w-ahmad commited on
Commit
700304d
·
verified ·
1 Parent(s): 4361520

Auto upload zain 2026-08-14T21:04:09.516498 (part 4)

Browse files
zain/Activation/wandb/debug-internal.log CHANGED
@@ -1,69 +1,27 @@
1
- {"time":"2026-08-14T20:51:35.100777306Z","level":"INFO","msg":"wandb-core"}
2
- {"time":"2026-08-14T20:51:35.100913071Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
3
- {"time":"2026-08-14T20:51:35.362984443Z","level":"INFO","msg":"stream: created new stream","id":"0vnbmyac"}
4
- {"time":"2026-08-14T20:51:35.363087423Z","level":"INFO","msg":"handler: started"}
5
- {"time":"2026-08-14T20:51:35.363181179Z","level":"INFO","msg":"stream: started"}
6
- {"time":"2026-08-14T20:51:35.363190958Z","level":"INFO","msg":"writer: started","stream_id":"0vnbmyac"}
7
- {"time":"2026-08-14T20:51:35.363209771Z","level":"INFO","msg":"sender: started"}
8
- {"time":"2026-08-14T20:51:35.741997277Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
9
- {"time":"2026-08-14T20:51:35.84269821Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
10
- {"time":"2026-08-14T20:51:50.74305459Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":1,"events_offset":0,"events_lines":1,"console_offset":0,"console_lines":2,"uploaded_len":2}
11
- {"time":"2026-08-14T20:51:50.862371107Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
12
- {"time":"2026-08-14T20:52:05.743189399Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":1,"history_lines":1,"events_offset":1,"events_lines":2,"console_offset":0,"console_lines":1}
13
- {"time":"2026-08-14T20:52:05.935614697Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
14
- {"time":"2026-08-14T20:52:20.742315291Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":2,"history_lines":1,"events_offset":3,"events_lines":2,"console_offset":0,"console_lines":1}
15
- {"time":"2026-08-14T20:52:20.879767685Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
16
- {"time":"2026-08-14T20:52:35.742223827Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3,"history_lines":1,"events_offset":5,"events_lines":2,"console_offset":0,"console_lines":1}
17
- {"time":"2026-08-14T20:52:35.91828813Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
18
- {"time":"2026-08-14T20:52:50.742917562Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":4,"history_lines":1,"events_offset":7,"events_lines":2,"console_offset":0,"console_lines":1}
19
- {"time":"2026-08-14T20:52:50.952860222Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
20
- {"time":"2026-08-14T20:53:05.742571989Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":5,"history_lines":1,"events_offset":9,"events_lines":2,"console_offset":2,"console_lines":10}
21
- {"time":"2026-08-14T20:53:05.950400826Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
22
- {"time":"2026-08-14T20:53:20.743003248Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":6,"history_lines":1,"events_offset":11,"events_lines":2,"console_offset":10,"console_lines":1}
23
- {"time":"2026-08-14T20:53:20.878601345Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
24
- {"time":"2026-08-14T20:53:35.742277588Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":7,"history_lines":1,"events_offset":13,"events_lines":2,"console_offset":10,"console_lines":1}
25
- {"time":"2026-08-14T20:53:35.878877156Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
26
- {"time":"2026-08-14T20:53:50.742344897Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":8,"history_lines":1,"events_offset":15,"events_lines":2,"console_offset":10,"console_lines":1}
27
- {"time":"2026-08-14T20:53:50.880217316Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
28
- {"time":"2026-08-14T20:54:05.742487579Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":9,"history_lines":1,"events_offset":17,"events_lines":2,"console_offset":10,"console_lines":1}
29
- {"time":"2026-08-14T20:54:05.963625523Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
30
- {"time":"2026-08-14T20:54:20.74274057Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":10,"history_lines":1,"events_offset":19,"events_lines":2,"console_offset":12,"console_lines":10}
31
- {"time":"2026-08-14T20:54:20.909526742Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
32
- {"time":"2026-08-14T20:54:35.742273229Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":11,"history_lines":1,"events_offset":21,"events_lines":2,"console_offset":20,"console_lines":1}
33
- {"time":"2026-08-14T20:54:35.900285773Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
34
- {"time":"2026-08-14T20:54:50.74282118Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":12,"history_lines":2,"events_offset":23,"events_lines":2,"console_offset":20,"console_lines":1}
35
- {"time":"2026-08-14T20:54:50.879927051Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
36
- {"time":"2026-08-14T20:55:05.742737309Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":14,"history_lines":1,"events_offset":25,"events_lines":2,"console_offset":20,"console_lines":1}
37
- {"time":"2026-08-14T20:55:05.890409369Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
38
- {"time":"2026-08-14T20:55:20.742717182Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":15,"history_lines":1,"events_offset":27,"events_lines":2,"console_offset":22,"console_lines":10}
39
- {"time":"2026-08-14T20:55:20.900741071Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
40
- {"time":"2026-08-14T20:55:35.742262345Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":16,"history_lines":2,"events_offset":29,"events_lines":2,"console_offset":30,"console_lines":1}
41
- {"time":"2026-08-14T20:55:35.880593639Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
42
- {"time":"2026-08-14T20:55:50.742451906Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":18,"history_lines":1,"events_offset":31,"events_lines":2,"console_offset":30,"console_lines":1}
43
- {"time":"2026-08-14T20:55:50.85634988Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
44
- {"time":"2026-08-14T20:56:05.742663154Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":19,"history_lines":2,"events_offset":33,"events_lines":2,"console_offset":30,"console_lines":1}
45
- {"time":"2026-08-14T20:56:05.912974963Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
46
- {"time":"2026-08-14T20:56:20.742907374Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":21,"history_lines":1,"events_offset":35,"events_lines":2,"console_offset":32,"console_lines":11}
47
- {"time":"2026-08-14T20:56:20.861920599Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
48
- {"time":"2026-08-14T20:56:35.743067548Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":22,"history_lines":1,"events_offset":37,"events_lines":2,"console_offset":40,"console_lines":1}
49
- {"time":"2026-08-14T20:56:35.862598492Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
50
- {"time":"2026-08-14T20:56:50.74299387Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":23,"history_lines":2,"events_offset":39,"events_lines":2,"console_offset":40,"console_lines":1}
51
- {"time":"2026-08-14T20:56:50.873632457Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
52
- {"time":"2026-08-14T20:57:05.743081486Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":25,"history_lines":1,"events_offset":41,"events_lines":2,"console_offset":43,"console_lines":9}
53
- {"time":"2026-08-14T20:57:05.926746736Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
54
- {"time":"2026-08-14T20:57:20.742460529Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":26,"history_lines":1,"events_offset":43,"events_lines":2,"console_offset":50,"console_lines":1}
55
- {"time":"2026-08-14T20:57:20.894469855Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
56
- {"time":"2026-08-14T20:57:35.742511261Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":27,"history_lines":2,"events_offset":45,"events_lines":2,"console_offset":50,"console_lines":1}
57
- {"time":"2026-08-14T20:57:35.89412732Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
58
- {"time":"2026-08-14T20:57:50.742672344Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":29,"history_lines":1,"events_offset":47,"events_lines":2,"console_offset":50,"console_lines":1}
59
- {"time":"2026-08-14T20:57:50.860204267Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
60
- {"time":"2026-08-14T20:58:05.743033614Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":30,"history_lines":1,"events_offset":49,"events_lines":2,"console_offset":52,"console_lines":10}
61
- {"time":"2026-08-14T20:58:05.900013888Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
62
- {"time":"2026-08-14T20:58:20.742345026Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":31,"history_lines":2,"events_offset":51,"events_lines":2,"console_offset":60,"console_lines":1}
63
- {"time":"2026-08-14T20:58:20.845188715Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
64
- {"time":"2026-08-14T20:58:35.742302555Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":33,"history_lines":1,"events_offset":53,"events_lines":2,"console_offset":60,"console_lines":1}
65
- {"time":"2026-08-14T20:58:35.870270983Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
66
- {"time":"2026-08-14T20:58:50.742429574Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":34,"history_lines":1,"events_offset":55,"events_lines":2,"console_offset":60,"console_lines":1}
67
- {"time":"2026-08-14T20:58:50.87090741Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
68
- {"time":"2026-08-14T20:59:05.742918017Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":35,"history_lines":2,"events_offset":57,"events_lines":2,"console_offset":62,"console_lines":11}
69
- {"time":"2026-08-14T20:59:05.878151617Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
 
1
+ {"time":"2026-08-14T21:01:55.967436258Z","level":"INFO","msg":"wandb-core"}
2
+ {"time":"2026-08-14T21:01:55.967577973Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
3
+ {"time":"2026-08-14T21:01:56.228468944Z","level":"INFO","msg":"stream: created new stream","id":"rxpj34pj"}
4
+ {"time":"2026-08-14T21:01:56.228571423Z","level":"INFO","msg":"handler: started"}
5
+ {"time":"2026-08-14T21:01:56.228674212Z","level":"INFO","msg":"stream: started"}
6
+ {"time":"2026-08-14T21:01:56.228689116Z","level":"INFO","msg":"writer: started","stream_id":"rxpj34pj"}
7
+ {"time":"2026-08-14T21:01:56.228712767Z","level":"INFO","msg":"sender: started"}
8
+ {"time":"2026-08-14T21:01:56.612709801Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
9
+ {"time":"2026-08-14T21:01:56.724524535Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
10
+ {"time":"2026-08-14T21:02:11.613736811Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":1,"events_offset":0,"events_lines":1,"console_offset":0,"console_lines":2,"uploaded_len":2}
11
+ {"time":"2026-08-14T21:02:11.755716385Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
12
+ {"time":"2026-08-14T21:02:26.613440627Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":1,"history_lines":1,"events_offset":1,"events_lines":2,"console_offset":0,"console_lines":1}
13
+ {"time":"2026-08-14T21:02:26.756459811Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
14
+ {"time":"2026-08-14T21:02:41.612944581Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":2,"history_lines":1,"events_offset":3,"events_lines":2,"console_offset":0,"console_lines":1}
15
+ {"time":"2026-08-14T21:02:41.737144385Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
16
+ {"time":"2026-08-14T21:02:56.61357413Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3,"history_lines":1,"events_offset":5,"events_lines":2,"console_offset":0,"console_lines":1}
17
+ {"time":"2026-08-14T21:02:56.736287618Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
18
+ {"time":"2026-08-14T21:03:11.613376401Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":4,"history_lines":1,"events_offset":7,"events_lines":2,"console_offset":0,"console_lines":1}
19
+ {"time":"2026-08-14T21:03:11.772005165Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
20
+ {"time":"2026-08-14T21:03:26.613829663Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":5,"history_lines":1,"events_offset":9,"events_lines":2,"console_offset":2,"console_lines":10}
21
+ {"time":"2026-08-14T21:03:26.755273016Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
22
+ {"time":"2026-08-14T21:03:41.613471478Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":6,"history_lines":1,"events_offset":11,"events_lines":2,"console_offset":10,"console_lines":1}
23
+ {"time":"2026-08-14T21:03:41.725523747Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
24
+ {"time":"2026-08-14T21:03:56.612890048Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":7,"history_lines":1,"events_offset":13,"events_lines":2,"console_offset":10,"console_lines":1}
25
+ {"time":"2026-08-14T21:03:56.723039149Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
26
+ {"time":"2026-08-14T21:04:11.613835461Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":8,"history_lines":1,"events_offset":15,"events_lines":2,"console_offset":10,"console_lines":1}
27
+ {"time":"2026-08-14T21:04:11.764020425Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
zain/Activation/wandb/debug.log CHANGED
@@ -1,19 +1,19 @@
1
- 2026-08-14 20:51:35,099 INFO MainThread:409188 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260814_205135-0vnbmyac/logs/debug.log
2
- 2026-08-14 20:51:35,099 INFO MainThread:409188 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260814_205135-0vnbmyac/logs/debug-internal.log
3
- 2026-08-14 20:51:35,099 INFO MainThread:409188 [wandb_init.py:init():772] calling init triggers
4
- 2026-08-14 20:51:35,099 INFO MainThread:409188 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
5
  config: {'_wandb': {}}
6
- 2026-08-14 20:51:35,099 INFO MainThread:409188 [wandb_init.py:init():820] starting backend
7
- 2026-08-14 20:51:35,099 INFO MainThread:409188 [wandb_init.py:init():835] sending inform_init request
8
- 2026-08-14 20:51:35,363 INFO MainThread:409188 [wandb_init.py:init():840] backend started and connected
9
- 2026-08-14 20:51:35,365 INFO MainThread:409188 [wandb_init.py:init():910] updated telemetry
10
- 2026-08-14 20:51:35,373 INFO MainThread:409188 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
11
- 2026-08-14 20:51:35,661 INFO MainThread:409188 [wandb_init.py:init():978] starting run threads in backend
12
- 2026-08-14 20:51:35,736 INFO MainThread:409188 [wandb_run.py:_console_start():2621] atexit reg
13
- 2026-08-14 20:51:35,736 INFO MainThread:409188 [wandb_run.py:_redirect():2471] redirect: wrap_raw
14
- 2026-08-14 20:51:35,736 INFO MainThread:409188 [wandb_run.py:_redirect():2540] Wrapping output streams.
15
- 2026-08-14 20:51:35,736 INFO MainThread:409188 [wandb_run.py:_redirect():2563] Redirects installed.
16
- 2026-08-14 20:51:35,737 INFO MainThread:409188 [wandb_init.py:init():1016] run started, returning control to user process
17
- 2026-08-14 20:51:35,738 INFO MainThread:409188 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.16.0.dev0', 'architectures': None, 'output_hidden_states': False, 'return_dict': True, 'dtype': None, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, 'vocab_size': 4096, 'hidden_size': 128, 'intermediate_size': 256, 'num_hidden_layers': 9, 'num_attention_heads': 4, 'num_key_value_heads': 4, 'hidden_act': 'silu', 'max_position_embeddings': 512, 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'pad_token_id': 0, 'bos_token_id': 1, 'eos_token_id': 2, 'pretraining_tp': 1, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 10000.0, 'rope_type': 'default'}, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'head_dim': 32, '_name_or_path': '', 'tokenizer_name': 'w-ahmad/tiny-stories-tokenizer', 'mlp_type': 'glu', 'activation': 'waleed', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-waleed-9L_run', 'per_device_train_batch_size': 512, 'num_train_epochs': 1, 'max_steps': 1000, 'learning_rate': 0.001, 'lr_scheduler_type': 'constant', 'lr_scheduler_kwargs': None, 'warmup_steps': 0, 'optim': 'adamw_torch', 'optim_args': None, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 1.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-waleed-9L-2.0M-20260814-205134', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 60000, 'eval_delay': 0, 'per_device_eval_batch_size': 512, 'prediction_loss_only': False, 'eval_on_start': False, 'eval_do_concat_batches': True, 'eval_use_gather_object': False, 'eval_accumulation_steps': None, 'include_for_metrics': [], 'batch_eval_metrics': False, 'save_only_model': False, 'save_strategy': 'steps', 'save_steps': 100, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/A-glu-waleed-9L', 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': None, 'dataloader_multiprocessing_context': None, 'dataloader_in_order': True, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_static_graph': None, 'ddp_backend': None, 'ddp_timeout': 1800, 'fsdp': None, 'fsdp_config': None, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'local_rank': -1}
18
- 2026-08-14 20:51:35,740 INFO MainThread:409188 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 2001280 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x153f2878a810>>
19
- 2026-08-14 20:51:35,740 INFO MainThread:409188 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 2001280 None
 
1
+ 2026-08-14 21:01:55,966 INFO MainThread:409188 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260814_210155-rxpj34pj/logs/debug.log
2
+ 2026-08-14 21:01:55,966 INFO MainThread:409188 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260814_210155-rxpj34pj/logs/debug-internal.log
3
+ 2026-08-14 21:01:55,966 INFO MainThread:409188 [wandb_init.py:init():772] calling init triggers
4
+ 2026-08-14 21:01:55,966 INFO MainThread:409188 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
5
  config: {'_wandb': {}}
6
+ 2026-08-14 21:01:55,966 INFO MainThread:409188 [wandb_init.py:init():820] starting backend
7
+ 2026-08-14 21:01:55,966 INFO MainThread:409188 [wandb_init.py:init():835] sending inform_init request
8
+ 2026-08-14 21:01:56,229 INFO MainThread:409188 [wandb_init.py:init():840] backend started and connected
9
+ 2026-08-14 21:01:56,230 INFO MainThread:409188 [wandb_init.py:init():910] updated telemetry
10
+ 2026-08-14 21:01:56,237 INFO MainThread:409188 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
11
+ 2026-08-14 21:01:56,533 INFO MainThread:409188 [wandb_init.py:init():978] starting run threads in backend
12
+ 2026-08-14 21:01:56,607 INFO MainThread:409188 [wandb_run.py:_console_start():2621] atexit reg
13
+ 2026-08-14 21:01:56,608 INFO MainThread:409188 [wandb_run.py:_redirect():2471] redirect: wrap_raw
14
+ 2026-08-14 21:01:56,608 INFO MainThread:409188 [wandb_run.py:_redirect():2540] Wrapping output streams.
15
+ 2026-08-14 21:01:56,608 INFO MainThread:409188 [wandb_run.py:_redirect():2563] Redirects installed.
16
+ 2026-08-14 21:01:56,609 INFO MainThread:409188 [wandb_init.py:init():1016] run started, returning control to user process
17
+ 2026-08-14 21:01:56,609 INFO MainThread:409188 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.16.0.dev0', 'architectures': None, 'output_hidden_states': False, 'return_dict': True, 'dtype': None, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, 'vocab_size': 4096, 'hidden_size': 128, 'intermediate_size': 256, 'num_hidden_layers': 9, 'num_attention_heads': 4, 'num_key_value_heads': 4, 'hidden_act': 'silu', 'max_position_embeddings': 512, 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'pad_token_id': 0, 'bos_token_id': 1, 'eos_token_id': 2, 'pretraining_tp': 1, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 10000.0, 'rope_type': 'default'}, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'head_dim': 32, '_name_or_path': '', 'tokenizer_name': 'w-ahmad/tiny-stories-tokenizer', 'mlp_type': 'glu', 'activation': 'situglu_low', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-situglu_low-9L_run', 'per_device_train_batch_size': 512, 'num_train_epochs': 1, 'max_steps': 1000, 'learning_rate': 0.001, 'lr_scheduler_type': 'constant', 'lr_scheduler_kwargs': None, 'warmup_steps': 0, 'optim': 'adamw_torch', 'optim_args': None, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 1.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-situglu_low-9L-2.0M-20260814-210155', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 60000, 'eval_delay': 0, 'per_device_eval_batch_size': 512, 'prediction_loss_only': False, 'eval_on_start': False, 'eval_do_concat_batches': True, 'eval_use_gather_object': False, 'eval_accumulation_steps': None, 'include_for_metrics': [], 'batch_eval_metrics': False, 'save_only_model': False, 'save_strategy': 'steps', 'save_steps': 100, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/A-glu-situglu_low-9L', 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': None, 'dataloader_multiprocessing_context': None, 'dataloader_in_order': True, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_static_graph': None, 'ddp_backend': None, 'ddp_timeout': 1800, 'fsdp': None, 'fsdp_config': None, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'local_rank': -1}
18
+ 2026-08-14 21:01:56,611 INFO MainThread:409188 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 2001280 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x15413e1378d0>>
19
+ 2026-08-14 21:01:56,611 INFO MainThread:409188 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 2001280 None
zain/Activation/wandb/run-20260814_193907-kk1xbqht/logs/debug-core.log CHANGED
@@ -42,3 +42,7 @@
42
  {"time":"2026-08-14T20:54:42.40094641Z","level":"INFO","msg":"connection: closed successfully","id":"2(@)"}
43
  {"time":"2026-08-14T20:54:42.400864953Z","level":"INFO","msg":"processOutgoingData: finished","id":"2(@)"}
44
  {"time":"2026-08-14T20:54:42.400960827Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"2(@)"}
 
 
 
 
 
42
  {"time":"2026-08-14T20:54:42.40094641Z","level":"INFO","msg":"connection: closed successfully","id":"2(@)"}
43
  {"time":"2026-08-14T20:54:42.400864953Z","level":"INFO","msg":"processOutgoingData: finished","id":"2(@)"}
44
  {"time":"2026-08-14T20:54:42.400960827Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"2(@)"}
45
+ {"time":"2026-08-14T21:01:09.497626422Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"3(@)"}
46
+ {"time":"2026-08-14T21:01:09.714752804Z","level":"INFO","msg":"handleInformInit: received","streamId":"qauftiuh","id":"3(@)"}
47
+ {"time":"2026-08-14T21:01:09.994191533Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"qauftiuh","id":"3(@)"}
48
+ {"time":"2026-08-14T21:01:15.507216386Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"wd49dhcig506"}
zain/Activation/wandb/run-20260814_195151-ix6wcbwv/logs/debug-core.log CHANGED
@@ -42,3 +42,7 @@
42
  {"time":"2026-08-14T20:54:42.40094641Z","level":"INFO","msg":"connection: closed successfully","id":"2(@)"}
43
  {"time":"2026-08-14T20:54:42.400864953Z","level":"INFO","msg":"processOutgoingData: finished","id":"2(@)"}
44
  {"time":"2026-08-14T20:54:42.400960827Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"2(@)"}
 
 
 
 
 
42
  {"time":"2026-08-14T20:54:42.40094641Z","level":"INFO","msg":"connection: closed successfully","id":"2(@)"}
43
  {"time":"2026-08-14T20:54:42.400864953Z","level":"INFO","msg":"processOutgoingData: finished","id":"2(@)"}
44
  {"time":"2026-08-14T20:54:42.400960827Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"2(@)"}
45
+ {"time":"2026-08-14T21:01:09.497626422Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"3(@)"}
46
+ {"time":"2026-08-14T21:01:09.714752804Z","level":"INFO","msg":"handleInformInit: received","streamId":"qauftiuh","id":"3(@)"}
47
+ {"time":"2026-08-14T21:01:09.994191533Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"qauftiuh","id":"3(@)"}
48
+ {"time":"2026-08-14T21:01:15.507216386Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"wd49dhcig506"}
zain/Activation/wandb/run-20260814_200425-npumf6lz/logs/debug-core.log CHANGED
@@ -33,3 +33,10 @@
33
  {"time":"2026-08-14T20:51:35.100639214Z","level":"INFO","msg":"handleInformInit: received","streamId":"0vnbmyac","id":"1(@)"}
34
  {"time":"2026-08-14T20:51:35.363188061Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"0vnbmyac","id":"1(@)"}
35
  {"time":"2026-08-14T20:51:40.739065686Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"8byxg89obfh9"}
 
 
 
 
 
 
 
 
33
  {"time":"2026-08-14T20:51:35.100639214Z","level":"INFO","msg":"handleInformInit: received","streamId":"0vnbmyac","id":"1(@)"}
34
  {"time":"2026-08-14T20:51:35.363188061Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"0vnbmyac","id":"1(@)"}
35
  {"time":"2026-08-14T20:51:40.739065686Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"8byxg89obfh9"}
36
+ {"time":"2026-08-14T21:01:54.898587298Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"8byxg89obfh9"}
37
+ {"time":"2026-08-14T21:01:55.393521917Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"8byxg89obfh9"}
38
+ {"time":"2026-08-14T21:01:55.395053333Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"0vnbmyac","id":"1(@)"}
39
+ {"time":"2026-08-14T21:01:55.395670668Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"0vnbmyac","id":"1(@)"}
40
+ {"time":"2026-08-14T21:01:55.967276961Z","level":"INFO","msg":"handleInformInit: received","streamId":"rxpj34pj","id":"1(@)"}
41
+ {"time":"2026-08-14T21:01:56.228683674Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"rxpj34pj","id":"1(@)"}
42
+ {"time":"2026-08-14T21:02:01.684005979Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"atuum5cul6gx"}
zain/Activation/wandb/run-20260814_200503-bdhnr27j/logs/debug-core.log CHANGED
@@ -42,3 +42,7 @@
42
  {"time":"2026-08-14T20:54:42.40094641Z","level":"INFO","msg":"connection: closed successfully","id":"2(@)"}
43
  {"time":"2026-08-14T20:54:42.400864953Z","level":"INFO","msg":"processOutgoingData: finished","id":"2(@)"}
44
  {"time":"2026-08-14T20:54:42.400960827Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"2(@)"}
 
 
 
 
 
42
  {"time":"2026-08-14T20:54:42.40094641Z","level":"INFO","msg":"connection: closed successfully","id":"2(@)"}
43
  {"time":"2026-08-14T20:54:42.400864953Z","level":"INFO","msg":"processOutgoingData: finished","id":"2(@)"}
44
  {"time":"2026-08-14T20:54:42.400960827Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"2(@)"}
45
+ {"time":"2026-08-14T21:01:09.497626422Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"3(@)"}
46
+ {"time":"2026-08-14T21:01:09.714752804Z","level":"INFO","msg":"handleInformInit: received","streamId":"qauftiuh","id":"3(@)"}
47
+ {"time":"2026-08-14T21:01:09.994191533Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"qauftiuh","id":"3(@)"}
48
+ {"time":"2026-08-14T21:01:15.507216386Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"wd49dhcig506"}
zain/Activation/wandb/run-20260814_201615-w8mr4w6k/logs/debug-core.log CHANGED
@@ -33,3 +33,10 @@
33
  {"time":"2026-08-14T20:51:35.100639214Z","level":"INFO","msg":"handleInformInit: received","streamId":"0vnbmyac","id":"1(@)"}
34
  {"time":"2026-08-14T20:51:35.363188061Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"0vnbmyac","id":"1(@)"}
35
  {"time":"2026-08-14T20:51:40.739065686Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"8byxg89obfh9"}
 
 
 
 
 
 
 
 
33
  {"time":"2026-08-14T20:51:35.100639214Z","level":"INFO","msg":"handleInformInit: received","streamId":"0vnbmyac","id":"1(@)"}
34
  {"time":"2026-08-14T20:51:35.363188061Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"0vnbmyac","id":"1(@)"}
35
  {"time":"2026-08-14T20:51:40.739065686Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"8byxg89obfh9"}
36
+ {"time":"2026-08-14T21:01:54.898587298Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"8byxg89obfh9"}
37
+ {"time":"2026-08-14T21:01:55.393521917Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"8byxg89obfh9"}
38
+ {"time":"2026-08-14T21:01:55.395053333Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"0vnbmyac","id":"1(@)"}
39
+ {"time":"2026-08-14T21:01:55.395670668Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"0vnbmyac","id":"1(@)"}
40
+ {"time":"2026-08-14T21:01:55.967276961Z","level":"INFO","msg":"handleInformInit: received","streamId":"rxpj34pj","id":"1(@)"}
41
+ {"time":"2026-08-14T21:01:56.228683674Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"rxpj34pj","id":"1(@)"}
42
+ {"time":"2026-08-14T21:02:01.684005979Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"atuum5cul6gx"}
zain/Activation/wandb/run-20260814_202128-twgo1e89/logs/debug-core.log CHANGED
@@ -42,3 +42,7 @@
42
  {"time":"2026-08-14T20:54:42.40094641Z","level":"INFO","msg":"connection: closed successfully","id":"2(@)"}
43
  {"time":"2026-08-14T20:54:42.400864953Z","level":"INFO","msg":"processOutgoingData: finished","id":"2(@)"}
44
  {"time":"2026-08-14T20:54:42.400960827Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"2(@)"}
 
 
 
 
 
42
  {"time":"2026-08-14T20:54:42.40094641Z","level":"INFO","msg":"connection: closed successfully","id":"2(@)"}
43
  {"time":"2026-08-14T20:54:42.400864953Z","level":"INFO","msg":"processOutgoingData: finished","id":"2(@)"}
44
  {"time":"2026-08-14T20:54:42.400960827Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"2(@)"}
45
+ {"time":"2026-08-14T21:01:09.497626422Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"3(@)"}
46
+ {"time":"2026-08-14T21:01:09.714752804Z","level":"INFO","msg":"handleInformInit: received","streamId":"qauftiuh","id":"3(@)"}
47
+ {"time":"2026-08-14T21:01:09.994191533Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"qauftiuh","id":"3(@)"}
48
+ {"time":"2026-08-14T21:01:15.507216386Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"wd49dhcig506"}