w-ahmad commited on
Commit
49f1ec3
·
verified ·
1 Parent(s): 6fb43e3

Auto upload zain 2026-08-12T19:27:28.533354

Browse files
Files changed (37) hide show
  1. zain/Activation/out/glu-waleed10-150L_run/checkpoint-1000/config.json +36 -0
  2. zain/Activation/out/glu-waleed10-150L_run/checkpoint-1000/model.safetensors +3 -0
  3. zain/Activation/out/glu-waleed10-150L_run/checkpoint-1000/optimizer.pt +3 -0
  4. zain/Activation/out/glu-waleed10-150L_run/checkpoint-1000/rng_state.pth +3 -0
  5. zain/Activation/out/glu-waleed10-150L_run/checkpoint-1000/scheduler.pt +3 -0
  6. zain/Activation/out/glu-waleed10-150L_run/checkpoint-1000/tokenizer.json +0 -0
  7. zain/Activation/out/glu-waleed10-150L_run/checkpoint-1000/tokenizer_config.json +13 -0
  8. zain/Activation/out/glu-waleed10-150L_run/checkpoint-1000/trainer_state.json +544 -0
  9. zain/Activation/out/glu-waleed10-150L_run/checkpoint-1000/training_args.bin +3 -0
  10. zain/Activation/out/glu-waleed10-150L_run/config.json +36 -0
  11. zain/Activation/out/glu-waleed10-150L_run/model.safetensors +3 -0
  12. zain/Activation/out/glu-waleed10-150L_run/tokenizer.json +0 -0
  13. zain/Activation/out/glu-waleed10-150L_run/tokenizer_config.json +13 -0
  14. zain/Activation/out/glu-waleed10-150L_run/training_args.bin +3 -0
  15. zain/Activation/out/glu-waleed10-150L_run/training_log.jsonl +21 -0
  16. zain/Activation/out/mlp-waleed10-150L_run/training_log.jsonl +5 -0
  17. zain/Activation/wandb/debug-internal.log +15 -91
  18. zain/Activation/wandb/debug.log +19 -19
  19. zain/Activation/wandb/run-20260812_175304-hrggki9k/logs/debug-core.log +7 -0
  20. zain/Activation/wandb/run-20260812_180713-utqzlg67/logs/debug-core.log +7 -0
  21. zain/Activation/wandb/run-20260812_182126-vyycsg6r/logs/debug-core.log +7 -0
  22. zain/Activation/wandb/run-20260812_183823-qtstmmvv/logs/debug-core.log +7 -0
  23. zain/Activation/wandb/run-20260812_185803-0fh9o8ec/logs/debug-core.log +7 -0
  24. zain/Activation/wandb/run-20260812_191207-w1cgnksl/files/config.yaml +445 -0
  25. zain/Activation/wandb/run-20260812_191207-w1cgnksl/files/output.log +30 -0
  26. zain/Activation/wandb/run-20260812_191207-w1cgnksl/files/wandb-summary.json +1 -0
  27. zain/Activation/wandb/run-20260812_191207-w1cgnksl/logs/debug-core.log +7 -0
  28. zain/Activation/wandb/run-20260812_191207-w1cgnksl/logs/debug-internal.log +40 -0
  29. zain/Activation/wandb/run-20260812_191207-w1cgnksl/logs/debug.log +5 -0
  30. zain/Activation/wandb/run-20260812_191207-w1cgnksl/run-w1cgnksl.wandb +2 -2
  31. zain/Activation/wandb/run-20260812_192631-1pwkdnr5/files/output.log +7 -0
  32. zain/Activation/wandb/run-20260812_192631-1pwkdnr5/files/requirements.txt +149 -0
  33. zain/Activation/wandb/run-20260812_192631-1pwkdnr5/files/wandb-metadata.json +107 -0
  34. zain/Activation/wandb/run-20260812_192631-1pwkdnr5/logs/debug-core.log +62 -0
  35. zain/Activation/wandb/run-20260812_192631-1pwkdnr5/logs/debug-internal.log +15 -0
  36. zain/Activation/wandb/run-20260812_192631-1pwkdnr5/logs/debug.log +20 -0
  37. zain/Activation/wandb/run-20260812_192631-1pwkdnr5/run-1pwkdnr5.wandb +0 -0
zain/Activation/out/glu-waleed10-150L_run/checkpoint-1000/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "waleed10",
3
+ "architectures": [
4
+ "TinyLlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 2,
11
+ "head_dim": 32,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 128,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 256,
16
+ "max_position_embeddings": 512,
17
+ "mlp_bias": false,
18
+ "mlp_type": "glu",
19
+ "model_type": "tiny_llama",
20
+ "num_attention_heads": 4,
21
+ "num_hidden_layers": 150,
22
+ "num_key_value_heads": 4,
23
+ "pad_token_id": 0,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-06,
26
+ "rope_parameters": {
27
+ "rope_theta": 10000.0,
28
+ "rope_type": "default"
29
+ },
30
+ "tie_word_embeddings": true,
31
+ "tokenizer_name": "w-ahmad/tiny-stories-tokenizer",
32
+ "transformers_version": "5.16.0.dev0",
33
+ "use_cache": false,
34
+ "vocab_size": 4096,
35
+ "waleed_beta": 10.0
36
+ }
zain/Activation/out/glu-waleed10-150L_run/checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0bbc5061b5746a1abd74321f4d52b94e18a8b3abf811112813f560c23d95160
3
+ size 50427120
zain/Activation/out/glu-waleed10-150L_run/checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6fca940bd99ac474f90e5dacf5a970e815f3a186a3d2d1f6fe8f4873b32e3e7
3
+ size 101708778
zain/Activation/out/glu-waleed10-150L_run/checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:645b71843375baf4cc10bc75a2f0f04e91b8e3f8e8929f518a87022898b3bc20
3
+ size 14244
zain/Activation/out/glu-waleed10-150L_run/checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9db76f238494a413266398860b344c6c4c0f3a045ef78b23af1afac6775a12d1
3
+ size 1064
zain/Activation/out/glu-waleed10-150L_run/checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
zain/Activation/out/glu-waleed10-150L_run/checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1024,
10
+ "pad_token": "<|endoftext|>",
11
+ "tokenizer_class": "GPT2Tokenizer",
12
+ "unk_token": "<|endoftext|>"
13
+ }
zain/Activation/out/glu-waleed10-150L_run/checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,544 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.06740815638692282,
6
+ "eval_steps": 50,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0013481631277384564,
14
+ "grad_norm": 1.2578125,
15
+ "learning_rate": 0.000475,
16
+ "loss": 7.956694793701172,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 0.002696326255476913,
21
+ "grad_norm": 0.8671875,
22
+ "learning_rate": 0.0009750000000000001,
23
+ "loss": 6.816313171386719,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 0.003370407819346141,
28
+ "eval_loss": 6.036281108856201,
29
+ "eval_runtime": 21.4504,
30
+ "eval_samples_per_second": 444.14,
31
+ "eval_steps_per_second": 3.496,
32
+ "step": 50
33
+ },
34
+ {
35
+ "epoch": 0.004044489383215369,
36
+ "grad_norm": 0.2421875,
37
+ "learning_rate": 0.001475,
38
+ "loss": 6.075027084350586,
39
+ "step": 60
40
+ },
41
+ {
42
+ "epoch": 0.005392652510953826,
43
+ "grad_norm": 0.85546875,
44
+ "learning_rate": 0.001975,
45
+ "loss": 5.990496826171875,
46
+ "step": 80
47
+ },
48
+ {
49
+ "epoch": 0.006740815638692282,
50
+ "grad_norm": 0.640625,
51
+ "learning_rate": 0.002475,
52
+ "loss": 5.911588287353515,
53
+ "step": 100
54
+ },
55
+ {
56
+ "epoch": 0.006740815638692282,
57
+ "eval_loss": 5.984175205230713,
58
+ "eval_runtime": 21.5004,
59
+ "eval_samples_per_second": 443.108,
60
+ "eval_steps_per_second": 3.488,
61
+ "step": 100
62
+ },
63
+ {
64
+ "epoch": 0.008088978766430738,
65
+ "grad_norm": 0.162109375,
66
+ "learning_rate": 0.0029749999999999998,
67
+ "loss": 5.884429931640625,
68
+ "step": 120
69
+ },
70
+ {
71
+ "epoch": 0.009437141894169195,
72
+ "grad_norm": 0.298828125,
73
+ "learning_rate": 0.003475,
74
+ "loss": 5.951210403442383,
75
+ "step": 140
76
+ },
77
+ {
78
+ "epoch": 0.010111223458038422,
79
+ "eval_loss": 6.011711120605469,
80
+ "eval_runtime": 21.6362,
81
+ "eval_samples_per_second": 440.327,
82
+ "eval_steps_per_second": 3.466,
83
+ "step": 150
84
+ },
85
+ {
86
+ "epoch": 0.010785305021907651,
87
+ "grad_norm": 0.28125,
88
+ "learning_rate": 0.003975,
89
+ "loss": 6.013200759887695,
90
+ "step": 160
91
+ },
92
+ {
93
+ "epoch": 0.012133468149646108,
94
+ "grad_norm": 0.20703125,
95
+ "learning_rate": 0.004475,
96
+ "loss": 5.959984207153321,
97
+ "step": 180
98
+ },
99
+ {
100
+ "epoch": 0.013481631277384564,
101
+ "grad_norm": 0.5,
102
+ "learning_rate": 0.004975,
103
+ "loss": 5.930151748657226,
104
+ "step": 200
105
+ },
106
+ {
107
+ "epoch": 0.013481631277384564,
108
+ "eval_loss": 5.93806791305542,
109
+ "eval_runtime": 21.3179,
110
+ "eval_samples_per_second": 446.901,
111
+ "eval_steps_per_second": 3.518,
112
+ "step": 200
113
+ },
114
+ {
115
+ "epoch": 0.01482979440512302,
116
+ "grad_norm": 0.125,
117
+ "learning_rate": 0.005,
118
+ "loss": 5.9299774169921875,
119
+ "step": 220
120
+ },
121
+ {
122
+ "epoch": 0.016177957532861477,
123
+ "grad_norm": 0.158203125,
124
+ "learning_rate": 0.005,
125
+ "loss": 5.916062545776367,
126
+ "step": 240
127
+ },
128
+ {
129
+ "epoch": 0.016852039096730706,
130
+ "eval_loss": 5.9525370597839355,
131
+ "eval_runtime": 21.3951,
132
+ "eval_samples_per_second": 445.288,
133
+ "eval_steps_per_second": 3.505,
134
+ "step": 250
135
+ },
136
+ {
137
+ "epoch": 0.01752612066059993,
138
+ "grad_norm": 0.1572265625,
139
+ "learning_rate": 0.005,
140
+ "loss": 5.9636791229248045,
141
+ "step": 260
142
+ },
143
+ {
144
+ "epoch": 0.01887428378833839,
145
+ "grad_norm": 0.1435546875,
146
+ "learning_rate": 0.005,
147
+ "loss": 5.89407958984375,
148
+ "step": 280
149
+ },
150
+ {
151
+ "epoch": 0.020222446916076844,
152
+ "grad_norm": 0.2265625,
153
+ "learning_rate": 0.005,
154
+ "loss": 5.739504623413086,
155
+ "step": 300
156
+ },
157
+ {
158
+ "epoch": 0.020222446916076844,
159
+ "eval_loss": 5.6643242835998535,
160
+ "eval_runtime": 21.4329,
161
+ "eval_samples_per_second": 444.504,
162
+ "eval_steps_per_second": 3.499,
163
+ "step": 300
164
+ },
165
+ {
166
+ "epoch": 0.021570610043815303,
167
+ "grad_norm": 0.330078125,
168
+ "learning_rate": 0.005,
169
+ "loss": 5.6463062286376955,
170
+ "step": 320
171
+ },
172
+ {
173
+ "epoch": 0.022918773171553757,
174
+ "grad_norm": 0.34765625,
175
+ "learning_rate": 0.005,
176
+ "loss": 5.56775131225586,
177
+ "step": 340
178
+ },
179
+ {
180
+ "epoch": 0.023592854735422986,
181
+ "eval_loss": 5.537689685821533,
182
+ "eval_runtime": 21.4426,
183
+ "eval_samples_per_second": 444.302,
184
+ "eval_steps_per_second": 3.498,
185
+ "step": 350
186
+ },
187
+ {
188
+ "epoch": 0.024266936299292215,
189
+ "grad_norm": 0.1875,
190
+ "learning_rate": 0.005,
191
+ "loss": 5.534560775756836,
192
+ "step": 360
193
+ },
194
+ {
195
+ "epoch": 0.02561509942703067,
196
+ "grad_norm": 0.66015625,
197
+ "learning_rate": 0.005,
198
+ "loss": 5.449129104614258,
199
+ "step": 380
200
+ },
201
+ {
202
+ "epoch": 0.026963262554769128,
203
+ "grad_norm": 0.35546875,
204
+ "learning_rate": 0.005,
205
+ "loss": 5.375603103637696,
206
+ "step": 400
207
+ },
208
+ {
209
+ "epoch": 0.026963262554769128,
210
+ "eval_loss": 5.315079689025879,
211
+ "eval_runtime": 21.3923,
212
+ "eval_samples_per_second": 445.348,
213
+ "eval_steps_per_second": 3.506,
214
+ "step": 400
215
+ },
216
+ {
217
+ "epoch": 0.028311425682507583,
218
+ "grad_norm": 1.0859375,
219
+ "learning_rate": 0.005,
220
+ "loss": 5.217065048217774,
221
+ "step": 420
222
+ },
223
+ {
224
+ "epoch": 0.02965958881024604,
225
+ "grad_norm": 0.56640625,
226
+ "learning_rate": 0.005,
227
+ "loss": 5.086183166503906,
228
+ "step": 440
229
+ },
230
+ {
231
+ "epoch": 0.030333670374115267,
232
+ "eval_loss": 4.963188171386719,
233
+ "eval_runtime": 21.415,
234
+ "eval_samples_per_second": 444.876,
235
+ "eval_steps_per_second": 3.502,
236
+ "step": 450
237
+ },
238
+ {
239
+ "epoch": 0.031007751937984496,
240
+ "grad_norm": 0.279296875,
241
+ "learning_rate": 0.005,
242
+ "loss": 4.954313278198242,
243
+ "step": 460
244
+ },
245
+ {
246
+ "epoch": 0.032355915065722954,
247
+ "grad_norm": 0.33984375,
248
+ "learning_rate": 0.005,
249
+ "loss": 4.772397994995117,
250
+ "step": 480
251
+ },
252
+ {
253
+ "epoch": 0.03370407819346141,
254
+ "grad_norm": 0.79296875,
255
+ "learning_rate": 0.005,
256
+ "loss": 4.591049575805664,
257
+ "step": 500
258
+ },
259
+ {
260
+ "epoch": 0.03370407819346141,
261
+ "eval_loss": 4.6361846923828125,
262
+ "eval_runtime": 21.393,
263
+ "eval_samples_per_second": 445.332,
264
+ "eval_steps_per_second": 3.506,
265
+ "step": 500
266
+ },
267
+ {
268
+ "epoch": 0.03505224132119986,
269
+ "grad_norm": 0.431640625,
270
+ "learning_rate": 0.005,
271
+ "loss": 4.517485809326172,
272
+ "step": 520
273
+ },
274
+ {
275
+ "epoch": 0.03640040444893832,
276
+ "grad_norm": 0.5390625,
277
+ "learning_rate": 0.005,
278
+ "loss": 4.398628234863281,
279
+ "step": 540
280
+ },
281
+ {
282
+ "epoch": 0.03707448601280755,
283
+ "eval_loss": 4.3811798095703125,
284
+ "eval_runtime": 21.3845,
285
+ "eval_samples_per_second": 445.509,
286
+ "eval_steps_per_second": 3.507,
287
+ "step": 550
288
+ },
289
+ {
290
+ "epoch": 0.03774856757667678,
291
+ "grad_norm": 0.341796875,
292
+ "learning_rate": 0.005,
293
+ "loss": 4.385685729980469,
294
+ "step": 560
295
+ },
296
+ {
297
+ "epoch": 0.03909673070441524,
298
+ "grad_norm": 0.3984375,
299
+ "learning_rate": 0.005,
300
+ "loss": 4.322913742065429,
301
+ "step": 580
302
+ },
303
+ {
304
+ "epoch": 0.04044489383215369,
305
+ "grad_norm": 0.43359375,
306
+ "learning_rate": 0.005,
307
+ "loss": 4.283470535278321,
308
+ "step": 600
309
+ },
310
+ {
311
+ "epoch": 0.04044489383215369,
312
+ "eval_loss": 4.249608039855957,
313
+ "eval_runtime": 21.2819,
314
+ "eval_samples_per_second": 447.658,
315
+ "eval_steps_per_second": 3.524,
316
+ "step": 600
317
+ },
318
+ {
319
+ "epoch": 0.04179305695989215,
320
+ "grad_norm": 0.58203125,
321
+ "learning_rate": 0.005,
322
+ "loss": 4.265676116943359,
323
+ "step": 620
324
+ },
325
+ {
326
+ "epoch": 0.043141220087630605,
327
+ "grad_norm": 0.7578125,
328
+ "learning_rate": 0.005,
329
+ "loss": 4.22065544128418,
330
+ "step": 640
331
+ },
332
+ {
333
+ "epoch": 0.043815301651499834,
334
+ "eval_loss": 4.480190277099609,
335
+ "eval_runtime": 21.4147,
336
+ "eval_samples_per_second": 444.882,
337
+ "eval_steps_per_second": 3.502,
338
+ "step": 650
339
+ },
340
+ {
341
+ "epoch": 0.044489383215369056,
342
+ "grad_norm": 1.75,
343
+ "learning_rate": 0.005,
344
+ "loss": 4.3253837585449215,
345
+ "step": 660
346
+ },
347
+ {
348
+ "epoch": 0.045837546343107514,
349
+ "grad_norm": 0.50390625,
350
+ "learning_rate": 0.005,
351
+ "loss": 4.34516487121582,
352
+ "step": 680
353
+ },
354
+ {
355
+ "epoch": 0.04718570947084597,
356
+ "grad_norm": 1.4765625,
357
+ "learning_rate": 0.005,
358
+ "loss": 4.221965408325195,
359
+ "step": 700
360
+ },
361
+ {
362
+ "epoch": 0.04718570947084597,
363
+ "eval_loss": 4.238162517547607,
364
+ "eval_runtime": 21.3466,
365
+ "eval_samples_per_second": 446.3,
366
+ "eval_steps_per_second": 3.513,
367
+ "step": 700
368
+ },
369
+ {
370
+ "epoch": 0.04853387259858443,
371
+ "grad_norm": 2.96875,
372
+ "learning_rate": 0.005,
373
+ "loss": 4.538877868652344,
374
+ "step": 720
375
+ },
376
+ {
377
+ "epoch": 0.04988203572632288,
378
+ "grad_norm": 2.53125,
379
+ "learning_rate": 0.005,
380
+ "loss": 4.674048614501953,
381
+ "step": 740
382
+ },
383
+ {
384
+ "epoch": 0.05055611729019211,
385
+ "eval_loss": 4.746744632720947,
386
+ "eval_runtime": 21.2691,
387
+ "eval_samples_per_second": 447.926,
388
+ "eval_steps_per_second": 3.526,
389
+ "step": 750
390
+ },
391
+ {
392
+ "epoch": 0.05123019885406134,
393
+ "grad_norm": 0.82421875,
394
+ "learning_rate": 0.005,
395
+ "loss": 4.683749771118164,
396
+ "step": 760
397
+ },
398
+ {
399
+ "epoch": 0.0525783619817998,
400
+ "grad_norm": 1.140625,
401
+ "learning_rate": 0.005,
402
+ "loss": 4.658499908447266,
403
+ "step": 780
404
+ },
405
+ {
406
+ "epoch": 0.053926525109538256,
407
+ "grad_norm": 1.1640625,
408
+ "learning_rate": 0.005,
409
+ "loss": 4.581509017944336,
410
+ "step": 800
411
+ },
412
+ {
413
+ "epoch": 0.053926525109538256,
414
+ "eval_loss": 4.618558406829834,
415
+ "eval_runtime": 21.2574,
416
+ "eval_samples_per_second": 448.173,
417
+ "eval_steps_per_second": 3.528,
418
+ "step": 800
419
+ },
420
+ {
421
+ "epoch": 0.05527468823727671,
422
+ "grad_norm": 4.53125,
423
+ "learning_rate": 0.005,
424
+ "loss": 4.660457992553711,
425
+ "step": 820
426
+ },
427
+ {
428
+ "epoch": 0.056622851365015166,
429
+ "grad_norm": 1.4296875,
430
+ "learning_rate": 0.005,
431
+ "loss": 4.6169921875,
432
+ "step": 840
433
+ },
434
+ {
435
+ "epoch": 0.057296932928884395,
436
+ "eval_loss": 4.634304046630859,
437
+ "eval_runtime": 21.4419,
438
+ "eval_samples_per_second": 444.317,
439
+ "eval_steps_per_second": 3.498,
440
+ "step": 850
441
+ },
442
+ {
443
+ "epoch": 0.057971014492753624,
444
+ "grad_norm": 0.78125,
445
+ "learning_rate": 0.005,
446
+ "loss": 4.649558258056641,
447
+ "step": 860
448
+ },
449
+ {
450
+ "epoch": 0.05931917762049208,
451
+ "grad_norm": 9.0625,
452
+ "learning_rate": 0.005,
453
+ "loss": 4.607862091064453,
454
+ "step": 880
455
+ },
456
+ {
457
+ "epoch": 0.06066734074823053,
458
+ "grad_norm": 2.796875,
459
+ "learning_rate": 0.005,
460
+ "loss": 4.670491409301758,
461
+ "step": 900
462
+ },
463
+ {
464
+ "epoch": 0.06066734074823053,
465
+ "eval_loss": 4.753029823303223,
466
+ "eval_runtime": 21.4319,
467
+ "eval_samples_per_second": 444.524,
468
+ "eval_steps_per_second": 3.499,
469
+ "step": 900
470
+ },
471
+ {
472
+ "epoch": 0.06201550387596899,
473
+ "grad_norm": 2.421875,
474
+ "learning_rate": 0.005,
475
+ "loss": 4.759043121337891,
476
+ "step": 920
477
+ },
478
+ {
479
+ "epoch": 0.06336366700370745,
480
+ "grad_norm": 1.921875,
481
+ "learning_rate": 0.005,
482
+ "loss": 4.756998062133789,
483
+ "step": 940
484
+ },
485
+ {
486
+ "epoch": 0.06403774856757667,
487
+ "eval_loss": 4.92280912399292,
488
+ "eval_runtime": 21.4588,
489
+ "eval_samples_per_second": 443.967,
490
+ "eval_steps_per_second": 3.495,
491
+ "step": 950
492
+ },
493
+ {
494
+ "epoch": 0.06471183013144591,
495
+ "grad_norm": 3.65625,
496
+ "learning_rate": 0.005,
497
+ "loss": 4.919535827636719,
498
+ "step": 960
499
+ },
500
+ {
501
+ "epoch": 0.06605999325918437,
502
+ "grad_norm": 39.75,
503
+ "learning_rate": 0.005,
504
+ "loss": 4.9029693603515625,
505
+ "step": 980
506
+ },
507
+ {
508
+ "epoch": 0.06740815638692282,
509
+ "grad_norm": 18.375,
510
+ "learning_rate": 0.005,
511
+ "loss": 5.32824821472168,
512
+ "step": 1000
513
+ },
514
+ {
515
+ "epoch": 0.06740815638692282,
516
+ "eval_loss": 5.330815315246582,
517
+ "eval_runtime": 21.4264,
518
+ "eval_samples_per_second": 444.638,
519
+ "eval_steps_per_second": 3.5,
520
+ "step": 1000
521
+ }
522
+ ],
523
+ "logging_steps": 20,
524
+ "max_steps": 1000,
525
+ "num_input_tokens_seen": 0,
526
+ "num_train_epochs": 1,
527
+ "save_steps": 1000,
528
+ "stateful_callbacks": {
529
+ "TrainerControl": {
530
+ "args": {
531
+ "should_epoch_stop": false,
532
+ "should_evaluate": false,
533
+ "should_log": false,
534
+ "should_save": true,
535
+ "should_training_stop": true
536
+ },
537
+ "attributes": {}
538
+ }
539
+ },
540
+ "total_flos": 4839413121024000.0,
541
+ "train_batch_size": 64,
542
+ "trial_name": null,
543
+ "trial_params": null
544
+ }
zain/Activation/out/glu-waleed10-150L_run/checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13e651baa06a6483caa944bd1bd9b2ffc5d0334408573c8642d0fc0ab01bde7b
3
+ size 4920
zain/Activation/out/glu-waleed10-150L_run/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "waleed10",
3
+ "architectures": [
4
+ "TinyLlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 2,
11
+ "head_dim": 32,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 128,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 256,
16
+ "max_position_embeddings": 512,
17
+ "mlp_bias": false,
18
+ "mlp_type": "glu",
19
+ "model_type": "tiny_llama",
20
+ "num_attention_heads": 4,
21
+ "num_hidden_layers": 150,
22
+ "num_key_value_heads": 4,
23
+ "pad_token_id": 0,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-06,
26
+ "rope_parameters": {
27
+ "rope_theta": 10000.0,
28
+ "rope_type": "default"
29
+ },
30
+ "tie_word_embeddings": true,
31
+ "tokenizer_name": "w-ahmad/tiny-stories-tokenizer",
32
+ "transformers_version": "5.16.0.dev0",
33
+ "use_cache": false,
34
+ "vocab_size": 4096,
35
+ "waleed_beta": 10.0
36
+ }
zain/Activation/out/glu-waleed10-150L_run/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0bbc5061b5746a1abd74321f4d52b94e18a8b3abf811112813f560c23d95160
3
+ size 50427120
zain/Activation/out/glu-waleed10-150L_run/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
zain/Activation/out/glu-waleed10-150L_run/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1024,
10
+ "pad_token": "<|endoftext|>",
11
+ "tokenizer_class": "GPT2Tokenizer",
12
+ "unk_token": "<|endoftext|>"
13
+ }
zain/Activation/out/glu-waleed10-150L_run/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13e651baa06a6483caa944bd1bd9b2ffc5d0334408573c8642d0fc0ab01bde7b
3
+ size 4920
zain/Activation/out/glu-waleed10-150L_run/training_log.jsonl CHANGED
@@ -49,3 +49,24 @@
49
  {"step": 700, "epoch": 0.04718570947084597, "timestamp": 1786562516.6689005, "eval_loss": 4.238162517547607, "eval_runtime": 21.3466, "eval_samples_per_second": 446.3, "eval_steps_per_second": 3.513, "train/total_time_seconds": 253.456104490906, "train/time_per_step_avg": 0.35650765791535377, "train/epoch_time_elapsed": 588.4872120581567, "train/estimated_remaining_minutes": 1.8104007463636145}
50
  {"step": 720, "epoch": 0.04853387259858443, "timestamp": 1786562524.9873672, "loss": 4.538877868652344, "grad_norm": 2.96875, "learning_rate": 0.005, "train/total_time_seconds": 260.77417112514377, "train/time_per_step_avg": 0.3587497878447175, "train/epoch_time_elapsed": 596.805680077523, "train/estimated_remaining_minutes": 1.6902029609963023}
51
  {"step": 740, "epoch": 0.04988203572632288, "timestamp": 1786562533.3492465, "loss": 4.674048614501953, "grad_norm": 2.53125, "learning_rate": 0.005, "train/total_time_seconds": 268.12411511316895, "train/time_per_step_avg": 0.3615063236653805, "train/epoch_time_elapsed": 605.1675585322082, "train/estimated_remaining_minutes": 1.57009616958162}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49
  {"step": 700, "epoch": 0.04718570947084597, "timestamp": 1786562516.6689005, "eval_loss": 4.238162517547607, "eval_runtime": 21.3466, "eval_samples_per_second": 446.3, "eval_steps_per_second": 3.513, "train/total_time_seconds": 253.456104490906, "train/time_per_step_avg": 0.35650765791535377, "train/epoch_time_elapsed": 588.4872120581567, "train/estimated_remaining_minutes": 1.8104007463636145}
50
  {"step": 720, "epoch": 0.04853387259858443, "timestamp": 1786562524.9873672, "loss": 4.538877868652344, "grad_norm": 2.96875, "learning_rate": 0.005, "train/total_time_seconds": 260.77417112514377, "train/time_per_step_avg": 0.3587497878447175, "train/epoch_time_elapsed": 596.805680077523, "train/estimated_remaining_minutes": 1.6902029609963023}
51
  {"step": 740, "epoch": 0.04988203572632288, "timestamp": 1786562533.3492465, "loss": 4.674048614501953, "grad_norm": 2.53125, "learning_rate": 0.005, "train/total_time_seconds": 268.12411511316895, "train/time_per_step_avg": 0.3615063236653805, "train/epoch_time_elapsed": 605.1675585322082, "train/estimated_remaining_minutes": 1.57009616958162}
52
+ {"step": 750, "epoch": 0.05055611729019211, "timestamp": 1786562558.677904, "eval_loss": 4.746744632720947, "eval_runtime": 21.2691, "eval_samples_per_second": 447.926, "eval_steps_per_second": 3.526, "train/total_time_seconds": 271.6843276694417, "train/time_per_step_avg": 0.36172512706369164, "train/epoch_time_elapsed": 630.496215172112, "train/estimated_remaining_minutes": 1.5093573759413426}
53
+ {"step": 760, "epoch": 0.05123019885406134, "timestamp": 1786562562.710026, "loss": 4.683749771118164, "grad_norm": 0.82421875, "learning_rate": 0.005, "train/total_time_seconds": 275.21573022753, "train/time_per_step_avg": 0.3618581830337644, "train/epoch_time_elapsed": 634.5283385068178, "train/estimated_remaining_minutes": 1.4485038433027895}
54
+ {"step": 780, "epoch": 0.0525783619817998, "timestamp": 1786562570.7748256, "loss": 4.658499908447266, "grad_norm": 1.140625, "learning_rate": 0.005, "train/total_time_seconds": 282.28284257650375, "train/time_per_step_avg": 0.3588425332307816, "train/epoch_time_elapsed": 642.5931377857924, "train/estimated_remaining_minutes": 1.3269706274963853}
55
+ {"step": 800, "epoch": 0.053926525109538256, "timestamp": 1786562578.8528824, "loss": 4.581509017944336, "grad_norm": 1.1640625, "learning_rate": 0.005, "train/total_time_seconds": 289.35492124035954, "train/time_per_step_avg": 0.35898816749453544, "train/epoch_time_elapsed": 650.6711945161223, "train/estimated_remaining_minutes": 1.2056455051681647}
56
+ {"step": 800, "epoch": 0.053926525109538256, "timestamp": 1786562600.1118803, "eval_loss": 4.618558406829834, "eval_runtime": 21.2574, "eval_samples_per_second": 448.173, "eval_steps_per_second": 3.528, "train/total_time_seconds": 289.35492124035954, "train/time_per_step_avg": 0.35898816749453544, "train/epoch_time_elapsed": 671.9301917403936, "train/estimated_remaining_minutes": 1.2056455051681647}
57
+ {"step": 820, "epoch": 0.05527468823727671, "timestamp": 1786562608.451814, "loss": 4.660457992553711, "grad_norm": 4.53125, "learning_rate": 0.005, "train/total_time_seconds": 296.70877849683166, "train/time_per_step_avg": 0.3593460737168789, "train/epoch_time_elapsed": 680.2701258845627, "train/estimated_remaining_minutes": 1.0855199213298719}
58
+ {"step": 840, "epoch": 0.056622851365015166, "timestamp": 1786562616.509304, "loss": 4.6169921875, "grad_norm": 1.4296875, "learning_rate": 0.005, "train/total_time_seconds": 303.78451693430543, "train/time_per_step_avg": 0.3566040182113647, "train/epoch_time_elapsed": 688.3276160620153, "train/estimated_remaining_minutes": 0.9643952918549379}
59
+ {"step": 850, "epoch": 0.057296932928884395, "timestamp": 1786562642.0177486, "eval_loss": 4.634304046630859, "eval_runtime": 21.4419, "eval_samples_per_second": 444.317, "eval_steps_per_second": 3.498, "train/total_time_seconds": 307.3349942751229, "train/time_per_step_avg": 0.3565066660568118, "train/epoch_time_elapsed": 713.8360601328313, "train/estimated_remaining_minutes": 0.9039264537503614}
60
+ {"step": 860, "epoch": 0.057971014492753624, "timestamp": 1786562646.1646216, "loss": 4.649558258056641, "grad_norm": 0.78125, "learning_rate": 0.005, "train/total_time_seconds": 310.98093512281775, "train/time_per_step_avg": 0.3576520489528775, "train/epoch_time_elapsed": 717.9829167090356, "train/estimated_remaining_minutes": 0.8437467232014435}
61
+ {"step": 880, "epoch": 0.05931917762049208, "timestamp": 1786562654.4958792, "loss": 4.607862091064453, "grad_norm": 9.0625, "learning_rate": 0.005, "train/total_time_seconds": 318.3036971911788, "train/time_per_step_avg": 0.36020854614675046, "train/epoch_time_elapsed": 726.3141922354698, "train/estimated_remaining_minutes": 0.7234174936163155}
62
+ {"step": 900, "epoch": 0.06066734074823053, "timestamp": 1786562662.9036863, "loss": 4.670491409301758, "grad_norm": 2.796875, "learning_rate": 0.005, "train/total_time_seconds": 325.68520964309573, "train/time_per_step_avg": 0.3633028840273619, "train/epoch_time_elapsed": 734.7219991981983, "train/estimated_remaining_minutes": 0.6031207585983255}
63
+ {"step": 900, "epoch": 0.06066734074823053, "timestamp": 1786562684.3371463, "eval_loss": 4.753029823303223, "eval_runtime": 21.4319, "eval_samples_per_second": 444.524, "eval_steps_per_second": 3.499, "train/total_time_seconds": 325.68520964309573, "train/time_per_step_avg": 0.3633028840273619, "train/epoch_time_elapsed": 756.1554586701095, "train/estimated_remaining_minutes": 0.6031207585983255}
64
+ {"step": 920, "epoch": 0.06201550387596899, "timestamp": 1786562692.670801, "loss": 4.759043121337891, "grad_norm": 2.421875, "learning_rate": 0.005, "train/total_time_seconds": 333.00877467542887, "train/time_per_step_avg": 0.3629999617859721, "train/epoch_time_elapsed": 764.4891140051186, "train/estimated_remaining_minutes": 0.4826214125730853}
65
+ {"step": 940, "epoch": 0.06336366700370745, "timestamp": 1786562700.9855404, "loss": 4.756998062133789, "grad_norm": 1.921875, "learning_rate": 0.005, "train/total_time_seconds": 340.331928499043, "train/time_per_step_avg": 0.3654741156473756, "train/epoch_time_elapsed": 772.8038536123931, "train/estimated_remaining_minutes": 0.36205524308408826}
66
+ {"step": 950, "epoch": 0.06403774856757667, "timestamp": 1786562726.8764348, "eval_loss": 4.92280912399292, "eval_runtime": 21.4588, "eval_samples_per_second": 443.967, "eval_steps_per_second": 3.495, "train/total_time_seconds": 344.2607752121985, "train/time_per_step_avg": 0.36925780937075614, "train/epoch_time_elapsed": 798.6947453357279, "train/estimated_remaining_minutes": 0.3019831361510513}
67
+ {"step": 960, "epoch": 0.06471183013144591, "timestamp": 1786562730.8847861, "loss": 4.919535827636719, "grad_norm": 3.65625, "learning_rate": 0.005, "train/total_time_seconds": 347.78044006973505, "train/time_per_step_avg": 0.36799504946917294, "train/epoch_time_elapsed": 802.7030985429883, "train/estimated_remaining_minutes": 0.24151419449287156}
68
+ {"step": 980, "epoch": 0.06605999325918437, "timestamp": 1786562738.9220173, "loss": 4.9029693603515625, "grad_norm": 39.75, "learning_rate": 0.005, "train/total_time_seconds": 354.8349937200546, "train/time_per_step_avg": 0.3653129652887583, "train/epoch_time_elapsed": 810.7403297461569, "train/estimated_remaining_minutes": 0.12069217473471247}
69
+ {"step": 1000, "epoch": 0.06740815638692282, "timestamp": 1786562746.9712386, "loss": 5.32824821472168, "grad_norm": 18.375, "learning_rate": 0.005, "train/total_time_seconds": 361.9019044712186, "train/time_per_step_avg": 0.36216694828122853, "train/epoch_time_elapsed": 818.7895508781075, "train/estimated_remaining_minutes": 0.0}
70
+ {"step": 1000, "epoch": 0.06740815638692282, "timestamp": 1786562768.3991892, "eval_loss": 5.330815315246582, "eval_runtime": 21.4264, "eval_samples_per_second": 444.638, "eval_steps_per_second": 3.5, "train/total_time_seconds": 361.9019044712186, "train/time_per_step_avg": 0.36216694828122853, "train/epoch_time_elapsed": 840.2175006978214, "train/estimated_remaining_minutes": 0.0}
71
+ {"step": 1000, "epoch": 0.06740815638692282, "timestamp": 1786562768.8314016, "train_runtime": 841.3959, "train_samples_per_second": 76.064, "train_steps_per_second": 1.189, "total_flos": 4839413121024000.0, "train_loss": 5.168452629089355, "train/total_time_seconds": 361.9019044712186, "train/time_per_step_avg": 0.36216694828122853, "train/epoch_time_elapsed": 840.6497106775641, "train/estimated_remaining_minutes": 0.0}
72
+ {"step": 1000, "epoch": 0.06740815638692282, "timestamp": 1786562790.2892313, "eval_loss": 5.330815315246582, "eval_runtime": 21.4546, "eval_samples_per_second": 444.055, "eval_steps_per_second": 3.496, "train/total_time_seconds": 361.9019044712186, "train/time_per_step_avg": 0.36216694828122853, "train/epoch_time_elapsed": 862.107542693615, "train/estimated_remaining_minutes": 0.0}
zain/Activation/out/mlp-waleed10-150L_run/training_log.jsonl ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {"step": 20, "epoch": 0.0013481631277384564, "timestamp": 1786562801.3040552, "loss": 7.9166419982910154, "grad_norm": 1.3046875, "learning_rate": 0.000475, "train/total_time_seconds": 7.589067380875349, "train/time_per_step_avg": 0.3794533690437675, "train/epoch_time_elapsed": 8.675439741462469, "train/estimated_remaining_minutes": 6.197738361048201}
2
+ {"step": 40, "epoch": 0.002696326255476913, "timestamp": 1786562809.1780546, "loss": 6.784420776367187, "grad_norm": 0.98828125, "learning_rate": 0.0009750000000000001, "train/total_time_seconds": 14.459735240787268, "train/time_per_step_avg": 0.3614933810196817, "train/epoch_time_elapsed": 16.549439433962107, "train/estimated_remaining_minutes": 5.783894096314907}
3
+ {"step": 50, "epoch": 0.003370407819346141, "timestamp": 1786562833.987479, "eval_loss": 6.158936977386475, "eval_runtime": 20.8926, "eval_samples_per_second": 455.998, "eval_steps_per_second": 3.59, "train/total_time_seconds": 17.88253027200699, "train/time_per_step_avg": 0.35765060544013977, "train/epoch_time_elapsed": 41.358862437307835, "train/estimated_remaining_minutes": 5.662801252802213}
4
+ {"step": 60, "epoch": 0.004044489383215369, "timestamp": 1786562838.0563142, "loss": 6.296163558959961, "grad_norm": 0.2734375, "learning_rate": 0.001475, "train/total_time_seconds": 21.40728884190321, "train/time_per_step_avg": 0.3567881473650535, "train/epoch_time_elapsed": 45.42769941687584, "train/estimated_remaining_minutes": 5.589680975385837}
5
+ {"step": 80, "epoch": 0.005392652510953826, "timestamp": 1786562845.9679003, "loss": 6.782315063476562, "grad_norm": 0.65625, "learning_rate": 0.001975, "train/total_time_seconds": 28.30780665948987, "train/time_per_step_avg": 0.35384758324362336, "train/epoch_time_elapsed": 53.339285012334585, "train/estimated_remaining_minutes": 5.425662943068891}
zain/Activation/wandb/debug-internal.log CHANGED
@@ -1,91 +1,15 @@
1
- {"time":"2026-08-12T19:12:07.497196304Z","level":"INFO","msg":"wandb-core"}
2
- {"time":"2026-08-12T19:12:07.497332182Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
3
- {"time":"2026-08-12T19:12:07.759577369Z","level":"INFO","msg":"stream: created new stream","id":"w1cgnksl"}
4
- {"time":"2026-08-12T19:12:07.759657193Z","level":"INFO","msg":"handler: started"}
5
- {"time":"2026-08-12T19:12:07.759784998Z","level":"INFO","msg":"stream: started"}
6
- {"time":"2026-08-12T19:12:07.759790925Z","level":"INFO","msg":"writer: started","stream_id":"w1cgnksl"}
7
- {"time":"2026-08-12T19:12:07.759842787Z","level":"INFO","msg":"sender: started"}
8
- {"time":"2026-08-12T19:12:09.060585544Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
9
- {"time":"2026-08-12T19:12:09.183194227Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
10
- {"time":"2026-08-12T19:12:24.061611124Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":1,"events_offset":0,"events_lines":2,"console_offset":0,"console_lines":2,"uploaded_len":2}
11
- {"time":"2026-08-12T19:12:24.181068505Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
12
- {"time":"2026-08-12T19:12:39.061114447Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":1,"history_lines":1,"events_offset":2,"events_lines":2,"console_offset":0,"console_lines":1}
13
- {"time":"2026-08-12T19:12:39.193740537Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
14
- {"time":"2026-08-12T19:12:54.06092764Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":2,"history_lines":1,"events_offset":4,"events_lines":2,"console_offset":0,"console_lines":1}
15
- {"time":"2026-08-12T19:12:54.205324978Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
16
- {"time":"2026-08-12T19:13:09.0610196Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":3,"history_lines":2,"events_offset":6,"events_lines":2,"console_offset":0,"console_lines":1}
17
- {"time":"2026-08-12T19:13:09.199437414Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
18
- {"time":"2026-08-12T19:13:24.0610101Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":5,"history_lines":1,"events_offset":8,"events_lines":2,"console_offset":0,"console_lines":1}
19
- {"time":"2026-08-12T19:13:24.180648331Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
20
- {"time":"2026-08-12T19:13:39.061168723Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":6,"history_lines":1,"events_offset":10,"events_lines":2,"console_offset":0,"console_lines":1}
21
- {"time":"2026-08-12T19:13:39.218037773Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
22
- {"time":"2026-08-12T19:13:54.061478676Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":7,"history_lines":2,"events_offset":12,"events_lines":2,"console_offset":0,"console_lines":1}
23
- {"time":"2026-08-12T19:13:54.174031009Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
24
- {"time":"2026-08-12T19:14:09.06082511Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":14,"events_lines":2,"console_offset":2,"console_lines":9}
25
- {"time":"2026-08-12T19:14:09.277738797Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
26
- {"time":"2026-08-12T19:14:24.061189035Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":9,"history_lines":2,"events_offset":16,"events_lines":2,"console_offset":0,"console_lines":1}
27
- {"time":"2026-08-12T19:14:24.210094589Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
28
- {"time":"2026-08-12T19:14:39.062085229Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":11,"history_lines":2,"events_offset":18,"events_lines":2,"console_offset":0,"console_lines":1}
29
- {"time":"2026-08-12T19:14:39.181918654Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
30
- {"time":"2026-08-12T19:14:54.061684683Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":20,"events_lines":2,"console_offset":3,"console_lines":1}
31
- {"time":"2026-08-12T19:14:54.205688627Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
32
- {"time":"2026-08-12T19:15:09.061278005Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":13,"history_lines":2,"events_offset":22,"events_lines":2,"console_offset":0,"console_lines":1}
33
- {"time":"2026-08-12T19:15:09.201507717Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
34
- {"time":"2026-08-12T19:15:24.060821842Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":15,"history_lines":1,"events_offset":24,"events_lines":2,"console_offset":0,"console_lines":1}
35
- {"time":"2026-08-12T19:15:24.178151466Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
36
- {"time":"2026-08-12T19:15:39.061227122Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":26,"events_lines":2,"console_offset":3,"console_lines":1}
37
- {"time":"2026-08-12T19:15:39.17104444Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
38
- {"time":"2026-08-12T19:15:54.061172015Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":16,"history_lines":3,"events_offset":28,"events_lines":2,"console_offset":0,"console_lines":1}
39
- {"time":"2026-08-12T19:15:54.199661839Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
40
- {"time":"2026-08-12T19:16:09.060855612Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":19,"history_lines":1,"events_offset":30,"events_lines":2,"console_offset":0,"console_lines":1}
41
- {"time":"2026-08-12T19:16:09.203956042Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
42
- {"time":"2026-08-12T19:16:24.060906721Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":20,"history_lines":1,"events_offset":32,"events_lines":2,"console_offset":0,"console_lines":1}
43
- {"time":"2026-08-12T19:16:24.18124757Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
44
- {"time":"2026-08-12T19:16:39.060765624Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":21,"history_lines":2,"events_offset":34,"events_lines":2,"console_offset":0,"console_lines":1}
45
- {"time":"2026-08-12T19:16:39.183442122Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
46
- {"time":"2026-08-12T19:16:54.060724758Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":36,"events_lines":2,"console_offset":0,"console_lines":1}
47
- {"time":"2026-08-12T19:16:54.169381693Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
48
- {"time":"2026-08-12T19:17:09.060868179Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":23,"history_lines":2,"events_offset":38,"events_lines":2,"console_offset":0,"console_lines":1}
49
- {"time":"2026-08-12T19:17:09.215007025Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
50
- {"time":"2026-08-12T19:17:24.060863895Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":25,"history_lines":1,"events_offset":40,"events_lines":2,"console_offset":0,"console_lines":1}
51
- {"time":"2026-08-12T19:17:24.188633325Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
52
- {"time":"2026-08-12T19:17:39.060792481Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":26,"history_lines":1,"events_offset":42,"events_lines":2,"console_offset":0,"console_lines":1}
53
- {"time":"2026-08-12T19:17:39.210094375Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
54
- {"time":"2026-08-12T19:17:54.061471204Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":27,"history_lines":1,"events_offset":44,"events_lines":2,"console_offset":0,"console_lines":1}
55
- {"time":"2026-08-12T19:17:54.199418171Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
56
- {"time":"2026-08-12T19:18:09.061000182Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":28,"history_lines":2,"events_offset":46,"events_lines":2,"console_offset":0,"console_lines":1}
57
- {"time":"2026-08-12T19:18:09.209093897Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
58
- {"time":"2026-08-12T19:18:24.060763863Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":48,"events_lines":2,"console_offset":3,"console_lines":1}
59
- {"time":"2026-08-12T19:18:24.1773145Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
60
- {"time":"2026-08-12T19:18:39.061681015Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":30,"history_lines":2,"events_offset":50,"events_lines":2,"console_offset":0,"console_lines":1}
61
- {"time":"2026-08-12T19:18:39.213849305Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
62
- {"time":"2026-08-12T19:18:54.061564717Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":32,"history_lines":2,"events_offset":52,"events_lines":2,"console_offset":3,"console_lines":1}
63
- {"time":"2026-08-12T19:18:54.183311031Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
64
- {"time":"2026-08-12T19:19:09.06124697Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":54,"events_lines":2,"console_offset":11,"console_lines":25}
65
- {"time":"2026-08-12T19:19:09.197160601Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
66
- {"time":"2026-08-12T19:19:24.061371815Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":34,"history_lines":2,"events_offset":56,"events_lines":2,"console_offset":36,"console_lines":2}
67
- {"time":"2026-08-12T19:19:24.169446986Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
68
- {"time":"2026-08-12T19:19:39.061619239Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":36,"history_lines":1,"events_offset":58,"events_lines":2,"console_offset":38,"console_lines":1}
69
- {"time":"2026-08-12T19:19:39.184700489Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
70
- {"time":"2026-08-12T19:19:54.061005576Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":37,"history_lines":1,"events_offset":60,"events_lines":2,"console_offset":39,"console_lines":1}
71
- {"time":"2026-08-12T19:19:54.203579208Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
72
- {"time":"2026-08-12T19:20:09.061544887Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":38,"history_lines":2,"events_offset":62,"events_lines":2,"console_offset":40,"console_lines":2}
73
- {"time":"2026-08-12T19:20:09.209145123Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
74
- {"time":"2026-08-12T19:20:24.061085273Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":40,"history_lines":1,"events_offset":64,"events_lines":2,"console_offset":42,"console_lines":1}
75
- {"time":"2026-08-12T19:20:24.180324215Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
76
- {"time":"2026-08-12T19:20:39.061567669Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":41,"history_lines":1,"events_offset":66,"events_lines":2,"console_offset":43,"console_lines":1}
77
- {"time":"2026-08-12T19:20:39.187049132Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
78
- {"time":"2026-08-12T19:20:54.060876869Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":42,"history_lines":2,"events_offset":68,"events_lines":2,"console_offset":44,"console_lines":2}
79
- {"time":"2026-08-12T19:20:54.208534847Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
80
- {"time":"2026-08-12T19:21:09.061014024Z","level":"INFO","msg":"filestream: sending request","total_files":1,"events_offset":70,"events_lines":2}
81
- {"time":"2026-08-12T19:21:09.205590728Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
82
- {"time":"2026-08-12T19:21:24.061230217Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":44,"history_lines":2,"events_offset":72,"events_lines":2,"console_offset":46,"console_lines":2}
83
- {"time":"2026-08-12T19:21:24.169771183Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
84
- {"time":"2026-08-12T19:21:39.061283547Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":46,"history_lines":2,"events_offset":74,"events_lines":2,"console_offset":48,"console_lines":2}
85
- {"time":"2026-08-12T19:21:39.17408722Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
86
- {"time":"2026-08-12T19:21:54.061571591Z","level":"INFO","msg":"filestream: sending request","total_files":1,"events_offset":76,"events_lines":2}
87
- {"time":"2026-08-12T19:21:54.160013406Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
88
- {"time":"2026-08-12T19:22:09.061421365Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":48,"history_lines":2,"events_offset":78,"events_lines":2,"console_offset":50,"console_lines":2}
89
- {"time":"2026-08-12T19:22:09.255653996Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
90
- {"time":"2026-08-12T19:22:24.061485993Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":50,"history_lines":1,"events_offset":80,"events_lines":2,"console_offset":52,"console_lines":1}
91
- {"time":"2026-08-12T19:22:24.206976463Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
 
1
+ {"time":"2026-08-12T19:26:32.010129578Z","level":"INFO","msg":"wandb-core"}
2
+ {"time":"2026-08-12T19:26:32.010264802Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
3
+ {"time":"2026-08-12T19:26:32.273779818Z","level":"INFO","msg":"stream: created new stream","id":"1pwkdnr5"}
4
+ {"time":"2026-08-12T19:26:32.273844939Z","level":"INFO","msg":"handler: started"}
5
+ {"time":"2026-08-12T19:26:32.273961668Z","level":"INFO","msg":"stream: started"}
6
+ {"time":"2026-08-12T19:26:32.273969985Z","level":"INFO","msg":"writer: started","stream_id":"1pwkdnr5"}
7
+ {"time":"2026-08-12T19:26:32.273991847Z","level":"INFO","msg":"sender: started"}
8
+ {"time":"2026-08-12T19:26:33.472626381Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
9
+ {"time":"2026-08-12T19:26:33.580547558Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
10
+ {"time":"2026-08-12T19:26:48.47323809Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":1,"events_offset":0,"events_lines":2,"console_offset":0,"console_lines":2,"uploaded_len":2}
11
+ {"time":"2026-08-12T19:26:48.600344001Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
12
+ {"time":"2026-08-12T19:27:03.473267558Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":1,"history_lines":1,"events_offset":2,"events_lines":2,"console_offset":0,"console_lines":1}
13
+ {"time":"2026-08-12T19:27:03.610205342Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
14
+ {"time":"2026-08-12T19:27:18.473731434Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":2,"history_lines":2,"events_offset":4,"events_lines":2,"console_offset":0,"console_lines":1}
15
+ {"time":"2026-08-12T19:27:18.592911793Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
zain/Activation/wandb/debug.log CHANGED
@@ -1,20 +1,20 @@
1
- 2026-08-12 19:12:07,495 INFO MainThread:1371664 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_191207-w1cgnksl/logs/debug.log
2
- 2026-08-12 19:12:07,496 INFO MainThread:1371664 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_191207-w1cgnksl/logs/debug-internal.log
3
- 2026-08-12 19:12:07,496 INFO MainThread:1371664 [wandb_init.py:init():772] calling init triggers
4
- 2026-08-12 19:12:07,496 INFO MainThread:1371664 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
5
  config: {'_wandb': {}}
6
- 2026-08-12 19:12:07,496 INFO MainThread:1371664 [wandb_init.py:init():820] starting backend
7
- 2026-08-12 19:12:07,496 INFO MainThread:1371664 [wandb_init.py:init():826] Connected to an existing wandb-core service via WANDB_SERVICE
8
- 2026-08-12 19:12:07,496 INFO MainThread:1371664 [wandb_init.py:init():835] sending inform_init request
9
- 2026-08-12 19:12:07,760 INFO MainThread:1371664 [wandb_init.py:init():840] backend started and connected
10
- 2026-08-12 19:12:07,761 INFO MainThread:1371664 [wandb_init.py:init():910] updated telemetry
11
- 2026-08-12 19:12:07,768 INFO MainThread:1371664 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
12
- 2026-08-12 19:12:08,094 INFO MainThread:1371664 [wandb_init.py:init():978] starting run threads in backend
13
- 2026-08-12 19:12:08,172 INFO MainThread:1371664 [wandb_run.py:_console_start():2621] atexit reg
14
- 2026-08-12 19:12:08,172 INFO MainThread:1371664 [wandb_run.py:_redirect():2471] redirect: wrap_raw
15
- 2026-08-12 19:12:08,172 INFO MainThread:1371664 [wandb_run.py:_redirect():2540] Wrapping output streams.
16
- 2026-08-12 19:12:08,172 INFO MainThread:1371664 [wandb_run.py:_redirect():2563] Redirects installed.
17
- 2026-08-12 19:12:08,173 INFO MainThread:1371664 [wandb_init.py:init():1016] run started, returning control to user process
18
- 2026-08-12 19:12:08,174 INFO MainThread:1371664 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.16.0.dev0', 'architectures': None, 'output_hidden_states': False, 'return_dict': True, 'dtype': None, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, 'vocab_size': 4096, 'hidden_size': 128, 'intermediate_size': 256, 'num_hidden_layers': 150, 'num_attention_heads': 4, 'num_key_value_heads': 4, 'hidden_act': 'silu', 'max_position_embeddings': 512, 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'pad_token_id': 0, 'bos_token_id': 1, 'eos_token_id': 2, 'pretraining_tp': 1, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 10000.0, 'rope_type': 'default'}, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'head_dim': 32, '_name_or_path': '', 'tokenizer_name': 'w-ahmad/tiny-stories-tokenizer', 'mlp_type': 'glu', 'activation': 'waleed10', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-waleed10-150L_run', 'per_device_train_batch_size': 64, 'num_train_epochs': 1, 'max_steps': 1000, 'learning_rate': 0.005, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 200, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 0.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-waleed10-150L-25.1M-20260812-191206', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 50, 'eval_delay': 0, 'per_device_eval_batch_size': 128, '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': 1000, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/6L-glu-waleed10-150L', 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': None, 'dataloader_multiprocessing_context': None, 'dataloader_in_order': True, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_static_graph': None, 'ddp_backend': None, 'ddp_timeout': 1800, 'fsdp': None, 'fsdp_config': None, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'local_rank': -1}
19
- 2026-08-12 19:12:08,181 INFO MainThread:1371664 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 25138816 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x14c5efb86510>>
20
- 2026-08-12 19:12:08,181 INFO MainThread:1371664 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 25138816 None
 
1
+ 2026-08-12 19:26:31,997 INFO MainThread:1371664 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_192631-1pwkdnr5/logs/debug.log
2
+ 2026-08-12 19:26:31,997 INFO MainThread:1371664 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_192631-1pwkdnr5/logs/debug-internal.log
3
+ 2026-08-12 19:26:31,997 INFO MainThread:1371664 [wandb_init.py:init():772] calling init triggers
4
+ 2026-08-12 19:26:31,997 INFO MainThread:1371664 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
5
  config: {'_wandb': {}}
6
+ 2026-08-12 19:26:31,997 INFO MainThread:1371664 [wandb_init.py:init():820] starting backend
7
+ 2026-08-12 19:26:31,997 INFO MainThread:1371664 [wandb_init.py:init():826] Connected to an existing wandb-core service via WANDB_SERVICE
8
+ 2026-08-12 19:26:31,997 INFO MainThread:1371664 [wandb_init.py:init():835] sending inform_init request
9
+ 2026-08-12 19:26:32,274 INFO MainThread:1371664 [wandb_init.py:init():840] backend started and connected
10
+ 2026-08-12 19:26:32,275 INFO MainThread:1371664 [wandb_init.py:init():910] updated telemetry
11
+ 2026-08-12 19:26:32,282 INFO MainThread:1371664 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
12
+ 2026-08-12 19:26:32,537 INFO MainThread:1371664 [wandb_init.py:init():978] starting run threads in backend
13
+ 2026-08-12 19:26:32,619 INFO MainThread:1371664 [wandb_run.py:_console_start():2621] atexit reg
14
+ 2026-08-12 19:26:32,619 INFO MainThread:1371664 [wandb_run.py:_redirect():2471] redirect: wrap_raw
15
+ 2026-08-12 19:26:32,619 INFO MainThread:1371664 [wandb_run.py:_redirect():2540] Wrapping output streams.
16
+ 2026-08-12 19:26:32,619 INFO MainThread:1371664 [wandb_run.py:_redirect():2563] Redirects installed.
17
+ 2026-08-12 19:26:32,620 INFO MainThread:1371664 [wandb_init.py:init():1016] run started, returning control to user process
18
+ 2026-08-12 19:26:32,621 INFO MainThread:1371664 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.16.0.dev0', 'architectures': None, 'output_hidden_states': False, 'return_dict': True, 'dtype': None, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, 'vocab_size': 4096, 'hidden_size': 128, 'intermediate_size': 256, 'num_hidden_layers': 150, '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': 'mlp', 'activation': 'waleed10', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/mlp-waleed10-150L_run', 'per_device_train_batch_size': 64, 'num_train_epochs': 1, 'max_steps': 1000, 'learning_rate': 0.005, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 200, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 0.0, '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-mlp-waleed10-150L-25.1M-20260812-192631', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 50, 'eval_delay': 0, 'per_device_eval_batch_size': 128, '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': 1000, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/6L-mlp-waleed10-150L', 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': None, 'dataloader_multiprocessing_context': None, 'dataloader_in_order': True, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_static_graph': None, 'ddp_backend': None, 'ddp_timeout': 1800, 'fsdp': None, 'fsdp_config': None, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'local_rank': -1}
19
+ 2026-08-12 19:26:32,628 INFO MainThread:1371664 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 25138816 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x14c635a74990>>
20
+ 2026-08-12 19:26:32,628 INFO MainThread:1371664 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 25138816 None
zain/Activation/wandb/run-20260812_175304-hrggki9k/logs/debug-core.log CHANGED
@@ -53,3 +53,10 @@
53
  {"time":"2026-08-12T19:12:07.497066272Z","level":"INFO","msg":"handleInformInit: received","streamId":"w1cgnksl","id":"3(@)"}
54
  {"time":"2026-08-12T19:12:07.759791901Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w1cgnksl","id":"3(@)"}
55
  {"time":"2026-08-12T19:12:13.17475902Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
 
 
 
 
 
 
 
 
53
  {"time":"2026-08-12T19:12:07.497066272Z","level":"INFO","msg":"handleInformInit: received","streamId":"w1cgnksl","id":"3(@)"}
54
  {"time":"2026-08-12T19:12:07.759791901Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w1cgnksl","id":"3(@)"}
55
  {"time":"2026-08-12T19:12:13.17475902Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
56
+ {"time":"2026-08-12T19:26:30.425472974Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
57
+ {"time":"2026-08-12T19:26:30.923201233Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
58
+ {"time":"2026-08-12T19:26:30.924734408Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"w1cgnksl","id":"3(@)"}
59
+ {"time":"2026-08-12T19:26:30.925492222Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"w1cgnksl","id":"3(@)"}
60
+ {"time":"2026-08-12T19:26:32.010000105Z","level":"INFO","msg":"handleInformInit: received","streamId":"1pwkdnr5","id":"3(@)"}
61
+ {"time":"2026-08-12T19:26:32.273967782Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"1pwkdnr5","id":"3(@)"}
62
+ {"time":"2026-08-12T19:26:37.621886772Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"lxypz1nseyt4"}
zain/Activation/wandb/run-20260812_180713-utqzlg67/logs/debug-core.log CHANGED
@@ -53,3 +53,10 @@
53
  {"time":"2026-08-12T19:12:07.497066272Z","level":"INFO","msg":"handleInformInit: received","streamId":"w1cgnksl","id":"3(@)"}
54
  {"time":"2026-08-12T19:12:07.759791901Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w1cgnksl","id":"3(@)"}
55
  {"time":"2026-08-12T19:12:13.17475902Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
 
 
 
 
 
 
 
 
53
  {"time":"2026-08-12T19:12:07.497066272Z","level":"INFO","msg":"handleInformInit: received","streamId":"w1cgnksl","id":"3(@)"}
54
  {"time":"2026-08-12T19:12:07.759791901Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w1cgnksl","id":"3(@)"}
55
  {"time":"2026-08-12T19:12:13.17475902Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
56
+ {"time":"2026-08-12T19:26:30.425472974Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
57
+ {"time":"2026-08-12T19:26:30.923201233Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
58
+ {"time":"2026-08-12T19:26:30.924734408Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"w1cgnksl","id":"3(@)"}
59
+ {"time":"2026-08-12T19:26:30.925492222Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"w1cgnksl","id":"3(@)"}
60
+ {"time":"2026-08-12T19:26:32.010000105Z","level":"INFO","msg":"handleInformInit: received","streamId":"1pwkdnr5","id":"3(@)"}
61
+ {"time":"2026-08-12T19:26:32.273967782Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"1pwkdnr5","id":"3(@)"}
62
+ {"time":"2026-08-12T19:26:37.621886772Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"lxypz1nseyt4"}
zain/Activation/wandb/run-20260812_182126-vyycsg6r/logs/debug-core.log CHANGED
@@ -53,3 +53,10 @@
53
  {"time":"2026-08-12T19:12:07.497066272Z","level":"INFO","msg":"handleInformInit: received","streamId":"w1cgnksl","id":"3(@)"}
54
  {"time":"2026-08-12T19:12:07.759791901Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w1cgnksl","id":"3(@)"}
55
  {"time":"2026-08-12T19:12:13.17475902Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
 
 
 
 
 
 
 
 
53
  {"time":"2026-08-12T19:12:07.497066272Z","level":"INFO","msg":"handleInformInit: received","streamId":"w1cgnksl","id":"3(@)"}
54
  {"time":"2026-08-12T19:12:07.759791901Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w1cgnksl","id":"3(@)"}
55
  {"time":"2026-08-12T19:12:13.17475902Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
56
+ {"time":"2026-08-12T19:26:30.425472974Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
57
+ {"time":"2026-08-12T19:26:30.923201233Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
58
+ {"time":"2026-08-12T19:26:30.924734408Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"w1cgnksl","id":"3(@)"}
59
+ {"time":"2026-08-12T19:26:30.925492222Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"w1cgnksl","id":"3(@)"}
60
+ {"time":"2026-08-12T19:26:32.010000105Z","level":"INFO","msg":"handleInformInit: received","streamId":"1pwkdnr5","id":"3(@)"}
61
+ {"time":"2026-08-12T19:26:32.273967782Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"1pwkdnr5","id":"3(@)"}
62
+ {"time":"2026-08-12T19:26:37.621886772Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"lxypz1nseyt4"}
zain/Activation/wandb/run-20260812_183823-qtstmmvv/logs/debug-core.log CHANGED
@@ -53,3 +53,10 @@
53
  {"time":"2026-08-12T19:12:07.497066272Z","level":"INFO","msg":"handleInformInit: received","streamId":"w1cgnksl","id":"3(@)"}
54
  {"time":"2026-08-12T19:12:07.759791901Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w1cgnksl","id":"3(@)"}
55
  {"time":"2026-08-12T19:12:13.17475902Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
 
 
 
 
 
 
 
 
53
  {"time":"2026-08-12T19:12:07.497066272Z","level":"INFO","msg":"handleInformInit: received","streamId":"w1cgnksl","id":"3(@)"}
54
  {"time":"2026-08-12T19:12:07.759791901Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w1cgnksl","id":"3(@)"}
55
  {"time":"2026-08-12T19:12:13.17475902Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
56
+ {"time":"2026-08-12T19:26:30.425472974Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
57
+ {"time":"2026-08-12T19:26:30.923201233Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
58
+ {"time":"2026-08-12T19:26:30.924734408Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"w1cgnksl","id":"3(@)"}
59
+ {"time":"2026-08-12T19:26:30.925492222Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"w1cgnksl","id":"3(@)"}
60
+ {"time":"2026-08-12T19:26:32.010000105Z","level":"INFO","msg":"handleInformInit: received","streamId":"1pwkdnr5","id":"3(@)"}
61
+ {"time":"2026-08-12T19:26:32.273967782Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"1pwkdnr5","id":"3(@)"}
62
+ {"time":"2026-08-12T19:26:37.621886772Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"lxypz1nseyt4"}
zain/Activation/wandb/run-20260812_185803-0fh9o8ec/logs/debug-core.log CHANGED
@@ -53,3 +53,10 @@
53
  {"time":"2026-08-12T19:12:07.497066272Z","level":"INFO","msg":"handleInformInit: received","streamId":"w1cgnksl","id":"3(@)"}
54
  {"time":"2026-08-12T19:12:07.759791901Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w1cgnksl","id":"3(@)"}
55
  {"time":"2026-08-12T19:12:13.17475902Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
 
 
 
 
 
 
 
 
53
  {"time":"2026-08-12T19:12:07.497066272Z","level":"INFO","msg":"handleInformInit: received","streamId":"w1cgnksl","id":"3(@)"}
54
  {"time":"2026-08-12T19:12:07.759791901Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w1cgnksl","id":"3(@)"}
55
  {"time":"2026-08-12T19:12:13.17475902Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
56
+ {"time":"2026-08-12T19:26:30.425472974Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
57
+ {"time":"2026-08-12T19:26:30.923201233Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
58
+ {"time":"2026-08-12T19:26:30.924734408Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"w1cgnksl","id":"3(@)"}
59
+ {"time":"2026-08-12T19:26:30.925492222Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"w1cgnksl","id":"3(@)"}
60
+ {"time":"2026-08-12T19:26:32.010000105Z","level":"INFO","msg":"handleInformInit: received","streamId":"1pwkdnr5","id":"3(@)"}
61
+ {"time":"2026-08-12T19:26:32.273967782Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"1pwkdnr5","id":"3(@)"}
62
+ {"time":"2026-08-12T19:26:37.621886772Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"lxypz1nseyt4"}
zain/Activation/wandb/run-20260812_191207-w1cgnksl/files/config.yaml ADDED
@@ -0,0 +1,445 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _name_or_path:
2
+ value: ""
3
+ _wandb:
4
+ value:
5
+ cli_version: 0.28.1
6
+ e:
7
+ 6lnbyc3acvy2bme0wurgw4k1v2n501g4:
8
+ args:
9
+ - --config
10
+ - /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/configs/baseline150L.yaml
11
+ - --variants
12
+ - glu-silu
13
+ - glu-relu
14
+ - glu-gelu
15
+ - glu-sigmoid
16
+ - glu-linear
17
+ - glu-waleed10
18
+ - mlp-waleed10
19
+ - glu-silu-waleed10
20
+ - mlp-silu-waleed10
21
+ - glu-situglu
22
+ - glu-waleed
23
+ - glu-situglu_low
24
+ - glu-waleedglu_low
25
+ codePath: sweep.py
26
+ codePathLocal: sweep.py
27
+ cpu_count: 112
28
+ cpu_count_logical: 224
29
+ cudaVersion: "12.4"
30
+ disk:
31
+ /:
32
+ total: "1560765693952"
33
+ used: "716198170624"
34
+ email: deepnevro@gmail.com
35
+ executable: /mnt/data/zainulabideen/zain-exp/notebooks/my_env/bin/python
36
+ git:
37
+ commit: c53713bcba08d1849136dad91288c4b82040634e
38
+ remote: https://github.com/w-ahmad1a10/Activation.git
39
+ gpu: NVIDIA H100 80GB HBM3
40
+ gpu_count: 8
41
+ gpu_nvidia:
42
+ - architecture: Hopper
43
+ cudaCores: 16896
44
+ memoryTotal: "85520809984"
45
+ name: NVIDIA H100 80GB HBM3
46
+ uuid: GPU-39c684a5-fde6-83d7-1663-0859795881ae
47
+ - architecture: Hopper
48
+ cudaCores: 16896
49
+ memoryTotal: "85520809984"
50
+ name: NVIDIA H100 80GB HBM3
51
+ uuid: GPU-68012e5a-38b6-b643-0ca6-62fb66720bf3
52
+ - architecture: Hopper
53
+ cudaCores: 16896
54
+ memoryTotal: "85520809984"
55
+ name: NVIDIA H100 80GB HBM3
56
+ uuid: GPU-132944c4-b689-2b5f-89a4-d730401677ab
57
+ - architecture: Hopper
58
+ cudaCores: 16896
59
+ memoryTotal: "85520809984"
60
+ name: NVIDIA H100 80GB HBM3
61
+ uuid: GPU-2df386cc-6d26-d0e2-7a2d-a057b0d95864
62
+ - architecture: Hopper
63
+ cudaCores: 16896
64
+ memoryTotal: "85520809984"
65
+ name: NVIDIA H100 80GB HBM3
66
+ uuid: GPU-bfa16575-1d94-1aa2-4537-2c93433f42ef
67
+ - architecture: Hopper
68
+ cudaCores: 16896
69
+ memoryTotal: "85520809984"
70
+ name: NVIDIA H100 80GB HBM3
71
+ uuid: GPU-bc6c3e3c-9b90-09ca-c034-774961847c54
72
+ - architecture: Hopper
73
+ cudaCores: 16896
74
+ memoryTotal: "85520809984"
75
+ name: NVIDIA H100 80GB HBM3
76
+ uuid: GPU-00a441e1-7c95-e7d6-4c35-43d6b291aea9
77
+ - architecture: Hopper
78
+ cudaCores: 16896
79
+ memoryTotal: "85520809984"
80
+ name: NVIDIA H100 80GB HBM3
81
+ uuid: GPU-1c4d29a2-4647-6fce-d8fc-0c5ecfbbd6ea
82
+ host: deeplens-k3s-node1
83
+ memory:
84
+ total: "2164089937920"
85
+ os: Linux-5.15.0-126-generic-x86_64-with-glibc2.35
86
+ program: /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/sweep.py
87
+ python: CPython 3.11.15
88
+ root: /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation
89
+ startedAt: "2026-08-12T19:12:07.494929Z"
90
+ writerId: 6lnbyc3acvy2bme0wurgw4k1v2n501g4
91
+ m:
92
+ - "1": train/global_step
93
+ "6":
94
+ - 3
95
+ "7": []
96
+ - "2": '*'
97
+ "5": 1
98
+ "6":
99
+ - 1
100
+ "7": []
101
+ python_version: 3.11.15
102
+ t:
103
+ "1":
104
+ - 1
105
+ - 5
106
+ - 11
107
+ - 41
108
+ - 49
109
+ - 51
110
+ - 53
111
+ - 71
112
+ "2":
113
+ - 1
114
+ - 5
115
+ - 11
116
+ - 41
117
+ - 49
118
+ - 51
119
+ - 53
120
+ - 71
121
+ "3":
122
+ - 2
123
+ - 7
124
+ - 13
125
+ - 19
126
+ - 62
127
+ - 66
128
+ "4": 3.11.15
129
+ "5": 0.28.1
130
+ "6": 5.16.0.dev0
131
+ "9":
132
+ "1": transformers_trainer
133
+ "12": 0.28.1
134
+ "13": linux-x86_64
135
+ accelerator_config:
136
+ value:
137
+ dispatch_batches: null
138
+ even_batches: true
139
+ gradient_accumulation_kwargs: null
140
+ non_blocking: false
141
+ split_batches: false
142
+ use_seedable_sampler: true
143
+ activation:
144
+ value: waleed10
145
+ adam_beta1:
146
+ value: 0.9
147
+ adam_beta2:
148
+ value: 0.999
149
+ adam_epsilon:
150
+ value: 1e-08
151
+ architectures:
152
+ value: null
153
+ attention_bias:
154
+ value: false
155
+ attention_dropout:
156
+ value: 0
157
+ auto_find_batch_size:
158
+ value: false
159
+ average_tokens_across_devices:
160
+ value: true
161
+ batch_eval_metrics:
162
+ value: false
163
+ bf16:
164
+ value: true
165
+ bf16_full_eval:
166
+ value: false
167
+ bos_token_id:
168
+ value: 1
169
+ chunk_size_feed_forward:
170
+ value: 0
171
+ data_seed:
172
+ value: 42
173
+ dataloader_drop_last:
174
+ value: false
175
+ dataloader_in_order:
176
+ value: true
177
+ dataloader_multiprocessing_context:
178
+ value: null
179
+ dataloader_num_workers:
180
+ value: 0
181
+ dataloader_persistent_workers:
182
+ value: false
183
+ dataloader_pin_memory:
184
+ value: true
185
+ dataloader_prefetch_factor:
186
+ value: null
187
+ ddp_backend:
188
+ value: null
189
+ ddp_broadcast_buffers:
190
+ value: null
191
+ ddp_bucket_cap_mb:
192
+ value: null
193
+ ddp_find_unused_parameters:
194
+ value: null
195
+ ddp_static_graph:
196
+ value: null
197
+ ddp_timeout:
198
+ value: 1800
199
+ debug:
200
+ value: []
201
+ deepspeed:
202
+ value: null
203
+ disable_tqdm:
204
+ value: false
205
+ do_eval:
206
+ value: true
207
+ do_predict:
208
+ value: false
209
+ do_train:
210
+ value: false
211
+ dtype:
212
+ value: null
213
+ enable_jit_checkpoint:
214
+ value: false
215
+ eos_token_id:
216
+ value: 2
217
+ eval_accumulation_steps:
218
+ value: null
219
+ eval_delay:
220
+ value: 0
221
+ eval_do_concat_batches:
222
+ value: true
223
+ eval_on_start:
224
+ value: false
225
+ eval_steps:
226
+ value: 50
227
+ eval_strategy:
228
+ value: steps
229
+ eval_use_gather_object:
230
+ value: false
231
+ fp16:
232
+ value: false
233
+ fp16_full_eval:
234
+ value: false
235
+ fsdp:
236
+ value: null
237
+ fsdp_config:
238
+ value: null
239
+ full_determinism:
240
+ value: false
241
+ gradient_accumulation_steps:
242
+ value: 1
243
+ gradient_checkpointing:
244
+ value: false
245
+ gradient_checkpointing_kwargs:
246
+ value: null
247
+ greater_is_better:
248
+ value: null
249
+ head_dim:
250
+ value: 32
251
+ hidden_act:
252
+ value: silu
253
+ hidden_size:
254
+ value: 128
255
+ hub_always_push:
256
+ value: false
257
+ hub_model_id:
258
+ value: w-ahmad/6L-glu-waleed10-150L
259
+ hub_private_repo:
260
+ value: null
261
+ hub_revision:
262
+ value: null
263
+ hub_strategy:
264
+ value: every_save
265
+ hub_token:
266
+ value: <HUB_TOKEN>
267
+ id2label:
268
+ value:
269
+ "0": LABEL_0
270
+ "1": LABEL_1
271
+ ignore_data_skip:
272
+ value: false
273
+ include_for_metrics:
274
+ value: []
275
+ include_num_input_tokens_seen:
276
+ value: "no"
277
+ initializer_range:
278
+ value: 0.02
279
+ intermediate_size:
280
+ value: 256
281
+ is_encoder_decoder:
282
+ value: false
283
+ label_names:
284
+ value: null
285
+ label_smoothing_factor:
286
+ value: 0
287
+ label2id:
288
+ value:
289
+ LABEL_0: 0
290
+ LABEL_1: 1
291
+ learning_rate:
292
+ value: 0.005
293
+ length_column_name:
294
+ value: length
295
+ liger_kernel_config:
296
+ value: null
297
+ load_best_model_at_end:
298
+ value: false
299
+ local_rank:
300
+ value: -1
301
+ log_level:
302
+ value: passive
303
+ log_level_replica:
304
+ value: warning
305
+ log_on_each_node:
306
+ value: true
307
+ logging_first_step:
308
+ value: false
309
+ logging_nan_inf_filter:
310
+ value: true
311
+ logging_steps:
312
+ value: 20
313
+ logging_strategy:
314
+ value: steps
315
+ lr_scheduler_kwargs:
316
+ value: null
317
+ lr_scheduler_type:
318
+ value: constant_with_warmup
319
+ max_grad_norm:
320
+ value: 0
321
+ max_position_embeddings:
322
+ value: 512
323
+ max_steps:
324
+ value: 1000
325
+ metric_for_best_model:
326
+ value: null
327
+ mlp_bias:
328
+ value: false
329
+ mlp_type:
330
+ value: glu
331
+ model/num_parameters:
332
+ value: 25138816
333
+ model_type:
334
+ value: tiny_llama
335
+ neftune_noise_alpha:
336
+ value: null
337
+ num_attention_heads:
338
+ value: 4
339
+ num_hidden_layers:
340
+ value: 150
341
+ num_key_value_heads:
342
+ value: 4
343
+ num_train_epochs:
344
+ value: 1
345
+ optim:
346
+ value: adamw_torch_fused
347
+ optim_args:
348
+ value: null
349
+ optim_target_modules:
350
+ value: null
351
+ output_attentions:
352
+ value: false
353
+ output_dir:
354
+ value: out/glu-waleed10-150L_run
355
+ output_hidden_states:
356
+ value: false
357
+ pad_token_id:
358
+ value: 0
359
+ parallelism_config:
360
+ value: null
361
+ per_device_eval_batch_size:
362
+ value: 128
363
+ per_device_train_batch_size:
364
+ value: 64
365
+ prediction_loss_only:
366
+ value: false
367
+ pretraining_tp:
368
+ value: 1
369
+ problem_type:
370
+ value: null
371
+ project:
372
+ value: huggingface
373
+ push_to_hub:
374
+ value: false
375
+ remove_unused_columns:
376
+ value: false
377
+ report_to:
378
+ value:
379
+ - wandb
380
+ restore_callback_states_from_checkpoint:
381
+ value: false
382
+ resume_from_checkpoint:
383
+ value: null
384
+ return_dict:
385
+ value: true
386
+ rms_norm_eps:
387
+ value: 1e-06
388
+ rope_parameters:
389
+ value:
390
+ rope_theta: 10000
391
+ rope_type: default
392
+ run_name:
393
+ value: LM-glu-waleed10-150L-25.1M-20260812-191206
394
+ save_on_each_node:
395
+ value: false
396
+ save_only_model:
397
+ value: false
398
+ save_steps:
399
+ value: 1000
400
+ save_strategy:
401
+ value: steps
402
+ save_total_limit:
403
+ value: null
404
+ seed:
405
+ value: 42
406
+ skip_memory_metrics:
407
+ value: true
408
+ tf32:
409
+ value: null
410
+ tie_word_embeddings:
411
+ value: true
412
+ tokenizer_name:
413
+ value: w-ahmad/tiny-stories-tokenizer
414
+ torch_compile:
415
+ value: false
416
+ torch_compile_backend:
417
+ value: null
418
+ torch_compile_mode:
419
+ value: null
420
+ torch_empty_cache_steps:
421
+ value: null
422
+ trackio_bucket_id:
423
+ value: null
424
+ trackio_space_id:
425
+ value: null
426
+ trackio_static_space_id:
427
+ value: null
428
+ train_sampling_strategy:
429
+ value: random
430
+ transformers_version:
431
+ value: 5.16.0.dev0
432
+ use_cache:
433
+ value: false
434
+ use_cpu:
435
+ value: false
436
+ use_liger_kernel:
437
+ value: false
438
+ vocab_size:
439
+ value: 4096
440
+ waleed_beta:
441
+ value: 10
442
+ warmup_steps:
443
+ value: 200
444
+ weight_decay:
445
+ value: 0
zain/Activation/wandb/run-20260812_191207-w1cgnksl/files/output.log CHANGED
@@ -51,3 +51,33 @@
51
  {'eval_loss': '4.238', 'eval_runtime': '21.35', 'eval_samples_per_second': '446.3', 'eval_steps_per_second': '3.513', 'epoch': '0.04719', 'train/total_time_seconds': '253.5', 'train/time_per_step_avg': '0.3565', 'train/epoch_time_elapsed': '588.5', 'train/estimated_remaining_minutes': '1.81'}
52
  {'loss': '4.539', 'grad_norm': '2.969', 'learning_rate': '0.005', 'epoch': '0.04853', 'train/total_time_seconds': '260.8', 'train/time_per_step_avg': '0.3587', 'train/epoch_time_elapsed': '596.8', 'train/estimated_remaining_minutes': '1.69'}
53
  {'loss': '4.674', 'grad_norm': '2.531', 'learning_rate': '0.005', 'epoch': '0.04988', 'train/total_time_seconds': '268.1', 'train/time_per_step_avg': '0.3615', 'train/epoch_time_elapsed': '605.2', 'train/estimated_remaining_minutes': '1.57'}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
  {'eval_loss': '4.238', 'eval_runtime': '21.35', 'eval_samples_per_second': '446.3', 'eval_steps_per_second': '3.513', 'epoch': '0.04719', 'train/total_time_seconds': '253.5', 'train/time_per_step_avg': '0.3565', 'train/epoch_time_elapsed': '588.5', 'train/estimated_remaining_minutes': '1.81'}
52
  {'loss': '4.539', 'grad_norm': '2.969', 'learning_rate': '0.005', 'epoch': '0.04853', 'train/total_time_seconds': '260.8', 'train/time_per_step_avg': '0.3587', 'train/epoch_time_elapsed': '596.8', 'train/estimated_remaining_minutes': '1.69'}
53
  {'loss': '4.674', 'grad_norm': '2.531', 'learning_rate': '0.005', 'epoch': '0.04988', 'train/total_time_seconds': '268.1', 'train/time_per_step_avg': '0.3615', 'train/epoch_time_elapsed': '605.2', 'train/estimated_remaining_minutes': '1.57'}
54
+ {'eval_loss': '4.747', 'eval_runtime': '21.27', 'eval_samples_per_second': '447.9', 'eval_steps_per_second': '3.526', 'epoch': '0.05056', 'train/total_time_seconds': '271.7', 'train/time_per_step_avg': '0.3617', 'train/epoch_time_elapsed': '630.5', 'train/estimated_remaining_minutes': '1.509'}
55
+ {'loss': '4.684', 'grad_norm': '0.8242', 'learning_rate': '0.005', 'epoch': '0.05123', 'train/total_time_seconds': '275.2', 'train/time_per_step_avg': '0.3619', 'train/epoch_time_elapsed': '634.5', 'train/estimated_remaining_minutes': '1.449'}
56
+ {'loss': '4.658', 'grad_norm': '1.141', 'learning_rate': '0.005', 'epoch': '0.05258', 'train/total_time_seconds': '282.3', 'train/time_per_step_avg': '0.3588', 'train/epoch_time_elapsed': '642.6', 'train/estimated_remaining_minutes': '1.327'}
57
+ {'loss': '4.582', 'grad_norm': '1.164', 'learning_rate': '0.005', 'epoch': '0.05393', 'train/total_time_seconds': '289.4', 'train/time_per_step_avg': '0.359', 'train/epoch_time_elapsed': '650.7', 'train/estimated_remaining_minutes': '1.206'}
58
+ {'eval_loss': '4.619', 'eval_runtime': '21.26', 'eval_samples_per_second': '448.2', 'eval_steps_per_second': '3.528', 'epoch': '0.05393', 'train/total_time_seconds': '289.4', 'train/time_per_step_avg': '0.359', 'train/epoch_time_elapsed': '671.9', 'train/estimated_remaining_minutes': '1.206'}
59
+ {'loss': '4.66', 'grad_norm': '4.531', 'learning_rate': '0.005', 'epoch': '0.05527', 'train/total_time_seconds': '296.7', 'train/time_per_step_avg': '0.3593', 'train/epoch_time_elapsed': '680.3', 'train/estimated_remaining_minutes': '1.086'}
60
+ {'loss': '4.617', 'grad_norm': '1.43', 'learning_rate': '0.005', 'epoch': '0.05662', 'train/total_time_seconds': '303.8', 'train/time_per_step_avg': '0.3566', 'train/epoch_time_elapsed': '688.3', 'train/estimated_remaining_minutes': '0.9644'}
61
+ {'eval_loss': '4.634', 'eval_runtime': '21.44', 'eval_samples_per_second': '444.3', 'eval_steps_per_second': '3.498', 'epoch': '0.0573', 'train/total_time_seconds': '307.3', 'train/time_per_step_avg': '0.3565', 'train/epoch_time_elapsed': '713.8', 'train/estimated_remaining_minutes': '0.9039'}
62
+ {'loss': '4.65', 'grad_norm': '0.7812', 'learning_rate': '0.005', 'epoch': '0.05797', 'train/total_time_seconds': '311', 'train/time_per_step_avg': '0.3577', 'train/epoch_time_elapsed': '718', 'train/estimated_remaining_minutes': '0.8437'}
63
+ {'loss': '4.608', 'grad_norm': '9.062', 'learning_rate': '0.005', 'epoch': '0.05932', 'train/total_time_seconds': '318.3', 'train/time_per_step_avg': '0.3602', 'train/epoch_time_elapsed': '726.3', 'train/estimated_remaining_minutes': '0.7234'}
64
+ {'loss': '4.67', 'grad_norm': '2.797', 'learning_rate': '0.005', 'epoch': '0.06067', 'train/total_time_seconds': '325.7', 'train/time_per_step_avg': '0.3633', 'train/epoch_time_elapsed': '734.7', 'train/estimated_remaining_minutes': '0.6031'}
65
+ {'eval_loss': '4.753', 'eval_runtime': '21.43', 'eval_samples_per_second': '444.5', 'eval_steps_per_second': '3.499', 'epoch': '0.06067', 'train/total_time_seconds': '325.7', 'train/time_per_step_avg': '0.3633', 'train/epoch_time_elapsed': '756.2', 'train/estimated_remaining_minutes': '0.6031'}
66
+ {'loss': '4.759', 'grad_norm': '2.422', 'learning_rate': '0.005', 'epoch': '0.06202', 'train/total_time_seconds': '333', 'train/time_per_step_avg': '0.363', 'train/epoch_time_elapsed': '764.5', 'train/estimated_remaining_minutes': '0.4826'}
67
+ {'loss': '4.757', 'grad_norm': '1.922', 'learning_rate': '0.005', 'epoch': '0.06336', 'train/total_time_seconds': '340.3', 'train/time_per_step_avg': '0.3655', 'train/epoch_time_elapsed': '772.8', 'train/estimated_remaining_minutes': '0.3621'}
68
+ {'eval_loss': '4.923', 'eval_runtime': '21.46', 'eval_samples_per_second': '444', 'eval_steps_per_second': '3.495', 'epoch': '0.06404', 'train/total_time_seconds': '344.3', 'train/time_per_step_avg': '0.3693', 'train/epoch_time_elapsed': '798.7', 'train/estimated_remaining_minutes': '0.302'}
69
+ {'loss': '4.92', 'grad_norm': '3.656', 'learning_rate': '0.005', 'epoch': '0.06471', 'train/total_time_seconds': '347.8', 'train/time_per_step_avg': '0.368', 'train/epoch_time_elapsed': '802.7', 'train/estimated_remaining_minutes': '0.2415'}
70
+ {'loss': '4.903', 'grad_norm': '39.75', 'learning_rate': '0.005', 'epoch': '0.06606', 'train/total_time_seconds': '354.8', 'train/time_per_step_avg': '0.3653', 'train/epoch_time_elapsed': '810.7', 'train/estimated_remaining_minutes': '0.1207'}
71
+ {'loss': '5.328', 'grad_norm': '18.38', 'learning_rate': '0.005', 'epoch': '0.06741', 'train/total_time_seconds': '361.9', 'train/time_per_step_avg': '0.3622', 'train/epoch_time_elapsed': '818.8', 'train/estimated_remaining_minutes': '0'}
72
+ {'eval_loss': '5.331', 'eval_runtime': '21.43', 'eval_samples_per_second': '444.6', 'eval_steps_per_second': '3.5', 'epoch': '0.06741', 'train/total_time_seconds': '361.9', 'train/time_per_step_avg': '0.3622', 'train/epoch_time_elapsed': '840.2', 'train/estimated_remaining_minutes': '0'}
73
+ - 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).
74
+ - If you are not the owner of the model architecture class, please contact the model code owner to update it.
75
+ Writing model shards: 100%|██████████| 1/1 [00:00<00:00, 9.15it/s]
76
+ 100%|██████████| 1000/1000 [14:01<00:00, 1.19it/s]0:00, 9.24it/s]
77
+ {'train_runtime': '841.4', 'train_samples_per_second': '76.06', 'train_steps_per_second': '1.189', 'train_loss': '5.168', 'epoch': '0.06741', 'train/total_time_seconds': '361.9', 'train/time_per_step_avg': '0.3622', 'train/epoch_time_elapsed': '840.6', 'train/estimated_remaining_minutes': '0'}
78
+ 100%|██████████| 75/75 [00:21<00:00, 3.56it/s]
79
+ [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.
80
+ - 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
81
+ - 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).
82
+ - If you are not the owner of the model architecture class, please contact the model code owner to update it.
83
+ Writing model shards: 100%|██████████| 1/1 [00:00<00:00, 10.48it/s]
zain/Activation/wandb/run-20260812_191207-w1cgnksl/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train/learning_rate":0.005,"train_samples_per_second":76.064,"train/train/time_per_step_avg":0.36216694828122853,"total_flos":4.839413121024e+15,"eval/loss":5.330815315246582,"train/loss":5.32824821472168,"_wandb":{"runtime":862},"train/train/epoch_time_elapsed":862.107542693615,"train/train/estimated_remaining_minutes":0,"eval/samples_per_second":444.055,"train/epoch":0.06740815638692282,"train_loss":5.168452629089355,"_runtime":862,"eval/steps_per_second":3.496,"train/train/total_time_seconds":361.9019044712186,"train/global_step":1000,"eval/runtime":21.4546,"train/grad_norm":18.375,"_timestamp":1.7865627902894785e+09,"train_runtime":841.3959,"_step":71,"train_steps_per_second":1.189}
zain/Activation/wandb/run-20260812_191207-w1cgnksl/logs/debug-core.log CHANGED
@@ -53,3 +53,10 @@
53
  {"time":"2026-08-12T19:12:07.497066272Z","level":"INFO","msg":"handleInformInit: received","streamId":"w1cgnksl","id":"3(@)"}
54
  {"time":"2026-08-12T19:12:07.759791901Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w1cgnksl","id":"3(@)"}
55
  {"time":"2026-08-12T19:12:13.17475902Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
 
 
 
 
 
 
 
 
53
  {"time":"2026-08-12T19:12:07.497066272Z","level":"INFO","msg":"handleInformInit: received","streamId":"w1cgnksl","id":"3(@)"}
54
  {"time":"2026-08-12T19:12:07.759791901Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w1cgnksl","id":"3(@)"}
55
  {"time":"2026-08-12T19:12:13.17475902Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
56
+ {"time":"2026-08-12T19:26:30.425472974Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
57
+ {"time":"2026-08-12T19:26:30.923201233Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
58
+ {"time":"2026-08-12T19:26:30.924734408Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"w1cgnksl","id":"3(@)"}
59
+ {"time":"2026-08-12T19:26:30.925492222Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"w1cgnksl","id":"3(@)"}
60
+ {"time":"2026-08-12T19:26:32.010000105Z","level":"INFO","msg":"handleInformInit: received","streamId":"1pwkdnr5","id":"3(@)"}
61
+ {"time":"2026-08-12T19:26:32.273967782Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"1pwkdnr5","id":"3(@)"}
62
+ {"time":"2026-08-12T19:26:37.621886772Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"lxypz1nseyt4"}
zain/Activation/wandb/run-20260812_191207-w1cgnksl/logs/debug-internal.log CHANGED
@@ -89,3 +89,43 @@
89
  {"time":"2026-08-12T19:22:09.255653996Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
90
  {"time":"2026-08-12T19:22:24.061485993Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":50,"history_lines":1,"events_offset":80,"events_lines":2,"console_offset":52,"console_lines":1}
91
  {"time":"2026-08-12T19:22:24.206976463Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
89
  {"time":"2026-08-12T19:22:09.255653996Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
90
  {"time":"2026-08-12T19:22:24.061485993Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":50,"history_lines":1,"events_offset":80,"events_lines":2,"console_offset":52,"console_lines":1}
91
  {"time":"2026-08-12T19:22:24.206976463Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
92
+ {"time":"2026-08-12T19:22:39.061181382Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":51,"history_lines":1,"events_offset":82,"events_lines":2,"console_offset":53,"console_lines":1}
93
+ {"time":"2026-08-12T19:22:39.180145446Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
94
+ {"time":"2026-08-12T19:22:54.061177559Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":52,"history_lines":2,"events_offset":84,"events_lines":2,"console_offset":54,"console_lines":2}
95
+ {"time":"2026-08-12T19:22:54.1898675Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
96
+ {"time":"2026-08-12T19:23:09.061482421Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":54,"history_lines":1,"events_offset":86,"events_lines":2,"console_offset":56,"console_lines":1}
97
+ {"time":"2026-08-12T19:23:09.236211462Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
98
+ {"time":"2026-08-12T19:23:24.061726554Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":55,"history_lines":1,"events_offset":88,"events_lines":2,"console_offset":57,"console_lines":1}
99
+ {"time":"2026-08-12T19:23:24.167672255Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
100
+ {"time":"2026-08-12T19:23:39.06104Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":56,"history_lines":2,"events_offset":90,"events_lines":2,"console_offset":58,"console_lines":2}
101
+ {"time":"2026-08-12T19:23:39.17725822Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
102
+ {"time":"2026-08-12T19:23:54.061031896Z","level":"INFO","msg":"filestream: sending request","total_files":1,"events_offset":92,"events_lines":2}
103
+ {"time":"2026-08-12T19:23:54.174138887Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
104
+ {"time":"2026-08-12T19:24:09.060924165Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":58,"history_lines":2,"events_offset":94,"events_lines":2,"console_offset":60,"console_lines":2}
105
+ {"time":"2026-08-12T19:24:09.225222221Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
106
+ {"time":"2026-08-12T19:24:24.061377855Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":60,"history_lines":2,"events_offset":96,"events_lines":2,"console_offset":62,"console_lines":2}
107
+ {"time":"2026-08-12T19:24:24.192705608Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
108
+ {"time":"2026-08-12T19:24:39.061112227Z","level":"INFO","msg":"filestream: sending request","total_files":1,"events_offset":98,"events_lines":2}
109
+ {"time":"2026-08-12T19:24:39.183074461Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
110
+ {"time":"2026-08-12T19:24:54.061486188Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":62,"history_lines":2,"events_offset":100,"events_lines":2,"console_offset":64,"console_lines":2}
111
+ {"time":"2026-08-12T19:24:54.198037727Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
112
+ {"time":"2026-08-12T19:25:09.061756098Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":64,"history_lines":1,"events_offset":102,"events_lines":2,"console_offset":66,"console_lines":1}
113
+ {"time":"2026-08-12T19:25:09.23033405Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
114
+ {"time":"2026-08-12T19:25:24.06081654Z","level":"INFO","msg":"filestream: sending request","total_files":1,"events_offset":104,"events_lines":2}
115
+ {"time":"2026-08-12T19:25:24.195961038Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
116
+ {"time":"2026-08-12T19:25:39.061593397Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":65,"history_lines":3,"events_offset":106,"events_lines":2,"console_offset":67,"console_lines":3}
117
+ {"time":"2026-08-12T19:25:39.180877195Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
118
+ {"time":"2026-08-12T19:25:54.061258934Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":68,"history_lines":1,"events_offset":108,"events_lines":2,"console_offset":70,"console_lines":1}
119
+ {"time":"2026-08-12T19:25:54.182607241Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
120
+ {"time":"2026-08-12T19:26:09.060911506Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":69,"history_lines":2,"events_offset":110,"events_lines":2,"console_offset":71,"console_lines":6}
121
+ {"time":"2026-08-12T19:26:09.2097277Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
122
+ {"time":"2026-08-12T19:26:24.061119798Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":112,"events_lines":2,"console_offset":77,"console_lines":1}
123
+ {"time":"2026-08-12T19:26:24.188229245Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
124
+ {"time":"2026-08-12T19:26:30.802914206Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
125
+ {"time":"2026-08-12T19:26:30.80313837Z","level":"INFO","msg":"filestream: sending request","total_files":3,"history_offset":71,"history_lines":1,"console_offset":77,"console_lines":6,"uploaded_len":3,"complete":true,"exit_code":0}
126
+ {"time":"2026-08-12T19:26:30.920763605Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
127
+ {"time":"2026-08-12T19:26:30.922110735Z","level":"INFO","msg":"handler: operation stats","stats":{}}
128
+ {"time":"2026-08-12T19:26:30.924760563Z","level":"INFO","msg":"stream: finishing up"}
129
+ {"time":"2026-08-12T19:26:30.924794183Z","level":"INFO","msg":"handler: closed"}
130
+ {"time":"2026-08-12T19:26:30.924925418Z","level":"INFO","msg":"sender: closed"}
131
+ {"time":"2026-08-12T19:26:30.924929498Z","level":"INFO","msg":"stream: all finished"}
zain/Activation/wandb/run-20260812_191207-w1cgnksl/logs/debug.log CHANGED
@@ -18,3 +18,8 @@ config: {'_wandb': {}}
18
  2026-08-12 19:12:08,174 INFO MainThread:1371664 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.16.0.dev0', 'architectures': None, 'output_hidden_states': False, 'return_dict': True, 'dtype': None, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, 'vocab_size': 4096, 'hidden_size': 128, 'intermediate_size': 256, 'num_hidden_layers': 150, 'num_attention_heads': 4, 'num_key_value_heads': 4, 'hidden_act': 'silu', 'max_position_embeddings': 512, 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'pad_token_id': 0, 'bos_token_id': 1, 'eos_token_id': 2, 'pretraining_tp': 1, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 10000.0, 'rope_type': 'default'}, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'head_dim': 32, '_name_or_path': '', 'tokenizer_name': 'w-ahmad/tiny-stories-tokenizer', 'mlp_type': 'glu', 'activation': 'waleed10', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-waleed10-150L_run', 'per_device_train_batch_size': 64, 'num_train_epochs': 1, 'max_steps': 1000, 'learning_rate': 0.005, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 200, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 0.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-waleed10-150L-25.1M-20260812-191206', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 50, 'eval_delay': 0, 'per_device_eval_batch_size': 128, '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': 1000, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/6L-glu-waleed10-150L', 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': None, 'dataloader_multiprocessing_context': None, 'dataloader_in_order': True, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_static_graph': None, 'ddp_backend': None, 'ddp_timeout': 1800, 'fsdp': None, 'fsdp_config': None, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'local_rank': -1}
19
  2026-08-12 19:12:08,181 INFO MainThread:1371664 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 25138816 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x14c5efb86510>>
20
  2026-08-12 19:12:08,181 INFO MainThread:1371664 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 25138816 None
 
 
 
 
 
 
18
  2026-08-12 19:12:08,174 INFO MainThread:1371664 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.16.0.dev0', 'architectures': None, 'output_hidden_states': False, 'return_dict': True, 'dtype': None, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, 'vocab_size': 4096, 'hidden_size': 128, 'intermediate_size': 256, 'num_hidden_layers': 150, 'num_attention_heads': 4, 'num_key_value_heads': 4, 'hidden_act': 'silu', 'max_position_embeddings': 512, 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'pad_token_id': 0, 'bos_token_id': 1, 'eos_token_id': 2, 'pretraining_tp': 1, 'tie_word_embeddings': True, 'rope_parameters': {'rope_theta': 10000.0, 'rope_type': 'default'}, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'head_dim': 32, '_name_or_path': '', 'tokenizer_name': 'w-ahmad/tiny-stories-tokenizer', 'mlp_type': 'glu', 'activation': 'waleed10', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/glu-waleed10-150L_run', 'per_device_train_batch_size': 64, 'num_train_epochs': 1, 'max_steps': 1000, 'learning_rate': 0.005, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 200, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 0.0, 'label_smoothing_factor': 0.0, 'bf16': True, 'fp16': False, 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'use_liger_kernel': False, 'liger_kernel_config': None, 'neftune_noise_alpha': None, 'torch_empty_cache_steps': None, 'auto_find_batch_size': False, 'logging_strategy': 'steps', 'logging_steps': 20, 'logging_first_step': False, 'log_on_each_node': True, 'logging_nan_inf_filter': True, 'include_num_input_tokens_seen': 'no', 'log_level': 'passive', 'log_level_replica': 'warning', 'disable_tqdm': False, 'report_to': ['wandb'], 'run_name': 'LM-glu-waleed10-150L-25.1M-20260812-191206', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 50, 'eval_delay': 0, 'per_device_eval_batch_size': 128, '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': 1000, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/6L-glu-waleed10-150L', 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': None, 'dataloader_multiprocessing_context': None, 'dataloader_in_order': True, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_static_graph': None, 'ddp_backend': None, 'ddp_timeout': 1800, 'fsdp': None, 'fsdp_config': None, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'local_rank': -1}
19
  2026-08-12 19:12:08,181 INFO MainThread:1371664 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 25138816 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x14c5efb86510>>
20
  2026-08-12 19:12:08,181 INFO MainThread:1371664 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 25138816 None
21
+ 2026-08-12 19:26:30,424 INFO MainThread:1371664 [wandb_run.py:_finish():2383] finishing run deepnevro-deepnevro/research2/w1cgnksl
22
+ 2026-08-12 19:26:30,425 INFO MainThread:1371664 [wandb_run.py:_atexit_cleanup():2588] got exitcode: 0
23
+ 2026-08-12 19:26:30,425 INFO MainThread:1371664 [wandb_run.py:_restore():2570] restore
24
+ 2026-08-12 19:26:30,425 INFO MainThread:1371664 [wandb_run.py:_restore():2576] restore done
25
+ 2026-08-12 19:26:30,924 INFO MainThread:1371664 [wandb_run.py:_footer_sync_info():3993] logging synced files
zain/Activation/wandb/run-20260812_191207-w1cgnksl/run-w1cgnksl.wandb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f5123013c00348f1dd3280fbc20d8fa62ae3795a0bb7f4bb77992bc29e1cc4a
3
- size 655360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9889e8b0c30e203e00fc6a5eabf12cf67bc6fb74552d8b0f8965eb0ae3141a4
3
+ size 938077
zain/Activation/wandb/run-20260812_192631-1pwkdnr5/files/output.log ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ 9%|▊ | 86/1000 [00:56<06:00, 2.54it/s]
2
+ {'loss': '7.917', 'grad_norm': '1.305', 'learning_rate': '0.000475', 'epoch': '0.001348', 'train/total_time_seconds': '7.589', 'train/time_per_step_avg': '0.3795', 'train/epoch_time_elapsed': '8.675', 'train/estimated_remaining_minutes': '6.198'}
3
+ {'loss': '6.784', 'grad_norm': '0.9883', 'learning_rate': '0.000975', 'epoch': '0.002696', 'train/total_time_seconds': '14.46', 'train/time_per_step_avg': '0.3615', 'train/epoch_time_elapsed': '16.55', 'train/estimated_remaining_minutes': '5.784'}
4
+
5
+ {'eval_loss': '6.159', 'eval_runtime': '20.89', 'eval_samples_per_second': '456', 'eval_steps_per_second': '3.59', 'epoch': '0.00337', 'train/total_time_seconds': '17.88', 'train/time_per_step_avg': '0.3577', 'train/epoch_time_elapsed': '41.36', 'train/estimated_remaining_minutes': '5.663'}
6
+ {'loss': '6.296', 'grad_norm': '0.2734', 'learning_rate': '0.001475', 'epoch': '0.004044', 'train/total_time_seconds': '21.41', 'train/time_per_step_avg': '0.3568', 'train/epoch_time_elapsed': '45.43', 'train/estimated_remaining_minutes': '5.59'}
7
+ {'loss': '6.782', 'grad_norm': '0.6562', 'learning_rate': '0.001975', 'epoch': '0.005393', 'train/total_time_seconds': '28.31', 'train/time_per_step_avg': '0.3538', 'train/epoch_time_elapsed': '53.34', 'train/estimated_remaining_minutes': '5.426'}
zain/Activation/wandb/run-20260812_192631-1pwkdnr5/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==5.16.0.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
zain/Activation/wandb/run-20260812_192631-1pwkdnr5/files/wandb-metadata.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-5.15.0-126-generic-x86_64-with-glibc2.35",
3
+ "python": "CPython 3.11.15",
4
+ "startedAt": "2026-08-12T19:26:31.995922Z",
5
+ "args": [
6
+ "--config",
7
+ "/mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/configs/baseline150L.yaml",
8
+ "--variants",
9
+ "glu-silu",
10
+ "glu-relu",
11
+ "glu-gelu",
12
+ "glu-sigmoid",
13
+ "glu-linear",
14
+ "glu-waleed10",
15
+ "mlp-waleed10",
16
+ "glu-silu-waleed10",
17
+ "mlp-silu-waleed10",
18
+ "glu-situglu",
19
+ "glu-waleed",
20
+ "glu-situglu_low",
21
+ "glu-waleedglu_low"
22
+ ],
23
+ "program": "/mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/sweep.py",
24
+ "codePath": "sweep.py",
25
+ "codePathLocal": "sweep.py",
26
+ "git": {
27
+ "remote": "https://github.com/w-ahmad1a10/Activation.git",
28
+ "commit": "c53713bcba08d1849136dad91288c4b82040634e"
29
+ },
30
+ "email": "deepnevro@gmail.com",
31
+ "root": "/mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation",
32
+ "host": "deeplens-k3s-node1",
33
+ "executable": "/mnt/data/zainulabideen/zain-exp/notebooks/my_env/bin/python",
34
+ "cpu_count": 112,
35
+ "cpu_count_logical": 224,
36
+ "gpu": "NVIDIA H100 80GB HBM3",
37
+ "gpu_count": 8,
38
+ "disk": {
39
+ "/": {
40
+ "total": "1560765693952",
41
+ "used": "716203872256"
42
+ }
43
+ },
44
+ "memory": {
45
+ "total": "2164089937920"
46
+ },
47
+ "gpu_nvidia": [
48
+ {
49
+ "name": "NVIDIA H100 80GB HBM3",
50
+ "memoryTotal": "85520809984",
51
+ "cudaCores": 16896,
52
+ "architecture": "Hopper",
53
+ "uuid": "GPU-39c684a5-fde6-83d7-1663-0859795881ae"
54
+ },
55
+ {
56
+ "name": "NVIDIA H100 80GB HBM3",
57
+ "memoryTotal": "85520809984",
58
+ "cudaCores": 16896,
59
+ "architecture": "Hopper",
60
+ "uuid": "GPU-68012e5a-38b6-b643-0ca6-62fb66720bf3"
61
+ },
62
+ {
63
+ "name": "NVIDIA H100 80GB HBM3",
64
+ "memoryTotal": "85520809984",
65
+ "cudaCores": 16896,
66
+ "architecture": "Hopper",
67
+ "uuid": "GPU-132944c4-b689-2b5f-89a4-d730401677ab"
68
+ },
69
+ {
70
+ "name": "NVIDIA H100 80GB HBM3",
71
+ "memoryTotal": "85520809984",
72
+ "cudaCores": 16896,
73
+ "architecture": "Hopper",
74
+ "uuid": "GPU-2df386cc-6d26-d0e2-7a2d-a057b0d95864"
75
+ },
76
+ {
77
+ "name": "NVIDIA H100 80GB HBM3",
78
+ "memoryTotal": "85520809984",
79
+ "cudaCores": 16896,
80
+ "architecture": "Hopper",
81
+ "uuid": "GPU-bfa16575-1d94-1aa2-4537-2c93433f42ef"
82
+ },
83
+ {
84
+ "name": "NVIDIA H100 80GB HBM3",
85
+ "memoryTotal": "85520809984",
86
+ "cudaCores": 16896,
87
+ "architecture": "Hopper",
88
+ "uuid": "GPU-bc6c3e3c-9b90-09ca-c034-774961847c54"
89
+ },
90
+ {
91
+ "name": "NVIDIA H100 80GB HBM3",
92
+ "memoryTotal": "85520809984",
93
+ "cudaCores": 16896,
94
+ "architecture": "Hopper",
95
+ "uuid": "GPU-00a441e1-7c95-e7d6-4c35-43d6b291aea9"
96
+ },
97
+ {
98
+ "name": "NVIDIA H100 80GB HBM3",
99
+ "memoryTotal": "85520809984",
100
+ "cudaCores": 16896,
101
+ "architecture": "Hopper",
102
+ "uuid": "GPU-1c4d29a2-4647-6fce-d8fc-0c5ecfbbd6ea"
103
+ }
104
+ ],
105
+ "cudaVersion": "12.4",
106
+ "writerId": "r7p1rq02aw8r3n23icm1x711rk5uv2d7"
107
+ }
zain/Activation/wandb/run-20260812_192631-1pwkdnr5/logs/debug-core.log ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2026-08-12T17:51:29.496049185Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmp7lru5pey/port-1355517.txt","pid":1355517,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
2
+ {"time":"2026-08-12T17:51:29.496747364Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":1355517}
3
+ {"time":"2026-08-12T17:51:29.49671311Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-1355517-1357782-3052194627/socket","Net":"unix"}}
4
+ {"time":"2026-08-12T17:51:29.674347603Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
5
+ {"time":"2026-08-12T17:52:11.162138091Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"2(@)"}
6
+ {"time":"2026-08-12T17:52:11.242645021Z","level":"INFO","msg":"handleInformInit: received","streamId":"ycyhhejh","id":"2(@)"}
7
+ {"time":"2026-08-12T17:52:11.508233203Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"ycyhhejh","id":"2(@)"}
8
+ {"time":"2026-08-12T17:52:17.001520061Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"6684d59dll8w"}
9
+ {"time":"2026-08-12T17:52:32.412124918Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"6684d59dll8w"}
10
+ {"time":"2026-08-12T17:52:32.887487538Z","level":"INFO","msg":"connection: cancelling request","id":"2(@)","requestId":"6684d59dll8w"}
11
+ {"time":"2026-08-12T17:52:32.888505Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"ycyhhejh","id":"2(@)"}
12
+ {"time":"2026-08-12T17:52:32.889313366Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"ycyhhejh","id":"2(@)"}
13
+ {"time":"2026-08-12T17:52:34.597228944Z","level":"INFO","msg":"connection: closing","id":"2(@)"}
14
+ {"time":"2026-08-12T17:52:34.597314364Z","level":"INFO","msg":"connection: closed successfully","id":"2(@)"}
15
+ {"time":"2026-08-12T17:52:34.597242804Z","level":"INFO","msg":"processOutgoingData: finished","id":"2(@)"}
16
+ {"time":"2026-08-12T17:52:34.597322441Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"2(@)"}
17
+ {"time":"2026-08-12T17:53:03.98517338Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"3(@)"}
18
+ {"time":"2026-08-12T17:53:04.076747848Z","level":"INFO","msg":"handleInformInit: received","streamId":"hrggki9k","id":"3(@)"}
19
+ {"time":"2026-08-12T17:53:04.339071164Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"hrggki9k","id":"3(@)"}
20
+ {"time":"2026-08-12T17:53:09.739880255Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tj6i5mzy43l0"}
21
+ {"time":"2026-08-12T18:07:11.667315857Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tj6i5mzy43l0"}
22
+ {"time":"2026-08-12T18:07:12.178747012Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tj6i5mzy43l0"}
23
+ {"time":"2026-08-12T18:07:12.180598654Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"hrggki9k","id":"3(@)"}
24
+ {"time":"2026-08-12T18:07:12.181733156Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"hrggki9k","id":"3(@)"}
25
+ {"time":"2026-08-12T18:07:13.412475061Z","level":"INFO","msg":"handleInformInit: received","streamId":"utqzlg67","id":"3(@)"}
26
+ {"time":"2026-08-12T18:07:13.679314069Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"utqzlg67","id":"3(@)"}
27
+ {"time":"2026-08-12T18:07:19.044675117Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"atkqmrzkldx8"}
28
+ {"time":"2026-08-12T18:21:24.445193258Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"atkqmrzkldx8"}
29
+ {"time":"2026-08-12T18:21:25.196343989Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"atkqmrzkldx8"}
30
+ {"time":"2026-08-12T18:21:25.198067009Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"utqzlg67","id":"3(@)"}
31
+ {"time":"2026-08-12T18:21:25.199000312Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"utqzlg67","id":"3(@)"}
32
+ {"time":"2026-08-12T18:21:26.321522195Z","level":"INFO","msg":"handleInformInit: received","streamId":"vyycsg6r","id":"3(@)"}
33
+ {"time":"2026-08-12T18:21:26.578729863Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"vyycsg6r","id":"3(@)"}
34
+ {"time":"2026-08-12T18:21:31.999599169Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"h28g0ntapnl9"}
35
+ {"time":"2026-08-12T18:38:21.284226521Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"h28g0ntapnl9"}
36
+ {"time":"2026-08-12T18:38:21.818456712Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"h28g0ntapnl9"}
37
+ {"time":"2026-08-12T18:38:21.81999609Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"vyycsg6r","id":"3(@)"}
38
+ {"time":"2026-08-12T18:38:21.828229465Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"vyycsg6r","id":"3(@)"}
39
+ {"time":"2026-08-12T18:38:23.104854149Z","level":"INFO","msg":"handleInformInit: received","streamId":"qtstmmvv","id":"3(@)"}
40
+ {"time":"2026-08-12T18:38:23.372128976Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"qtstmmvv","id":"3(@)"}
41
+ {"time":"2026-08-12T18:38:28.777282159Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"b7qhqvo21369"}
42
+ {"time":"2026-08-12T18:58:01.448371065Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"b7qhqvo21369"}
43
+ {"time":"2026-08-12T18:58:02.001524628Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"b7qhqvo21369"}
44
+ {"time":"2026-08-12T18:58:02.003105094Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"qtstmmvv","id":"3(@)"}
45
+ {"time":"2026-08-12T18:58:02.003794074Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"qtstmmvv","id":"3(@)"}
46
+ {"time":"2026-08-12T18:58:03.201898424Z","level":"INFO","msg":"handleInformInit: received","streamId":"0fh9o8ec","id":"3(@)"}
47
+ {"time":"2026-08-12T18:58:03.568010316Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"0fh9o8ec","id":"3(@)"}
48
+ {"time":"2026-08-12T18:58:09.158050393Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
49
+ {"time":"2026-08-12T19:12:05.373774541Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
50
+ {"time":"2026-08-12T19:12:05.978597092Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"tdwgcmrpt4zh"}
51
+ {"time":"2026-08-12T19:12:05.980085967Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"0fh9o8ec","id":"3(@)"}
52
+ {"time":"2026-08-12T19:12:05.98075482Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"0fh9o8ec","id":"3(@)"}
53
+ {"time":"2026-08-12T19:12:07.497066272Z","level":"INFO","msg":"handleInformInit: received","streamId":"w1cgnksl","id":"3(@)"}
54
+ {"time":"2026-08-12T19:12:07.759791901Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"w1cgnksl","id":"3(@)"}
55
+ {"time":"2026-08-12T19:12:13.17475902Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
56
+ {"time":"2026-08-12T19:26:30.425472974Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
57
+ {"time":"2026-08-12T19:26:30.923201233Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"at6np4o5kef7"}
58
+ {"time":"2026-08-12T19:26:30.924734408Z","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"w1cgnksl","id":"3(@)"}
59
+ {"time":"2026-08-12T19:26:30.925492222Z","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"w1cgnksl","id":"3(@)"}
60
+ {"time":"2026-08-12T19:26:32.010000105Z","level":"INFO","msg":"handleInformInit: received","streamId":"1pwkdnr5","id":"3(@)"}
61
+ {"time":"2026-08-12T19:26:32.273967782Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"1pwkdnr5","id":"3(@)"}
62
+ {"time":"2026-08-12T19:26:37.621886772Z","level":"INFO","msg":"connection: cancelling request","id":"3(@)","requestId":"lxypz1nseyt4"}
zain/Activation/wandb/run-20260812_192631-1pwkdnr5/logs/debug-internal.log ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2026-08-12T19:26:32.010129578Z","level":"INFO","msg":"wandb-core"}
2
+ {"time":"2026-08-12T19:26:32.010264802Z","level":"INFO","msg":"stream: starting","core version":"0.28.1"}
3
+ {"time":"2026-08-12T19:26:32.273779818Z","level":"INFO","msg":"stream: created new stream","id":"1pwkdnr5"}
4
+ {"time":"2026-08-12T19:26:32.273844939Z","level":"INFO","msg":"handler: started"}
5
+ {"time":"2026-08-12T19:26:32.273961668Z","level":"INFO","msg":"stream: started"}
6
+ {"time":"2026-08-12T19:26:32.273969985Z","level":"INFO","msg":"writer: started","stream_id":"1pwkdnr5"}
7
+ {"time":"2026-08-12T19:26:32.273991847Z","level":"INFO","msg":"sender: started"}
8
+ {"time":"2026-08-12T19:26:33.472626381Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":0,"console_lines":1}
9
+ {"time":"2026-08-12T19:26:33.580547558Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
10
+ {"time":"2026-08-12T19:26:48.47323809Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":0,"history_lines":1,"events_offset":0,"events_lines":2,"console_offset":0,"console_lines":2,"uploaded_len":2}
11
+ {"time":"2026-08-12T19:26:48.600344001Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
12
+ {"time":"2026-08-12T19:27:03.473267558Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":1,"history_lines":1,"events_offset":2,"events_lines":2,"console_offset":0,"console_lines":1}
13
+ {"time":"2026-08-12T19:27:03.610205342Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
14
+ {"time":"2026-08-12T19:27:18.473731434Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":2,"history_lines":2,"events_offset":4,"events_lines":2,"console_offset":0,"console_lines":1}
15
+ {"time":"2026-08-12T19:27:18.592911793Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
zain/Activation/wandb/run-20260812_192631-1pwkdnr5/logs/debug.log ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2026-08-12 19:26:31,997 INFO MainThread:1371664 [wandb_init.py:setup_run_log_directory():729] Logging user logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_192631-1pwkdnr5/logs/debug.log
2
+ 2026-08-12 19:26:31,997 INFO MainThread:1371664 [wandb_init.py:setup_run_log_directory():730] Logging internal logs to /mnt/data/zainulabideen/zain-exp/notebooks/zain/Activation/wandb/run-20260812_192631-1pwkdnr5/logs/debug-internal.log
3
+ 2026-08-12 19:26:31,997 INFO MainThread:1371664 [wandb_init.py:init():772] calling init triggers
4
+ 2026-08-12 19:26:31,997 INFO MainThread:1371664 [wandb_init.py:init():777] wandb.init called with sweep_config: {}
5
+ config: {'_wandb': {}}
6
+ 2026-08-12 19:26:31,997 INFO MainThread:1371664 [wandb_init.py:init():820] starting backend
7
+ 2026-08-12 19:26:31,997 INFO MainThread:1371664 [wandb_init.py:init():826] Connected to an existing wandb-core service via WANDB_SERVICE
8
+ 2026-08-12 19:26:31,997 INFO MainThread:1371664 [wandb_init.py:init():835] sending inform_init request
9
+ 2026-08-12 19:26:32,274 INFO MainThread:1371664 [wandb_init.py:init():840] backend started and connected
10
+ 2026-08-12 19:26:32,275 INFO MainThread:1371664 [wandb_init.py:init():910] updated telemetry
11
+ 2026-08-12 19:26:32,282 INFO MainThread:1371664 [wandb_init.py:init():933] communicating run to backend with 90.0 second timeout
12
+ 2026-08-12 19:26:32,537 INFO MainThread:1371664 [wandb_init.py:init():978] starting run threads in backend
13
+ 2026-08-12 19:26:32,619 INFO MainThread:1371664 [wandb_run.py:_console_start():2621] atexit reg
14
+ 2026-08-12 19:26:32,619 INFO MainThread:1371664 [wandb_run.py:_redirect():2471] redirect: wrap_raw
15
+ 2026-08-12 19:26:32,619 INFO MainThread:1371664 [wandb_run.py:_redirect():2540] Wrapping output streams.
16
+ 2026-08-12 19:26:32,619 INFO MainThread:1371664 [wandb_run.py:_redirect():2563] Redirects installed.
17
+ 2026-08-12 19:26:32,620 INFO MainThread:1371664 [wandb_init.py:init():1016] run started, returning control to user process
18
+ 2026-08-12 19:26:32,621 INFO MainThread:1371664 [wandb_run.py:_config_callback():1346] config_cb None None {'transformers_version': '5.16.0.dev0', 'architectures': None, 'output_hidden_states': False, 'return_dict': True, 'dtype': None, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'problem_type': None, 'vocab_size': 4096, 'hidden_size': 128, 'intermediate_size': 256, 'num_hidden_layers': 150, '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': 'mlp', 'activation': 'waleed10', 'waleed_beta': 10.0, 'model_type': 'tiny_llama', 'output_attentions': False, 'output_dir': 'out/mlp-waleed10-150L_run', 'per_device_train_batch_size': 64, 'num_train_epochs': 1, 'max_steps': 1000, 'learning_rate': 0.005, 'lr_scheduler_type': 'constant_with_warmup', 'lr_scheduler_kwargs': None, 'warmup_steps': 200, 'optim': 'adamw_torch_fused', 'optim_args': None, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'optim_target_modules': None, 'gradient_accumulation_steps': 1, 'average_tokens_across_devices': True, 'max_grad_norm': 0.0, '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-mlp-waleed10-150L-25.1M-20260812-192631', 'project': 'huggingface', 'trackio_space_id': None, 'trackio_bucket_id': None, 'trackio_static_space_id': None, 'eval_strategy': 'steps', 'eval_steps': 50, 'eval_delay': 0, 'per_device_eval_batch_size': 128, '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': 1000, 'save_on_each_node': False, 'save_total_limit': None, 'enable_jit_checkpoint': False, 'push_to_hub': False, 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_model_id': 'w-ahmad/6L-mlp-waleed10-150L', 'hub_strategy': 'every_save', 'hub_always_push': False, 'hub_revision': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'restore_callback_states_from_checkpoint': False, 'full_determinism': False, 'seed': 42, 'data_seed': 42, 'use_cpu': False, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'parallelism_config': None, 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'dataloader_prefetch_factor': None, 'dataloader_multiprocessing_context': None, 'dataloader_in_order': True, 'remove_unused_columns': False, 'label_names': None, 'train_sampling_strategy': 'random', 'length_column_name': 'length', 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'ddp_static_graph': None, 'ddp_backend': None, 'ddp_timeout': 1800, 'fsdp': None, 'fsdp_config': None, 'deepspeed': None, 'debug': [], 'skip_memory_metrics': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'resume_from_checkpoint': None, 'local_rank': -1}
19
+ 2026-08-12 19:26:32,628 INFO MainThread:1371664 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 25138816 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x14c635a74990>>
20
+ 2026-08-12 19:26:32,628 INFO MainThread:1371664 [wandb_run.py:_config_callback():1346] config_cb model/num_parameters 25138816 None
zain/Activation/wandb/run-20260812_192631-1pwkdnr5/run-1pwkdnr5.wandb ADDED
Binary file (32.8 kB). View file