:14:11.326970059Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:14:26.114941022Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":42,"history_lines":1,"events_offset":77,"events_lines":2,"console_offset":82,"console_lines":1}
+{"time":"2026-08-14T20:14:26.333466762Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:14:41.114791674Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":43,"history_lines":1,"events_offset":79,"events_lines":2,"console_offset":82,"console_lines":1}
+{"time":"2026-08-14T20:14:41.244078273Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:14:56.114978786Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":44,"history_lines":1,"events_offset":81,"events_lines":2,"console_offset":82,"console_lines":1}
+{"time":"2026-08-14T20:14:56.383885256Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:15:11.114924037Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":45,"history_lines":1,"events_offset":83,"events_lines":2,"console_offset":84,"console_lines":10}
+{"time":"2026-08-14T20:15:11.289537223Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:15:26.114743152Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":46,"history_lines":1,"events_offset":85,"events_lines":2,"console_offset":92,"console_lines":1}
+{"time":"2026-08-14T20:15:26.228786693Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:15:41.11488822Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":47,"history_lines":1,"events_offset":87,"events_lines":2,"console_offset":92,"console_lines":1}
+{"time":"2026-08-14T20:15:41.272844007Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:15:56.115099158Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":48,"history_lines":2,"events_offset":89,"events_lines":2,"console_offset":92,"console_lines":1}
+{"time":"2026-08-14T20:15:56.263681167Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:16:11.115004658Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":50,"history_lines":2,"events_offset":91,"events_lines":2,"console_offset":92,"console_lines":1}
+{"time":"2026-08-14T20:16:11.3225746Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:16:14.974789931Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2026-08-14T20:16:14.975039073Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":52,"history_lines":1,"events_offset":93,"events_lines":1,"console_offset":94,"console_lines":18,"uploaded_len":3,"complete":true,"exit_code":0}
+{"time":"2026-08-14T20:16:15.11276974Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:16:15.114228774Z","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2026-08-14T20:16:15.117620748Z","level":"INFO","msg":"stream: finishing up"}
+{"time":"2026-08-14T20:16:15.117645054Z","level":"INFO","msg":"handler: closed"}
+{"time":"2026-08-14T20:16:15.117712941Z","level":"INFO","msg":"sender: closed"}
+{"time":"2026-08-14T20:16:15.117717043Z","level":"INFO","msg":"stream: all finished"}

zain/Activation/wandb/run-20260814_200425-npumf6lz/logs/debug.log

@@ -20,3 +20,8 @@ config: {'_wandb': {}}
 2026-08-14 20:04:26,111 INFO    MainThread:409188 [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': 9, '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': 'waleed10', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-waleed10-9L_run', 'per_device_train_batch_size': 512, 'num_train_epochs': 1, 'max_steps': 1000, 'learning_rate': 0.001, 'lr_scheduler_type': 'constant', 'lr_scheduler_kwargs': None, 'warmup_steps': 0, 'optim': 'adamw_torch', 'optim_args': None, 'weight_decay': 0.01, '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-waleed10-9L-2.0M-20260814-200424', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 60000, 'eval_delay': 0, 'per_device_eval_batch_size': 512, '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/A-glu-waleed10-9L', '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}
 2026-08-14 20:04:26,113 INFO    MainThread:409188 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 2001280 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x153f49fa5610>>
 2026-08-14 20:04:26,113 INFO    MainThread:409188 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 2001280 None
+2026-08-14 20:16:14,526 INFO    MainThread:409188 [wandb_run.py:_finish():2383] finishing run deepnevro-deepnevro/research1/npumf6lz
+2026-08-14 20:16:14,526 INFO    MainThread:409188 [wandb_run.py:_atexit_cleanup():2588] got exitcode: 0
+2026-08-14 20:16:14,526 INFO    MainThread:409188 [wandb_run.py:_restore():2570] restore
+2026-08-14 20:16:14,526 INFO    MainThread:409188 [wandb_run.py:_restore():2576] restore done
+2026-08-14 20:16:15,117 INFO    MainThread:409188 [wandb_run.py:_footer_sync_info():3993] logging synced files

zain/Activation/wandb/run-20260814_200425-npumf6lz/run-npumf6lz.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51a82862ddb75a34d6a0a73d48b55a0423aaf266575d450d3b217d0a7619449f
-size 360448
+oid sha256:122aa63bbb4376e16b61ed2d668e034deef623c0506f421d858deb742b8450bb
+size 525882

zain/Activation/wandb/run-20260814_200503-bdhnr27j/files/output.log

@@ -118,7 +118,88 @@ Writing model shards: 100%|██████████| 1/1 [00:00<00:00, 16.
   - 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, 17.84it/s]
- 51%|█████     | 1267/2500 [07:49<08:06,  2.53it/s], ?it/s]
+ 52%|█████▏    | 1300/2500 [08:02<07:17,  2.74it/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': '2.695', 'grad_norm': '0.459', 'learning_rate': '0.0007', 'epoch': '0.08224', 'train/total_time_seconds': '387.9', 'train/time_per_step_avg': '0.3136', 'train/epoch_time_elapsed': '452.5', 'train/estimated_remaining_minutes': '6.783'}
 {'loss': '2.681', 'grad_norm': '0.5078', 'learning_rate': '0.0007', 'epoch': '0.08359', 'train/total_time_seconds': '394.3', 'train/time_per_step_avg': '0.3134', 'train/epoch_time_elapsed': '459.9', 'train/estimated_remaining_minutes': '6.678'}
 {'loss': '2.668', 'grad_norm': '0.4805', 'learning_rate': '0.0007', 'epoch': '0.08493', 'train/total_time_seconds': '400.8', 'train/time_per_step_avg': '0.3162', 'train/epoch_time_elapsed': '467.3', 'train/estimated_remaining_minutes': '6.573'}
+{'loss': '2.65', 'grad_norm': '0.457', 'learning_rate': '0.0007', 'epoch': '0.08628', 'train/total_time_seconds': '407.1', 'train/time_per_step_avg': '0.3158', 'train/epoch_time_elapsed': '474.7', 'train/estimated_remaining_minutes': '6.466'}
+{'loss': '2.643', 'grad_norm': '0.5156', 'learning_rate': '0.0007', 'epoch': '0.08763', 'train/total_time_seconds': '413.4', 'train/time_per_step_avg': '0.317', 'train/epoch_time_elapsed': '482', 'train/estimated_remaining_minutes': '6.36'}
+  - 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, 12.12it/s]
+ 56%|█████▌    | 1400/2500 [08:39<06:30,  2.82it/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': '2.633', 'grad_norm': '0.5078', 'learning_rate': '0.0007', 'epoch': '0.08898', 'train/total_time_seconds': '419.8', 'train/time_per_step_avg': '0.3188', 'train/epoch_time_elapsed': '490', 'train/estimated_remaining_minutes': '6.255'}
+{'loss': '2.62', 'grad_norm': '0.5195', 'learning_rate': '0.0007', 'epoch': '0.09033', 'train/total_time_seconds': '426.1', 'train/time_per_step_avg': '0.3175', 'train/epoch_time_elapsed': '497.3', 'train/estimated_remaining_minutes': '6.147'}
+{'loss': '2.619', 'grad_norm': '0.5156', 'learning_rate': '0.0007', 'epoch': '0.09168', 'train/total_time_seconds': '432.4', 'train/time_per_step_avg': '0.3167', 'train/epoch_time_elapsed': '504.6', 'train/estimated_remaining_minutes': '6.041'}
+{'loss': '2.597', 'grad_norm': '0.4629', 'learning_rate': '0.0007', 'epoch': '0.09302', 'train/total_time_seconds': '438.9', 'train/time_per_step_avg': '0.3187', 'train/epoch_time_elapsed': '512.2', 'train/estimated_remaining_minutes': '5.937'}
+{'loss': '2.59', 'grad_norm': '0.459', 'learning_rate': '0.0007', 'epoch': '0.09437', 'train/total_time_seconds': '445', 'train/time_per_step_avg': '0.3165', 'train/epoch_time_elapsed': '519.3', 'train/estimated_remaining_minutes': '5.828'}
+  - 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, 15.49it/s]
+ 60%|██████    | 1500/2500 [09:16<06:31,  2.55it/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': '2.6', 'grad_norm': '0.4551', 'learning_rate': '0.0007', 'epoch': '0.09572', 'train/total_time_seconds': '451.4', 'train/time_per_step_avg': '0.3161', 'train/epoch_time_elapsed': '526.9', 'train/estimated_remaining_minutes': '5.722'}
+{'loss': '2.575', 'grad_norm': '0.5039', 'learning_rate': '0.0007', 'epoch': '0.09707', 'train/total_time_seconds': '457.7', 'train/time_per_step_avg': '0.3165', 'train/epoch_time_elapsed': '534.3', 'train/estimated_remaining_minutes': '5.616'}
+{'loss': '2.564', 'grad_norm': '0.4785', 'learning_rate': '0.0007', 'epoch': '0.09842', 'train/total_time_seconds': '464.2', 'train/time_per_step_avg': '0.3173', 'train/epoch_time_elapsed': '541.7', 'train/estimated_remaining_minutes': '5.51'}
+{'loss': '2.551', 'grad_norm': '0.4414', 'learning_rate': '0.0007', 'epoch': '0.09976', 'train/total_time_seconds': '470.4', 'train/time_per_step_avg': '0.3151', 'train/epoch_time_elapsed': '549', 'train/estimated_remaining_minutes': '5.404'}
+{'loss': '2.536', 'grad_norm': '0.4609', 'learning_rate': '0.0007', 'epoch': '0.1011', 'train/total_time_seconds': '476.9', 'train/time_per_step_avg': '0.3184', 'train/epoch_time_elapsed': '556.4', 'train/estimated_remaining_minutes': '5.298'}
+  - 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, 16.60it/s]
+ 64%|██████▍   | 1600/2500 [09:53<05:06,  2.93it/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': '2.538', 'grad_norm': '0.4961', 'learning_rate': '0.0007', 'epoch': '0.1025', 'train/total_time_seconds': '483.4', 'train/time_per_step_avg': '0.3196', 'train/epoch_time_elapsed': '564.2', 'train/estimated_remaining_minutes': '5.194'}
+{'loss': '2.529', 'grad_norm': '0.459', 'learning_rate': '0.0007', 'epoch': '0.1038', 'train/total_time_seconds': '489.4', 'train/time_per_step_avg': '0.3165', 'train/epoch_time_elapsed': '571.2', 'train/estimated_remaining_minutes': '5.084'}
+{'loss': '2.513', 'grad_norm': '0.4863', 'learning_rate': '0.0007', 'epoch': '0.1052', 'train/total_time_seconds': '495.9', 'train/time_per_step_avg': '0.3173', 'train/epoch_time_elapsed': '578.7', 'train/estimated_remaining_minutes': '4.98'}
+{'loss': '2.533', 'grad_norm': '0.4648', 'learning_rate': '0.0007', 'epoch': '0.1065', 'train/total_time_seconds': '502.3', 'train/time_per_step_avg': '0.3184', 'train/epoch_time_elapsed': '586.1', 'train/estimated_remaining_minutes': '4.874'}
+{'loss': '2.5', 'grad_norm': '0.4395', 'learning_rate': '0.0007', 'epoch': '0.1079', 'train/total_time_seconds': '508.4', 'train/time_per_step_avg': '0.3154', 'train/epoch_time_elapsed': '593.2', 'train/estimated_remaining_minutes': '4.766'}
+  - 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, 16.83it/s]
+ 68%|██████▊   | 1700/2500 [10:29<05:19,  2.50it/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': '2.491', 'grad_norm': '0.4258', 'learning_rate': '0.0007', 'epoch': '0.1092', 'train/total_time_seconds': '514.7', 'train/time_per_step_avg': '0.3131', 'train/epoch_time_elapsed': '600.8', 'train/estimated_remaining_minutes': '4.66'}
+{'loss': '2.505', 'grad_norm': '0.459', 'learning_rate': '0.0007', 'epoch': '0.1105', 'train/total_time_seconds': '520.7', 'train/time_per_step_avg': '0.3135', 'train/epoch_time_elapsed': '607.9', 'train/estimated_remaining_minutes': '4.551'}
+{'loss': '2.485', 'grad_norm': '0.4082', 'learning_rate': '0.0007', 'epoch': '0.1119', 'train/total_time_seconds': '527.2', 'train/time_per_step_avg': '0.3129', 'train/epoch_time_elapsed': '615.3', 'train/estimated_remaining_minutes': '4.446'}
+{'loss': '2.469', 'grad_norm': '0.457', 'learning_rate': '0.0007', 'epoch': '0.1132', 'train/total_time_seconds': '533.5', 'train/time_per_step_avg': '0.3122', 'train/epoch_time_elapsed': '622.6', 'train/estimated_remaining_minutes': '4.34'}
+{'loss': '2.479', 'grad_norm': '0.4375', 'learning_rate': '0.0007', 'epoch': '0.1146', 'train/total_time_seconds': '539.9', 'train/time_per_step_avg': '0.3146', 'train/epoch_time_elapsed': '630', 'train/estimated_remaining_minutes': '4.234'}
+  - 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, 17.76it/s]
+ 72%|███████▏  | 1800/2500 [11:05<03:54,  2.99it/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': '2.459', 'grad_norm': '0.5234', 'learning_rate': '0.0007', 'epoch': '0.1159', 'train/total_time_seconds': '546.3', 'train/time_per_step_avg': '0.3159', 'train/epoch_time_elapsed': '637.7', 'train/estimated_remaining_minutes': '4.129'}
+{'loss': '2.444', 'grad_norm': '0.498', 'learning_rate': '0.0007', 'epoch': '0.1173', 'train/total_time_seconds': '552.5', 'train/time_per_step_avg': '0.3177', 'train/epoch_time_elapsed': '644.9', 'train/estimated_remaining_minutes': '4.022'}
+{'loss': '2.45', 'grad_norm': '0.5078', 'learning_rate': '0.0007', 'epoch': '0.1186', 'train/total_time_seconds': '558.8', 'train/time_per_step_avg': '0.316', 'train/epoch_time_elapsed': '652.2', 'train/estimated_remaining_minutes': '3.916'}
+{'loss': '2.465', 'grad_norm': '0.4648', 'learning_rate': '0.0007', 'epoch': '0.12', 'train/total_time_seconds': '564.2', 'train/time_per_step_avg': '0.3072', 'train/epoch_time_elapsed': '658.6', 'train/estimated_remaining_minutes': '3.804'}
+{'loss': '2.46', 'grad_norm': '0.5312', 'learning_rate': '0.0007', 'epoch': '0.1213', 'train/total_time_seconds': '569.7', 'train/time_per_step_avg': '0.2987', 'train/epoch_time_elapsed': '665.2', 'train/estimated_remaining_minutes': '3.693'}
+  - 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, 12.53it/s]
+ 76%|███████▌  | 1900/2500 [11:41<03:36,  2.78it/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': '2.45', 'grad_norm': '0.4609', 'learning_rate': '0.0007', 'epoch': '0.1227', 'train/total_time_seconds': '575.3', 'train/time_per_step_avg': '0.2905', 'train/epoch_time_elapsed': '672.1', 'train/estimated_remaining_minutes': '3.583'}
+{'loss': '2.415', 'grad_norm': '0.4707', 'learning_rate': '0.0007', 'epoch': '0.124', 'train/total_time_seconds': '581.3', 'train/time_per_step_avg': '0.2879', 'train/epoch_time_elapsed': '679.1', 'train/estimated_remaining_minutes': '3.475'}
+{'loss': '2.416', 'grad_norm': '0.459', 'learning_rate': '0.0007', 'epoch': '0.1254', 'train/total_time_seconds': '587.9', 'train/time_per_step_avg': '0.2915', 'train/epoch_time_elapsed': '686.7', 'train/estimated_remaining_minutes': '3.372'}
+{'loss': '2.407', 'grad_norm': '0.4258', 'learning_rate': '0.0007', 'epoch': '0.1267', 'train/total_time_seconds': '594.4', 'train/time_per_step_avg': '0.3023', 'train/epoch_time_elapsed': '694.3', 'train/estimated_remaining_minutes': '3.267'}
+{'loss': '2.413', 'grad_norm': '0.459', 'learning_rate': '0.0007', 'epoch': '0.1281', 'train/total_time_seconds': '600.7', 'train/time_per_step_avg': '0.3099', 'train/epoch_time_elapsed': '701.5', 'train/estimated_remaining_minutes': '3.162'}
+  - 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, 14.99it/s]
+ 80%|████████  | 2000/2500 [12:18<03:01,  2.75it/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': '2.391', 'grad_norm': '0.4629', 'learning_rate': '0.0007', 'epoch': '0.1294', 'train/total_time_seconds': '607.2', 'train/time_per_step_avg': '0.3186', 'train/epoch_time_elapsed': '709.3', 'train/estimated_remaining_minutes': '3.057'}
+{'loss': '2.398', 'grad_norm': '0.4668', 'learning_rate': '0.0007', 'epoch': '0.1308', 'train/total_time_seconds': '613.5', 'train/time_per_step_avg': '0.3222', 'train/epoch_time_elapsed': '716.6', 'train/estimated_remaining_minutes': '2.952'}
+{'loss': '2.372', 'grad_norm': '0.4219', 'learning_rate': '0.0007', 'epoch': '0.1321', 'train/total_time_seconds': '619.8', 'train/time_per_step_avg': '0.319', 'train/epoch_time_elapsed': '723.9', 'train/estimated_remaining_minutes': '2.846'}
+{'loss': '2.399', 'grad_norm': '0.4531', 'learning_rate': '0.0007', 'epoch': '0.1335', 'train/total_time_seconds': '626.3', 'train/time_per_step_avg': '0.3187', 'train/epoch_time_elapsed': '731.4', 'train/estimated_remaining_minutes': '2.741'}
+{'loss': '2.367', 'grad_norm': '0.4297', 'learning_rate': '0.0007', 'epoch': '0.1348', 'train/total_time_seconds': '632.6', 'train/time_per_step_avg': '0.3188', 'train/epoch_time_elapsed': '738.7', 'train/estimated_remaining_minutes': '2.636'}
+  - 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, 15.49it/s]
+ 84%|████████▍ | 2097/2500 [12:54<02:37,  2.56it/s], ?it/s]
+{'loss': '2.376', 'grad_norm': '0.4512', 'learning_rate': '0.0007', 'epoch': '0.1362', 'train/total_time_seconds': '639', 'train/time_per_step_avg': '0.3182', 'train/epoch_time_elapsed': '746.4', 'train/estimated_remaining_minutes': '2.531'}
+{'loss': '2.357', 'grad_norm': '0.4238', 'learning_rate': '0.0007', 'epoch': '0.1375', 'train/total_time_seconds': '645.4', 'train/time_per_step_avg': '0.3191', 'train/epoch_time_elapsed': '753.8', 'train/estimated_remaining_minutes': '2.426'}
+{'loss': '2.376', 'grad_norm': '0.4297', 'learning_rate': '0.0007', 'epoch': '0.1389', 'train/total_time_seconds': '651.7', 'train/time_per_step_avg': '0.319', 'train/epoch_time_elapsed': '761.2', 'train/estimated_remaining_minutes': '2.32'}
+{'loss': '2.349', 'grad_norm': '0.4336', 'learning_rate': '0.0007', 'epoch': '0.1402', 'train/total_time_seconds': '658.1', 'train/time_per_step_avg': '0.3182', 'train/epoch_time_elapsed': '768.6', 'train/estimated_remaining_minutes': '2.215'}

zain/Activation/wandb/run-20260814_200503-bdhnr27j/logs/debug-internal.log

@@ -69,3 +69,43 @@
 {"time":"2026-08-14T20:12:33.807298622Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
 {"time":"2026-08-14T20:12:48.650587497Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":60,"history_lines":2,"events_offset":59,"events_lines":2,"console_offset":114,"console_lines":9}
 {"time":"2026-08-14T20:12:48.778517356Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:13:03.650382619Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":62,"history_lines":2,"events_offset":61,"events_lines":2,"console_offset":120,"console_lines":1}
+{"time":"2026-08-14T20:13:03.812326587Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:13:18.650609978Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":64,"history_lines":2,"events_offset":63,"events_lines":2,"console_offset":120,"console_lines":1}
+{"time":"2026-08-14T20:13:18.787625414Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:13:33.650851367Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":66,"history_lines":2,"events_offset":65,"events_lines":2,"console_offset":123,"console_lines":11}
+{"time":"2026-08-14T20:13:33.781915802Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:13:48.651052669Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":68,"history_lines":2,"events_offset":67,"events_lines":2,"console_offset":130,"console_lines":1}
+{"time":"2026-08-14T20:13:48.772219264Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:14:03.65067478Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":70,"history_lines":2,"events_offset":69,"events_lines":2,"console_offset":134,"console_lines":9}
+{"time":"2026-08-14T20:14:03.809449015Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:14:18.651244607Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":72,"history_lines":2,"events_offset":71,"events_lines":2,"console_offset":140,"console_lines":1}
+{"time":"2026-08-14T20:14:18.763302563Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:14:33.650937932Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":74,"history_lines":2,"events_offset":73,"events_lines":2,"console_offset":140,"console_lines":1}
+{"time":"2026-08-14T20:14:33.778832466Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:14:48.650651663Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":76,"history_lines":2,"events_offset":75,"events_lines":2,"console_offset":143,"console_lines":11}
+{"time":"2026-08-14T20:14:48.770293364Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:15:03.650588908Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":78,"history_lines":2,"events_offset":77,"events_lines":2,"console_offset":150,"console_lines":1}
+{"time":"2026-08-14T20:15:03.764486615Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:15:18.650584258Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":80,"history_lines":2,"events_offset":79,"events_lines":2,"console_offset":154,"console_lines":9}
+{"time":"2026-08-14T20:15:18.790512039Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:15:33.650596416Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":82,"history_lines":3,"events_offset":81,"events_lines":2,"console_offset":160,"console_lines":1}
+{"time":"2026-08-14T20:15:33.823998257Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:15:48.650722093Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":85,"history_lines":2,"events_offset":83,"events_lines":2,"console_offset":163,"console_lines":10}
+{"time":"2026-08-14T20:15:48.755930599Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:16:03.651032195Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":87,"history_lines":2,"events_offset":85,"events_lines":2,"console_offset":170,"console_lines":1}
+{"time":"2026-08-14T20:16:03.795996781Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:16:18.650727513Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":89,"history_lines":2,"events_offset":87,"events_lines":2,"console_offset":170,"console_lines":1}
+{"time":"2026-08-14T20:16:18.799850631Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:16:33.650569883Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":91,"history_lines":2,"events_offset":89,"events_lines":2,"console_offset":173,"console_lines":11}
+{"time":"2026-08-14T20:16:33.797225326Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:16:48.651021172Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":93,"history_lines":2,"events_offset":91,"events_lines":2,"console_offset":180,"console_lines":1}
+{"time":"2026-08-14T20:16:48.813680002Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:17:03.651276095Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":95,"history_lines":2,"events_offset":93,"events_lines":2,"console_offset":184,"console_lines":9}
+{"time":"2026-08-14T20:17:03.785055961Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:17:18.650577088Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":97,"history_lines":2,"events_offset":95,"events_lines":2,"console_offset":190,"console_lines":1}
+{"time":"2026-08-14T20:17:18.787294354Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:17:33.651157229Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":99,"history_lines":2,"events_offset":97,"events_lines":2,"console_offset":190,"console_lines":1}
+{"time":"2026-08-14T20:17:33.78015232Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:17:48.651274947Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":101,"history_lines":2,"events_offset":99,"events_lines":2,"console_offset":193,"console_lines":11}
+{"time":"2026-08-14T20:17:48.811733241Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}

zain/Activation/wandb/run-20260814_200503-bdhnr27j/run-bdhnr27j.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68c5db310fafd4711d9a05e4f734b1c50c3ffe6b64a510b1f186eae1f72fc77e
-size 425984
+oid sha256:fa4265b9d4c7fc9b48937c829def591fe3bdd8527ea69354cdb1b540950c34cd
+size 720896

zain/Activation/wandb/run-20260814_201615-w8mr4w6k/files/output.log

@@ -0,0 +1,13 @@
+ 10%|█         | 100/1000 [01:09<10:11,  1.47it/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': '7.168', 'grad_norm': '0.9727', 'learning_rate': '0.001', 'epoch': '0.01078', 'train/total_time_seconds': '6.391', 'train/time_per_step_avg': '0.3196', 'train/epoch_time_elapsed': '14.32', 'train/estimated_remaining_minutes': '5.22'}
+{'loss': '5.993', 'grad_norm': '0.6094', 'learning_rate': '0.001', 'epoch': '0.02156', 'train/total_time_seconds': '12.72', 'train/time_per_step_avg': '0.3181', 'train/epoch_time_elapsed': '28.1', 'train/estimated_remaining_minutes': '5.089'}
+{'loss': '5.496', 'grad_norm': '0.4883', 'learning_rate': '0.001', 'epoch': '0.03235', 'train/total_time_seconds': '19.04', 'train/time_per_step_avg': '0.3174', 'train/epoch_time_elapsed': '41.88', 'train/estimated_remaining_minutes': '4.972'}
+{'loss': '4.935', 'grad_norm': '0.543', 'learning_rate': '0.001', 'epoch': '0.04313', 'train/total_time_seconds': '25.43', 'train/time_per_step_avg': '0.3179', 'train/epoch_time_elapsed': '55.68', 'train/estimated_remaining_minutes': '4.874'}
+{'loss': '4.48', 'grad_norm': '0.418', 'learning_rate': '0.001', 'epoch': '0.05391', 'train/total_time_seconds': '31.75', 'train/time_per_step_avg': '0.3175', 'train/epoch_time_elapsed': '69.39', 'train/estimated_remaining_minutes': '4.763'}
+  - 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, 165.02it/s]
+ 15%|█▌        | 151/1000 [01:44<09:09,  1.54it/s]?, ?it/s]
+{'loss': '4.172', 'grad_norm': '0.3789', 'learning_rate': '0.001', 'epoch': '0.06469', 'train/total_time_seconds': '38.08', 'train/time_per_step_avg': '0.3169', 'train/epoch_time_elapsed': '83.18', 'train/estimated_remaining_minutes': '4.655'}
+{'loss': '3.941', 'grad_norm': '0.5508', 'learning_rate': '0.001', 'epoch': '0.07547', 'train/total_time_seconds': '44.47', 'train/time_per_step_avg': '0.3175', 'train/epoch_time_elapsed': '97.07', 'train/estimated_remaining_minutes': '4.553'}

zain/Activation/wandb/run-20260814_201615-w8mr4w6k/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-20260814_201615-w8mr4w6k/files/wandb-metadata.json

@@ -0,0 +1,101 @@
+{
+  "os":  "Linux-5.15.0-126-generic-x86_64-with-glibc2.35",
+  "python":  "CPython 3.11.15",
+  "startedAt":  "2026-08-14T20:16:15.757135Z",
+  "args":  [
+    "--config",
+    "/mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/configs/baseline.yaml",
+    "--variants",
+    "glu-waleed10",
+    "glu-silu-waleed10",
+    "mlp-waleed10",
+    "mlp-silu-waleed10",
+    "glu-waleed",
+    "glu-situglu_low",
+    "glu-waleedglu_low"
+  ],
+  "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":  "3fb47c6943d6927eafc39bd399a3d3a520bae74a"
+  },
+  "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":  "696163196928"
+    }
+  },
+  "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":  "faj8llaeeykyxuhlp4h5pcq5ogfd7h8q"
+}

zain/Activation/wandb/run-20260814_201615-w8mr4w6k/logs/debug-core.log

@@ -0,0 +1,14 @@
+{"time":"2026-08-14T20:04:25.06988208Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmp4_27mh86/port-409188.txt","pid":409188,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
+{"time":"2026-08-14T20:04:25.070357566Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":409188}
+{"time":"2026-08-14T20:04:25.070338944Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-409188-410559-1836801570/socket","Net":"unix"}}
+{"time":"2026-08-14T20:04:25.24795932Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
+{"time":"2026-08-14T20:04:25.504127391Z","level":"INFO","msg":"handleInformInit: received","streamId":"npumf6lz","id":"1(@)"}
+{"time":"2026-08-14T20:04:25.765319769Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"npumf6lz","id":"1(@)"}
+{"time":"2026-08-14T20:04:31.109816098Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"d0p7d03ygyti"}
+{"time":"2026-08-14T20:16:14.526898083Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"d0p7d03ygyti"}
+{"time":"2026-08-14T20:16:15.115854524Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"d0p7d03ygyti"}
+{"time":"2026-08-14T20:16:15.117591712Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"npumf6lz","id":"1(@)"}
+{"time":"2026-08-14T20:16:15.118263697Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"npumf6lz","id":"1(@)"}
+{"time":"2026-08-14T20:16:15.759561877Z","level":"INFO","msg":"handleInformInit: received","streamId":"w8mr4w6k","id":"1(@)"}
+{"time":"2026-08-14T20:16:16.020082435Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w8mr4w6k","id":"1(@)"}
+{"time":"2026-08-14T20:16:21.531557612Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"ewwa8fnip5gl"}

zain/Activation/wandb/run-20260814_201615-w8mr4w6k/logs/debug-internal.log

@@ -0,0 +1,23 @@
+{"time":"2026-08-14T20:16:15.759688663Z","level":"INFO","msg":"wandb-core"}
+{"time":"2026-08-14T20:16:15.75981584Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
+{"time":"2026-08-14T20:16:16.019892925Z","level":"INFO","msg":"stream: created new stream","id":"w8mr4w6k"}
+{"time":"2026-08-14T20:16:16.01997882Z","level":"INFO","msg":"handler: started"}
+{"time":"2026-08-14T20:16:16.020075043Z","level":"INFO","msg":"stream: started"}
+{"time":"2026-08-14T20:16:16.02008577Z","level":"INFO","msg":"writer: started","stream_id":"w8mr4w6k"}
+{"time":"2026-08-14T20:16:16.020113292Z","level":"INFO","msg":"sender: started"}
+{"time":"2026-08-14T20:16:16.531359023Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
+{"time":"2026-08-14T20:16:16.686067824Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:16:31.532246567Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":1,"events_offset":0,"events_lines":1,"console_offset":0,"console_lines":2,"uploaded_len":2}
+{"time":"2026-08-14T20:16:31.65014999Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:16:46.53154926Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":1,"history_lines":1,"events_offset":1,"events_lines":2,"console_offset":0,"console_lines":1}
+{"time":"2026-08-14T20:16:46.697907798Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:17:01.532416577Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":2,"history_lines":1,"events_offset":3,"events_lines":2,"console_offset":0,"console_lines":1}
+{"time":"2026-08-14T20:17:01.661940731Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:17:16.532407844Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3,"history_lines":1,"events_offset":5,"events_lines":2,"console_offset":0,"console_lines":1}
+{"time":"2026-08-14T20:17:16.655117007Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:17:31.531597694Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":4,"history_lines":1,"events_offset":7,"events_lines":2,"console_offset":0,"console_lines":1}
+{"time":"2026-08-14T20:17:31.671651312Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:17:46.532231919Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":5,"history_lines":1,"events_offset":9,"events_lines":2,"console_offset":2,"console_lines":10}
+{"time":"2026-08-14T20:17:46.65675743Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-14T20:18:01.532320003Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":6,"history_lines":1,"events_offset":11,"events_lines":2,"console_offset":10,"console_lines":1}
+{"time":"2026-08-14T20:18:01.703907556Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}

zain/Activation/wandb/run-20260814_201615-w8mr4w6k/logs/debug.log

@@ -0,0 +1,19 @@
+2026-08-14 20:16:15,758 INFO    MainThread:409188 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260814_201615-w8mr4w6k/logs/debug.log
+2026-08-14 20:16:15,758 INFO    MainThread:409188 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260814_201615-w8mr4w6k/logs/debug-internal.log
+2026-08-14 20:16:15,758 INFO    MainThread:409188 [wandb_init.py:init():772] calling init triggers
+2026-08-14 20:16:15,758 INFO    MainThread:409188 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
+config: {'_wandb': {}}
+2026-08-14 20:16:15,758 INFO    MainThread:409188 [wandb_init.py:init():820] starting backend
+2026-08-14 20:16:15,758 INFO    MainThread:409188 [wandb_init.py:init():835] sending inform_init request
+2026-08-14 20:16:16,020 INFO    MainThread:409188 [wandb_init.py:init():840] backend started and connected
+2026-08-14 20:16:16,021 INFO    MainThread:409188 [wandb_init.py:init():910] updated telemetry
+2026-08-14 20:16:16,028 INFO    MainThread:409188 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
+2026-08-14 20:16:16,449 INFO    MainThread:409188 [wandb_init.py:init():978] starting run threads in backend
+2026-08-14 20:16:16,526 INFO    MainThread:409188 [wandb_run.py:_console_start():2621] atexit reg
+2026-08-14 20:16:16,526 INFO    MainThread:409188 [wandb_run.py:_redirect():2471] redirect: wrap_raw
+2026-08-14 20:16:16,526 INFO    MainThread:409188 [wandb_run.py:_redirect():2540] Wrapping output streams.
+2026-08-14 20:16:16,526 INFO    MainThread:409188 [wandb_run.py:_redirect():2563] Redirects installed.
+2026-08-14 20:16:16,527 INFO    MainThread:409188 [wandb_init.py:init():1016] run started, returning control to user process
+2026-08-14 20:16:16,528 INFO    MainThread:409188 [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': 9, '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-waleed10-9L_run', 'per_device_train_batch_size': 512, 'num_train_epochs': 1, 'max_steps': 1000, 'learning_rate': 0.001, 'lr_scheduler_type': 'constant', 'lr_scheduler_kwargs': None, 'warmup_steps': 0, 'optim': 'adamw_torch', 'optim_args': None, 'weight_decay': 0.01, '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-waleed10-9L-2.0M-20260814-201615', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 60000, 'eval_delay': 0, 'per_device_eval_batch_size': 512, '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/A-glu-silu-waleed10-9L', '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}
+2026-08-14 20:16:16,530 INFO    MainThread:409188 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 2001280 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x153f494c8950>>
+2026-08-14 20:16:16,530 INFO    MainThread:409188 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 2001280 None