w-ahmad commited on
Commit
f08df4b
·
verified ·
1 Parent(s): 30ba027

Auto upload zain 2026-08-14T21:30:04.912464 (part 3)

Browse files
zain/Activation/out/glu-waleedglu_low-9L_run/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "waleedglu_low",
3
+ "architectures": [
4
+ "TinyLlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 2,
11
+ "head_dim": 32,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 128,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 256,
16
+ "max_position_embeddings": 512,
17
+ "mlp_bias": false,
18
+ "mlp_type": "glu",
19
+ "model_type": "tiny_llama",
20
+ "num_attention_heads": 4,
21
+ "num_hidden_layers": 9,
22
+ "num_key_value_heads": 4,
23
+ "pad_token_id": 0,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-06,
26
+ "rope_parameters": {
27
+ "rope_theta": 10000.0,
28
+ "rope_type": "default"
29
+ },
30
+ "tie_word_embeddings": true,
31
+ "tokenizer_name": "w-ahmad/tiny-stories-tokenizer",
32
+ "transformers_version": "5.16.0.dev0",
33
+ "use_cache": false,
34
+ "vocab_size": 4096,
35
+ "waleed_beta": 10.0
36
+ }
zain/Activation/out/glu-waleedglu_low-9L_run/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b85b07be31b59b8c317a4a1a0fa3b71d9dc59dadcb3b0997c5789896bae7417
3
+ size 4011496
zain/Activation/out/glu-waleedglu_low-9L_run/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
zain/Activation/out/glu-waleedglu_low-9L_run/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1024,
10
+ "pad_token": "<|endoftext|>",
11
+ "tokenizer_class": "GPT2Tokenizer",
12
+ "unk_token": "<|endoftext|>"
13
+ }
zain/Activation/out/glu-waleedglu_low-9L_run/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f407d56ebb06d0a5638185b1d3995ddaf419213345d6af2b2318046d202d294a
3
+ size 4920
zain/Activation/out/glu-waleedglu_low-9L_run/training_log.jsonl CHANGED
@@ -45,3 +45,9 @@
45
  {"step": 900, "epoch": 0.48517520215633425, "timestamp": 1786742668.6246903, "loss": 2.274534797668457, "grad_norm": 0.65625, "learning_rate": 0.001, "train/total_time_seconds": 278.43139854073524, "train/time_per_step_avg": 0.3286478287726641, "train/epoch_time_elapsed": 619.9497459866107, "train/estimated_remaining_minutes": 0.5156137010013615}
46
  {"step": 920, "epoch": 0.49595687331536387, "timestamp": 1786742682.780034, "loss": 2.267928886413574, "grad_norm": 0.90234375, "learning_rate": 0.001, "train/total_time_seconds": 284.71959809586406, "train/time_per_step_avg": 0.325905754417181, "train/epoch_time_elapsed": 634.1050899587572, "train/estimated_remaining_minutes": 0.4126370986896581}
47
  {"step": 940, "epoch": 0.5067385444743935, "timestamp": 1786742697.2689917, "loss": 2.264225387573242, "grad_norm": 0.65625, "learning_rate": 0.001, "train/total_time_seconds": 291.5479309335351, "train/time_per_step_avg": 0.327793457955122, "train/epoch_time_elapsed": 648.5940477028489, "train/estimated_remaining_minutes": 0.310157373333548}
 
 
 
 
 
 
 
45
  {"step": 900, "epoch": 0.48517520215633425, "timestamp": 1786742668.6246903, "loss": 2.274534797668457, "grad_norm": 0.65625, "learning_rate": 0.001, "train/total_time_seconds": 278.43139854073524, "train/time_per_step_avg": 0.3286478287726641, "train/epoch_time_elapsed": 619.9497459866107, "train/estimated_remaining_minutes": 0.5156137010013615}
46
  {"step": 920, "epoch": 0.49595687331536387, "timestamp": 1786742682.780034, "loss": 2.267928886413574, "grad_norm": 0.90234375, "learning_rate": 0.001, "train/total_time_seconds": 284.71959809586406, "train/time_per_step_avg": 0.325905754417181, "train/epoch_time_elapsed": 634.1050899587572, "train/estimated_remaining_minutes": 0.4126370986896581}
47
  {"step": 940, "epoch": 0.5067385444743935, "timestamp": 1786742697.2689917, "loss": 2.264225387573242, "grad_norm": 0.65625, "learning_rate": 0.001, "train/total_time_seconds": 291.5479309335351, "train/time_per_step_avg": 0.327793457955122, "train/epoch_time_elapsed": 648.5940477028489, "train/estimated_remaining_minutes": 0.310157373333548}
48
+ {"step": 960, "epoch": 0.5175202156334232, "timestamp": 1786742711.4762301, "loss": 2.2582265853881838, "grad_norm": 0.640625, "learning_rate": 0.001, "train/total_time_seconds": 298.0419538356364, "train/time_per_step_avg": 0.32635555606335404, "train/epoch_time_elapsed": 662.8012860007584, "train/estimated_remaining_minutes": 0.20697357905252525}
49
+ {"step": 980, "epoch": 0.5283018867924528, "timestamp": 1786742725.5599833, "loss": 2.251361846923828, "grad_norm": 0.6484375, "learning_rate": 0.001, "train/total_time_seconds": 304.54746324568987, "train/time_per_step_avg": 0.32261256091296675, "train/epoch_time_elapsed": 676.8850391805172, "train/estimated_remaining_minutes": 0.10358757253254756}
50
+ {"step": 1000, "epoch": 0.5390835579514824, "timestamp": 1786742739.7487693, "loss": 2.245043182373047, "grad_norm": 0.5703125, "learning_rate": 0.001, "train/total_time_seconds": 311.0822930634022, "train/time_per_step_avg": 0.3265089452266693, "train/epoch_time_elapsed": 691.0738254673779, "train/estimated_remaining_minutes": 0.0}
51
+ {"step": 1000, "epoch": 0.5390835579514824, "timestamp": 1786742749.0478988, "eval_loss": 2.23911452293396, "eval_runtime": 9.2976, "eval_samples_per_second": 1024.678, "eval_steps_per_second": 2.044, "train/total_time_seconds": 311.0822930634022, "train/time_per_step_avg": 0.3265089452266693, "train/epoch_time_elapsed": 700.3729538843036, "train/estimated_remaining_minutes": 0.0}
52
+ {"step": 1000, "epoch": 0.5390835579514824, "timestamp": 1786742749.0965137, "train_runtime": 701.2502, "train_samples_per_second": 730.125, "train_steps_per_second": 1.426, "total_flos": 2323107545088000.0, "train_loss": 2.969754108428955, "train/total_time_seconds": 311.0822930634022, "train/time_per_step_avg": 0.3265089452266693, "train/epoch_time_elapsed": 700.4215688928962, "train/estimated_remaining_minutes": 0.0}
53
+ {"step": 1000, "epoch": 0.5390835579514824, "timestamp": 1786742758.6421924, "eval_loss": 2.23911452293396, "eval_runtime": 9.5433, "eval_samples_per_second": 998.289, "eval_steps_per_second": 1.991, "train/total_time_seconds": 311.0822930634022, "train/time_per_step_avg": 0.3265089452266693, "train/epoch_time_elapsed": 709.9672477468848, "train/estimated_remaining_minutes": 0.0}
zain/Activation/out/mlp-waleed10-21L_run/training_log.jsonl ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ {"step": 20, "epoch": 0.01078167115902965, "timestamp": 1786742916.252608, "loss": 7.273417663574219, "grad_norm": 1.0546875, "learning_rate": 0.001, "train/total_time_seconds": 6.614837985485792, "train/time_per_step_avg": 0.3307418992742896, "train/epoch_time_elapsed": 14.850544281303883, "train/estimated_remaining_minutes": 5.40211768814673}
2
+ {"step": 40, "epoch": 0.0215633423180593, "timestamp": 1786742935.6271088, "loss": 5.986497497558593, "grad_norm": 0.82421875, "learning_rate": 0.001, "train/total_time_seconds": 18.307914339005947, "train/time_per_step_avg": 0.45769785847514866, "train/epoch_time_elapsed": 34.22504559531808, "train/estimated_remaining_minutes": 7.3231657356023785}
zain/Activation/out/sweep_summary.json CHANGED
@@ -1,37 +1,51 @@
1
  [
2
  {
3
- "variant": "glu-relu-100L",
4
- "eval_loss": 2.0720698833465576,
5
- "out": "out/glu-relu-100L_run",
6
- "run_name": "LM-glu-relu-100L-16.9M-20260814-193906",
7
  "status": "success"
8
  },
9
  {
10
- "variant": "glu-gelu-100L",
11
- "eval_loss": 2.1001250743865967,
12
- "out": "out/glu-gelu-100L_run",
13
- "run_name": "LM-glu-gelu-100L-16.9M-20260814-195150",
14
  "status": "success"
15
  },
16
  {
17
- "variant": "glu-sigmoid-100L",
18
- "eval_loss": 2.279484510421753,
19
- "out": "out/glu-sigmoid-100L_run",
20
- "run_name": "LM-glu-sigmoid-100L-16.9M-20260814-200502",
21
  "status": "success"
22
  },
23
  {
24
- "variant": "glu-waleed10-100L",
25
- "eval_loss": 2.1119372844696045,
26
- "out": "out/glu-waleed10-100L_run",
27
- "run_name": "LM-glu-waleed10-100L-16.9M-20260814-202127",
28
  "status": "success"
29
  },
30
  {
31
- "variant": "glu-silu-waleed10-100L",
32
- "eval_loss": 2.1338183879852295,
33
- "out": "out/glu-silu-waleed10-100L_run",
34
- "run_name": "LM-glu-silu-waleed10-100L-16.9M-20260814-203802",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  "status": "success"
36
  }
37
  ]
 
1
  [
2
  {
3
+ "variant": "glu-waleed10-9L",
4
+ "eval_loss": 2.248227596282959,
5
+ "out": "out/glu-waleed10-9L_run",
6
+ "run_name": "LM-glu-waleed10-9L-2.0M-20260814-200424",
7
  "status": "success"
8
  },
9
  {
10
+ "variant": "glu-silu-waleed10-9L",
11
+ "eval_loss": 2.241689443588257,
12
+ "out": "out/glu-silu-waleed10-9L_run",
13
+ "run_name": "LM-glu-silu-waleed10-9L-2.0M-20260814-201615",
14
  "status": "success"
15
  },
16
  {
17
+ "variant": "mlp-waleed10-9L",
18
+ "eval_loss": 2.6366770267486572,
19
+ "out": "out/mlp-waleed10-9L_run",
20
+ "run_name": "LM-mlp-waleed10-9L-2.0M-20260814-202806",
21
  "status": "success"
22
  },
23
  {
24
+ "variant": "mlp-silu-waleed10-9L",
25
+ "eval_loss": 2.4668548107147217,
26
+ "out": "out/mlp-silu-waleed10-9L_run",
27
+ "run_name": "LM-mlp-silu-waleed10-9L-2.0M-20260814-203944",
28
  "status": "success"
29
  },
30
  {
31
+ "variant": "glu-waleed-9L",
32
+ "eval_loss": 2.2454068660736084,
33
+ "out": "out/glu-waleed-9L_run",
34
+ "run_name": "LM-glu-waleed-9L-2.0M-20260814-205134",
35
+ "status": "success"
36
+ },
37
+ {
38
+ "variant": "glu-situglu_low-9L",
39
+ "eval_loss": 2.262706995010376,
40
+ "out": "out/glu-situglu_low-9L_run",
41
+ "run_name": "LM-glu-situglu_low-9L-2.0M-20260814-210155",
42
+ "status": "success"
43
+ },
44
+ {
45
+ "variant": "glu-waleedglu_low-9L",
46
+ "eval_loss": 2.23911452293396,
47
+ "out": "out/glu-waleedglu_low-9L_run",
48
+ "run_name": "LM-glu-waleedglu_low-9L-2.0M-20260814-211407",
49
  "status": "success"
50
  }
51
  ]
zain/Activation/wandb/debug-internal.log CHANGED
@@ -1,39 +1,47 @@
1
- {"time":"2026-08-14T21:22:08.718376102Z","level":"INFO","msg":"wandb-core"}
2
- {"time":"2026-08-14T21:22:08.718525858Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
3
- {"time":"2026-08-14T21:22:08.976613612Z","level":"INFO","msg":"stream: created new stream","id":"n6fjpg9o"}
4
- {"time":"2026-08-14T21:22:08.976696773Z","level":"INFO","msg":"handler: started"}
5
- {"time":"2026-08-14T21:22:08.976788691Z","level":"INFO","msg":"stream: started"}
6
- {"time":"2026-08-14T21:22:08.976799484Z","level":"INFO","msg":"writer: started","stream_id":"n6fjpg9o"}
7
- {"time":"2026-08-14T21:22:08.976816759Z","level":"INFO","msg":"sender: started"}
8
- {"time":"2026-08-14T21:22:09.440727374Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":2}
9
- {"time":"2026-08-14T21:22:09.564001995Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
10
- {"time":"2026-08-14T21:22:24.441386534Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":1,"events_offset":0,"events_lines":1,"console_offset":1,"console_lines":2,"uploaded_len":2}
11
- {"time":"2026-08-14T21:22:24.565168312Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":2114}
12
- {"time":"2026-08-14T21:22:24.565228778Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":1}
13
- {"time":"2026-08-14T21:22:24.566661239Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":2550}
14
- {"time":"2026-08-14T21:22:24.580559569Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":4582}
15
- {"time":"2026-08-14T21:22:24.582142267Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":7648}
16
- {"time":"2026-08-14T21:22:24.582225626Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":2}
17
- {"time":"2026-08-14T21:22:24.58362392Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":8253}
18
- {"time":"2026-08-14T21:22:24.591015121Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":3485}
19
- {"time":"2026-08-14T21:22:24.63313691Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
20
- {"time":"2026-08-14T21:22:39.460806372Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":1,"history_lines":2,"events_offset":1,"events_lines":2,"console_offset":1,"console_lines":1}
21
- {"time":"2026-08-14T21:22:40.248095374Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
22
- {"time":"2026-08-14T21:22:54.463226542Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3,"history_lines":2,"events_offset":3,"events_lines":2,"console_offset":1,"console_lines":1}
23
- {"time":"2026-08-14T21:22:55.366744214Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
24
- {"time":"2026-08-14T21:23:09.459842995Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":5,"history_lines":2,"events_offset":5,"events_lines":2,"console_offset":3,"console_lines":11}
25
- {"time":"2026-08-14T21:23:10.4784956Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
26
- {"time":"2026-08-14T21:23:24.461746485Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":7,"history_lines":3,"events_offset":7,"events_lines":2,"console_offset":11,"console_lines":1}
27
- {"time":"2026-08-14T21:23:25.376290181Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
28
- {"time":"2026-08-14T21:23:39.462574873Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":10,"history_lines":2,"events_offset":9,"events_lines":2,"console_offset":14,"console_lines":10}
29
- {"time":"2026-08-14T21:23:40.503407948Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
30
- {"time":"2026-08-14T21:23:54.464486353Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":12,"history_lines":2,"events_offset":11,"events_lines":2,"console_offset":21,"console_lines":1}
31
- {"time":"2026-08-14T21:23:55.425354112Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
32
- {"time":"2026-08-14T21:24:09.454582762Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":14,"history_lines":2,"events_offset":13,"events_lines":2,"console_offset":21,"console_lines":1}
33
- {"time":"2026-08-14T21:24:10.482988855Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
34
- {"time":"2026-08-14T21:24:24.462276209Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":16,"history_lines":2,"events_offset":15,"events_lines":2,"console_offset":24,"console_lines":11}
35
- {"time":"2026-08-14T21:24:25.32436768Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
36
- {"time":"2026-08-14T21:24:39.460780565Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":18,"history_lines":2,"events_offset":17,"events_lines":2,"console_offset":31,"console_lines":1}
37
- {"time":"2026-08-14T21:24:40.427030871Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
38
- {"time":"2026-08-14T21:24:54.460542104Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":20,"history_lines":2,"events_offset":19,"events_lines":2,"console_offset":35,"console_lines":9}
39
- {"time":"2026-08-14T21:24:55.385800453Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
 
 
 
 
 
 
 
 
 
1
+ {"time":"2026-08-14T21:28:35.344927311Z","level":"INFO","msg":"wandb-core"}
2
+ {"time":"2026-08-14T21:28:35.34506265Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
3
+ {"time":"2026-08-14T21:28:35.602855263Z","level":"INFO","msg":"stream: created new stream","id":"gqskne0x"}
4
+ {"time":"2026-08-14T21:28:35.602933409Z","level":"INFO","msg":"handler: started"}
5
+ {"time":"2026-08-14T21:28:35.603016258Z","level":"INFO","msg":"stream: started"}
6
+ {"time":"2026-08-14T21:28:35.603043817Z","level":"INFO","msg":"writer: started","stream_id":"gqskne0x"}
7
+ {"time":"2026-08-14T21:28:35.60305765Z","level":"INFO","msg":"sender: started"}
8
+ {"time":"2026-08-14T21:28:36.090276496Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
9
+ {"time":"2026-08-14T21:28:36.211652827Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
10
+ {"time":"2026-08-14T21:28:51.09126529Z","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":3,"uploaded_len":2}
11
+ {"time":"2026-08-14T21:28:51.261717283Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
12
+ {"time":"2026-08-14T21:28:53.048390257Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":3104}
13
+ {"time":"2026-08-14T21:28:53.048417504Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":1}
14
+ {"time":"2026-08-14T21:28:53.050441969Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":3665}
15
+ {"time":"2026-08-14T21:28:53.050479366Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":1}
16
+ {"time":"2026-08-14T21:28:53.051308024Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":3981}
17
+ {"time":"2026-08-14T21:28:53.052248742Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":269}
18
+ {"time":"2026-08-14T21:28:53.052348345Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":4293}
19
+ {"time":"2026-08-14T21:28:53.053710973Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":419}
20
+ {"time":"2026-08-14T21:28:53.054973484Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":5282}
21
+ {"time":"2026-08-14T21:28:53.05654974Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":576}
22
+ {"time":"2026-08-14T21:28:53.057424589Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":6166}
23
+ {"time":"2026-08-14T21:28:53.058161238Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":225}
24
+ {"time":"2026-08-14T21:28:53.059182778Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":6765}
25
+ {"time":"2026-08-14T21:28:53.059372384Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":41}
26
+ {"time":"2026-08-14T21:28:53.059719473Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":6917}
27
+ {"time":"2026-08-14T21:28:53.059850702Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":21}
28
+ {"time":"2026-08-14T21:28:53.061202591Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":7342}
29
+ {"time":"2026-08-14T21:28:53.061276823Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":12}
30
+ {"time":"2026-08-14T21:28:53.068366857Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":9009}
31
+ {"time":"2026-08-14T21:28:53.068403516Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":1}
32
+ {"time":"2026-08-14T21:28:53.070211602Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":9602}
33
+ {"time":"2026-08-14T21:28:53.071216814Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":294}
34
+ {"time":"2026-08-14T21:28:53.071521294Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":10000}
35
+ {"time":"2026-08-14T21:28:53.072106936Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":190}
36
+ {"time":"2026-08-14T21:28:53.075408887Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":11406}
37
+ {"time":"2026-08-14T21:28:53.076614643Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":333}
38
+ {"time":"2026-08-14T21:29:06.110603465Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":1,"history_lines":2,"events_offset":1,"events_lines":2,"console_offset":1,"console_lines":1}
39
+ {"time":"2026-08-14T21:29:06.83621196Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
40
+ {"time":"2026-08-14T21:29:21.108433332Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3,"history_lines":3,"events_offset":3,"events_lines":2,"console_offset":1,"console_lines":1}
41
+ {"time":"2026-08-14T21:29:21.999015678Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
42
+ {"time":"2026-08-14T21:29:36.110784946Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":6,"history_lines":2,"events_offset":5,"events_lines":2,"console_offset":3,"console_lines":12}
43
+ {"time":"2026-08-14T21:29:36.946170207Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
44
+ {"time":"2026-08-14T21:29:51.109458297Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":8,"history_lines":3,"events_offset":7,"events_lines":2,"console_offset":11,"console_lines":1}
45
+ {"time":"2026-08-14T21:29:52.226871571Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
46
+ {"time":"2026-08-14T21:30:06.110393089Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":11,"history_lines":2,"events_offset":9,"events_lines":2,"console_offset":15,"console_lines":10}
47
+ {"time":"2026-08-14T21:30:07.570174219Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
zain/Activation/wandb/debug.log CHANGED
@@ -1,20 +1,20 @@
1
- 2026-08-14 21:22:08,716 INFO MainThread:936813 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260814_212208-n6fjpg9o/logs/debug.log
2
- 2026-08-14 21:22:08,716 INFO MainThread:936813 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260814_212208-n6fjpg9o/logs/debug-internal.log
3
- 2026-08-14 21:22:08,717 INFO MainThread:936813 [wandb_init.py:init():772] calling init triggers
4
- 2026-08-14 21:22:08,717 INFO MainThread:936813 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
5
  config: {'_wandb': {}}
6
- 2026-08-14 21:22:08,717 INFO MainThread:936813 [wandb_init.py:init():820] starting backend
7
- 2026-08-14 21:22:08,717 INFO MainThread:936813 [wandb_init.py:init():826] Connected to an existing wandb-core service via WANDB_SERVICE
8
- 2026-08-14 21:22:08,717 INFO MainThread:936813 [wandb_init.py:init():835] sending inform_init request
9
- 2026-08-14 21:22:08,977 INFO MainThread:936813 [wandb_init.py:init():840] backend started and connected
10
- 2026-08-14 21:22:08,978 INFO MainThread:936813 [wandb_init.py:init():910] updated telemetry
11
- 2026-08-14 21:22:08,985 INFO MainThread:936813 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
12
- 2026-08-14 21:22:09,347 INFO MainThread:936813 [wandb_init.py:init():978] starting run threads in backend
13
- 2026-08-14 21:22:09,426 INFO MainThread:936813 [wandb_run.py:_console_start():2621] atexit reg
14
- 2026-08-14 21:22:09,427 INFO MainThread:936813 [wandb_run.py:_redirect():2471] redirect: wrap_raw
15
- 2026-08-14 21:22:09,427 INFO MainThread:936813 [wandb_run.py:_redirect():2540] Wrapping output streams.
16
- 2026-08-14 21:22:09,427 INFO MainThread:936813 [wandb_run.py:_redirect():2563] Redirects installed.
17
- 2026-08-14 21:22:09,428 INFO MainThread:936813 [wandb_init.py:init():1016] run started, returning control to user process
18
- 2026-08-14 21:22:09,429 INFO MainThread:936813 [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': 4, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-waleed10-100L_trash_run', 'per_device_train_batch_size': 64, 'num_train_epochs': 1, 'max_steps': 3500, 'learning_rate': 9e-05, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 50, '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-20260814-212207', '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': 50, '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}
19
- 2026-08-14 21:22:09,434 INFO MainThread:936813 [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 0x14ee39bf4050>>
20
- 2026-08-14 21:22:09,434 INFO MainThread:936813 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 16934016 None
 
1
+ 2026-08-14 21:28:35,343 INFO MainThread:936813 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260814_212835-gqskne0x/logs/debug.log
2
+ 2026-08-14 21:28:35,343 INFO MainThread:936813 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260814_212835-gqskne0x/logs/debug-internal.log
3
+ 2026-08-14 21:28:35,343 INFO MainThread:936813 [wandb_init.py:init():772] calling init triggers
4
+ 2026-08-14 21:28:35,343 INFO MainThread:936813 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
5
  config: {'_wandb': {}}
6
+ 2026-08-14 21:28:35,343 INFO MainThread:936813 [wandb_init.py:init():820] starting backend
7
+ 2026-08-14 21:28:35,343 INFO MainThread:936813 [wandb_init.py:init():826] Connected to an existing wandb-core service via WANDB_SERVICE
8
+ 2026-08-14 21:28:35,343 INFO MainThread:936813 [wandb_init.py:init():835] sending inform_init request
9
+ 2026-08-14 21:28:35,603 INFO MainThread:936813 [wandb_init.py:init():840] backend started and connected
10
+ 2026-08-14 21:28:35,605 INFO MainThread:936813 [wandb_init.py:init():910] updated telemetry
11
+ 2026-08-14 21:28:35,614 INFO MainThread:936813 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
12
+ 2026-08-14 21:28:35,996 INFO MainThread:936813 [wandb_init.py:init():978] starting run threads in backend
13
+ 2026-08-14 21:28:36,075 INFO MainThread:936813 [wandb_run.py:_console_start():2621] atexit reg
14
+ 2026-08-14 21:28:36,075 INFO MainThread:936813 [wandb_run.py:_redirect():2471] redirect: wrap_raw
15
+ 2026-08-14 21:28:36,076 INFO MainThread:936813 [wandb_run.py:_redirect():2540] Wrapping output streams.
16
+ 2026-08-14 21:28:36,076 INFO MainThread:936813 [wandb_run.py:_redirect():2563] Redirects installed.
17
+ 2026-08-14 21:28:36,077 INFO MainThread:936813 [wandb_init.py:init():1016] run started, returning control to user process
18
+ 2026-08-14 21:28:36,078 INFO MainThread:936813 [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': 'silu-waleed10', 'waleed_beta': 4, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-silu-waleed10-100L_trash_run', 'per_device_train_batch_size': 64, 'num_train_epochs': 1, 'max_steps': 3500, 'learning_rate': 9e-05, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 50, '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-silu-waleed10-100L-16.9M-20260814-212834', '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': 50, '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-silu-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}
19
+ 2026-08-14 21:28:36,083 INFO MainThread:936813 [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 0x14ee399dda90>>
20
+ 2026-08-14 21:28:36,083 INFO MainThread:936813 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 16934016 None
zain/Activation/wandb/run-20260814_193907-kk1xbqht/logs/debug-core.log CHANGED
@@ -68,3 +68,10 @@
68
  {"time":"2026-08-14T21:22:08.718181031Z","level":"INFO","msg":"handleInformInit: received","streamId":"n6fjpg9o","id":"3(@)"}
69
  {"time":"2026-08-14T21:22:08.976795469Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"n6fjpg9o","id":"3(@)"}
70
  {"time":"2026-08-14T21:22:14.472169125Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"qlc6t75fdq0u"}
 
 
 
 
 
 
 
 
68
  {"time":"2026-08-14T21:22:08.718181031Z","level":"INFO","msg":"handleInformInit: received","streamId":"n6fjpg9o","id":"3(@)"}
69
  {"time":"2026-08-14T21:22:08.976795469Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"n6fjpg9o","id":"3(@)"}
70
  {"time":"2026-08-14T21:22:14.472169125Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"qlc6t75fdq0u"}
71
+ {"time":"2026-08-14T21:28:18.727248774Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"qlc6t75fdq0u"}
72
+ {"time":"2026-08-14T21:28:20.378913364Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"qlc6t75fdq0u"}
73
+ {"time":"2026-08-14T21:28:20.400345521Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"n6fjpg9o","id":"3(@)"}
74
+ {"time":"2026-08-14T21:28:20.400969576Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"n6fjpg9o","id":"3(@)"}
75
+ {"time":"2026-08-14T21:28:35.344777056Z","level":"INFO","msg":"handleInformInit: received","streamId":"gqskne0x","id":"3(@)"}
76
+ {"time":"2026-08-14T21:28:35.603024157Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"gqskne0x","id":"3(@)"}
77
+ {"time":"2026-08-14T21:28:41.078893683Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"yxbo55z35lse"}