Hugging Face's logo

quinnlue
/
mixture-transfer-runs

Safetensors
Model card Files
xet
 Community
quinnlue commited on
Commit
d716fe2
·
verified ·
1 Parent(s): 4d15c4b

Upload folder using huggingface_hub

Browse files
Files changed (22) hide show
  1. .gitattributes +1 -0
  2. p1-smoke-sup-15m/config.yaml +112 -0
  3. p1-smoke-sup-15m/events.jsonl +0 -0
  4. p1-smoke-sup-15m/exports/step_00002000/.upload_verified.json +28 -0
  5. p1-smoke-sup-15m/exports/step_00004000/.upload_verified.json +28 -0
  6. p1-smoke-sup-15m/exports/step_00006000/.upload_verified.json +28 -0
  7. p1-smoke-sup-15m/exports/step_00008000/.upload_verified.json +28 -0
  8. p1-smoke-sup-15m/mixture_plan.npy +3 -0
  9. p1-smoke-sup-15m/run.json +94 -0
  10. p1-smoke-sup-15m/status.json +13 -0
  11. p1-smoke-sup-15m/wandb/debug-internal.log +39 -0
  12. p1-smoke-sup-15m/wandb/debug.log +24 -0
  13. p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/files/config.yaml +249 -0
  14. p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/files/output.log +0 -0
  15. p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/files/requirements.txt +115 -0
  16. p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/files/wandb-metadata.json +118 -0
  17. p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/files/wandb-summary.json +1 -0
  18. p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/logs/debug-core.log +160 -0
  19. p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/logs/debug-internal.log +39 -0
  20. p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/logs/debug.log +24 -0
  21. p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/run-phase1-p1-smoke-sup-15m.wandb +3 -0
  22. p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/run-phase1-p1-smoke-sup-15m.wandb.syncstate +1 -0
.gitattributes CHANGED
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  p1-smoke-eat-15m/wandb/run-20260816_182621-phase1-p1-smoke-eat-15m/run-phase1-p1-smoke-eat-15m.wandb filter=lfs diff=lfs merge=lfs -text
37
  p1-smoke-mae-15m/wandb/run-20260816_182622-phase1-p1-smoke-mae-15m/run-phase1-p1-smoke-mae-15m.wandb filter=lfs diff=lfs merge=lfs -text
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  p1-smoke-eat-15m/wandb/run-20260816_182621-phase1-p1-smoke-eat-15m/run-phase1-p1-smoke-eat-15m.wandb filter=lfs diff=lfs merge=lfs -text
37
  p1-smoke-mae-15m/wandb/run-20260816_182622-phase1-p1-smoke-mae-15m/run-phase1-p1-smoke-mae-15m.wandb filter=lfs diff=lfs merge=lfs -text
38
+ p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/run-phase1-p1-smoke-sup-15m.wandb filter=lfs diff=lfs merge=lfs -text
p1-smoke-sup-15m/config.yaml ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ embed_dim: 384
3
+ depth: 8
4
+ num_heads: 6
5
+ mlp_ratio: 4
6
+ target_frames: 1024
7
+ mel_bins: 64
8
+ patch_time: 16
9
+ patch_freq: 16
10
+ decoder_layers: 6
11
+ decoder_groups: 16
12
+ decoder_kernel: 3
13
+ objective:
14
+ kind: sup
15
+ mae_norm_pix: true
16
+ num_classes: 527
17
+ clone_batch: 1
18
+ mask_prob: 0.8
19
+ mask_length: 5
20
+ mask_prob_adjust: 0.07
21
+ average_top_k_layers: 0
22
+ utterance_weight: 1.0
23
+ normalize_utterance_target: false
24
+ ema_decay: 0.9998
25
+ ema_end_decay: 0.99999
26
+ ema_anneal_steps: null
27
+ data:
28
+ data_dir: /workspace/data/asmel_flat
29
+ train_split: train
30
+ val_split: balanced_train
31
+ revision: ''
32
+ batch_size: 48
33
+ num_workers: 12
34
+ prefetch_factor: 4
35
+ pin_memory: true
36
+ persistent_workers: true
37
+ drop_last: true
38
+ seed: 0
39
+ max_shards: 0
40
+ mixture:
41
+ cluster_index: /workspace/data/asmel_flat/train_cluster_index.npy
42
+ distributions: null
43
+ dist_id: null
44
+ weights:
45
+ - 0.161611328125
46
+ - 0.042833984375
47
+ - 0.066421875
48
+ - 0.0
49
+ - 0.0354609375
50
+ - 0.0
51
+ - 0.027091796875
52
+ - 0.000837890625
53
+ - 0.02515625
54
+ - 0.0256796875
55
+ - 0.0
56
+ - 0.0005234375
57
+ - 0.314330078125
58
+ - 0.01475
59
+ - 0.192939453125
60
+ - 0.000208984375
61
+ - 0.000208984375
62
+ - 0.0655859375
63
+ - 0.005177734375
64
+ - 0.021181640625
65
+ repetition_cap: 1000.0
66
+ distinct_fraction: null
67
+ optim:
68
+ lr: 0.001
69
+ betas:
70
+ - 0.9
71
+ - 0.95
72
+ eps: 1.0e-08
73
+ weight_decay: 0.05
74
+ clip_norm: 4.0
75
+ warmup_frac: 0.1
76
+ min_lr_scale: 0.002
77
+ loop:
78
+ budget_clips: 384000
79
+ schedule_clips: null
80
+ gradient_accumulation_steps: 1
81
+ precision: bfloat16
82
+ compile: true
83
+ compile_mode: default
84
+ log_every_n_steps: 20
85
+ heartbeat_every_n_steps: 50
86
+ max_steps: null
87
+ eval:
88
+ enabled: true
89
+ every_n_steps: 1000
90
+ num_clips: 2048
91
+ mask_seed: 12345
92
+ batch_size: 48
93
+ checkpoint:
94
+ save_every_n_steps: 2000
95
+ export_every_n_steps: 2000
96
+ keep_last_n_exports: 0
97
+ tracking:
98
+ campaign_id: phase1
99
+ trial_id: p1-smoke-sup-15m
100
+ wandb_project: mixture-transfer
101
+ wandb_entity: null
102
+ wandb_mode: online
103
+ wandb_run_id: null
104
+ hub_repo_id: null
105
+ hub_private: false
106
+ hub_upload: false
107
+ runtime:
108
+ seed: 0
109
+ data_loader_seed: null
110
+ objective_seed: null
111
+ deterministic: false
112
+ allow_tf32: true
p1-smoke-sup-15m/events.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
p1-smoke-sup-15m/exports/step_00002000/.upload_verified.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "prefix": "p1-smoke-sup-15m/exports/step_00002000",
3
+ "repo": "quinnlue/mixture-transfer-runs",
4
+ "verified_at": 1786939669.4007266,
5
+ "bytes": 57599288,
6
+ "n_files": 3,
7
+ "files": {
8
+ "p1-smoke-sup-15m/exports/step_00002000/config.yaml": {
9
+ "size": 2126,
10
+ "local_sha256": "a5fea8283a005b27959f873628ae7118e7ab3fb03f3541f0c907d1c1933952e4",
11
+ "remote_sha256": null,
12
+ "sha256_verified": false
13
+ },
14
+ "p1-smoke-sup-15m/exports/step_00002000/model.safetensors": {
15
+ "size": 57582184,
16
+ "local_sha256": "3437df9e66bac07a8116c9dc9fa83e927aec989921ec726dd593aa124693ce6a",
17
+ "remote_sha256": "3437df9e66bac07a8116c9dc9fa83e927aec989921ec726dd593aa124693ce6a",
18
+ "sha256_verified": true
19
+ },
20
+ "p1-smoke-sup-15m/exports/step_00002000/probe.json": {
21
+ "size": 14978,
22
+ "local_sha256": "662307f69207c51a43c5f86031ea77aadcec0b7c4798dff5f71cc0a2855f4106",
23
+ "remote_sha256": null,
24
+ "sha256_verified": false
25
+ }
26
+ },
27
+ "sha256_verified_files": 1
28
+ }
p1-smoke-sup-15m/exports/step_00004000/.upload_verified.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "prefix": "p1-smoke-sup-15m/exports/step_00004000",
3
+ "repo": "quinnlue/mixture-transfer-runs",
4
+ "verified_at": 1786939682.9741702,
5
+ "bytes": 57599282,
6
+ "n_files": 3,
7
+ "files": {
8
+ "p1-smoke-sup-15m/exports/step_00004000/config.yaml": {
9
+ "size": 2126,
10
+ "local_sha256": "a5fea8283a005b27959f873628ae7118e7ab3fb03f3541f0c907d1c1933952e4",
11
+ "remote_sha256": null,
12
+ "sha256_verified": false
13
+ },
14
+ "p1-smoke-sup-15m/exports/step_00004000/model.safetensors": {
15
+ "size": 57582184,
16
+ "local_sha256": "3baed1a70cc81ca2431c5cae51677a9c6fb114bee11c60e428b5b148b07251b1",
17
+ "remote_sha256": "3baed1a70cc81ca2431c5cae51677a9c6fb114bee11c60e428b5b148b07251b1",
18
+ "sha256_verified": true
19
+ },
20
+ "p1-smoke-sup-15m/exports/step_00004000/probe.json": {
21
+ "size": 14972,
22
+ "local_sha256": "79d0dc3e690cba97be106dd5bca7b3949dad612b2eb3d6148d8369bd70a086d3",
23
+ "remote_sha256": null,
24
+ "sha256_verified": false
25
+ }
26
+ },
27
+ "sha256_verified_files": 1
28
+ }
p1-smoke-sup-15m/exports/step_00006000/.upload_verified.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "prefix": "p1-smoke-sup-15m/exports/step_00006000",
3
+ "repo": "quinnlue/mixture-transfer-runs",
4
+ "verified_at": 1786939694.03284,
5
+ "bytes": 57599265,
6
+ "n_files": 3,
7
+ "files": {
8
+ "p1-smoke-sup-15m/exports/step_00006000/config.yaml": {
9
+ "size": 2126,
10
+ "local_sha256": "a5fea8283a005b27959f873628ae7118e7ab3fb03f3541f0c907d1c1933952e4",
11
+ "remote_sha256": null,
12
+ "sha256_verified": false
13
+ },
14
+ "p1-smoke-sup-15m/exports/step_00006000/model.safetensors": {
15
+ "size": 57582184,
16
+ "local_sha256": "2592c8f9ae21893354f83e9622e5d2fa2c06ad52d11996c211419ab295b9be0a",
17
+ "remote_sha256": "2592c8f9ae21893354f83e9622e5d2fa2c06ad52d11996c211419ab295b9be0a",
18
+ "sha256_verified": true
19
+ },
20
+ "p1-smoke-sup-15m/exports/step_00006000/probe.json": {
21
+ "size": 14955,
22
+ "local_sha256": "326a67b8c0746f51bc1fa8c394912b9bedd17440651943ab4af8afaf58243410",
23
+ "remote_sha256": null,
24
+ "sha256_verified": false
25
+ }
26
+ },
27
+ "sha256_verified_files": 1
28
+ }
p1-smoke-sup-15m/exports/step_00008000/.upload_verified.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "prefix": "p1-smoke-sup-15m/exports/step_00008000",
3
+ "repo": "quinnlue/mixture-transfer-runs",
4
+ "verified_at": 1786939707.2098677,
5
+ "bytes": 57599220,
6
+ "n_files": 3,
7
+ "files": {
8
+ "p1-smoke-sup-15m/exports/step_00008000/config.yaml": {
9
+ "size": 2126,
10
+ "local_sha256": "a5fea8283a005b27959f873628ae7118e7ab3fb03f3541f0c907d1c1933952e4",
11
+ "remote_sha256": null,
12
+ "sha256_verified": false
13
+ },
14
+ "p1-smoke-sup-15m/exports/step_00008000/model.safetensors": {
15
+ "size": 57582184,
16
+ "local_sha256": "23e78c55b4d6cbc2e1edd2c79e62d03c0c0643eb1315145313d1c0bfe849a129",
17
+ "remote_sha256": "23e78c55b4d6cbc2e1edd2c79e62d03c0c0643eb1315145313d1c0bfe849a129",
18
+ "sha256_verified": true
19
+ },
20
+ "p1-smoke-sup-15m/exports/step_00008000/probe.json": {
21
+ "size": 14910,
22
+ "local_sha256": "a5fdbeee361696f7bab439037adaf798d73192fef4f1c7077ac8ec0c9b987e3e",
23
+ "remote_sha256": null,
24
+ "sha256_verified": false
25
+ }
26
+ },
27
+ "sha256_verified_files": 1
28
+ }
p1-smoke-sup-15m/mixture_plan.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0bf477b6c96a86401f1d652b80b0747bc2d12d78926c5e6f9012f6271dfc1b9
3
+ size 3072128
p1-smoke-sup-15m/run.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "campaign_id": "phase1",
3
+ "trial_id": "p1-smoke-sup-15m",
4
+ "fingerprint": "47a2c6af9f43d811",
5
+ "wandb_run_id": "phase1-p1-smoke-sup-15m",
6
+ "environment": {
7
+ "git_sha": "c3ed4f7086fd770b27c6d2c9980eb6b06ad4a3da",
8
+ "git_dirty": true,
9
+ "torch": "2.12.0+cu130",
10
+ "cuda": "13.0",
11
+ "cudnn": 92000,
12
+ "gpu_count": 1,
13
+ "gpu_name": "NVIDIA GeForce RTX 4090",
14
+ "gpu_memory_gib": 23.52,
15
+ "capability": "8.9",
16
+ "driver": "580.173.02"
17
+ },
18
+ "parameters": {
19
+ "encoder_params": 14294784,
20
+ "decoder_params": 0,
21
+ "trainable_params": 14497679,
22
+ "total_params": 14497679
23
+ },
24
+ "schedule": {
25
+ "budget_clips": 384000,
26
+ "schedule_clips": null,
27
+ "clips_per_step": 48,
28
+ "total_steps": 8000,
29
+ "schedule_steps": 8000,
30
+ "warmup_steps": 800,
31
+ "ema_anneal_steps": 8000,
32
+ "final_lr": 2.0000475012781556e-06,
33
+ "final_ema_decay": 0.9999899762500001
34
+ },
35
+ "geometry": {
36
+ "patch_grid": [
37
+ 64,
38
+ 4
39
+ ],
40
+ "num_patches": 256,
41
+ "visible_patches": 51,
42
+ "centers_per_mask": 0
43
+ },
44
+ "data": {
45
+ "split": "train",
46
+ "rows": 1912024,
47
+ "shards": 96,
48
+ "sampled_sha256": "58cddcb9592605014dfe6c40579aa65d2a3216cdb77feeaf0267c183e9f0d5a9",
49
+ "val_split": "balanced_train",
50
+ "val_clips": 2048
51
+ },
52
+ "mixture": {
53
+ "dist_id": null,
54
+ "has_weights": true,
55
+ "repetition_cap": 1000.0,
56
+ "distinct_fraction": null,
57
+ "max_repetition": 1.0886501794830168,
58
+ "distinct_clips": 336891,
59
+ "capped_clusters": 0,
60
+ "realized_weights": [
61
+ 0.16161197916666667,
62
+ 0.042833333333333334,
63
+ 0.066421875,
64
+ 0.0,
65
+ 0.0354609375,
66
+ 0.0,
67
+ 0.027091145833333333,
68
+ 0.0008385416666666667,
69
+ 0.02515625,
70
+ 0.0256796875,
71
+ 0.0,
72
+ 0.0005234375,
73
+ 0.31433072916666666,
74
+ 0.01475,
75
+ 0.19294010416666665,
76
+ 0.00020833333333333335,
77
+ 0.00020833333333333335,
78
+ 0.0655859375,
79
+ 0.005177083333333333,
80
+ 0.021182291666666665
81
+ ]
82
+ },
83
+ "started_at": 1786904783.7652953,
84
+ "finished_at": 1786904955.8473148,
85
+ "summary": {
86
+ "completed": true,
87
+ "final_step": 8000,
88
+ "clips_seen": 384000,
89
+ "peak_gib": 1.5364618301391602,
90
+ "val/loss": 0.03064619516953826,
91
+ "val/frame": 0.03064619516953826,
92
+ "val/utterance": 0.0
93
+ }
94
+ }
p1-smoke-sup-15m/status.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "state": "complete",
3
+ "updated_at": 1786904955.848866,
4
+ "step": 8000,
5
+ "total_steps": 8000,
6
+ "clips_seen": 384000,
7
+ "completed": true,
8
+ "final_step": 8000,
9
+ "peak_gib": 1.5364618301391602,
10
+ "val/loss": 0.03064619516953826,
11
+ "val/frame": 0.03064619516953826,
12
+ "val/utterance": 0.0
13
+ }
p1-smoke-sup-15m/wandb/debug-internal.log ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2026-08-16T18:26:22.440217762Z","level":"INFO","msg":"wandb-core"}
2
+ {"time":"2026-08-16T18:26:22.440553246Z","level":"INFO","msg":"stream: starting","core version":"0.28.2"}
3
+ {"time":"2026-08-16T18:26:22.682446615Z","level":"INFO","msg":"stream: created new stream","id":"phase1-p1-smoke-sup-15m"}
4
+ {"time":"2026-08-16T18:26:22.682565127Z","level":"INFO","msg":"handler: started"}
5
+ {"time":"2026-08-16T18:26:22.682654518Z","level":"INFO","msg":"stream: started"}
6
+ {"time":"2026-08-16T18:26:22.682733129Z","level":"INFO","msg":"writer: started","stream_id":"phase1-p1-smoke-sup-15m"}
7
+ {"time":"2026-08-16T18:26:22.68276007Z","level":"INFO","msg":"sender: started"}
8
+ {"time":"2026-08-16T18:26:24.121014701Z","level":"INFO","msg":"filestream: sending request","total_files":1}
9
+ {"time":"2026-08-16T18:26:24.438362818Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
10
+ {"time":"2026-08-16T18:26:39.121514598Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":0,"events_lines":2,"console_offset":0,"console_lines":19,"uploaded_len":2}
11
+ {"time":"2026-08-16T18:26:39.374611087Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
12
+ {"time":"2026-08-16T18:26:54.121200631Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":40,"events_offset":2,"events_lines":2,"console_offset":19,"console_lines":41}
13
+ {"time":"2026-08-16T18:26:54.44562981Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
14
+ {"time":"2026-08-16T18:27:09.12189949Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":40,"history_lines":42,"events_offset":4,"events_lines":2,"console_offset":60,"console_lines":43}
15
+ {"time":"2026-08-16T18:27:09.438536963Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
16
+ {"time":"2026-08-16T18:27:24.122183518Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":82,"history_lines":40,"events_offset":6,"events_lines":2,"console_offset":103,"console_lines":41}
17
+ {"time":"2026-08-16T18:27:24.429272452Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
18
+ {"time":"2026-08-16T18:27:39.122296503Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":122,"history_lines":42,"events_offset":8,"events_lines":2,"console_offset":144,"console_lines":43}
19
+ {"time":"2026-08-16T18:27:39.950761431Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
20
+ {"time":"2026-08-16T18:27:54.121773862Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":164,"history_lines":41,"events_offset":10,"events_lines":2,"console_offset":187,"console_lines":42}
21
+ {"time":"2026-08-16T18:27:54.440782009Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
22
+ {"time":"2026-08-16T18:28:09.121832992Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":205,"history_lines":42,"events_offset":12,"events_lines":2,"console_offset":229,"console_lines":42}
23
+ {"time":"2026-08-16T18:28:09.449802827Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
24
+ {"time":"2026-08-16T18:28:24.121472485Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":247,"history_lines":37,"events_offset":14,"events_lines":2,"console_offset":271,"console_lines":38}
25
+ {"time":"2026-08-16T18:28:24.465737555Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
26
+ {"time":"2026-08-16T18:28:39.12194747Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":284,"history_lines":37,"events_offset":16,"events_lines":2,"console_offset":309,"console_lines":38}
27
+ {"time":"2026-08-16T18:28:39.426587476Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
28
+ {"time":"2026-08-16T18:28:54.121798683Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":321,"history_lines":35,"events_offset":18,"events_lines":2,"console_offset":347,"console_lines":36}
29
+ {"time":"2026-08-16T18:28:54.428028508Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
30
+ {"time":"2026-08-16T18:29:09.122057906Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":356,"history_lines":31,"events_offset":20,"events_lines":2,"console_offset":383,"console_lines":31}
31
+ {"time":"2026-08-16T18:29:09.419780564Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
32
+ {"time":"2026-08-16T18:29:17.534114877Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
33
+ {"time":"2026-08-16T18:29:17.534443301Z","level":"INFO","msg":"filestream: sending request","total_files":3,"history_offset":387,"history_lines":13,"console_offset":414,"console_lines":13,"uploaded_len":3,"complete":true,"exit_code":0}
34
+ {"time":"2026-08-16T18:29:17.833673472Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
35
+ {"time":"2026-08-16T18:29:17.835738729Z","level":"INFO","msg":"handler: operation stats","stats":{}}
36
+ {"time":"2026-08-16T18:29:17.839881375Z","level":"INFO","msg":"stream: finishing up"}
37
+ {"time":"2026-08-16T18:29:17.839897485Z","level":"INFO","msg":"handler: closed"}
38
+ {"time":"2026-08-16T18:29:17.840004977Z","level":"INFO","msg":"sender: closed"}
39
+ {"time":"2026-08-16T18:29:17.840011917Z","level":"INFO","msg":"stream: all finished"}
p1-smoke-sup-15m/wandb/debug.log ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2026-08-16 18:26:22,437 INFO MainThread:16560 [wandb_setup.py:_flush():81] Current SDK version is 0.28.2
2
+ 2026-08-16 18:26:22,437 INFO MainThread:16560 [wandb_setup.py:_flush():81] Configure stats pid to 16560
3
+ 2026-08-16 18:26:22,437 INFO MainThread:16560 [wandb_setup.py:_flush():81] Loading settings from environment variables
4
+ 2026-08-16 18:26:22,437 INFO MainThread:16560 [wandb_init.py:setup_run_log_directory():739] Logging user logs to /workspace/runs/p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/logs/debug.log
5
+ 2026-08-16 18:26:22,437 INFO MainThread:16560 [wandb_init.py:setup_run_log_directory():740] Logging internal logs to /workspace/runs/p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/logs/debug-internal.log
6
+ 2026-08-16 18:26:22,437 INFO MainThread:16560 [wandb_init.py:init():783] calling init triggers
7
+ 2026-08-16 18:26:22,437 INFO MainThread:16560 [wandb_init.py:init():788] wandb.init called with sweep_config: {}
8
+ config: {'model': {'embed_dim': 384, 'depth': 8, 'num_heads': 6, 'mlp_ratio': 4, 'target_frames': 1024, 'mel_bins': 64, 'patch_time': 16, 'patch_freq': 16, 'decoder_layers': 6, 'decoder_groups': 16, 'decoder_kernel': 3}, 'objective': {'kind': 'sup', 'mae_norm_pix': True, 'num_classes': 527, 'clone_batch': 1, 'mask_prob': 0.8, 'mask_length': 5, 'mask_prob_adjust': 0.07, 'average_top_k_layers': 0, 'utterance_weight': 1.0, 'normalize_utterance_target': False, 'ema_decay': 0.9998, 'ema_end_decay': 0.99999, 'ema_anneal_steps': None}, 'data': {'data_dir': '/workspace/data/asmel_flat', 'train_split': 'train', 'val_split': 'balanced_train', 'revision': '', 'batch_size': 48, 'num_workers': 12, 'prefetch_factor': 4, 'pin_memory': True, 'persistent_workers': True, 'drop_last': True, 'seed': 0, 'max_shards': 0}, 'mixture': {'cluster_index': '/workspace/data/asmel_flat/train_cluster_index.npy', 'distributions': None, 'dist_id': None, 'weights': [0.161611328125, 0.042833984375, 0.066421875, 0.0, 0.0354609375, 0.0, 0.027091796875, 0.000837890625, 0.02515625, 0.0256796875, 0.0, 0.0005234375, 0.314330078125, 0.01475, 0.192939453125, 0.000208984375, 0.000208984375, 0.0655859375, 0.005177734375, 0.021181640625], 'repetition_cap': 1000.0, 'distinct_fraction': None}, 'optim': {'lr': 0.001, 'betas': [0.9, 0.95], 'eps': 1e-08, 'weight_decay': 0.05, 'clip_norm': 4.0, 'warmup_frac': 0.1, 'min_lr_scale': 0.002}, 'loop': {'budget_clips': 384000, 'schedule_clips': None, 'gradient_accumulation_steps': 1, 'precision': 'bfloat16', 'compile': True, 'compile_mode': 'default', 'log_every_n_steps': 20, 'heartbeat_every_n_steps': 50, 'max_steps': None}, 'eval': {'enabled': True, 'every_n_steps': 1000, 'num_clips': 2048, 'mask_seed': 12345, 'batch_size': 48}, 'checkpoint': {'save_every_n_steps': 2000, 'export_every_n_steps': 2000, 'keep_last_n_exports': 0}, 'tracking': {'campaign_id': 'phase1', 'trial_id': 'p1-smoke-sup-15m', 'wandb_project': 'mixture-transfer', 'wandb_entity': None, 'wandb_mode': 'online', 'wandb_run_id': None, 'hub_repo_id': None, 'hub_private': False, 'hub_upload': False}, 'runtime': {'seed': 0, 'data_loader_seed': None, 'objective_seed': None, 'deterministic': False, 'allow_tf32': True}, '_wandb': {}}
9
+ 2026-08-16 18:26:22,437 INFO MainThread:16560 [wandb_init.py:init():831] starting backend
10
+ 2026-08-16 18:26:22,437 INFO MainThread:16560 [wandb_init.py:init():846] sending inform_init request
11
+ 2026-08-16 18:26:22,683 INFO MainThread:16560 [wandb_init.py:init():851] backend started and connected
12
+ 2026-08-16 18:26:22,684 INFO MainThread:16560 [wandb_init.py:init():921] updated telemetry
13
+ 2026-08-16 18:26:22,697 INFO MainThread:16560 [wandb_init.py:init():944] communicating run to backend with 90.0 second timeout
14
+ 2026-08-16 18:26:23,593 INFO MainThread:16560 [wandb_init.py:init():981] starting run threads in backend
15
+ 2026-08-16 18:26:23,668 INFO MainThread:16560 [wandb_run.py:_console_start():2626] atexit reg
16
+ 2026-08-16 18:26:23,668 INFO MainThread:16560 [wandb_run.py:_redirect():2476] redirect: wrap_raw
17
+ 2026-08-16 18:26:23,668 INFO MainThread:16560 [wandb_run.py:_redirect():2545] Wrapping output streams.
18
+ 2026-08-16 18:26:23,668 INFO MainThread:16560 [wandb_run.py:_redirect():2568] Redirects installed.
19
+ 2026-08-16 18:26:23,669 INFO MainThread:16560 [wandb_init.py:init():1019] run started, returning control to user process
20
+ 2026-08-16 18:29:15,849 INFO MainThread:16560 [wandb_run.py:_finish():2397] finishing run luequinn-montana-state-university/mixture-transfer/phase1-p1-smoke-sup-15m
21
+ 2026-08-16 18:29:15,849 INFO MainThread:16560 [wandb_run.py:_atexit_cleanup():2593] got exitcode: 0
22
+ 2026-08-16 18:29:15,850 INFO MainThread:16560 [wandb_run.py:_restore():2575] restore
23
+ 2026-08-16 18:29:15,850 INFO MainThread:16560 [wandb_run.py:_restore():2581] restore done
24
+ 2026-08-16 18:29:17,839 INFO MainThread:16560 [wandb_run.py:_footer_sync_info():4025] logging synced files
p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/files/config.yaml ADDED
@@ -0,0 +1,249 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _wandb:
2
+ value:
3
+ cli_version: 0.28.2
4
+ e:
5
+ kl8tnmjaxnku9jouy33x0vp8rg7alj7f:
6
+ args:
7
+ - --config
8
+ - configs/base.yaml
9
+ - --config
10
+ - configs/scale_15m.yaml
11
+ - --config
12
+ - configs/budget_40k.yaml
13
+ - --config
14
+ - configs/obj_sup.yaml
15
+ - --set
16
+ - loop.budget_clips=384000
17
+ - --set
18
+ - checkpoint.export_every_n_steps=2000
19
+ - --set
20
+ - checkpoint.save_every_n_steps=2000
21
+ - --set
22
+ - optim.lr=1.0e-3
23
+ - --set
24
+ - eval.every_n_steps=1000
25
+ - --set
26
+ - mixture.cluster_index=/workspace/data/asmel_flat/train_cluster_index.npy
27
+ - --set
28
+ - mixture.weights=[0.161611328125, 0.042833984375, 0.066421875, 0.0, 0.0354609375, 0.0, 0.027091796875, 0.000837890625, 0.02515625, 0.0256796875, 0.0, 0.0005234375, 0.314330078125, 0.01475, 0.192939453125, 0.000208984375, 0.000208984375, 0.0655859375, 0.005177734375, 0.021181640625]
29
+ - --set
30
+ - tracking.campaign_id=phase1
31
+ - --set
32
+ - tracking.trial_id=p1-smoke-sup-15m
33
+ - --set
34
+ - tracking.wandb_project=mixture-transfer
35
+ - --output-dir
36
+ - /workspace/runs/p1-smoke-sup-15m
37
+ cpu_count: 112
38
+ cpu_count_logical: 224
39
+ cudaVersion: "13.0"
40
+ disk:
41
+ /:
42
+ total: "549755813888"
43
+ used: "150857805824"
44
+ email: luequinn@gmail.com
45
+ executable: /venv/main/bin/python
46
+ git:
47
+ commit: c3ed4f7086fd770b27c6d2c9980eb6b06ad4a3da
48
+ gpu: NVIDIA GeForce RTX 4090
49
+ gpu_count: 8
50
+ gpu_nvidia:
51
+ - architecture: Ada
52
+ cudaCores: 16384
53
+ memoryTotal: "25757220864"
54
+ name: NVIDIA GeForce RTX 4090
55
+ uuid: GPU-e953afa7-1257-d569-95ea-b1eaea8d26c6
56
+ - architecture: Ada
57
+ cudaCores: 16384
58
+ memoryTotal: "25757220864"
59
+ name: NVIDIA GeForce RTX 4090
60
+ uuid: GPU-008b9ed1-b1a3-2de2-12bb-eddf323625d3
61
+ - architecture: Ada
62
+ cudaCores: 16384
63
+ memoryTotal: "25757220864"
64
+ name: NVIDIA GeForce RTX 4090
65
+ uuid: GPU-0c1a8517-a56e-66e6-c91a-297dbd059b0e
66
+ - architecture: Ada
67
+ cudaCores: 16384
68
+ memoryTotal: "25757220864"
69
+ name: NVIDIA GeForce RTX 4090
70
+ uuid: GPU-338ffd2f-eca1-e50f-fd79-a10706d991e2
71
+ - architecture: Ada
72
+ cudaCores: 16384
73
+ memoryTotal: "25757220864"
74
+ name: NVIDIA GeForce RTX 4090
75
+ uuid: GPU-0b498470-e696-0ceb-43c2-53b31f6448e8
76
+ - architecture: Ada
77
+ cudaCores: 16384
78
+ memoryTotal: "25757220864"
79
+ name: NVIDIA GeForce RTX 4090
80
+ uuid: GPU-fc644027-042c-f6f4-7636-2a9b4ffb3f8e
81
+ - architecture: Ada
82
+ cudaCores: 16384
83
+ memoryTotal: "25757220864"
84
+ name: NVIDIA GeForce RTX 4090
85
+ uuid: GPU-b86c050f-5196-4a9c-bbb5-d078a0818244
86
+ - architecture: Ada
87
+ cudaCores: 16384
88
+ memoryTotal: "25757220864"
89
+ name: NVIDIA GeForce RTX 4090
90
+ uuid: GPU-472ff6a0-ffd0-311b-0cd9-6e0b4ca76c3c
91
+ host: ed94ef2c39aa
92
+ memory:
93
+ total: "540803837952"
94
+ os: Linux-5.15.0-187-generic-x86_64-with-glibc2.39
95
+ program: -m eatmap.cli.pretrain
96
+ python: CPython 3.12.13
97
+ root: /workspace/runs/p1-smoke-sup-15m
98
+ startedAt: "2026-08-16T18:26:22.434971Z"
99
+ writerId: kl8tnmjaxnku9jouy33x0vp8rg7alj7f
100
+ m:
101
+ - "1": optimizer_step
102
+ "6":
103
+ - 3
104
+ "7": []
105
+ - "2": '*'
106
+ "5": 1
107
+ "6":
108
+ - 1
109
+ "7": []
110
+ python_version: 3.12.13
111
+ t:
112
+ "1":
113
+ - 1
114
+ "2":
115
+ - 1
116
+ "3":
117
+ - 2
118
+ - 7
119
+ - 13
120
+ - 14
121
+ - 16
122
+ - 61
123
+ - 62
124
+ "4": 3.12.13
125
+ "5": 0.28.2
126
+ "12": 0.28.2
127
+ "13": linux-x86_64
128
+ checkpoint:
129
+ value:
130
+ export_every_n_steps: 2000
131
+ keep_last_n_exports: 0
132
+ save_every_n_steps: 2000
133
+ data:
134
+ value:
135
+ batch_size: 48
136
+ data_dir: /workspace/data/asmel_flat
137
+ drop_last: true
138
+ max_shards: 0
139
+ num_workers: 12
140
+ persistent_workers: true
141
+ pin_memory: true
142
+ prefetch_factor: 4
143
+ revision: ""
144
+ seed: 0
145
+ train_split: train
146
+ val_split: balanced_train
147
+ eval:
148
+ value:
149
+ batch_size: 48
150
+ enabled: true
151
+ every_n_steps: 1000
152
+ mask_seed: 12345
153
+ num_clips: 2048
154
+ loop:
155
+ value:
156
+ budget_clips: 384000
157
+ compile: true
158
+ compile_mode: default
159
+ gradient_accumulation_steps: 1
160
+ heartbeat_every_n_steps: 50
161
+ log_every_n_steps: 20
162
+ max_steps: null
163
+ precision: bfloat16
164
+ schedule_clips: null
165
+ mixture:
166
+ value:
167
+ cluster_index: /workspace/data/asmel_flat/train_cluster_index.npy
168
+ dist_id: null
169
+ distinct_fraction: null
170
+ distributions: null
171
+ repetition_cap: 1000
172
+ weights:
173
+ - 0.161611328125
174
+ - 0.042833984375
175
+ - 0.066421875
176
+ - 0
177
+ - 0.0354609375
178
+ - 0
179
+ - 0.027091796875
180
+ - 0.000837890625
181
+ - 0.02515625
182
+ - 0.0256796875
183
+ - 0
184
+ - 0.0005234375
185
+ - 0.314330078125
186
+ - 0.01475
187
+ - 0.192939453125
188
+ - 0.000208984375
189
+ - 0.000208984375
190
+ - 0.0655859375
191
+ - 0.005177734375
192
+ - 0.021181640625
193
+ model:
194
+ value:
195
+ decoder_groups: 16
196
+ decoder_kernel: 3
197
+ decoder_layers: 6
198
+ depth: 8
199
+ embed_dim: 384
200
+ mel_bins: 64
201
+ mlp_ratio: 4
202
+ num_heads: 6
203
+ patch_freq: 16
204
+ patch_time: 16
205
+ target_frames: 1024
206
+ objective:
207
+ value:
208
+ average_top_k_layers: 0
209
+ clone_batch: 1
210
+ ema_anneal_steps: null
211
+ ema_decay: 0.9998
212
+ ema_end_decay: 0.99999
213
+ kind: sup
214
+ mae_norm_pix: true
215
+ mask_length: 5
216
+ mask_prob: 0.8
217
+ mask_prob_adjust: 0.07
218
+ normalize_utterance_target: false
219
+ num_classes: 527
220
+ utterance_weight: 1
221
+ optim:
222
+ value:
223
+ betas:
224
+ - 0.9
225
+ - 0.95
226
+ clip_norm: 4
227
+ eps: 1e-08
228
+ lr: 0.001
229
+ min_lr_scale: 0.002
230
+ warmup_frac: 0.1
231
+ weight_decay: 0.05
232
+ runtime:
233
+ value:
234
+ allow_tf32: true
235
+ data_loader_seed: null
236
+ deterministic: false
237
+ objective_seed: null
238
+ seed: 0
239
+ tracking:
240
+ value:
241
+ campaign_id: phase1
242
+ hub_private: false
243
+ hub_repo_id: null
244
+ hub_upload: false
245
+ trial_id: p1-smoke-sup-15m
246
+ wandb_entity: null
247
+ wandb_mode: online
248
+ wandb_project: mixture-transfer
249
+ wandb_run_id: null
p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/files/output.log ADDED
The diff for this file is too large to render. See raw diff
 
p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/files/requirements.txt ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ packaging==26.2
2
+ pip==26.1.2
3
+ wheel==0.47.0
4
+ aiosignal==1.4.0
5
+ typing-inspection==0.4.4
6
+ xxhash==4.0.0
7
+ aiohappyeyeballs==2.7.1
8
+ multidict==6.7.1
9
+ safetensors==0.8.0
10
+ annotated-types==0.8.0
11
+ charset-normalizer==3.5.1
12
+ propcache==0.5.2
13
+ pydantic_core==2.46.4
14
+ urllib3==2.7.0
15
+ opentelemetry-api==1.44.0
16
+ yarl==1.24.5
17
+ frozenlist==1.8.0
18
+ dill==0.4.1
19
+ aiohttp==3.14.3
20
+ requests==2.34.2
21
+ attrs==26.1.0
22
+ multiprocess==0.70.19
23
+ protobuf==7.35.1
24
+ pydantic==2.13.4
25
+ datasets==5.0.1
26
+ sentry-sdk==2.68.0
27
+ wandb==0.28.2
28
+ pyarrow==25.0.1
29
+ pandas==3.0.5
30
+ scipy==1.18.0
31
+ hf_transfer==0.1.9
32
+ iniconfig==2.3.0
33
+ pluggy==1.6.0
34
+ pytest==9.1.1
35
+ cuda-bindings==13.3.1
36
+ cuda-pathfinder==1.5.5
37
+ cuda-toolkit==13.0.2
38
+ Jinja2==3.1.6
39
+ MarkupSafe==3.0.3
40
+ mpmath==1.3.0
41
+ networkx==3.6.1
42
+ numpy==2.4.6
43
+ nvidia-cublas==13.1.1.3
44
+ nvidia-cuda-cupti==13.0.85
45
+ nvidia-cuda-nvrtc==13.0.88
46
+ nvidia-cuda-runtime==13.0.96
47
+ nvidia-cudnn-cu13==9.20.0.48
48
+ nvidia-cufft==12.0.0.61
49
+ nvidia-cufile==1.15.1.6
50
+ nvidia-curand==10.4.0.35
51
+ nvidia-cusolver==12.0.4.66
52
+ nvidia-cusparse==12.6.3.3
53
+ nvidia-cusparselt-cu13==0.8.1
54
+ nvidia-nccl-cu13==2.29.7
55
+ nvidia-nvjitlink==13.0.88
56
+ nvidia-nvshmem-cu13==3.4.5
57
+ nvidia-nvtx==13.0.85
58
+ pillow==12.2.0
59
+ setuptools==81.0.0
60
+ sympy==1.14.0
61
+ torch==2.12.0+cu130
62
+ torchcodec==0.12.0+cu130
63
+ torchvision==0.27.0+cu130
64
+ triton==3.7.0
65
+ annotated-doc==0.0.4
66
+ anyio==4.13.0
67
+ asttokens==3.0.1
68
+ certifi==2026.5.20
69
+ click==8.4.1
70
+ comm==0.2.3
71
+ debugpy==1.8.21
72
+ decorator==5.3.1
73
+ executing==2.2.1
74
+ filelock==3.29.1
75
+ fsspec==2026.4.0
76
+ h11==0.16.0
77
+ hf-xet==1.5.0
78
+ httpcore==1.0.9
79
+ httpx==0.28.1
80
+ huggingface_hub==1.18.0
81
+ idna==3.18
82
+ ipykernel==7.2.0
83
+ ipython==9.14.1
84
+ ipython_pygments_lexers==1.1.1
85
+ ipywidgets==8.1.8
86
+ jedi==0.20.0
87
+ jupyter_client==8.9.0
88
+ jupyter_core==5.9.1
89
+ jupyterlab_widgets==3.0.16
90
+ markdown-it-py==4.2.0
91
+ matplotlib-inline==0.2.2
92
+ mdurl==0.1.2
93
+ nest-asyncio==1.6.0
94
+ parso==0.8.7
95
+ pexpect==4.9.0
96
+ platformdirs==4.10.0
97
+ prompt_toolkit==3.0.52
98
+ psutil==7.2.2
99
+ ptyprocess==0.7.0
100
+ pure_eval==0.2.3
101
+ Pygments==2.20.0
102
+ python-dateutil==2.9.0.post0
103
+ PyYAML==6.0.3
104
+ pyzmq==27.1.0
105
+ rich==15.0.0
106
+ shellingham==1.5.4
107
+ six==1.17.0
108
+ stack-data==0.6.3
109
+ tornado==6.5.6
110
+ tqdm==4.68.0
111
+ traitlets==5.15.1
112
+ typer==0.25.1
113
+ typing_extensions==4.15.0
114
+ wcwidth==0.7.0
115
+ widgetsnbextension==4.0.15
p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/files/wandb-metadata.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-5.15.0-187-generic-x86_64-with-glibc2.39",
3
+ "python": "CPython 3.12.13",
4
+ "startedAt": "2026-08-16T18:26:22.434971Z",
5
+ "args": [
6
+ "--config",
7
+ "configs/base.yaml",
8
+ "--config",
9
+ "configs/scale_15m.yaml",
10
+ "--config",
11
+ "configs/budget_40k.yaml",
12
+ "--config",
13
+ "configs/obj_sup.yaml",
14
+ "--set",
15
+ "loop.budget_clips=384000",
16
+ "--set",
17
+ "checkpoint.export_every_n_steps=2000",
18
+ "--set",
19
+ "checkpoint.save_every_n_steps=2000",
20
+ "--set",
21
+ "optim.lr=1.0e-3",
22
+ "--set",
23
+ "eval.every_n_steps=1000",
24
+ "--set",
25
+ "mixture.cluster_index=/workspace/data/asmel_flat/train_cluster_index.npy",
26
+ "--set",
27
+ "mixture.weights=[0.161611328125, 0.042833984375, 0.066421875, 0.0, 0.0354609375, 0.0, 0.027091796875, 0.000837890625, 0.02515625, 0.0256796875, 0.0, 0.0005234375, 0.314330078125, 0.01475, 0.192939453125, 0.000208984375, 0.000208984375, 0.0655859375, 0.005177734375, 0.021181640625]",
28
+ "--set",
29
+ "tracking.campaign_id=phase1",
30
+ "--set",
31
+ "tracking.trial_id=p1-smoke-sup-15m",
32
+ "--set",
33
+ "tracking.wandb_project=mixture-transfer",
34
+ "--output-dir",
35
+ "/workspace/runs/p1-smoke-sup-15m"
36
+ ],
37
+ "program": "-m eatmap.cli.pretrain",
38
+ "git": {
39
+ "commit": "c3ed4f7086fd770b27c6d2c9980eb6b06ad4a3da"
40
+ },
41
+ "email": "luequinn@gmail.com",
42
+ "root": "/workspace/runs/p1-smoke-sup-15m",
43
+ "host": "ed94ef2c39aa",
44
+ "executable": "/venv/main/bin/python",
45
+ "cpu_count": 112,
46
+ "cpu_count_logical": 224,
47
+ "gpu": "NVIDIA GeForce RTX 4090",
48
+ "gpu_count": 8,
49
+ "disk": {
50
+ "/": {
51
+ "total": "549755813888",
52
+ "used": "150857805824"
53
+ }
54
+ },
55
+ "memory": {
56
+ "total": "540803837952"
57
+ },
58
+ "gpu_nvidia": [
59
+ {
60
+ "name": "NVIDIA GeForce RTX 4090",
61
+ "memoryTotal": "25757220864",
62
+ "cudaCores": 16384,
63
+ "architecture": "Ada",
64
+ "uuid": "GPU-e953afa7-1257-d569-95ea-b1eaea8d26c6"
65
+ },
66
+ {
67
+ "name": "NVIDIA GeForce RTX 4090",
68
+ "memoryTotal": "25757220864",
69
+ "cudaCores": 16384,
70
+ "architecture": "Ada",
71
+ "uuid": "GPU-008b9ed1-b1a3-2de2-12bb-eddf323625d3"
72
+ },
73
+ {
74
+ "name": "NVIDIA GeForce RTX 4090",
75
+ "memoryTotal": "25757220864",
76
+ "cudaCores": 16384,
77
+ "architecture": "Ada",
78
+ "uuid": "GPU-0c1a8517-a56e-66e6-c91a-297dbd059b0e"
79
+ },
80
+ {
81
+ "name": "NVIDIA GeForce RTX 4090",
82
+ "memoryTotal": "25757220864",
83
+ "cudaCores": 16384,
84
+ "architecture": "Ada",
85
+ "uuid": "GPU-338ffd2f-eca1-e50f-fd79-a10706d991e2"
86
+ },
87
+ {
88
+ "name": "NVIDIA GeForce RTX 4090",
89
+ "memoryTotal": "25757220864",
90
+ "cudaCores": 16384,
91
+ "architecture": "Ada",
92
+ "uuid": "GPU-0b498470-e696-0ceb-43c2-53b31f6448e8"
93
+ },
94
+ {
95
+ "name": "NVIDIA GeForce RTX 4090",
96
+ "memoryTotal": "25757220864",
97
+ "cudaCores": 16384,
98
+ "architecture": "Ada",
99
+ "uuid": "GPU-fc644027-042c-f6f4-7636-2a9b4ffb3f8e"
100
+ },
101
+ {
102
+ "name": "NVIDIA GeForce RTX 4090",
103
+ "memoryTotal": "25757220864",
104
+ "cudaCores": 16384,
105
+ "architecture": "Ada",
106
+ "uuid": "GPU-b86c050f-5196-4a9c-bbb5-d078a0818244"
107
+ },
108
+ {
109
+ "name": "NVIDIA GeForce RTX 4090",
110
+ "memoryTotal": "25757220864",
111
+ "cudaCores": 16384,
112
+ "architecture": "Ada",
113
+ "uuid": "GPU-472ff6a0-ffd0-311b-0cd9-6e0b4ca76c3c"
114
+ }
115
+ ],
116
+ "cudaVersion": "13.0",
117
+ "writerId": "kl8tnmjaxnku9jouy33x0vp8rg7alj7f"
118
+ }
p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train/frame_loss":0.014098604209721088,"clips_seen":384000,"train/utterance_loss":0,"peak_gib":1.5364618301391602,"ema_anneal_steps":8000,"final_lr":2.0000475012781556e-06,"schedule_steps":8000,"final_step":8000,"val/frame":0.03064619516953826,"_timestamp":1.7869049557633986e+09,"encoder_params":14294784,"clips_per_step":48,"_wandb":{"runtime":172},"perf/data_wait_frac":0.0036904262742326727,"max_repetition":1.0886501794830168,"val/utterance":0,"val/loss":0.03064619516953826,"budget_clips":384000,"final_ema_decay":0.9999899762500001,"decoder_params":0,"train/grad_norm":0.0031838202849030495,"_runtime":172.256341335,"perf/peak_gib":1.5364618301391602,"total_params":14497679,"progress/clips_seen":384000,"_step":8000,"perf/clips_per_s":2306.7236000674934,"progress/epoch_frac":0.2008342991510567,"train/loss":0.014098604209721088,"trainable_params":14497679,"completed":true,"warmup_steps":800,"train/ema_decay":0.99999,"train/lr":2.0000475012781556e-06,"total_steps":8000,"optimizer_step":8000}
p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/logs/debug-core.log ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2026-08-16T18:26:21.30854655Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpmhnme0j1/port-16562.txt","pid":16562,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
2
+ {"time":"2026-08-16T18:26:21.309185809Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":16562}
3
+ {"time":"2026-08-16T18:26:21.309182749Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-16562-18349-2383001383/socket","Net":"unix"}}
4
+ {"time":"2026-08-16T18:26:21.321537663Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmp0ujgifk6/port-16559.txt","pid":16559,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
5
+ {"time":"2026-08-16T18:26:21.322206562Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":16559}
6
+ {"time":"2026-08-16T18:26:21.322128121Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-16559-18409-1504691835/socket","Net":"unix"}}
7
+ {"time":"2026-08-16T18:26:21.459626453Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
8
+ {"time":"2026-08-16T18:26:21.475244093Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
9
+ {"time":"2026-08-16T18:26:21.48215054Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmp3let_7iv/port-16560.txt","pid":16560,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
10
+ {"time":"2026-08-16T18:26:21.48288763Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":16560}
11
+ {"time":"2026-08-16T18:26:21.48287934Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-16560-18694-2440142749/socket","Net":"unix"}}
12
+ {"time":"2026-08-16T18:26:21.543574983Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmp66ulp9c2/port-16555.txt","pid":16555,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
13
+ {"time":"2026-08-16T18:26:21.544160632Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":16555}
14
+ {"time":"2026-08-16T18:26:21.544100711Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-16555-18763-1154992375/socket","Net":"unix"}}
15
+ {"time":"2026-08-16T18:26:21.58532428Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmp_hp2mbfx/port-16564.txt","pid":16564,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
16
+ {"time":"2026-08-16T18:26:21.58604437Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":16564}
17
+ {"time":"2026-08-16T18:26:21.58603942Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-16564-18825-2603103548/socket","Net":"unix"}}
18
+ {"time":"2026-08-16T18:26:21.610165979Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpw8gl5h87/port-16557.txt","pid":16557,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
19
+ {"time":"2026-08-16T18:26:21.610694537Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":16557}
20
+ {"time":"2026-08-16T18:26:21.610673746Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-16557-18889-1183568292/socket","Net":"unix"}}
21
+ {"time":"2026-08-16T18:26:21.632711845Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
22
+ {"time":"2026-08-16T18:26:21.696515883Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
23
+ {"time":"2026-08-16T18:26:21.7340687Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
24
+ {"time":"2026-08-16T18:26:21.749807401Z","level":"INFO","msg":"handleInformInit: received","streamId":"phase1-p1-tput-mae-1m","id":"1(@)"}
25
+ {"time":"2026-08-16T18:26:21.762194636Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
26
+ {"time":"2026-08-16T18:26:21.95823818Z","level":"INFO","msg":"handleInformInit: received","streamId":"phase1-p1-smoke-eat-15m","id":"1(@)"}
27
+ {"time":"2026-08-16T18:26:22.013325634Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"phase1-p1-tput-mae-1m","id":"1(@)"}
28
+ {"time":"2026-08-16T18:26:22.03502734Z","level":"INFO","msg":"handleInformInit: received","streamId":"phase1-p1-tput-mae-base","id":"1(@)"}
29
+ {"time":"2026-08-16T18:26:22.057566596Z","level":"INFO","msg":"handleInformInit: received","streamId":"phase1-p1-smoke-mae-15m","id":"1(@)"}
30
+ {"time":"2026-08-16T18:26:22.201508509Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"phase1-p1-smoke-eat-15m","id":"1(@)"}
31
+ {"time":"2026-08-16T18:26:22.264647076Z","level":"INFO","msg":"handleInformInit: received","streamId":"phase1-p1-tput-mae-5m","id":"1(@)"}
32
+ {"time":"2026-08-16T18:26:22.399035893Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"phase1-p1-tput-mae-5m","id":"1(@)"}
33
+ {"time":"2026-08-16T18:26:22.401520548Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"phase1-p1-tput-mae-base","id":"1(@)"}
34
+ {"time":"2026-08-16T18:26:22.420088769Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"phase1-p1-smoke-mae-15m","id":"1(@)"}
35
+ {"time":"2026-08-16T18:26:22.439131356Z","level":"INFO","msg":"handleInformInit: received","streamId":"phase1-p1-smoke-sup-15m","id":"1(@)"}
36
+ {"time":"2026-08-16T18:26:22.682666468Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"phase1-p1-smoke-sup-15m","id":"1(@)"}
37
+ {"time":"2026-08-16T18:26:27.969942543Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"l9cqzyjdq1ax"}
38
+ {"time":"2026-08-16T18:26:28.389984624Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"vw9s5umqreid"}
39
+ {"time":"2026-08-16T18:26:28.61065111Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"ksfz0e2b0nsk"}
40
+ {"time":"2026-08-16T18:26:28.73611983Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"wxv1ssbefa4o"}
41
+ {"time":"2026-08-16T18:26:28.792134195Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"fck5qv17mj4x"}
42
+ {"time":"2026-08-16T18:26:28.995307444Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"khfeetg48au3"}
43
+ {"time":"2026-08-16T18:26:52.751731821Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"processor export timeout: retry-able request failure: body: failed to forward logs"}
44
+ {"time":"2026-08-16T18:26:52.960912917Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"processor export timeout: retry-able request failure: body: failed to forward logs"}
45
+ {"time":"2026-08-16T18:26:53.0365257Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"processor export timeout: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/logs\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
46
+ {"time":"2026-08-16T18:26:53.059691553Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"processor export timeout: retry-able request failure: body: failed to forward logs"}
47
+ {"time":"2026-08-16T18:26:53.266014057Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"processor export timeout: retry-able request failure: body: failed to forward logs"}
48
+ {"time":"2026-08-16T18:26:53.441964868Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"processor export timeout: retry-able request failure: body: failed to forward logs"}
49
+ {"time":"2026-08-16T18:26:58.968264874Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: context deadline exceeded: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": context deadline exceeded"}
50
+ {"time":"2026-08-16T18:26:59.98452834Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: reader collect and export timeout: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": context deadline exceeded"}
51
+ {"time":"2026-08-16T18:27:09.244962077Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: reader collect and export timeout: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": context deadline exceeded"}
52
+ {"time":"2026-08-16T18:28:04.772568287Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: reader collect and export timeout: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
53
+ {"time":"2026-08-16T18:28:06.250706164Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: reader collect and export timeout: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": context deadline exceeded (Client.Timeout exceeded while awaiting headers)"}
54
+ {"time":"2026-08-16T18:28:13.424086339Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"l9cqzyjdq1ax"}
55
+ {"time":"2026-08-16T18:28:14.233722997Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"khfeetg48au3"}
56
+ {"time":"2026-08-16T18:28:15.171451371Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"l9cqzyjdq1ax"}
57
+ {"time":"2026-08-16T18:28:15.174906049Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"phase1-p1-tput-mae-1m","id":"1(@)"}
58
+ {"time":"2026-08-16T18:28:15.175244933Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: context canceled: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": context deadline exceeded"}
59
+ {"time":"2026-08-16T18:28:15.370518269Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"phase1-p1-tput-mae-1m","id":"1(@)"}
60
+ {"time":"2026-08-16T18:28:16.018778989Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"khfeetg48au3"}
61
+ {"time":"2026-08-16T18:28:16.021270063Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"phase1-p1-tput-mae-5m","id":"1(@)"}
62
+ {"time":"2026-08-16T18:28:16.021476846Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: context canceled: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
63
+ {"time":"2026-08-16T18:28:16.031625335Z","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
64
+ {"time":"2026-08-16T18:28:16.031675216Z","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
65
+ {"time":"2026-08-16T18:28:16.031687806Z","level":"INFO","msg":"connection: closing","id":"1(@)"}
66
+ {"time":"2026-08-16T18:28:16.031725066Z","level":"INFO","msg":"processOutgoingData: finished","id":"1(@)"}
67
+ {"time":"2026-08-16T18:28:16.031733656Z","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
68
+ {"time":"2026-08-16T18:28:16.031767727Z","level":"INFO","msg":"server: is shutting down"}
69
+ {"time":"2026-08-16T18:28:16.032871082Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: context canceled: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": context deadline exceeded (Client.Timeout exceeded while awaiting headers)"}
70
+ {"time":"2026-08-16T18:28:16.031797037Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: context canceled: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
71
+ {"time":"2026-08-16T18:28:16.032980973Z","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-16559-18409-1504691835/socket","Net":"unix"}}
72
+ {"time":"2026-08-16T18:28:16.194059141Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"phase1-p1-tput-mae-5m","id":"1(@)"}
73
+ {"time":"2026-08-16T18:28:17.01235087Z","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
74
+ {"time":"2026-08-16T18:28:17.015568144Z","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
75
+ {"time":"2026-08-16T18:28:17.015593914Z","level":"INFO","msg":"processOutgoingData: finished","id":"1(@)"}
76
+ {"time":"2026-08-16T18:28:17.015583854Z","level":"INFO","msg":"connection: closing","id":"1(@)"}
77
+ {"time":"2026-08-16T18:28:17.015629304Z","level":"INFO","msg":"server: is shutting down"}
78
+ {"time":"2026-08-16T18:28:17.015654705Z","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
79
+ {"time":"2026-08-16T18:28:17.015696215Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: context canceled: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
80
+ {"time":"2026-08-16T18:28:17.015723646Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: context canceled: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": context deadline exceeded"}
81
+ {"time":"2026-08-16T18:28:17.015832197Z","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-16562-18349-2383001383/socket","Net":"unix"}}
82
+ {"time":"2026-08-16T18:28:17.208517947Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
83
+ {"time":"2026-08-16T18:28:17.208567908Z","level":"INFO","msg":"server: all connections closed"}
84
+ {"time":"2026-08-16T18:28:18.033234571Z","level":"ERROR","msg":"wbapi: error shutting down OpenTelemetry handler","error":"shutdown errors: [failed to upload metrics: context deadline exceeded: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": context deadline exceeded context deadline exceeded]"}
85
+ {"time":"2026-08-16T18:28:18.033319782Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
86
+ {"time":"2026-08-16T18:28:18.033340612Z","level":"INFO","msg":"server: all connections closed"}
87
+ {"time":"2026-08-16T18:28:44.232484931Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"fck5qv17mj4x"}
88
+ {"time":"2026-08-16T18:28:45.972933135Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"fck5qv17mj4x"}
89
+ {"time":"2026-08-16T18:28:45.974907092Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"phase1-p1-tput-mae-base","id":"1(@)"}
90
+ {"time":"2026-08-16T18:28:45.975126885Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: context canceled: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": context deadline exceeded"}
91
+ {"time":"2026-08-16T18:28:46.160735492Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"phase1-p1-tput-mae-base","id":"1(@)"}
92
+ {"time":"2026-08-16T18:28:46.717779815Z","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
93
+ {"time":"2026-08-16T18:28:46.717851476Z","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
94
+ {"time":"2026-08-16T18:28:46.717872696Z","level":"INFO","msg":"processOutgoingData: finished","id":"1(@)"}
95
+ {"time":"2026-08-16T18:28:46.717863516Z","level":"INFO","msg":"connection: closing","id":"1(@)"}
96
+ {"time":"2026-08-16T18:28:46.717958907Z","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
97
+ {"time":"2026-08-16T18:28:46.717969317Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: context canceled: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": context deadline exceeded"}
98
+ {"time":"2026-08-16T18:28:46.717895166Z","level":"INFO","msg":"server: is shutting down"}
99
+ {"time":"2026-08-16T18:28:46.718001338Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"context canceled"}
100
+ {"time":"2026-08-16T18:28:46.718029608Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: context canceled: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": context deadline exceeded (Client.Timeout exceeded while awaiting headers)"}
101
+ {"time":"2026-08-16T18:28:46.720766935Z","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-16564-18825-2603103548/socket","Net":"unix"}}
102
+ {"time":"2026-08-16T18:28:46.911660823Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
103
+ {"time":"2026-08-16T18:28:46.911691443Z","level":"INFO","msg":"server: all connections closed"}
104
+ {"time":"2026-08-16T18:29:15.850497456Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"wxv1ssbefa4o"}
105
+ {"time":"2026-08-16T18:29:17.837814037Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"wxv1ssbefa4o"}
106
+ {"time":"2026-08-16T18:29:17.839866685Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"phase1-p1-smoke-sup-15m","id":"1(@)"}
107
+ {"time":"2026-08-16T18:29:18.027998909Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"phase1-p1-smoke-sup-15m","id":"1(@)"}
108
+ {"time":"2026-08-16T18:29:18.629463218Z","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
109
+ {"time":"2026-08-16T18:29:18.629553739Z","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
110
+ {"time":"2026-08-16T18:29:18.62956906Z","level":"INFO","msg":"connection: closing","id":"1(@)"}
111
+ {"time":"2026-08-16T18:29:18.62961844Z","level":"INFO","msg":"server: is shutting down"}
112
+ {"time":"2026-08-16T18:29:18.62961407Z","level":"INFO","msg":"processOutgoingData: finished","id":"1(@)"}
113
+ {"time":"2026-08-16T18:29:18.629642841Z","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
114
+ {"time":"2026-08-16T18:29:18.63253545Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": context canceled"}
115
+ {"time":"2026-08-16T18:29:18.629742772Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: context canceled: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
116
+ {"time":"2026-08-16T18:29:18.632736183Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"context canceled"}
117
+ {"time":"2026-08-16T18:29:18.629851783Z","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-16560-18694-2440142749/socket","Net":"unix"}}
118
+ {"time":"2026-08-16T18:29:18.835088248Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
119
+ {"time":"2026-08-16T18:29:18.835132678Z","level":"INFO","msg":"server: all connections closed"}
120
+ {"time":"2026-08-16T18:29:20.558423448Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: reader collect and export timeout: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
121
+ {"time":"2026-08-16T18:29:41.46223488Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: reader collect and export timeout: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": context deadline exceeded"}
122
+ {"time":"2026-08-16T18:30:18.607962876Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"vw9s5umqreid"}
123
+ {"time":"2026-08-16T18:30:21.391832516Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"vw9s5umqreid"}
124
+ {"time":"2026-08-16T18:30:21.393990715Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"phase1-p1-smoke-mae-15m","id":"1(@)"}
125
+ {"time":"2026-08-16T18:30:21.394317039Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: context canceled: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
126
+ {"time":"2026-08-16T18:30:21.394335879Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"context canceled"}
127
+ {"time":"2026-08-16T18:30:23.395587696Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"phase1-p1-smoke-mae-15m","id":"1(@)"}
128
+ {"time":"2026-08-16T18:30:23.395652076Z","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
129
+ {"time":"2026-08-16T18:30:23.395674577Z","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
130
+ {"time":"2026-08-16T18:30:23.395688347Z","level":"INFO","msg":"connection: closing","id":"1(@)"}
131
+ {"time":"2026-08-16T18:30:23.395725297Z","level":"INFO","msg":"processOutgoingData: finished","id":"1(@)"}
132
+ {"time":"2026-08-16T18:30:23.395751018Z","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
133
+ {"time":"2026-08-16T18:30:23.395760568Z","level":"INFO","msg":"server: is shutting down"}
134
+ {"time":"2026-08-16T18:30:23.395811849Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: context canceled: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
135
+ {"time":"2026-08-16T18:30:23.395841849Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"context canceled"}
136
+ {"time":"2026-08-16T18:30:23.395825649Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": context canceled"}
137
+ {"time":"2026-08-16T18:30:23.396041002Z","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-16557-18889-1183568292/socket","Net":"unix"}}
138
+ {"time":"2026-08-16T18:30:23.588893756Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
139
+ {"time":"2026-08-16T18:30:23.588937377Z","level":"INFO","msg":"server: all connections closed"}
140
+ {"time":"2026-08-16T18:34:14.206481072Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: reader collect and export timeout: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": context deadline exceeded"}
141
+ {"time":"2026-08-16T18:36:01.54000989Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: reader collect and export timeout: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
142
+ {"time":"2026-08-16T18:36:59.959805224Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: context deadline exceeded: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": context deadline exceeded"}
143
+ {"time":"2026-08-16T18:40:11.577090574Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: reader collect and export timeout: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
144
+ {"time":"2026-08-16T18:42:04.587441358Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"ksfz0e2b0nsk"}
145
+ {"time":"2026-08-16T18:42:07.028928543Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"ksfz0e2b0nsk"}
146
+ {"time":"2026-08-16T18:42:07.035991344Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"phase1-p1-smoke-eat-15m","id":"1(@)"}
147
+ {"time":"2026-08-16T18:42:07.036546775Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": context canceled"}
148
+ {"time":"2026-08-16T18:42:07.48062985Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"phase1-p1-smoke-eat-15m","id":"1(@)"}
149
+ {"time":"2026-08-16T18:42:07.754880429Z","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
150
+ {"time":"2026-08-16T18:42:07.754995899Z","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
151
+ {"time":"2026-08-16T18:42:07.755007989Z","level":"INFO","msg":"processOutgoingData: finished","id":"1(@)"}
152
+ {"time":"2026-08-16T18:42:07.755049819Z","level":"INFO","msg":"server: is shutting down"}
153
+ {"time":"2026-08-16T18:42:07.755030869Z","level":"INFO","msg":"connection: closing","id":"1(@)"}
154
+ {"time":"2026-08-16T18:42:07.755126999Z","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
155
+ {"time":"2026-08-16T18:42:07.755176609Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: context canceled: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
156
+ {"time":"2026-08-16T18:42:07.755231129Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"failed to upload metrics: context canceled: retry-able request failure: Post \"https://api.wandb.ai/sdk/otel/v1/metrics\": net/http: request canceled (Client.Timeout exceeded while awaiting headers)"}
157
+ {"time":"2026-08-16T18:42:07.755256629Z","level":"ERROR","msg":"analytics: failed to send telemetry to backend proxy","error":"context canceled"}
158
+ {"time":"2026-08-16T18:42:07.75538186Z","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-16555-18763-1154992375/socket","Net":"unix"}}
159
+ {"time":"2026-08-16T18:42:07.991511459Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
160
+ {"time":"2026-08-16T18:42:07.991573859Z","level":"INFO","msg":"server: all connections closed"}
p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/logs/debug-internal.log ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2026-08-16T18:26:22.440217762Z","level":"INFO","msg":"wandb-core"}
2
+ {"time":"2026-08-16T18:26:22.440553246Z","level":"INFO","msg":"stream: starting","core version":"0.28.2"}
3
+ {"time":"2026-08-16T18:26:22.682446615Z","level":"INFO","msg":"stream: created new stream","id":"phase1-p1-smoke-sup-15m"}
4
+ {"time":"2026-08-16T18:26:22.682565127Z","level":"INFO","msg":"handler: started"}
5
+ {"time":"2026-08-16T18:26:22.682654518Z","level":"INFO","msg":"stream: started"}
6
+ {"time":"2026-08-16T18:26:22.682733129Z","level":"INFO","msg":"writer: started","stream_id":"phase1-p1-smoke-sup-15m"}
7
+ {"time":"2026-08-16T18:26:22.68276007Z","level":"INFO","msg":"sender: started"}
8
+ {"time":"2026-08-16T18:26:24.121014701Z","level":"INFO","msg":"filestream: sending request","total_files":1}
9
+ {"time":"2026-08-16T18:26:24.438362818Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
10
+ {"time":"2026-08-16T18:26:39.121514598Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":0,"events_lines":2,"console_offset":0,"console_lines":19,"uploaded_len":2}
11
+ {"time":"2026-08-16T18:26:39.374611087Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
12
+ {"time":"2026-08-16T18:26:54.121200631Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":40,"events_offset":2,"events_lines":2,"console_offset":19,"console_lines":41}
13
+ {"time":"2026-08-16T18:26:54.44562981Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
14
+ {"time":"2026-08-16T18:27:09.12189949Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":40,"history_lines":42,"events_offset":4,"events_lines":2,"console_offset":60,"console_lines":43}
15
+ {"time":"2026-08-16T18:27:09.438536963Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
16
+ {"time":"2026-08-16T18:27:24.122183518Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":82,"history_lines":40,"events_offset":6,"events_lines":2,"console_offset":103,"console_lines":41}
17
+ {"time":"2026-08-16T18:27:24.429272452Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
18
+ {"time":"2026-08-16T18:27:39.122296503Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":122,"history_lines":42,"events_offset":8,"events_lines":2,"console_offset":144,"console_lines":43}
19
+ {"time":"2026-08-16T18:27:39.950761431Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
20
+ {"time":"2026-08-16T18:27:54.121773862Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":164,"history_lines":41,"events_offset":10,"events_lines":2,"console_offset":187,"console_lines":42}
21
+ {"time":"2026-08-16T18:27:54.440782009Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
22
+ {"time":"2026-08-16T18:28:09.121832992Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":205,"history_lines":42,"events_offset":12,"events_lines":2,"console_offset":229,"console_lines":42}
23
+ {"time":"2026-08-16T18:28:09.449802827Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
24
+ {"time":"2026-08-16T18:28:24.121472485Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":247,"history_lines":37,"events_offset":14,"events_lines":2,"console_offset":271,"console_lines":38}
25
+ {"time":"2026-08-16T18:28:24.465737555Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
26
+ {"time":"2026-08-16T18:28:39.12194747Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":284,"history_lines":37,"events_offset":16,"events_lines":2,"console_offset":309,"console_lines":38}
27
+ {"time":"2026-08-16T18:28:39.426587476Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
28
+ {"time":"2026-08-16T18:28:54.121798683Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":321,"history_lines":35,"events_offset":18,"events_lines":2,"console_offset":347,"console_lines":36}
29
+ {"time":"2026-08-16T18:28:54.428028508Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
30
+ {"time":"2026-08-16T18:29:09.122057906Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":356,"history_lines":31,"events_offset":20,"events_lines":2,"console_offset":383,"console_lines":31}
31
+ {"time":"2026-08-16T18:29:09.419780564Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
32
+ {"time":"2026-08-16T18:29:17.534114877Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
33
+ {"time":"2026-08-16T18:29:17.534443301Z","level":"INFO","msg":"filestream: sending request","total_files":3,"history_offset":387,"history_lines":13,"console_offset":414,"console_lines":13,"uploaded_len":3,"complete":true,"exit_code":0}
34
+ {"time":"2026-08-16T18:29:17.833673472Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
35
+ {"time":"2026-08-16T18:29:17.835738729Z","level":"INFO","msg":"handler: operation stats","stats":{}}
36
+ {"time":"2026-08-16T18:29:17.839881375Z","level":"INFO","msg":"stream: finishing up"}
37
+ {"time":"2026-08-16T18:29:17.839897485Z","level":"INFO","msg":"handler: closed"}
38
+ {"time":"2026-08-16T18:29:17.840004977Z","level":"INFO","msg":"sender: closed"}
39
+ {"time":"2026-08-16T18:29:17.840011917Z","level":"INFO","msg":"stream: all finished"}
p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/logs/debug.log ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2026-08-16 18:26:22,437 INFO MainThread:16560 [wandb_setup.py:_flush():81] Current SDK version is 0.28.2
2
+ 2026-08-16 18:26:22,437 INFO MainThread:16560 [wandb_setup.py:_flush():81] Configure stats pid to 16560
3
+ 2026-08-16 18:26:22,437 INFO MainThread:16560 [wandb_setup.py:_flush():81] Loading settings from environment variables
4
+ 2026-08-16 18:26:22,437 INFO MainThread:16560 [wandb_init.py:setup_run_log_directory():739] Logging user logs to /workspace/runs/p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/logs/debug.log
5
+ 2026-08-16 18:26:22,437 INFO MainThread:16560 [wandb_init.py:setup_run_log_directory():740] Logging internal logs to /workspace/runs/p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/logs/debug-internal.log
6
+ 2026-08-16 18:26:22,437 INFO MainThread:16560 [wandb_init.py:init():783] calling init triggers
7
+ 2026-08-16 18:26:22,437 INFO MainThread:16560 [wandb_init.py:init():788] wandb.init called with sweep_config: {}
8
+ config: {'model': {'embed_dim': 384, 'depth': 8, 'num_heads': 6, 'mlp_ratio': 4, 'target_frames': 1024, 'mel_bins': 64, 'patch_time': 16, 'patch_freq': 16, 'decoder_layers': 6, 'decoder_groups': 16, 'decoder_kernel': 3}, 'objective': {'kind': 'sup', 'mae_norm_pix': True, 'num_classes': 527, 'clone_batch': 1, 'mask_prob': 0.8, 'mask_length': 5, 'mask_prob_adjust': 0.07, 'average_top_k_layers': 0, 'utterance_weight': 1.0, 'normalize_utterance_target': False, 'ema_decay': 0.9998, 'ema_end_decay': 0.99999, 'ema_anneal_steps': None}, 'data': {'data_dir': '/workspace/data/asmel_flat', 'train_split': 'train', 'val_split': 'balanced_train', 'revision': '', 'batch_size': 48, 'num_workers': 12, 'prefetch_factor': 4, 'pin_memory': True, 'persistent_workers': True, 'drop_last': True, 'seed': 0, 'max_shards': 0}, 'mixture': {'cluster_index': '/workspace/data/asmel_flat/train_cluster_index.npy', 'distributions': None, 'dist_id': None, 'weights': [0.161611328125, 0.042833984375, 0.066421875, 0.0, 0.0354609375, 0.0, 0.027091796875, 0.000837890625, 0.02515625, 0.0256796875, 0.0, 0.0005234375, 0.314330078125, 0.01475, 0.192939453125, 0.000208984375, 0.000208984375, 0.0655859375, 0.005177734375, 0.021181640625], 'repetition_cap': 1000.0, 'distinct_fraction': None}, 'optim': {'lr': 0.001, 'betas': [0.9, 0.95], 'eps': 1e-08, 'weight_decay': 0.05, 'clip_norm': 4.0, 'warmup_frac': 0.1, 'min_lr_scale': 0.002}, 'loop': {'budget_clips': 384000, 'schedule_clips': None, 'gradient_accumulation_steps': 1, 'precision': 'bfloat16', 'compile': True, 'compile_mode': 'default', 'log_every_n_steps': 20, 'heartbeat_every_n_steps': 50, 'max_steps': None}, 'eval': {'enabled': True, 'every_n_steps': 1000, 'num_clips': 2048, 'mask_seed': 12345, 'batch_size': 48}, 'checkpoint': {'save_every_n_steps': 2000, 'export_every_n_steps': 2000, 'keep_last_n_exports': 0}, 'tracking': {'campaign_id': 'phase1', 'trial_id': 'p1-smoke-sup-15m', 'wandb_project': 'mixture-transfer', 'wandb_entity': None, 'wandb_mode': 'online', 'wandb_run_id': None, 'hub_repo_id': None, 'hub_private': False, 'hub_upload': False}, 'runtime': {'seed': 0, 'data_loader_seed': None, 'objective_seed': None, 'deterministic': False, 'allow_tf32': True}, '_wandb': {}}
9
+ 2026-08-16 18:26:22,437 INFO MainThread:16560 [wandb_init.py:init():831] starting backend
10
+ 2026-08-16 18:26:22,437 INFO MainThread:16560 [wandb_init.py:init():846] sending inform_init request
11
+ 2026-08-16 18:26:22,683 INFO MainThread:16560 [wandb_init.py:init():851] backend started and connected
12
+ 2026-08-16 18:26:22,684 INFO MainThread:16560 [wandb_init.py:init():921] updated telemetry
13
+ 2026-08-16 18:26:22,697 INFO MainThread:16560 [wandb_init.py:init():944] communicating run to backend with 90.0 second timeout
14
+ 2026-08-16 18:26:23,593 INFO MainThread:16560 [wandb_init.py:init():981] starting run threads in backend
15
+ 2026-08-16 18:26:23,668 INFO MainThread:16560 [wandb_run.py:_console_start():2626] atexit reg
16
+ 2026-08-16 18:26:23,668 INFO MainThread:16560 [wandb_run.py:_redirect():2476] redirect: wrap_raw
17
+ 2026-08-16 18:26:23,668 INFO MainThread:16560 [wandb_run.py:_redirect():2545] Wrapping output streams.
18
+ 2026-08-16 18:26:23,668 INFO MainThread:16560 [wandb_run.py:_redirect():2568] Redirects installed.
19
+ 2026-08-16 18:26:23,669 INFO MainThread:16560 [wandb_init.py:init():1019] run started, returning control to user process
20
+ 2026-08-16 18:29:15,849 INFO MainThread:16560 [wandb_run.py:_finish():2397] finishing run luequinn-montana-state-university/mixture-transfer/phase1-p1-smoke-sup-15m
21
+ 2026-08-16 18:29:15,849 INFO MainThread:16560 [wandb_run.py:_atexit_cleanup():2593] got exitcode: 0
22
+ 2026-08-16 18:29:15,850 INFO MainThread:16560 [wandb_run.py:_restore():2575] restore
23
+ 2026-08-16 18:29:15,850 INFO MainThread:16560 [wandb_run.py:_restore():2581] restore done
24
+ 2026-08-16 18:29:17,839 INFO MainThread:16560 [wandb_run.py:_footer_sync_info():4025] logging synced files
p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/run-phase1-p1-smoke-sup-15m.wandb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:862a85b5fff40764f5dd3e87dfe4f3fba4a85b25c48b898d20827c3081cfe172
3
+ size 690447
p1-smoke-sup-15m/wandb/run-20260816_182622-phase1-p1-smoke-sup-15m/run-phase1-p1-smoke-sup-15m.wandb.syncstate ADDED
@@ -0,0 +1 @@
 
 
1
+ {"starting_step":0}