Auto upload zain 2026-08-17T21:56:09.246116

zain/Activation/out/glu-waleed10-100L_run/config.json

@@ -0,0 +1,37 @@
+{
+  "activation": "waleed10",
+  "architectures": [
+    "TinyLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "mlp_type": "glu",
+  "model_type": "tiny_llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 100,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "powlu_m": 3.0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "tokenizer_name": "w-ahmad/tiny-stories-tokenizer",
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": false,
+  "vocab_size": 4096,
+  "waleed_beta": 10
+}

zain/Activation/out/glu-waleed10-100L_run/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5a75cb7729ae138bac0c30ffb3b0da5b7902b6e0d5afc4e0059a39cd9f90448
+size 33967272

zain/Activation/out/glu-waleed10-100L_run/tokenizer_config.json

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

zain/Activation/out/glu-waleed10-100L_run/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a48a9175d03ddab0ddfdf28b7f3b300292f8c5c15a49069a4660d3bd75c2a85
+size 4920

zain/Activation/out/glu-waleed10-100L_run/training_log.jsonl

@@ -126,3 +126,4 @@
 {"step": 2500, "epoch": 0.16852039096730703, "timestamp": 1787003708.0514393, "loss": 2.099496269226074, "grad_norm": 0.373046875, "learning_rate": 0.0007, "train/total_time_seconds": 592.235937781632, "train/time_per_step_avg": 0.2351588799804449, "train/epoch_time_elapsed": 739.2880429252982, "train/estimated_remaining_minutes": 0.0}
 {"step": 2500, "epoch": 0.16852039096730703, "timestamp": 1787003723.416086, "eval_loss": 2.1109981536865234, "eval_runtime": 15.3628, "eval_samples_per_second": 620.134, "eval_steps_per_second": 0.651, "train/total_time_seconds": 592.235937781632, "train/time_per_step_avg": 0.2351588799804449, "train/epoch_time_elapsed": 754.6526881679893, "train/estimated_remaining_minutes": 0.0}
 {"step": 2500, "epoch": 0.16852039096730703, "timestamp": 1787003723.6850483, "train_runtime": 755.6169, "train_samples_per_second": 211.748, "train_steps_per_second": 3.309, "total_flos": 8065709506560000.0, "train_loss": 3.0004124618530272, "train/total_time_seconds": 592.235937781632, "train/time_per_step_avg": 0.2351588799804449, "train/epoch_time_elapsed": 754.9216492772102, "train/estimated_remaining_minutes": 0.0}
+{"step": 2500, "epoch": 0.16852039096730703, "timestamp": 1787003739.0247736, "eval_loss": 2.1109981536865234, "eval_runtime": 15.3366, "eval_samples_per_second": 621.195, "eval_steps_per_second": 0.652, "train/total_time_seconds": 592.235937781632, "train/time_per_step_avg": 0.2351588799804449, "train/epoch_time_elapsed": 770.2613758407533, "train/estimated_remaining_minutes": 0.0}

zain/Activation/out/sweep_summary.json

@@ -1,9 +1,9 @@
 [
   {
-    "variant": "glu-powlu-100L",
-    "eval_loss": 2.1375532150268555,
-    "out": "out/glu-powlu-100L_run",
-    "run_name": "LM-glu-powlu-100L-16.9M-20260817-212142",
+    "variant": "glu-waleed10-100L",
+    "eval_loss": 2.1109981536865234,
+    "out": "out/glu-waleed10-100L_run",
+    "run_name": "LM-glu-waleed10-100L-16.9M-20260817-214247",
     "status": "success"
   }
 ]

zain/Activation/wandb/debug-internal.log

@@ -109,3 +109,11 @@
 {"time":"2026-08-17T21:55:18.864555475Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
 {"time":"2026-08-17T21:55:33.764214533Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":126,"history_lines":2,"events_offset":99,"events_lines":2,"console_offset":242,"console_lines":1}
 {"time":"2026-08-17T21:55:33.868401542Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-17T21:55:39.514425851Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2026-08-17T21:55:39.514648079Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":128,"history_lines":1,"events_offset":101,"events_lines":1,"console_offset":247,"console_lines":16,"uploaded_len":3,"complete":true,"exit_code":0}
+{"time":"2026-08-17T21:55:39.643703267Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
+{"time":"2026-08-17T21:55:39.644854437Z","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2026-08-17T21:55:39.647531062Z","level":"INFO","msg":"stream: finishing up"}
+{"time":"2026-08-17T21:55:39.647544246Z","level":"INFO","msg":"handler: closed"}
+{"time":"2026-08-17T21:55:39.647611239Z","level":"INFO","msg":"sender: closed"}
+{"time":"2026-08-17T21:55:39.647617196Z","level":"INFO","msg":"stream: all finished"}

zain/Activation/wandb/debug.log

@@ -21,3 +21,8 @@ config: {'_wandb': {}}
 2026-08-17 21:42:48,758 INFO    MainThread:156888 [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': 'waleed10', 'waleed_beta': 10, 'powlu_m': 3.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-waleed10-100L_run', 'per_device_train_batch_size': 64, 'num_train_epochs': 1, 'max_steps': 2500, 'learning_rate': 0.0007, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 500, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 1.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-waleed10-100L-16.9M-20260817-214247', '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-waleed10-100L', 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': None, 'dataloader_multiprocessing_context': None, 'dataloader_in_order': True, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_static_graph': None, 'ddp_backend': None, 'ddp_timeout': 1800, 'fsdp': None, 'fsdp_config': None, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'local_rank': -1}
 2026-08-17 21:42:48,762 INFO    MainThread:156888 [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 0x14e8739544d0>>
 2026-08-17 21:42:48,762 INFO    MainThread:156888 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 16934016 None
+2026-08-17 21:55:39,118 INFO    MainThread:156888 [wandb_run.py:_finish():2383] finishing run deepnevro-deepnevro/research3/bayjxr06
+2026-08-17 21:55:39,118 INFO    MainThread:156888 [wandb_run.py:_atexit_cleanup():2588] got exitcode: 0
+2026-08-17 21:55:39,118 INFO    MainThread:156888 [wandb_run.py:_restore():2570] restore
+2026-08-17 21:55:39,118 INFO    MainThread:156888 [wandb_run.py:_restore():2576] restore done
+2026-08-17 21:55:39,647 INFO    MainThread:156888 [wandb_run.py:_footer_sync_info():3993] logging synced files

zain/Activation/wandb/run-20260817_201809-chi6cgt9/logs/debug-core.log

@@ -93,3 +93,11 @@
 {"time":"2026-08-17T21:42:48.193764205Z","level":"INFO","msg":"handleInformInit: received","streamId":"bayjxr06","id":"4(@)"}
 {"time":"2026-08-17T21:42:48.434515875Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"bayjxr06","id":"4(@)"}
 {"time":"2026-08-17T21:42:53.75650754Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"z4mrpmc6mupe"}
+{"time":"2026-08-17T21:55:39.11909524Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"z4mrpmc6mupe"}
+{"time":"2026-08-17T21:55:39.645968409Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"z4mrpmc6mupe"}
+{"time":"2026-08-17T21:55:39.647499084Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"bayjxr06","id":"4(@)"}
+{"time":"2026-08-17T21:55:39.648181434Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"bayjxr06","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784781346Z","level":"INFO","msg":"connection: closing","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784866686Z","level":"INFO","msg":"connection: closed successfully","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784796267Z","level":"INFO","msg":"processOutgoingData: finished","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784876267Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"4(@)"}

zain/Activation/wandb/run-20260817_201955-d2y5n025/logs/debug-core.log

@@ -93,3 +93,11 @@
 {"time":"2026-08-17T21:42:48.193764205Z","level":"INFO","msg":"handleInformInit: received","streamId":"bayjxr06","id":"4(@)"}
 {"time":"2026-08-17T21:42:48.434515875Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"bayjxr06","id":"4(@)"}
 {"time":"2026-08-17T21:42:53.75650754Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"z4mrpmc6mupe"}
+{"time":"2026-08-17T21:55:39.11909524Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"z4mrpmc6mupe"}
+{"time":"2026-08-17T21:55:39.645968409Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"z4mrpmc6mupe"}
+{"time":"2026-08-17T21:55:39.647499084Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"bayjxr06","id":"4(@)"}
+{"time":"2026-08-17T21:55:39.648181434Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"bayjxr06","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784781346Z","level":"INFO","msg":"connection: closing","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784866686Z","level":"INFO","msg":"connection: closed successfully","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784796267Z","level":"INFO","msg":"processOutgoingData: finished","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784876267Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"4(@)"}

zain/Activation/wandb/run-20260817_202145-meqn6qqc/logs/debug-core.log

@@ -93,3 +93,11 @@
 {"time":"2026-08-17T21:42:48.193764205Z","level":"INFO","msg":"handleInformInit: received","streamId":"bayjxr06","id":"4(@)"}
 {"time":"2026-08-17T21:42:48.434515875Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"bayjxr06","id":"4(@)"}
 {"time":"2026-08-17T21:42:53.75650754Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"z4mrpmc6mupe"}
+{"time":"2026-08-17T21:55:39.11909524Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"z4mrpmc6mupe"}
+{"time":"2026-08-17T21:55:39.645968409Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"z4mrpmc6mupe"}
+{"time":"2026-08-17T21:55:39.647499084Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"bayjxr06","id":"4(@)"}
+{"time":"2026-08-17T21:55:39.648181434Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"bayjxr06","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784781346Z","level":"INFO","msg":"connection: closing","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784866686Z","level":"INFO","msg":"connection: closed successfully","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784796267Z","level":"INFO","msg":"processOutgoingData: finished","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784876267Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"4(@)"}

zain/Activation/wandb/run-20260817_202336-sdre4o68/logs/debug-core.log

@@ -93,3 +93,11 @@
 {"time":"2026-08-17T21:42:48.193764205Z","level":"INFO","msg":"handleInformInit: received","streamId":"bayjxr06","id":"4(@)"}
 {"time":"2026-08-17T21:42:48.434515875Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"bayjxr06","id":"4(@)"}
 {"time":"2026-08-17T21:42:53.75650754Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"z4mrpmc6mupe"}
+{"time":"2026-08-17T21:55:39.11909524Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"z4mrpmc6mupe"}
+{"time":"2026-08-17T21:55:39.645968409Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"z4mrpmc6mupe"}
+{"time":"2026-08-17T21:55:39.647499084Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"bayjxr06","id":"4(@)"}
+{"time":"2026-08-17T21:55:39.648181434Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"bayjxr06","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784781346Z","level":"INFO","msg":"connection: closing","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784866686Z","level":"INFO","msg":"connection: closed successfully","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784796267Z","level":"INFO","msg":"processOutgoingData: finished","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784876267Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"4(@)"}

zain/Activation/wandb/run-20260817_202539-5ly4s0xi/logs/debug-core.log

@@ -93,3 +93,11 @@
 {"time":"2026-08-17T21:42:48.193764205Z","level":"INFO","msg":"handleInformInit: received","streamId":"bayjxr06","id":"4(@)"}
 {"time":"2026-08-17T21:42:48.434515875Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"bayjxr06","id":"4(@)"}
 {"time":"2026-08-17T21:42:53.75650754Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"z4mrpmc6mupe"}
+{"time":"2026-08-17T21:55:39.11909524Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"z4mrpmc6mupe"}
+{"time":"2026-08-17T21:55:39.645968409Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"z4mrpmc6mupe"}
+{"time":"2026-08-17T21:55:39.647499084Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"bayjxr06","id":"4(@)"}
+{"time":"2026-08-17T21:55:39.648181434Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"bayjxr06","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784781346Z","level":"INFO","msg":"connection: closing","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784866686Z","level":"INFO","msg":"connection: closed successfully","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784796267Z","level":"INFO","msg":"processOutgoingData: finished","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784876267Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"4(@)"}

zain/Activation/wandb/run-20260817_202746-fahqmmw3/logs/debug-core.log

@@ -93,3 +93,11 @@
 {"time":"2026-08-17T21:42:48.193764205Z","level":"INFO","msg":"handleInformInit: received","streamId":"bayjxr06","id":"4(@)"}
 {"time":"2026-08-17T21:42:48.434515875Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"bayjxr06","id":"4(@)"}
 {"time":"2026-08-17T21:42:53.75650754Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"z4mrpmc6mupe"}
+{"time":"2026-08-17T21:55:39.11909524Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"z4mrpmc6mupe"}
+{"time":"2026-08-17T21:55:39.645968409Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"z4mrpmc6mupe"}
+{"time":"2026-08-17T21:55:39.647499084Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"bayjxr06","id":"4(@)"}
+{"time":"2026-08-17T21:55:39.648181434Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"bayjxr06","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784781346Z","level":"INFO","msg":"connection: closing","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784866686Z","level":"INFO","msg":"connection: closed successfully","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784796267Z","level":"INFO","msg":"processOutgoingData: finished","id":"4(@)"}
+{"time":"2026-08-17T21:55:41.784876267Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"4(@)"}