Auto upload zain 2026-08-12T23:51:54.973102 (part 2)

zain/Activation/out/sweep_summary.json

@@ -0,0 +1,38 @@
+[
+  {
+    "variant": "glu-silu-waleed10-100L",
+    "eval_loss": 2.122779130935669,
+    "out": "out/glu-silu-waleed10-100L_run",
+    "run_name": "LM-glu-silu-waleed10-100L-16.9M-20260812-222757"
+  },
+  {
+    "variant": "glu-situglu-100L",
+    "eval_loss": 2.1253936290740967,
+    "out": "out/glu-situglu-100L_run",
+    "run_name": "LM-glu-situglu-100L-16.9M-20260812-224110"
+  },
+  {
+    "variant": "glu-waleed-100L",
+    "eval_loss": 2.1097662448883057,
+    "out": "out/glu-waleed-100L_run",
+    "run_name": "LM-glu-waleed-100L-16.9M-20260812-225525"
+  },
+  {
+    "variant": "glu-situglu_low-100L",
+    "eval_loss": 2.1262547969818115,
+    "out": "out/glu-situglu_low-100L_run",
+    "run_name": "LM-glu-situglu_low-100L-16.9M-20260812-230914"
+  },
+  {
+    "variant": "glu-waleedglu_low-100L",
+    "eval_loss": 2.106821060180664,
+    "out": "out/glu-waleedglu_low-100L_run",
+    "run_name": "LM-glu-waleedglu_low-100L-16.9M-20260812-232325"
+  },
+  {
+    "variant": "glu-linear-100L",
+    "eval_loss": 2.1097066402435303,
+    "out": "out/glu-linear-100L_run",
+    "run_name": "LM-glu-linear-100L-16.9M-20260812-233703"
+  }
+]

zain/Activation/wandb/debug-internal.log

@@ -85,3 +85,35 @@
 {"time":"2026-08-12T23:46:35.998150976Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
 {"time":"2026-08-12T23:46:50.874132215Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":98,"history_lines":3,"events_offset":76,"events_lines":2,"console_offset":190,"console_lines":1}
 {"time":"2026-08-12T23:46:51.1109748Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:47:05.873911748Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":101,"history_lines":3,"events_offset":78,"events_lines":2,"console_offset":194,"console_lines":11}
+{"time":"2026-08-12T23:47:06.048101755Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:47:20.874022923Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":104,"history_lines":2,"events_offset":80,"events_lines":2,"console_offset":200,"console_lines":1}
+{"time":"2026-08-12T23:47:21.005671585Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:47:35.873635563Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":106,"history_lines":3,"events_offset":82,"events_lines":2,"console_offset":205,"console_lines":10}
+{"time":"2026-08-12T23:47:36.000550646Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:47:50.87376451Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":109,"history_lines":2,"events_offset":84,"events_lines":2,"console_offset":210,"console_lines":1}
+{"time":"2026-08-12T23:47:51.121247495Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:48:05.873619511Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":111,"history_lines":3,"events_offset":86,"events_lines":2,"console_offset":215,"console_lines":10}
+{"time":"2026-08-12T23:48:06.082648628Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:48:20.874292434Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":114,"history_lines":2,"events_offset":88,"events_lines":2,"console_offset":220,"console_lines":1}
+{"time":"2026-08-12T23:48:21.069644658Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:48:35.874379741Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":116,"history_lines":3,"events_offset":90,"events_lines":2,"console_offset":225,"console_lines":10}
+{"time":"2026-08-12T23:48:36.100237591Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:48:50.873603862Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":119,"history_lines":2,"events_offset":92,"events_lines":2,"console_offset":230,"console_lines":1}
+{"time":"2026-08-12T23:48:50.998416569Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:49:05.873747271Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":121,"history_lines":3,"events_offset":94,"events_lines":2,"console_offset":235,"console_lines":10}
+{"time":"2026-08-12T23:49:06.067209608Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:49:20.873615557Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":96,"events_lines":2,"console_offset":240,"console_lines":1}
+{"time":"2026-08-12T23:49:21.08163947Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:49:35.873636608Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":124,"history_lines":2,"events_offset":98,"events_lines":2,"console_offset":240,"console_lines":1}
+{"time":"2026-08-12T23:49:35.988320548Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:49:50.873659846Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":126,"history_lines":2,"events_offset":100,"events_lines":2,"console_offset":240,"console_lines":1}
+{"time":"2026-08-12T23:49:51.048489153Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:49:56.598587763Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2026-08-12T23:49:56.598789418Z","level":"INFO","msg":"filestream: sending request","total_files":3,"history_offset":128,"history_lines":1,"console_offset":245,"console_lines":15,"uploaded_len":3,"complete":true,"exit_code":0}
+{"time":"2026-08-12T23:49:56.701784518Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:49:56.702912833Z","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2026-08-12T23:49:56.705484814Z","level":"INFO","msg":"stream: finishing up"}
+{"time":"2026-08-12T23:49:56.705519356Z","level":"INFO","msg":"handler: closed"}
+{"time":"2026-08-12T23:49:56.705632565Z","level":"INFO","msg":"sender: closed"}
+{"time":"2026-08-12T23:49:56.705637913Z","level":"INFO","msg":"stream: all finished"}

zain/Activation/wandb/debug.log

@@ -18,3 +18,8 @@ config: {'_wandb': {}}
 2026-08-12 23:37:05,310 INFO    MainThread:3978000 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.16.0.dev0', 'architectures': None, 'output_hidden_states': False, 'return_dict': True, 'dtype': None, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, 'vocab_size': 4096, 'hidden_size': 128, 'intermediate_size': 256, 'num_hidden_layers': 100, 'num_attention_heads': 4, 'num_key_value_heads': 4, 'hidden_act': 'silu', 'max_position_embeddings': 512, 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'pad_token_id': 0, 'bos_token_id': 1, 'eos_token_id': 2, 'pretraining_tp': 1, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 10000.0, 'rope_type': 'default'}, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'head_dim': 32, '_name_or_path': '', 'tokenizer_name': 'w-ahmad/tiny-stories-tokenizer', 'mlp_type': 'glu', 'activation': 'linear', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-linear-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-linear-100L-16.9M-20260812-233703', '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-linear-100L', 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': None, 'dataloader_multiprocessing_context': None, 'dataloader_in_order': True, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_static_graph': None, 'ddp_backend': None, 'ddp_timeout': 1800, 'fsdp': None, 'fsdp_config': None, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'local_rank': -1}
 2026-08-12 23:37:05,315 INFO    MainThread:3978000 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 16934016 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x14d9ca094510>>
 2026-08-12 23:37:05,315 INFO    MainThread:3978000 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 16934016 None
+2026-08-12 23:49:56,215 INFO    MainThread:3978000 [wandb_run.py:_finish():2383] finishing run deepnevro-deepnevro/research3/tpo5j00e
+2026-08-12 23:49:56,216 INFO    MainThread:3978000 [wandb_run.py:_atexit_cleanup():2588] got exitcode: 0
+2026-08-12 23:49:56,216 INFO    MainThread:3978000 [wandb_run.py:_restore():2570] restore
+2026-08-12 23:49:56,216 INFO    MainThread:3978000 [wandb_run.py:_restore():2576] restore done
+2026-08-12 23:49:56,704 INFO    MainThread:3978000 [wandb_run.py:_footer_sync_info():3993] logging synced files

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

@@ -90,3 +90,11 @@
 {"time":"2026-08-12T23:37:04.659365837Z","level":"INFO","msg":"handleInformInit: received","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:04.922876846Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:10.31045638Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.216535938Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.703966372Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.705445032Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:56.705984097Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200430345Z","level":"INFO","msg":"connection: closing","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200526275Z","level":"INFO","msg":"connection: closed successfully","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200433558Z","level":"INFO","msg":"processOutgoingData: finished","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200535053Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"5(@)"}

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

@@ -90,3 +90,11 @@
 {"time":"2026-08-12T23:37:04.659365837Z","level":"INFO","msg":"handleInformInit: received","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:04.922876846Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:10.31045638Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.216535938Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.703966372Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.705445032Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:56.705984097Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200430345Z","level":"INFO","msg":"connection: closing","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200526275Z","level":"INFO","msg":"connection: closed successfully","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200433558Z","level":"INFO","msg":"processOutgoingData: finished","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200535053Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"5(@)"}

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

@@ -90,3 +90,11 @@
 {"time":"2026-08-12T23:37:04.659365837Z","level":"INFO","msg":"handleInformInit: received","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:04.922876846Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:10.31045638Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.216535938Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.703966372Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.705445032Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:56.705984097Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200430345Z","level":"INFO","msg":"connection: closing","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200526275Z","level":"INFO","msg":"connection: closed successfully","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200433558Z","level":"INFO","msg":"processOutgoingData: finished","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200535053Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"5(@)"}

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

@@ -90,3 +90,11 @@
 {"time":"2026-08-12T23:37:04.659365837Z","level":"INFO","msg":"handleInformInit: received","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:04.922876846Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:10.31045638Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.216535938Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.703966372Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.705445032Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:56.705984097Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200430345Z","level":"INFO","msg":"connection: closing","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200526275Z","level":"INFO","msg":"connection: closed successfully","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200433558Z","level":"INFO","msg":"processOutgoingData: finished","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200535053Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"5(@)"}

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

@@ -90,3 +90,11 @@
 {"time":"2026-08-12T23:37:04.659365837Z","level":"INFO","msg":"handleInformInit: received","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:04.922876846Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:10.31045638Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.216535938Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.703966372Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.705445032Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:56.705984097Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200430345Z","level":"INFO","msg":"connection: closing","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200526275Z","level":"INFO","msg":"connection: closed successfully","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200433558Z","level":"INFO","msg":"processOutgoingData: finished","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200535053Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"5(@)"}

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

@@ -90,3 +90,11 @@
 {"time":"2026-08-12T23:37:04.659365837Z","level":"INFO","msg":"handleInformInit: received","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:04.922876846Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:10.31045638Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.216535938Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.703966372Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.705445032Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:56.705984097Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200430345Z","level":"INFO","msg":"connection: closing","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200526275Z","level":"INFO","msg":"connection: closed successfully","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200433558Z","level":"INFO","msg":"processOutgoingData: finished","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200535053Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"5(@)"}

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

@@ -90,3 +90,11 @@
 {"time":"2026-08-12T23:37:04.659365837Z","level":"INFO","msg":"handleInformInit: received","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:04.922876846Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:10.31045638Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.216535938Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.703966372Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.705445032Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:56.705984097Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200430345Z","level":"INFO","msg":"connection: closing","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200526275Z","level":"INFO","msg":"connection: closed successfully","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200433558Z","level":"INFO","msg":"processOutgoingData: finished","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200535053Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"5(@)"}

zain/Activation/wandb/run-20260812_225525-hf77resg/logs/debug-core.log

@@ -90,3 +90,11 @@
 {"time":"2026-08-12T23:37:04.659365837Z","level":"INFO","msg":"handleInformInit: received","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:04.922876846Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:10.31045638Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.216535938Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.703966372Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.705445032Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:56.705984097Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200430345Z","level":"INFO","msg":"connection: closing","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200526275Z","level":"INFO","msg":"connection: closed successfully","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200433558Z","level":"INFO","msg":"processOutgoingData: finished","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200535053Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"5(@)"}

zain/Activation/wandb/run-20260812_230915-vvjf0upl/logs/debug-core.log

@@ -90,3 +90,11 @@
 {"time":"2026-08-12T23:37:04.659365837Z","level":"INFO","msg":"handleInformInit: received","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:04.922876846Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:10.31045638Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.216535938Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.703966372Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.705445032Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:56.705984097Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200430345Z","level":"INFO","msg":"connection: closing","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200526275Z","level":"INFO","msg":"connection: closed successfully","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200433558Z","level":"INFO","msg":"processOutgoingData: finished","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200535053Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"5(@)"}

zain/Activation/wandb/run-20260812_232326-8u0k1nti/logs/debug-core.log

@@ -90,3 +90,11 @@
 {"time":"2026-08-12T23:37:04.659365837Z","level":"INFO","msg":"handleInformInit: received","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:04.922876846Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:10.31045638Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.216535938Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.703966372Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.705445032Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:56.705984097Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200430345Z","level":"INFO","msg":"connection: closing","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200526275Z","level":"INFO","msg":"connection: closed successfully","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200433558Z","level":"INFO","msg":"processOutgoingData: finished","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200535053Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"5(@)"}

zain/Activation/wandb/run-20260812_233704-tpo5j00e/files/config.yaml

@@ -0,0 +1,438 @@
+_name_or_path:
+    value: ""
+_wandb:
+    value:
+        cli_version: 0.28.1
+        e:
+            4qopxlj5t12670m45s6hbdlio87c05xg:
+                args:
+                    - --config
+                    - /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/configs/baseline100L.yaml
+                    - --variants
+                    - glu-silu-waleed10
+                    - glu-situglu
+                    - glu-waleed
+                    - glu-situglu_low
+                    - glu-waleedglu_low
+                    - glu-linear
+                codePath: sweep.py
+                codePathLocal: sweep.py
+                cpu_count: 112
+                cpu_count_logical: 224
+                cudaVersion: "12.4"
+                disk:
+                    /:
+                        total: "1560765693952"
+                        used: "716448854016"
+                email: deepnevro@gmail.com
+                executable: /mnt/data/zainulabideen/zain-exp/notebooks/my_env/bin/python
+                git:
+                    commit: 26a43c7dee7982e610a25ac78443de9ce18f5077
+                    remote: https://github.com/w-ahmad1a10/Activation.git
+                gpu: NVIDIA H100 80GB HBM3
+                gpu_count: 8
+                gpu_nvidia:
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-39c684a5-fde6-83d7-1663-0859795881ae
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-68012e5a-38b6-b643-0ca6-62fb66720bf3
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-132944c4-b689-2b5f-89a4-d730401677ab
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-2df386cc-6d26-d0e2-7a2d-a057b0d95864
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-bfa16575-1d94-1aa2-4537-2c93433f42ef
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-bc6c3e3c-9b90-09ca-c034-774961847c54
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-00a441e1-7c95-e7d6-4c35-43d6b291aea9
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-1c4d29a2-4647-6fce-d8fc-0c5ecfbbd6ea
+                host: deeplens-k3s-node1
+                memory:
+                    total: "2164089937920"
+                os: Linux-5.15.0-126-generic-x86_64-with-glibc2.35
+                program: /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/sweep.py
+                python: CPython 3.11.15
+                root: /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation
+                startedAt: "2026-08-12T23:37:04.657044Z"
+                writerId: 4qopxlj5t12670m45s6hbdlio87c05xg
+        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: linear
+adam_beta1:
+    value: 0.9
+adam_beta2:
+    value: 0.999
+adam_epsilon:
+    value: 1e-08
+architectures:
+    value: null
+attention_bias:
+    value: false
+attention_dropout:
+    value: 0
+auto_find_batch_size:
+    value: false
+average_tokens_across_devices:
+    value: true
+batch_eval_metrics:
+    value: false
+bf16:
+    value: true
+bf16_full_eval:
+    value: false
+bos_token_id:
+    value: 1
+chunk_size_feed_forward:
+    value: 0
+data_seed:
+    value: 42
+dataloader_drop_last:
+    value: false
+dataloader_in_order:
+    value: true
+dataloader_multiprocessing_context:
+    value: null
+dataloader_num_workers:
+    value: 0
+dataloader_persistent_workers:
+    value: false
+dataloader_pin_memory:
+    value: true
+dataloader_prefetch_factor:
+    value: null
+ddp_backend:
+    value: null
+ddp_broadcast_buffers:
+    value: null
+ddp_bucket_cap_mb:
+    value: null
+ddp_find_unused_parameters:
+    value: null
+ddp_static_graph:
+    value: null
+ddp_timeout:
+    value: 1800
+debug:
+    value: []
+deepspeed:
+    value: null
+disable_tqdm:
+    value: false
+do_eval:
+    value: true
+do_predict:
+    value: false
+do_train:
+    value: false
+dtype:
+    value: null
+enable_jit_checkpoint:
+    value: false
+eos_token_id:
+    value: 2
+eval_accumulation_steps:
+    value: null
+eval_delay:
+    value: 0
+eval_do_concat_batches:
+    value: true
+eval_on_start:
+    value: false
+eval_steps:
+    value: 2498
+eval_strategy:
+    value: steps
+eval_use_gather_object:
+    value: false
+fp16:
+    value: false
+fp16_full_eval:
+    value: false
+fsdp:
+    value: null
+fsdp_config:
+    value: null
+full_determinism:
+    value: false
+gradient_accumulation_steps:
+    value: 1
+gradient_checkpointing:
+    value: false
+gradient_checkpointing_kwargs:
+    value: null
+greater_is_better:
+    value: null
+head_dim:
+    value: 32
+hidden_act:
+    value: silu
+hidden_size:
+    value: 128
+hub_always_push:
+    value: false
+hub_model_id:
+    value: w-ahmad/6L-glu-linear-100L
+hub_private_repo:
+    value: null
+hub_revision:
+    value: null
+hub_strategy:
+    value: every_save
+hub_token:
+    value: <HUB_TOKEN>
+id2label:
+    value:
+        "0": LABEL_0
+        "1": LABEL_1
+ignore_data_skip:
+    value: false
+include_for_metrics:
+    value: []
+include_num_input_tokens_seen:
+    value: "no"
+initializer_range:
+    value: 0.02
+intermediate_size:
+    value: 256
+is_encoder_decoder:
+    value: false
+label_names:
+    value: null
+label_smoothing_factor:
+    value: 0
+label2id:
+    value:
+        LABEL_0: 0
+        LABEL_1: 1
+learning_rate:
+    value: 0.0007
+length_column_name:
+    value: length
+liger_kernel_config:
+    value: null
+load_best_model_at_end:
+    value: false
+local_rank:
+    value: -1
+log_level:
+    value: passive
+log_level_replica:
+    value: warning
+log_on_each_node:
+    value: true
+logging_first_step:
+    value: false
+logging_nan_inf_filter:
+    value: true
+logging_steps:
+    value: 20
+logging_strategy:
+    value: steps
+lr_scheduler_kwargs:
+    value: null
+lr_scheduler_type:
+    value: constant_with_warmup
+max_grad_norm:
+    value: 1
+max_position_embeddings:
+    value: 512
+max_steps:
+    value: 2500
+metric_for_best_model:
+    value: null
+mlp_bias:
+    value: false
+mlp_type:
+    value: glu
+model/num_parameters:
+    value: 16934016
+model_type:
+    value: tiny_llama
+neftune_noise_alpha:
+    value: null
+num_attention_heads:
+    value: 4
+num_hidden_layers:
+    value: 100
+num_key_value_heads:
+    value: 4
+num_train_epochs:
+    value: 1
+optim:
+    value: adamw_torch_fused
+optim_args:
+    value: null
+optim_target_modules:
+    value: null
+output_attentions:
+    value: false
+output_dir:
+    value: out/glu-linear-100L_run
+output_hidden_states:
+    value: false
+pad_token_id:
+    value: 0
+parallelism_config:
+    value: null
+per_device_eval_batch_size:
+    value: 1024
+per_device_train_batch_size:
+    value: 64
+prediction_loss_only:
+    value: false
+pretraining_tp:
+    value: 1
+problem_type:
+    value: null
+project:
+    value: huggingface
+push_to_hub:
+    value: false
+remove_unused_columns:
+    value: false
+report_to:
+    value:
+        - wandb
+restore_callback_states_from_checkpoint:
+    value: false
+resume_from_checkpoint:
+    value: null
+return_dict:
+    value: true
+rms_norm_eps:
+    value: 1e-06
+rope_parameters:
+    value:
+        rope_theta: 10000
+        rope_type: default
+run_name:
+    value: LM-glu-linear-100L-16.9M-20260812-233703
+save_on_each_node:
+    value: false
+save_only_model:
+    value: false
+save_steps:
+    value: 100
+save_strategy:
+    value: steps
+save_total_limit:
+    value: null
+seed:
+    value: 42
+skip_memory_metrics:
+    value: true
+tf32:
+    value: null
+tie_word_embeddings:
+    value: true
+tokenizer_name:
+    value: w-ahmad/tiny-stories-tokenizer
+torch_compile:
+    value: false
+torch_compile_backend:
+    value: null
+torch_compile_mode:
+    value: null
+torch_empty_cache_steps:
+    value: null
+trackio_bucket_id:
+    value: null
+trackio_space_id:
+    value: null
+trackio_static_space_id:
+    value: null
+train_sampling_strategy:
+    value: random
+transformers_version:
+    value: 5.16.0.dev0
+use_cache:
+    value: false
+use_cpu:
+    value: false
+use_liger_kernel:
+    value: false
+vocab_size:
+    value: 4096
+waleed_beta:
+    value: 10
+warmup_steps:
+    value: 500
+weight_decay:
+    value: 0

zain/Activation/wandb/run-20260812_233704-tpo5j00e/files/output.log

@@ -198,5 +198,63 @@ Writing model shards: 100%|██████████| 1/1 [00:00<00:00, 19.
   - 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, 18.11it/s]
- 81%|████████  | 2029/2500 [09:46<02:15,  3.48it/s], ?it/s]
+ 84%|████████▍ | 2100/2500 [10:06<01:57,  3.39it/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': '2.191', 'grad_norm': '0.4023', 'learning_rate': '0.0007', 'epoch': '0.1362', 'train/total_time_seconds': '476.3', 'train/time_per_step_avg': '0.2381', 'train/epoch_time_elapsed': '582.7', 'train/estimated_remaining_minutes': '1.886'}
+{'loss': '2.171', 'grad_norm': '0.4434', 'learning_rate': '0.0007', 'epoch': '0.1375', 'train/total_time_seconds': '481', 'train/time_per_step_avg': '0.2381', 'train/epoch_time_elapsed': '588.4', 'train/estimated_remaining_minutes': '1.808'}
+{'loss': '2.189', 'grad_norm': '0.3965', 'learning_rate': '0.0007', 'epoch': '0.1389', 'train/total_time_seconds': '485.7', 'train/time_per_step_avg': '0.2382', 'train/epoch_time_elapsed': '594.1', 'train/estimated_remaining_minutes': '1.729'}
+{'loss': '2.167', 'grad_norm': '0.3887', 'learning_rate': '0.0007', 'epoch': '0.1402', 'train/total_time_seconds': '490.5', 'train/time_per_step_avg': '0.2383', 'train/epoch_time_elapsed': '599.9', 'train/estimated_remaining_minutes': '1.651'}
+{'loss': '2.157', 'grad_norm': '0.377', 'learning_rate': '0.0007', 'epoch': '0.1416', 'train/total_time_seconds': '495.4', 'train/time_per_step_avg': '0.2406', 'train/epoch_time_elapsed': '605.9', 'train/estimated_remaining_minutes': '1.573'}
+  - 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, 14.67it/s]
+ 88%|████████▊ | 2200/2500 [10:36<01:27,  3.41it/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': '2.166', 'grad_norm': '0.3828', 'learning_rate': '0.0007', 'epoch': '0.1429', 'train/total_time_seconds': '500.2', 'train/time_per_step_avg': '0.2388', 'train/epoch_time_elapsed': '612', 'train/estimated_remaining_minutes': '1.494'}
+{'loss': '2.167', 'grad_norm': '0.4023', 'learning_rate': '0.0007', 'epoch': '0.1443', 'train/total_time_seconds': '505.1', 'train/time_per_step_avg': '0.2405', 'train/epoch_time_elapsed': '618', 'train/estimated_remaining_minutes': '1.416'}
+{'loss': '2.152', 'grad_norm': '0.3887', 'learning_rate': '0.0007', 'epoch': '0.1456', 'train/total_time_seconds': '509.9', 'train/time_per_step_avg': '0.2419', 'train/epoch_time_elapsed': '623.8', 'train/estimated_remaining_minutes': '1.338'}
+{'loss': '2.162', 'grad_norm': '0.3945', 'learning_rate': '0.0007', 'epoch': '0.1469', 'train/total_time_seconds': '514.7', 'train/time_per_step_avg': '0.2424', 'train/epoch_time_elapsed': '629.6', 'train/estimated_remaining_minutes': '1.259'}
+{'loss': '2.136', 'grad_norm': '0.3848', 'learning_rate': '0.0007', 'epoch': '0.1483', 'train/total_time_seconds': '519.5', 'train/time_per_step_avg': '0.2416', 'train/epoch_time_elapsed': '635.5', 'train/estimated_remaining_minutes': '1.181'}
+  - 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, 16.67it/s]
+ 92%|█████████▏| 2300/2500 [11:05<01:00,  3.28it/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': '2.144', 'grad_norm': '0.4062', 'learning_rate': '0.0007', 'epoch': '0.1496', 'train/total_time_seconds': '524.4', 'train/time_per_step_avg': '0.2416', 'train/epoch_time_elapsed': '641.7', 'train/estimated_remaining_minutes': '1.102'}
+{'loss': '2.156', 'grad_norm': '0.4199', 'learning_rate': '0.0007', 'epoch': '0.151', 'train/total_time_seconds': '529.2', 'train/time_per_step_avg': '0.241', 'train/epoch_time_elapsed': '647.5', 'train/estimated_remaining_minutes': '1.024'}
+{'loss': '2.133', 'grad_norm': '0.4043', 'learning_rate': '0.0007', 'epoch': '0.1523', 'train/total_time_seconds': '534.1', 'train/time_per_step_avg': '0.2416', 'train/epoch_time_elapsed': '653.4', 'train/estimated_remaining_minutes': '0.9452'}
+{'loss': '2.144', 'grad_norm': '0.3789', 'learning_rate': '0.0007', 'epoch': '0.1537', 'train/total_time_seconds': '538.9', 'train/time_per_step_avg': '0.2421', 'train/epoch_time_elapsed': '659.3', 'train/estimated_remaining_minutes': '0.8667'}
+{'loss': '2.127', 'grad_norm': '0.3945', 'learning_rate': '0.0007', 'epoch': '0.155', 'train/total_time_seconds': '543.8', 'train/time_per_step_avg': '0.2423', 'train/epoch_time_elapsed': '665.2', 'train/estimated_remaining_minutes': '0.7881'}
+  - 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, 17.38it/s]
+ 96%|█████████▌| 2400/2500 [11:35<00:29,  3.38it/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': '2.135', 'grad_norm': '0.4121', 'learning_rate': '0.0007', 'epoch': '0.1564', 'train/total_time_seconds': '548.8', 'train/time_per_step_avg': '0.2445', 'train/epoch_time_elapsed': '671.6', 'train/estimated_remaining_minutes': '0.7097'}
+{'loss': '2.124', 'grad_norm': '0.3711', 'learning_rate': '0.0007', 'epoch': '0.1577', 'train/total_time_seconds': '553.6', 'train/time_per_step_avg': '0.2445', 'train/epoch_time_elapsed': '677.4', 'train/estimated_remaining_minutes': '0.6309'}
+{'loss': '2.127', 'grad_norm': '0.3867', 'learning_rate': '0.0007', 'epoch': '0.1591', 'train/total_time_seconds': '558.4', 'train/time_per_step_avg': '0.2438', 'train/epoch_time_elapsed': '683.2', 'train/estimated_remaining_minutes': '0.5521'}
+{'loss': '2.13', 'grad_norm': '0.3887', 'learning_rate': '0.0007', 'epoch': '0.1604', 'train/total_time_seconds': '563.2', 'train/time_per_step_avg': '0.2433', 'train/epoch_time_elapsed': '689.1', 'train/estimated_remaining_minutes': '0.4733'}
+{'loss': '2.116', 'grad_norm': '0.4062', 'learning_rate': '0.0007', 'epoch': '0.1618', 'train/total_time_seconds': '568.1', 'train/time_per_step_avg': '0.2433', 'train/epoch_time_elapsed': '695', 'train/estimated_remaining_minutes': '0.3945'}
+  - 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, 16.05it/s]
+100%|██████████| 2500/2500 [12:35<00:00,  3.51s[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': '2.118', 'grad_norm': '0.4023', 'learning_rate': '0.0007', 'epoch': '0.1631', 'train/total_time_seconds': '572.9', 'train/time_per_step_avg': '0.2413', 'train/epoch_time_elapsed': '701.1', 'train/estimated_remaining_minutes': '0.3157'}
+{'loss': '2.105', 'grad_norm': '0.3809', 'learning_rate': '0.0007', 'epoch': '0.1645', 'train/total_time_seconds': '577.8', 'train/time_per_step_avg': '0.2416', 'train/epoch_time_elapsed': '707', 'train/estimated_remaining_minutes': '0.2368'}
+{'loss': '2.117', 'grad_norm': '0.3828', 'learning_rate': '0.0007', 'epoch': '0.1658', 'train/total_time_seconds': '582.6', 'train/time_per_step_avg': '0.2415', 'train/epoch_time_elapsed': '712.8', 'train/estimated_remaining_minutes': '0.1579'}
+{'loss': '2.117', 'grad_norm': '0.3926', 'learning_rate': '0.0007', 'epoch': '0.1672', 'train/total_time_seconds': '587.4', 'train/time_per_step_avg': '0.2417', 'train/epoch_time_elapsed': '718.7', 'train/estimated_remaining_minutes': '0.07895'}
+  - 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': '2.11', 'eval_runtime': '15.33', 'eval_samples_per_second': '621.6', 'eval_steps_per_second': '0.652', 'epoch': '0.1684', 'train/total_time_seconds': '591.8', 'train/time_per_step_avg': '0.2416', 'train/epoch_time_elapsed': '739.3', 'train/estimated_remaining_minutes': '0.007896'}
+{'loss': '2.1', 'grad_norm': '0.3789', 'learning_rate': '0.0007', 'epoch': '0.1685', 'train/total_time_seconds': '592.2', 'train/time_per_step_avg': '0.2415', 'train/epoch_time_elapsed': '739.8', 'train/estimated_remaining_minutes': '0'}
+{'eval_loss': '2.11', 'eval_runtime': '15.33', 'eval_samples_per_second': '621.4', 'eval_steps_per_second': '0.652', 'epoch': '0.1685', 'train/total_time_seconds': '592.2', 'train/time_per_step_avg': '0.2415', 'train/epoch_time_elapsed': '755.2', '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, 13.65it/s]
+100%|██████████| 2500/2500 [12:36<00:00,  3.31it/s], ?it/s]
+{'train_runtime': '756.2', 'train_samples_per_second': '211.6', 'train_steps_per_second': '3.306', 'train_loss': '3.001', 'epoch': '0.1685', 'train/total_time_seconds': '592.2', 'train/time_per_step_avg': '0.2415', 'train/epoch_time_elapsed': '755.5', 'train/estimated_remaining_minutes': '0'}
+100%|██████████| 10/10 [00:13<00:00,  1.31s/it]
+[transformers] TinyLlamaForCausalLM has generative capabilities, as `prepare_inputs_for_generation` is explicitly defined. However, it doesn't directly inherit from `GenerationMixin`. From 👉v4.50👈 onwards, `PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions.
+  - If you're using `trust_remote_code=True`, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
+  - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
+  - If you are not the owner of the model architecture class, please contact the model code owner to update it.
+Writing model shards: 100%|██████████| 1/1 [00:00<00:00, 17.20it/s]

zain/Activation/wandb/run-20260812_233704-tpo5j00e/files/wandb-summary.json

@@ -0,0 +1 @@
+{"_wandb":{"runtime":770},"train/train/total_time_seconds":592.2469161488116,"train_runtime":756.2272,"eval/runtime":15.3092,"train/train/epoch_time_elapsed":770.8056703023612,"train_samples_per_second":211.577,"total_flos":8.06570950656e+15,"_runtime":770,"_step":128,"eval/loss":2.1097066402435303,"train_steps_per_second":3.306,"eval/samples_per_second":622.305,"train/train/time_per_step_avg":0.2415289905667305,"train/grad_norm":0.37890625,"eval/steps_per_second":0.653,"_timestamp":1.7865785961217074e+09,"train/train/estimated_remaining_minutes":0,"train/learning_rate":0.0007,"train/loss":2.100436973571777,"train/global_step":2500,"train_loss":3.001207452392578,"train/epoch":0.16852039096730703}

zain/Activation/wandb/run-20260812_233704-tpo5j00e/logs/debug-core.log

@@ -90,3 +90,11 @@
 {"time":"2026-08-12T23:37:04.659365837Z","level":"INFO","msg":"handleInformInit: received","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:04.922876846Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"tpo5j00e","id":"5(@)"}
 {"time":"2026-08-12T23:37:10.31045638Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.216535938Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.703966372Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"zbcpym8ebxly"}
+{"time":"2026-08-12T23:49:56.705445032Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:56.705984097Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"tpo5j00e","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200430345Z","level":"INFO","msg":"connection: closing","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200526275Z","level":"INFO","msg":"connection: closed successfully","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200433558Z","level":"INFO","msg":"processOutgoingData: finished","id":"5(@)"}
+{"time":"2026-08-12T23:49:58.200535053Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"5(@)"}

zain/Activation/wandb/run-20260812_233704-tpo5j00e/logs/debug-internal.log

@@ -85,3 +85,35 @@
 {"time":"2026-08-12T23:46:35.998150976Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
 {"time":"2026-08-12T23:46:50.874132215Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":98,"history_lines":3,"events_offset":76,"events_lines":2,"console_offset":190,"console_lines":1}
 {"time":"2026-08-12T23:46:51.1109748Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:47:05.873911748Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":101,"history_lines":3,"events_offset":78,"events_lines":2,"console_offset":194,"console_lines":11}
+{"time":"2026-08-12T23:47:06.048101755Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:47:20.874022923Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":104,"history_lines":2,"events_offset":80,"events_lines":2,"console_offset":200,"console_lines":1}
+{"time":"2026-08-12T23:47:21.005671585Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:47:35.873635563Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":106,"history_lines":3,"events_offset":82,"events_lines":2,"console_offset":205,"console_lines":10}
+{"time":"2026-08-12T23:47:36.000550646Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:47:50.87376451Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":109,"history_lines":2,"events_offset":84,"events_lines":2,"console_offset":210,"console_lines":1}
+{"time":"2026-08-12T23:47:51.121247495Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:48:05.873619511Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":111,"history_lines":3,"events_offset":86,"events_lines":2,"console_offset":215,"console_lines":10}
+{"time":"2026-08-12T23:48:06.082648628Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:48:20.874292434Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":114,"history_lines":2,"events_offset":88,"events_lines":2,"console_offset":220,"console_lines":1}
+{"time":"2026-08-12T23:48:21.069644658Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:48:35.874379741Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":116,"history_lines":3,"events_offset":90,"events_lines":2,"console_offset":225,"console_lines":10}
+{"time":"2026-08-12T23:48:36.100237591Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:48:50.873603862Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":119,"history_lines":2,"events_offset":92,"events_lines":2,"console_offset":230,"console_lines":1}
+{"time":"2026-08-12T23:48:50.998416569Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:49:05.873747271Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":121,"history_lines":3,"events_offset":94,"events_lines":2,"console_offset":235,"console_lines":10}
+{"time":"2026-08-12T23:49:06.067209608Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:49:20.873615557Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":96,"events_lines":2,"console_offset":240,"console_lines":1}
+{"time":"2026-08-12T23:49:21.08163947Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:49:35.873636608Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":124,"history_lines":2,"events_offset":98,"events_lines":2,"console_offset":240,"console_lines":1}
+{"time":"2026-08-12T23:49:35.988320548Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:49:50.873659846Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":126,"history_lines":2,"events_offset":100,"events_lines":2,"console_offset":240,"console_lines":1}
+{"time":"2026-08-12T23:49:51.048489153Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:49:56.598587763Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2026-08-12T23:49:56.598789418Z","level":"INFO","msg":"filestream: sending request","total_files":3,"history_offset":128,"history_lines":1,"console_offset":245,"console_lines":15,"uploaded_len":3,"complete":true,"exit_code":0}
+{"time":"2026-08-12T23:49:56.701784518Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-12T23:49:56.702912833Z","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2026-08-12T23:49:56.705484814Z","level":"INFO","msg":"stream: finishing up"}
+{"time":"2026-08-12T23:49:56.705519356Z","level":"INFO","msg":"handler: closed"}
+{"time":"2026-08-12T23:49:56.705632565Z","level":"INFO","msg":"sender: closed"}
+{"time":"2026-08-12T23:49:56.705637913Z","level":"INFO","msg":"stream: all finished"}

zain/Activation/wandb/run-20260812_233704-tpo5j00e/logs/debug.log

@@ -18,3 +18,8 @@ config: {'_wandb': {}}
 2026-08-12 23:37:05,310 INFO    MainThread:3978000 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.16.0.dev0', 'architectures': None, 'output_hidden_states': False, 'return_dict': True, 'dtype': None, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, 'vocab_size': 4096, 'hidden_size': 128, 'intermediate_size': 256, 'num_hidden_layers': 100, 'num_attention_heads': 4, 'num_key_value_heads': 4, 'hidden_act': 'silu', 'max_position_embeddings': 512, 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'pad_token_id': 0, 'bos_token_id': 1, 'eos_token_id': 2, 'pretraining_tp': 1, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 10000.0, 'rope_type': 'default'}, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'head_dim': 32, '_name_or_path': '', 'tokenizer_name': 'w-ahmad/tiny-stories-tokenizer', 'mlp_type': 'glu', 'activation': 'linear', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-linear-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-linear-100L-16.9M-20260812-233703', '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-linear-100L', 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': None, 'dataloader_multiprocessing_context': None, 'dataloader_in_order': True, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_static_graph': None, 'ddp_backend': None, 'ddp_timeout': 1800, 'fsdp': None, 'fsdp_config': None, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'local_rank': -1}
 2026-08-12 23:37:05,315 INFO    MainThread:3978000 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 16934016 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x14d9ca094510>>
 2026-08-12 23:37:05,315 INFO    MainThread:3978000 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 16934016 None
+2026-08-12 23:49:56,215 INFO    MainThread:3978000 [wandb_run.py:_finish():2383] finishing run deepnevro-deepnevro/research3/tpo5j00e
+2026-08-12 23:49:56,216 INFO    MainThread:3978000 [wandb_run.py:_atexit_cleanup():2588] got exitcode: 0
+2026-08-12 23:49:56,216 INFO    MainThread:3978000 [wandb_run.py:_restore():2570] restore
+2026-08-12 23:49:56,216 INFO    MainThread:3978000 [wandb_run.py:_restore():2576] restore done
+2026-08-12 23:49:56,704 INFO    MainThread:3978000 [wandb_run.py:_footer_sync_info():3993] logging synced files

zain/Activation/wandb/run-20260812_233704-tpo5j00e/run-tpo5j00e.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0af7a2a6ab4c2f8e74e2aaf695ba41a618c3432bd26271f4dbfd0dce107cc40f
-size 655360
+oid sha256:0e8c372abca862a576b74703502d7d4917ae126c385be1268175a7ac663bf48a
+size 877846