Auto upload zain 2026-08-19T16:38:46.885721

zain/Activation/wandb/debug-internal.log

@@ -1,35 +1,9 @@
-{"time":"2026-08-19T16:30:14.408862805Z","level":"INFO","msg":"wandb-core"}
-{"time":"2026-08-19T16:30:14.409145225Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
-{"time":"2026-08-19T16:30:14.673839961Z","level":"INFO","msg":"stream: created new stream","id":"smtfejrp"}
-{"time":"2026-08-19T16:30:14.673914385Z","level":"INFO","msg":"handler: started"}
-{"time":"2026-08-19T16:30:14.674023743Z","level":"INFO","msg":"stream: started"}
-{"time":"2026-08-19T16:30:14.67404595Z","level":"INFO","msg":"writer: started","stream_id":"smtfejrp"}
-{"time":"2026-08-19T16:30:14.674053413Z","level":"INFO","msg":"sender: started"}
-{"time":"2026-08-19T16:30:15.573430136Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
-{"time":"2026-08-19T16:30:15.803201108Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-19T16:30:30.574169941Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":16,"events_offset":0,"events_lines":1,"console_offset":0,"console_lines":34,"uploaded_len":2}
-{"time":"2026-08-19T16:30:30.711458871Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-19T16:30:45.574202013Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":16,"history_lines":16,"events_offset":1,"events_lines":2,"console_offset":33,"console_lines":27}
-{"time":"2026-08-19T16:30:45.755515219Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-19T16:31:00.573737519Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":32,"history_lines":11,"events_offset":3,"events_lines":2,"console_offset":54,"console_lines":1}
-{"time":"2026-08-19T16:31:00.75827199Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-19T16:31:15.574343371Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":43,"history_lines":11,"events_offset":5,"events_lines":2,"console_offset":60,"console_lines":43}
-{"time":"2026-08-19T16:31:15.798424562Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-19T16:31:30.573773942Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":54,"history_lines":18,"events_offset":7,"events_lines":2,"console_offset":96,"console_lines":1}
-{"time":"2026-08-19T16:31:30.694320256Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-19T16:31:45.574312952Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":72,"history_lines":15,"events_offset":9,"events_lines":2,"console_offset":102,"console_lines":63}
-{"time":"2026-08-19T16:31:45.774027402Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-19T16:32:00.574639142Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":87,"history_lines":11,"events_offset":11,"events_lines":2,"console_offset":159,"console_lines":1}
-{"time":"2026-08-19T16:32:00.704830872Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-19T16:32:15.573881284Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":98,"history_lines":11,"events_offset":13,"events_lines":2,"console_offset":165,"console_lines":43}
-{"time":"2026-08-19T16:32:15.785173455Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-19T16:32:30.574343755Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":109,"history_lines":19,"events_offset":15,"events_lines":2,"console_offset":201,"console_lines":1}
-{"time":"2026-08-19T16:32:30.715820396Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-19T16:32:45.573977636Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":128,"history_lines":14,"events_offset":17,"events_lines":2,"console_offset":207,"console_lines":63}
-{"time":"2026-08-19T16:32:45.688687126Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-19T16:33:00.574401218Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":142,"history_lines":11,"events_offset":19,"events_lines":2,"console_offset":264,"console_lines":1}
-{"time":"2026-08-19T16:33:00.726033404Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-19T16:33:15.575478736Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":153,"history_lines":13,"events_offset":21,"events_lines":2,"console_offset":270,"console_lines":49}
-{"time":"2026-08-19T16:33:15.746742621Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
-{"time":"2026-08-19T16:33:30.574073819Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":166,"history_lines":18,"events_offset":23,"events_lines":2,"console_offset":317,"console_lines":1}
-{"time":"2026-08-19T16:33:30.725976627Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-19T16:38:45.593954868Z","level":"INFO","msg":"wandb-core"}
+{"time":"2026-08-19T16:38:45.594350472Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
+{"time":"2026-08-19T16:38:45.859229209Z","level":"INFO","msg":"stream: created new stream","id":"74tq2syl"}
+{"time":"2026-08-19T16:38:45.859322278Z","level":"INFO","msg":"handler: started"}
+{"time":"2026-08-19T16:38:45.859420632Z","level":"INFO","msg":"stream: started"}
+{"time":"2026-08-19T16:38:45.859446053Z","level":"INFO","msg":"writer: started","stream_id":"74tq2syl"}
+{"time":"2026-08-19T16:38:45.859457193Z","level":"INFO","msg":"sender: started"}
+{"time":"2026-08-19T16:38:46.255563583Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
+{"time":"2026-08-19T16:38:46.375363227Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}

zain/Activation/wandb/debug.log

@@ -1,23 +1,23 @@
-2026-08-19 16:30:14,407 INFO    MainThread:3508170 [wandb_setup.py:_flush():81] Current SDK version is 0.28.1
-2026-08-19 16:30:14,407 INFO    MainThread:3508170 [wandb_setup.py:_flush():81] Configure stats pid to 3508170
-2026-08-19 16:30:14,407 INFO    MainThread:3508170 [wandb_setup.py:_flush():81] Loading settings from environment variables
-2026-08-19 16:30:14,407 INFO    MainThread:3508170 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260819_163014-smtfejrp/logs/debug.log
-2026-08-19 16:30:14,407 INFO    MainThread:3508170 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260819_163014-smtfejrp/logs/debug-internal.log
-2026-08-19 16:30:14,407 INFO    MainThread:3508170 [wandb_init.py:init():772] calling init triggers
-2026-08-19 16:30:14,407 INFO    MainThread:3508170 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
+2026-08-19 16:38:45,592 INFO    MainThread:3592847 [wandb_setup.py:_flush():81] Current SDK version is 0.28.1
+2026-08-19 16:38:45,592 INFO    MainThread:3592847 [wandb_setup.py:_flush():81] Configure stats pid to 3592847
+2026-08-19 16:38:45,592 INFO    MainThread:3592847 [wandb_setup.py:_flush():81] Loading settings from environment variables
+2026-08-19 16:38:45,592 INFO    MainThread:3592847 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260819_163845-74tq2syl/logs/debug.log
+2026-08-19 16:38:45,592 INFO    MainThread:3592847 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260819_163845-74tq2syl/logs/debug-internal.log
+2026-08-19 16:38:45,592 INFO    MainThread:3592847 [wandb_init.py:init():772] calling init triggers
+2026-08-19 16:38:45,592 INFO    MainThread:3592847 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
 config: {'_wandb': {}}
-2026-08-19 16:30:14,407 INFO    MainThread:3508170 [wandb_init.py:init():820] starting backend
-2026-08-19 16:30:14,407 INFO    MainThread:3508170 [wandb_init.py:init():826] Connected to an existing wandb-core service via WANDB_SERVICE
-2026-08-19 16:30:14,407 INFO    MainThread:3508170 [wandb_init.py:init():835] sending inform_init request
-2026-08-19 16:30:14,674 INFO    MainThread:3508170 [wandb_init.py:init():840] backend started and connected
-2026-08-19 16:30:14,678 INFO    MainThread:3508170 [wandb_init.py:init():910] updated telemetry
-2026-08-19 16:30:14,685 INFO    MainThread:3508170 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
-2026-08-19 16:30:15,492 INFO    MainThread:3508170 [wandb_init.py:init():978] starting run threads in backend
-2026-08-19 16:30:15,566 INFO    MainThread:3508170 [wandb_run.py:_console_start():2621] atexit reg
-2026-08-19 16:30:15,566 INFO    MainThread:3508170 [wandb_run.py:_redirect():2471] redirect: wrap_raw
-2026-08-19 16:30:15,566 INFO    MainThread:3508170 [wandb_run.py:_redirect():2540] Wrapping output streams.
-2026-08-19 16:30:15,566 INFO    MainThread:3508170 [wandb_run.py:_redirect():2563] Redirects installed.
-2026-08-19 16:30:15,569 INFO    MainThread:3508170 [wandb_init.py:init():1016] run started, returning control to user process
-2026-08-19 16:30:15,570 INFO    MainThread:3508170 [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': 3, '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': 'mlp', 'activation': 'linear', 'waleed_beta': 10.0, 'powlu_m': 3.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/mlp-linear-3L_run', 'per_device_train_batch_size': 16, 'num_train_epochs': 1, 'max_steps': 5000, 'learning_rate': 0.0003, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 1000, '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-mlp-linear-3L-1.0M-20260819-163013', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 200, 'eval_delay': 0, 'per_device_eval_batch_size': 1500, '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-mlp-linear-3L', '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}
-2026-08-19 16:30:15,572 INFO    MainThread:3508170 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 1016704 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x1495a6a04a90>>
-2026-08-19 16:30:15,572 INFO    MainThread:3508170 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 1016704 None
+2026-08-19 16:38:45,592 INFO    MainThread:3592847 [wandb_init.py:init():820] starting backend
+2026-08-19 16:38:45,592 INFO    MainThread:3592847 [wandb_init.py:init():826] Connected to an existing wandb-core service via WANDB_SERVICE
+2026-08-19 16:38:45,592 INFO    MainThread:3592847 [wandb_init.py:init():835] sending inform_init request
+2026-08-19 16:38:45,859 INFO    MainThread:3592847 [wandb_init.py:init():840] backend started and connected
+2026-08-19 16:38:45,863 INFO    MainThread:3592847 [wandb_init.py:init():910] updated telemetry
+2026-08-19 16:38:45,869 INFO    MainThread:3592847 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
+2026-08-19 16:38:46,172 INFO    MainThread:3592847 [wandb_init.py:init():978] starting run threads in backend
+2026-08-19 16:38:46,248 INFO    MainThread:3592847 [wandb_run.py:_console_start():2621] atexit reg
+2026-08-19 16:38:46,248 INFO    MainThread:3592847 [wandb_run.py:_redirect():2471] redirect: wrap_raw
+2026-08-19 16:38:46,248 INFO    MainThread:3592847 [wandb_run.py:_redirect():2540] Wrapping output streams.
+2026-08-19 16:38:46,248 INFO    MainThread:3592847 [wandb_run.py:_redirect():2563] Redirects installed.
+2026-08-19 16:38:46,251 INFO    MainThread:3592847 [wandb_init.py:init():1016] run started, returning control to user process
+2026-08-19 16:38:46,252 INFO    MainThread:3592847 [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': 3, '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': 'mlp', 'activation': 'linear', 'waleed_beta': 10.0, 'powlu_m': 3.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/mlp-linear-3L_run', 'per_device_train_batch_size': 16, 'num_train_epochs': 1, 'max_steps': 5000, 'learning_rate': 0.0007, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 1000, '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-mlp-linear-3L-1.0M-20260819-163844', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 200, 'eval_delay': 0, 'per_device_eval_batch_size': 1500, '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-mlp-linear-3L', '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}
+2026-08-19 16:38:46,254 INFO    MainThread:3592847 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 1016704 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x154219923410>>
+2026-08-19 16:38:46,254 INFO    MainThread:3592847 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 1016704 None

zain/Activation/wandb/run-20260819_163845-74tq2syl/files/output.log

@@ -0,0 +1 @@
+  0%|          | 0/5000 [00:00<?, ?it/s]

zain/Activation/wandb/run-20260819_163845-74tq2syl/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
+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
+tokenizers==0.23.1
+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-20260819_163845-74tq2syl/files/wandb-metadata.json

@@ -0,0 +1,95 @@
+{
+  "os":  "Linux-5.15.0-126-generic-x86_64-with-glibc2.35",
+  "python":  "CPython 3.11.15",
+  "startedAt":  "2026-08-19T16:38:45.591292Z",
+  "args":  [
+    "--config",
+    "/mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/configs/baseline100L.yaml",
+    "--variants",
+    "mlp-linear-3L"
+  ],
+  "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":  "463c9961366755fc55f02df9a0d471b3cbcb025e"
+  },
+  "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":  "708409778176"
+    }
+  },
+  "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":  "unfzenft6jshfy2yfr3z6fuq55s2vslz"
+}

zain/Activation/wandb/run-20260819_163845-74tq2syl/logs/debug-core.log

@@ -0,0 +1,7 @@
+{"time":"2026-08-19T16:38:32.839280488Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpn7u591yp/port-3590110.txt","pid":3590110,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
+{"time":"2026-08-19T16:38:32.840574816Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":3590110}
+{"time":"2026-08-19T16:38:32.84057072Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-3590110-3591582-3840970873/socket","Net":"unix"}}
+{"time":"2026-08-19T16:38:33.017601922Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
+{"time":"2026-08-19T16:38:45.523223978Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"2(@)"}
+{"time":"2026-08-19T16:38:45.593765665Z","level":"INFO","msg":"handleInformInit: received","streamId":"74tq2syl","id":"2(@)"}
+{"time":"2026-08-19T16:38:45.85943264Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"74tq2syl","id":"2(@)"}

zain/Activation/wandb/run-20260819_163845-74tq2syl/logs/debug-internal.log

@@ -0,0 +1,9 @@
+{"time":"2026-08-19T16:38:45.593954868Z","level":"INFO","msg":"wandb-core"}
+{"time":"2026-08-19T16:38:45.594350472Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
+{"time":"2026-08-19T16:38:45.859229209Z","level":"INFO","msg":"stream: created new stream","id":"74tq2syl"}
+{"time":"2026-08-19T16:38:45.859322278Z","level":"INFO","msg":"handler: started"}
+{"time":"2026-08-19T16:38:45.859420632Z","level":"INFO","msg":"stream: started"}
+{"time":"2026-08-19T16:38:45.859446053Z","level":"INFO","msg":"writer: started","stream_id":"74tq2syl"}
+{"time":"2026-08-19T16:38:45.859457193Z","level":"INFO","msg":"sender: started"}
+{"time":"2026-08-19T16:38:46.255563583Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
+{"time":"2026-08-19T16:38:46.375363227Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}

zain/Activation/wandb/run-20260819_163845-74tq2syl/logs/debug.log

@@ -0,0 +1,23 @@
+2026-08-19 16:38:45,592 INFO    MainThread:3592847 [wandb_setup.py:_flush():81] Current SDK version is 0.28.1
+2026-08-19 16:38:45,592 INFO    MainThread:3592847 [wandb_setup.py:_flush():81] Configure stats pid to 3592847
+2026-08-19 16:38:45,592 INFO    MainThread:3592847 [wandb_setup.py:_flush():81] Loading settings from environment variables
+2026-08-19 16:38:45,592 INFO    MainThread:3592847 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260819_163845-74tq2syl/logs/debug.log
+2026-08-19 16:38:45,592 INFO    MainThread:3592847 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260819_163845-74tq2syl/logs/debug-internal.log
+2026-08-19 16:38:45,592 INFO    MainThread:3592847 [wandb_init.py:init():772] calling init triggers
+2026-08-19 16:38:45,592 INFO    MainThread:3592847 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
+config: {'_wandb': {}}
+2026-08-19 16:38:45,592 INFO    MainThread:3592847 [wandb_init.py:init():820] starting backend
+2026-08-19 16:38:45,592 INFO    MainThread:3592847 [wandb_init.py:init():826] Connected to an existing wandb-core service via WANDB_SERVICE
+2026-08-19 16:38:45,592 INFO    MainThread:3592847 [wandb_init.py:init():835] sending inform_init request
+2026-08-19 16:38:45,859 INFO    MainThread:3592847 [wandb_init.py:init():840] backend started and connected
+2026-08-19 16:38:45,863 INFO    MainThread:3592847 [wandb_init.py:init():910] updated telemetry
+2026-08-19 16:38:45,869 INFO    MainThread:3592847 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
+2026-08-19 16:38:46,172 INFO    MainThread:3592847 [wandb_init.py:init():978] starting run threads in backend
+2026-08-19 16:38:46,248 INFO    MainThread:3592847 [wandb_run.py:_console_start():2621] atexit reg
+2026-08-19 16:38:46,248 INFO    MainThread:3592847 [wandb_run.py:_redirect():2471] redirect: wrap_raw
+2026-08-19 16:38:46,248 INFO    MainThread:3592847 [wandb_run.py:_redirect():2540] Wrapping output streams.
+2026-08-19 16:38:46,248 INFO    MainThread:3592847 [wandb_run.py:_redirect():2563] Redirects installed.
+2026-08-19 16:38:46,251 INFO    MainThread:3592847 [wandb_init.py:init():1016] run started, returning control to user process
+2026-08-19 16:38:46,252 INFO    MainThread:3592847 [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': 3, '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': 'mlp', 'activation': 'linear', 'waleed_beta': 10.0, 'powlu_m': 3.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/mlp-linear-3L_run', 'per_device_train_batch_size': 16, 'num_train_epochs': 1, 'max_steps': 5000, 'learning_rate': 0.0007, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 1000, '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-mlp-linear-3L-1.0M-20260819-163844', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 200, 'eval_delay': 0, 'per_device_eval_batch_size': 1500, '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-mlp-linear-3L', '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}
+2026-08-19 16:38:46,254 INFO    MainThread:3592847 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 1016704 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x154219923410>>
+2026-08-19 16:38:46,254 INFO    MainThread:3592847 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 1016704 None