w-ahmad commited on
Commit
ef938be
·
verified ·
1 Parent(s): f84afdf

Auto upload 2026-08-06T22:47:10.147161 (part 4)

Browse files
.gitattributes CHANGED
@@ -55,3 +55,4 @@ wandb/run-20260806_221920-2u9w6sh8/run-2u9w6sh8.wandb filter=lfs diff=lfs merge=
55
  out/glu-silu-94L_run/training_log.jsonl filter=lfs diff=lfs merge=lfs -text
56
  wandb/run-20260806_223224-qz489gza/run-qz489gza.wandb filter=lfs diff=lfs merge=lfs -text
57
  out/glu-relu-94L_run/training_log.jsonl filter=lfs diff=lfs merge=lfs -text
 
 
55
  out/glu-silu-94L_run/training_log.jsonl filter=lfs diff=lfs merge=lfs -text
56
  wandb/run-20260806_223224-qz489gza/run-qz489gza.wandb filter=lfs diff=lfs merge=lfs -text
57
  out/glu-relu-94L_run/training_log.jsonl filter=lfs diff=lfs merge=lfs -text
58
+ wandb/run-20260806_224537-4k21flpq/run-4k21flpq.wandb filter=lfs diff=lfs merge=lfs -text
wandb/run-20260806_214555-al1jdpoz/logs/debug-core.log CHANGED
@@ -330,3 +330,15 @@
330
  {"time":"2026-08-06T22:32:24.316080626Z","level":"INFO","msg":"handleInformInit: received","streamId":"qz489gza","id":"22(@)"}
331
  {"time":"2026-08-06T22:32:24.575636983Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"qz489gza","id":"22(@)"}
332
  {"time":"2026-08-06T22:32:30.136334704Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
 
 
 
 
 
 
 
 
 
 
 
 
 
330
  {"time":"2026-08-06T22:32:24.316080626Z","level":"INFO","msg":"handleInformInit: received","streamId":"qz489gza","id":"22(@)"}
331
  {"time":"2026-08-06T22:32:24.575636983Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"qz489gza","id":"22(@)"}
332
  {"time":"2026-08-06T22:32:30.136334704Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
333
+ {"time":"2026-08-06T22:45:25.631649058Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
334
+ {"time":"2026-08-06T22:45:27.004459218Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
335
+ {"time":"2026-08-06T22:45:27.32624292Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"qz489gza","id":"22(@)"}
336
+ {"time":"2026-08-06T22:45:27.328474372Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"qz489gza","id":"22(@)"}
337
+ {"time":"2026-08-06T22:45:29.337669198Z","level":"INFO","msg":"connection: closing","id":"22(@)"}
338
+ {"time":"2026-08-06T22:45:29.337779491Z","level":"INFO","msg":"connection: closed successfully","id":"22(@)"}
339
+ {"time":"2026-08-06T22:45:29.337689564Z","level":"INFO","msg":"processOutgoingData: finished","id":"22(@)"}
340
+ {"time":"2026-08-06T22:45:29.33778783Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"22(@)"}
341
+ {"time":"2026-08-06T22:45:37.17939079Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"23(@)"}
342
+ {"time":"2026-08-06T22:45:37.25952131Z","level":"INFO","msg":"handleInformInit: received","streamId":"4k21flpq","id":"23(@)"}
343
+ {"time":"2026-08-06T22:45:37.520210586Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"4k21flpq","id":"23(@)"}
344
+ {"time":"2026-08-06T22:45:42.854176028Z","level":"INFO","msg":"connection: cancelling request","id":"23(@)","requestId":"pgphnf19ojfr"}
wandb/run-20260806_215402-xj8o3fye/logs/debug-core.log CHANGED
@@ -330,3 +330,15 @@
330
  {"time":"2026-08-06T22:32:24.316080626Z","level":"INFO","msg":"handleInformInit: received","streamId":"qz489gza","id":"22(@)"}
331
  {"time":"2026-08-06T22:32:24.575636983Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"qz489gza","id":"22(@)"}
332
  {"time":"2026-08-06T22:32:30.136334704Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
 
 
 
 
 
 
 
 
 
 
 
 
 
330
  {"time":"2026-08-06T22:32:24.316080626Z","level":"INFO","msg":"handleInformInit: received","streamId":"qz489gza","id":"22(@)"}
331
  {"time":"2026-08-06T22:32:24.575636983Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"qz489gza","id":"22(@)"}
332
  {"time":"2026-08-06T22:32:30.136334704Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
333
+ {"time":"2026-08-06T22:45:25.631649058Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
334
+ {"time":"2026-08-06T22:45:27.004459218Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
335
+ {"time":"2026-08-06T22:45:27.32624292Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"qz489gza","id":"22(@)"}
336
+ {"time":"2026-08-06T22:45:27.328474372Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"qz489gza","id":"22(@)"}
337
+ {"time":"2026-08-06T22:45:29.337669198Z","level":"INFO","msg":"connection: closing","id":"22(@)"}
338
+ {"time":"2026-08-06T22:45:29.337779491Z","level":"INFO","msg":"connection: closed successfully","id":"22(@)"}
339
+ {"time":"2026-08-06T22:45:29.337689564Z","level":"INFO","msg":"processOutgoingData: finished","id":"22(@)"}
340
+ {"time":"2026-08-06T22:45:29.33778783Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"22(@)"}
341
+ {"time":"2026-08-06T22:45:37.17939079Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"23(@)"}
342
+ {"time":"2026-08-06T22:45:37.25952131Z","level":"INFO","msg":"handleInformInit: received","streamId":"4k21flpq","id":"23(@)"}
343
+ {"time":"2026-08-06T22:45:37.520210586Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"4k21flpq","id":"23(@)"}
344
+ {"time":"2026-08-06T22:45:42.854176028Z","level":"INFO","msg":"connection: cancelling request","id":"23(@)","requestId":"pgphnf19ojfr"}
wandb/run-20260806_220210-y74jog3n/logs/debug-core.log CHANGED
@@ -330,3 +330,15 @@
330
  {"time":"2026-08-06T22:32:24.316080626Z","level":"INFO","msg":"handleInformInit: received","streamId":"qz489gza","id":"22(@)"}
331
  {"time":"2026-08-06T22:32:24.575636983Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"qz489gza","id":"22(@)"}
332
  {"time":"2026-08-06T22:32:30.136334704Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
 
 
 
 
 
 
 
 
 
 
 
 
 
330
  {"time":"2026-08-06T22:32:24.316080626Z","level":"INFO","msg":"handleInformInit: received","streamId":"qz489gza","id":"22(@)"}
331
  {"time":"2026-08-06T22:32:24.575636983Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"qz489gza","id":"22(@)"}
332
  {"time":"2026-08-06T22:32:30.136334704Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
333
+ {"time":"2026-08-06T22:45:25.631649058Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
334
+ {"time":"2026-08-06T22:45:27.004459218Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
335
+ {"time":"2026-08-06T22:45:27.32624292Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"qz489gza","id":"22(@)"}
336
+ {"time":"2026-08-06T22:45:27.328474372Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"qz489gza","id":"22(@)"}
337
+ {"time":"2026-08-06T22:45:29.337669198Z","level":"INFO","msg":"connection: closing","id":"22(@)"}
338
+ {"time":"2026-08-06T22:45:29.337779491Z","level":"INFO","msg":"connection: closed successfully","id":"22(@)"}
339
+ {"time":"2026-08-06T22:45:29.337689564Z","level":"INFO","msg":"processOutgoingData: finished","id":"22(@)"}
340
+ {"time":"2026-08-06T22:45:29.33778783Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"22(@)"}
341
+ {"time":"2026-08-06T22:45:37.17939079Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"23(@)"}
342
+ {"time":"2026-08-06T22:45:37.25952131Z","level":"INFO","msg":"handleInformInit: received","streamId":"4k21flpq","id":"23(@)"}
343
+ {"time":"2026-08-06T22:45:37.520210586Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"4k21flpq","id":"23(@)"}
344
+ {"time":"2026-08-06T22:45:42.854176028Z","level":"INFO","msg":"connection: cancelling request","id":"23(@)","requestId":"pgphnf19ojfr"}
wandb/run-20260806_221051-mmhv6fed/logs/debug-core.log CHANGED
@@ -330,3 +330,15 @@
330
  {"time":"2026-08-06T22:32:24.316080626Z","level":"INFO","msg":"handleInformInit: received","streamId":"qz489gza","id":"22(@)"}
331
  {"time":"2026-08-06T22:32:24.575636983Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"qz489gza","id":"22(@)"}
332
  {"time":"2026-08-06T22:32:30.136334704Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
 
 
 
 
 
 
 
 
 
 
 
 
 
330
  {"time":"2026-08-06T22:32:24.316080626Z","level":"INFO","msg":"handleInformInit: received","streamId":"qz489gza","id":"22(@)"}
331
  {"time":"2026-08-06T22:32:24.575636983Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"qz489gza","id":"22(@)"}
332
  {"time":"2026-08-06T22:32:30.136334704Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
333
+ {"time":"2026-08-06T22:45:25.631649058Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
334
+ {"time":"2026-08-06T22:45:27.004459218Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
335
+ {"time":"2026-08-06T22:45:27.32624292Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"qz489gza","id":"22(@)"}
336
+ {"time":"2026-08-06T22:45:27.328474372Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"qz489gza","id":"22(@)"}
337
+ {"time":"2026-08-06T22:45:29.337669198Z","level":"INFO","msg":"connection: closing","id":"22(@)"}
338
+ {"time":"2026-08-06T22:45:29.337779491Z","level":"INFO","msg":"connection: closed successfully","id":"22(@)"}
339
+ {"time":"2026-08-06T22:45:29.337689564Z","level":"INFO","msg":"processOutgoingData: finished","id":"22(@)"}
340
+ {"time":"2026-08-06T22:45:29.33778783Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"22(@)"}
341
+ {"time":"2026-08-06T22:45:37.17939079Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"23(@)"}
342
+ {"time":"2026-08-06T22:45:37.25952131Z","level":"INFO","msg":"handleInformInit: received","streamId":"4k21flpq","id":"23(@)"}
343
+ {"time":"2026-08-06T22:45:37.520210586Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"4k21flpq","id":"23(@)"}
344
+ {"time":"2026-08-06T22:45:42.854176028Z","level":"INFO","msg":"connection: cancelling request","id":"23(@)","requestId":"pgphnf19ojfr"}
wandb/run-20260806_221920-2u9w6sh8/logs/debug-core.log CHANGED
@@ -330,3 +330,15 @@
330
  {"time":"2026-08-06T22:32:24.316080626Z","level":"INFO","msg":"handleInformInit: received","streamId":"qz489gza","id":"22(@)"}
331
  {"time":"2026-08-06T22:32:24.575636983Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"qz489gza","id":"22(@)"}
332
  {"time":"2026-08-06T22:32:30.136334704Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
 
 
 
 
 
 
 
 
 
 
 
 
 
330
  {"time":"2026-08-06T22:32:24.316080626Z","level":"INFO","msg":"handleInformInit: received","streamId":"qz489gza","id":"22(@)"}
331
  {"time":"2026-08-06T22:32:24.575636983Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"qz489gza","id":"22(@)"}
332
  {"time":"2026-08-06T22:32:30.136334704Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
333
+ {"time":"2026-08-06T22:45:25.631649058Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
334
+ {"time":"2026-08-06T22:45:27.004459218Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
335
+ {"time":"2026-08-06T22:45:27.32624292Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"qz489gza","id":"22(@)"}
336
+ {"time":"2026-08-06T22:45:27.328474372Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"qz489gza","id":"22(@)"}
337
+ {"time":"2026-08-06T22:45:29.337669198Z","level":"INFO","msg":"connection: closing","id":"22(@)"}
338
+ {"time":"2026-08-06T22:45:29.337779491Z","level":"INFO","msg":"connection: closed successfully","id":"22(@)"}
339
+ {"time":"2026-08-06T22:45:29.337689564Z","level":"INFO","msg":"processOutgoingData: finished","id":"22(@)"}
340
+ {"time":"2026-08-06T22:45:29.33778783Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"22(@)"}
341
+ {"time":"2026-08-06T22:45:37.17939079Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"23(@)"}
342
+ {"time":"2026-08-06T22:45:37.25952131Z","level":"INFO","msg":"handleInformInit: received","streamId":"4k21flpq","id":"23(@)"}
343
+ {"time":"2026-08-06T22:45:37.520210586Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"4k21flpq","id":"23(@)"}
344
+ {"time":"2026-08-06T22:45:42.854176028Z","level":"INFO","msg":"connection: cancelling request","id":"23(@)","requestId":"pgphnf19ojfr"}
wandb/run-20260806_223224-qz489gza/files/config.yaml ADDED
@@ -0,0 +1,433 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _name_or_path:
2
+ value: ""
3
+ _wandb:
4
+ value:
5
+ cli_version: 0.28.1
6
+ e:
7
+ ecjzoonlwfnmvzqvx0rdavz8i8167qux:
8
+ args:
9
+ - --config
10
+ - configs/baseline.yaml
11
+ - --variants
12
+ - glu-relu-94L
13
+ - --push
14
+ codePath: sweep.py
15
+ codePathLocal: sweep.py
16
+ cpu_count: 112
17
+ cpu_count_logical: 224
18
+ cudaVersion: "12.4"
19
+ disk:
20
+ /:
21
+ total: "1560765693952"
22
+ used: "703834615808"
23
+ email: deepnevro@gmail.com
24
+ executable: /mnt/data/zainulabideen/zain-exp/notebooks/my_env/bin/python
25
+ git:
26
+ commit: 8d6f97d73f5521e4c38c6e1bda59bf8d4b489655
27
+ remote: https://github.com/deepnevro/Activation.git
28
+ gpu: NVIDIA H100 80GB HBM3
29
+ gpu_count: 8
30
+ gpu_nvidia:
31
+ - architecture: Hopper
32
+ cudaCores: 16896
33
+ memoryTotal: "85520809984"
34
+ name: NVIDIA H100 80GB HBM3
35
+ uuid: GPU-39c684a5-fde6-83d7-1663-0859795881ae
36
+ - architecture: Hopper
37
+ cudaCores: 16896
38
+ memoryTotal: "85520809984"
39
+ name: NVIDIA H100 80GB HBM3
40
+ uuid: GPU-68012e5a-38b6-b643-0ca6-62fb66720bf3
41
+ - architecture: Hopper
42
+ cudaCores: 16896
43
+ memoryTotal: "85520809984"
44
+ name: NVIDIA H100 80GB HBM3
45
+ uuid: GPU-132944c4-b689-2b5f-89a4-d730401677ab
46
+ - architecture: Hopper
47
+ cudaCores: 16896
48
+ memoryTotal: "85520809984"
49
+ name: NVIDIA H100 80GB HBM3
50
+ uuid: GPU-2df386cc-6d26-d0e2-7a2d-a057b0d95864
51
+ - architecture: Hopper
52
+ cudaCores: 16896
53
+ memoryTotal: "85520809984"
54
+ name: NVIDIA H100 80GB HBM3
55
+ uuid: GPU-bfa16575-1d94-1aa2-4537-2c93433f42ef
56
+ - architecture: Hopper
57
+ cudaCores: 16896
58
+ memoryTotal: "85520809984"
59
+ name: NVIDIA H100 80GB HBM3
60
+ uuid: GPU-bc6c3e3c-9b90-09ca-c034-774961847c54
61
+ - architecture: Hopper
62
+ cudaCores: 16896
63
+ memoryTotal: "85520809984"
64
+ name: NVIDIA H100 80GB HBM3
65
+ uuid: GPU-00a441e1-7c95-e7d6-4c35-43d6b291aea9
66
+ - architecture: Hopper
67
+ cudaCores: 16896
68
+ memoryTotal: "85520809984"
69
+ name: NVIDIA H100 80GB HBM3
70
+ uuid: GPU-1c4d29a2-4647-6fce-d8fc-0c5ecfbbd6ea
71
+ host: deeplens-k3s-node1
72
+ memory:
73
+ total: "2164089937920"
74
+ os: Linux-5.15.0-126-generic-x86_64-with-glibc2.35
75
+ program: /mnt/data/zainulabideen/zain-exp/notebooks/Activation/sweep.py
76
+ python: CPython 3.11.15
77
+ root: /mnt/data/zainulabideen/zain-exp/notebooks/Activation
78
+ startedAt: "2026-08-06T22:32:24.313688Z"
79
+ writerId: ecjzoonlwfnmvzqvx0rdavz8i8167qux
80
+ m:
81
+ - "1": train/global_step
82
+ "6":
83
+ - 3
84
+ "7": []
85
+ - "2": '*'
86
+ "5": 1
87
+ "6":
88
+ - 1
89
+ "7": []
90
+ python_version: 3.11.15
91
+ t:
92
+ "1":
93
+ - 1
94
+ - 5
95
+ - 11
96
+ - 41
97
+ - 49
98
+ - 51
99
+ - 53
100
+ - 71
101
+ "2":
102
+ - 1
103
+ - 5
104
+ - 11
105
+ - 41
106
+ - 49
107
+ - 51
108
+ - 53
109
+ - 71
110
+ "3":
111
+ - 2
112
+ - 7
113
+ - 13
114
+ - 19
115
+ - 41
116
+ - 62
117
+ - 66
118
+ "4": 3.11.15
119
+ "5": 0.28.1
120
+ "6": 5.15.0.dev0
121
+ "9":
122
+ "1": transformers_trainer
123
+ "12": 0.28.1
124
+ "13": linux-x86_64
125
+ accelerator_config:
126
+ value:
127
+ dispatch_batches: null
128
+ even_batches: true
129
+ gradient_accumulation_kwargs: null
130
+ non_blocking: false
131
+ split_batches: false
132
+ use_seedable_sampler: true
133
+ activation:
134
+ value: relu
135
+ adam_beta1:
136
+ value: 0.9
137
+ adam_beta2:
138
+ value: 0.999
139
+ adam_epsilon:
140
+ value: 1e-08
141
+ architectures:
142
+ value: null
143
+ attention_bias:
144
+ value: false
145
+ attention_dropout:
146
+ value: 0
147
+ auto_find_batch_size:
148
+ value: false
149
+ average_tokens_across_devices:
150
+ value: true
151
+ batch_eval_metrics:
152
+ value: false
153
+ bf16:
154
+ value: true
155
+ bf16_full_eval:
156
+ value: false
157
+ bos_token_id:
158
+ value: 1
159
+ chunk_size_feed_forward:
160
+ value: 0
161
+ data_seed:
162
+ value: 42
163
+ dataloader_drop_last:
164
+ value: false
165
+ dataloader_in_order:
166
+ value: true
167
+ dataloader_multiprocessing_context:
168
+ value: null
169
+ dataloader_num_workers:
170
+ value: 0
171
+ dataloader_persistent_workers:
172
+ value: false
173
+ dataloader_pin_memory:
174
+ value: true
175
+ dataloader_prefetch_factor:
176
+ value: null
177
+ ddp_backend:
178
+ value: null
179
+ ddp_broadcast_buffers:
180
+ value: null
181
+ ddp_bucket_cap_mb:
182
+ value: null
183
+ ddp_find_unused_parameters:
184
+ value: null
185
+ ddp_static_graph:
186
+ value: null
187
+ ddp_timeout:
188
+ value: 1800
189
+ debug:
190
+ value: []
191
+ deepspeed:
192
+ value: null
193
+ disable_tqdm:
194
+ value: false
195
+ do_eval:
196
+ value: true
197
+ do_predict:
198
+ value: false
199
+ do_train:
200
+ value: false
201
+ dtype:
202
+ value: null
203
+ enable_jit_checkpoint:
204
+ value: false
205
+ eos_token_id:
206
+ value: 2
207
+ eval_accumulation_steps:
208
+ value: null
209
+ eval_delay:
210
+ value: 0
211
+ eval_do_concat_batches:
212
+ value: true
213
+ eval_on_start:
214
+ value: false
215
+ eval_steps:
216
+ value: 200
217
+ eval_strategy:
218
+ value: steps
219
+ eval_use_gather_object:
220
+ value: false
221
+ fp16:
222
+ value: false
223
+ fp16_full_eval:
224
+ value: false
225
+ fsdp:
226
+ value: null
227
+ fsdp_config:
228
+ value: null
229
+ full_determinism:
230
+ value: false
231
+ gradient_accumulation_steps:
232
+ value: 1
233
+ gradient_checkpointing:
234
+ value: false
235
+ gradient_checkpointing_kwargs:
236
+ value: null
237
+ greater_is_better:
238
+ value: null
239
+ head_dim:
240
+ value: 32
241
+ hidden_act:
242
+ value: silu
243
+ hidden_size:
244
+ value: 128
245
+ hub_always_push:
246
+ value: false
247
+ hub_model_id:
248
+ value: w-ahmad/ACTio-glu-relu-94L
249
+ hub_private_repo:
250
+ value: null
251
+ hub_revision:
252
+ value: null
253
+ hub_strategy:
254
+ value: every_save
255
+ hub_token:
256
+ value: <HUB_TOKEN>
257
+ id2label:
258
+ value:
259
+ "0": LABEL_0
260
+ "1": LABEL_1
261
+ ignore_data_skip:
262
+ value: false
263
+ include_for_metrics:
264
+ value: []
265
+ include_num_input_tokens_seen:
266
+ value: "no"
267
+ initializer_range:
268
+ value: 0.02
269
+ intermediate_size:
270
+ value: 256
271
+ is_encoder_decoder:
272
+ value: false
273
+ label_names:
274
+ value: null
275
+ label_smoothing_factor:
276
+ value: 0
277
+ label2id:
278
+ value:
279
+ LABEL_0: 0
280
+ LABEL_1: 1
281
+ learning_rate:
282
+ value: 0.0003
283
+ length_column_name:
284
+ value: length
285
+ liger_kernel_config:
286
+ value: null
287
+ load_best_model_at_end:
288
+ value: false
289
+ local_rank:
290
+ value: -1
291
+ log_level:
292
+ value: passive
293
+ log_level_replica:
294
+ value: warning
295
+ log_on_each_node:
296
+ value: true
297
+ logging_first_step:
298
+ value: false
299
+ logging_nan_inf_filter:
300
+ value: true
301
+ logging_steps:
302
+ value: 20
303
+ logging_strategy:
304
+ value: steps
305
+ lr_scheduler_kwargs:
306
+ value: null
307
+ lr_scheduler_type:
308
+ value: constant
309
+ max_grad_norm:
310
+ value: 1
311
+ max_position_embeddings:
312
+ value: 512
313
+ max_steps:
314
+ value: 2000
315
+ metric_for_best_model:
316
+ value: null
317
+ mlp_bias:
318
+ value: false
319
+ mlp_type:
320
+ value: glu
321
+ model/num_parameters:
322
+ value: 15949440
323
+ model_type:
324
+ value: tiny_llama
325
+ neftune_noise_alpha:
326
+ value: null
327
+ num_attention_heads:
328
+ value: 4
329
+ num_hidden_layers:
330
+ value: 94
331
+ num_key_value_heads:
332
+ value: 4
333
+ num_train_epochs:
334
+ value: 1
335
+ optim:
336
+ value: adamw_torch
337
+ optim_args:
338
+ value: null
339
+ optim_target_modules:
340
+ value: null
341
+ output_attentions:
342
+ value: false
343
+ output_dir:
344
+ value: out/glu-relu-94L_run
345
+ output_hidden_states:
346
+ value: false
347
+ pad_token_id:
348
+ value: 0
349
+ parallelism_config:
350
+ value: null
351
+ per_device_eval_batch_size:
352
+ value: 64
353
+ per_device_train_batch_size:
354
+ value: 64
355
+ prediction_loss_only:
356
+ value: false
357
+ pretraining_tp:
358
+ value: 1
359
+ problem_type:
360
+ value: null
361
+ project:
362
+ value: huggingface
363
+ push_to_hub:
364
+ value: true
365
+ remove_unused_columns:
366
+ value: false
367
+ report_to:
368
+ value:
369
+ - wandb
370
+ restore_callback_states_from_checkpoint:
371
+ value: false
372
+ resume_from_checkpoint:
373
+ value: null
374
+ return_dict:
375
+ value: true
376
+ rms_norm_eps:
377
+ value: 1e-06
378
+ rope_parameters:
379
+ value:
380
+ rope_theta: 10000
381
+ rope_type: default
382
+ run_name:
383
+ value: LM-glu-relu-94L-15.9M-20260806-223223
384
+ save_on_each_node:
385
+ value: false
386
+ save_only_model:
387
+ value: false
388
+ save_steps:
389
+ value: 500
390
+ save_strategy:
391
+ value: steps
392
+ save_total_limit:
393
+ value: null
394
+ seed:
395
+ value: 42
396
+ skip_memory_metrics:
397
+ value: true
398
+ tf32:
399
+ value: null
400
+ tie_word_embeddings:
401
+ value: true
402
+ tokenizer_name:
403
+ value: w-ahmad/tiny-stories-tokenizer
404
+ torch_compile:
405
+ value: false
406
+ torch_compile_backend:
407
+ value: null
408
+ torch_compile_mode:
409
+ value: null
410
+ torch_empty_cache_steps:
411
+ value: null
412
+ trackio_bucket_id:
413
+ value: null
414
+ trackio_space_id:
415
+ value: null
416
+ trackio_static_space_id:
417
+ value: null
418
+ train_sampling_strategy:
419
+ value: random
420
+ transformers_version:
421
+ value: 5.15.0.dev0
422
+ use_cache:
423
+ value: false
424
+ use_cpu:
425
+ value: false
426
+ use_liger_kernel:
427
+ value: false
428
+ vocab_size:
429
+ value: 4096
430
+ warmup_steps:
431
+ value: 0
432
+ weight_decay:
433
+ value: 0.01
wandb/run-20260806_223224-qz489gza/files/output.log CHANGED
@@ -102,7 +102,71 @@ Writing model shards: 100%|█████████████████
102
  - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
103
  - If you are not the owner of the model architecture class, please contact the model code owner to update it.
104
  Writing model shards: 100%|██████████████████████| 1/1 [00:00<00:00, 15.63it/s]
105
- 78%|█████████████████████████████| 1562/2000 [09:40<02:04, 3.52it/s]
106
  {'loss': '0.3087', 'grad_norm': '0.3066', 'learning_rate': '0.0003', 'epoch': '0.1025', 'train/total_time_seconds': '365.6', 'train/time_per_step_avg': '0.2414', 'train/epoch_time_elapsed': '568', 'train/estimated_remaining_minutes': '1.924'}
107
  {'loss': '0.3063', 'grad_norm': '0.2656', 'learning_rate': '0.0003', 'epoch': '0.1038', 'train/total_time_seconds': '370.3', 'train/time_per_step_avg': '0.2383', 'train/epoch_time_elapsed': '573.7', 'train/estimated_remaining_minutes': '1.843'}
108
  {'loss': '0.3774', 'grad_norm': '2.625', 'learning_rate': '0.0003', 'epoch': '0.1052', 'train/total_time_seconds': '375', 'train/time_per_step_avg': '0.2381', 'train/epoch_time_elapsed': '579.4', 'train/estimated_remaining_minutes': '1.763'}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
102
  - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
103
  - If you are not the owner of the model architecture class, please contact the model code owner to update it.
104
  Writing model shards: 100%|██████████████████████| 1/1 [00:00<00:00, 15.63it/s]
105
+ 80%|██████████████████████████████▍ | 1600/2000 [10:08<01:58, 3.39it/s]/mnt/data/zainulabideen/zain-exp/notebooks/Activation/exp.py:464: UserWarning: std(): degrees of freedom is <= 0. Correction should be strictly less than the reduction factor (input numel divided by output numel). (Triggered internally at /pytorch/aten/src/ATen/native/ReduceOps.cpp:1831.)
106
  {'loss': '0.3087', 'grad_norm': '0.3066', 'learning_rate': '0.0003', 'epoch': '0.1025', 'train/total_time_seconds': '365.6', 'train/time_per_step_avg': '0.2414', 'train/epoch_time_elapsed': '568', 'train/estimated_remaining_minutes': '1.924'}
107
  {'loss': '0.3063', 'grad_norm': '0.2656', 'learning_rate': '0.0003', 'epoch': '0.1038', 'train/total_time_seconds': '370.3', 'train/time_per_step_avg': '0.2383', 'train/epoch_time_elapsed': '573.7', 'train/estimated_remaining_minutes': '1.843'}
108
  {'loss': '0.3774', 'grad_norm': '2.625', 'learning_rate': '0.0003', 'epoch': '0.1052', 'train/total_time_seconds': '375', 'train/time_per_step_avg': '0.2381', 'train/epoch_time_elapsed': '579.4', 'train/estimated_remaining_minutes': '1.763'}
109
+ {'loss': '0.3463', 'grad_norm': '1.188', 'learning_rate': '0.0003', 'epoch': '0.1065', 'train/total_time_seconds': '379.7', 'train/time_per_step_avg': '0.2376', 'train/epoch_time_elapsed': '585', 'train/estimated_remaining_minutes': '1.682'}
110
+ {'loss': '0.3228', 'grad_norm': '2.109', 'learning_rate': '0.0003', 'epoch': '0.1079', 'train/total_time_seconds': '384.4', 'train/time_per_step_avg': '0.2362', 'train/epoch_time_elapsed': '590.8', 'train/estimated_remaining_minutes': '1.602'}
111
+ "std": tensor.std().item(),
112
+ {'eval_loss': '0.3453', 'eval_runtime': '17.22', 'eval_samples_per_second': '553.4', 'eval_steps_per_second': '8.654', 'epoch': '0.1079', 'train/total_time_seconds': '384.4', 'train/time_per_step_avg': '0.2362', 'train/epoch_time_elapsed': '608', 'train/estimated_remaining_minutes': '1.602'}
113
+ 100%|██████████████████████████████████████| 2000/2000 [12:39<00:00, 3.53it/s][transformers] TinyLlamaForCausalLM has generative capabilities, as `prepare_inputs_for_generation` is explicitly defined. However, it doesn't directly inherit from `GenerationMixin`. From 👉v4.50👈 onwards, `PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions.
114
+ {'loss': '0.3181', 'grad_norm': '0.3555', 'learning_rate': '0.0003', 'epoch': '0.1092', 'train/total_time_seconds': '389.7', 'train/time_per_step_avg': '0.2415', 'train/epoch_time_elapsed': '614.6', 'train/estimated_remaining_minutes': '1.524', 'train/global/act/norm': '5.166e+04', 'train/global/act/mean': '-0.06026', 'train/global/act/std': '0', 'train/global/act/max_abs': '11.19', 'train/global/act/frac_near_dtype_limit': '0', 'train/global/act/frac_near_user_limit': '0', 'train/global/grad/norm': '1.518', 'train/global/grad/mean': '-9.89e-08', 'train/global/grad/std': '0.0003803', 'train/global/grad/max_abs': '0.04883', 'train/global/grad/frac_near_dtype_limit': '0', 'train/global/grad/frac_near_user_limit': '0', 'train/global/param/norm': '187.4', 'train/global/param/mean': '0.001591', 'train/global/param/std': '0.0469', 'train/global/param/max_abs': '1', 'train/global/param/frac_near_dtype_limit': '0', 'train/global/param/frac_near_user_limit': '0', 'train/layer_model_layers_65/act/norm': '5422', 'train/layer_model_layers_65/act/mean': '-0.04994', 'train/layer_model_layers_65/act/std': '0.7069', 'train/layer_model_layers_65/act/max_abs': '7.031', 'train/layer_model_layers_65/act/frac_near_dtype_limit': '0', 'train/layer_model_layers_65/act/frac_near_user_limit': '0', 'train/layer_model_layers_65/grad/norm': '0.1005', 'train/layer_model_layers_65/grad/mean': '-1.14e-06', 'train/layer_model_layers_65/grad/std': '0.0002481', 'train/layer_model_layers_65/grad/max_abs': '0.005402', 'train/layer_model_layers_65/grad/frac_near_dtype_limit': '0', 'train/layer_model_layers_65/grad/frac_near_user_limit': '0', 'train/layer_model_layers_38/act/norm': '3614', 'train/layer_model_layers_38/act/mean': '-0.02015', 'train/layer_model_layers_38/act/std': '0.4714', 'train/layer_model_layers_38/act/max_abs': '4.781', 'train/layer_model_layers_38/act/frac_near_dtype_limit': '0', 'train/layer_model_layers_38/act/frac_near_user_limit': '0', 'train/layer_model_layers_38/grad/norm': '0.09342', 'train/layer_model_layers_38/grad/mean': '8.76e-09', 'train/layer_model_layers_38/grad/std': '0.0002307', 'train/layer_model_layers_38/grad/max_abs': '0.005737', 'train/layer_model_layers_38/grad/frac_near_dtype_limit': '0', 'train/layer_model_layers_38/grad/frac_near_user_limit': '0', 'train/layer_model_layers_20/act/norm': '3583', 'train/layer_model_layers_20/act/mean': '-0.0219', 'train/layer_model_layers_20/act/std': '0.4674', 'train/layer_model_layers_20/act/max_abs': '4.125', 'train/layer_model_layers_20/act/frac_near_dtype_limit': '0', 'train/layer_model_layers_20/act/frac_near_user_limit': '0', 'train/layer_model_layers_20/grad/norm': '0.07125', 'train/layer_model_layers_20/grad/mean': '9.208e-08', 'train/layer_model_layers_20/grad/std': '0.0001758', 'train/layer_model_layers_20/grad/max_abs': '0.00415', 'train/layer_model_layers_20/grad/frac_near_dtype_limit': '0', 'train/layer_model_layers_20/grad/frac_near_user_limit': '0', 'train/layer_model_layers_3/act/norm': '5163', 'train/layer_model_layers_3/act/mean': '-0.02824', 'train/layer_model_layers_3/act/std': '0.6726', 'train/layer_model_layers_3/act/max_abs': '5.719', 'train/layer_model_layers_3/act/frac_near_dtype_limit': '0', 'train/layer_model_layers_3/act/frac_near_user_limit': '0', 'train/layer_model_layers_3/grad/norm': '0.3937', 'train/layer_model_layers_3/grad/mean': '1.61e-06', 'train/layer_model_layers_3/grad/std': '0.0009718', 'train/layer_model_layers_3/grad/max_abs': '0.01538', 'train/layer_model_layers_3/grad/frac_near_dtype_limit': '0', 'train/layer_model_layers_3/grad/frac_near_user_limit': '0', 'train/layer__model_layers_3/param/norm': '18.36', 'train/layer__model_layers_3/param/mean': '0.001608', 'train/layer__model_layers_3/param/std': '0.04529', 'train/layer__model_layers_3/param/max_abs': '1', 'train/layer__model_layers_3/param/frac_near_dtype_limit': '0', 'train/layer__model_layers_3/param/frac_near_user_limit': '0', 'train/layer_model_layers_2/act/norm': '4131', 'train/layer_model_layers_2/act/mean': '0.00627', 'train/layer_model_layers_2/act/std': '0.5386', 'train/laye
115
+ {'loss': '0.303', 'grad_norm': '0.2734', 'learning_rate': '0.0003', 'epoch': '0.1105', 'train/total_time_seconds': '394.4', 'train/time_per_step_avg': '0.2411', 'train/epoch_time_elapsed': '620.4', 'train/estimated_remaining_minutes': '1.443'}
116
+ {'loss': '0.2965', 'grad_norm': '0.2344', 'learning_rate': '0.0003', 'epoch': '0.1119', 'train/total_time_seconds': '399.2', 'train/time_per_step_avg': '0.2416', 'train/epoch_time_elapsed': '626.3', 'train/estimated_remaining_minutes': '1.363'}
117
+ {'loss': '0.2939', 'grad_norm': '0.2314', 'learning_rate': '0.0003', 'epoch': '0.1132', 'train/total_time_seconds': '403.8', 'train/time_per_step_avg': '0.2414', 'train/epoch_time_elapsed': '631.9', 'train/estimated_remaining_minutes': '1.282'}
118
+ {'loss': '0.2931', 'grad_norm': '0.2451', 'learning_rate': '0.0003', 'epoch': '0.1146', 'train/total_time_seconds': '408.5', 'train/time_per_step_avg': '0.2405', 'train/epoch_time_elapsed': '637.5', 'train/estimated_remaining_minutes': '1.201'}
119
+ {'loss': '0.2893', 'grad_norm': '0.2275', 'learning_rate': '0.0003', 'epoch': '0.1159', 'train/total_time_seconds': '413.2', 'train/time_per_step_avg': '0.2345', 'train/epoch_time_elapsed': '643.2', 'train/estimated_remaining_minutes': '1.121'}
120
+ {'loss': '0.288', 'grad_norm': '0.2373', 'learning_rate': '0.0003', 'epoch': '0.1173', 'train/total_time_seconds': '417.8', 'train/time_per_step_avg': '0.2342', 'train/epoch_time_elapsed': '648.8', 'train/estimated_remaining_minutes': '1.041'}
121
+ {'loss': '0.2852', 'grad_norm': '0.2334', 'learning_rate': '0.0003', 'epoch': '0.1186', 'train/total_time_seconds': '422.7', 'train/time_per_step_avg': '0.2356', 'train/epoch_time_elapsed': '654.7', 'train/estimated_remaining_minutes': '0.9608'}
122
+ {'loss': '0.2853', 'grad_norm': '0.2393', 'learning_rate': '0.0003', 'epoch': '0.12', 'train/total_time_seconds': '427.5', 'train/time_per_step_avg': '0.2363', 'train/epoch_time_elapsed': '660.4', 'train/estimated_remaining_minutes': '0.8805'}
123
+ {'loss': '0.2843', 'grad_norm': '0.2246', 'learning_rate': '0.0003', 'epoch': '0.1213', 'train/total_time_seconds': '432.1', 'train/time_per_step_avg': '0.2364', 'train/epoch_time_elapsed': '666', 'train/estimated_remaining_minutes': '0.8002'}
124
+ - If you're using `trust_remote_code=True`, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
125
+ {'eval_loss': '0.2832', 'eval_runtime': '17.24', 'eval_samples_per_second': '552.7', 'eval_steps_per_second': '8.644', 'epoch': '0.1213', 'train/total_time_seconds': '432.1', 'train/time_per_step_avg': '0.2364', 'train/epoch_time_elapsed': '683.3', 'train/estimated_remaining_minutes': '0.8002'}
126
+ {'loss': '0.2834', 'grad_norm': '0.2324', 'learning_rate': '0.0003', 'epoch': '0.1227', 'train/total_time_seconds': '437.4', 'train/time_per_step_avg': '0.2422', 'train/epoch_time_elapsed': '689.8', 'train/estimated_remaining_minutes': '0.721', 'train/global/act/norm': '5.185e+04', 'train/global/act/mean': '-0.06141', 'train/global/act/std': '0', 'train/global/act/max_abs': '11.38', 'train/global/act/frac_near_dtype_limit': '0', 'train/global/act/frac_near_user_limit': '0', 'train/global/grad/norm': '0.2333', 'train/global/grad/mean': '-1.088e-07', 'train/global/grad/std': '5.835e-05', 'train/global/grad/max_abs': '0.01904', 'train/global/grad/frac_near_dtype_limit': '0', 'train/global/grad/frac_near_user_limit': '0', 'train/global/param/norm': '187.7', 'train/global/param/mean': '0.001591', 'train/global/param/std': '0.04697', 'train/global/param/max_abs': '1', 'train/global/param/frac_near_dtype_limit': '0', 'train/global/param/frac_near_user_limit': '0', 'train/layer_model_layers_65/act/norm': '5472', 'train/layer_model_layers_65/act/mean': '-0.05204', 'train/layer_model_layers_65/act/std': '0.7133', 'train/layer_model_layers_65/act/max_abs': '7', 'train/layer_model_layers_65/act/frac_near_dtype_limit': '0', 'train/layer_model_layers_65/act/frac_near_user_limit': '0', 'train/layer_model_layers_65/grad/norm': '0.007946', 'train/layer_model_layers_65/grad/mean': '6.453e-08', 'train/layer_model_layers_65/grad/std': '1.96e-05', 'train/layer_model_layers_65/grad/max_abs': '0.0002956', 'train/layer_model_layers_65/grad/frac_near_dtype_limit': '0', 'train/layer_model_layers_65/grad/frac_near_user_limit': '0', 'train/layer_model_layers_38/act/norm': '3614', 'train/layer_model_layers_38/act/mean': '-0.02033', 'train/layer_model_layers_38/act/std': '0.4713', 'train/layer_model_layers_38/act/max_abs': '4.719', 'train/layer_model_layers_38/act/frac_near_dtype_limit': '0', 'train/layer_model_layers_38/act/frac_near_user_limit': '0', 'train/layer_model_layers_38/grad/norm': '0.006327', 'train/layer_model_layers_38/grad/mean': '1.42e-08', 'train/layer_model_layers_38/grad/std': '1.563e-05', 'train/layer_model_layers_38/grad/max_abs': '0.0003738', 'train/layer_model_layers_38/grad/frac_near_dtype_limit': '0', 'train/layer_model_layers_38/grad/frac_near_user_limit': '0', 'train/layer_model_layers_20/act/norm': '3585', 'train/layer_model_layers_20/act/mean': '-0.023', 'train/layer_model_layers_20/act/std': '0.4675', 'train/layer_model_layers_20/act/max_abs': '4.188', 'train/layer_model_layers_20/act/frac_near_dtype_limit': '0', 'train/layer_model_layers_20/act/frac_near_user_limit': '0', 'train/layer_model_layers_20/grad/norm': '0.005027', 'train/layer_model_layers_20/grad/mean': '-1.987e-08', 'train/layer_model_layers_20/grad/std': '1.241e-05', 'train/layer_model_layers_20/grad/max_abs': '0.0002747', 'train/layer_model_layers_20/grad/frac_near_dtype_limit': '0', 'train/layer_model_layers_20/grad/frac_near_user_limit': '0', 'train/layer_model_layers_3/act/norm': '5290', 'train/layer_model_layers_3/act/mean': '-0.02852', 'train/layer_model_layers_3/act/std': '0.6893', 'train/layer_model_layers_3/act/max_abs': '5.875', 'train/layer_model_layers_3/act/frac_near_dtype_limit': '0', 'train/layer_model_layers_3/act/frac_near_user_limit': '0', 'train/layer_model_layers_3/grad/norm': '0.02502', 'train/layer_model_layers_3/grad/mean': '-2.554e-07', 'train/layer_model_layers_3/grad/std': '6.179e-05', 'train/layer_model_layers_3/grad/max_abs': '0.001144', 'train/layer_model_layers_3/grad/frac_near_dtype_limit': '0', 'train/layer_model_layers_3/grad/frac_near_user_limit': '0', 'train/layer__model_layers_3/param/norm': '18.37', 'train/layer__model_layers_3/param/mean': '0.001608', 'train/layer__model_layers_3/param/std': '0.04532', 'train/layer__model_layers_3/param/max_abs': '1', 'train/layer__model_layers_3/param/frac_near_dtype_limit': '0', 'train/layer__model_layers_3/param/frac_near_user_limit': '0', 'train/layer_model_layers_2/act/norm': '4187', 'train/layer_model_layers_2/act/mean': '0.007595', 'train/layer_model_layers_2/act/std': '0.5457',
127
+ {'loss': '0.2765', 'grad_norm': '0.2256', 'learning_rate': '0.0003', 'epoch': '0.124', 'train/total_time_seconds': '442', 'train/time_per_step_avg': '0.2424', 'train/epoch_time_elapsed': '695.7', 'train/estimated_remaining_minutes': '0.6407'}
128
+ {'loss': '0.2756', 'grad_norm': '0.248', 'learning_rate': '0.0003', 'epoch': '0.1254', 'train/total_time_seconds': '446.8', 'train/time_per_step_avg': '0.2411', 'train/epoch_time_elapsed': '701.6', 'train/estimated_remaining_minutes': '0.5606'}
129
+ {'loss': '0.2746', 'grad_norm': '0.2354', 'learning_rate': '0.0003', 'epoch': '0.1267', 'train/total_time_seconds': '451.5', 'train/time_per_step_avg': '0.2406', 'train/epoch_time_elapsed': '707.2', 'train/estimated_remaining_minutes': '0.4803'}
130
+ {'loss': '0.2735', 'grad_norm': '0.2432', 'learning_rate': '0.0003', 'epoch': '0.1281', 'train/total_time_seconds': '456.2', 'train/time_per_step_avg': '0.241', 'train/epoch_time_elapsed': '712.9', 'train/estimated_remaining_minutes': '0.4002'}
131
+ {'loss': '0.2704', 'grad_norm': '0.2393', 'learning_rate': '0.0003', 'epoch': '0.1294', 'train/total_time_seconds': '461', 'train/time_per_step_avg': '0.2358', 'train/epoch_time_elapsed': '718.6', 'train/estimated_remaining_minutes': '0.3201'}
132
+ {'loss': '0.2709', 'grad_norm': '0.2305', 'learning_rate': '0.0003', 'epoch': '0.1308', 'train/total_time_seconds': '465.7', 'train/time_per_step_avg': '0.2364', 'train/epoch_time_elapsed': '724.3', 'train/estimated_remaining_minutes': '0.24'}
133
+ {'loss': '0.2666', 'grad_norm': '0.2266', 'learning_rate': '0.0003', 'epoch': '0.1321', 'train/total_time_seconds': '470.4', 'train/time_per_step_avg': '0.2355', 'train/epoch_time_elapsed': '730', 'train/estimated_remaining_minutes': '0.16'}
134
+ {'loss': '0.2679', 'grad_norm': '0.2305', 'learning_rate': '0.0003', 'epoch': '0.1335', 'train/total_time_seconds': '475.1', 'train/time_per_step_avg': '0.2363', 'train/epoch_time_elapsed': '735.7', 'train/estimated_remaining_minutes': '0.07999'}
135
+ {'loss': '0.266', 'grad_norm': '0.2236', 'learning_rate': '0.0003', 'epoch': '0.1348', 'train/total_time_seconds': '479.9', 'train/time_per_step_avg': '0.2369', 'train/epoch_time_elapsed': '741.5', 'train/estimated_remaining_minutes': '0'}
136
+ {'eval_loss': '0.2678', 'eval_runtime': '17.38', 'eval_samples_per_second': '548.2', 'eval_steps_per_second': '8.573', 'epoch': '0.1348', 'train/total_time_seconds': '479.9', 'train/time_per_step_avg': '0.2369', 'train/epoch_time_elapsed': '758.9', 'train/estimated_remaining_minutes': '0'}
137
+ - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
138
+ - If you are not the owner of the model architecture class, please contact the model code owner to update it.
139
+ Writing model shards: 100%|██████████████████████| 1/1 [00:00<00:00, 14.56it/s]
140
+ 100%|██████████████████████████████████████| 2000/2000 [12:40<00:00, 2.63it/s]
141
+ {'train_runtime': '760.1', 'train_samples_per_second': '168.4', 'train_steps_per_second': '2.631', 'train_loss': '1.392', 'epoch': '0.1348', 'train/total_time_seconds': '479.9', 'train/time_per_step_avg': '0.2369', 'train/epoch_time_elapsed': '759.2', 'train/estimated_remaining_minutes': '0'}
142
+ 100%|████████████████████████████████████████| 149/149 [00:17<00:00, 8.54it/s]
143
+ [transformers] TinyLlamaForCausalLM has generative capabilities, as `prepare_inputs_for_generation` is explicitly defined. However, it doesn't directly inherit from `GenerationMixin`. From 👉v4.50👈 onwards, `PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions.
144
+ - If you're using `trust_remote_code=True`, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
145
+ - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
146
+ - If you are not the owner of the model architecture class, please contact the model code owner to update it.
147
+ Writing model shards: 100%|██████████████████████| 1/1 [00:00<00:00, 15.95it/s]
148
+ [transformers] TinyLlamaForCausalLM has generative capabilities, as `prepare_inputs_for_generation` is explicitly defined. However, it doesn't directly inherit from `GenerationMixin`. From 👉v4.50👈 onwards, `PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions.
149
+ - If you're using `trust_remote_code=True`, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
150
+ - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
151
+ - If you are not the owner of the model architecture class, please contact the model code owner to update it.
152
+ Writing model shards: 100%|██████████████████████| 1/1 [00:00<00:00, 17.53it/s]
153
+ Found 7 files to upload
154
+  Preparing ████████████████████ 7 / 7 ✓
155
+  Uploading ████████████████████ 3 / 3 files 21.4kB ✓
156
+  Committing ████████░░░░░░░░░░░░ 3 / 7
157
+  Preparing ████████████████████ 7 / 7 ✓
158
+  Uploading ████████████████████ 3 / 3 files 21.4kB ✓
159
+  Committing ████████░░░░░░░░░░░░ 3 / 7
160
+  Preparing ████████████████████ 7 / 7 ✓
161
+  Uploading ████████████████████ 3 / 3 files 21.4kB ✓
162
+  Committing ████████████████████ 7 / 7 ✓
163
+ [transformers] TinyLlamaForCausalLM has generative capabilities, as `prepare_inputs_for_generation` is explicitly defined. However, it doesn't directly inherit from `GenerationMixin`. From 👉v4.50👈 onwards, `PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions.
164
+ - If you're using `trust_remote_code=True`, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes
165
+ - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).
166
+ - If you are not the owner of the model architecture class, please contact the model code owner to update it.
167
+ Writing model shards: 100%|██████████████████████| 1/1 [00:00<00:00, 16.45it/s]
168
+ Found 7 files to upload
169
+  Preparing ████████████████████ 7 / 7 ✓
170
+  Uploading ████████████████████ 3 / 3 files ✓
171
+  Committing ████████████████████ 7 / 7 ✓
172
+ No files have been modified since last commit. Skipping to prevent empty commit.
wandb/run-20260806_223224-qz489gza/files/wandb-summary.json ADDED
The diff for this file is too large to render. See raw diff
 
wandb/run-20260806_223224-qz489gza/logs/debug-core.log CHANGED
@@ -330,3 +330,15 @@
330
  {"time":"2026-08-06T22:32:24.316080626Z","level":"INFO","msg":"handleInformInit: received","streamId":"qz489gza","id":"22(@)"}
331
  {"time":"2026-08-06T22:32:24.575636983Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"qz489gza","id":"22(@)"}
332
  {"time":"2026-08-06T22:32:30.136334704Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
 
 
 
 
 
 
 
 
 
 
 
 
 
330
  {"time":"2026-08-06T22:32:24.316080626Z","level":"INFO","msg":"handleInformInit: received","streamId":"qz489gza","id":"22(@)"}
331
  {"time":"2026-08-06T22:32:24.575636983Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"qz489gza","id":"22(@)"}
332
  {"time":"2026-08-06T22:32:30.136334704Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
333
+ {"time":"2026-08-06T22:45:25.631649058Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
334
+ {"time":"2026-08-06T22:45:27.004459218Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
335
+ {"time":"2026-08-06T22:45:27.32624292Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"qz489gza","id":"22(@)"}
336
+ {"time":"2026-08-06T22:45:27.328474372Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"qz489gza","id":"22(@)"}
337
+ {"time":"2026-08-06T22:45:29.337669198Z","level":"INFO","msg":"connection: closing","id":"22(@)"}
338
+ {"time":"2026-08-06T22:45:29.337779491Z","level":"INFO","msg":"connection: closed successfully","id":"22(@)"}
339
+ {"time":"2026-08-06T22:45:29.337689564Z","level":"INFO","msg":"processOutgoingData: finished","id":"22(@)"}
340
+ {"time":"2026-08-06T22:45:29.33778783Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"22(@)"}
341
+ {"time":"2026-08-06T22:45:37.17939079Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"23(@)"}
342
+ {"time":"2026-08-06T22:45:37.25952131Z","level":"INFO","msg":"handleInformInit: received","streamId":"4k21flpq","id":"23(@)"}
343
+ {"time":"2026-08-06T22:45:37.520210586Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"4k21flpq","id":"23(@)"}
344
+ {"time":"2026-08-06T22:45:42.854176028Z","level":"INFO","msg":"connection: cancelling request","id":"23(@)","requestId":"pgphnf19ojfr"}
wandb/run-20260806_223224-qz489gza/logs/debug-internal.log CHANGED
@@ -107,3 +107,39 @@
107
  {"time":"2026-08-06T22:41:41.304944714Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
108
  {"time":"2026-08-06T22:41:55.346282761Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":80,"history_lines":3,"events_offset":74,"events_lines":2,"console_offset":72,"console_lines":1}
109
  {"time":"2026-08-06T22:41:56.384195329Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
107
  {"time":"2026-08-06T22:41:41.304944714Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
108
  {"time":"2026-08-06T22:41:55.346282761Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":80,"history_lines":3,"events_offset":74,"events_lines":2,"console_offset":72,"console_lines":1}
109
  {"time":"2026-08-06T22:41:56.384195329Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
110
+ {"time":"2026-08-06T22:42:10.350347618Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":83,"history_lines":3,"events_offset":76,"events_lines":2,"console_offset":77,"console_lines":32}
111
+ {"time":"2026-08-06T22:42:11.496568143Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
112
+ {"time":"2026-08-06T22:42:25.347536858Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":86,"history_lines":1,"events_offset":78,"events_lines":2,"console_offset":104,"console_lines":1}
113
+ {"time":"2026-08-06T22:42:26.4688044Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
114
+ {"time":"2026-08-06T22:42:40.373881079Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":87,"history_lines":2,"events_offset":80,"events_lines":2,"console_offset":104,"console_lines":1}
115
+ {"time":"2026-08-06T22:42:41.630808461Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
116
+ {"time":"2026-08-06T22:42:55.346054795Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":89,"history_lines":2,"events_offset":82,"events_lines":2,"console_offset":109,"console_lines":7}
117
+ {"time":"2026-08-06T22:42:56.366180856Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
118
+ {"time":"2026-08-06T22:43:10.345537927Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":91,"history_lines":3,"events_offset":84,"events_lines":2,"console_offset":112,"console_lines":1}
119
+ {"time":"2026-08-06T22:43:11.4882937Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
120
+ {"time":"2026-08-06T22:43:25.350760968Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":94,"history_lines":2,"events_offset":86,"events_lines":2,"console_offset":112,"console_lines":1}
121
+ {"time":"2026-08-06T22:43:26.421059533Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
122
+ {"time":"2026-08-06T22:43:40.346518512Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":96,"history_lines":2,"events_offset":88,"events_lines":2,"console_offset":112,"console_lines":1}
123
+ {"time":"2026-08-06T22:43:41.384258079Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
124
+ {"time":"2026-08-06T22:43:55.370407819Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":98,"history_lines":2,"events_offset":90,"events_lines":2,"console_offset":112,"console_lines":1}
125
+ {"time":"2026-08-06T22:43:56.605703891Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
126
+ {"time":"2026-08-06T22:44:10.34649914Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":100,"history_lines":2,"events_offset":92,"events_lines":2,"console_offset":112,"console_lines":1}
127
+ {"time":"2026-08-06T22:44:11.359961554Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
128
+ {"time":"2026-08-06T22:44:25.349864374Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":102,"history_lines":3,"events_offset":94,"events_lines":2,"console_offset":112,"console_lines":1}
129
+ {"time":"2026-08-06T22:44:26.399084032Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
130
+ {"time":"2026-08-06T22:44:40.346062486Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":105,"history_lines":2,"events_offset":96,"events_lines":2,"console_offset":112,"console_lines":1}
131
+ {"time":"2026-08-06T22:44:41.346280567Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
132
+ {"time":"2026-08-06T22:44:55.345312943Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":107,"history_lines":2,"events_offset":98,"events_lines":2,"console_offset":112,"console_lines":1}
133
+ {"time":"2026-08-06T22:44:56.390583792Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
134
+ {"time":"2026-08-06T22:45:10.346429629Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":109,"history_lines":2,"events_offset":100,"events_lines":2,"console_offset":112,"console_lines":1}
135
+ {"time":"2026-08-06T22:45:11.486733206Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
136
+ {"time":"2026-08-06T22:45:25.353361363Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":111,"history_lines":1,"events_offset":102,"events_lines":2,"console_offset":116,"console_lines":51}
137
+ {"time":"2026-08-06T22:45:26.336931114Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
138
+ {"time":"2026-08-06T22:45:26.625234049Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
139
+ {"time":"2026-08-06T22:45:26.643029904Z","level":"INFO","msg":"filestream: sending request","total_files":2,"console_offset":166,"console_lines":6,"uploaded_len":3,"complete":true,"exit_code":0}
140
+ {"time":"2026-08-06T22:45:26.973490402Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
141
+ {"time":"2026-08-06T22:45:26.974882347Z","level":"INFO","msg":"handler: operation stats","stats":{}}
142
+ {"time":"2026-08-06T22:45:27.326334254Z","level":"INFO","msg":"stream: finishing up"}
143
+ {"time":"2026-08-06T22:45:27.326458162Z","level":"INFO","msg":"handler: closed"}
144
+ {"time":"2026-08-06T22:45:27.327039639Z","level":"INFO","msg":"sender: closed"}
145
+ {"time":"2026-08-06T22:45:27.327073756Z","level":"INFO","msg":"stream: all finished"}
wandb/run-20260806_223224-qz489gza/logs/debug.log CHANGED
@@ -21,3 +21,8 @@ config: {'_wandb': {}}
21
  2026-08-06 22:32:25,137 INFO MainThread:1570418 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.15.0.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': 94, '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': 'relu', 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-relu-94L_run', 'per_device_train_batch_size': 64, 'num_train_epochs': 1, 'max_steps': 2000, 'learning_rate': 0.0003, 'lr_scheduler_type': 'constant', 'lr_scheduler_kwargs': None, 'warmup_steps': 0, 'optim': 'adamw_torch', 'optim_args': None, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 1.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-relu-94L-15.9M-20260806-223223', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 200, 'eval_delay': 0, 'per_device_eval_batch_size': 64, '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': 500, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': True, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/ACTio-glu-relu-94L', '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}
22
  2026-08-06 22:32:25,140 INFO MainThread:1570418 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 15949440 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x14ece81bb8d0>>
23
  2026-08-06 22:32:25,140 INFO MainThread:1570418 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 15949440 None
 
 
 
 
 
 
21
  2026-08-06 22:32:25,137 INFO MainThread:1570418 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.15.0.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': 94, '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': 'relu', 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-relu-94L_run', 'per_device_train_batch_size': 64, 'num_train_epochs': 1, 'max_steps': 2000, 'learning_rate': 0.0003, 'lr_scheduler_type': 'constant', 'lr_scheduler_kwargs': None, 'warmup_steps': 0, 'optim': 'adamw_torch', 'optim_args': None, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 1.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-relu-94L-15.9M-20260806-223223', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 200, 'eval_delay': 0, 'per_device_eval_batch_size': 64, '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': 500, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': True, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/ACTio-glu-relu-94L', '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}
22
  2026-08-06 22:32:25,140 INFO MainThread:1570418 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 15949440 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x14ece81bb8d0>>
23
  2026-08-06 22:32:25,140 INFO MainThread:1570418 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 15949440 None
24
+ 2026-08-06 22:45:25,630 INFO MainThread:1570418 [wandb_run.py:_finish():2383] finishing run deepnevro-deepnevro/huggingface/qz489gza
25
+ 2026-08-06 22:45:25,631 INFO MainThread:1570418 [wandb_run.py:_atexit_cleanup():2588] got exitcode: 0
26
+ 2026-08-06 22:45:25,631 INFO MainThread:1570418 [wandb_run.py:_restore():2570] restore
27
+ 2026-08-06 22:45:25,631 INFO MainThread:1570418 [wandb_run.py:_restore():2576] restore done
28
+ 2026-08-06 22:45:27,324 INFO MainThread:1570418 [wandb_run.py:_footer_sync_info():3993] logging synced files
wandb/run-20260806_223224-qz489gza/run-qz489gza.wandb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5581464a09169672218c572940aaeda3575308a38ad0bbd573ac08abf271afd
3
- size 39288832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63312891512d6a84f30a4ca62ded7281f448187b2e14bd736a52ada0188b47ad
3
+ size 48753644
wandb/run-20260806_224537-4k21flpq/files/output.log ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [transformers] `use_return_dict` is deprecated! Use `return_dict` instead!
2
+ /mnt/data/zainulabideen/zain-exp/notebooks/Activation/exp.py:464: UserWarning: std(): degrees of freedom is <= 0. Correction should be strictly less than the reduction factor (input numel divided by output numel). (Triggered internally at /pytorch/aten/src/ATen/native/ReduceOps.cpp:1831.)
3
+ "std": tensor.std().item(),
4
+ 14%|█████▎ | 270/2000 [01:35<08:00, 3.60it/s]
5
+ {'loss': '7.762', 'grad_norm': '1.25', 'learning_rate': '0.0003', 'epoch': '0.001348', 'train/total_time_seconds': '5.973', 'train/time_per_step_avg': '0.2986', 'train/epoch_time_elapsed': '7.403', 'train/estimated_remaining_minutes': '9.855', 'train/global/act/norm': '3.141e+04', 'train/global/act/mean': '-0.003631', 'train/global/act/std': '0', 'train/global/act/max_abs': '8.328', 'train/global/act/frac_near_dtype_limit': '0', 'train/global/act/frac_near_user_limit': '0', 'train/global/grad/norm': '1.916', 'train/global/grad/mean': '-3.398e-08', 'train/global/grad/std': '0.00048', 'train/global/grad/max_abs': '0.1108', 'train/global/grad/frac_near_dtype_limit': '0', 'train/global/grad/frac_near_user_limit': '0', 'train/global/param/norm': '174.8', 'train/global/param/mean': '0.001522', 'train/global/param/std': '0.04375', 'train/global/param/max_abs': '1', 'train/global/param/frac_near_dtype_limit': '0', 'train/global/param/frac_near_user_limit': '0', 'train/layer__model_layers_93/param/norm': '17.93', 'train/layer__model_layers_93/param/mean': '0.001677', 'train/layer__model_layers_93/param/std': '0.04424', 'train/layer__model_layers_93/param/max_abs': '1', 'train/layer__model_layers_93/param/frac_near_dtype_limit': '0', 'train/layer__model_layers_93/param/frac_near_user_limit': '0', 'train/layer_model_layers_2/act/norm': '3147', 'train/layer_model_layers_2/act/mean': '-0.002471', 'train/layer_model_layers_2/act/std': '0.4111', 'train/layer_model_layers_2/act/max_abs': '5.531', 'train/layer_model_layers_2/act/frac_near_dtype_limit': '0', 'train/layer_model_layers_2/act/frac_near_user_limit': '0', 'train/layer_model_layers_2/grad/norm': '0.6158', 'train/layer_model_layers_2/grad/mean': '-6.741e-07', 'train/layer_model_layers_2/grad/std': '0.00152', 'train/layer_model_layers_2/grad/max_abs': '0.02808', 'train/layer_model_layers_2/grad/frac_near_dtype_limit': '0', 'train/layer_model_layers_2/grad/frac_near_user_limit': '0', 'train/layer__model_layers_78/param/norm': '17.93', 'train/layer__model_layers_78/param/mean': '0.001569', 'train/layer__model_layers_78/param/std': '0.04425', 'train/layer__model_layers_78/param/max_abs': '1', 'train/layer__model_layers_78/param/frac_near_dtype_limit': '0', 'train/layer__model_layers_78/param/frac_near_user_limit': '0', 'train/layer__model_layers_90/param/norm': '17.94', 'train/layer__model_layers_90/param/mean': '0.001602', 'train/layer__model_layers_90/param/std': '0.04425', 'train/layer__model_layers_90/param/max_abs': '1', 'train/layer__model_layers_90/param/frac_near_dtype_limit': '0', 'train/layer__model_layers_90/param/frac_near_user_limit': '0', 'train/layer_model_layers_48/act/norm': '3210', 'train/layer_model_layers_48/act/mean': '-0.000527', 'train/layer_model_layers_48/act/std': '0.419', 'train/layer_model_layers_48/act/max_abs': '4.594', 'train/layer_model_layers_48/act/frac_near_dtype_limit': '0', 'train/layer_model_layers_48/act/frac_near_user_limit': '0', 'train/layer_model_layers_48/grad/norm': '0.0884', 'train/layer_model_layers_48/grad/mean': '-3.365e-07', 'train/layer_model_layers_48/grad/std': '0.0002182', 'train/layer_model_layers_48/grad/max_abs': '0.006348', 'train/layer_model_layers_48/grad/frac_near_dtype_limit': '0', 'train/layer_model_layers_48/grad/frac_near_user_limit': '0', 'train/layer__model_layers_58/param/norm': '17.93', 'train/layer__model_layers_58/param/mean': '0.001566', 'train/layer__model_layers_58/param/std': '0.04424', 'train/layer__model_layers_58/param/max_abs': '1', 'train/layer__model_layers_58/param/frac_near_dtype_limit': '0', 'train/layer__model_layers_58/param/frac_near_user_limit': '0', 'train/layer_model_layers_75/act/norm': '3257', 'train/layer_model_layers_75/act/mean': '-0.002902', 'train/layer_model_layers_75/act/std': '0.4251', 'train/layer_model_layers_75/act/max_abs': '4.469', 'train/layer_model_layers_75/act/frac_near_dtype_limit': '0', 'train/layer_model_layers_75/act/frac_near_user_limit': '0', 'train/layer_model_layers_75/grad/norm': '0.07415', 'train/layer_model_layers_75/grad/mean': '-7.348e-08', 'train/layer_model_lay
6
+ {'loss': '7.001', 'grad_norm': '1.156', 'learning_rate': '0.0003', 'epoch': '0.002696', 'train/total_time_seconds': '10.53', 'train/time_per_step_avg': '0.2633', 'train/epoch_time_elapsed': '13.18', 'train/estimated_remaining_minutes': '8.601'}
7
+ {'loss': '6.47', 'grad_norm': '0.8984', 'learning_rate': '0.0003', 'epoch': '0.004044', 'train/total_time_seconds': '15.09', 'train/time_per_step_avg': '0.2515', 'train/epoch_time_elapsed': '18.74', 'train/estimated_remaining_minutes': '8.132'}
8
+ {'loss': '6.166', 'grad_norm': '0.5586', 'learning_rate': '0.0003', 'epoch': '0.005393', 'train/total_time_seconds': '19.7', 'train/time_per_step_avg': '0.2463', 'train/epoch_time_elapsed': '24.35', 'train/estimated_remaining_minutes': '7.881'}
9
+ {'loss': '6.043', 'grad_norm': '0.3711', 'learning_rate': '0.0003', 'epoch': '0.006741', 'train/total_time_seconds': '24.29', 'train/time_per_step_avg': '0.2429', 'train/epoch_time_elapsed': '29.91', 'train/estimated_remaining_minutes': '7.692'}
10
+ {'loss': '5.951', 'grad_norm': '0.4023', 'learning_rate': '0.0003', 'epoch': '0.008089', 'train/total_time_seconds': '28.85', 'train/time_per_step_avg': '0.2287', 'train/epoch_time_elapsed': '35.43', 'train/estimated_remaining_minutes': '7.532'}
11
+ {'loss': '5.82', 'grad_norm': '2.188', 'learning_rate': '0.0003', 'epoch': '0.009437', 'train/total_time_seconds': '33.41', 'train/time_per_step_avg': '0.2288', 'train/epoch_time_elapsed': '40.97', 'train/estimated_remaining_minutes': '7.398'}
12
+ {'loss': '5.594', 'grad_norm': '1.945', 'learning_rate': '0.0003', 'epoch': '0.01079', 'train/total_time_seconds': '38.01', 'train/time_per_step_avg': '0.2292', 'train/epoch_time_elapsed': '46.53', 'train/estimated_remaining_minutes': '7.284'}
13
+ {'loss': '5.212', 'grad_norm': '0.7109', 'learning_rate': '0.0003', 'epoch': '0.01213', 'train/total_time_seconds': '42.57', 'train/time_per_step_avg': '0.2286', 'train/epoch_time_elapsed': '52.09', 'train/estimated_remaining_minutes': '7.173'}
14
+ {'loss': '4.872', 'grad_norm': '0.6992', 'learning_rate': '0.0003', 'epoch': '0.01348', 'train/total_time_seconds': '47.15', 'train/time_per_step_avg': '0.2286', 'train/epoch_time_elapsed': '57.65', 'train/estimated_remaining_minutes': '7.072'}
15
+
16
+ {'eval_loss': '4.71', 'eval_runtime': '17.01', 'eval_samples_per_second': '560.2', 'eval_steps_per_second': '8.762', 'epoch': '0.01348', 'train/total_time_seconds': '47.15', 'train/time_per_step_avg': '0.2286', 'train/epoch_time_elapsed': '74.66', 'train/estimated_remaining_minutes': '7.072'}
17
+ {'loss': '4.602', 'grad_norm': '2.859', 'learning_rate': '0.0003', 'epoch': '0.01483', 'train/total_time_seconds': '52.28', 'train/time_per_step_avg': '0.2343', 'train/epoch_time_elapsed': '81.07', 'train/estimated_remaining_minutes': '7.049', 'train/global/act/norm': '6.188e+04', 'train/global/act/mean': '-0.04512', 'train/global/act/std': '0', 'train/global/act/max_abs': '10.44', 'train/global/act/frac_near_dtype_limit': '0', 'train/global/act/frac_near_user_limit': '0', 'train/global/grad/norm': '0.7572', 'train/global/grad/mean': '-1.021e-07', 'train/global/grad/std': '0.0001895', 'train/global/grad/max_abs': '0.07178', 'train/global/grad/frac_near_dtype_limit': '0', 'train/global/grad/frac_near_user_limit': '0', 'train/global/param/norm': '177.3', 'train/global/param/mean': '0.001565', 'train/global/param/std': '0.04437', 'train/global/param/max_abs': '1', 'train/global/param/frac_near_dtype_limit': '0', 'train/global/param/frac_near_user_limit': '0', 'train/layer__model_layers_93/param/norm': '18.17', 'train/layer__model_layers_93/param/mean': '0.001681', 'train/layer__model_layers_93/param/std': '0.04482', 'train/layer__model_layers_93/param/max_abs': '1', 'train/layer__model_layers_93/param/frac_near_dtype_limit': '0', 'train/layer__model_layers_93/param/frac_near_user_limit': '0', 'train/layer_model_layers_2/act/norm': '3505', 'train/layer_model_layers_2/act/mean': '-0.002494', 'train/layer_model_layers_2/act/std': '0.4577', 'train/layer_model_layers_2/act/max_abs': '4.062', 'train/layer_model_layers_2/act/frac_near_dtype_limit': '0', 'train/layer_model_layers_2/act/frac_near_user_limit': '0', 'train/layer_model_layers_2/grad/norm': '0.09074', 'train/layer_model_layers_2/grad/mean': '1.894e-08', 'train/layer_model_layers_2/grad/std': '0.000224', 'train/layer_model_layers_2/grad/max_abs': '0.003738', 'train/layer_model_layers_2/grad/frac_near_dtype_limit': '0', 'train/layer_model_layers_2/grad/frac_near_user_limit': '0', 'train/layer__model_layers_78/param/norm': '18.28', 'train/layer__model_layers_78/param/mean': '0.001595', 'train/layer__model_layers_78/param/std': '0.0451', 'train/layer__model_layers_78/param/max_abs': '1', 'train/layer__model_layers_78/param/frac_near_dtype_limit': '0', 'train/layer__model_layers_78/param/frac_near_user_limit': '0', 'train/layer__model_layers_90/param/norm': '18.21', 'train/layer__model_layers_90/param/mean': '0.00164', 'train/layer__model_layers_90/param/std': '0.04492', 'train/layer__model_layers_90/param/max_abs': '1', 'train/layer__model_layers_90/param/frac_near_dtype_limit': '0', 'train/layer__model_layers_90/param/frac_near_user_limit': '0', 'train/layer_model_layers_48/act/norm': '5590', 'train/layer_model_layers_48/act/mean': '-0.01205', 'train/layer_model_layers_48/act/std': '0.73', 'train/layer_model_layers_48/act/max_abs': '6.5', 'train/layer_model_layers_48/act/frac_near_dtype_limit': '0', 'train/layer_model_layers_48/act/frac_near_user_limit': '0', 'train/layer_model_layers_48/grad/norm': '0.02343', 'train/layer_model_layers_48/grad/mean': '-1.511e-07', 'train/layer_model_layers_48/grad/std': '5.784e-05', 'train/layer_model_layers_48/grad/max_abs': '0.0007668', 'train/layer_model_layers_48/grad/frac_near_dtype_limit': '0', 'train/layer_model_layers_48/grad/frac_near_user_limit': '0', 'train/layer__model_layers_58/param/norm': '18.17', 'train/layer__model_layers_58/param/mean': '0.001525', 'train/layer__model_layers_58/param/std': '0.04484', 'train/layer__model_layers_58/param/max_abs': '1', 'train/layer__model_layers_58/param/frac_near_dtype_limit': '0', 'train/layer__model_layers_58/param/frac_near_user_limit': '0', 'train/layer_model_layers_75/act/norm': '8296', 'train/layer_model_layers_75/act/mean': '-0.04333', 'train/layer_model_layers_75/act/std': '1.082', 'train/layer_model_layers_75/act/max_abs': '9.125', 'train/layer_model_layers_75/act/frac_near_dtype_limit': '0', 'train/layer_model_layers_75/act/frac_near_user_limit': '0', 'train/layer_model_layers_75/grad/norm': '0.02333', 'train/layer_model_layers_75/grad/mean': '3.531e-08', 'train/layer_model_layer
18
+ {'loss': '4.389', 'grad_norm': '4', 'learning_rate': '0.0003', 'epoch': '0.01618', 'train/total_time_seconds': '56.89', 'train/time_per_step_avg': '0.2348', 'train/epoch_time_elapsed': '86.86', 'train/estimated_remaining_minutes': '6.953'}
19
+ {'loss': '4.151', 'grad_norm': '1.32', 'learning_rate': '0.0003', 'epoch': '0.01753', 'train/total_time_seconds': '61.45', 'train/time_per_step_avg': '0.2345', 'train/epoch_time_elapsed': '92.39', 'train/estimated_remaining_minutes': '6.854'}
wandb/run-20260806_224537-4k21flpq/files/requirements.txt ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ asttokens==3.0.1
2
+ comm==0.2.3
3
+ debugpy==1.8.21
4
+ decorator==5.3.1
5
+ executing==2.2.1
6
+ nest-asyncio==1.6.0
7
+ parso==0.8.7
8
+ platformdirs==4.11.0
9
+ psutil==7.2.2
10
+ ptyprocess==0.7.0
11
+ pure_eval==0.2.3
12
+ Pygments==2.20.0
13
+ pyzmq==27.1.0
14
+ setuptools==83.0.0
15
+ six==1.17.0
16
+ tornado==6.5.7
17
+ traitlets==5.15.0
18
+ fsspec==2026.4.0
19
+ wcwidth==0.8.2
20
+ ipython_pygments_lexers==1.1.1
21
+ jedi==0.20.0
22
+ jupyter_core==5.9.1
23
+ matplotlib-inline==0.2.2
24
+ pexpect==4.9.0
25
+ prompt_toolkit==3.0.53
26
+ python-dateutil==2.9.0.post0
27
+ stack_data==0.6.3
28
+ wheel==0.47.0
29
+ jupyter_client==8.9.1
30
+ pip==26.1.2
31
+ ipython==9.15.0
32
+ ipykernel==7.2.0
33
+ threadpoolctl==3.6.0
34
+ pyparsing==3.3.2
35
+ typing_extensions==4.15.0
36
+ Jinja2==3.1.6
37
+ narwhals==2.24.0
38
+ kiwisolver==1.5.0
39
+ joblib==1.5.3
40
+ fonttools==4.63.0
41
+ cycler==0.12.1
42
+ scipy==1.17.1
43
+ pandas==3.0.5
44
+ contourpy==1.3.3
45
+ scikit-learn==1.9.0
46
+ matplotlib==3.11.1
47
+ urllib3==2.7.0
48
+ tqdm==4.70.0
49
+ idna==3.18
50
+ charset-normalizer==3.4.9
51
+ certifi==2026.7.22
52
+ requests==2.34.2
53
+ seaborn==0.13.2
54
+ uv==0.12.0
55
+ shellingham==1.5.4
56
+ mpmath==1.3.0
57
+ attrs==26.1.0
58
+ hf-xet==1.5.2
59
+ nvidia-nccl-cu12==2.21.5
60
+ MarkupSafe==3.0.3
61
+ regex==2026.7.19
62
+ importlib_metadata==9.0.0
63
+ httpcore==1.0.9
64
+ annotated-doc==0.0.5
65
+ multidict==6.7.1
66
+ aiohttp==3.14.3
67
+ aiosignal==1.4.0
68
+ xxhash==3.8.1
69
+ aiohappyeyeballs==2.7.1
70
+ mdurl==0.1.2
71
+ cuda-toolkit==13.0.3.0
72
+ networkx==3.6.1
73
+ PyYAML==6.0.3
74
+ nvidia-cufile==1.15.1.6
75
+ typer==0.27.0
76
+ torchaudio==2.6.0+cu124
77
+ rich==15.0.0
78
+ nvidia-cufft-cu12==11.2.1.3
79
+ h11==0.16.0
80
+ dill==0.4.1
81
+ cuda-pathfinder==1.6.0
82
+ filelock==3.29.0
83
+ nvidia-nvtx-cu12==12.4.127
84
+ httpx==0.28.1
85
+ anyio==4.14.2
86
+ numpy==2.4.4
87
+ yarl==1.24.5
88
+ click==8.4.2
89
+ triton==3.2.0
90
+ frozenlist==1.8.0
91
+ zipp==4.1.0
92
+ propcache==0.5.2
93
+ tokenizers==0.22.2
94
+ markdown-it-py==4.2.0
95
+ nvidia-cuda-runtime==13.0.96
96
+ cuda-bindings==13.3.1
97
+ nvidia-cuda-cupti==13.0.85
98
+ torch==2.6.0+cu124
99
+ multiprocess==0.70.19
100
+ pillow==12.2.0
101
+ transformers==5.15.0.dev0
102
+ wandb==0.28.1
103
+ nvidia-curand==10.4.0.35
104
+ sympy==1.13.1
105
+ nvidia-cusparse==12.6.3.3
106
+ nvidia-cuda-nvrtc==13.0.88
107
+ typing-inspection==0.4.2
108
+ nvidia-cusolver==12.0.4.66
109
+ nvidia-cufft==12.0.0.61
110
+ nvidia-cudnn-cu13==9.20.0.48
111
+ nvidia-cublas==13.1.1.3
112
+ pyarrow==25.0.0
113
+ evaluate==0.4.6
114
+ diffusers==0.39.0
115
+ pydantic==2.13.4
116
+ annotated-types==0.8.0
117
+ protobuf==7.35.1
118
+ sentry-sdk==2.66.1
119
+ einops==0.8.2
120
+ packaging==26.2
121
+ nvidia-nvjitlink-cu12==12.4.127
122
+ nvidia-curand-cu12==10.3.5.147
123
+ nvidia-cusparselt-cu12==0.6.2
124
+ nvidia-cusparse-cu12==12.3.1.170
125
+ nvidia-cuda-runtime-cu12==12.4.127
126
+ torchvision==0.21.0+cu124
127
+ nvidia-cuda-nvrtc-cu12==12.4.127
128
+ nvidia-cuda-cupti-cu12==12.4.127
129
+ nvidia-cusolver-cu12==11.6.1.9
130
+ nvidia-cublas-cu12==12.4.5.8
131
+ nvidia-cudnn-cu12==9.1.0.70
132
+ huggingface_hub==1.26.0
133
+ datasets==5.0.1
134
+ safetensors==0.8.0
135
+ accelerate==1.14.0
136
+ pydantic_core==2.46.4
137
+ ninja==1.13.0
138
+ autocommand==2.2.2
139
+ backports.tarfile==1.2.0
140
+ importlib_metadata==8.7.1
141
+ jaraco.text==4.0.0
142
+ jaraco.context==6.1.0
143
+ jaraco.functools==4.4.0
144
+ more-itertools==10.8.0
145
+ packaging==26.0
146
+ platformdirs==4.4.0
147
+ tomli==2.4.0
148
+ wheel==0.46.3
149
+ zipp==3.23.0
wandb/run-20260806_224537-4k21flpq/files/wandb-metadata.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-5.15.0-126-generic-x86_64-with-glibc2.35",
3
+ "python": "CPython 3.11.15",
4
+ "startedAt": "2026-08-06T22:45:37.256933Z",
5
+ "args": [
6
+ "--config",
7
+ "configs/baseline.yaml",
8
+ "--variants",
9
+ "glu-gelu-94L",
10
+ "--push"
11
+ ],
12
+ "program": "/mnt/data/zainulabideen/zain-exp/notebooks/Activation/sweep.py",
13
+ "codePath": "sweep.py",
14
+ "codePathLocal": "sweep.py",
15
+ "git": {
16
+ "remote": "https://github.com/deepnevro/Activation.git",
17
+ "commit": "8d6f97d73f5521e4c38c6e1bda59bf8d4b489655"
18
+ },
19
+ "email": "deepnevro@gmail.com",
20
+ "root": "/mnt/data/zainulabideen/zain-exp/notebooks/Activation",
21
+ "host": "deeplens-k3s-node1",
22
+ "executable": "/mnt/data/zainulabideen/zain-exp/notebooks/my_env/bin/python",
23
+ "cpu_count": 112,
24
+ "cpu_count_logical": 224,
25
+ "gpu": "NVIDIA H100 80GB HBM3",
26
+ "gpu_count": 8,
27
+ "disk": {
28
+ "/": {
29
+ "total": "1560765693952",
30
+ "used": "703843528704"
31
+ }
32
+ },
33
+ "memory": {
34
+ "total": "2164089937920"
35
+ },
36
+ "gpu_nvidia": [
37
+ {
38
+ "name": "NVIDIA H100 80GB HBM3",
39
+ "memoryTotal": "85520809984",
40
+ "cudaCores": 16896,
41
+ "architecture": "Hopper",
42
+ "uuid": "GPU-39c684a5-fde6-83d7-1663-0859795881ae"
43
+ },
44
+ {
45
+ "name": "NVIDIA H100 80GB HBM3",
46
+ "memoryTotal": "85520809984",
47
+ "cudaCores": 16896,
48
+ "architecture": "Hopper",
49
+ "uuid": "GPU-68012e5a-38b6-b643-0ca6-62fb66720bf3"
50
+ },
51
+ {
52
+ "name": "NVIDIA H100 80GB HBM3",
53
+ "memoryTotal": "85520809984",
54
+ "cudaCores": 16896,
55
+ "architecture": "Hopper",
56
+ "uuid": "GPU-132944c4-b689-2b5f-89a4-d730401677ab"
57
+ },
58
+ {
59
+ "name": "NVIDIA H100 80GB HBM3",
60
+ "memoryTotal": "85520809984",
61
+ "cudaCores": 16896,
62
+ "architecture": "Hopper",
63
+ "uuid": "GPU-2df386cc-6d26-d0e2-7a2d-a057b0d95864"
64
+ },
65
+ {
66
+ "name": "NVIDIA H100 80GB HBM3",
67
+ "memoryTotal": "85520809984",
68
+ "cudaCores": 16896,
69
+ "architecture": "Hopper",
70
+ "uuid": "GPU-bfa16575-1d94-1aa2-4537-2c93433f42ef"
71
+ },
72
+ {
73
+ "name": "NVIDIA H100 80GB HBM3",
74
+ "memoryTotal": "85520809984",
75
+ "cudaCores": 16896,
76
+ "architecture": "Hopper",
77
+ "uuid": "GPU-bc6c3e3c-9b90-09ca-c034-774961847c54"
78
+ },
79
+ {
80
+ "name": "NVIDIA H100 80GB HBM3",
81
+ "memoryTotal": "85520809984",
82
+ "cudaCores": 16896,
83
+ "architecture": "Hopper",
84
+ "uuid": "GPU-00a441e1-7c95-e7d6-4c35-43d6b291aea9"
85
+ },
86
+ {
87
+ "name": "NVIDIA H100 80GB HBM3",
88
+ "memoryTotal": "85520809984",
89
+ "cudaCores": 16896,
90
+ "architecture": "Hopper",
91
+ "uuid": "GPU-1c4d29a2-4647-6fce-d8fc-0c5ecfbbd6ea"
92
+ }
93
+ ],
94
+ "cudaVersion": "12.4",
95
+ "writerId": "kwbq6ro0up5x6hbn45qt4orzdys0qbr3"
96
+ }
wandb/run-20260806_224537-4k21flpq/logs/debug-core.log ADDED
@@ -0,0 +1,344 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2026-08-06T18:04:46.538250567Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmp2a2e5_ej/port-3216433.txt","pid":3216433,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
2
+ {"time":"2026-08-06T18:04:46.539844561Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":3216433}
3
+ {"time":"2026-08-06T18:04:46.539820323Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-3216433-3217992-4167316671/socket","Net":"unix"}}
4
+ {"time":"2026-08-06T18:04:46.719997957Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
5
+ {"time":"2026-08-06T18:05:08.298825026Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"2(@)"}
6
+ {"time":"2026-08-06T18:05:08.367098402Z","level":"INFO","msg":"handleInformInit: received","streamId":"z39kc1mj","id":"2(@)"}
7
+ {"time":"2026-08-06T18:05:08.627294329Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"z39kc1mj","id":"2(@)"}
8
+ {"time":"2026-08-06T18:05:14.00962682Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"yvj0vp5mnk1k"}
9
+ {"time":"2026-08-06T18:09:51.272768584Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"yvj0vp5mnk1k"}
10
+ {"time":"2026-08-06T18:09:51.880581594Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"yvj0vp5mnk1k"}
11
+ {"time":"2026-08-06T18:09:51.88512942Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"z39kc1mj","id":"2(@)"}
12
+ {"time":"2026-08-06T18:09:51.885935784Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"z39kc1mj","id":"2(@)"}
13
+ {"time":"2026-08-06T18:09:52.564856588Z","level":"INFO","msg":"handleInformInit: received","streamId":"sbc92q1f","id":"2(@)"}
14
+ {"time":"2026-08-06T18:09:52.825658469Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"sbc92q1f","id":"2(@)"}
15
+ {"time":"2026-08-06T18:09:58.169270574Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"0a8yqf8zu5md"}
16
+ {"time":"2026-08-06T18:14:33.893632231Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"0a8yqf8zu5md"}
17
+ {"time":"2026-08-06T18:14:34.593822464Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"0a8yqf8zu5md"}
18
+ {"time":"2026-08-06T18:14:34.598479224Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"sbc92q1f","id":"2(@)"}
19
+ {"time":"2026-08-06T18:14:34.599045264Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"sbc92q1f","id":"2(@)"}
20
+ {"time":"2026-08-06T18:14:35.180480118Z","level":"INFO","msg":"handleInformInit: received","streamId":"dhvsvux4","id":"2(@)"}
21
+ {"time":"2026-08-06T18:14:35.444177659Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"dhvsvux4","id":"2(@)"}
22
+ {"time":"2026-08-06T18:14:40.859467699Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"xsm3myskoe8a"}
23
+ {"time":"2026-08-06T18:19:23.935068699Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"xsm3myskoe8a"}
24
+ {"time":"2026-08-06T18:19:24.531383847Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"xsm3myskoe8a"}
25
+ {"time":"2026-08-06T18:19:24.535902551Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"dhvsvux4","id":"2(@)"}
26
+ {"time":"2026-08-06T18:19:24.542000275Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"dhvsvux4","id":"2(@)"}
27
+ {"time":"2026-08-06T18:19:25.081465341Z","level":"INFO","msg":"handleInformInit: received","streamId":"9sn2dmlk","id":"2(@)"}
28
+ {"time":"2026-08-06T18:19:25.34384648Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"9sn2dmlk","id":"2(@)"}
29
+ {"time":"2026-08-06T18:19:30.809155481Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"zzesry1w2hdw"}
30
+ {"time":"2026-08-06T18:24:12.774105293Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"zzesry1w2hdw"}
31
+ {"time":"2026-08-06T18:24:13.368319922Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"zzesry1w2hdw"}
32
+ {"time":"2026-08-06T18:24:13.372879394Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"9sn2dmlk","id":"2(@)"}
33
+ {"time":"2026-08-06T18:24:13.373724105Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"9sn2dmlk","id":"2(@)"}
34
+ {"time":"2026-08-06T18:24:13.834178741Z","level":"INFO","msg":"handleInformInit: received","streamId":"glrlrwzy","id":"2(@)"}
35
+ {"time":"2026-08-06T18:24:14.092984473Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"glrlrwzy","id":"2(@)"}
36
+ {"time":"2026-08-06T18:24:19.407624607Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"3kgpmaa5yqm8"}
37
+ {"time":"2026-08-06T18:28:57.315589018Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"3kgpmaa5yqm8"}
38
+ {"time":"2026-08-06T18:28:58.034501646Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"3kgpmaa5yqm8"}
39
+ {"time":"2026-08-06T18:28:58.038814253Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"glrlrwzy","id":"2(@)"}
40
+ {"time":"2026-08-06T18:28:58.039552064Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"glrlrwzy","id":"2(@)"}
41
+ {"time":"2026-08-06T18:28:58.635343408Z","level":"INFO","msg":"handleInformInit: received","streamId":"f8vsthww","id":"2(@)"}
42
+ {"time":"2026-08-06T18:28:58.89471792Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"f8vsthww","id":"2(@)"}
43
+ {"time":"2026-08-06T18:29:04.225144507Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"hxcqfm4f6xmj"}
44
+ {"time":"2026-08-06T18:33:43.770331969Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"hxcqfm4f6xmj"}
45
+ {"time":"2026-08-06T18:33:44.645462268Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"hxcqfm4f6xmj"}
46
+ {"time":"2026-08-06T18:33:44.65006597Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"f8vsthww","id":"2(@)"}
47
+ {"time":"2026-08-06T18:33:44.650717299Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"f8vsthww","id":"2(@)"}
48
+ {"time":"2026-08-06T18:33:45.189506437Z","level":"INFO","msg":"handleInformInit: received","streamId":"zqgvabr6","id":"2(@)"}
49
+ {"time":"2026-08-06T18:33:45.447018472Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"zqgvabr6","id":"2(@)"}
50
+ {"time":"2026-08-06T18:33:50.799671196Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"ym5cu38tet69"}
51
+ {"time":"2026-08-06T18:38:39.107641115Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"ym5cu38tet69"}
52
+ {"time":"2026-08-06T18:38:39.705738046Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"ym5cu38tet69"}
53
+ {"time":"2026-08-06T18:38:39.710293346Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"zqgvabr6","id":"2(@)"}
54
+ {"time":"2026-08-06T18:38:39.711083242Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"zqgvabr6","id":"2(@)"}
55
+ {"time":"2026-08-06T18:38:40.320944199Z","level":"INFO","msg":"handleInformInit: received","streamId":"gmvu7t1t","id":"2(@)"}
56
+ {"time":"2026-08-06T18:38:40.582286439Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"gmvu7t1t","id":"2(@)"}
57
+ {"time":"2026-08-06T18:38:48.97913833Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"6tdudi35br7r"}
58
+ {"time":"2026-08-06T18:46:26.722216001Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"6tdudi35br7r"}
59
+ {"time":"2026-08-06T18:46:27.275612753Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"6tdudi35br7r"}
60
+ {"time":"2026-08-06T18:46:27.280086872Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"gmvu7t1t","id":"2(@)"}
61
+ {"time":"2026-08-06T18:46:27.280677847Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"gmvu7t1t","id":"2(@)"}
62
+ {"time":"2026-08-06T18:46:29.09769104Z","level":"INFO","msg":"handleInformInit: received","streamId":"xt6mu0ut","id":"2(@)"}
63
+ {"time":"2026-08-06T18:46:29.361795862Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"xt6mu0ut","id":"2(@)"}
64
+ {"time":"2026-08-06T18:46:34.718953302Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"h26us7kbwf6q"}
65
+ {"time":"2026-08-06T18:51:12.250107627Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"h26us7kbwf6q"}
66
+ {"time":"2026-08-06T18:51:12.792287965Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"h26us7kbwf6q"}
67
+ {"time":"2026-08-06T18:51:12.799944198Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"xt6mu0ut","id":"2(@)"}
68
+ {"time":"2026-08-06T18:51:12.80073712Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"xt6mu0ut","id":"2(@)"}
69
+ {"time":"2026-08-06T18:51:13.407850587Z","level":"INFO","msg":"handleInformInit: received","streamId":"txoxj9kx","id":"2(@)"}
70
+ {"time":"2026-08-06T18:51:13.666829851Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"txoxj9kx","id":"2(@)"}
71
+ {"time":"2026-08-06T18:51:19.006579451Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"2ppndpd2p84x"}
72
+ {"time":"2026-08-06T18:56:15.261635059Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"2ppndpd2p84x"}
73
+ {"time":"2026-08-06T18:56:15.79846543Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"2ppndpd2p84x"}
74
+ {"time":"2026-08-06T18:56:15.802884441Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"txoxj9kx","id":"2(@)"}
75
+ {"time":"2026-08-06T18:56:15.80381425Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"txoxj9kx","id":"2(@)"}
76
+ {"time":"2026-08-06T18:56:16.442462648Z","level":"INFO","msg":"handleInformInit: received","streamId":"fipes79r","id":"2(@)"}
77
+ {"time":"2026-08-06T18:56:16.702985583Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"fipes79r","id":"2(@)"}
78
+ {"time":"2026-08-06T18:56:22.045243322Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"azy3e61yjir6"}
79
+ {"time":"2026-08-06T19:01:14.449110053Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"azy3e61yjir6"}
80
+ {"time":"2026-08-06T19:01:14.993302658Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"azy3e61yjir6"}
81
+ {"time":"2026-08-06T19:01:14.997642507Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"fipes79r","id":"2(@)"}
82
+ {"time":"2026-08-06T19:01:14.998278532Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"fipes79r","id":"2(@)"}
83
+ {"time":"2026-08-06T19:01:15.465614427Z","level":"INFO","msg":"handleInformInit: received","streamId":"f3qsgvmt","id":"2(@)"}
84
+ {"time":"2026-08-06T19:01:15.725617356Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"f3qsgvmt","id":"2(@)"}
85
+ {"time":"2026-08-06T19:01:21.030632908Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"p32bak4478pg"}
86
+ {"time":"2026-08-06T19:06:15.28447298Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"p32bak4478pg"}
87
+ {"time":"2026-08-06T19:06:15.966487263Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"p32bak4478pg"}
88
+ {"time":"2026-08-06T19:06:15.970784791Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"f3qsgvmt","id":"2(@)"}
89
+ {"time":"2026-08-06T19:06:15.971416137Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"f3qsgvmt","id":"2(@)"}
90
+ {"time":"2026-08-06T19:06:16.506483042Z","level":"INFO","msg":"handleInformInit: received","streamId":"hvwhjauo","id":"2(@)"}
91
+ {"time":"2026-08-06T19:06:16.776483111Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"hvwhjauo","id":"2(@)"}
92
+ {"time":"2026-08-06T19:06:22.117142885Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"36s3hnqayddj"}
93
+ {"time":"2026-08-06T19:11:25.640393793Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"36s3hnqayddj"}
94
+ {"time":"2026-08-06T19:11:26.228253868Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"36s3hnqayddj"}
95
+ {"time":"2026-08-06T19:11:26.232498509Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"hvwhjauo","id":"2(@)"}
96
+ {"time":"2026-08-06T19:11:26.23318865Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"hvwhjauo","id":"2(@)"}
97
+ {"time":"2026-08-06T19:11:28.189921358Z","level":"INFO","msg":"processOutgoingData: finished","id":"2(@)"}
98
+ {"time":"2026-08-06T19:11:28.189919669Z","level":"INFO","msg":"connection: closing","id":"2(@)"}
99
+ {"time":"2026-08-06T19:11:28.190020399Z","level":"INFO","msg":"connection: closed successfully","id":"2(@)"}
100
+ {"time":"2026-08-06T19:11:28.190025107Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"2(@)"}
101
+ {"time":"2026-08-06T20:29:10.67349436Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"3(@)"}
102
+ {"time":"2026-08-06T20:29:10.899139178Z","level":"INFO","msg":"handleInformInit: received","streamId":"50qq810b","id":"3(@)"}
103
+ {"time":"2026-08-06T20:29:11.161778778Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"50qq810b","id":"3(@)"}
104
+ {"time":"2026-08-06T20:29:16.551101449Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"6gdiifnull5c"}
105
+ {"time":"2026-08-06T20:33:25.239918313Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"6gdiifnull5c"}
106
+ {"time":"2026-08-06T20:33:25.941458876Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"6gdiifnull5c"}
107
+ {"time":"2026-08-06T20:33:25.945769271Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"50qq810b","id":"3(@)"}
108
+ {"time":"2026-08-06T20:33:25.946336535Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"50qq810b","id":"3(@)"}
109
+ {"time":"2026-08-06T20:33:27.87172088Z","level":"INFO","msg":"connection: closing","id":"3(@)"}
110
+ {"time":"2026-08-06T20:33:27.871734329Z","level":"INFO","msg":"processOutgoingData: finished","id":"3(@)"}
111
+ {"time":"2026-08-06T20:33:27.87180156Z","level":"INFO","msg":"connection: closed successfully","id":"3(@)"}
112
+ {"time":"2026-08-06T20:33:27.871808221Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"3(@)"}
113
+ {"time":"2026-08-06T20:33:35.004799102Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"4(@)"}
114
+ {"time":"2026-08-06T20:33:35.301190488Z","level":"INFO","msg":"handleInformInit: received","streamId":"6n8s22c0","id":"4(@)"}
115
+ {"time":"2026-08-06T20:33:35.559898551Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"6n8s22c0","id":"4(@)"}
116
+ {"time":"2026-08-06T20:33:40.924660759Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"gujpb2xg58lm"}
117
+ {"time":"2026-08-06T20:37:48.507530405Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"gujpb2xg58lm"}
118
+ {"time":"2026-08-06T20:37:49.20082224Z","level":"INFO","msg":"connection: cancelling request","id":"4(@)","requestId":"gujpb2xg58lm"}
119
+ {"time":"2026-08-06T20:37:49.205183371Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"6n8s22c0","id":"4(@)"}
120
+ {"time":"2026-08-06T20:37:49.206009979Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"6n8s22c0","id":"4(@)"}
121
+ {"time":"2026-08-06T20:37:51.078419586Z","level":"INFO","msg":"connection: closing","id":"4(@)"}
122
+ {"time":"2026-08-06T20:37:51.07854494Z","level":"INFO","msg":"connection: closed successfully","id":"4(@)"}
123
+ {"time":"2026-08-06T20:37:51.078458019Z","level":"INFO","msg":"processOutgoingData: finished","id":"4(@)"}
124
+ {"time":"2026-08-06T20:37:51.078568095Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"4(@)"}
125
+ {"time":"2026-08-06T20:37:58.922451042Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"5(@)"}
126
+ {"time":"2026-08-06T20:37:59.137836857Z","level":"INFO","msg":"handleInformInit: received","streamId":"m4g42ash","id":"5(@)"}
127
+ {"time":"2026-08-06T20:37:59.399144811Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"m4g42ash","id":"5(@)"}
128
+ {"time":"2026-08-06T20:38:04.799520658Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"gsc8gq67qpxh"}
129
+ {"time":"2026-08-06T20:42:11.620911985Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"gsc8gq67qpxh"}
130
+ {"time":"2026-08-06T20:42:12.345957716Z","level":"INFO","msg":"connection: cancelling request","id":"5(@)","requestId":"gsc8gq67qpxh"}
131
+ {"time":"2026-08-06T20:42:12.350342881Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"m4g42ash","id":"5(@)"}
132
+ {"time":"2026-08-06T20:42:12.350969477Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"m4g42ash","id":"5(@)"}
133
+ {"time":"2026-08-06T20:42:14.214972127Z","level":"INFO","msg":"connection: closing","id":"5(@)"}
134
+ {"time":"2026-08-06T20:42:14.215065871Z","level":"INFO","msg":"connection: closed successfully","id":"5(@)"}
135
+ {"time":"2026-08-06T20:42:14.214982216Z","level":"INFO","msg":"processOutgoingData: finished","id":"5(@)"}
136
+ {"time":"2026-08-06T20:42:14.215075769Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"5(@)"}
137
+ {"time":"2026-08-06T20:42:21.47149625Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"6(@)"}
138
+ {"time":"2026-08-06T20:42:21.54327094Z","level":"INFO","msg":"handleInformInit: received","streamId":"wp360ttn","id":"6(@)"}
139
+ {"time":"2026-08-06T20:42:21.803599498Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"wp360ttn","id":"6(@)"}
140
+ {"time":"2026-08-06T20:42:27.07851781Z","level":"INFO","msg":"connection: cancelling request","id":"6(@)","requestId":"bk9a1z245pn3"}
141
+ {"time":"2026-08-06T20:46:34.337431219Z","level":"INFO","msg":"connection: cancelling request","id":"6(@)","requestId":"bk9a1z245pn3"}
142
+ {"time":"2026-08-06T20:46:35.010256698Z","level":"INFO","msg":"connection: cancelling request","id":"6(@)","requestId":"bk9a1z245pn3"}
143
+ {"time":"2026-08-06T20:46:35.01481264Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"wp360ttn","id":"6(@)"}
144
+ {"time":"2026-08-06T20:46:35.015419174Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"wp360ttn","id":"6(@)"}
145
+ {"time":"2026-08-06T20:46:37.063706429Z","level":"INFO","msg":"connection: closing","id":"6(@)"}
146
+ {"time":"2026-08-06T20:46:37.06378302Z","level":"INFO","msg":"connection: closed successfully","id":"6(@)"}
147
+ {"time":"2026-08-06T20:46:37.063717769Z","level":"INFO","msg":"processOutgoingData: finished","id":"6(@)"}
148
+ {"time":"2026-08-06T20:46:37.063792963Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"6(@)"}
149
+ {"time":"2026-08-06T20:46:44.665285682Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"7(@)"}
150
+ {"time":"2026-08-06T20:46:44.790234975Z","level":"INFO","msg":"handleInformInit: received","streamId":"8mwfoysp","id":"7(@)"}
151
+ {"time":"2026-08-06T20:46:45.052126921Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"8mwfoysp","id":"7(@)"}
152
+ {"time":"2026-08-06T20:46:50.354882158Z","level":"INFO","msg":"connection: cancelling request","id":"7(@)","requestId":"zsmv7lxj564h"}
153
+ {"time":"2026-08-06T20:51:04.423871647Z","level":"INFO","msg":"connection: cancelling request","id":"7(@)","requestId":"zsmv7lxj564h"}
154
+ {"time":"2026-08-06T20:51:05.165391456Z","level":"INFO","msg":"connection: cancelling request","id":"7(@)","requestId":"zsmv7lxj564h"}
155
+ {"time":"2026-08-06T20:51:05.169802539Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"8mwfoysp","id":"7(@)"}
156
+ {"time":"2026-08-06T20:51:05.170548103Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"8mwfoysp","id":"7(@)"}
157
+ {"time":"2026-08-06T20:51:07.106424725Z","level":"INFO","msg":"connection: closing","id":"7(@)"}
158
+ {"time":"2026-08-06T20:51:07.106509262Z","level":"INFO","msg":"connection: closed successfully","id":"7(@)"}
159
+ {"time":"2026-08-06T20:51:07.106433413Z","level":"INFO","msg":"processOutgoingData: finished","id":"7(@)"}
160
+ {"time":"2026-08-06T20:51:07.106518766Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"7(@)"}
161
+ {"time":"2026-08-06T20:51:14.33857564Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"8(@)"}
162
+ {"time":"2026-08-06T20:51:14.412043912Z","level":"INFO","msg":"handleInformInit: received","streamId":"jyn4q7id","id":"8(@)"}
163
+ {"time":"2026-08-06T20:51:14.672968943Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"jyn4q7id","id":"8(@)"}
164
+ {"time":"2026-08-06T20:51:20.036604771Z","level":"INFO","msg":"connection: cancelling request","id":"8(@)","requestId":"0a4iq1mlfhmv"}
165
+ {"time":"2026-08-06T20:55:30.610180022Z","level":"INFO","msg":"connection: cancelling request","id":"8(@)","requestId":"0a4iq1mlfhmv"}
166
+ {"time":"2026-08-06T20:55:31.149309264Z","level":"INFO","msg":"connection: cancelling request","id":"8(@)","requestId":"0a4iq1mlfhmv"}
167
+ {"time":"2026-08-06T20:55:31.153725839Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"jyn4q7id","id":"8(@)"}
168
+ {"time":"2026-08-06T20:55:31.154366097Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"jyn4q7id","id":"8(@)"}
169
+ {"time":"2026-08-06T20:55:33.161131775Z","level":"INFO","msg":"connection: closing","id":"8(@)"}
170
+ {"time":"2026-08-06T20:55:33.161148781Z","level":"INFO","msg":"processOutgoingData: finished","id":"8(@)"}
171
+ {"time":"2026-08-06T20:55:33.161225029Z","level":"INFO","msg":"connection: closed successfully","id":"8(@)"}
172
+ {"time":"2026-08-06T20:55:33.161231921Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"8(@)"}
173
+ {"time":"2026-08-06T20:55:40.881828681Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"9(@)"}
174
+ {"time":"2026-08-06T20:55:41.137982051Z","level":"INFO","msg":"handleInformInit: received","streamId":"ux707dhp","id":"9(@)"}
175
+ {"time":"2026-08-06T20:55:41.396559317Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"ux707dhp","id":"9(@)"}
176
+ {"time":"2026-08-06T20:55:46.80520653Z","level":"INFO","msg":"connection: cancelling request","id":"9(@)","requestId":"7ln72rdxtrl8"}
177
+ {"time":"2026-08-06T21:01:07.807151171Z","level":"INFO","msg":"connection: cancelling request","id":"9(@)","requestId":"7ln72rdxtrl8"}
178
+ {"time":"2026-08-06T21:01:08.632027106Z","level":"INFO","msg":"connection: cancelling request","id":"9(@)","requestId":"7ln72rdxtrl8"}
179
+ {"time":"2026-08-06T21:01:08.640292401Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"ux707dhp","id":"9(@)"}
180
+ {"time":"2026-08-06T21:01:08.641071161Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"ux707dhp","id":"9(@)"}
181
+ {"time":"2026-08-06T21:01:10.217979026Z","level":"INFO","msg":"connection: closing","id":"9(@)"}
182
+ {"time":"2026-08-06T21:01:10.218001261Z","level":"INFO","msg":"processOutgoingData: finished","id":"9(@)"}
183
+ {"time":"2026-08-06T21:01:10.218063029Z","level":"INFO","msg":"connection: closed successfully","id":"9(@)"}
184
+ {"time":"2026-08-06T21:01:10.218091836Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"9(@)"}
185
+ {"time":"2026-08-06T21:01:17.660905195Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"10(@)"}
186
+ {"time":"2026-08-06T21:01:17.883585458Z","level":"INFO","msg":"handleInformInit: received","streamId":"ne96fzuv","id":"10(@)"}
187
+ {"time":"2026-08-06T21:01:18.131118768Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"ne96fzuv","id":"10(@)"}
188
+ {"time":"2026-08-06T21:01:23.486800717Z","level":"INFO","msg":"connection: cancelling request","id":"10(@)","requestId":"saemn5wo6b36"}
189
+ {"time":"2026-08-06T21:06:38.967470021Z","level":"INFO","msg":"connection: cancelling request","id":"10(@)","requestId":"saemn5wo6b36"}
190
+ {"time":"2026-08-06T21:06:39.770490846Z","level":"INFO","msg":"connection: cancelling request","id":"10(@)","requestId":"saemn5wo6b36"}
191
+ {"time":"2026-08-06T21:06:39.778440708Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"ne96fzuv","id":"10(@)"}
192
+ {"time":"2026-08-06T21:06:39.779161583Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"ne96fzuv","id":"10(@)"}
193
+ {"time":"2026-08-06T21:06:41.416113473Z","level":"INFO","msg":"processOutgoingData: finished","id":"10(@)"}
194
+ {"time":"2026-08-06T21:06:41.416109712Z","level":"INFO","msg":"connection: closing","id":"10(@)"}
195
+ {"time":"2026-08-06T21:06:41.416210065Z","level":"INFO","msg":"connection: closed successfully","id":"10(@)"}
196
+ {"time":"2026-08-06T21:06:41.41621463Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"10(@)"}
197
+ {"time":"2026-08-06T21:06:49.167670364Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"11(@)"}
198
+ {"time":"2026-08-06T21:06:49.551478863Z","level":"INFO","msg":"handleInformInit: received","streamId":"81scdhoz","id":"11(@)"}
199
+ {"time":"2026-08-06T21:06:49.811685654Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"81scdhoz","id":"11(@)"}
200
+ {"time":"2026-08-06T21:06:55.197839638Z","level":"INFO","msg":"connection: cancelling request","id":"11(@)","requestId":"3kup4mffqzdp"}
201
+ {"time":"2026-08-06T21:12:13.037601019Z","level":"INFO","msg":"connection: cancelling request","id":"11(@)","requestId":"3kup4mffqzdp"}
202
+ {"time":"2026-08-06T21:12:13.884375251Z","level":"INFO","msg":"connection: cancelling request","id":"11(@)","requestId":"3kup4mffqzdp"}
203
+ {"time":"2026-08-06T21:12:13.892499726Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"81scdhoz","id":"11(@)"}
204
+ {"time":"2026-08-06T21:12:13.893241759Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"81scdhoz","id":"11(@)"}
205
+ {"time":"2026-08-06T21:12:15.762818452Z","level":"INFO","msg":"processOutgoingData: finished","id":"11(@)"}
206
+ {"time":"2026-08-06T21:12:15.7628123Z","level":"INFO","msg":"connection: closing","id":"11(@)"}
207
+ {"time":"2026-08-06T21:12:15.762905937Z","level":"INFO","msg":"connection: closed successfully","id":"11(@)"}
208
+ {"time":"2026-08-06T21:12:15.762910233Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"11(@)"}
209
+ {"time":"2026-08-06T21:12:23.228305533Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"12(@)"}
210
+ {"time":"2026-08-06T21:12:23.467551186Z","level":"INFO","msg":"handleInformInit: received","streamId":"bg578kxx","id":"12(@)"}
211
+ {"time":"2026-08-06T21:12:23.730830089Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"bg578kxx","id":"12(@)"}
212
+ {"time":"2026-08-06T21:12:29.071098063Z","level":"INFO","msg":"connection: cancelling request","id":"12(@)","requestId":"uw7ylvshe19o"}
213
+ {"time":"2026-08-06T21:17:48.564799797Z","level":"INFO","msg":"connection: cancelling request","id":"12(@)","requestId":"uw7ylvshe19o"}
214
+ {"time":"2026-08-06T21:17:49.248999487Z","level":"INFO","msg":"connection: cancelling request","id":"12(@)","requestId":"uw7ylvshe19o"}
215
+ {"time":"2026-08-06T21:17:49.25757284Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"bg578kxx","id":"12(@)"}
216
+ {"time":"2026-08-06T21:17:49.258204596Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"bg578kxx","id":"12(@)"}
217
+ {"time":"2026-08-06T21:17:51.216079094Z","level":"INFO","msg":"processOutgoingData: finished","id":"12(@)"}
218
+ {"time":"2026-08-06T21:17:51.216072239Z","level":"INFO","msg":"connection: closing","id":"12(@)"}
219
+ {"time":"2026-08-06T21:17:51.216179866Z","level":"INFO","msg":"connection: closed successfully","id":"12(@)"}
220
+ {"time":"2026-08-06T21:17:51.216185068Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"12(@)"}
221
+ {"time":"2026-08-06T21:17:58.492557811Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"13(@)"}
222
+ {"time":"2026-08-06T21:17:58.67148951Z","level":"INFO","msg":"handleInformInit: received","streamId":"et66wpfp","id":"13(@)"}
223
+ {"time":"2026-08-06T21:17:58.929501734Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"et66wpfp","id":"13(@)"}
224
+ {"time":"2026-08-06T21:18:04.245453961Z","level":"INFO","msg":"connection: cancelling request","id":"13(@)","requestId":"lhdvtgg70ea4"}
225
+ {"time":"2026-08-06T21:23:39.596723237Z","level":"INFO","msg":"connection: cancelling request","id":"13(@)","requestId":"lhdvtgg70ea4"}
226
+ {"time":"2026-08-06T21:23:40.337073726Z","level":"INFO","msg":"connection: cancelling request","id":"13(@)","requestId":"lhdvtgg70ea4"}
227
+ {"time":"2026-08-06T21:23:40.345953532Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"et66wpfp","id":"13(@)"}
228
+ {"time":"2026-08-06T21:23:40.346749897Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"et66wpfp","id":"13(@)"}
229
+ {"time":"2026-08-06T21:23:41.788308924Z","level":"INFO","msg":"connection: closing","id":"13(@)"}
230
+ {"time":"2026-08-06T21:23:41.788416199Z","level":"INFO","msg":"connection: closed successfully","id":"13(@)"}
231
+ {"time":"2026-08-06T21:23:41.788322Z","level":"INFO","msg":"processOutgoingData: finished","id":"13(@)"}
232
+ {"time":"2026-08-06T21:23:41.788429036Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"13(@)"}
233
+ {"time":"2026-08-06T21:23:49.09450616Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"14(@)"}
234
+ {"time":"2026-08-06T21:23:49.262302742Z","level":"INFO","msg":"handleInformInit: received","streamId":"khl56ofx","id":"14(@)"}
235
+ {"time":"2026-08-06T21:23:49.52021693Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"khl56ofx","id":"14(@)"}
236
+ {"time":"2026-08-06T21:23:54.866290658Z","level":"INFO","msg":"connection: cancelling request","id":"14(@)","requestId":"qky58qgzcva8"}
237
+ {"time":"2026-08-06T21:29:21.67482211Z","level":"INFO","msg":"connection: cancelling request","id":"14(@)","requestId":"qky58qgzcva8"}
238
+ {"time":"2026-08-06T21:29:22.58105129Z","level":"INFO","msg":"connection: cancelling request","id":"14(@)","requestId":"qky58qgzcva8"}
239
+ {"time":"2026-08-06T21:29:22.589480032Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"khl56ofx","id":"14(@)"}
240
+ {"time":"2026-08-06T21:29:22.590122391Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"khl56ofx","id":"14(@)"}
241
+ {"time":"2026-08-06T21:29:24.515242519Z","level":"INFO","msg":"connection: closing","id":"14(@)"}
242
+ {"time":"2026-08-06T21:29:24.51533068Z","level":"INFO","msg":"connection: closed successfully","id":"14(@)"}
243
+ {"time":"2026-08-06T21:29:24.515249386Z","level":"INFO","msg":"processOutgoingData: finished","id":"14(@)"}
244
+ {"time":"2026-08-06T21:29:24.515339803Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"14(@)"}
245
+ {"time":"2026-08-06T21:29:31.942325053Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"15(@)"}
246
+ {"time":"2026-08-06T21:29:32.173598531Z","level":"INFO","msg":"handleInformInit: received","streamId":"4imkt5vi","id":"15(@)"}
247
+ {"time":"2026-08-06T21:29:32.432359343Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"4imkt5vi","id":"15(@)"}
248
+ {"time":"2026-08-06T21:29:37.739318379Z","level":"INFO","msg":"connection: cancelling request","id":"15(@)","requestId":"9nvowy3r168s"}
249
+ {"time":"2026-08-06T21:37:29.12441145Z","level":"INFO","msg":"connection: cancelling request","id":"15(@)","requestId":"9nvowy3r168s"}
250
+ {"time":"2026-08-06T21:37:30.409147798Z","level":"INFO","msg":"connection: cancelling request","id":"15(@)","requestId":"9nvowy3r168s"}
251
+ {"time":"2026-08-06T21:37:30.426750357Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"4imkt5vi","id":"15(@)"}
252
+ {"time":"2026-08-06T21:37:30.427491444Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"4imkt5vi","id":"15(@)"}
253
+ {"time":"2026-08-06T21:37:32.430981419Z","level":"INFO","msg":"processOutgoingData: finished","id":"15(@)"}
254
+ {"time":"2026-08-06T21:37:32.430981727Z","level":"INFO","msg":"connection: closing","id":"15(@)"}
255
+ {"time":"2026-08-06T21:37:32.431084379Z","level":"INFO","msg":"connection: closed successfully","id":"15(@)"}
256
+ {"time":"2026-08-06T21:37:32.431089742Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"15(@)"}
257
+ {"time":"2026-08-06T21:37:40.18018664Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"16(@)"}
258
+ {"time":"2026-08-06T21:37:40.385174957Z","level":"INFO","msg":"handleInformInit: received","streamId":"9e1cur4e","id":"16(@)"}
259
+ {"time":"2026-08-06T21:37:40.645608571Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"9e1cur4e","id":"16(@)"}
260
+ {"time":"2026-08-06T21:37:46.020841955Z","level":"INFO","msg":"connection: cancelling request","id":"16(@)","requestId":"e63qralmxroy"}
261
+ {"time":"2026-08-06T21:45:44.504944903Z","level":"INFO","msg":"connection: cancelling request","id":"16(@)","requestId":"e63qralmxroy"}
262
+ {"time":"2026-08-06T21:45:45.829542922Z","level":"INFO","msg":"connection: cancelling request","id":"16(@)","requestId":"e63qralmxroy"}
263
+ {"time":"2026-08-06T21:45:45.846894286Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"9e1cur4e","id":"16(@)"}
264
+ {"time":"2026-08-06T21:45:45.847774659Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"9e1cur4e","id":"16(@)"}
265
+ {"time":"2026-08-06T21:45:47.840474379Z","level":"INFO","msg":"connection: closing","id":"16(@)"}
266
+ {"time":"2026-08-06T21:45:47.840570823Z","level":"INFO","msg":"connection: closed successfully","id":"16(@)"}
267
+ {"time":"2026-08-06T21:45:47.840483537Z","level":"INFO","msg":"processOutgoingData: finished","id":"16(@)"}
268
+ {"time":"2026-08-06T21:45:47.840582986Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"16(@)"}
269
+ {"time":"2026-08-06T21:45:55.262958851Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"17(@)"}
270
+ {"time":"2026-08-06T21:45:55.469011896Z","level":"INFO","msg":"handleInformInit: received","streamId":"al1jdpoz","id":"17(@)"}
271
+ {"time":"2026-08-06T21:45:55.727539722Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"al1jdpoz","id":"17(@)"}
272
+ {"time":"2026-08-06T21:46:01.122943223Z","level":"INFO","msg":"connection: cancelling request","id":"17(@)","requestId":"93lxyszdkp4s"}
273
+ {"time":"2026-08-06T21:53:51.88662296Z","level":"INFO","msg":"connection: cancelling request","id":"17(@)","requestId":"93lxyszdkp4s"}
274
+ {"time":"2026-08-06T21:53:53.216806274Z","level":"INFO","msg":"connection: cancelling request","id":"17(@)","requestId":"93lxyszdkp4s"}
275
+ {"time":"2026-08-06T21:53:53.234315065Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"al1jdpoz","id":"17(@)"}
276
+ {"time":"2026-08-06T21:53:53.235006365Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"al1jdpoz","id":"17(@)"}
277
+ {"time":"2026-08-06T21:53:54.719889867Z","level":"INFO","msg":"connection: closing","id":"17(@)"}
278
+ {"time":"2026-08-06T21:53:54.71996882Z","level":"INFO","msg":"connection: closed successfully","id":"17(@)"}
279
+ {"time":"2026-08-06T21:53:54.719896895Z","level":"INFO","msg":"processOutgoingData: finished","id":"17(@)"}
280
+ {"time":"2026-08-06T21:53:54.719978015Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"17(@)"}
281
+ {"time":"2026-08-06T21:54:02.704682357Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"18(@)"}
282
+ {"time":"2026-08-06T21:54:02.926309852Z","level":"INFO","msg":"handleInformInit: received","streamId":"xj8o3fye","id":"18(@)"}
283
+ {"time":"2026-08-06T21:54:03.190237343Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"xj8o3fye","id":"18(@)"}
284
+ {"time":"2026-08-06T21:54:08.572923545Z","level":"INFO","msg":"connection: cancelling request","id":"18(@)","requestId":"wp88z9hofgto"}
285
+ {"time":"2026-08-06T22:01:58.949861095Z","level":"INFO","msg":"connection: cancelling request","id":"18(@)","requestId":"wp88z9hofgto"}
286
+ {"time":"2026-08-06T22:02:00.413196665Z","level":"INFO","msg":"connection: cancelling request","id":"18(@)","requestId":"wp88z9hofgto"}
287
+ {"time":"2026-08-06T22:02:00.430424345Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"xj8o3fye","id":"18(@)"}
288
+ {"time":"2026-08-06T22:02:00.431151699Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"xj8o3fye","id":"18(@)"}
289
+ {"time":"2026-08-06T22:02:02.48611794Z","level":"INFO","msg":"connection: closing","id":"18(@)"}
290
+ {"time":"2026-08-06T22:02:02.486205017Z","level":"INFO","msg":"connection: closed successfully","id":"18(@)"}
291
+ {"time":"2026-08-06T22:02:02.486123904Z","level":"INFO","msg":"processOutgoingData: finished","id":"18(@)"}
292
+ {"time":"2026-08-06T22:02:02.48621421Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"18(@)"}
293
+ {"time":"2026-08-06T22:02:10.269940778Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"19(@)"}
294
+ {"time":"2026-08-06T22:02:10.439113476Z","level":"INFO","msg":"handleInformInit: received","streamId":"y74jog3n","id":"19(@)"}
295
+ {"time":"2026-08-06T22:02:10.698054902Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"y74jog3n","id":"19(@)"}
296
+ {"time":"2026-08-06T22:02:16.042923531Z","level":"INFO","msg":"connection: cancelling request","id":"19(@)","requestId":"zee4komq248b"}
297
+ {"time":"2026-08-06T22:10:40.201957301Z","level":"INFO","msg":"connection: cancelling request","id":"19(@)","requestId":"zee4komq248b"}
298
+ {"time":"2026-08-06T22:10:41.673521316Z","level":"INFO","msg":"connection: cancelling request","id":"19(@)","requestId":"zee4komq248b"}
299
+ {"time":"2026-08-06T22:10:41.690938257Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"y74jog3n","id":"19(@)"}
300
+ {"time":"2026-08-06T22:10:41.691692107Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"y74jog3n","id":"19(@)"}
301
+ {"time":"2026-08-06T22:10:43.724610654Z","level":"INFO","msg":"connection: closing","id":"19(@)"}
302
+ {"time":"2026-08-06T22:10:43.724616012Z","level":"INFO","msg":"processOutgoingData: finished","id":"19(@)"}
303
+ {"time":"2026-08-06T22:10:43.724709021Z","level":"INFO","msg":"connection: closed successfully","id":"19(@)"}
304
+ {"time":"2026-08-06T22:10:43.724714942Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"19(@)"}
305
+ {"time":"2026-08-06T22:10:51.347033931Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"20(@)"}
306
+ {"time":"2026-08-06T22:10:51.560725873Z","level":"INFO","msg":"handleInformInit: received","streamId":"mmhv6fed","id":"20(@)"}
307
+ {"time":"2026-08-06T22:10:51.824628616Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"mmhv6fed","id":"20(@)"}
308
+ {"time":"2026-08-06T22:10:57.222474886Z","level":"INFO","msg":"connection: cancelling request","id":"20(@)","requestId":"m8oneq7o9rzj"}
309
+ {"time":"2026-08-06T22:19:09.602074687Z","level":"INFO","msg":"connection: cancelling request","id":"20(@)","requestId":"m8oneq7o9rzj"}
310
+ {"time":"2026-08-06T22:19:11.114939367Z","level":"INFO","msg":"connection: cancelling request","id":"20(@)","requestId":"m8oneq7o9rzj"}
311
+ {"time":"2026-08-06T22:19:11.131701315Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"mmhv6fed","id":"20(@)"}
312
+ {"time":"2026-08-06T22:19:11.132470276Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"mmhv6fed","id":"20(@)"}
313
+ {"time":"2026-08-06T22:19:13.207296331Z","level":"INFO","msg":"connection: closing","id":"20(@)"}
314
+ {"time":"2026-08-06T22:19:13.207397849Z","level":"INFO","msg":"connection: closed successfully","id":"20(@)"}
315
+ {"time":"2026-08-06T22:19:13.207306165Z","level":"INFO","msg":"processOutgoingData: finished","id":"20(@)"}
316
+ {"time":"2026-08-06T22:19:13.207408716Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"20(@)"}
317
+ {"time":"2026-08-06T22:19:20.777260921Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"21(@)"}
318
+ {"time":"2026-08-06T22:19:20.987353307Z","level":"INFO","msg":"handleInformInit: received","streamId":"2u9w6sh8","id":"21(@)"}
319
+ {"time":"2026-08-06T22:19:21.245435793Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"2u9w6sh8","id":"21(@)"}
320
+ {"time":"2026-08-06T22:19:26.590992416Z","level":"INFO","msg":"connection: cancelling request","id":"21(@)","requestId":"map9ky32c65b"}
321
+ {"time":"2026-08-06T22:32:11.823573406Z","level":"INFO","msg":"connection: cancelling request","id":"21(@)","requestId":"map9ky32c65b"}
322
+ {"time":"2026-08-06T22:32:14.003255108Z","level":"INFO","msg":"connection: cancelling request","id":"21(@)","requestId":"map9ky32c65b"}
323
+ {"time":"2026-08-06T22:32:14.332589446Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"2u9w6sh8","id":"21(@)"}
324
+ {"time":"2026-08-06T22:32:14.333311597Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"2u9w6sh8","id":"21(@)"}
325
+ {"time":"2026-08-06T22:32:16.374866238Z","level":"INFO","msg":"connection: closing","id":"21(@)"}
326
+ {"time":"2026-08-06T22:32:16.374875872Z","level":"INFO","msg":"processOutgoingData: finished","id":"21(@)"}
327
+ {"time":"2026-08-06T22:32:16.374948978Z","level":"INFO","msg":"connection: closed successfully","id":"21(@)"}
328
+ {"time":"2026-08-06T22:32:16.374969822Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"21(@)"}
329
+ {"time":"2026-08-06T22:32:24.229326154Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"22(@)"}
330
+ {"time":"2026-08-06T22:32:24.316080626Z","level":"INFO","msg":"handleInformInit: received","streamId":"qz489gza","id":"22(@)"}
331
+ {"time":"2026-08-06T22:32:24.575636983Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"qz489gza","id":"22(@)"}
332
+ {"time":"2026-08-06T22:32:30.136334704Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
333
+ {"time":"2026-08-06T22:45:25.631649058Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
334
+ {"time":"2026-08-06T22:45:27.004459218Z","level":"INFO","msg":"connection: cancelling request","id":"22(@)","requestId":"3xuhlvh7p4qd"}
335
+ {"time":"2026-08-06T22:45:27.32624292Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"qz489gza","id":"22(@)"}
336
+ {"time":"2026-08-06T22:45:27.328474372Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"qz489gza","id":"22(@)"}
337
+ {"time":"2026-08-06T22:45:29.337669198Z","level":"INFO","msg":"connection: closing","id":"22(@)"}
338
+ {"time":"2026-08-06T22:45:29.337779491Z","level":"INFO","msg":"connection: closed successfully","id":"22(@)"}
339
+ {"time":"2026-08-06T22:45:29.337689564Z","level":"INFO","msg":"processOutgoingData: finished","id":"22(@)"}
340
+ {"time":"2026-08-06T22:45:29.33778783Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"22(@)"}
341
+ {"time":"2026-08-06T22:45:37.17939079Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"23(@)"}
342
+ {"time":"2026-08-06T22:45:37.25952131Z","level":"INFO","msg":"handleInformInit: received","streamId":"4k21flpq","id":"23(@)"}
343
+ {"time":"2026-08-06T22:45:37.520210586Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"4k21flpq","id":"23(@)"}
344
+ {"time":"2026-08-06T22:45:42.854176028Z","level":"INFO","msg":"connection: cancelling request","id":"23(@)","requestId":"pgphnf19ojfr"}
wandb/run-20260806_224537-4k21flpq/logs/debug-internal.log ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2026-08-06T22:45:37.259672476Z","level":"INFO","msg":"wandb-core"}
2
+ {"time":"2026-08-06T22:45:37.259787782Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
3
+ {"time":"2026-08-06T22:45:37.520030085Z","level":"INFO","msg":"stream: created new stream","id":"4k21flpq"}
4
+ {"time":"2026-08-06T22:45:37.520098596Z","level":"INFO","msg":"handler: started"}
5
+ {"time":"2026-08-06T22:45:37.520204581Z","level":"INFO","msg":"stream: started"}
6
+ {"time":"2026-08-06T22:45:37.520215062Z","level":"INFO","msg":"writer: started","stream_id":"4k21flpq"}
7
+ {"time":"2026-08-06T22:45:37.520234257Z","level":"INFO","msg":"sender: started"}
8
+ {"time":"2026-08-06T22:45:38.046912533Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
9
+ {"time":"2026-08-06T22:45:38.147486179Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
10
+ {"time":"2026-08-06T22:45:45.516616674Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":445}
11
+ {"time":"2026-08-06T22:45:45.519205981Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":883}
12
+ {"time":"2026-08-06T22:45:45.520246025Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":1785}
13
+ {"time":"2026-08-06T22:45:45.520509526Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":63}
14
+ {"time":"2026-08-06T22:45:45.525068197Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":3641}
15
+ {"time":"2026-08-06T22:45:45.525228019Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":10}
16
+ {"time":"2026-08-06T22:45:45.527329699Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":4518}
17
+ {"time":"2026-08-06T22:45:45.531557362Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":1518}
18
+ {"time":"2026-08-06T22:45:45.531912786Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":6183}
19
+ {"time":"2026-08-06T22:45:45.532357942Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":116}
20
+ {"time":"2026-08-06T22:45:45.535523288Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":7423}
21
+ {"time":"2026-08-06T22:45:45.535624893Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":9}
22
+ {"time":"2026-08-06T22:45:45.535769966Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":7483}
23
+ {"time":"2026-08-06T22:45:45.53597386Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":47}
24
+ {"time":"2026-08-06T22:45:45.536534683Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":7705}
25
+ {"time":"2026-08-06T22:45:45.557843071Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":6522}
26
+ {"time":"2026-08-06T22:45:45.558217274Z","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":14275}
27
+ {"time":"2026-08-06T22:45:45.558252901Z","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":1}
28
+ {"time":"2026-08-06T22:45:53.091394425Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":2,"events_offset":0,"events_lines":2,"console_offset":1,"console_lines":5,"uploaded_len":2}
29
+ {"time":"2026-08-06T22:45:54.053809924Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
30
+ {"time":"2026-08-06T22:46:08.066629374Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":2,"history_lines":3,"events_offset":2,"events_lines":2,"console_offset":3,"console_lines":1}
31
+ {"time":"2026-08-06T22:46:09.169528606Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
32
+ {"time":"2026-08-06T22:46:23.066167056Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":5,"history_lines":2,"events_offset":4,"events_lines":2,"console_offset":3,"console_lines":1}
33
+ {"time":"2026-08-06T22:46:24.163272873Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
34
+ {"time":"2026-08-06T22:46:38.064525724Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":7,"history_lines":3,"events_offset":6,"events_lines":2,"console_offset":3,"console_lines":1}
35
+ {"time":"2026-08-06T22:46:39.226014587Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
36
+ {"time":"2026-08-06T22:46:53.065607372Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":10,"history_lines":1,"events_offset":8,"events_lines":2,"console_offset":3,"console_lines":1}
37
+ {"time":"2026-08-06T22:46:54.224816288Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
38
+ {"time":"2026-08-06T22:47:08.094013281Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":11,"history_lines":2,"events_offset":10,"events_lines":2,"console_offset":3,"console_lines":1}
39
+ {"time":"2026-08-06T22:47:09.288236737Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
wandb/run-20260806_224537-4k21flpq/logs/debug.log ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2026-08-06 22:45:37,258 INFO MainThread:1695277 [wandb_setup.py:_flush():81] Current SDK version is 0.28.1
2
+ 2026-08-06 22:45:37,258 INFO MainThread:1695277 [wandb_setup.py:_flush():81] Configure stats pid to 1695277
3
+ 2026-08-06 22:45:37,258 INFO MainThread:1695277 [wandb_setup.py:_flush():81] Loading settings from environment variables
4
+ 2026-08-06 22:45:37,258 INFO MainThread:1695277 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/Activation/wandb/run-20260806_224537-4k21flpq/logs/debug.log
5
+ 2026-08-06 22:45:37,258 INFO MainThread:1695277 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/Activation/wandb/run-20260806_224537-4k21flpq/logs/debug-internal.log
6
+ 2026-08-06 22:45:37,258 INFO MainThread:1695277 [wandb_init.py:init():772] calling init triggers
7
+ 2026-08-06 22:45:37,258 INFO MainThread:1695277 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
8
+ config: {'_wandb': {}}
9
+ 2026-08-06 22:45:37,258 INFO MainThread:1695277 [wandb_init.py:init():820] starting backend
10
+ 2026-08-06 22:45:37,258 INFO MainThread:1695277 [wandb_init.py:init():826] Connected to an existing wandb-core service via WANDB_SERVICE
11
+ 2026-08-06 22:45:37,258 INFO MainThread:1695277 [wandb_init.py:init():835] sending inform_init request
12
+ 2026-08-06 22:45:37,520 INFO MainThread:1695277 [wandb_init.py:init():840] backend started and connected
13
+ 2026-08-06 22:45:37,524 INFO MainThread:1695277 [wandb_init.py:init():910] updated telemetry
14
+ 2026-08-06 22:45:37,530 INFO MainThread:1695277 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
15
+ 2026-08-06 22:45:37,779 INFO MainThread:1695277 [wandb_init.py:init():978] starting run threads in backend
16
+ 2026-08-06 22:45:37,851 INFO MainThread:1695277 [wandb_run.py:_console_start():2621] atexit reg
17
+ 2026-08-06 22:45:37,851 INFO MainThread:1695277 [wandb_run.py:_redirect():2471] redirect: wrap_raw
18
+ 2026-08-06 22:45:37,851 INFO MainThread:1695277 [wandb_run.py:_redirect():2540] Wrapping output streams.
19
+ 2026-08-06 22:45:37,851 INFO MainThread:1695277 [wandb_run.py:_redirect():2563] Redirects installed.
20
+ 2026-08-06 22:45:37,854 INFO MainThread:1695277 [wandb_init.py:init():1016] run started, returning control to user process
21
+ 2026-08-06 22:45:37,855 INFO MainThread:1695277 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.15.0.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': 94, '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': 'gelu', 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-gelu-94L_run', 'per_device_train_batch_size': 64, 'num_train_epochs': 1, 'max_steps': 2000, 'learning_rate': 0.0003, 'lr_scheduler_type': 'constant', 'lr_scheduler_kwargs': None, 'warmup_steps': 0, 'optim': 'adamw_torch', 'optim_args': None, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 1.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-gelu-94L-15.9M-20260806-224536', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 200, 'eval_delay': 0, 'per_device_eval_batch_size': 64, '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': 500, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': True, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/ACTio-glu-gelu-94L', '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}
22
+ 2026-08-06 22:45:37,859 INFO MainThread:1695277 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 15949440 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x1537681738d0>>
23
+ 2026-08-06 22:45:37,859 INFO MainThread:1695277 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 15949440 None
wandb/run-20260806_224537-4k21flpq/run-4k21flpq.wandb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11bb6a78a69faf31fc9c24fbeaa515939e89afec6e5960535b0e276ce0e530fe
3
+ size 11304960