Allanatrix commited on
Commit
7cbc40f
·
verified ·
1 Parent(s): 565f4bb

Delete metadata

Browse files
metadata/Final_V3_manifest.json DELETED
@@ -1,10 +0,0 @@
1
- {
2
- "model_name": "Final_V3",
3
- "created_at_utc": "2026-04-13T19:53:04Z",
4
- "source_checkpoint": "/home/ubuntu/artifacts/nexa_mol/v1_full_pretrain/phase1_blackwell_v3/current_checkpoint.pt",
5
- "checkpoint_alias": "/home/ubuntu/artifacts/nexa_mol/v1_full_pretrain/phase1_blackwell_v3/Final_V3.pt",
6
- "bytes": 151419519,
7
- "run_name": "gems_v1_full_pretrain_blackwell_phase1_v3",
8
- "dataset_root": "/home/ubuntu/data/gems_v1_v1_full_pretrain_phase1_v3",
9
- "phase": "ssl_structure_foundation_final_v3"
10
- }
 
 
 
 
 
 
 
 
 
 
 
metadata/archive/20260413T201817Z/latest_checkpoint.txt DELETED
@@ -1 +0,0 @@
1
- /home/ubuntu/artifacts/nexa_mol/final_v3_structure_alignment/v26_r1/current_checkpoint.pt
 
 
metadata/archive/20260413T202042Z/latest_checkpoint.txt DELETED
@@ -1 +0,0 @@
1
- /home/ubuntu/artifacts/nexa_mol/final_v3_structure_alignment/v26_r1/current_checkpoint.pt
 
 
metadata/archive/20260413T213902Z/day1_validation_report.json DELETED
@@ -1,2475 +0,0 @@
1
- {
2
- "analysis_basis": [
3
- "docs/projects/msms_pipeline/Technical_Plan.md",
4
- "docs/projects/msms_pipeline/Engineering.md"
5
- ],
6
- "created_at": "2026-04-13T21:36:19Z",
7
- "dataset_root": "/home/ubuntu/data/gems_v1_handoff_labeled_v26",
8
- "debug_metric_pressures": {
9
- "gpu_max_memory_gb": {
10
- "desired_direction": "stable",
11
- "early_mean": 13.252925169950275,
12
- "improvement_pct": 100.0,
13
- "improvement_pct_clipped": 100.0,
14
- "last": 13.279157161712646,
15
- "late_mean": 13.279157161712646,
16
- "mid_mean": 13.279059082097401,
17
- "pressure": "pressure_up",
18
- "pressure_arrow": "\u2197",
19
- "pressure_score": 1.0
20
- },
21
- "structure_confidence_separation": {
22
- "desired_direction": "higher",
23
- "early_mean": -0.007918493679557749,
24
- "improvement_pct": -531.5617836245987,
25
- "improvement_pct_clipped": -100.0,
26
- "last": -0.0040241447277367115,
27
- "late_mean": -0.05001017991881603,
28
- "mid_mean": -0.032136323077151974,
29
- "pressure": "pressure_down",
30
- "pressure_arrow": "\u2198",
31
- "pressure_score": -1.0
32
- },
33
- "structure_correct_logit_mean": {
34
- "desired_direction": "higher",
35
- "early_mean": 6.134031791907514,
36
- "improvement_pct": 47.305071917778086,
37
- "improvement_pct_clipped": 47.305071917778086,
38
- "last": 9.1875,
39
- "late_mean": 9.035739942528735,
40
- "mid_mean": 9.474891618497109,
41
- "pressure": "pressure_up",
42
- "pressure_arrow": "\u2197",
43
- "pressure_score": 1.0
44
- },
45
- "structure_fingerprint_cosine": {
46
- "desired_direction": "higher",
47
- "early_mean": 0.3965519580968543,
48
- "improvement_pct": 17.58747890372286,
49
- "improvement_pct_clipped": 17.58747890372286,
50
- "last": 0.46021854877471924,
51
- "late_mean": 0.46629545006943846,
52
- "mid_mean": 0.4464927057310336,
53
- "pressure": "pressure_up",
54
- "pressure_arrow": "\u2197",
55
- "pressure_score": 1.0
56
- },
57
- "structure_hit_at_1": {
58
- "desired_direction": "higher",
59
- "early_mean": 0.007880238439306358,
60
- "improvement_pct": 549.6830023383724,
61
- "improvement_pct_clipped": 100.0,
62
- "last": 0.00390625,
63
- "late_mean": 0.051196569683908046,
64
- "mid_mean": 0.032706376445086706,
65
- "pressure": "pressure_up",
66
- "pressure_arrow": "\u2197",
67
- "pressure_score": 1.0
68
- },
69
- "structure_hit_at_20": {
70
- "desired_direction": "higher",
71
- "early_mean": 0.10721865968208093,
72
- "improvement_pct": 239.4614028144399,
73
- "improvement_pct_clipped": 100.0,
74
- "last": 0.1171875,
75
- "late_mean": 0.3639659662356322,
76
- "mid_mean": 0.28105807442196534,
77
- "pressure": "pressure_up",
78
- "pressure_arrow": "\u2197",
79
- "pressure_score": 1.0
80
- },
81
- "structure_hit_at_5": {
82
- "desired_direction": "higher",
83
- "early_mean": 0.03360955563583815,
84
- "improvement_pct": 402.47008675709174,
85
- "improvement_pct_clipped": 100.0,
86
- "last": 0.029296875,
87
- "late_mean": 0.16887796336206898,
88
- "mid_mean": 0.11673591040462428,
89
- "pressure": "pressure_up",
90
- "pressure_arrow": "\u2197",
91
- "pressure_score": 1.0
92
- },
93
- "structure_logit_margin_mean": {
94
- "desired_direction": "higher",
95
- "early_mean": -1.1263999277456647,
96
- "improvement_pct": 1.2274364862230593,
97
- "improvement_pct_clipped": 1.2274364862230593,
98
- "last": -1.0078125,
99
- "late_mean": -1.1125740840517242,
100
- "mid_mean": -1.0154725885115607,
101
- "pressure": "pressure_none",
102
- "pressure_arrow": "\u2192",
103
- "pressure_score": 0.0
104
- },
105
- "structure_retrieval_logit_std": {
106
- "desired_direction": "higher",
107
- "early_mean": 1.0455416592559375,
108
- "improvement_pct": 112.05988926255111,
109
- "improvement_pct_clipped": 100.0,
110
- "last": 0.9839304089546204,
111
- "late_mean": 2.2171744848119803,
112
- "mid_mean": 2.0036371215919537,
113
- "pressure": "pressure_up",
114
- "pressure_arrow": "\u2197",
115
- "pressure_score": 1.0
116
- },
117
- "structure_retrieval_loss": {
118
- "desired_direction": "lower",
119
- "early_mean": 10.237479978903181,
120
- "improvement_pct": 10.094066619063353,
121
- "improvement_pct_clipped": 10.094066619063353,
122
- "last": 10.630162239074707,
123
- "late_mean": 9.204101929719421,
124
- "mid_mean": 9.41523380775672,
125
- "pressure": "pressure_up",
126
- "pressure_arrow": "\u2197",
127
- "pressure_score": 1.0
128
- },
129
- "structure_target_rank_mean": {
130
- "desired_direction": "lower",
131
- "early_mean": 351.84337743858384,
132
- "improvement_pct": 58.80171764880722,
133
- "improvement_pct_clipped": 58.80171764880722,
134
- "last": 314.703125,
135
- "late_mean": 144.9534280711207,
136
- "mid_mean": 176.16389315390174,
137
- "pressure": "pressure_up",
138
- "pressure_arrow": "\u2197",
139
- "pressure_score": 1.0
140
- },
141
- "structure_top1_top2_gap_mean": {
142
- "desired_direction": "higher",
143
- "early_mean": 0.09793567106213873,
144
- "improvement_pct": 59.221149173532794,
145
- "improvement_pct_clipped": 59.221149173532794,
146
- "last": 0.0986328125,
147
- "late_mean": 0.1559343009159483,
148
- "mid_mean": 0.12284365968208093,
149
- "pressure": "pressure_up",
150
- "pressure_arrow": "\u2197",
151
- "pressure_score": 1.0
152
- },
153
- "structure_top1_top2_gap_norm_mean": {
154
- "desired_direction": "higher",
155
- "early_mean": 0.12215662799301864,
156
- "improvement_pct": -35.653274040957065,
157
- "improvement_pct_clipped": -35.653274040957065,
158
- "last": 0.10155132412910461,
159
- "late_mean": 0.07860379065547524,
160
- "mid_mean": 0.07032911504236604,
161
- "pressure": "pressure_down",
162
- "pressure_arrow": "\u2198",
163
- "pressure_score": -1.0
164
- },
165
- "structure_top_negative_logit_mean": {
166
- "desired_direction": "lower",
167
- "early_mean": 7.262102601156069,
168
- "improvement_pct": -39.724147080005764,
169
- "improvement_pct_clipped": -39.724147080005764,
170
- "last": 10.1875,
171
- "late_mean": 10.14691091954023,
172
- "mid_mean": 10.490606936416185,
173
- "pressure": "pressure_down",
174
- "pressure_arrow": "\u2198",
175
- "pressure_score": -1.0
176
- },
177
- "structure_uncertain_fraction": {
178
- "desired_direction": "lower",
179
- "early_mean": 0.924663565751445,
180
- "improvement_pct": -6.108024336610137,
181
- "improvement_pct_clipped": -6.108024336610137,
182
- "last": 0.970703125,
183
- "late_mean": 0.9811422413793104,
184
- "mid_mean": 0.984747561416185,
185
- "pressure": "pressure_down",
186
- "pressure_arrow": "\u2198",
187
- "pressure_score": -1.0
188
- },
189
- "train_loss_ema": {
190
- "desired_direction": "lower",
191
- "early_mean": 6.265581717362126,
192
- "improvement_pct": 10.455707205061195,
193
- "improvement_pct_clipped": 10.455707205061195,
194
- "last": 6.519052214060582,
195
- "late_mean": 5.610470838300897,
196
- "mid_mean": 5.8371378655061745,
197
- "pressure": "pressure_up",
198
- "pressure_arrow": "\u2197",
199
- "pressure_score": 1.0
200
- },
201
- "val_ssl_loss": {
202
- "desired_direction": "lower",
203
- "early_mean": 1.0849772497183745,
204
- "improvement_pct": 2.3192742421198114,
205
- "improvement_pct_clipped": 2.3192742421198114,
206
- "last": 1.0397093277424574,
207
- "late_mean": 1.0598136518327963,
208
- "mid_mean": 1.0747967428483425,
209
- "pressure": "pressure_none",
210
- "pressure_arrow": "\u2192",
211
- "pressure_score": 0.0
212
- },
213
- "val_structure_correct_logit_mean": {
214
- "desired_direction": "higher",
215
- "early_mean": 8.0311279296875,
216
- "improvement_pct": 16.44145855816145,
217
- "improvement_pct_clipped": 16.44145855816145,
218
- "last": 9.49462890625,
219
- "late_mean": 9.3515625,
220
- "mid_mean": 8.441162109375,
221
- "pressure": "pressure_up",
222
- "pressure_arrow": "\u2197",
223
- "pressure_score": 1.0
224
- },
225
- "val_structure_retrieval_logit_std": {
226
- "desired_direction": "higher",
227
- "early_mean": 1.2326001720502973,
228
- "improvement_pct": 102.32641409365677,
229
- "improvement_pct_clipped": 100.0,
230
- "last": 2.6622845763340592,
231
- "late_mean": 2.49387572822161,
232
- "mid_mean": 2.022283688886091,
233
- "pressure": "pressure_up",
234
- "pressure_arrow": "\u2197",
235
- "pressure_score": 1.0
236
- },
237
- "val_structure_retrieval_loss": {
238
- "desired_direction": "lower",
239
- "early_mean": 11.562767315655947,
240
- "improvement_pct": 4.864921250164783,
241
- "improvement_pct_clipped": 4.864921250164783,
242
- "last": 10.882395941764116,
243
- "late_mean": 11.000247791409492,
244
- "mid_mean": 12.150514367967844,
245
- "pressure": "pressure_none",
246
- "pressure_arrow": "\u2192",
247
- "pressure_score": 0.0
248
- },
249
- "val_structure_top1_top2_gap_norm_mean": {
250
- "desired_direction": "higher",
251
- "early_mean": 0.06950851557485294,
252
- "improvement_pct": -16.826381575968767,
253
- "improvement_pct_clipped": -16.826381575968767,
254
- "last": 0.05411380449368153,
255
- "late_mean": 0.0578127475164365,
256
- "mid_mean": 0.07577372609375743,
257
- "pressure": "pressure_down",
258
- "pressure_arrow": "\u2198",
259
- "pressure_score": -1.0
260
- },
261
- "val_structure_top_negative_logit_mean": {
262
- "desired_direction": "lower",
263
- "early_mean": 9.2255859375,
264
- "improvement_pct": -16.07653223245475,
265
- "improvement_pct_clipped": -16.07653223245475,
266
- "last": 10.714599609375,
267
- "late_mean": 10.708740234375,
268
- "mid_mean": 10.51171875,
269
- "pressure": "pressure_down",
270
- "pressure_arrow": "\u2198",
271
- "pressure_score": -1.0
272
- },
273
- "weighted_regularizer_to_contrastive_ratio": {
274
- "desired_direction": "lower",
275
- "early_mean": 0.0667222202939108,
276
- "improvement_pct": 54.60656419810926,
277
- "improvement_pct_clipped": 54.60656419810926,
278
- "last": 0.028996589606316913,
279
- "late_mean": 0.03028750823471251,
280
- "mid_mean": 0.0329437448262181,
281
- "pressure": "pressure_up",
282
- "pressure_arrow": "\u2197",
283
- "pressure_score": 1.0
284
- }
285
- },
286
- "debug_metric_pressures_display": {
287
- "gpu_max_memory_gb": {
288
- "desired_direction": "stable",
289
- "early_mean": 13.252925169950275,
290
- "goal_display": "goal \u2248",
291
- "improvement_pct": 100.0,
292
- "improvement_pct_display": "+100.00%",
293
- "last": 13.279157161712646,
294
- "late_mean": 13.279157161712646,
295
- "mid_mean": 13.279059082097401,
296
- "pressure": "pressure_up",
297
- "pressure_arrow": "\u2197",
298
- "pressure_display": "goal \u2248 | \u2197 +100.00% improving",
299
- "pressure_score": 1.0,
300
- "trend_label": "improving"
301
- },
302
- "structure_confidence_separation": {
303
- "desired_direction": "higher",
304
- "early_mean": -0.007918493679557749,
305
- "goal_display": "goal \u2191",
306
- "improvement_pct": -531.5617836245987,
307
- "improvement_pct_clipped": -100.0,
308
- "improvement_pct_clipped_display": "-100.00%",
309
- "improvement_pct_display": "-531.56%",
310
- "last": -0.0040241447277367115,
311
- "late_mean": -0.05001017991881603,
312
- "mid_mean": -0.032136323077151974,
313
- "pressure": "pressure_down",
314
- "pressure_arrow": "\u2198",
315
- "pressure_display": "goal \u2191 | \u2198 -531.56% worsening",
316
- "pressure_score": -1.0,
317
- "trend_label": "worsening"
318
- },
319
- "structure_correct_logit_mean": {
320
- "desired_direction": "higher",
321
- "early_mean": 6.134031791907514,
322
- "goal_display": "goal \u2191",
323
- "improvement_pct": 47.305071917778086,
324
- "improvement_pct_display": "+47.31%",
325
- "last": 9.1875,
326
- "late_mean": 9.035739942528735,
327
- "mid_mean": 9.474891618497109,
328
- "pressure": "pressure_up",
329
- "pressure_arrow": "\u2197",
330
- "pressure_display": "goal \u2191 | \u2197 +47.31% improving",
331
- "pressure_score": 1.0,
332
- "trend_label": "improving"
333
- },
334
- "structure_fingerprint_cosine": {
335
- "desired_direction": "higher",
336
- "early_mean": 0.3965519580968543,
337
- "goal_display": "goal \u2191",
338
- "improvement_pct": 17.58747890372286,
339
- "improvement_pct_display": "+17.59%",
340
- "last": 0.46021854877471924,
341
- "late_mean": 0.46629545006943846,
342
- "mid_mean": 0.4464927057310336,
343
- "pressure": "pressure_up",
344
- "pressure_arrow": "\u2197",
345
- "pressure_display": "goal \u2191 | \u2197 +17.59% improving",
346
- "pressure_score": 1.0,
347
- "trend_label": "improving"
348
- },
349
- "structure_hit_at_1": {
350
- "desired_direction": "higher",
351
- "early_mean": 0.007880238439306358,
352
- "goal_display": "goal \u2191",
353
- "improvement_pct": 549.6830023383724,
354
- "improvement_pct_clipped": 100.0,
355
- "improvement_pct_clipped_display": "+100.00%",
356
- "improvement_pct_display": "+549.68%",
357
- "last": 0.00390625,
358
- "late_mean": 0.051196569683908046,
359
- "mid_mean": 0.032706376445086706,
360
- "pressure": "pressure_up",
361
- "pressure_arrow": "\u2197",
362
- "pressure_display": "goal \u2191 | \u2197 +549.68% improving",
363
- "pressure_score": 1.0,
364
- "trend_label": "improving"
365
- },
366
- "structure_hit_at_20": {
367
- "desired_direction": "higher",
368
- "early_mean": 0.10721865968208093,
369
- "goal_display": "goal \u2191",
370
- "improvement_pct": 239.4614028144399,
371
- "improvement_pct_clipped": 100.0,
372
- "improvement_pct_clipped_display": "+100.00%",
373
- "improvement_pct_display": "+239.46%",
374
- "last": 0.1171875,
375
- "late_mean": 0.3639659662356322,
376
- "mid_mean": 0.28105807442196534,
377
- "pressure": "pressure_up",
378
- "pressure_arrow": "\u2197",
379
- "pressure_display": "goal \u2191 | \u2197 +239.46% improving",
380
- "pressure_score": 1.0,
381
- "trend_label": "improving"
382
- },
383
- "structure_hit_at_5": {
384
- "desired_direction": "higher",
385
- "early_mean": 0.03360955563583815,
386
- "goal_display": "goal \u2191",
387
- "improvement_pct": 402.47008675709174,
388
- "improvement_pct_clipped": 100.0,
389
- "improvement_pct_clipped_display": "+100.00%",
390
- "improvement_pct_display": "+402.47%",
391
- "last": 0.029296875,
392
- "late_mean": 0.16887796336206898,
393
- "mid_mean": 0.11673591040462428,
394
- "pressure": "pressure_up",
395
- "pressure_arrow": "\u2197",
396
- "pressure_display": "goal \u2191 | \u2197 +402.47% improving",
397
- "pressure_score": 1.0,
398
- "trend_label": "improving"
399
- },
400
- "structure_logit_margin_mean": {
401
- "desired_direction": "higher",
402
- "early_mean": -1.1263999277456647,
403
- "goal_display": "goal \u2191",
404
- "improvement_pct": 1.2274364862230593,
405
- "improvement_pct_display": "+1.23%",
406
- "last": -1.0078125,
407
- "late_mean": -1.1125740840517242,
408
- "mid_mean": -1.0154725885115607,
409
- "pressure": "pressure_none",
410
- "pressure_arrow": "\u2192",
411
- "pressure_display": "goal \u2191 | \u2192 +1.23% flat",
412
- "trend_label": "flat"
413
- },
414
- "structure_retrieval_logit_std": {
415
- "desired_direction": "higher",
416
- "early_mean": 1.0455416592559375,
417
- "goal_display": "goal \u2191",
418
- "improvement_pct": 112.05988926255111,
419
- "improvement_pct_clipped": 100.0,
420
- "improvement_pct_clipped_display": "+100.00%",
421
- "improvement_pct_display": "+112.06%",
422
- "last": 0.9839304089546204,
423
- "late_mean": 2.2171744848119803,
424
- "mid_mean": 2.0036371215919537,
425
- "pressure": "pressure_up",
426
- "pressure_arrow": "\u2197",
427
- "pressure_display": "goal \u2191 | \u2197 +112.06% improving",
428
- "pressure_score": 1.0,
429
- "trend_label": "improving"
430
- },
431
- "structure_retrieval_loss": {
432
- "desired_direction": "lower",
433
- "early_mean": 10.237479978903181,
434
- "goal_display": "goal \u2193",
435
- "improvement_pct": 10.094066619063353,
436
- "improvement_pct_display": "+10.09%",
437
- "last": 10.630162239074707,
438
- "late_mean": 9.204101929719421,
439
- "mid_mean": 9.41523380775672,
440
- "pressure": "pressure_up",
441
- "pressure_arrow": "\u2197",
442
- "pressure_display": "goal \u2193 | \u2197 +10.09% improving",
443
- "pressure_score": 1.0,
444
- "trend_label": "improving"
445
- },
446
- "structure_target_rank_mean": {
447
- "desired_direction": "lower",
448
- "early_mean": 351.84337743858384,
449
- "goal_display": "goal \u2193",
450
- "improvement_pct": 58.80171764880722,
451
- "improvement_pct_display": "+58.80%",
452
- "last": 314.703125,
453
- "late_mean": 144.9534280711207,
454
- "mid_mean": 176.16389315390174,
455
- "pressure": "pressure_up",
456
- "pressure_arrow": "\u2197",
457
- "pressure_display": "goal \u2193 | \u2197 +58.80% improving",
458
- "pressure_score": 1.0,
459
- "trend_label": "improving"
460
- },
461
- "structure_top1_top2_gap_mean": {
462
- "desired_direction": "higher",
463
- "early_mean": 0.09793567106213873,
464
- "goal_display": "goal \u2191",
465
- "improvement_pct": 59.221149173532794,
466
- "improvement_pct_display": "+59.22%",
467
- "last": 0.0986328125,
468
- "late_mean": 0.1559343009159483,
469
- "mid_mean": 0.12284365968208093,
470
- "pressure": "pressure_up",
471
- "pressure_arrow": "\u2197",
472
- "pressure_display": "goal \u2191 | \u2197 +59.22% improving",
473
- "pressure_score": 1.0,
474
- "trend_label": "improving"
475
- },
476
- "structure_top1_top2_gap_norm_mean": {
477
- "desired_direction": "higher",
478
- "early_mean": 0.12215662799301864,
479
- "goal_display": "goal \u2191",
480
- "improvement_pct": -35.653274040957065,
481
- "improvement_pct_display": "-35.65%",
482
- "last": 0.10155132412910461,
483
- "late_mean": 0.07860379065547524,
484
- "mid_mean": 0.07032911504236604,
485
- "pressure": "pressure_down",
486
- "pressure_arrow": "\u2198",
487
- "pressure_display": "goal \u2191 | \u2198 -35.65% worsening",
488
- "pressure_score": -1.0,
489
- "trend_label": "worsening"
490
- },
491
- "structure_top_negative_logit_mean": {
492
- "desired_direction": "lower",
493
- "early_mean": 7.262102601156069,
494
- "goal_display": "goal \u2193",
495
- "improvement_pct": -39.724147080005764,
496
- "improvement_pct_display": "-39.72%",
497
- "last": 10.1875,
498
- "late_mean": 10.14691091954023,
499
- "mid_mean": 10.490606936416185,
500
- "pressure": "pressure_down",
501
- "pressure_arrow": "\u2198",
502
- "pressure_display": "goal \u2193 | \u2198 -39.72% worsening",
503
- "pressure_score": -1.0,
504
- "trend_label": "worsening"
505
- },
506
- "structure_uncertain_fraction": {
507
- "desired_direction": "lower",
508
- "early_mean": 0.924663565751445,
509
- "goal_display": "goal \u2193",
510
- "improvement_pct": -6.108024336610137,
511
- "improvement_pct_display": "-6.11%",
512
- "last": 0.970703125,
513
- "late_mean": 0.9811422413793104,
514
- "mid_mean": 0.984747561416185,
515
- "pressure": "pressure_down",
516
- "pressure_arrow": "\u2198",
517
- "pressure_display": "goal \u2193 | \u2198 -6.11% worsening",
518
- "pressure_score": -1.0,
519
- "trend_label": "worsening"
520
- },
521
- "train_loss_ema": {
522
- "desired_direction": "lower",
523
- "early_mean": 6.265581717362126,
524
- "goal_display": "goal \u2193",
525
- "improvement_pct": 10.455707205061195,
526
- "improvement_pct_display": "+10.46%",
527
- "last": 6.519052214060582,
528
- "late_mean": 5.610470838300897,
529
- "mid_mean": 5.8371378655061745,
530
- "pressure": "pressure_up",
531
- "pressure_arrow": "\u2197",
532
- "pressure_display": "goal \u2193 | \u2197 +10.46% improving",
533
- "pressure_score": 1.0,
534
- "trend_label": "improving"
535
- },
536
- "val_ssl_loss": {
537
- "desired_direction": "lower",
538
- "early_mean": 1.0849772497183745,
539
- "goal_display": "goal \u2193",
540
- "improvement_pct": 2.3192742421198114,
541
- "improvement_pct_display": "+2.32%",
542
- "last": 1.0397093277424574,
543
- "late_mean": 1.0598136518327963,
544
- "mid_mean": 1.0747967428483425,
545
- "pressure": "pressure_none",
546
- "pressure_arrow": "\u2192",
547
- "pressure_display": "goal \u2193 | \u2192 +2.32% flat",
548
- "trend_label": "flat"
549
- },
550
- "val_structure_correct_logit_mean": {
551
- "desired_direction": "higher",
552
- "early_mean": 8.0311279296875,
553
- "goal_display": "goal \u2191",
554
- "improvement_pct": 16.44145855816145,
555
- "improvement_pct_display": "+16.44%",
556
- "last": 9.49462890625,
557
- "late_mean": 9.3515625,
558
- "mid_mean": 8.441162109375,
559
- "pressure": "pressure_up",
560
- "pressure_arrow": "\u2197",
561
- "pressure_display": "goal \u2191 | \u2197 +16.44% improving",
562
- "pressure_score": 1.0,
563
- "trend_label": "improving"
564
- },
565
- "val_structure_retrieval_logit_std": {
566
- "desired_direction": "higher",
567
- "early_mean": 1.2326001720502973,
568
- "goal_display": "goal \u2191",
569
- "improvement_pct": 102.32641409365677,
570
- "improvement_pct_clipped": 100.0,
571
- "improvement_pct_clipped_display": "+100.00%",
572
- "improvement_pct_display": "+102.33%",
573
- "last": 2.6622845763340592,
574
- "late_mean": 2.49387572822161,
575
- "mid_mean": 2.022283688886091,
576
- "pressure": "pressure_up",
577
- "pressure_arrow": "\u2197",
578
- "pressure_display": "goal \u2191 | \u2197 +102.33% improving",
579
- "pressure_score": 1.0,
580
- "trend_label": "improving"
581
- },
582
- "val_structure_retrieval_loss": {
583
- "desired_direction": "lower",
584
- "early_mean": 11.562767315655947,
585
- "goal_display": "goal \u2193",
586
- "improvement_pct": 4.864921250164783,
587
- "improvement_pct_display": "+4.86%",
588
- "last": 10.882395941764116,
589
- "late_mean": 11.000247791409492,
590
- "mid_mean": 12.150514367967844,
591
- "pressure": "pressure_none",
592
- "pressure_arrow": "\u2192",
593
- "pressure_display": "goal \u2193 | \u2192 +4.86% flat",
594
- "trend_label": "flat"
595
- },
596
- "val_structure_top1_top2_gap_norm_mean": {
597
- "desired_direction": "higher",
598
- "early_mean": 0.06950851557485294,
599
- "goal_display": "goal \u2191",
600
- "improvement_pct": -16.826381575968767,
601
- "improvement_pct_display": "-16.83%",
602
- "last": 0.05411380449368153,
603
- "late_mean": 0.0578127475164365,
604
- "mid_mean": 0.07577372609375743,
605
- "pressure": "pressure_down",
606
- "pressure_arrow": "\u2198",
607
- "pressure_display": "goal \u2191 | \u2198 -16.83% worsening",
608
- "pressure_score": -1.0,
609
- "trend_label": "worsening"
610
- },
611
- "val_structure_top_negative_logit_mean": {
612
- "desired_direction": "lower",
613
- "early_mean": 9.2255859375,
614
- "goal_display": "goal \u2193",
615
- "improvement_pct": -16.07653223245475,
616
- "improvement_pct_display": "-16.08%",
617
- "last": 10.714599609375,
618
- "late_mean": 10.708740234375,
619
- "mid_mean": 10.51171875,
620
- "pressure": "pressure_down",
621
- "pressure_arrow": "\u2198",
622
- "pressure_display": "goal \u2193 | \u2198 -16.08% worsening",
623
- "pressure_score": -1.0,
624
- "trend_label": "worsening"
625
- },
626
- "weighted_regularizer_to_contrastive_ratio": {
627
- "desired_direction": "lower",
628
- "early_mean": 0.0667222202939108,
629
- "goal_display": "goal \u2193",
630
- "improvement_pct": 54.60656419810926,
631
- "improvement_pct_display": "+54.61%",
632
- "last": 0.028996589606316913,
633
- "late_mean": 0.03028750823471251,
634
- "mid_mean": 0.0329437448262181,
635
- "pressure": "pressure_up",
636
- "pressure_arrow": "\u2197",
637
- "pressure_display": "goal \u2193 | \u2197 +54.61% improving",
638
- "pressure_score": 1.0,
639
- "trend_label": "improving"
640
- }
641
- },
642
- "debug_metrics": {
643
- "contrastive_loss": 0.5768923759460449,
644
- "covariance_loss": 10.012618064880371,
645
- "dataloader_wait_pct_300s": 0.0382592069912683,
646
- "dataloader_wait_pct_60s": 0.0961140629935623,
647
- "dataloader_wait_pct_900s": 0.066640439237091,
648
- "dataloader_wait_pct_run": 0.06717802801040498,
649
- "gpu_active_fraction": 1.0,
650
- "gpu_max_memory_gb": 13.279157161712646,
651
- "gpu_mem_used_mean_gb": 14.1943359375,
652
- "gpu_mem_util_mean_pct": 14.848754175733243,
653
- "gpu_snapshot_available": 1.0,
654
- "gpu_util_max_pct": 54.0,
655
- "gpu_util_mean_pct": 36.0,
656
- "gpu_util_min_pct": 18.0,
657
- "grad_norm": 1.7659728527069092,
658
- "mfu_estimate": 0.06267708747552383,
659
- "samples_per_sec": 1399.0203442084614,
660
- "samples_per_sec_300s": 1547.033197547462,
661
- "samples_per_sec_60s": 1399.0203442084614,
662
- "samples_per_sec_900s": 1512.7885250414204,
663
- "samples_per_sec_run_mean": 1533.0231795943853,
664
- "step_time_cv_300s": 0.06743440395418321,
665
- "step_time_cv_900s": 0.09218780075615579,
666
- "step_time_sec": 0.3659703749981418,
667
- "structure_bce_loss": 0.08383000642061234,
668
- "structure_close_fraction": 0.029296875,
669
- "structure_confidence_candidate_count": 2126.0,
670
- "structure_confidence_separation": -0.0040241447277367115,
671
- "structure_correct_logit_mean": 9.1875,
672
- "structure_fingerprint_cosine": 0.46021854877471924,
673
- "structure_hit_at_1": 0.00390625,
674
- "structure_hit_at_20": 0.1171875,
675
- "structure_hit_at_5": 0.029296875,
676
- "structure_logit_margin_mean": -1.0078125,
677
- "structure_retrieval_logit_std": 0.9839304089546204,
678
- "structure_retrieval_loss": 10.630162239074707,
679
- "structure_target_rank_mean": 314.703125,
680
- "structure_top1_top2_gap_mean": 0.0986328125,
681
- "structure_top1_top2_gap_norm_mean": 0.10155132412910461,
682
- "structure_top_negative_logit_mean": 10.1875,
683
- "structure_uncertain_fraction": 0.970703125,
684
- "structure_uncertain_hit_at_1": 0.0040241447277367115,
685
- "train_loss": 6.491608619689941,
686
- "train_loss_ema": 6.519052214060582,
687
- "val_loss": 6.646750174145564,
688
- "val_ssl_loss": 1.0397093277424574,
689
- "val_structure_close_fraction": 0.0077972412109375,
690
- "val_structure_close_hit_at_1": 0.014835291571216658,
691
- "val_structure_confidence_candidate_count": 4096.0,
692
- "val_structure_confidence_separation": -0.027957430157584895,
693
- "val_structure_correct_logit_mean": 9.49462890625,
694
- "val_structure_retrieval_logit_std": 2.6622845763340592,
695
- "val_structure_retrieval_loss": 10.882395941764116,
696
- "val_structure_top1_top2_gap_mean": 0.11855697631835938,
697
- "val_structure_top1_top2_gap_norm_mean": 0.05411380449368153,
698
- "val_structure_top_negative_logit_mean": 10.714599609375,
699
- "val_structure_uncertain_fraction": 0.9922027587890625,
700
- "val_structure_uncertain_hit_at_1": 0.027957430157584895,
701
- "variance_loss": 0.00213623046875,
702
- "weighted_regularizer_to_contrastive_ratio": 0.028996589606316913
703
- },
704
- "eval_coverage": {
705
- "configured_test_shard_count": 2,
706
- "configured_test_shards": [
707
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/test/shard_20260313_051433_00000.parquet",
708
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/test/shard_20260313_051454_00000.parquet"
709
- ],
710
- "configured_val_shard_count": 2,
711
- "configured_val_shards": [
712
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051433_00000.parquet",
713
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051454_00000.parquet"
714
- ],
715
- "created_at": "2026-04-13T21:36:17Z",
716
- "eval_batch_limit": 256,
717
- "eval_batches_per_shard_limit": 0,
718
- "eval_loader_mode": "stream",
719
- "eval_mode": "deep",
720
- "full_holdout_coverage": 0.0,
721
- "full_holdout_sweep": false,
722
- "full_test_coverage": 0.0,
723
- "full_val_coverage": 1.0,
724
- "missing_test_shards": [
725
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/test/shard_20260313_051433_00000.parquet",
726
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/test/shard_20260313_051454_00000.parquet"
727
- ],
728
- "missing_val_shards": [],
729
- "observed_eval_batches": 256,
730
- "observed_eval_samples": 131072,
731
- "observed_test_shard_count": 0,
732
- "observed_test_shards": [],
733
- "observed_val_shard_count": 2,
734
- "observed_val_shards": [
735
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051433_00000.parquet",
736
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051454_00000.parquet"
737
- ],
738
- "per_shard_batch_count": {
739
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051433_00000.parquet": 128,
740
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051454_00000.parquet": 128
741
- },
742
- "per_shard_sample_count": {
743
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051433_00000.parquet": 65536,
744
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051454_00000.parquet": 65536
745
- },
746
- "run_step": 10000,
747
- "step": 91001,
748
- "unexpected_eval_shards": []
749
- },
750
- "failure_modes": [
751
- {
752
- "detail": "Observed shard counts {'train': 4, 'val': 2, 'test': 2}; the canonical Day 1 loader contract requires all splits to be readable.",
753
- "name": "dataset_shards_accessible",
754
- "status": "pass"
755
- },
756
- {
757
- "detail": "Training batches continued to arrive with positive throughput and no iterator stall.",
758
- "name": "dataloader_streaming_stable",
759
- "status": "pass"
760
- },
761
- {
762
- "detail": "Technical_Plan requires zero NaN or Inf tensors and finite train/val loss.",
763
- "name": "non_finite_loss_or_tensor_failure",
764
- "status": "pass"
765
- },
766
- {
767
- "detail": "Engineering.md expects slope-aware monitoring; missing validation or retrieval metrics make trend judgment weaker.",
768
- "name": "validation_observability_gap",
769
- "status": "pass"
770
- },
771
- {
772
- "detail": "Technical_Plan Day 1 success requires stable GPU memory through the bounded run.",
773
- "name": "gpu_memory_instability",
774
- "status": "pass"
775
- },
776
- {
777
- "detail": "Checkpoint save and reload is an explicit Day 1 success criterion.",
778
- "name": "checkpoint_save_reload_failure",
779
- "status": "pass"
780
- },
781
- {
782
- "detail": "Engineering.md expects embedding variance monitoring and non-collapsed representations.",
783
- "name": "embedding_collapse",
784
- "status": "pass"
785
- },
786
- {
787
- "detail": "The current instability mode is regularization overpowering the SSL objective and producing jagged total loss.",
788
- "name": "regularizer_dominance",
789
- "status": "pass"
790
- },
791
- {
792
- "detail": "Once the bridge phase begins, Technical_Plan requires retrieval-oriented validation rather than only augmented contrastive loss.",
793
- "name": "structure_supervision_gap",
794
- "status": "pass"
795
- },
796
- {
797
- "detail": "Structure-first qualification now requires explicit confidence diagnostics such as top-1/top-2 separation and uncertainty buckets, not just broader retrieval metrics.",
798
- "name": "confidence_surface_gap",
799
- "status": "pass"
800
- },
801
- {
802
- "detail": "The bridge phase should prefer chemistry-grounded fingerprint targets; hashed fallback targets weaken the retrieval signal.",
803
- "name": "chemistry_target_backend_gap",
804
- "status": "pass"
805
- },
806
- {
807
- "detail": "Bridge runs must improve retrieval after fingerprint fit saturates; fitting BCE while val Hit@20 stays at candidate-bank baseline means ranking is not generalizing.",
808
- "name": "bridge_fit_without_ranking",
809
- "status": "pass"
810
- },
811
- {
812
- "detail": "Engineering.md flags acquisition-artefact shortcut risk; adduct and instrument embeddings remain deliberately down-scaled.",
813
- "name": "metadata_shortcutting",
814
- "status": "watch"
815
- }
816
- ],
817
- "fast_eval_surface": {
818
- "batch_size": 512,
819
- "batches_per_shard": 0,
820
- "configured_val_shard_count": 2,
821
- "configured_val_shards": [
822
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051433_00000.parquet",
823
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051454_00000.parquet"
824
- ],
825
- "created_at": "2026-04-13T20:20:58Z",
826
- "loader_mode": "stream",
827
- "per_shard_batch_count": {},
828
- "per_shard_row_count": {},
829
- "row_count": 0
830
- },
831
- "metric_pressure_summary": {
832
- "average_improvement_pct": 34.52368967199551,
833
- "metric_count": 39,
834
- "overall_arrow": "\u2197",
835
- "overall_pressure": "pressure_up",
836
- "pressure_down_count": 11,
837
- "pressure_none_count": 7,
838
- "pressure_up_count": 21,
839
- "pressure_up_fraction": 0.5384615384615384,
840
- "weighted_improvement_pct": 21.88570985770741,
841
- "weighted_pressure_score": 0.2838709677419355
842
- },
843
- "metric_pressure_summary_display": {
844
- "average_improvement_pct": 34.52368967199551,
845
- "average_improvement_pct_display": "+34.52%",
846
- "metric_count": 39,
847
- "overall_arrow": "\u2197",
848
- "overall_display": "\u2197 improving (+21.89% weighted)",
849
- "overall_label": "improving",
850
- "overall_pressure": "pressure_up",
851
- "pressure_down_count": 11,
852
- "pressure_none_count": 7,
853
- "pressure_up_count": 21,
854
- "pressure_up_fraction": 0.5384615384615384,
855
- "pressure_up_fraction_display": "+53.85%",
856
- "weighted_improvement_pct": 21.88570985770741,
857
- "weighted_improvement_pct_display": "+21.89%",
858
- "weighted_pressure_score": 0.2838709677419355
859
- },
860
- "metric_pressures": {
861
- "contrastive_loss": {
862
- "desired_direction": "lower",
863
- "early_mean": 1.409792113166324,
864
- "improvement_pct": -1.6400841264380104,
865
- "improvement_pct_clipped": -1.6400841264380104,
866
- "last": 0.5768923759460449,
867
- "late_mean": 1.43291388983014,
868
- "mid_mean": 1.3598130204084982,
869
- "pressure": "pressure_none",
870
- "pressure_arrow": "\u2192",
871
- "pressure_score": 0.0
872
- },
873
- "gpu_max_memory_gb": {
874
- "desired_direction": "stable",
875
- "early_mean": 13.252925169950275,
876
- "improvement_pct": 100.0,
877
- "improvement_pct_clipped": 100.0,
878
- "last": 13.279157161712646,
879
- "late_mean": 13.279157161712646,
880
- "mid_mean": 13.279059082097401,
881
- "pressure": "pressure_up",
882
- "pressure_arrow": "\u2197",
883
- "pressure_score": 1.0
884
- },
885
- "grad_norm": {
886
- "desired_direction": "stable",
887
- "early_mean": 4.638080189338309,
888
- "improvement_pct": -100.0,
889
- "improvement_pct_clipped": -100.0,
890
- "last": 1.7659728527069092,
891
- "late_mean": 6.072961742165445,
892
- "mid_mean": 4.979553528603791,
893
- "pressure": "pressure_down",
894
- "pressure_arrow": "\u2198",
895
- "pressure_score": -1.0
896
- },
897
- "samples_per_sec": {
898
- "desired_direction": "higher",
899
- "early_mean": 1575.5664566260843,
900
- "improvement_pct": -2.8825714693532967,
901
- "improvement_pct_clipped": -2.8825714693532967,
902
- "last": 1399.0203442084614,
903
- "late_mean": 1530.1496274666802,
904
- "mid_mean": 1531.3735887168505,
905
- "pressure": "pressure_down",
906
- "pressure_arrow": "\u2198",
907
- "pressure_score": -1.0
908
- },
909
- "structure_bce_loss": {
910
- "desired_direction": "lower",
911
- "early_mean": 0.12293951650489272,
912
- "improvement_pct": 39.749156913940595,
913
- "improvement_pct_clipped": 39.749156913940595,
914
- "last": 0.08383000642061234,
915
- "late_mean": 0.07407209518012302,
916
- "mid_mean": 0.07652380578004556,
917
- "pressure": "pressure_up",
918
- "pressure_arrow": "\u2197",
919
- "pressure_score": 1.0
920
- },
921
- "structure_confidence_separation": {
922
- "desired_direction": "higher",
923
- "early_mean": -0.007918493679557749,
924
- "improvement_pct": -531.5617836245987,
925
- "improvement_pct_clipped": -100.0,
926
- "last": -0.0040241447277367115,
927
- "late_mean": -0.05001017991881603,
928
- "mid_mean": -0.032136323077151974,
929
- "pressure": "pressure_down",
930
- "pressure_arrow": "\u2198",
931
- "pressure_score": -1.0
932
- },
933
- "structure_correct_logit_mean": {
934
- "desired_direction": "higher",
935
- "early_mean": 6.134031791907514,
936
- "improvement_pct": 47.305071917778086,
937
- "improvement_pct_clipped": 47.305071917778086,
938
- "last": 9.1875,
939
- "late_mean": 9.035739942528735,
940
- "mid_mean": 9.474891618497109,
941
- "pressure": "pressure_up",
942
- "pressure_arrow": "\u2197",
943
- "pressure_score": 1.0
944
- },
945
- "structure_fingerprint_cosine": {
946
- "desired_direction": "higher",
947
- "early_mean": 0.3965519580968543,
948
- "improvement_pct": 17.58747890372286,
949
- "improvement_pct_clipped": 17.58747890372286,
950
- "last": 0.46021854877471924,
951
- "late_mean": 0.46629545006943846,
952
- "mid_mean": 0.4464927057310336,
953
- "pressure": "pressure_up",
954
- "pressure_arrow": "\u2197",
955
- "pressure_score": 1.0
956
- },
957
- "structure_hit_at_1": {
958
- "desired_direction": "higher",
959
- "early_mean": 0.007880238439306358,
960
- "improvement_pct": 549.6830023383724,
961
- "improvement_pct_clipped": 100.0,
962
- "last": 0.00390625,
963
- "late_mean": 0.051196569683908046,
964
- "mid_mean": 0.032706376445086706,
965
- "pressure": "pressure_up",
966
- "pressure_arrow": "\u2197",
967
- "pressure_score": 1.0
968
- },
969
- "structure_hit_at_20": {
970
- "desired_direction": "higher",
971
- "early_mean": 0.10721865968208093,
972
- "improvement_pct": 239.4614028144399,
973
- "improvement_pct_clipped": 100.0,
974
- "last": 0.1171875,
975
- "late_mean": 0.3639659662356322,
976
- "mid_mean": 0.28105807442196534,
977
- "pressure": "pressure_up",
978
- "pressure_arrow": "\u2197",
979
- "pressure_score": 1.0
980
- },
981
- "structure_hit_at_5": {
982
- "desired_direction": "higher",
983
- "early_mean": 0.03360955563583815,
984
- "improvement_pct": 402.47008675709174,
985
- "improvement_pct_clipped": 100.0,
986
- "last": 0.029296875,
987
- "late_mean": 0.16887796336206898,
988
- "mid_mean": 0.11673591040462428,
989
- "pressure": "pressure_up",
990
- "pressure_arrow": "\u2197",
991
- "pressure_score": 1.0
992
- },
993
- "structure_logit_margin_mean": {
994
- "desired_direction": "higher",
995
- "early_mean": -1.1263999277456647,
996
- "improvement_pct": 1.2274364862230593,
997
- "improvement_pct_clipped": 1.2274364862230593,
998
- "last": -1.0078125,
999
- "late_mean": -1.1125740840517242,
1000
- "mid_mean": -1.0154725885115607,
1001
- "pressure": "pressure_none",
1002
- "pressure_arrow": "\u2192",
1003
- "pressure_score": 0.0
1004
- },
1005
- "structure_retrieval_logit_std": {
1006
- "desired_direction": "higher",
1007
- "early_mean": 1.0455416592559375,
1008
- "improvement_pct": 112.05988926255111,
1009
- "improvement_pct_clipped": 100.0,
1010
- "last": 0.9839304089546204,
1011
- "late_mean": 2.2171744848119803,
1012
- "mid_mean": 2.0036371215919537,
1013
- "pressure": "pressure_up",
1014
- "pressure_arrow": "\u2197",
1015
- "pressure_score": 1.0
1016
- },
1017
- "structure_retrieval_loss": {
1018
- "desired_direction": "lower",
1019
- "early_mean": 10.237479978903181,
1020
- "improvement_pct": 10.094066619063353,
1021
- "improvement_pct_clipped": 10.094066619063353,
1022
- "last": 10.630162239074707,
1023
- "late_mean": 9.204101929719421,
1024
- "mid_mean": 9.41523380775672,
1025
- "pressure": "pressure_up",
1026
- "pressure_arrow": "\u2197",
1027
- "pressure_score": 1.0
1028
- },
1029
- "structure_target_rank_mean": {
1030
- "desired_direction": "lower",
1031
- "early_mean": 351.84337743858384,
1032
- "improvement_pct": 58.80171764880722,
1033
- "improvement_pct_clipped": 58.80171764880722,
1034
- "last": 314.703125,
1035
- "late_mean": 144.9534280711207,
1036
- "mid_mean": 176.16389315390174,
1037
- "pressure": "pressure_up",
1038
- "pressure_arrow": "\u2197",
1039
- "pressure_score": 1.0
1040
- },
1041
- "structure_top1_top2_gap_mean": {
1042
- "desired_direction": "higher",
1043
- "early_mean": 0.09793567106213873,
1044
- "improvement_pct": 59.221149173532794,
1045
- "improvement_pct_clipped": 59.221149173532794,
1046
- "last": 0.0986328125,
1047
- "late_mean": 0.1559343009159483,
1048
- "mid_mean": 0.12284365968208093,
1049
- "pressure": "pressure_up",
1050
- "pressure_arrow": "\u2197",
1051
- "pressure_score": 1.0
1052
- },
1053
- "structure_top1_top2_gap_norm_mean": {
1054
- "desired_direction": "higher",
1055
- "early_mean": 0.12215662799301864,
1056
- "improvement_pct": -35.653274040957065,
1057
- "improvement_pct_clipped": -35.653274040957065,
1058
- "last": 0.10155132412910461,
1059
- "late_mean": 0.07860379065547524,
1060
- "mid_mean": 0.07032911504236604,
1061
- "pressure": "pressure_down",
1062
- "pressure_arrow": "\u2198",
1063
- "pressure_score": -1.0
1064
- },
1065
- "structure_top_negative_logit_mean": {
1066
- "desired_direction": "lower",
1067
- "early_mean": 7.262102601156069,
1068
- "improvement_pct": -39.724147080005764,
1069
- "improvement_pct_clipped": -39.724147080005764,
1070
- "last": 10.1875,
1071
- "late_mean": 10.14691091954023,
1072
- "mid_mean": 10.490606936416185,
1073
- "pressure": "pressure_down",
1074
- "pressure_arrow": "\u2198",
1075
- "pressure_score": -1.0
1076
- },
1077
- "structure_uncertain_fraction": {
1078
- "desired_direction": "lower",
1079
- "early_mean": 0.924663565751445,
1080
- "improvement_pct": -6.108024336610137,
1081
- "improvement_pct_clipped": -6.108024336610137,
1082
- "last": 0.970703125,
1083
- "late_mean": 0.9811422413793104,
1084
- "mid_mean": 0.984747561416185,
1085
- "pressure": "pressure_down",
1086
- "pressure_arrow": "\u2198",
1087
- "pressure_score": -1.0
1088
- },
1089
- "train_loss": {
1090
- "desired_direction": "lower",
1091
- "early_mean": 6.340343519442343,
1092
- "improvement_pct": 10.566866163080938,
1093
- "improvement_pct_clipped": 10.566866163080938,
1094
- "last": 6.491608619689941,
1095
- "late_mean": 5.670367905463295,
1096
- "mid_mean": 5.795929590401622,
1097
- "pressure": "pressure_up",
1098
- "pressure_arrow": "\u2197",
1099
- "pressure_score": 1.0
1100
- },
1101
- "train_loss_ema": {
1102
- "desired_direction": "lower",
1103
- "early_mean": 6.265581717362126,
1104
- "improvement_pct": 10.455707205061195,
1105
- "improvement_pct_clipped": 10.455707205061195,
1106
- "last": 6.519052214060582,
1107
- "late_mean": 5.610470838300897,
1108
- "mid_mean": 5.8371378655061745,
1109
- "pressure": "pressure_up",
1110
- "pressure_arrow": "\u2197",
1111
- "pressure_score": 1.0
1112
- },
1113
- "val_hit_at_1": {
1114
- "desired_direction": "higher",
1115
- "early_mean": 0.0079345703125,
1116
- "improvement_pct": 207.78846153846155,
1117
- "improvement_pct_clipped": 100.0,
1118
- "last": 0.0282135009765625,
1119
- "late_mean": 0.02442169189453125,
1120
- "mid_mean": 0.01372528076171875,
1121
- "pressure": "pressure_none",
1122
- "pressure_arrow": "\u2192",
1123
- "pressure_score": 0.0
1124
- },
1125
- "val_hit_at_20": {
1126
- "desired_direction": "higher",
1127
- "early_mean": 0.08158111572265625,
1128
- "improvement_pct": 76.67165435331526,
1129
- "improvement_pct_clipped": 76.67165435331526,
1130
- "last": 0.15270233154296875,
1131
- "late_mean": 0.14413070678710938,
1132
- "mid_mean": 0.094146728515625,
1133
- "pressure": "pressure_up",
1134
- "pressure_arrow": "\u2197",
1135
- "pressure_score": 1.0
1136
- },
1137
- "val_hit_at_5": {
1138
- "desired_direction": "higher",
1139
- "early_mean": 0.0288543701171875,
1140
- "improvement_pct": 134.8492860920148,
1141
- "improvement_pct_clipped": 100.0,
1142
- "last": 0.0726776123046875,
1143
- "late_mean": 0.0677642822265625,
1144
- "mid_mean": 0.0425567626953125,
1145
- "pressure": "pressure_up",
1146
- "pressure_arrow": "\u2197",
1147
- "pressure_score": 1.0
1148
- },
1149
- "val_loss": {
1150
- "desired_direction": "lower",
1151
- "early_mean": 1.2876316868363775,
1152
- "improvement_pct": -55.82459156154955,
1153
- "improvement_pct_clipped": -55.82459156154955,
1154
- "last": 6.646750174145564,
1155
- "late_mean": 2.006446816829876,
1156
- "mid_mean": 2.20697861268016,
1157
- "pressure": "pressure_down",
1158
- "pressure_arrow": "\u2198",
1159
- "pressure_score": -1.0
1160
- },
1161
- "val_ssl_loss": {
1162
- "desired_direction": "lower",
1163
- "early_mean": 1.0849772497183745,
1164
- "improvement_pct": 2.3192742421198114,
1165
- "improvement_pct_clipped": 2.3192742421198114,
1166
- "last": 1.0397093277424574,
1167
- "late_mean": 1.0598136518327963,
1168
- "mid_mean": 1.0747967428483425,
1169
- "pressure": "pressure_none",
1170
- "pressure_arrow": "\u2192",
1171
- "pressure_score": 0.0
1172
- },
1173
- "val_structure_bce_loss": {
1174
- "desired_direction": "lower",
1175
- "early_mean": 0.0771060927848642,
1176
- "improvement_pct": 12.199713989530546,
1177
- "improvement_pct_clipped": 12.199713989530546,
1178
- "last": 0.06532714269997086,
1179
- "late_mean": 0.06769936999660872,
1180
- "mid_mean": 0.07029345531468391,
1181
- "pressure": "pressure_up",
1182
- "pressure_arrow": "\u2197",
1183
- "pressure_score": 1.0
1184
- },
1185
- "val_structure_confidence_separation": {
1186
- "desired_direction": "higher",
1187
- "early_mean": -0.00795668972114072,
1188
- "improvement_pct": -204.85499246505236,
1189
- "improvement_pct_clipped": -100.0,
1190
- "last": -0.027957430157584895,
1191
- "late_mean": -0.024256365849851136,
1192
- "mid_mean": -0.01309866098972634,
1193
- "pressure": "pressure_down",
1194
- "pressure_arrow": "\u2198",
1195
- "pressure_score": -1.0
1196
- },
1197
- "val_structure_correct_logit_mean": {
1198
- "desired_direction": "higher",
1199
- "early_mean": 8.0311279296875,
1200
- "improvement_pct": 16.44145855816145,
1201
- "improvement_pct_clipped": 16.44145855816145,
1202
- "last": 9.49462890625,
1203
- "late_mean": 9.3515625,
1204
- "mid_mean": 8.441162109375,
1205
- "pressure": "pressure_up",
1206
- "pressure_arrow": "\u2197",
1207
- "pressure_score": 1.0
1208
- },
1209
- "val_structure_fingerprint_cosine": {
1210
- "desired_direction": "higher",
1211
- "early_mean": 0.4147872725734487,
1212
- "improvement_pct": 0.17175282510408285,
1213
- "improvement_pct_clipped": 0.17175282510408285,
1214
- "last": 0.4255251376889646,
1215
- "late_mean": 0.4154996814322658,
1216
- "mid_mean": 0.4204998221830465,
1217
- "pressure": "pressure_none",
1218
- "pressure_arrow": "\u2192",
1219
- "pressure_score": 0.0
1220
- },
1221
- "val_structure_logit_margin_mean": {
1222
- "desired_direction": "higher",
1223
- "early_mean": -1.194091796875,
1224
- "improvement_pct": -13.669239419341647,
1225
- "improvement_pct_clipped": -13.669239419341647,
1226
- "last": -1.221923828125,
1227
- "late_mean": -1.3573150634765625,
1228
- "mid_mean": -2.0707931518554688,
1229
- "pressure": "pressure_down",
1230
- "pressure_arrow": "\u2198",
1231
- "pressure_score": -1.0
1232
- },
1233
- "val_structure_retrieval_logit_std": {
1234
- "desired_direction": "higher",
1235
- "early_mean": 1.2326001720502973,
1236
- "improvement_pct": 102.32641409365677,
1237
- "improvement_pct_clipped": 100.0,
1238
- "last": 2.6622845763340592,
1239
- "late_mean": 2.49387572822161,
1240
- "mid_mean": 2.022283688886091,
1241
- "pressure": "pressure_up",
1242
- "pressure_arrow": "\u2197",
1243
- "pressure_score": 1.0
1244
- },
1245
- "val_structure_retrieval_loss": {
1246
- "desired_direction": "lower",
1247
- "early_mean": 11.562767315655947,
1248
- "improvement_pct": 4.864921250164783,
1249
- "improvement_pct_clipped": 4.864921250164783,
1250
- "last": 10.882395941764116,
1251
- "late_mean": 11.000247791409492,
1252
- "mid_mean": 12.150514367967844,
1253
- "pressure": "pressure_none",
1254
- "pressure_arrow": "\u2192",
1255
- "pressure_score": 0.0
1256
- },
1257
- "val_structure_target_rank_mean": {
1258
- "desired_direction": "lower",
1259
- "early_mean": 760.7540435791016,
1260
- "improvement_pct": 45.44775026271755,
1261
- "improvement_pct_clipped": 45.44775026271755,
1262
- "last": 379.8781280517578,
1263
- "late_mean": 415.0084457397461,
1264
- "mid_mean": 683.3385162353516,
1265
- "pressure": "pressure_up",
1266
- "pressure_arrow": "\u2197",
1267
- "pressure_score": 1.0
1268
- },
1269
- "val_structure_top1_top2_gap_mean": {
1270
- "desired_direction": "higher",
1271
- "early_mean": 0.07839679718017578,
1272
- "improvement_pct": 54.90785232041847,
1273
- "improvement_pct_clipped": 54.90785232041847,
1274
- "last": 0.11855697631835938,
1275
- "late_mean": 0.12144279479980469,
1276
- "mid_mean": 0.1310901641845703,
1277
- "pressure": "pressure_up",
1278
- "pressure_arrow": "\u2197",
1279
- "pressure_score": 1.0
1280
- },
1281
- "val_structure_top1_top2_gap_norm_mean": {
1282
- "desired_direction": "higher",
1283
- "early_mean": 0.06950851557485294,
1284
- "improvement_pct": -16.826381575968767,
1285
- "improvement_pct_clipped": -16.826381575968767,
1286
- "last": 0.05411380449368153,
1287
- "late_mean": 0.0578127475164365,
1288
- "mid_mean": 0.07577372609375743,
1289
- "pressure": "pressure_down",
1290
- "pressure_arrow": "\u2198",
1291
- "pressure_score": -1.0
1292
- },
1293
- "val_structure_top_negative_logit_mean": {
1294
- "desired_direction": "lower",
1295
- "early_mean": 9.2255859375,
1296
- "improvement_pct": -16.07653223245475,
1297
- "improvement_pct_clipped": -16.07653223245475,
1298
- "last": 10.714599609375,
1299
- "late_mean": 10.708740234375,
1300
- "mid_mean": 10.51171875,
1301
- "pressure": "pressure_down",
1302
- "pressure_arrow": "\u2198",
1303
- "pressure_score": -1.0
1304
- },
1305
- "val_structure_uncertain_fraction": {
1306
- "desired_direction": "lower",
1307
- "early_mean": 0.9941177368164062,
1308
- "improvement_pct": -0.03261678728482514,
1309
- "improvement_pct_clipped": -0.03261678728482514,
1310
- "last": 0.9922027587890625,
1311
- "late_mean": 0.9944419860839844,
1312
- "mid_mean": 0.9762382507324219,
1313
- "pressure": "pressure_none",
1314
- "pressure_arrow": "\u2192",
1315
- "pressure_score": 0.0
1316
- },
1317
- "weighted_regularizer_to_contrastive_ratio": {
1318
- "desired_direction": "lower",
1319
- "early_mean": 0.0667222202939108,
1320
- "improvement_pct": 54.60656419810926,
1321
- "improvement_pct_clipped": 54.60656419810926,
1322
- "last": 0.028996589606316913,
1323
- "late_mean": 0.03028750823471251,
1324
- "mid_mean": 0.0329437448262181,
1325
- "pressure": "pressure_up",
1326
- "pressure_arrow": "\u2197",
1327
- "pressure_score": 1.0
1328
- }
1329
- },
1330
- "metric_pressures_display": {
1331
- "contrastive_loss": {
1332
- "desired_direction": "lower",
1333
- "early_mean": 1.409792113166324,
1334
- "goal_display": "goal \u2193",
1335
- "improvement_pct": -1.6400841264380104,
1336
- "improvement_pct_display": "-1.64%",
1337
- "last": 0.5768923759460449,
1338
- "late_mean": 1.43291388983014,
1339
- "mid_mean": 1.3598130204084982,
1340
- "pressure": "pressure_none",
1341
- "pressure_arrow": "\u2192",
1342
- "pressure_display": "goal \u2193 | \u2192 -1.64% flat",
1343
- "trend_label": "flat"
1344
- },
1345
- "gpu_max_memory_gb": {
1346
- "desired_direction": "stable",
1347
- "early_mean": 13.252925169950275,
1348
- "goal_display": "goal \u2248",
1349
- "improvement_pct": 100.0,
1350
- "improvement_pct_display": "+100.00%",
1351
- "last": 13.279157161712646,
1352
- "late_mean": 13.279157161712646,
1353
- "mid_mean": 13.279059082097401,
1354
- "pressure": "pressure_up",
1355
- "pressure_arrow": "\u2197",
1356
- "pressure_display": "goal \u2248 | \u2197 +100.00% improving",
1357
- "pressure_score": 1.0,
1358
- "trend_label": "improving"
1359
- },
1360
- "grad_norm": {
1361
- "desired_direction": "stable",
1362
- "early_mean": 4.638080189338309,
1363
- "goal_display": "goal \u2248",
1364
- "improvement_pct": -100.0,
1365
- "improvement_pct_display": "-100.00%",
1366
- "last": 1.7659728527069092,
1367
- "late_mean": 6.072961742165445,
1368
- "mid_mean": 4.979553528603791,
1369
- "pressure": "pressure_down",
1370
- "pressure_arrow": "\u2198",
1371
- "pressure_display": "goal \u2248 | \u2198 -100.00% worsening",
1372
- "pressure_score": -1.0,
1373
- "trend_label": "worsening"
1374
- },
1375
- "samples_per_sec": {
1376
- "desired_direction": "higher",
1377
- "early_mean": 1575.5664566260843,
1378
- "goal_display": "goal \u2191",
1379
- "improvement_pct": -2.8825714693532967,
1380
- "improvement_pct_display": "-2.88%",
1381
- "last": 1399.0203442084614,
1382
- "late_mean": 1530.1496274666802,
1383
- "mid_mean": 1531.3735887168505,
1384
- "pressure": "pressure_down",
1385
- "pressure_arrow": "\u2198",
1386
- "pressure_display": "goal \u2191 | \u2198 -2.88% worsening",
1387
- "pressure_score": -1.0,
1388
- "trend_label": "worsening"
1389
- },
1390
- "structure_bce_loss": {
1391
- "desired_direction": "lower",
1392
- "early_mean": 0.12293951650489272,
1393
- "goal_display": "goal \u2193",
1394
- "improvement_pct": 39.749156913940595,
1395
- "improvement_pct_display": "+39.75%",
1396
- "last": 0.08383000642061234,
1397
- "late_mean": 0.07407209518012302,
1398
- "mid_mean": 0.07652380578004556,
1399
- "pressure": "pressure_up",
1400
- "pressure_arrow": "\u2197",
1401
- "pressure_display": "goal \u2193 | \u2197 +39.75% improving",
1402
- "pressure_score": 1.0,
1403
- "trend_label": "improving"
1404
- },
1405
- "structure_confidence_separation": {
1406
- "desired_direction": "higher",
1407
- "early_mean": -0.007918493679557749,
1408
- "goal_display": "goal \u2191",
1409
- "improvement_pct": -531.5617836245987,
1410
- "improvement_pct_clipped": -100.0,
1411
- "improvement_pct_clipped_display": "-100.00%",
1412
- "improvement_pct_display": "-531.56%",
1413
- "last": -0.0040241447277367115,
1414
- "late_mean": -0.05001017991881603,
1415
- "mid_mean": -0.032136323077151974,
1416
- "pressure": "pressure_down",
1417
- "pressure_arrow": "\u2198",
1418
- "pressure_display": "goal \u2191 | \u2198 -531.56% worsening",
1419
- "pressure_score": -1.0,
1420
- "trend_label": "worsening"
1421
- },
1422
- "structure_correct_logit_mean": {
1423
- "desired_direction": "higher",
1424
- "early_mean": 6.134031791907514,
1425
- "goal_display": "goal \u2191",
1426
- "improvement_pct": 47.305071917778086,
1427
- "improvement_pct_display": "+47.31%",
1428
- "last": 9.1875,
1429
- "late_mean": 9.035739942528735,
1430
- "mid_mean": 9.474891618497109,
1431
- "pressure": "pressure_up",
1432
- "pressure_arrow": "\u2197",
1433
- "pressure_display": "goal \u2191 | \u2197 +47.31% improving",
1434
- "pressure_score": 1.0,
1435
- "trend_label": "improving"
1436
- },
1437
- "structure_fingerprint_cosine": {
1438
- "desired_direction": "higher",
1439
- "early_mean": 0.3965519580968543,
1440
- "goal_display": "goal \u2191",
1441
- "improvement_pct": 17.58747890372286,
1442
- "improvement_pct_display": "+17.59%",
1443
- "last": 0.46021854877471924,
1444
- "late_mean": 0.46629545006943846,
1445
- "mid_mean": 0.4464927057310336,
1446
- "pressure": "pressure_up",
1447
- "pressure_arrow": "\u2197",
1448
- "pressure_display": "goal \u2191 | \u2197 +17.59% improving",
1449
- "pressure_score": 1.0,
1450
- "trend_label": "improving"
1451
- },
1452
- "structure_hit_at_1": {
1453
- "desired_direction": "higher",
1454
- "early_mean": 0.007880238439306358,
1455
- "goal_display": "goal \u2191",
1456
- "improvement_pct": 549.6830023383724,
1457
- "improvement_pct_clipped": 100.0,
1458
- "improvement_pct_clipped_display": "+100.00%",
1459
- "improvement_pct_display": "+549.68%",
1460
- "last": 0.00390625,
1461
- "late_mean": 0.051196569683908046,
1462
- "mid_mean": 0.032706376445086706,
1463
- "pressure": "pressure_up",
1464
- "pressure_arrow": "\u2197",
1465
- "pressure_display": "goal \u2191 | \u2197 +549.68% improving",
1466
- "pressure_score": 1.0,
1467
- "trend_label": "improving"
1468
- },
1469
- "structure_hit_at_20": {
1470
- "desired_direction": "higher",
1471
- "early_mean": 0.10721865968208093,
1472
- "goal_display": "goal \u2191",
1473
- "improvement_pct": 239.4614028144399,
1474
- "improvement_pct_clipped": 100.0,
1475
- "improvement_pct_clipped_display": "+100.00%",
1476
- "improvement_pct_display": "+239.46%",
1477
- "last": 0.1171875,
1478
- "late_mean": 0.3639659662356322,
1479
- "mid_mean": 0.28105807442196534,
1480
- "pressure": "pressure_up",
1481
- "pressure_arrow": "\u2197",
1482
- "pressure_display": "goal \u2191 | \u2197 +239.46% improving",
1483
- "pressure_score": 1.0,
1484
- "trend_label": "improving"
1485
- },
1486
- "structure_hit_at_5": {
1487
- "desired_direction": "higher",
1488
- "early_mean": 0.03360955563583815,
1489
- "goal_display": "goal \u2191",
1490
- "improvement_pct": 402.47008675709174,
1491
- "improvement_pct_clipped": 100.0,
1492
- "improvement_pct_clipped_display": "+100.00%",
1493
- "improvement_pct_display": "+402.47%",
1494
- "last": 0.029296875,
1495
- "late_mean": 0.16887796336206898,
1496
- "mid_mean": 0.11673591040462428,
1497
- "pressure": "pressure_up",
1498
- "pressure_arrow": "\u2197",
1499
- "pressure_display": "goal \u2191 | \u2197 +402.47% improving",
1500
- "pressure_score": 1.0,
1501
- "trend_label": "improving"
1502
- },
1503
- "structure_logit_margin_mean": {
1504
- "desired_direction": "higher",
1505
- "early_mean": -1.1263999277456647,
1506
- "goal_display": "goal \u2191",
1507
- "improvement_pct": 1.2274364862230593,
1508
- "improvement_pct_display": "+1.23%",
1509
- "last": -1.0078125,
1510
- "late_mean": -1.1125740840517242,
1511
- "mid_mean": -1.0154725885115607,
1512
- "pressure": "pressure_none",
1513
- "pressure_arrow": "\u2192",
1514
- "pressure_display": "goal \u2191 | \u2192 +1.23% flat",
1515
- "trend_label": "flat"
1516
- },
1517
- "structure_retrieval_logit_std": {
1518
- "desired_direction": "higher",
1519
- "early_mean": 1.0455416592559375,
1520
- "goal_display": "goal \u2191",
1521
- "improvement_pct": 112.05988926255111,
1522
- "improvement_pct_clipped": 100.0,
1523
- "improvement_pct_clipped_display": "+100.00%",
1524
- "improvement_pct_display": "+112.06%",
1525
- "last": 0.9839304089546204,
1526
- "late_mean": 2.2171744848119803,
1527
- "mid_mean": 2.0036371215919537,
1528
- "pressure": "pressure_up",
1529
- "pressure_arrow": "\u2197",
1530
- "pressure_display": "goal \u2191 | \u2197 +112.06% improving",
1531
- "pressure_score": 1.0,
1532
- "trend_label": "improving"
1533
- },
1534
- "structure_retrieval_loss": {
1535
- "desired_direction": "lower",
1536
- "early_mean": 10.237479978903181,
1537
- "goal_display": "goal \u2193",
1538
- "improvement_pct": 10.094066619063353,
1539
- "improvement_pct_display": "+10.09%",
1540
- "last": 10.630162239074707,
1541
- "late_mean": 9.204101929719421,
1542
- "mid_mean": 9.41523380775672,
1543
- "pressure": "pressure_up",
1544
- "pressure_arrow": "\u2197",
1545
- "pressure_display": "goal \u2193 | \u2197 +10.09% improving",
1546
- "pressure_score": 1.0,
1547
- "trend_label": "improving"
1548
- },
1549
- "structure_target_rank_mean": {
1550
- "desired_direction": "lower",
1551
- "early_mean": 351.84337743858384,
1552
- "goal_display": "goal \u2193",
1553
- "improvement_pct": 58.80171764880722,
1554
- "improvement_pct_display": "+58.80%",
1555
- "last": 314.703125,
1556
- "late_mean": 144.9534280711207,
1557
- "mid_mean": 176.16389315390174,
1558
- "pressure": "pressure_up",
1559
- "pressure_arrow": "\u2197",
1560
- "pressure_display": "goal \u2193 | \u2197 +58.80% improving",
1561
- "pressure_score": 1.0,
1562
- "trend_label": "improving"
1563
- },
1564
- "structure_top1_top2_gap_mean": {
1565
- "desired_direction": "higher",
1566
- "early_mean": 0.09793567106213873,
1567
- "goal_display": "goal \u2191",
1568
- "improvement_pct": 59.221149173532794,
1569
- "improvement_pct_display": "+59.22%",
1570
- "last": 0.0986328125,
1571
- "late_mean": 0.1559343009159483,
1572
- "mid_mean": 0.12284365968208093,
1573
- "pressure": "pressure_up",
1574
- "pressure_arrow": "\u2197",
1575
- "pressure_display": "goal \u2191 | \u2197 +59.22% improving",
1576
- "pressure_score": 1.0,
1577
- "trend_label": "improving"
1578
- },
1579
- "structure_top1_top2_gap_norm_mean": {
1580
- "desired_direction": "higher",
1581
- "early_mean": 0.12215662799301864,
1582
- "goal_display": "goal \u2191",
1583
- "improvement_pct": -35.653274040957065,
1584
- "improvement_pct_display": "-35.65%",
1585
- "last": 0.10155132412910461,
1586
- "late_mean": 0.07860379065547524,
1587
- "mid_mean": 0.07032911504236604,
1588
- "pressure": "pressure_down",
1589
- "pressure_arrow": "\u2198",
1590
- "pressure_display": "goal \u2191 | \u2198 -35.65% worsening",
1591
- "pressure_score": -1.0,
1592
- "trend_label": "worsening"
1593
- },
1594
- "structure_top_negative_logit_mean": {
1595
- "desired_direction": "lower",
1596
- "early_mean": 7.262102601156069,
1597
- "goal_display": "goal \u2193",
1598
- "improvement_pct": -39.724147080005764,
1599
- "improvement_pct_display": "-39.72%",
1600
- "last": 10.1875,
1601
- "late_mean": 10.14691091954023,
1602
- "mid_mean": 10.490606936416185,
1603
- "pressure": "pressure_down",
1604
- "pressure_arrow": "\u2198",
1605
- "pressure_display": "goal \u2193 | \u2198 -39.72% worsening",
1606
- "pressure_score": -1.0,
1607
- "trend_label": "worsening"
1608
- },
1609
- "structure_uncertain_fraction": {
1610
- "desired_direction": "lower",
1611
- "early_mean": 0.924663565751445,
1612
- "goal_display": "goal \u2193",
1613
- "improvement_pct": -6.108024336610137,
1614
- "improvement_pct_display": "-6.11%",
1615
- "last": 0.970703125,
1616
- "late_mean": 0.9811422413793104,
1617
- "mid_mean": 0.984747561416185,
1618
- "pressure": "pressure_down",
1619
- "pressure_arrow": "\u2198",
1620
- "pressure_display": "goal \u2193 | \u2198 -6.11% worsening",
1621
- "pressure_score": -1.0,
1622
- "trend_label": "worsening"
1623
- },
1624
- "train_loss": {
1625
- "desired_direction": "lower",
1626
- "early_mean": 6.340343519442343,
1627
- "goal_display": "goal \u2193",
1628
- "improvement_pct": 10.566866163080938,
1629
- "improvement_pct_display": "+10.57%",
1630
- "last": 6.491608619689941,
1631
- "late_mean": 5.670367905463295,
1632
- "mid_mean": 5.795929590401622,
1633
- "pressure": "pressure_up",
1634
- "pressure_arrow": "\u2197",
1635
- "pressure_display": "goal \u2193 | \u2197 +10.57% improving",
1636
- "pressure_score": 1.0,
1637
- "trend_label": "improving"
1638
- },
1639
- "train_loss_ema": {
1640
- "desired_direction": "lower",
1641
- "early_mean": 6.265581717362126,
1642
- "goal_display": "goal \u2193",
1643
- "improvement_pct": 10.455707205061195,
1644
- "improvement_pct_display": "+10.46%",
1645
- "last": 6.519052214060582,
1646
- "late_mean": 5.610470838300897,
1647
- "mid_mean": 5.8371378655061745,
1648
- "pressure": "pressure_up",
1649
- "pressure_arrow": "\u2197",
1650
- "pressure_display": "goal \u2193 | \u2197 +10.46% improving",
1651
- "pressure_score": 1.0,
1652
- "trend_label": "improving"
1653
- },
1654
- "val_hit_at_1": {
1655
- "desired_direction": "higher",
1656
- "early_mean": 0.0079345703125,
1657
- "goal_display": "goal \u2191",
1658
- "improvement_pct": 207.78846153846155,
1659
- "improvement_pct_clipped": 100.0,
1660
- "improvement_pct_clipped_display": "+100.00%",
1661
- "improvement_pct_display": "+207.79%",
1662
- "last": 0.0282135009765625,
1663
- "late_mean": 0.02442169189453125,
1664
- "mid_mean": 0.01372528076171875,
1665
- "pressure": "pressure_none",
1666
- "pressure_arrow": "\u2192",
1667
- "pressure_display": "goal \u2191 | \u2192 +207.79% flat",
1668
- "trend_label": "flat"
1669
- },
1670
- "val_hit_at_20": {
1671
- "desired_direction": "higher",
1672
- "early_mean": 0.08158111572265625,
1673
- "goal_display": "goal \u2191",
1674
- "improvement_pct": 76.67165435331526,
1675
- "improvement_pct_display": "+76.67%",
1676
- "last": 0.15270233154296875,
1677
- "late_mean": 0.14413070678710938,
1678
- "mid_mean": 0.094146728515625,
1679
- "pressure": "pressure_up",
1680
- "pressure_arrow": "\u2197",
1681
- "pressure_display": "goal \u2191 | \u2197 +76.67% improving",
1682
- "pressure_score": 1.0,
1683
- "trend_label": "improving"
1684
- },
1685
- "val_hit_at_5": {
1686
- "desired_direction": "higher",
1687
- "early_mean": 0.0288543701171875,
1688
- "goal_display": "goal \u2191",
1689
- "improvement_pct": 134.8492860920148,
1690
- "improvement_pct_clipped": 100.0,
1691
- "improvement_pct_clipped_display": "+100.00%",
1692
- "improvement_pct_display": "+134.85%",
1693
- "last": 0.0726776123046875,
1694
- "late_mean": 0.0677642822265625,
1695
- "mid_mean": 0.0425567626953125,
1696
- "pressure": "pressure_up",
1697
- "pressure_arrow": "\u2197",
1698
- "pressure_display": "goal \u2191 | \u2197 +134.85% improving",
1699
- "pressure_score": 1.0,
1700
- "trend_label": "improving"
1701
- },
1702
- "val_loss": {
1703
- "desired_direction": "lower",
1704
- "early_mean": 1.2876316868363775,
1705
- "goal_display": "goal \u2193",
1706
- "improvement_pct": -55.82459156154955,
1707
- "improvement_pct_display": "-55.82%",
1708
- "last": 6.646750174145564,
1709
- "late_mean": 2.006446816829876,
1710
- "mid_mean": 2.20697861268016,
1711
- "pressure": "pressure_down",
1712
- "pressure_arrow": "\u2198",
1713
- "pressure_display": "goal \u2193 | \u2198 -55.82% worsening",
1714
- "pressure_score": -1.0,
1715
- "trend_label": "worsening"
1716
- },
1717
- "val_ssl_loss": {
1718
- "desired_direction": "lower",
1719
- "early_mean": 1.0849772497183745,
1720
- "goal_display": "goal \u2193",
1721
- "improvement_pct": 2.3192742421198114,
1722
- "improvement_pct_display": "+2.32%",
1723
- "last": 1.0397093277424574,
1724
- "late_mean": 1.0598136518327963,
1725
- "mid_mean": 1.0747967428483425,
1726
- "pressure": "pressure_none",
1727
- "pressure_arrow": "\u2192",
1728
- "pressure_display": "goal \u2193 | \u2192 +2.32% flat",
1729
- "trend_label": "flat"
1730
- },
1731
- "val_structure_bce_loss": {
1732
- "desired_direction": "lower",
1733
- "early_mean": 0.0771060927848642,
1734
- "goal_display": "goal \u2193",
1735
- "improvement_pct": 12.199713989530546,
1736
- "improvement_pct_display": "+12.20%",
1737
- "last": 0.06532714269997086,
1738
- "late_mean": 0.06769936999660872,
1739
- "mid_mean": 0.07029345531468391,
1740
- "pressure": "pressure_up",
1741
- "pressure_arrow": "\u2197",
1742
- "pressure_display": "goal \u2193 | \u2197 +12.20% improving",
1743
- "pressure_score": 1.0,
1744
- "trend_label": "improving"
1745
- },
1746
- "val_structure_confidence_separation": {
1747
- "desired_direction": "higher",
1748
- "early_mean": -0.00795668972114072,
1749
- "goal_display": "goal \u2191",
1750
- "improvement_pct": -204.85499246505236,
1751
- "improvement_pct_clipped": -100.0,
1752
- "improvement_pct_clipped_display": "-100.00%",
1753
- "improvement_pct_display": "-204.85%",
1754
- "last": -0.027957430157584895,
1755
- "late_mean": -0.024256365849851136,
1756
- "mid_mean": -0.01309866098972634,
1757
- "pressure": "pressure_down",
1758
- "pressure_arrow": "\u2198",
1759
- "pressure_display": "goal \u2191 | \u2198 -204.85% worsening",
1760
- "pressure_score": -1.0,
1761
- "trend_label": "worsening"
1762
- },
1763
- "val_structure_correct_logit_mean": {
1764
- "desired_direction": "higher",
1765
- "early_mean": 8.0311279296875,
1766
- "goal_display": "goal \u2191",
1767
- "improvement_pct": 16.44145855816145,
1768
- "improvement_pct_display": "+16.44%",
1769
- "last": 9.49462890625,
1770
- "late_mean": 9.3515625,
1771
- "mid_mean": 8.441162109375,
1772
- "pressure": "pressure_up",
1773
- "pressure_arrow": "\u2197",
1774
- "pressure_display": "goal \u2191 | \u2197 +16.44% improving",
1775
- "pressure_score": 1.0,
1776
- "trend_label": "improving"
1777
- },
1778
- "val_structure_fingerprint_cosine": {
1779
- "desired_direction": "higher",
1780
- "early_mean": 0.4147872725734487,
1781
- "goal_display": "goal \u2191",
1782
- "improvement_pct": 0.17175282510408285,
1783
- "improvement_pct_display": "+0.17%",
1784
- "last": 0.4255251376889646,
1785
- "late_mean": 0.4154996814322658,
1786
- "mid_mean": 0.4204998221830465,
1787
- "pressure": "pressure_none",
1788
- "pressure_arrow": "\u2192",
1789
- "pressure_display": "goal \u2191 | \u2192 +0.17% flat",
1790
- "trend_label": "flat"
1791
- },
1792
- "val_structure_logit_margin_mean": {
1793
- "desired_direction": "higher",
1794
- "early_mean": -1.194091796875,
1795
- "goal_display": "goal \u2191",
1796
- "improvement_pct": -13.669239419341647,
1797
- "improvement_pct_display": "-13.67%",
1798
- "last": -1.221923828125,
1799
- "late_mean": -1.3573150634765625,
1800
- "mid_mean": -2.0707931518554688,
1801
- "pressure": "pressure_down",
1802
- "pressure_arrow": "\u2198",
1803
- "pressure_display": "goal \u2191 | \u2198 -13.67% worsening",
1804
- "pressure_score": -1.0,
1805
- "trend_label": "worsening"
1806
- },
1807
- "val_structure_retrieval_logit_std": {
1808
- "desired_direction": "higher",
1809
- "early_mean": 1.2326001720502973,
1810
- "goal_display": "goal \u2191",
1811
- "improvement_pct": 102.32641409365677,
1812
- "improvement_pct_clipped": 100.0,
1813
- "improvement_pct_clipped_display": "+100.00%",
1814
- "improvement_pct_display": "+102.33%",
1815
- "last": 2.6622845763340592,
1816
- "late_mean": 2.49387572822161,
1817
- "mid_mean": 2.022283688886091,
1818
- "pressure": "pressure_up",
1819
- "pressure_arrow": "\u2197",
1820
- "pressure_display": "goal \u2191 | \u2197 +102.33% improving",
1821
- "pressure_score": 1.0,
1822
- "trend_label": "improving"
1823
- },
1824
- "val_structure_retrieval_loss": {
1825
- "desired_direction": "lower",
1826
- "early_mean": 11.562767315655947,
1827
- "goal_display": "goal \u2193",
1828
- "improvement_pct": 4.864921250164783,
1829
- "improvement_pct_display": "+4.86%",
1830
- "last": 10.882395941764116,
1831
- "late_mean": 11.000247791409492,
1832
- "mid_mean": 12.150514367967844,
1833
- "pressure": "pressure_none",
1834
- "pressure_arrow": "\u2192",
1835
- "pressure_display": "goal \u2193 | \u2192 +4.86% flat",
1836
- "trend_label": "flat"
1837
- },
1838
- "val_structure_target_rank_mean": {
1839
- "desired_direction": "lower",
1840
- "early_mean": 760.7540435791016,
1841
- "goal_display": "goal \u2193",
1842
- "improvement_pct": 45.44775026271755,
1843
- "improvement_pct_display": "+45.45%",
1844
- "last": 379.8781280517578,
1845
- "late_mean": 415.0084457397461,
1846
- "mid_mean": 683.3385162353516,
1847
- "pressure": "pressure_up",
1848
- "pressure_arrow": "\u2197",
1849
- "pressure_display": "goal \u2193 | \u2197 +45.45% improving",
1850
- "pressure_score": 1.0,
1851
- "trend_label": "improving"
1852
- },
1853
- "val_structure_top1_top2_gap_mean": {
1854
- "desired_direction": "higher",
1855
- "early_mean": 0.07839679718017578,
1856
- "goal_display": "goal \u2191",
1857
- "improvement_pct": 54.90785232041847,
1858
- "improvement_pct_display": "+54.91%",
1859
- "last": 0.11855697631835938,
1860
- "late_mean": 0.12144279479980469,
1861
- "mid_mean": 0.1310901641845703,
1862
- "pressure": "pressure_up",
1863
- "pressure_arrow": "\u2197",
1864
- "pressure_display": "goal \u2191 | \u2197 +54.91% improving",
1865
- "pressure_score": 1.0,
1866
- "trend_label": "improving"
1867
- },
1868
- "val_structure_top1_top2_gap_norm_mean": {
1869
- "desired_direction": "higher",
1870
- "early_mean": 0.06950851557485294,
1871
- "goal_display": "goal \u2191",
1872
- "improvement_pct": -16.826381575968767,
1873
- "improvement_pct_display": "-16.83%",
1874
- "last": 0.05411380449368153,
1875
- "late_mean": 0.0578127475164365,
1876
- "mid_mean": 0.07577372609375743,
1877
- "pressure": "pressure_down",
1878
- "pressure_arrow": "\u2198",
1879
- "pressure_display": "goal \u2191 | \u2198 -16.83% worsening",
1880
- "pressure_score": -1.0,
1881
- "trend_label": "worsening"
1882
- },
1883
- "val_structure_top_negative_logit_mean": {
1884
- "desired_direction": "lower",
1885
- "early_mean": 9.2255859375,
1886
- "goal_display": "goal \u2193",
1887
- "improvement_pct": -16.07653223245475,
1888
- "improvement_pct_display": "-16.08%",
1889
- "last": 10.714599609375,
1890
- "late_mean": 10.708740234375,
1891
- "mid_mean": 10.51171875,
1892
- "pressure": "pressure_down",
1893
- "pressure_arrow": "\u2198",
1894
- "pressure_display": "goal \u2193 | \u2198 -16.08% worsening",
1895
- "pressure_score": -1.0,
1896
- "trend_label": "worsening"
1897
- },
1898
- "val_structure_uncertain_fraction": {
1899
- "desired_direction": "lower",
1900
- "early_mean": 0.9941177368164062,
1901
- "goal_display": "goal \u2193",
1902
- "improvement_pct": -0.03261678728482514,
1903
- "improvement_pct_display": "-0.03%",
1904
- "last": 0.9922027587890625,
1905
- "late_mean": 0.9944419860839844,
1906
- "mid_mean": 0.9762382507324219,
1907
- "pressure": "pressure_none",
1908
- "pressure_arrow": "\u2192",
1909
- "pressure_display": "goal \u2193 | \u2192 -0.03% flat",
1910
- "trend_label": "flat"
1911
- },
1912
- "weighted_regularizer_to_contrastive_ratio": {
1913
- "desired_direction": "lower",
1914
- "early_mean": 0.0667222202939108,
1915
- "goal_display": "goal \u2193",
1916
- "improvement_pct": 54.60656419810926,
1917
- "improvement_pct_display": "+54.61%",
1918
- "last": 0.028996589606316913,
1919
- "late_mean": 0.03028750823471251,
1920
- "mid_mean": 0.0329437448262181,
1921
- "pressure": "pressure_up",
1922
- "pressure_arrow": "\u2197",
1923
- "pressure_display": "goal \u2193 | \u2197 +54.61% improving",
1924
- "pressure_score": 1.0,
1925
- "trend_label": "improving"
1926
- }
1927
- },
1928
- "metrics": {
1929
- "backbone_lr": 3.886130904636371e-06,
1930
- "checkpoint_path": "/home/ubuntu/artifacts/nexa_mol/final_v3_structure_alignment/v26_r1/current_checkpoint.pt",
1931
- "checkpoint_reloaded": 1.0,
1932
- "contrastive_loss": 0.5768923759460449,
1933
- "covariance_loss": 10.012618064880371,
1934
- "covariance_to_contrastive_ratio": 17.356128252623712,
1935
- "covariance_weight": 0.0015,
1936
- "dataloader_time_sec": 0.00035174899676349014,
1937
- "dataloader_wait_pct_300s": 0.0382592069912683,
1938
- "dataloader_wait_pct_60s": 0.0961140629935623,
1939
- "dataloader_wait_pct_900s": 0.066640439237091,
1940
- "dataloader_wait_pct_run": 0.06717802801040498,
1941
- "different_inchikey_mean_cosine": 0.004679911238535274,
1942
- "distributed_rank": 0.0,
1943
- "distributed_world_size": 1.0,
1944
- "effective_batch_size": 512.0,
1945
- "effective_hard_negative_scale": 1.0,
1946
- "effective_retrieval_weight": 0.6,
1947
- "effective_structure_bce_weight": 1.0,
1948
- "embedding_mean_norm": 1.0,
1949
- "embedding_offdiag_mean_cosine": 0.009513536468148232,
1950
- "embedding_std": 0.07216806709766388,
1951
- "global_batch_size": 512.0,
1952
- "gpu_active_fraction": 1.0,
1953
- "gpu_count_observed": 2.0,
1954
- "gpu_max_memory_gb": 13.279157161712646,
1955
- "gpu_mem_used_mean_gb": 14.1943359375,
1956
- "gpu_mem_util_mean_pct": 14.848754175733243,
1957
- "gpu_memory_stable": true,
1958
- "gpu_memory_utilization": 0.13982381154325935,
1959
- "gpu_snapshot_available": 1.0,
1960
- "gpu_util_max_pct": 54.0,
1961
- "gpu_util_mean_pct": 36.0,
1962
- "gpu_util_min_pct": 18.0,
1963
- "grad_norm": 1.7659728527069092,
1964
- "holdout_full_coverage": 0.0,
1965
- "local_batch_size": 512.0,
1966
- "lr": 3.886130904636371e-06,
1967
- "mfu_estimate": 0.06267708747552383,
1968
- "msms_objective": "hybrid",
1969
- "optimizer_step": 1.0,
1970
- "regularizer_ramp": 1.0,
1971
- "resume_checkpoint_path": "/home/ubuntu/artifacts/nexa_mol/final_v3_structure_alignment/v26_r1/current_checkpoint.pt",
1972
- "resume_start_step": 81002.0,
1973
- "resumed_from_checkpoint": 1.0,
1974
- "retrieval_head_lr": 1.9430654523181854e-05,
1975
- "same_inchikey_mean_cosine": 0.16267980930137343,
1976
- "samples_per_sec": 1399.0203442084614,
1977
- "samples_per_sec_300s": 1547.033197547462,
1978
- "samples_per_sec_60s": 1399.0203442084614,
1979
- "samples_per_sec_900s": 1512.7885250414204,
1980
- "samples_per_sec_run_mean": 1533.0231795943853,
1981
- "step_time_cv_300s": 0.06743440395418321,
1982
- "step_time_cv_60s": 0.0,
1983
- "step_time_cv_900s": 0.09218780075615579,
1984
- "step_time_sec": 0.3659703749981418,
1985
- "structure_bce_locked": 0.0,
1986
- "structure_bce_loss": 0.08383000642061234,
1987
- "structure_candidate_count": 2126.0,
1988
- "structure_clear_fraction": 0.0,
1989
- "structure_clear_hit_at_1": 0.0,
1990
- "structure_close_fraction": 0.029296875,
1991
- "structure_close_hit_at_1": 0.0,
1992
- "structure_confidence_bucket_score_mean": 0.10155132412910461,
1993
- "structure_confidence_bucket_score_mode": "normalized_gap",
1994
- "structure_confidence_candidate_count": 2126.0,
1995
- "structure_confidence_clear_threshold": 1.0,
1996
- "structure_confidence_close_threshold": 0.35,
1997
- "structure_confidence_eval_key_mode": "target_identity",
1998
- "structure_confidence_separation": -0.0040241447277367115,
1999
- "structure_correct_logit_mean": 9.1875,
2000
- "structure_fingerprint_cosine": 0.46021854877471924,
2001
- "structure_hard_negative_bonus_applied": 1.0,
2002
- "structure_hard_negative_bonus_mean": 0.060302734375,
2003
- "structure_hard_negative_scale": 1.0,
2004
- "structure_head_lr": 1.9430654523181854e-05,
2005
- "structure_hit_at_1": 0.00390625,
2006
- "structure_hit_at_20": 0.1171875,
2007
- "structure_hit_at_5": 0.029296875,
2008
- "structure_local_ce_loss": 3.545562744140625,
2009
- "structure_local_ce_loss_weight": 0.4,
2010
- "structure_local_rerank_loss": 0.0,
2011
- "structure_local_rerank_loss_weight": 0.0,
2012
- "structure_local_rerank_score_scale": 1.0,
2013
- "structure_logit_margin_mean": -1.0078125,
2014
- "structure_margin_loss": 0.0,
2015
- "structure_margin_loss_weight": 0.0,
2016
- "structure_missing_formula_fraction": 0.0,
2017
- "structure_missing_inchikey_fraction": 0.0,
2018
- "structure_pairwise_logistic_loss": 0.0,
2019
- "structure_pairwise_logistic_loss_weight": 0.0,
2020
- "structure_positive_count_mean": 1.0,
2021
- "structure_post_label_candidate_count": 2126.0,
2022
- "structure_post_precursor_candidate_count": 2128.0,
2023
- "structure_prefilter_candidate_count": 2128.0,
2024
- "structure_retrieval_logit_std": 0.9839304089546204,
2025
- "structure_retrieval_loss": 10.630162239074707,
2026
- "structure_retrieval_scorer": "projected_dot",
2027
- "structure_retrieval_target_mode": "sample",
2028
- "structure_skipped_query_fraction": 0.0,
2029
- "structure_soft_target_exact_mix": 0.4,
2030
- "structure_soft_target_loss": 7.523618221282959,
2031
- "structure_soft_target_loss_weight": 0.3,
2032
- "structure_target_backend": "rdkit_morgan",
2033
- "structure_target_equivalent_count_mean": 1.0,
2034
- "structure_target_identity_collision_count": 0.0,
2035
- "structure_target_rank_mean": 314.703125,
2036
- "structure_to_ssl_ratio": 217.7124787233957,
2037
- "structure_top1_top2_gap_mean": 0.0986328125,
2038
- "structure_top1_top2_gap_norm_mean": 0.10155132412910461,
2039
- "structure_top_negative_logit_mean": 10.1875,
2040
- "structure_uncertain_fraction": 0.970703125,
2041
- "structure_uncertain_hit_at_1": 0.0040241447277367115,
2042
- "structure_valid_query_fraction": 1.0,
2043
- "test_expected_shard_count": 2.0,
2044
- "test_full_coverage": 0.0,
2045
- "test_observed_shard_count": 0.0,
2046
- "train_loss": 6.491608619689941,
2047
- "train_loss_ema": 6.519052214060582,
2048
- "train_retrieval_bank_size": 4096.0,
2049
- "val_deep_eval_single_view": 0.0,
2050
- "val_deep_eval_structure_only": 0.0,
2051
- "val_effective_structure_bce_weight": 1.0,
2052
- "val_eval_loader_mode": "stream",
2053
- "val_eval_mode": "deep",
2054
- "val_expected_shard_count": 2.0,
2055
- "val_full_coverage": 1.0,
2056
- "val_hit_at_1": 0.0282135009765625,
2057
- "val_hit_at_20": 0.15270233154296875,
2058
- "val_hit_at_5": 0.0726776123046875,
2059
- "val_loss": 6.646750174145564,
2060
- "val_observed_eval_batches": 256.0,
2061
- "val_observed_shard_count": 2.0,
2062
- "val_ssl_loss": 1.0397093277424574,
2063
- "val_structure_bce_loss": 0.06532714269997086,
2064
- "val_structure_candidate_count": 4119.69140625,
2065
- "val_structure_clear_fraction": 0.0,
2066
- "val_structure_clear_hit_at_1": 0.0,
2067
- "val_structure_close_fraction": 0.0077972412109375,
2068
- "val_structure_close_hit_at_1": 0.014835291571216658,
2069
- "val_structure_confidence_candidate_count": 4096.0,
2070
- "val_structure_confidence_separation": -0.027957430157584895,
2071
- "val_structure_correct_logit_mean": 9.49462890625,
2072
- "val_structure_fingerprint_cosine": 0.4255251376889646,
2073
- "val_structure_logit_margin_mean": -1.221923828125,
2074
- "val_structure_missing_formula_fraction": 0.0,
2075
- "val_structure_missing_inchikey_fraction": 0.0,
2076
- "val_structure_retrieval_logit_std": 2.6622845763340592,
2077
- "val_structure_retrieval_loss": 10.882395941764116,
2078
- "val_structure_target_equivalent_count_mean": 1.0,
2079
- "val_structure_target_identity_collision_count": 23.69140625,
2080
- "val_structure_target_rank_mean": 379.8781280517578,
2081
- "val_structure_top1_top2_gap_mean": 0.11855697631835938,
2082
- "val_structure_top1_top2_gap_norm_mean": 0.05411380449368153,
2083
- "val_structure_top_negative_logit_mean": 10.714599609375,
2084
- "val_structure_uncertain_fraction": 0.9922027587890625,
2085
- "val_structure_uncertain_hit_at_1": 0.027957430157584895,
2086
- "variance_loss": 0.00213623046875,
2087
- "variance_weight": 0.8,
2088
- "weighted_covariance_loss": 0.015018927097320557,
2089
- "weighted_regularizer_to_contrastive_ratio": 0.028996589606316913,
2090
- "weighted_ssl_loss": 0.02968101501464844,
2091
- "weighted_structure_bce_loss": 0.08383000642061234,
2092
- "weighted_structure_retrieval_loss": 6.378097343444824,
2093
- "weighted_variance_loss": 0.001708984375
2094
- },
2095
- "primary_metric_pressure_summary": {
2096
- "average_improvement_pct": -14.247321653690681,
2097
- "metric_count": 12,
2098
- "overall_arrow": "\u2197",
2099
- "overall_pressure": "pressure_up",
2100
- "pressure_down_count": 4,
2101
- "pressure_none_count": 3,
2102
- "pressure_up_count": 5,
2103
- "pressure_up_fraction": 0.4166666666666667,
2104
- "weighted_improvement_pct": -4.446275812252011,
2105
- "weighted_pressure_score": 0.1702127659574468
2106
- },
2107
- "primary_metric_pressure_summary_display": {
2108
- "average_improvement_pct": -14.247321653690681,
2109
- "average_improvement_pct_display": "-14.25%",
2110
- "metric_count": 12,
2111
- "overall_arrow": "\u2197",
2112
- "overall_display": "\u2197 improving (-4.45% weighted)",
2113
- "overall_label": "improving",
2114
- "overall_pressure": "pressure_up",
2115
- "pressure_down_count": 4,
2116
- "pressure_none_count": 3,
2117
- "pressure_up_count": 5,
2118
- "pressure_up_fraction": 0.4166666666666667,
2119
- "pressure_up_fraction_display": "+41.67%",
2120
- "weighted_improvement_pct": -4.446275812252011,
2121
- "weighted_improvement_pct_display": "-4.45%",
2122
- "weighted_pressure_score": 0.1702127659574468
2123
- },
2124
- "primary_metric_pressures": {
2125
- "contrastive_loss": {
2126
- "desired_direction": "lower",
2127
- "early_mean": 1.409792113166324,
2128
- "improvement_pct": -1.6400841264380104,
2129
- "improvement_pct_clipped": -1.6400841264380104,
2130
- "last": 0.5768923759460449,
2131
- "late_mean": 1.43291388983014,
2132
- "mid_mean": 1.3598130204084982,
2133
- "pressure": "pressure_none",
2134
- "pressure_arrow": "\u2192",
2135
- "pressure_score": 0.0
2136
- },
2137
- "grad_norm": {
2138
- "desired_direction": "stable",
2139
- "early_mean": 4.638080189338309,
2140
- "improvement_pct": -100.0,
2141
- "improvement_pct_clipped": -100.0,
2142
- "last": 1.7659728527069092,
2143
- "late_mean": 6.072961742165445,
2144
- "mid_mean": 4.979553528603791,
2145
- "pressure": "pressure_down",
2146
- "pressure_arrow": "\u2198",
2147
- "pressure_score": -1.0
2148
- },
2149
- "samples_per_sec": {
2150
- "desired_direction": "higher",
2151
- "early_mean": 1575.5664566260843,
2152
- "improvement_pct": -2.8825714693532967,
2153
- "improvement_pct_clipped": -2.8825714693532967,
2154
- "last": 1399.0203442084614,
2155
- "late_mean": 1530.1496274666802,
2156
- "mid_mean": 1531.3735887168505,
2157
- "pressure": "pressure_down",
2158
- "pressure_arrow": "\u2198",
2159
- "pressure_score": -1.0
2160
- },
2161
- "structure_bce_loss": {
2162
- "desired_direction": "lower",
2163
- "early_mean": 0.12293951650489272,
2164
- "improvement_pct": 39.749156913940595,
2165
- "improvement_pct_clipped": 39.749156913940595,
2166
- "last": 0.08383000642061234,
2167
- "late_mean": 0.07407209518012302,
2168
- "mid_mean": 0.07652380578004556,
2169
- "pressure": "pressure_up",
2170
- "pressure_arrow": "\u2197",
2171
- "pressure_score": 1.0
2172
- },
2173
- "train_loss": {
2174
- "desired_direction": "lower",
2175
- "early_mean": 6.340343519442343,
2176
- "improvement_pct": 10.566866163080938,
2177
- "improvement_pct_clipped": 10.566866163080938,
2178
- "last": 6.491608619689941,
2179
- "late_mean": 5.670367905463295,
2180
- "mid_mean": 5.795929590401622,
2181
- "pressure": "pressure_up",
2182
- "pressure_arrow": "\u2197",
2183
- "pressure_score": 1.0
2184
- },
2185
- "val_hit_at_20": {
2186
- "desired_direction": "higher",
2187
- "early_mean": 0.08158111572265625,
2188
- "improvement_pct": 76.67165435331526,
2189
- "improvement_pct_clipped": 76.67165435331526,
2190
- "last": 0.15270233154296875,
2191
- "late_mean": 0.14413070678710938,
2192
- "mid_mean": 0.094146728515625,
2193
- "pressure": "pressure_up",
2194
- "pressure_arrow": "\u2197",
2195
- "pressure_score": 1.0
2196
- },
2197
- "val_loss": {
2198
- "desired_direction": "lower",
2199
- "early_mean": 1.2876316868363775,
2200
- "improvement_pct": -55.82459156154955,
2201
- "improvement_pct_clipped": -55.82459156154955,
2202
- "last": 6.646750174145564,
2203
- "late_mean": 2.006446816829876,
2204
- "mid_mean": 2.20697861268016,
2205
- "pressure": "pressure_down",
2206
- "pressure_arrow": "\u2198",
2207
- "pressure_score": -1.0
2208
- },
2209
- "val_structure_bce_loss": {
2210
- "desired_direction": "lower",
2211
- "early_mean": 0.0771060927848642,
2212
- "improvement_pct": 12.199713989530546,
2213
- "improvement_pct_clipped": 12.199713989530546,
2214
- "last": 0.06532714269997086,
2215
- "late_mean": 0.06769936999660872,
2216
- "mid_mean": 0.07029345531468391,
2217
- "pressure": "pressure_up",
2218
- "pressure_arrow": "\u2197",
2219
- "pressure_score": 1.0
2220
- },
2221
- "val_structure_confidence_separation": {
2222
- "desired_direction": "higher",
2223
- "early_mean": -0.00795668972114072,
2224
- "improvement_pct": -204.85499246505236,
2225
- "improvement_pct_clipped": -100.0,
2226
- "last": -0.027957430157584895,
2227
- "late_mean": -0.024256365849851136,
2228
- "mid_mean": -0.01309866098972634,
2229
- "pressure": "pressure_down",
2230
- "pressure_arrow": "\u2198",
2231
- "pressure_score": -1.0
2232
- },
2233
- "val_structure_fingerprint_cosine": {
2234
- "desired_direction": "higher",
2235
- "early_mean": 0.4147872725734487,
2236
- "improvement_pct": 0.17175282510408285,
2237
- "improvement_pct_clipped": 0.17175282510408285,
2238
- "last": 0.4255251376889646,
2239
- "late_mean": 0.4154996814322658,
2240
- "mid_mean": 0.4204998221830465,
2241
- "pressure": "pressure_none",
2242
- "pressure_arrow": "\u2192",
2243
- "pressure_score": 0.0
2244
- },
2245
- "val_structure_top1_top2_gap_mean": {
2246
- "desired_direction": "higher",
2247
- "early_mean": 0.07839679718017578,
2248
- "improvement_pct": 54.90785232041847,
2249
- "improvement_pct_clipped": 54.90785232041847,
2250
- "last": 0.11855697631835938,
2251
- "late_mean": 0.12144279479980469,
2252
- "mid_mean": 0.1310901641845703,
2253
- "pressure": "pressure_up",
2254
- "pressure_arrow": "\u2197",
2255
- "pressure_score": 1.0
2256
- },
2257
- "val_structure_uncertain_fraction": {
2258
- "desired_direction": "lower",
2259
- "early_mean": 0.9941177368164062,
2260
- "improvement_pct": -0.03261678728482514,
2261
- "improvement_pct_clipped": -0.03261678728482514,
2262
- "last": 0.9922027587890625,
2263
- "late_mean": 0.9944419860839844,
2264
- "mid_mean": 0.9762382507324219,
2265
- "pressure": "pressure_none",
2266
- "pressure_arrow": "\u2192",
2267
- "pressure_score": 0.0
2268
- }
2269
- },
2270
- "primary_metric_pressures_display": {
2271
- "contrastive_loss": {
2272
- "desired_direction": "lower",
2273
- "early_mean": 1.409792113166324,
2274
- "goal_display": "goal \u2193",
2275
- "improvement_pct": -1.6400841264380104,
2276
- "improvement_pct_display": "-1.64%",
2277
- "last": 0.5768923759460449,
2278
- "late_mean": 1.43291388983014,
2279
- "mid_mean": 1.3598130204084982,
2280
- "pressure": "pressure_none",
2281
- "pressure_arrow": "\u2192",
2282
- "pressure_display": "goal \u2193 | \u2192 -1.64% flat",
2283
- "trend_label": "flat"
2284
- },
2285
- "grad_norm": {
2286
- "desired_direction": "stable",
2287
- "early_mean": 4.638080189338309,
2288
- "goal_display": "goal \u2248",
2289
- "improvement_pct": -100.0,
2290
- "improvement_pct_display": "-100.00%",
2291
- "last": 1.7659728527069092,
2292
- "late_mean": 6.072961742165445,
2293
- "mid_mean": 4.979553528603791,
2294
- "pressure": "pressure_down",
2295
- "pressure_arrow": "\u2198",
2296
- "pressure_display": "goal \u2248 | \u2198 -100.00% worsening",
2297
- "pressure_score": -1.0,
2298
- "trend_label": "worsening"
2299
- },
2300
- "samples_per_sec": {
2301
- "desired_direction": "higher",
2302
- "early_mean": 1575.5664566260843,
2303
- "goal_display": "goal \u2191",
2304
- "improvement_pct": -2.8825714693532967,
2305
- "improvement_pct_display": "-2.88%",
2306
- "last": 1399.0203442084614,
2307
- "late_mean": 1530.1496274666802,
2308
- "mid_mean": 1531.3735887168505,
2309
- "pressure": "pressure_down",
2310
- "pressure_arrow": "\u2198",
2311
- "pressure_display": "goal \u2191 | \u2198 -2.88% worsening",
2312
- "pressure_score": -1.0,
2313
- "trend_label": "worsening"
2314
- },
2315
- "structure_bce_loss": {
2316
- "desired_direction": "lower",
2317
- "early_mean": 0.12293951650489272,
2318
- "goal_display": "goal \u2193",
2319
- "improvement_pct": 39.749156913940595,
2320
- "improvement_pct_display": "+39.75%",
2321
- "last": 0.08383000642061234,
2322
- "late_mean": 0.07407209518012302,
2323
- "mid_mean": 0.07652380578004556,
2324
- "pressure": "pressure_up",
2325
- "pressure_arrow": "\u2197",
2326
- "pressure_display": "goal \u2193 | \u2197 +39.75% improving",
2327
- "pressure_score": 1.0,
2328
- "trend_label": "improving"
2329
- },
2330
- "train_loss": {
2331
- "desired_direction": "lower",
2332
- "early_mean": 6.340343519442343,
2333
- "goal_display": "goal \u2193",
2334
- "improvement_pct": 10.566866163080938,
2335
- "improvement_pct_display": "+10.57%",
2336
- "last": 6.491608619689941,
2337
- "late_mean": 5.670367905463295,
2338
- "mid_mean": 5.795929590401622,
2339
- "pressure": "pressure_up",
2340
- "pressure_arrow": "\u2197",
2341
- "pressure_display": "goal \u2193 | \u2197 +10.57% improving",
2342
- "pressure_score": 1.0,
2343
- "trend_label": "improving"
2344
- },
2345
- "val_hit_at_20": {
2346
- "desired_direction": "higher",
2347
- "early_mean": 0.08158111572265625,
2348
- "goal_display": "goal \u2191",
2349
- "improvement_pct": 76.67165435331526,
2350
- "improvement_pct_display": "+76.67%",
2351
- "last": 0.15270233154296875,
2352
- "late_mean": 0.14413070678710938,
2353
- "mid_mean": 0.094146728515625,
2354
- "pressure": "pressure_up",
2355
- "pressure_arrow": "\u2197",
2356
- "pressure_display": "goal \u2191 | \u2197 +76.67% improving",
2357
- "pressure_score": 1.0,
2358
- "trend_label": "improving"
2359
- },
2360
- "val_loss": {
2361
- "desired_direction": "lower",
2362
- "early_mean": 1.2876316868363775,
2363
- "goal_display": "goal \u2193",
2364
- "improvement_pct": -55.82459156154955,
2365
- "improvement_pct_display": "-55.82%",
2366
- "last": 6.646750174145564,
2367
- "late_mean": 2.006446816829876,
2368
- "mid_mean": 2.20697861268016,
2369
- "pressure": "pressure_down",
2370
- "pressure_arrow": "\u2198",
2371
- "pressure_display": "goal \u2193 | \u2198 -55.82% worsening",
2372
- "pressure_score": -1.0,
2373
- "trend_label": "worsening"
2374
- },
2375
- "val_structure_bce_loss": {
2376
- "desired_direction": "lower",
2377
- "early_mean": 0.0771060927848642,
2378
- "goal_display": "goal \u2193",
2379
- "improvement_pct": 12.199713989530546,
2380
- "improvement_pct_display": "+12.20%",
2381
- "last": 0.06532714269997086,
2382
- "late_mean": 0.06769936999660872,
2383
- "mid_mean": 0.07029345531468391,
2384
- "pressure": "pressure_up",
2385
- "pressure_arrow": "\u2197",
2386
- "pressure_display": "goal \u2193 | \u2197 +12.20% improving",
2387
- "pressure_score": 1.0,
2388
- "trend_label": "improving"
2389
- },
2390
- "val_structure_confidence_separation": {
2391
- "desired_direction": "higher",
2392
- "early_mean": -0.00795668972114072,
2393
- "goal_display": "goal \u2191",
2394
- "improvement_pct": -204.85499246505236,
2395
- "improvement_pct_clipped": -100.0,
2396
- "improvement_pct_clipped_display": "-100.00%",
2397
- "improvement_pct_display": "-204.85%",
2398
- "last": -0.027957430157584895,
2399
- "late_mean": -0.024256365849851136,
2400
- "mid_mean": -0.01309866098972634,
2401
- "pressure": "pressure_down",
2402
- "pressure_arrow": "\u2198",
2403
- "pressure_display": "goal \u2191 | \u2198 -204.85% worsening",
2404
- "pressure_score": -1.0,
2405
- "trend_label": "worsening"
2406
- },
2407
- "val_structure_fingerprint_cosine": {
2408
- "desired_direction": "higher",
2409
- "early_mean": 0.4147872725734487,
2410
- "goal_display": "goal \u2191",
2411
- "improvement_pct": 0.17175282510408285,
2412
- "improvement_pct_display": "+0.17%",
2413
- "last": 0.4255251376889646,
2414
- "late_mean": 0.4154996814322658,
2415
- "mid_mean": 0.4204998221830465,
2416
- "pressure": "pressure_none",
2417
- "pressure_arrow": "\u2192",
2418
- "pressure_display": "goal \u2191 | \u2192 +0.17% flat",
2419
- "trend_label": "flat"
2420
- },
2421
- "val_structure_top1_top2_gap_mean": {
2422
- "desired_direction": "higher",
2423
- "early_mean": 0.07839679718017578,
2424
- "goal_display": "goal \u2191",
2425
- "improvement_pct": 54.90785232041847,
2426
- "improvement_pct_display": "+54.91%",
2427
- "last": 0.11855697631835938,
2428
- "late_mean": 0.12144279479980469,
2429
- "mid_mean": 0.1310901641845703,
2430
- "pressure": "pressure_up",
2431
- "pressure_arrow": "\u2197",
2432
- "pressure_display": "goal \u2191 | \u2197 +54.91% improving",
2433
- "pressure_score": 1.0,
2434
- "trend_label": "improving"
2435
- },
2436
- "val_structure_uncertain_fraction": {
2437
- "desired_direction": "lower",
2438
- "early_mean": 0.9941177368164062,
2439
- "goal_display": "goal \u2193",
2440
- "improvement_pct": -0.03261678728482514,
2441
- "improvement_pct_display": "-0.03%",
2442
- "last": 0.9922027587890625,
2443
- "late_mean": 0.9944419860839844,
2444
- "mid_mean": 0.9762382507324219,
2445
- "pressure": "pressure_none",
2446
- "pressure_arrow": "\u2192",
2447
- "pressure_display": "goal \u2193 | \u2192 -0.03% flat",
2448
- "trend_label": "flat"
2449
- }
2450
- },
2451
- "primary_metrics": {
2452
- "contrastive_loss": 0.5768923759460449,
2453
- "different_inchikey_mean_cosine": 0.004679911238535274,
2454
- "embedding_std": 0.07216806709766388,
2455
- "grad_norm": 1.7659728527069092,
2456
- "samples_per_sec": 1399.0203442084614,
2457
- "structure_bce_loss": 0.08383000642061234,
2458
- "train_loss": 6.491608619689941,
2459
- "val_hit_at_20": 0.15270233154296875,
2460
- "val_loss": 6.646750174145564,
2461
- "val_structure_bce_loss": 0.06532714269997086,
2462
- "val_structure_candidate_count": 4119.69140625,
2463
- "val_structure_clear_hit_at_1": 0.0,
2464
- "val_structure_confidence_separation": -0.027957430157584895,
2465
- "val_structure_fingerprint_cosine": 0.4255251376889646,
2466
- "val_structure_top1_top2_gap_mean": 0.11855697631835938,
2467
- "val_structure_uncertain_fraction": 0.9922027587890625
2468
- },
2469
- "run_name": "final_v3_structure_alignment_v26_r1",
2470
- "shard_counts": {
2471
- "test": 2,
2472
- "train": 4,
2473
- "val": 2
2474
- }
2475
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
metadata/archive/20260413T213902Z/latest_checkpoint.txt DELETED
@@ -1 +0,0 @@
1
- /home/ubuntu/artifacts/nexa_mol/final_v3_structure_alignment/v26_r1/current_checkpoint.pt
 
 
metadata/archive/20260413T213902Z/latest_metrics.json DELETED
@@ -1,169 +0,0 @@
1
- {
2
- "backbone_lr": 3.886130904636371e-06,
3
- "checkpoint_path": "/home/ubuntu/artifacts/nexa_mol/final_v3_structure_alignment/v26_r1/current_checkpoint.pt",
4
- "checkpoint_reloaded": 1.0,
5
- "contrastive_loss": 0.5768923759460449,
6
- "covariance_loss": 10.012618064880371,
7
- "covariance_to_contrastive_ratio": 17.356128252623712,
8
- "covariance_weight": 0.0015,
9
- "dataloader_time_sec": 0.00035174899676349014,
10
- "dataloader_wait_pct_300s": 0.0382592069912683,
11
- "dataloader_wait_pct_60s": 0.0961140629935623,
12
- "dataloader_wait_pct_900s": 0.066640439237091,
13
- "dataloader_wait_pct_run": 0.06717802801040498,
14
- "different_inchikey_mean_cosine": 0.004679911238535274,
15
- "distributed_rank": 0.0,
16
- "distributed_world_size": 1.0,
17
- "effective_batch_size": 512.0,
18
- "effective_hard_negative_scale": 1.0,
19
- "effective_retrieval_weight": 0.6,
20
- "effective_structure_bce_weight": 1.0,
21
- "embedding_mean_norm": 1.0,
22
- "embedding_offdiag_mean_cosine": 0.009513536468148232,
23
- "embedding_std": 0.07216806709766388,
24
- "final_report": 1.0,
25
- "global_batch_size": 512.0,
26
- "gpu_active_fraction": 1.0,
27
- "gpu_count_observed": 2.0,
28
- "gpu_max_memory_gb": 13.279157161712646,
29
- "gpu_mem_used_mean_gb": 14.1943359375,
30
- "gpu_mem_util_mean_pct": 14.848754175733243,
31
- "gpu_memory_stable": true,
32
- "gpu_memory_utilization": 0.13982381154325935,
33
- "gpu_snapshot_available": 1.0,
34
- "gpu_util_max_pct": 54.0,
35
- "gpu_util_mean_pct": 36.0,
36
- "gpu_util_min_pct": 18.0,
37
- "grad_norm": 1.7659728527069092,
38
- "holdout_full_coverage": 0.0,
39
- "local_batch_size": 512.0,
40
- "lr": 3.886130904636371e-06,
41
- "mfu_estimate": 0.06267708747552383,
42
- "msms_objective": "hybrid",
43
- "optimizer_step": 1.0,
44
- "regularizer_ramp": 1.0,
45
- "resume_checkpoint_path": "/home/ubuntu/artifacts/nexa_mol/final_v3_structure_alignment/v26_r1/current_checkpoint.pt",
46
- "resume_start_step": 81002.0,
47
- "resumed_from_checkpoint": 1.0,
48
- "retrieval_head_lr": 1.9430654523181854e-05,
49
- "same_inchikey_mean_cosine": 0.16267980930137343,
50
- "samples_per_sec": 1399.0203442084614,
51
- "samples_per_sec_300s": 1547.033197547462,
52
- "samples_per_sec_60s": 1399.0203442084614,
53
- "samples_per_sec_900s": 1512.7885250414204,
54
- "samples_per_sec_run_mean": 1533.0231795943853,
55
- "step": 91001,
56
- "step_time_cv_300s": 0.06743440395418321,
57
- "step_time_cv_60s": 0.0,
58
- "step_time_cv_900s": 0.09218780075615579,
59
- "step_time_sec": 0.3659703749981418,
60
- "structure_bce_locked": 0.0,
61
- "structure_bce_loss": 0.08383000642061234,
62
- "structure_candidate_count": 2126.0,
63
- "structure_clear_fraction": 0.0,
64
- "structure_clear_hit_at_1": 0.0,
65
- "structure_close_fraction": 0.029296875,
66
- "structure_close_hit_at_1": 0.0,
67
- "structure_confidence_bucket_score_mean": 0.10155132412910461,
68
- "structure_confidence_bucket_score_mode": "normalized_gap",
69
- "structure_confidence_candidate_count": 2126.0,
70
- "structure_confidence_clear_threshold": 1.0,
71
- "structure_confidence_close_threshold": 0.35,
72
- "structure_confidence_eval_key_mode": "target_identity",
73
- "structure_confidence_separation": -0.0040241447277367115,
74
- "structure_correct_logit_mean": 9.1875,
75
- "structure_fingerprint_cosine": 0.46021854877471924,
76
- "structure_hard_negative_bonus_applied": 1.0,
77
- "structure_hard_negative_bonus_mean": 0.060302734375,
78
- "structure_hard_negative_scale": 1.0,
79
- "structure_head_lr": 1.9430654523181854e-05,
80
- "structure_hit_at_1": 0.00390625,
81
- "structure_hit_at_20": 0.1171875,
82
- "structure_hit_at_5": 0.029296875,
83
- "structure_local_ce_loss": 3.545562744140625,
84
- "structure_local_ce_loss_weight": 0.4,
85
- "structure_local_rerank_loss": 0.0,
86
- "structure_local_rerank_loss_weight": 0.0,
87
- "structure_local_rerank_score_scale": 1.0,
88
- "structure_logit_margin_mean": -1.0078125,
89
- "structure_margin_loss": 0.0,
90
- "structure_margin_loss_weight": 0.0,
91
- "structure_missing_formula_fraction": 0.0,
92
- "structure_missing_inchikey_fraction": 0.0,
93
- "structure_pairwise_logistic_loss": 0.0,
94
- "structure_pairwise_logistic_loss_weight": 0.0,
95
- "structure_positive_count_mean": 1.0,
96
- "structure_post_label_candidate_count": 2126.0,
97
- "structure_post_precursor_candidate_count": 2128.0,
98
- "structure_prefilter_candidate_count": 2128.0,
99
- "structure_retrieval_logit_std": 0.9839304089546204,
100
- "structure_retrieval_loss": 10.630162239074707,
101
- "structure_retrieval_scorer": "projected_dot",
102
- "structure_retrieval_target_mode": "sample",
103
- "structure_skipped_query_fraction": 0.0,
104
- "structure_soft_target_exact_mix": 0.4,
105
- "structure_soft_target_loss": 7.523618221282959,
106
- "structure_soft_target_loss_weight": 0.3,
107
- "structure_target_backend": "rdkit_morgan",
108
- "structure_target_equivalent_count_mean": 1.0,
109
- "structure_target_identity_collision_count": 0.0,
110
- "structure_target_rank_mean": 314.703125,
111
- "structure_to_ssl_ratio": 217.7124787233957,
112
- "structure_top1_top2_gap_mean": 0.0986328125,
113
- "structure_top1_top2_gap_norm_mean": 0.10155132412910461,
114
- "structure_top_negative_logit_mean": 10.1875,
115
- "structure_uncertain_fraction": 0.970703125,
116
- "structure_uncertain_hit_at_1": 0.0040241447277367115,
117
- "structure_valid_query_fraction": 1.0,
118
- "test_expected_shard_count": 2.0,
119
- "test_full_coverage": 0.0,
120
- "test_observed_shard_count": 0.0,
121
- "train_loss": 6.491608619689941,
122
- "train_loss_ema": 6.519052214060582,
123
- "train_retrieval_bank_size": 4096.0,
124
- "val_deep_eval_single_view": 0.0,
125
- "val_deep_eval_structure_only": 0.0,
126
- "val_effective_structure_bce_weight": 1.0,
127
- "val_eval_loader_mode": "stream",
128
- "val_eval_mode": "deep",
129
- "val_expected_shard_count": 2.0,
130
- "val_full_coverage": 1.0,
131
- "val_hit_at_1": 0.0282135009765625,
132
- "val_hit_at_20": 0.15270233154296875,
133
- "val_hit_at_5": 0.0726776123046875,
134
- "val_loss": 6.646750174145564,
135
- "val_observed_eval_batches": 256.0,
136
- "val_observed_shard_count": 2.0,
137
- "val_ssl_loss": 1.0397093277424574,
138
- "val_structure_bce_loss": 0.06532714269997086,
139
- "val_structure_candidate_count": 4119.69140625,
140
- "val_structure_clear_fraction": 0.0,
141
- "val_structure_clear_hit_at_1": 0.0,
142
- "val_structure_close_fraction": 0.0077972412109375,
143
- "val_structure_close_hit_at_1": 0.014835291571216658,
144
- "val_structure_confidence_candidate_count": 4096.0,
145
- "val_structure_confidence_separation": -0.027957430157584895,
146
- "val_structure_correct_logit_mean": 9.49462890625,
147
- "val_structure_fingerprint_cosine": 0.4255251376889646,
148
- "val_structure_logit_margin_mean": -1.221923828125,
149
- "val_structure_missing_formula_fraction": 0.0,
150
- "val_structure_missing_inchikey_fraction": 0.0,
151
- "val_structure_retrieval_logit_std": 2.6622845763340592,
152
- "val_structure_retrieval_loss": 10.882395941764116,
153
- "val_structure_target_equivalent_count_mean": 1.0,
154
- "val_structure_target_identity_collision_count": 23.69140625,
155
- "val_structure_target_rank_mean": 379.8781280517578,
156
- "val_structure_top1_top2_gap_mean": 0.11855697631835938,
157
- "val_structure_top1_top2_gap_norm_mean": 0.05411380449368153,
158
- "val_structure_top_negative_logit_mean": 10.714599609375,
159
- "val_structure_uncertain_fraction": 0.9922027587890625,
160
- "val_structure_uncertain_hit_at_1": 0.027957430157584895,
161
- "variance_loss": 0.00213623046875,
162
- "variance_weight": 0.8,
163
- "weighted_covariance_loss": 0.015018927097320557,
164
- "weighted_regularizer_to_contrastive_ratio": 0.028996589606316913,
165
- "weighted_ssl_loss": 0.02968101501464844,
166
- "weighted_structure_bce_loss": 0.08383000642061234,
167
- "weighted_structure_retrieval_loss": 6.378097343444824,
168
- "weighted_variance_loss": 0.001708984375
169
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
metadata/archive/20260413T213902Z/perf_summary.json DELETED
@@ -1,16 +0,0 @@
1
- {
2
- "logged_points": 521,
3
- "train_loss_min": 3.2278988361358643,
4
- "train_loss_max": 7.677141189575195,
5
- "train_loss_last": 6.491608619689941,
6
- "train_loss_ema_last": 6.519052214060582,
7
- "weighted_regularizer_ratio_median": 0.02686493425176378,
8
- "weighted_regularizer_ratio_p90": 0.09558363904110317,
9
- "samples_per_sec_mean": 1545.3851888056406,
10
- "samples_per_sec_min": 930.5498563655322,
11
- "samples_per_sec_max": 2247.460787425693,
12
- "step_time_mean": 0.33468720350667036,
13
- "mfu_mean": 0.06923433462788683,
14
- "mfu_max": 0.10068781126337953,
15
- "gpu_mem_max_gb": 13.279157161712646
16
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
metadata/archive/20260413T213902Z/results.md DELETED
@@ -1,171 +0,0 @@
1
- # MS/MS Training Run Result
2
-
3
- - Run name: `final_v3_structure_alignment_v26_r1`
4
- - Created at: `2026-04-13T21:36:19Z`
5
- - Dataset root: `/home/ubuntu/data/gems_v1_handoff_labeled_v26`
6
- - Shard counts: `{'train': 4, 'val': 2, 'test': 2}`
7
-
8
- ## Primary Metrics
9
-
10
- - `train_loss`: `6.491608619689941`
11
- - `val_loss`: `6.646750174145564`
12
- - `grad_norm`: `1.7659728527069092`
13
- - `contrastive_loss`: `0.5768923759460449`
14
- - `structure_bce_loss`: `0.08383000642061234`
15
- - `val_structure_bce_loss`: `0.06532714269997086`
16
- - `val_structure_fingerprint_cosine`: `0.4255251376889646`
17
- - `different_inchikey_mean_cosine`: `0.004679911238535274`
18
- - `embedding_std`: `0.07216806709766388`
19
- - `val_hit_at_20`: `0.15270233154296875`
20
- - `val_structure_candidate_count`: `4119.69140625`
21
- - `val_structure_top1_top2_gap_mean`: `0.11855697631835938`
22
- - `val_structure_uncertain_fraction`: `0.9922027587890625`
23
- - `val_structure_clear_hit_at_1`: `0.0`
24
- - `val_structure_confidence_separation`: `-0.027957430157584895`
25
- - `samples_per_sec`: `1399.0203442084614`
26
-
27
- ## Failure Mode Assessment
28
-
29
- - `dataset_shards_accessible`: pass. Observed shard counts {'train': 4, 'val': 2, 'test': 2}; the canonical Day 1 loader contract requires all splits to be readable.
30
- - `dataloader_streaming_stable`: pass. Training batches continued to arrive with positive throughput and no iterator stall.
31
- - `non_finite_loss_or_tensor_failure`: pass. Technical_Plan requires zero NaN or Inf tensors and finite train/val loss.
32
- - `validation_observability_gap`: pass. Engineering.md expects slope-aware monitoring; missing validation or retrieval metrics make trend judgment weaker.
33
- - `gpu_memory_instability`: pass. Technical_Plan Day 1 success requires stable GPU memory through the bounded run.
34
- - `checkpoint_save_reload_failure`: pass. Checkpoint save and reload is an explicit Day 1 success criterion.
35
- - `embedding_collapse`: pass. Engineering.md expects embedding variance monitoring and non-collapsed representations.
36
- - `regularizer_dominance`: pass. The current instability mode is regularization overpowering the SSL objective and producing jagged total loss.
37
- - `structure_supervision_gap`: pass. Once the bridge phase begins, Technical_Plan requires retrieval-oriented validation rather than only augmented contrastive loss.
38
- - `confidence_surface_gap`: pass. Structure-first qualification now requires explicit confidence diagnostics such as top-1/top-2 separation and uncertainty buckets, not just broader retrieval metrics.
39
- - `chemistry_target_backend_gap`: pass. The bridge phase should prefer chemistry-grounded fingerprint targets; hashed fallback targets weaken the retrieval signal.
40
- - `bridge_fit_without_ranking`: pass. Bridge runs must improve retrieval after fingerprint fit saturates; fitting BCE while val Hit@20 stays at candidate-bank baseline means ranking is not generalizing.
41
- - `metadata_shortcutting`: watch. Engineering.md flags acquisition-artefact shortcut risk; adduct and instrument embeddings remain deliberately down-scaled.
42
-
43
- ## Pressure Summary
44
-
45
- - all metrics overall: `↗ improving (+21.89% weighted)`
46
- - all metrics weighted improvement: `+21.89%`
47
- - all metrics average improvement: `+34.52%`
48
- - all metrics weighted pressure score: `0.284`
49
- - all metrics counts: `up=21` `none=7` `down=11` `up_fraction=+53.85%`
50
- - primary metrics overall: `↗ improving (-4.45% weighted)`
51
- - primary metrics weighted improvement: `-4.45%`
52
-
53
- ## Metric Pressure
54
-
55
- - `train_loss`: `goal ↓ | ↗ +10.57% improving` (early `6.340343519442343`, mid `5.795929590401622`, late `5.670367905463295`, last `6.491608619689941`)
56
- - `train_loss_ema`: `goal ↓ | ↗ +10.46% improving` (early `6.265581717362126`, mid `5.8371378655061745`, late `5.610470838300897`, last `6.519052214060582`)
57
- - `contrastive_loss`: `goal ↓ | → -1.64% flat` (early `1.409792113166324`, mid `1.3598130204084982`, late `1.43291388983014`, last `0.5768923759460449`)
58
- - `val_loss`: `goal ↓ | ↘ -55.82% worsening` (early `1.2876316868363775`, mid `2.20697861268016`, late `2.006446816829876`, last `6.646750174145564`)
59
- - `val_ssl_loss`: `goal ↓ | → +2.32% flat` (early `1.0849772497183745`, mid `1.0747967428483425`, late `1.0598136518327963`, last `1.0397093277424574`)
60
- - `structure_bce_loss`: `goal ↓ | ↗ +39.75% improving` (early `0.12293951650489272`, mid `0.07652380578004556`, late `0.07407209518012302`, last `0.08383000642061234`)
61
- - `val_structure_bce_loss`: `goal ↓ | ↗ +12.20% improving` (early `0.0771060927848642`, mid `0.07029345531468391`, late `0.06769936999660872`, last `0.06532714269997086`)
62
- - `structure_retrieval_loss`: `goal ↓ | ↗ +10.09% improving` (early `10.237479978903181`, mid `9.41523380775672`, late `9.204101929719421`, last `10.630162239074707`)
63
- - `val_structure_retrieval_loss`: `goal ↓ | → +4.86% flat` (early `11.562767315655947`, mid `12.150514367967844`, late `11.000247791409492`, last `10.882395941764116`)
64
- - `structure_fingerprint_cosine`: `goal ↑ | ↗ +17.59% improving` (early `0.3965519580968543`, mid `0.4464927057310336`, late `0.46629545006943846`, last `0.46021854877471924`)
65
- - `val_structure_fingerprint_cosine`: `goal ↑ | → +0.17% flat` (early `0.4147872725734487`, mid `0.4204998221830465`, late `0.4154996814322658`, last `0.4255251376889646`)
66
- - `structure_target_rank_mean`: `goal ↓ | ↗ +58.80% improving` (early `351.84337743858384`, mid `176.16389315390174`, late `144.9534280711207`, last `314.703125`)
67
- - `val_structure_target_rank_mean`: `goal ↓ | ↗ +45.45% improving` (early `760.7540435791016`, mid `683.3385162353516`, late `415.0084457397461`, last `379.8781280517578`)
68
- - `structure_correct_logit_mean`: `goal ↑ | ↗ +47.31% improving` (early `6.134031791907514`, mid `9.474891618497109`, late `9.035739942528735`, last `9.1875`)
69
- - `val_structure_correct_logit_mean`: `goal ↑ | ↗ +16.44% improving` (early `8.0311279296875`, mid `8.441162109375`, late `9.3515625`, last `9.49462890625`)
70
- - `structure_top_negative_logit_mean`: `goal ↓ | ↘ -39.72% worsening` (early `7.262102601156069`, mid `10.490606936416185`, late `10.14691091954023`, last `10.1875`)
71
- - `val_structure_top_negative_logit_mean`: `goal ↓ | ↘ -16.08% worsening` (early `9.2255859375`, mid `10.51171875`, late `10.708740234375`, last `10.714599609375`)
72
- - `structure_logit_margin_mean`: `goal ↑ | → +1.23% flat` (early `-1.1263999277456647`, mid `-1.0154725885115607`, late `-1.1125740840517242`, last `-1.0078125`)
73
- - `val_structure_logit_margin_mean`: `goal ↑ | ↘ -13.67% worsening` (early `-1.194091796875`, mid `-2.0707931518554688`, late `-1.3573150634765625`, last `-1.221923828125`)
74
- - `structure_retrieval_logit_std`: `goal ↑ | ↗ +112.06% improving` (early `1.0455416592559375`, mid `2.0036371215919537`, late `2.2171744848119803`, last `0.9839304089546204`)
75
- - `val_structure_retrieval_logit_std`: `goal ↑ | ↗ +102.33% improving` (early `1.2326001720502973`, mid `2.022283688886091`, late `2.49387572822161`, last `2.6622845763340592`)
76
- - `structure_top1_top2_gap_mean`: `goal ↑ | ↗ +59.22% improving` (early `0.09793567106213873`, mid `0.12284365968208093`, late `0.1559343009159483`, last `0.0986328125`)
77
- - `val_structure_top1_top2_gap_mean`: `goal ↑ | ↗ +54.91% improving` (early `0.07839679718017578`, mid `0.1310901641845703`, late `0.12144279479980469`, last `0.11855697631835938`)
78
- - `structure_top1_top2_gap_norm_mean`: `goal ↑ | ↘ -35.65% worsening` (early `0.12215662799301864`, mid `0.07032911504236604`, late `0.07860379065547524`, last `0.10155132412910461`)
79
- - `val_structure_top1_top2_gap_norm_mean`: `goal ↑ | ↘ -16.83% worsening` (early `0.06950851557485294`, mid `0.07577372609375743`, late `0.0578127475164365`, last `0.05411380449368153`)
80
- - `structure_uncertain_fraction`: `goal ↓ | ↘ -6.11% worsening` (early `0.924663565751445`, mid `0.984747561416185`, late `0.9811422413793104`, last `0.970703125`)
81
- - `val_structure_uncertain_fraction`: `goal ↓ | → -0.03% flat` (early `0.9941177368164062`, mid `0.9762382507324219`, late `0.9944419860839844`, last `0.9922027587890625`)
82
- - `structure_confidence_separation`: `goal ↑ | ↘ -531.56% worsening` (early `-0.007918493679557749`, mid `-0.032136323077151974`, late `-0.05001017991881603`, last `-0.0040241447277367115`)
83
- - `val_structure_confidence_separation`: `goal ↑ | ↘ -204.85% worsening` (early `-0.00795668972114072`, mid `-0.01309866098972634`, late `-0.024256365849851136`, last `-0.027957430157584895`)
84
- - `structure_hit_at_1`: `goal ↑ | ↗ +549.68% improving` (early `0.007880238439306358`, mid `0.032706376445086706`, late `0.051196569683908046`, last `0.00390625`)
85
- - `structure_hit_at_5`: `goal ↑ | ↗ +402.47% improving` (early `0.03360955563583815`, mid `0.11673591040462428`, late `0.16887796336206898`, last `0.029296875`)
86
- - `structure_hit_at_20`: `goal ↑ | ↗ +239.46% improving` (early `0.10721865968208093`, mid `0.28105807442196534`, late `0.3639659662356322`, last `0.1171875`)
87
- - `val_hit_at_1`: `goal ↑ | → +207.79% flat` (early `0.0079345703125`, mid `0.01372528076171875`, late `0.02442169189453125`, last `0.0282135009765625`)
88
- - `val_hit_at_5`: `goal ↑ | ↗ +134.85% improving` (early `0.0288543701171875`, mid `0.0425567626953125`, late `0.0677642822265625`, last `0.0726776123046875`)
89
- - `val_hit_at_20`: `goal ↑ | ↗ +76.67% improving` (early `0.08158111572265625`, mid `0.094146728515625`, late `0.14413070678710938`, last `0.15270233154296875`)
90
- - `weighted_regularizer_to_contrastive_ratio`: `goal ↓ | ↗ +54.61% improving` (early `0.0667222202939108`, mid `0.0329437448262181`, late `0.03028750823471251`, last `0.028996589606316913`)
91
- - `samples_per_sec`: `goal ↑ | ↘ -2.88% worsening` (early `1575.5664566260843`, mid `1531.3735887168505`, late `1530.1496274666802`, last `1399.0203442084614`)
92
- - `gpu_max_memory_gb`: `goal ≈ | ↗ +100.00% improving` (early `13.252925169950275`, mid `13.279059082097401`, late `13.279157161712646`, last `13.279157161712646`)
93
- - `grad_norm`: `goal ≈ | ↘ -100.00% worsening` (early `4.638080189338309`, mid `4.979553528603791`, late `6.072961742165445`, last `1.7659728527069092`)
94
-
95
- ## Primary Metric Pressure
96
-
97
- - `train_loss`: `goal ↓ | ↗ +10.57% improving` (early `6.340343519442343`, mid `5.795929590401622`, late `5.670367905463295`, last `6.491608619689941`)
98
- - `val_loss`: `goal ↓ | ↘ -55.82% worsening` (early `1.2876316868363775`, mid `2.20697861268016`, late `2.006446816829876`, last `6.646750174145564`)
99
- - `grad_norm`: `goal ≈ | ↘ -100.00% worsening` (early `4.638080189338309`, mid `4.979553528603791`, late `6.072961742165445`, last `1.7659728527069092`)
100
- - `contrastive_loss`: `goal ↓ | → -1.64% flat` (early `1.409792113166324`, mid `1.3598130204084982`, late `1.43291388983014`, last `0.5768923759460449`)
101
- - `structure_bce_loss`: `goal ↓ | ↗ +39.75% improving` (early `0.12293951650489272`, mid `0.07652380578004556`, late `0.07407209518012302`, last `0.08383000642061234`)
102
- - `val_structure_bce_loss`: `goal ↓ | ↗ +12.20% improving` (early `0.0771060927848642`, mid `0.07029345531468391`, late `0.06769936999660872`, last `0.06532714269997086`)
103
- - `val_structure_fingerprint_cosine`: `goal ↑ | → +0.17% flat` (early `0.4147872725734487`, mid `0.4204998221830465`, late `0.4154996814322658`, last `0.4255251376889646`)
104
- - `val_hit_at_20`: `goal ↑ | ↗ +76.67% improving` (early `0.08158111572265625`, mid `0.094146728515625`, late `0.14413070678710938`, last `0.15270233154296875`)
105
- - `val_structure_top1_top2_gap_mean`: `goal ↑ | ↗ +54.91% improving` (early `0.07839679718017578`, mid `0.1310901641845703`, late `0.12144279479980469`, last `0.11855697631835938`)
106
- - `val_structure_uncertain_fraction`: `goal ↓ | → -0.03% flat` (early `0.9941177368164062`, mid `0.9762382507324219`, late `0.9944419860839844`, last `0.9922027587890625`)
107
- - `val_structure_confidence_separation`: `goal ↑ | ↘ -204.85% worsening` (early `-0.00795668972114072`, mid `-0.01309866098972634`, late `-0.024256365849851136`, last `-0.027957430157584895`)
108
- - `samples_per_sec`: `goal ↑ | ↘ -2.88% worsening` (early `1575.5664566260843`, mid `1531.3735887168505`, late `1530.1496274666802`, last `1399.0203442084614`)
109
-
110
- ## Debug Metrics
111
-
112
- - `train_loss`: `6.491608619689941`
113
- - `train_loss_ema`: `6.519052214060582`
114
- - `val_loss`: `6.646750174145564`
115
- - `contrastive_loss`: `0.5768923759460449`
116
- - `val_ssl_loss`: `1.0397093277424574`
117
- - `variance_loss`: `0.00213623046875`
118
- - `covariance_loss`: `10.012618064880371`
119
- - `structure_bce_loss`: `0.08383000642061234`
120
- - `structure_retrieval_loss`: `10.630162239074707`
121
- - `val_structure_retrieval_loss`: `10.882395941764116`
122
- - `structure_fingerprint_cosine`: `0.46021854877471924`
123
- - `structure_hit_at_1`: `0.00390625`
124
- - `structure_hit_at_5`: `0.029296875`
125
- - `structure_hit_at_20`: `0.1171875`
126
- - `structure_target_rank_mean`: `314.703125`
127
- - `structure_logit_margin_mean`: `-1.0078125`
128
- - `structure_retrieval_logit_std`: `0.9839304089546204`
129
- - `val_structure_retrieval_logit_std`: `2.6622845763340592`
130
- - `structure_correct_logit_mean`: `9.1875`
131
- - `structure_top_negative_logit_mean`: `10.1875`
132
- - `val_structure_correct_logit_mean`: `9.49462890625`
133
- - `val_structure_top_negative_logit_mean`: `10.714599609375`
134
- - `structure_top1_top2_gap_mean`: `0.0986328125`
135
- - `structure_top1_top2_gap_norm_mean`: `0.10155132412910461`
136
- - `structure_confidence_candidate_count`: `2126.0`
137
- - `structure_close_fraction`: `0.029296875`
138
- - `structure_uncertain_fraction`: `0.970703125`
139
- - `structure_uncertain_hit_at_1`: `0.0040241447277367115`
140
- - `structure_confidence_separation`: `-0.0040241447277367115`
141
- - `val_structure_top1_top2_gap_mean`: `0.11855697631835938`
142
- - `val_structure_top1_top2_gap_norm_mean`: `0.05411380449368153`
143
- - `val_structure_confidence_candidate_count`: `4096.0`
144
- - `val_structure_close_fraction`: `0.0077972412109375`
145
- - `val_structure_uncertain_fraction`: `0.9922027587890625`
146
- - `val_structure_close_hit_at_1`: `0.014835291571216658`
147
- - `val_structure_uncertain_hit_at_1`: `0.027957430157584895`
148
- - `val_structure_confidence_separation`: `-0.027957430157584895`
149
- - `grad_norm`: `1.7659728527069092`
150
- - `weighted_regularizer_to_contrastive_ratio`: `0.028996589606316913`
151
- - `samples_per_sec`: `1399.0203442084614`
152
- - `samples_per_sec_60s`: `1399.0203442084614`
153
- - `samples_per_sec_300s`: `1547.033197547462`
154
- - `samples_per_sec_900s`: `1512.7885250414204`
155
- - `samples_per_sec_run_mean`: `1533.0231795943853`
156
- - `gpu_max_memory_gb`: `13.279157161712646`
157
- - `gpu_util_mean_pct`: `36.0`
158
- - `gpu_util_min_pct`: `18.0`
159
- - `gpu_util_max_pct`: `54.0`
160
- - `gpu_active_fraction`: `1.0`
161
- - `gpu_mem_used_mean_gb`: `14.1943359375`
162
- - `gpu_mem_util_mean_pct`: `14.848754175733243`
163
- - `gpu_snapshot_available`: `1.0`
164
- - `step_time_sec`: `0.3659703749981418`
165
- - `step_time_cv_300s`: `0.06743440395418321`
166
- - `step_time_cv_900s`: `0.09218780075615579`
167
- - `dataloader_wait_pct_60s`: `0.0961140629935623`
168
- - `dataloader_wait_pct_300s`: `0.0382592069912683`
169
- - `dataloader_wait_pct_900s`: `0.066640439237091`
170
- - `dataloader_wait_pct_run`: `0.06717802801040498`
171
- - `mfu_estimate`: `0.06267708747552383`
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
metadata/checksums.sha256 DELETED
@@ -1,27 +0,0 @@
1
- cef7a30afbc0f4c107dc791039b42edf61bff2337023f9d80b6ff5a2a94bbf29 README.md
2
- 3c5d7e36bbc4d76a4158562380e32c82248a7b9e4035117d0bbaf900e8184e0c config.json
3
- 4046e164198deb550b34a4fc54bed0d5b40ccc57a646db5f8c56e261519d8e57 configs/foundation_config.json
4
- 3b45ebb5770bed57ef75be985fba71513fffdb9ba075d21ab280208e3efa02a4 configs/runtime_requirements.json
5
- 1debd145d109a2c27d435f8250bcb577366fd143d3977ac48effeeb7674c200f configs/structure_alignment_config.json
6
- 6a792005b4d2a70b53215b461a36fd9608a39df5898bb1d0a8b35f5af824177c metadata/Final_V3_manifest.json
7
- e5fb430337eb1516bd168f019e1733b1baf37eb568776e009fb6f348c88e4537 metadata/archive/20260413T201817Z/latest_checkpoint.txt
8
- e5fb430337eb1516bd168f019e1733b1baf37eb568776e009fb6f348c88e4537 metadata/archive/20260413T202042Z/latest_checkpoint.txt
9
- a11f8a97e622078c7c0f2fa3f62525f13ed71ff0304deabe84656a7a576855c5 metadata/archive/20260413T213902Z/day1_validation_report.json
10
- e5fb430337eb1516bd168f019e1733b1baf37eb568776e009fb6f348c88e4537 metadata/archive/20260413T213902Z/latest_checkpoint.txt
11
- 3e77984c10d6e0f9e8205a142dce9a4c3d513a719b39afda4095b27b92e2cbf2 metadata/archive/20260413T213902Z/latest_metrics.json
12
- c983893fe5aaf41c63a5d16cf0fdf055196785f23b2cd2ca4cd0a8812fc1ada6 metadata/archive/20260413T213902Z/perf_summary.json
13
- 2135caf8c7d03112bd8b7fea56da9cf466b1d0f668809d984c33420b179111a8 metadata/archive/20260413T213902Z/results.md
14
- 631653ad2feae896c11e3ae34f29ec90c317070d5c729bc5178ac3e7d2f23f2d metadata/closeout_receipt.json
15
- a11f8a97e622078c7c0f2fa3f62525f13ed71ff0304deabe84656a7a576855c5 metadata/day1_validation_report.json
16
- 6ef7558b9352003473eae0d9b03d9af20b1bd428865378cc5608bfd33cb0d97a metadata/eval_coverage.json
17
- 0ae4aef28a9733a7bb7f4a2422c09d7dc4f8a8238807be0e5c8e58843c2f3e32 metadata/fast_eval_surface.json
18
- e5fb430337eb1516bd168f019e1733b1baf37eb568776e009fb6f348c88e4537 metadata/latest_checkpoint.txt
19
- 3e77984c10d6e0f9e8205a142dce9a4c3d513a719b39afda4095b27b92e2cbf2 metadata/latest_metrics.json
20
- c983893fe5aaf41c63a5d16cf0fdf055196785f23b2cd2ca4cd0a8812fc1ada6 metadata/perf_summary.json
21
- 2135caf8c7d03112bd8b7fea56da9cf466b1d0f668809d984c33420b179111a8 metadata/results.md
22
- d25e392e32ea4aa38534689591582c99ae5d75e007f74390d57d79983adc665a metadata/training_surface.json
23
- 3a5746d461f17c831bcd08c4180482f7a8424b06e248eaa595202e73929726f0 model_index.json
24
- d3f6e70ec0b19c0fd8569a4ebd328a117508fe9b333274971967d2da2f9954ff runtime/README.md
25
- 896284beda3cff6c54e6c3e291ed5c0b2ad8ae708df880831137dee5ed7380db runtime/nexamass_encoder.py
26
- 870b30c7bb6a340a460306882fe631d76282f233baf3920ca3a45c363eaf0ee6 weights/Final_V3-model_state.safetensors
27
- 6e006a6fa4ba6b8f127c7eabc9eaf6b7b64675e0136dee3ca1655bb3a4a3eadd weights/NexaMass-V3-Struct-model_state.safetensors
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
metadata/closeout_receipt.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "created_at": "2026-04-13T21:47:04Z",
3
- "dataset_receipt_path": "/home/ubuntu/artifacts/nexa_mol/final_v3_structure_alignment/v26_r1/dataset_receipt.json",
4
- "dataset_snapshot_uploaded": false,
5
- "remote_checkpoint_uri": "wasabi:nexa-ms/models/dreams_pretrain_v1/checkpoints",
6
- "remote_dataset_uri": "wasabi:nexa-ms/processed/gems_v1/receipts",
7
- "remote_log_uri": "wasabi:nexa-ms/models/dreams_pretrain_v1/logs",
8
- "run_name": "final_v3_structure_alignment_v26_r1"
9
- }
 
 
 
 
 
 
 
 
 
 
metadata/day1_validation_report.json DELETED
@@ -1,2475 +0,0 @@
1
- {
2
- "analysis_basis": [
3
- "docs/projects/msms_pipeline/Technical_Plan.md",
4
- "docs/projects/msms_pipeline/Engineering.md"
5
- ],
6
- "created_at": "2026-04-13T21:36:19Z",
7
- "dataset_root": "/home/ubuntu/data/gems_v1_handoff_labeled_v26",
8
- "debug_metric_pressures": {
9
- "gpu_max_memory_gb": {
10
- "desired_direction": "stable",
11
- "early_mean": 13.252925169950275,
12
- "improvement_pct": 100.0,
13
- "improvement_pct_clipped": 100.0,
14
- "last": 13.279157161712646,
15
- "late_mean": 13.279157161712646,
16
- "mid_mean": 13.279059082097401,
17
- "pressure": "pressure_up",
18
- "pressure_arrow": "\u2197",
19
- "pressure_score": 1.0
20
- },
21
- "structure_confidence_separation": {
22
- "desired_direction": "higher",
23
- "early_mean": -0.007918493679557749,
24
- "improvement_pct": -531.5617836245987,
25
- "improvement_pct_clipped": -100.0,
26
- "last": -0.0040241447277367115,
27
- "late_mean": -0.05001017991881603,
28
- "mid_mean": -0.032136323077151974,
29
- "pressure": "pressure_down",
30
- "pressure_arrow": "\u2198",
31
- "pressure_score": -1.0
32
- },
33
- "structure_correct_logit_mean": {
34
- "desired_direction": "higher",
35
- "early_mean": 6.134031791907514,
36
- "improvement_pct": 47.305071917778086,
37
- "improvement_pct_clipped": 47.305071917778086,
38
- "last": 9.1875,
39
- "late_mean": 9.035739942528735,
40
- "mid_mean": 9.474891618497109,
41
- "pressure": "pressure_up",
42
- "pressure_arrow": "\u2197",
43
- "pressure_score": 1.0
44
- },
45
- "structure_fingerprint_cosine": {
46
- "desired_direction": "higher",
47
- "early_mean": 0.3965519580968543,
48
- "improvement_pct": 17.58747890372286,
49
- "improvement_pct_clipped": 17.58747890372286,
50
- "last": 0.46021854877471924,
51
- "late_mean": 0.46629545006943846,
52
- "mid_mean": 0.4464927057310336,
53
- "pressure": "pressure_up",
54
- "pressure_arrow": "\u2197",
55
- "pressure_score": 1.0
56
- },
57
- "structure_hit_at_1": {
58
- "desired_direction": "higher",
59
- "early_mean": 0.007880238439306358,
60
- "improvement_pct": 549.6830023383724,
61
- "improvement_pct_clipped": 100.0,
62
- "last": 0.00390625,
63
- "late_mean": 0.051196569683908046,
64
- "mid_mean": 0.032706376445086706,
65
- "pressure": "pressure_up",
66
- "pressure_arrow": "\u2197",
67
- "pressure_score": 1.0
68
- },
69
- "structure_hit_at_20": {
70
- "desired_direction": "higher",
71
- "early_mean": 0.10721865968208093,
72
- "improvement_pct": 239.4614028144399,
73
- "improvement_pct_clipped": 100.0,
74
- "last": 0.1171875,
75
- "late_mean": 0.3639659662356322,
76
- "mid_mean": 0.28105807442196534,
77
- "pressure": "pressure_up",
78
- "pressure_arrow": "\u2197",
79
- "pressure_score": 1.0
80
- },
81
- "structure_hit_at_5": {
82
- "desired_direction": "higher",
83
- "early_mean": 0.03360955563583815,
84
- "improvement_pct": 402.47008675709174,
85
- "improvement_pct_clipped": 100.0,
86
- "last": 0.029296875,
87
- "late_mean": 0.16887796336206898,
88
- "mid_mean": 0.11673591040462428,
89
- "pressure": "pressure_up",
90
- "pressure_arrow": "\u2197",
91
- "pressure_score": 1.0
92
- },
93
- "structure_logit_margin_mean": {
94
- "desired_direction": "higher",
95
- "early_mean": -1.1263999277456647,
96
- "improvement_pct": 1.2274364862230593,
97
- "improvement_pct_clipped": 1.2274364862230593,
98
- "last": -1.0078125,
99
- "late_mean": -1.1125740840517242,
100
- "mid_mean": -1.0154725885115607,
101
- "pressure": "pressure_none",
102
- "pressure_arrow": "\u2192",
103
- "pressure_score": 0.0
104
- },
105
- "structure_retrieval_logit_std": {
106
- "desired_direction": "higher",
107
- "early_mean": 1.0455416592559375,
108
- "improvement_pct": 112.05988926255111,
109
- "improvement_pct_clipped": 100.0,
110
- "last": 0.9839304089546204,
111
- "late_mean": 2.2171744848119803,
112
- "mid_mean": 2.0036371215919537,
113
- "pressure": "pressure_up",
114
- "pressure_arrow": "\u2197",
115
- "pressure_score": 1.0
116
- },
117
- "structure_retrieval_loss": {
118
- "desired_direction": "lower",
119
- "early_mean": 10.237479978903181,
120
- "improvement_pct": 10.094066619063353,
121
- "improvement_pct_clipped": 10.094066619063353,
122
- "last": 10.630162239074707,
123
- "late_mean": 9.204101929719421,
124
- "mid_mean": 9.41523380775672,
125
- "pressure": "pressure_up",
126
- "pressure_arrow": "\u2197",
127
- "pressure_score": 1.0
128
- },
129
- "structure_target_rank_mean": {
130
- "desired_direction": "lower",
131
- "early_mean": 351.84337743858384,
132
- "improvement_pct": 58.80171764880722,
133
- "improvement_pct_clipped": 58.80171764880722,
134
- "last": 314.703125,
135
- "late_mean": 144.9534280711207,
136
- "mid_mean": 176.16389315390174,
137
- "pressure": "pressure_up",
138
- "pressure_arrow": "\u2197",
139
- "pressure_score": 1.0
140
- },
141
- "structure_top1_top2_gap_mean": {
142
- "desired_direction": "higher",
143
- "early_mean": 0.09793567106213873,
144
- "improvement_pct": 59.221149173532794,
145
- "improvement_pct_clipped": 59.221149173532794,
146
- "last": 0.0986328125,
147
- "late_mean": 0.1559343009159483,
148
- "mid_mean": 0.12284365968208093,
149
- "pressure": "pressure_up",
150
- "pressure_arrow": "\u2197",
151
- "pressure_score": 1.0
152
- },
153
- "structure_top1_top2_gap_norm_mean": {
154
- "desired_direction": "higher",
155
- "early_mean": 0.12215662799301864,
156
- "improvement_pct": -35.653274040957065,
157
- "improvement_pct_clipped": -35.653274040957065,
158
- "last": 0.10155132412910461,
159
- "late_mean": 0.07860379065547524,
160
- "mid_mean": 0.07032911504236604,
161
- "pressure": "pressure_down",
162
- "pressure_arrow": "\u2198",
163
- "pressure_score": -1.0
164
- },
165
- "structure_top_negative_logit_mean": {
166
- "desired_direction": "lower",
167
- "early_mean": 7.262102601156069,
168
- "improvement_pct": -39.724147080005764,
169
- "improvement_pct_clipped": -39.724147080005764,
170
- "last": 10.1875,
171
- "late_mean": 10.14691091954023,
172
- "mid_mean": 10.490606936416185,
173
- "pressure": "pressure_down",
174
- "pressure_arrow": "\u2198",
175
- "pressure_score": -1.0
176
- },
177
- "structure_uncertain_fraction": {
178
- "desired_direction": "lower",
179
- "early_mean": 0.924663565751445,
180
- "improvement_pct": -6.108024336610137,
181
- "improvement_pct_clipped": -6.108024336610137,
182
- "last": 0.970703125,
183
- "late_mean": 0.9811422413793104,
184
- "mid_mean": 0.984747561416185,
185
- "pressure": "pressure_down",
186
- "pressure_arrow": "\u2198",
187
- "pressure_score": -1.0
188
- },
189
- "train_loss_ema": {
190
- "desired_direction": "lower",
191
- "early_mean": 6.265581717362126,
192
- "improvement_pct": 10.455707205061195,
193
- "improvement_pct_clipped": 10.455707205061195,
194
- "last": 6.519052214060582,
195
- "late_mean": 5.610470838300897,
196
- "mid_mean": 5.8371378655061745,
197
- "pressure": "pressure_up",
198
- "pressure_arrow": "\u2197",
199
- "pressure_score": 1.0
200
- },
201
- "val_ssl_loss": {
202
- "desired_direction": "lower",
203
- "early_mean": 1.0849772497183745,
204
- "improvement_pct": 2.3192742421198114,
205
- "improvement_pct_clipped": 2.3192742421198114,
206
- "last": 1.0397093277424574,
207
- "late_mean": 1.0598136518327963,
208
- "mid_mean": 1.0747967428483425,
209
- "pressure": "pressure_none",
210
- "pressure_arrow": "\u2192",
211
- "pressure_score": 0.0
212
- },
213
- "val_structure_correct_logit_mean": {
214
- "desired_direction": "higher",
215
- "early_mean": 8.0311279296875,
216
- "improvement_pct": 16.44145855816145,
217
- "improvement_pct_clipped": 16.44145855816145,
218
- "last": 9.49462890625,
219
- "late_mean": 9.3515625,
220
- "mid_mean": 8.441162109375,
221
- "pressure": "pressure_up",
222
- "pressure_arrow": "\u2197",
223
- "pressure_score": 1.0
224
- },
225
- "val_structure_retrieval_logit_std": {
226
- "desired_direction": "higher",
227
- "early_mean": 1.2326001720502973,
228
- "improvement_pct": 102.32641409365677,
229
- "improvement_pct_clipped": 100.0,
230
- "last": 2.6622845763340592,
231
- "late_mean": 2.49387572822161,
232
- "mid_mean": 2.022283688886091,
233
- "pressure": "pressure_up",
234
- "pressure_arrow": "\u2197",
235
- "pressure_score": 1.0
236
- },
237
- "val_structure_retrieval_loss": {
238
- "desired_direction": "lower",
239
- "early_mean": 11.562767315655947,
240
- "improvement_pct": 4.864921250164783,
241
- "improvement_pct_clipped": 4.864921250164783,
242
- "last": 10.882395941764116,
243
- "late_mean": 11.000247791409492,
244
- "mid_mean": 12.150514367967844,
245
- "pressure": "pressure_none",
246
- "pressure_arrow": "\u2192",
247
- "pressure_score": 0.0
248
- },
249
- "val_structure_top1_top2_gap_norm_mean": {
250
- "desired_direction": "higher",
251
- "early_mean": 0.06950851557485294,
252
- "improvement_pct": -16.826381575968767,
253
- "improvement_pct_clipped": -16.826381575968767,
254
- "last": 0.05411380449368153,
255
- "late_mean": 0.0578127475164365,
256
- "mid_mean": 0.07577372609375743,
257
- "pressure": "pressure_down",
258
- "pressure_arrow": "\u2198",
259
- "pressure_score": -1.0
260
- },
261
- "val_structure_top_negative_logit_mean": {
262
- "desired_direction": "lower",
263
- "early_mean": 9.2255859375,
264
- "improvement_pct": -16.07653223245475,
265
- "improvement_pct_clipped": -16.07653223245475,
266
- "last": 10.714599609375,
267
- "late_mean": 10.708740234375,
268
- "mid_mean": 10.51171875,
269
- "pressure": "pressure_down",
270
- "pressure_arrow": "\u2198",
271
- "pressure_score": -1.0
272
- },
273
- "weighted_regularizer_to_contrastive_ratio": {
274
- "desired_direction": "lower",
275
- "early_mean": 0.0667222202939108,
276
- "improvement_pct": 54.60656419810926,
277
- "improvement_pct_clipped": 54.60656419810926,
278
- "last": 0.028996589606316913,
279
- "late_mean": 0.03028750823471251,
280
- "mid_mean": 0.0329437448262181,
281
- "pressure": "pressure_up",
282
- "pressure_arrow": "\u2197",
283
- "pressure_score": 1.0
284
- }
285
- },
286
- "debug_metric_pressures_display": {
287
- "gpu_max_memory_gb": {
288
- "desired_direction": "stable",
289
- "early_mean": 13.252925169950275,
290
- "goal_display": "goal \u2248",
291
- "improvement_pct": 100.0,
292
- "improvement_pct_display": "+100.00%",
293
- "last": 13.279157161712646,
294
- "late_mean": 13.279157161712646,
295
- "mid_mean": 13.279059082097401,
296
- "pressure": "pressure_up",
297
- "pressure_arrow": "\u2197",
298
- "pressure_display": "goal \u2248 | \u2197 +100.00% improving",
299
- "pressure_score": 1.0,
300
- "trend_label": "improving"
301
- },
302
- "structure_confidence_separation": {
303
- "desired_direction": "higher",
304
- "early_mean": -0.007918493679557749,
305
- "goal_display": "goal \u2191",
306
- "improvement_pct": -531.5617836245987,
307
- "improvement_pct_clipped": -100.0,
308
- "improvement_pct_clipped_display": "-100.00%",
309
- "improvement_pct_display": "-531.56%",
310
- "last": -0.0040241447277367115,
311
- "late_mean": -0.05001017991881603,
312
- "mid_mean": -0.032136323077151974,
313
- "pressure": "pressure_down",
314
- "pressure_arrow": "\u2198",
315
- "pressure_display": "goal \u2191 | \u2198 -531.56% worsening",
316
- "pressure_score": -1.0,
317
- "trend_label": "worsening"
318
- },
319
- "structure_correct_logit_mean": {
320
- "desired_direction": "higher",
321
- "early_mean": 6.134031791907514,
322
- "goal_display": "goal \u2191",
323
- "improvement_pct": 47.305071917778086,
324
- "improvement_pct_display": "+47.31%",
325
- "last": 9.1875,
326
- "late_mean": 9.035739942528735,
327
- "mid_mean": 9.474891618497109,
328
- "pressure": "pressure_up",
329
- "pressure_arrow": "\u2197",
330
- "pressure_display": "goal \u2191 | \u2197 +47.31% improving",
331
- "pressure_score": 1.0,
332
- "trend_label": "improving"
333
- },
334
- "structure_fingerprint_cosine": {
335
- "desired_direction": "higher",
336
- "early_mean": 0.3965519580968543,
337
- "goal_display": "goal \u2191",
338
- "improvement_pct": 17.58747890372286,
339
- "improvement_pct_display": "+17.59%",
340
- "last": 0.46021854877471924,
341
- "late_mean": 0.46629545006943846,
342
- "mid_mean": 0.4464927057310336,
343
- "pressure": "pressure_up",
344
- "pressure_arrow": "\u2197",
345
- "pressure_display": "goal \u2191 | \u2197 +17.59% improving",
346
- "pressure_score": 1.0,
347
- "trend_label": "improving"
348
- },
349
- "structure_hit_at_1": {
350
- "desired_direction": "higher",
351
- "early_mean": 0.007880238439306358,
352
- "goal_display": "goal \u2191",
353
- "improvement_pct": 549.6830023383724,
354
- "improvement_pct_clipped": 100.0,
355
- "improvement_pct_clipped_display": "+100.00%",
356
- "improvement_pct_display": "+549.68%",
357
- "last": 0.00390625,
358
- "late_mean": 0.051196569683908046,
359
- "mid_mean": 0.032706376445086706,
360
- "pressure": "pressure_up",
361
- "pressure_arrow": "\u2197",
362
- "pressure_display": "goal \u2191 | \u2197 +549.68% improving",
363
- "pressure_score": 1.0,
364
- "trend_label": "improving"
365
- },
366
- "structure_hit_at_20": {
367
- "desired_direction": "higher",
368
- "early_mean": 0.10721865968208093,
369
- "goal_display": "goal \u2191",
370
- "improvement_pct": 239.4614028144399,
371
- "improvement_pct_clipped": 100.0,
372
- "improvement_pct_clipped_display": "+100.00%",
373
- "improvement_pct_display": "+239.46%",
374
- "last": 0.1171875,
375
- "late_mean": 0.3639659662356322,
376
- "mid_mean": 0.28105807442196534,
377
- "pressure": "pressure_up",
378
- "pressure_arrow": "\u2197",
379
- "pressure_display": "goal \u2191 | \u2197 +239.46% improving",
380
- "pressure_score": 1.0,
381
- "trend_label": "improving"
382
- },
383
- "structure_hit_at_5": {
384
- "desired_direction": "higher",
385
- "early_mean": 0.03360955563583815,
386
- "goal_display": "goal \u2191",
387
- "improvement_pct": 402.47008675709174,
388
- "improvement_pct_clipped": 100.0,
389
- "improvement_pct_clipped_display": "+100.00%",
390
- "improvement_pct_display": "+402.47%",
391
- "last": 0.029296875,
392
- "late_mean": 0.16887796336206898,
393
- "mid_mean": 0.11673591040462428,
394
- "pressure": "pressure_up",
395
- "pressure_arrow": "\u2197",
396
- "pressure_display": "goal \u2191 | \u2197 +402.47% improving",
397
- "pressure_score": 1.0,
398
- "trend_label": "improving"
399
- },
400
- "structure_logit_margin_mean": {
401
- "desired_direction": "higher",
402
- "early_mean": -1.1263999277456647,
403
- "goal_display": "goal \u2191",
404
- "improvement_pct": 1.2274364862230593,
405
- "improvement_pct_display": "+1.23%",
406
- "last": -1.0078125,
407
- "late_mean": -1.1125740840517242,
408
- "mid_mean": -1.0154725885115607,
409
- "pressure": "pressure_none",
410
- "pressure_arrow": "\u2192",
411
- "pressure_display": "goal \u2191 | \u2192 +1.23% flat",
412
- "trend_label": "flat"
413
- },
414
- "structure_retrieval_logit_std": {
415
- "desired_direction": "higher",
416
- "early_mean": 1.0455416592559375,
417
- "goal_display": "goal \u2191",
418
- "improvement_pct": 112.05988926255111,
419
- "improvement_pct_clipped": 100.0,
420
- "improvement_pct_clipped_display": "+100.00%",
421
- "improvement_pct_display": "+112.06%",
422
- "last": 0.9839304089546204,
423
- "late_mean": 2.2171744848119803,
424
- "mid_mean": 2.0036371215919537,
425
- "pressure": "pressure_up",
426
- "pressure_arrow": "\u2197",
427
- "pressure_display": "goal \u2191 | \u2197 +112.06% improving",
428
- "pressure_score": 1.0,
429
- "trend_label": "improving"
430
- },
431
- "structure_retrieval_loss": {
432
- "desired_direction": "lower",
433
- "early_mean": 10.237479978903181,
434
- "goal_display": "goal \u2193",
435
- "improvement_pct": 10.094066619063353,
436
- "improvement_pct_display": "+10.09%",
437
- "last": 10.630162239074707,
438
- "late_mean": 9.204101929719421,
439
- "mid_mean": 9.41523380775672,
440
- "pressure": "pressure_up",
441
- "pressure_arrow": "\u2197",
442
- "pressure_display": "goal \u2193 | \u2197 +10.09% improving",
443
- "pressure_score": 1.0,
444
- "trend_label": "improving"
445
- },
446
- "structure_target_rank_mean": {
447
- "desired_direction": "lower",
448
- "early_mean": 351.84337743858384,
449
- "goal_display": "goal \u2193",
450
- "improvement_pct": 58.80171764880722,
451
- "improvement_pct_display": "+58.80%",
452
- "last": 314.703125,
453
- "late_mean": 144.9534280711207,
454
- "mid_mean": 176.16389315390174,
455
- "pressure": "pressure_up",
456
- "pressure_arrow": "\u2197",
457
- "pressure_display": "goal \u2193 | \u2197 +58.80% improving",
458
- "pressure_score": 1.0,
459
- "trend_label": "improving"
460
- },
461
- "structure_top1_top2_gap_mean": {
462
- "desired_direction": "higher",
463
- "early_mean": 0.09793567106213873,
464
- "goal_display": "goal \u2191",
465
- "improvement_pct": 59.221149173532794,
466
- "improvement_pct_display": "+59.22%",
467
- "last": 0.0986328125,
468
- "late_mean": 0.1559343009159483,
469
- "mid_mean": 0.12284365968208093,
470
- "pressure": "pressure_up",
471
- "pressure_arrow": "\u2197",
472
- "pressure_display": "goal \u2191 | \u2197 +59.22% improving",
473
- "pressure_score": 1.0,
474
- "trend_label": "improving"
475
- },
476
- "structure_top1_top2_gap_norm_mean": {
477
- "desired_direction": "higher",
478
- "early_mean": 0.12215662799301864,
479
- "goal_display": "goal \u2191",
480
- "improvement_pct": -35.653274040957065,
481
- "improvement_pct_display": "-35.65%",
482
- "last": 0.10155132412910461,
483
- "late_mean": 0.07860379065547524,
484
- "mid_mean": 0.07032911504236604,
485
- "pressure": "pressure_down",
486
- "pressure_arrow": "\u2198",
487
- "pressure_display": "goal \u2191 | \u2198 -35.65% worsening",
488
- "pressure_score": -1.0,
489
- "trend_label": "worsening"
490
- },
491
- "structure_top_negative_logit_mean": {
492
- "desired_direction": "lower",
493
- "early_mean": 7.262102601156069,
494
- "goal_display": "goal \u2193",
495
- "improvement_pct": -39.724147080005764,
496
- "improvement_pct_display": "-39.72%",
497
- "last": 10.1875,
498
- "late_mean": 10.14691091954023,
499
- "mid_mean": 10.490606936416185,
500
- "pressure": "pressure_down",
501
- "pressure_arrow": "\u2198",
502
- "pressure_display": "goal \u2193 | \u2198 -39.72% worsening",
503
- "pressure_score": -1.0,
504
- "trend_label": "worsening"
505
- },
506
- "structure_uncertain_fraction": {
507
- "desired_direction": "lower",
508
- "early_mean": 0.924663565751445,
509
- "goal_display": "goal \u2193",
510
- "improvement_pct": -6.108024336610137,
511
- "improvement_pct_display": "-6.11%",
512
- "last": 0.970703125,
513
- "late_mean": 0.9811422413793104,
514
- "mid_mean": 0.984747561416185,
515
- "pressure": "pressure_down",
516
- "pressure_arrow": "\u2198",
517
- "pressure_display": "goal \u2193 | \u2198 -6.11% worsening",
518
- "pressure_score": -1.0,
519
- "trend_label": "worsening"
520
- },
521
- "train_loss_ema": {
522
- "desired_direction": "lower",
523
- "early_mean": 6.265581717362126,
524
- "goal_display": "goal \u2193",
525
- "improvement_pct": 10.455707205061195,
526
- "improvement_pct_display": "+10.46%",
527
- "last": 6.519052214060582,
528
- "late_mean": 5.610470838300897,
529
- "mid_mean": 5.8371378655061745,
530
- "pressure": "pressure_up",
531
- "pressure_arrow": "\u2197",
532
- "pressure_display": "goal \u2193 | \u2197 +10.46% improving",
533
- "pressure_score": 1.0,
534
- "trend_label": "improving"
535
- },
536
- "val_ssl_loss": {
537
- "desired_direction": "lower",
538
- "early_mean": 1.0849772497183745,
539
- "goal_display": "goal \u2193",
540
- "improvement_pct": 2.3192742421198114,
541
- "improvement_pct_display": "+2.32%",
542
- "last": 1.0397093277424574,
543
- "late_mean": 1.0598136518327963,
544
- "mid_mean": 1.0747967428483425,
545
- "pressure": "pressure_none",
546
- "pressure_arrow": "\u2192",
547
- "pressure_display": "goal \u2193 | \u2192 +2.32% flat",
548
- "trend_label": "flat"
549
- },
550
- "val_structure_correct_logit_mean": {
551
- "desired_direction": "higher",
552
- "early_mean": 8.0311279296875,
553
- "goal_display": "goal \u2191",
554
- "improvement_pct": 16.44145855816145,
555
- "improvement_pct_display": "+16.44%",
556
- "last": 9.49462890625,
557
- "late_mean": 9.3515625,
558
- "mid_mean": 8.441162109375,
559
- "pressure": "pressure_up",
560
- "pressure_arrow": "\u2197",
561
- "pressure_display": "goal \u2191 | \u2197 +16.44% improving",
562
- "pressure_score": 1.0,
563
- "trend_label": "improving"
564
- },
565
- "val_structure_retrieval_logit_std": {
566
- "desired_direction": "higher",
567
- "early_mean": 1.2326001720502973,
568
- "goal_display": "goal \u2191",
569
- "improvement_pct": 102.32641409365677,
570
- "improvement_pct_clipped": 100.0,
571
- "improvement_pct_clipped_display": "+100.00%",
572
- "improvement_pct_display": "+102.33%",
573
- "last": 2.6622845763340592,
574
- "late_mean": 2.49387572822161,
575
- "mid_mean": 2.022283688886091,
576
- "pressure": "pressure_up",
577
- "pressure_arrow": "\u2197",
578
- "pressure_display": "goal \u2191 | \u2197 +102.33% improving",
579
- "pressure_score": 1.0,
580
- "trend_label": "improving"
581
- },
582
- "val_structure_retrieval_loss": {
583
- "desired_direction": "lower",
584
- "early_mean": 11.562767315655947,
585
- "goal_display": "goal \u2193",
586
- "improvement_pct": 4.864921250164783,
587
- "improvement_pct_display": "+4.86%",
588
- "last": 10.882395941764116,
589
- "late_mean": 11.000247791409492,
590
- "mid_mean": 12.150514367967844,
591
- "pressure": "pressure_none",
592
- "pressure_arrow": "\u2192",
593
- "pressure_display": "goal \u2193 | \u2192 +4.86% flat",
594
- "trend_label": "flat"
595
- },
596
- "val_structure_top1_top2_gap_norm_mean": {
597
- "desired_direction": "higher",
598
- "early_mean": 0.06950851557485294,
599
- "goal_display": "goal \u2191",
600
- "improvement_pct": -16.826381575968767,
601
- "improvement_pct_display": "-16.83%",
602
- "last": 0.05411380449368153,
603
- "late_mean": 0.0578127475164365,
604
- "mid_mean": 0.07577372609375743,
605
- "pressure": "pressure_down",
606
- "pressure_arrow": "\u2198",
607
- "pressure_display": "goal \u2191 | \u2198 -16.83% worsening",
608
- "pressure_score": -1.0,
609
- "trend_label": "worsening"
610
- },
611
- "val_structure_top_negative_logit_mean": {
612
- "desired_direction": "lower",
613
- "early_mean": 9.2255859375,
614
- "goal_display": "goal \u2193",
615
- "improvement_pct": -16.07653223245475,
616
- "improvement_pct_display": "-16.08%",
617
- "last": 10.714599609375,
618
- "late_mean": 10.708740234375,
619
- "mid_mean": 10.51171875,
620
- "pressure": "pressure_down",
621
- "pressure_arrow": "\u2198",
622
- "pressure_display": "goal \u2193 | \u2198 -16.08% worsening",
623
- "pressure_score": -1.0,
624
- "trend_label": "worsening"
625
- },
626
- "weighted_regularizer_to_contrastive_ratio": {
627
- "desired_direction": "lower",
628
- "early_mean": 0.0667222202939108,
629
- "goal_display": "goal \u2193",
630
- "improvement_pct": 54.60656419810926,
631
- "improvement_pct_display": "+54.61%",
632
- "last": 0.028996589606316913,
633
- "late_mean": 0.03028750823471251,
634
- "mid_mean": 0.0329437448262181,
635
- "pressure": "pressure_up",
636
- "pressure_arrow": "\u2197",
637
- "pressure_display": "goal \u2193 | \u2197 +54.61% improving",
638
- "pressure_score": 1.0,
639
- "trend_label": "improving"
640
- }
641
- },
642
- "debug_metrics": {
643
- "contrastive_loss": 0.5768923759460449,
644
- "covariance_loss": 10.012618064880371,
645
- "dataloader_wait_pct_300s": 0.0382592069912683,
646
- "dataloader_wait_pct_60s": 0.0961140629935623,
647
- "dataloader_wait_pct_900s": 0.066640439237091,
648
- "dataloader_wait_pct_run": 0.06717802801040498,
649
- "gpu_active_fraction": 1.0,
650
- "gpu_max_memory_gb": 13.279157161712646,
651
- "gpu_mem_used_mean_gb": 14.1943359375,
652
- "gpu_mem_util_mean_pct": 14.848754175733243,
653
- "gpu_snapshot_available": 1.0,
654
- "gpu_util_max_pct": 54.0,
655
- "gpu_util_mean_pct": 36.0,
656
- "gpu_util_min_pct": 18.0,
657
- "grad_norm": 1.7659728527069092,
658
- "mfu_estimate": 0.06267708747552383,
659
- "samples_per_sec": 1399.0203442084614,
660
- "samples_per_sec_300s": 1547.033197547462,
661
- "samples_per_sec_60s": 1399.0203442084614,
662
- "samples_per_sec_900s": 1512.7885250414204,
663
- "samples_per_sec_run_mean": 1533.0231795943853,
664
- "step_time_cv_300s": 0.06743440395418321,
665
- "step_time_cv_900s": 0.09218780075615579,
666
- "step_time_sec": 0.3659703749981418,
667
- "structure_bce_loss": 0.08383000642061234,
668
- "structure_close_fraction": 0.029296875,
669
- "structure_confidence_candidate_count": 2126.0,
670
- "structure_confidence_separation": -0.0040241447277367115,
671
- "structure_correct_logit_mean": 9.1875,
672
- "structure_fingerprint_cosine": 0.46021854877471924,
673
- "structure_hit_at_1": 0.00390625,
674
- "structure_hit_at_20": 0.1171875,
675
- "structure_hit_at_5": 0.029296875,
676
- "structure_logit_margin_mean": -1.0078125,
677
- "structure_retrieval_logit_std": 0.9839304089546204,
678
- "structure_retrieval_loss": 10.630162239074707,
679
- "structure_target_rank_mean": 314.703125,
680
- "structure_top1_top2_gap_mean": 0.0986328125,
681
- "structure_top1_top2_gap_norm_mean": 0.10155132412910461,
682
- "structure_top_negative_logit_mean": 10.1875,
683
- "structure_uncertain_fraction": 0.970703125,
684
- "structure_uncertain_hit_at_1": 0.0040241447277367115,
685
- "train_loss": 6.491608619689941,
686
- "train_loss_ema": 6.519052214060582,
687
- "val_loss": 6.646750174145564,
688
- "val_ssl_loss": 1.0397093277424574,
689
- "val_structure_close_fraction": 0.0077972412109375,
690
- "val_structure_close_hit_at_1": 0.014835291571216658,
691
- "val_structure_confidence_candidate_count": 4096.0,
692
- "val_structure_confidence_separation": -0.027957430157584895,
693
- "val_structure_correct_logit_mean": 9.49462890625,
694
- "val_structure_retrieval_logit_std": 2.6622845763340592,
695
- "val_structure_retrieval_loss": 10.882395941764116,
696
- "val_structure_top1_top2_gap_mean": 0.11855697631835938,
697
- "val_structure_top1_top2_gap_norm_mean": 0.05411380449368153,
698
- "val_structure_top_negative_logit_mean": 10.714599609375,
699
- "val_structure_uncertain_fraction": 0.9922027587890625,
700
- "val_structure_uncertain_hit_at_1": 0.027957430157584895,
701
- "variance_loss": 0.00213623046875,
702
- "weighted_regularizer_to_contrastive_ratio": 0.028996589606316913
703
- },
704
- "eval_coverage": {
705
- "configured_test_shard_count": 2,
706
- "configured_test_shards": [
707
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/test/shard_20260313_051433_00000.parquet",
708
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/test/shard_20260313_051454_00000.parquet"
709
- ],
710
- "configured_val_shard_count": 2,
711
- "configured_val_shards": [
712
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051433_00000.parquet",
713
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051454_00000.parquet"
714
- ],
715
- "created_at": "2026-04-13T21:36:17Z",
716
- "eval_batch_limit": 256,
717
- "eval_batches_per_shard_limit": 0,
718
- "eval_loader_mode": "stream",
719
- "eval_mode": "deep",
720
- "full_holdout_coverage": 0.0,
721
- "full_holdout_sweep": false,
722
- "full_test_coverage": 0.0,
723
- "full_val_coverage": 1.0,
724
- "missing_test_shards": [
725
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/test/shard_20260313_051433_00000.parquet",
726
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/test/shard_20260313_051454_00000.parquet"
727
- ],
728
- "missing_val_shards": [],
729
- "observed_eval_batches": 256,
730
- "observed_eval_samples": 131072,
731
- "observed_test_shard_count": 0,
732
- "observed_test_shards": [],
733
- "observed_val_shard_count": 2,
734
- "observed_val_shards": [
735
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051433_00000.parquet",
736
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051454_00000.parquet"
737
- ],
738
- "per_shard_batch_count": {
739
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051433_00000.parquet": 128,
740
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051454_00000.parquet": 128
741
- },
742
- "per_shard_sample_count": {
743
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051433_00000.parquet": 65536,
744
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051454_00000.parquet": 65536
745
- },
746
- "run_step": 10000,
747
- "step": 91001,
748
- "unexpected_eval_shards": []
749
- },
750
- "failure_modes": [
751
- {
752
- "detail": "Observed shard counts {'train': 4, 'val': 2, 'test': 2}; the canonical Day 1 loader contract requires all splits to be readable.",
753
- "name": "dataset_shards_accessible",
754
- "status": "pass"
755
- },
756
- {
757
- "detail": "Training batches continued to arrive with positive throughput and no iterator stall.",
758
- "name": "dataloader_streaming_stable",
759
- "status": "pass"
760
- },
761
- {
762
- "detail": "Technical_Plan requires zero NaN or Inf tensors and finite train/val loss.",
763
- "name": "non_finite_loss_or_tensor_failure",
764
- "status": "pass"
765
- },
766
- {
767
- "detail": "Engineering.md expects slope-aware monitoring; missing validation or retrieval metrics make trend judgment weaker.",
768
- "name": "validation_observability_gap",
769
- "status": "pass"
770
- },
771
- {
772
- "detail": "Technical_Plan Day 1 success requires stable GPU memory through the bounded run.",
773
- "name": "gpu_memory_instability",
774
- "status": "pass"
775
- },
776
- {
777
- "detail": "Checkpoint save and reload is an explicit Day 1 success criterion.",
778
- "name": "checkpoint_save_reload_failure",
779
- "status": "pass"
780
- },
781
- {
782
- "detail": "Engineering.md expects embedding variance monitoring and non-collapsed representations.",
783
- "name": "embedding_collapse",
784
- "status": "pass"
785
- },
786
- {
787
- "detail": "The current instability mode is regularization overpowering the SSL objective and producing jagged total loss.",
788
- "name": "regularizer_dominance",
789
- "status": "pass"
790
- },
791
- {
792
- "detail": "Once the bridge phase begins, Technical_Plan requires retrieval-oriented validation rather than only augmented contrastive loss.",
793
- "name": "structure_supervision_gap",
794
- "status": "pass"
795
- },
796
- {
797
- "detail": "Structure-first qualification now requires explicit confidence diagnostics such as top-1/top-2 separation and uncertainty buckets, not just broader retrieval metrics.",
798
- "name": "confidence_surface_gap",
799
- "status": "pass"
800
- },
801
- {
802
- "detail": "The bridge phase should prefer chemistry-grounded fingerprint targets; hashed fallback targets weaken the retrieval signal.",
803
- "name": "chemistry_target_backend_gap",
804
- "status": "pass"
805
- },
806
- {
807
- "detail": "Bridge runs must improve retrieval after fingerprint fit saturates; fitting BCE while val Hit@20 stays at candidate-bank baseline means ranking is not generalizing.",
808
- "name": "bridge_fit_without_ranking",
809
- "status": "pass"
810
- },
811
- {
812
- "detail": "Engineering.md flags acquisition-artefact shortcut risk; adduct and instrument embeddings remain deliberately down-scaled.",
813
- "name": "metadata_shortcutting",
814
- "status": "watch"
815
- }
816
- ],
817
- "fast_eval_surface": {
818
- "batch_size": 512,
819
- "batches_per_shard": 0,
820
- "configured_val_shard_count": 2,
821
- "configured_val_shards": [
822
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051433_00000.parquet",
823
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051454_00000.parquet"
824
- ],
825
- "created_at": "2026-04-13T20:20:58Z",
826
- "loader_mode": "stream",
827
- "per_shard_batch_count": {},
828
- "per_shard_row_count": {},
829
- "row_count": 0
830
- },
831
- "metric_pressure_summary": {
832
- "average_improvement_pct": 34.52368967199551,
833
- "metric_count": 39,
834
- "overall_arrow": "\u2197",
835
- "overall_pressure": "pressure_up",
836
- "pressure_down_count": 11,
837
- "pressure_none_count": 7,
838
- "pressure_up_count": 21,
839
- "pressure_up_fraction": 0.5384615384615384,
840
- "weighted_improvement_pct": 21.88570985770741,
841
- "weighted_pressure_score": 0.2838709677419355
842
- },
843
- "metric_pressure_summary_display": {
844
- "average_improvement_pct": 34.52368967199551,
845
- "average_improvement_pct_display": "+34.52%",
846
- "metric_count": 39,
847
- "overall_arrow": "\u2197",
848
- "overall_display": "\u2197 improving (+21.89% weighted)",
849
- "overall_label": "improving",
850
- "overall_pressure": "pressure_up",
851
- "pressure_down_count": 11,
852
- "pressure_none_count": 7,
853
- "pressure_up_count": 21,
854
- "pressure_up_fraction": 0.5384615384615384,
855
- "pressure_up_fraction_display": "+53.85%",
856
- "weighted_improvement_pct": 21.88570985770741,
857
- "weighted_improvement_pct_display": "+21.89%",
858
- "weighted_pressure_score": 0.2838709677419355
859
- },
860
- "metric_pressures": {
861
- "contrastive_loss": {
862
- "desired_direction": "lower",
863
- "early_mean": 1.409792113166324,
864
- "improvement_pct": -1.6400841264380104,
865
- "improvement_pct_clipped": -1.6400841264380104,
866
- "last": 0.5768923759460449,
867
- "late_mean": 1.43291388983014,
868
- "mid_mean": 1.3598130204084982,
869
- "pressure": "pressure_none",
870
- "pressure_arrow": "\u2192",
871
- "pressure_score": 0.0
872
- },
873
- "gpu_max_memory_gb": {
874
- "desired_direction": "stable",
875
- "early_mean": 13.252925169950275,
876
- "improvement_pct": 100.0,
877
- "improvement_pct_clipped": 100.0,
878
- "last": 13.279157161712646,
879
- "late_mean": 13.279157161712646,
880
- "mid_mean": 13.279059082097401,
881
- "pressure": "pressure_up",
882
- "pressure_arrow": "\u2197",
883
- "pressure_score": 1.0
884
- },
885
- "grad_norm": {
886
- "desired_direction": "stable",
887
- "early_mean": 4.638080189338309,
888
- "improvement_pct": -100.0,
889
- "improvement_pct_clipped": -100.0,
890
- "last": 1.7659728527069092,
891
- "late_mean": 6.072961742165445,
892
- "mid_mean": 4.979553528603791,
893
- "pressure": "pressure_down",
894
- "pressure_arrow": "\u2198",
895
- "pressure_score": -1.0
896
- },
897
- "samples_per_sec": {
898
- "desired_direction": "higher",
899
- "early_mean": 1575.5664566260843,
900
- "improvement_pct": -2.8825714693532967,
901
- "improvement_pct_clipped": -2.8825714693532967,
902
- "last": 1399.0203442084614,
903
- "late_mean": 1530.1496274666802,
904
- "mid_mean": 1531.3735887168505,
905
- "pressure": "pressure_down",
906
- "pressure_arrow": "\u2198",
907
- "pressure_score": -1.0
908
- },
909
- "structure_bce_loss": {
910
- "desired_direction": "lower",
911
- "early_mean": 0.12293951650489272,
912
- "improvement_pct": 39.749156913940595,
913
- "improvement_pct_clipped": 39.749156913940595,
914
- "last": 0.08383000642061234,
915
- "late_mean": 0.07407209518012302,
916
- "mid_mean": 0.07652380578004556,
917
- "pressure": "pressure_up",
918
- "pressure_arrow": "\u2197",
919
- "pressure_score": 1.0
920
- },
921
- "structure_confidence_separation": {
922
- "desired_direction": "higher",
923
- "early_mean": -0.007918493679557749,
924
- "improvement_pct": -531.5617836245987,
925
- "improvement_pct_clipped": -100.0,
926
- "last": -0.0040241447277367115,
927
- "late_mean": -0.05001017991881603,
928
- "mid_mean": -0.032136323077151974,
929
- "pressure": "pressure_down",
930
- "pressure_arrow": "\u2198",
931
- "pressure_score": -1.0
932
- },
933
- "structure_correct_logit_mean": {
934
- "desired_direction": "higher",
935
- "early_mean": 6.134031791907514,
936
- "improvement_pct": 47.305071917778086,
937
- "improvement_pct_clipped": 47.305071917778086,
938
- "last": 9.1875,
939
- "late_mean": 9.035739942528735,
940
- "mid_mean": 9.474891618497109,
941
- "pressure": "pressure_up",
942
- "pressure_arrow": "\u2197",
943
- "pressure_score": 1.0
944
- },
945
- "structure_fingerprint_cosine": {
946
- "desired_direction": "higher",
947
- "early_mean": 0.3965519580968543,
948
- "improvement_pct": 17.58747890372286,
949
- "improvement_pct_clipped": 17.58747890372286,
950
- "last": 0.46021854877471924,
951
- "late_mean": 0.46629545006943846,
952
- "mid_mean": 0.4464927057310336,
953
- "pressure": "pressure_up",
954
- "pressure_arrow": "\u2197",
955
- "pressure_score": 1.0
956
- },
957
- "structure_hit_at_1": {
958
- "desired_direction": "higher",
959
- "early_mean": 0.007880238439306358,
960
- "improvement_pct": 549.6830023383724,
961
- "improvement_pct_clipped": 100.0,
962
- "last": 0.00390625,
963
- "late_mean": 0.051196569683908046,
964
- "mid_mean": 0.032706376445086706,
965
- "pressure": "pressure_up",
966
- "pressure_arrow": "\u2197",
967
- "pressure_score": 1.0
968
- },
969
- "structure_hit_at_20": {
970
- "desired_direction": "higher",
971
- "early_mean": 0.10721865968208093,
972
- "improvement_pct": 239.4614028144399,
973
- "improvement_pct_clipped": 100.0,
974
- "last": 0.1171875,
975
- "late_mean": 0.3639659662356322,
976
- "mid_mean": 0.28105807442196534,
977
- "pressure": "pressure_up",
978
- "pressure_arrow": "\u2197",
979
- "pressure_score": 1.0
980
- },
981
- "structure_hit_at_5": {
982
- "desired_direction": "higher",
983
- "early_mean": 0.03360955563583815,
984
- "improvement_pct": 402.47008675709174,
985
- "improvement_pct_clipped": 100.0,
986
- "last": 0.029296875,
987
- "late_mean": 0.16887796336206898,
988
- "mid_mean": 0.11673591040462428,
989
- "pressure": "pressure_up",
990
- "pressure_arrow": "\u2197",
991
- "pressure_score": 1.0
992
- },
993
- "structure_logit_margin_mean": {
994
- "desired_direction": "higher",
995
- "early_mean": -1.1263999277456647,
996
- "improvement_pct": 1.2274364862230593,
997
- "improvement_pct_clipped": 1.2274364862230593,
998
- "last": -1.0078125,
999
- "late_mean": -1.1125740840517242,
1000
- "mid_mean": -1.0154725885115607,
1001
- "pressure": "pressure_none",
1002
- "pressure_arrow": "\u2192",
1003
- "pressure_score": 0.0
1004
- },
1005
- "structure_retrieval_logit_std": {
1006
- "desired_direction": "higher",
1007
- "early_mean": 1.0455416592559375,
1008
- "improvement_pct": 112.05988926255111,
1009
- "improvement_pct_clipped": 100.0,
1010
- "last": 0.9839304089546204,
1011
- "late_mean": 2.2171744848119803,
1012
- "mid_mean": 2.0036371215919537,
1013
- "pressure": "pressure_up",
1014
- "pressure_arrow": "\u2197",
1015
- "pressure_score": 1.0
1016
- },
1017
- "structure_retrieval_loss": {
1018
- "desired_direction": "lower",
1019
- "early_mean": 10.237479978903181,
1020
- "improvement_pct": 10.094066619063353,
1021
- "improvement_pct_clipped": 10.094066619063353,
1022
- "last": 10.630162239074707,
1023
- "late_mean": 9.204101929719421,
1024
- "mid_mean": 9.41523380775672,
1025
- "pressure": "pressure_up",
1026
- "pressure_arrow": "\u2197",
1027
- "pressure_score": 1.0
1028
- },
1029
- "structure_target_rank_mean": {
1030
- "desired_direction": "lower",
1031
- "early_mean": 351.84337743858384,
1032
- "improvement_pct": 58.80171764880722,
1033
- "improvement_pct_clipped": 58.80171764880722,
1034
- "last": 314.703125,
1035
- "late_mean": 144.9534280711207,
1036
- "mid_mean": 176.16389315390174,
1037
- "pressure": "pressure_up",
1038
- "pressure_arrow": "\u2197",
1039
- "pressure_score": 1.0
1040
- },
1041
- "structure_top1_top2_gap_mean": {
1042
- "desired_direction": "higher",
1043
- "early_mean": 0.09793567106213873,
1044
- "improvement_pct": 59.221149173532794,
1045
- "improvement_pct_clipped": 59.221149173532794,
1046
- "last": 0.0986328125,
1047
- "late_mean": 0.1559343009159483,
1048
- "mid_mean": 0.12284365968208093,
1049
- "pressure": "pressure_up",
1050
- "pressure_arrow": "\u2197",
1051
- "pressure_score": 1.0
1052
- },
1053
- "structure_top1_top2_gap_norm_mean": {
1054
- "desired_direction": "higher",
1055
- "early_mean": 0.12215662799301864,
1056
- "improvement_pct": -35.653274040957065,
1057
- "improvement_pct_clipped": -35.653274040957065,
1058
- "last": 0.10155132412910461,
1059
- "late_mean": 0.07860379065547524,
1060
- "mid_mean": 0.07032911504236604,
1061
- "pressure": "pressure_down",
1062
- "pressure_arrow": "\u2198",
1063
- "pressure_score": -1.0
1064
- },
1065
- "structure_top_negative_logit_mean": {
1066
- "desired_direction": "lower",
1067
- "early_mean": 7.262102601156069,
1068
- "improvement_pct": -39.724147080005764,
1069
- "improvement_pct_clipped": -39.724147080005764,
1070
- "last": 10.1875,
1071
- "late_mean": 10.14691091954023,
1072
- "mid_mean": 10.490606936416185,
1073
- "pressure": "pressure_down",
1074
- "pressure_arrow": "\u2198",
1075
- "pressure_score": -1.0
1076
- },
1077
- "structure_uncertain_fraction": {
1078
- "desired_direction": "lower",
1079
- "early_mean": 0.924663565751445,
1080
- "improvement_pct": -6.108024336610137,
1081
- "improvement_pct_clipped": -6.108024336610137,
1082
- "last": 0.970703125,
1083
- "late_mean": 0.9811422413793104,
1084
- "mid_mean": 0.984747561416185,
1085
- "pressure": "pressure_down",
1086
- "pressure_arrow": "\u2198",
1087
- "pressure_score": -1.0
1088
- },
1089
- "train_loss": {
1090
- "desired_direction": "lower",
1091
- "early_mean": 6.340343519442343,
1092
- "improvement_pct": 10.566866163080938,
1093
- "improvement_pct_clipped": 10.566866163080938,
1094
- "last": 6.491608619689941,
1095
- "late_mean": 5.670367905463295,
1096
- "mid_mean": 5.795929590401622,
1097
- "pressure": "pressure_up",
1098
- "pressure_arrow": "\u2197",
1099
- "pressure_score": 1.0
1100
- },
1101
- "train_loss_ema": {
1102
- "desired_direction": "lower",
1103
- "early_mean": 6.265581717362126,
1104
- "improvement_pct": 10.455707205061195,
1105
- "improvement_pct_clipped": 10.455707205061195,
1106
- "last": 6.519052214060582,
1107
- "late_mean": 5.610470838300897,
1108
- "mid_mean": 5.8371378655061745,
1109
- "pressure": "pressure_up",
1110
- "pressure_arrow": "\u2197",
1111
- "pressure_score": 1.0
1112
- },
1113
- "val_hit_at_1": {
1114
- "desired_direction": "higher",
1115
- "early_mean": 0.0079345703125,
1116
- "improvement_pct": 207.78846153846155,
1117
- "improvement_pct_clipped": 100.0,
1118
- "last": 0.0282135009765625,
1119
- "late_mean": 0.02442169189453125,
1120
- "mid_mean": 0.01372528076171875,
1121
- "pressure": "pressure_none",
1122
- "pressure_arrow": "\u2192",
1123
- "pressure_score": 0.0
1124
- },
1125
- "val_hit_at_20": {
1126
- "desired_direction": "higher",
1127
- "early_mean": 0.08158111572265625,
1128
- "improvement_pct": 76.67165435331526,
1129
- "improvement_pct_clipped": 76.67165435331526,
1130
- "last": 0.15270233154296875,
1131
- "late_mean": 0.14413070678710938,
1132
- "mid_mean": 0.094146728515625,
1133
- "pressure": "pressure_up",
1134
- "pressure_arrow": "\u2197",
1135
- "pressure_score": 1.0
1136
- },
1137
- "val_hit_at_5": {
1138
- "desired_direction": "higher",
1139
- "early_mean": 0.0288543701171875,
1140
- "improvement_pct": 134.8492860920148,
1141
- "improvement_pct_clipped": 100.0,
1142
- "last": 0.0726776123046875,
1143
- "late_mean": 0.0677642822265625,
1144
- "mid_mean": 0.0425567626953125,
1145
- "pressure": "pressure_up",
1146
- "pressure_arrow": "\u2197",
1147
- "pressure_score": 1.0
1148
- },
1149
- "val_loss": {
1150
- "desired_direction": "lower",
1151
- "early_mean": 1.2876316868363775,
1152
- "improvement_pct": -55.82459156154955,
1153
- "improvement_pct_clipped": -55.82459156154955,
1154
- "last": 6.646750174145564,
1155
- "late_mean": 2.006446816829876,
1156
- "mid_mean": 2.20697861268016,
1157
- "pressure": "pressure_down",
1158
- "pressure_arrow": "\u2198",
1159
- "pressure_score": -1.0
1160
- },
1161
- "val_ssl_loss": {
1162
- "desired_direction": "lower",
1163
- "early_mean": 1.0849772497183745,
1164
- "improvement_pct": 2.3192742421198114,
1165
- "improvement_pct_clipped": 2.3192742421198114,
1166
- "last": 1.0397093277424574,
1167
- "late_mean": 1.0598136518327963,
1168
- "mid_mean": 1.0747967428483425,
1169
- "pressure": "pressure_none",
1170
- "pressure_arrow": "\u2192",
1171
- "pressure_score": 0.0
1172
- },
1173
- "val_structure_bce_loss": {
1174
- "desired_direction": "lower",
1175
- "early_mean": 0.0771060927848642,
1176
- "improvement_pct": 12.199713989530546,
1177
- "improvement_pct_clipped": 12.199713989530546,
1178
- "last": 0.06532714269997086,
1179
- "late_mean": 0.06769936999660872,
1180
- "mid_mean": 0.07029345531468391,
1181
- "pressure": "pressure_up",
1182
- "pressure_arrow": "\u2197",
1183
- "pressure_score": 1.0
1184
- },
1185
- "val_structure_confidence_separation": {
1186
- "desired_direction": "higher",
1187
- "early_mean": -0.00795668972114072,
1188
- "improvement_pct": -204.85499246505236,
1189
- "improvement_pct_clipped": -100.0,
1190
- "last": -0.027957430157584895,
1191
- "late_mean": -0.024256365849851136,
1192
- "mid_mean": -0.01309866098972634,
1193
- "pressure": "pressure_down",
1194
- "pressure_arrow": "\u2198",
1195
- "pressure_score": -1.0
1196
- },
1197
- "val_structure_correct_logit_mean": {
1198
- "desired_direction": "higher",
1199
- "early_mean": 8.0311279296875,
1200
- "improvement_pct": 16.44145855816145,
1201
- "improvement_pct_clipped": 16.44145855816145,
1202
- "last": 9.49462890625,
1203
- "late_mean": 9.3515625,
1204
- "mid_mean": 8.441162109375,
1205
- "pressure": "pressure_up",
1206
- "pressure_arrow": "\u2197",
1207
- "pressure_score": 1.0
1208
- },
1209
- "val_structure_fingerprint_cosine": {
1210
- "desired_direction": "higher",
1211
- "early_mean": 0.4147872725734487,
1212
- "improvement_pct": 0.17175282510408285,
1213
- "improvement_pct_clipped": 0.17175282510408285,
1214
- "last": 0.4255251376889646,
1215
- "late_mean": 0.4154996814322658,
1216
- "mid_mean": 0.4204998221830465,
1217
- "pressure": "pressure_none",
1218
- "pressure_arrow": "\u2192",
1219
- "pressure_score": 0.0
1220
- },
1221
- "val_structure_logit_margin_mean": {
1222
- "desired_direction": "higher",
1223
- "early_mean": -1.194091796875,
1224
- "improvement_pct": -13.669239419341647,
1225
- "improvement_pct_clipped": -13.669239419341647,
1226
- "last": -1.221923828125,
1227
- "late_mean": -1.3573150634765625,
1228
- "mid_mean": -2.0707931518554688,
1229
- "pressure": "pressure_down",
1230
- "pressure_arrow": "\u2198",
1231
- "pressure_score": -1.0
1232
- },
1233
- "val_structure_retrieval_logit_std": {
1234
- "desired_direction": "higher",
1235
- "early_mean": 1.2326001720502973,
1236
- "improvement_pct": 102.32641409365677,
1237
- "improvement_pct_clipped": 100.0,
1238
- "last": 2.6622845763340592,
1239
- "late_mean": 2.49387572822161,
1240
- "mid_mean": 2.022283688886091,
1241
- "pressure": "pressure_up",
1242
- "pressure_arrow": "\u2197",
1243
- "pressure_score": 1.0
1244
- },
1245
- "val_structure_retrieval_loss": {
1246
- "desired_direction": "lower",
1247
- "early_mean": 11.562767315655947,
1248
- "improvement_pct": 4.864921250164783,
1249
- "improvement_pct_clipped": 4.864921250164783,
1250
- "last": 10.882395941764116,
1251
- "late_mean": 11.000247791409492,
1252
- "mid_mean": 12.150514367967844,
1253
- "pressure": "pressure_none",
1254
- "pressure_arrow": "\u2192",
1255
- "pressure_score": 0.0
1256
- },
1257
- "val_structure_target_rank_mean": {
1258
- "desired_direction": "lower",
1259
- "early_mean": 760.7540435791016,
1260
- "improvement_pct": 45.44775026271755,
1261
- "improvement_pct_clipped": 45.44775026271755,
1262
- "last": 379.8781280517578,
1263
- "late_mean": 415.0084457397461,
1264
- "mid_mean": 683.3385162353516,
1265
- "pressure": "pressure_up",
1266
- "pressure_arrow": "\u2197",
1267
- "pressure_score": 1.0
1268
- },
1269
- "val_structure_top1_top2_gap_mean": {
1270
- "desired_direction": "higher",
1271
- "early_mean": 0.07839679718017578,
1272
- "improvement_pct": 54.90785232041847,
1273
- "improvement_pct_clipped": 54.90785232041847,
1274
- "last": 0.11855697631835938,
1275
- "late_mean": 0.12144279479980469,
1276
- "mid_mean": 0.1310901641845703,
1277
- "pressure": "pressure_up",
1278
- "pressure_arrow": "\u2197",
1279
- "pressure_score": 1.0
1280
- },
1281
- "val_structure_top1_top2_gap_norm_mean": {
1282
- "desired_direction": "higher",
1283
- "early_mean": 0.06950851557485294,
1284
- "improvement_pct": -16.826381575968767,
1285
- "improvement_pct_clipped": -16.826381575968767,
1286
- "last": 0.05411380449368153,
1287
- "late_mean": 0.0578127475164365,
1288
- "mid_mean": 0.07577372609375743,
1289
- "pressure": "pressure_down",
1290
- "pressure_arrow": "\u2198",
1291
- "pressure_score": -1.0
1292
- },
1293
- "val_structure_top_negative_logit_mean": {
1294
- "desired_direction": "lower",
1295
- "early_mean": 9.2255859375,
1296
- "improvement_pct": -16.07653223245475,
1297
- "improvement_pct_clipped": -16.07653223245475,
1298
- "last": 10.714599609375,
1299
- "late_mean": 10.708740234375,
1300
- "mid_mean": 10.51171875,
1301
- "pressure": "pressure_down",
1302
- "pressure_arrow": "\u2198",
1303
- "pressure_score": -1.0
1304
- },
1305
- "val_structure_uncertain_fraction": {
1306
- "desired_direction": "lower",
1307
- "early_mean": 0.9941177368164062,
1308
- "improvement_pct": -0.03261678728482514,
1309
- "improvement_pct_clipped": -0.03261678728482514,
1310
- "last": 0.9922027587890625,
1311
- "late_mean": 0.9944419860839844,
1312
- "mid_mean": 0.9762382507324219,
1313
- "pressure": "pressure_none",
1314
- "pressure_arrow": "\u2192",
1315
- "pressure_score": 0.0
1316
- },
1317
- "weighted_regularizer_to_contrastive_ratio": {
1318
- "desired_direction": "lower",
1319
- "early_mean": 0.0667222202939108,
1320
- "improvement_pct": 54.60656419810926,
1321
- "improvement_pct_clipped": 54.60656419810926,
1322
- "last": 0.028996589606316913,
1323
- "late_mean": 0.03028750823471251,
1324
- "mid_mean": 0.0329437448262181,
1325
- "pressure": "pressure_up",
1326
- "pressure_arrow": "\u2197",
1327
- "pressure_score": 1.0
1328
- }
1329
- },
1330
- "metric_pressures_display": {
1331
- "contrastive_loss": {
1332
- "desired_direction": "lower",
1333
- "early_mean": 1.409792113166324,
1334
- "goal_display": "goal \u2193",
1335
- "improvement_pct": -1.6400841264380104,
1336
- "improvement_pct_display": "-1.64%",
1337
- "last": 0.5768923759460449,
1338
- "late_mean": 1.43291388983014,
1339
- "mid_mean": 1.3598130204084982,
1340
- "pressure": "pressure_none",
1341
- "pressure_arrow": "\u2192",
1342
- "pressure_display": "goal \u2193 | \u2192 -1.64% flat",
1343
- "trend_label": "flat"
1344
- },
1345
- "gpu_max_memory_gb": {
1346
- "desired_direction": "stable",
1347
- "early_mean": 13.252925169950275,
1348
- "goal_display": "goal \u2248",
1349
- "improvement_pct": 100.0,
1350
- "improvement_pct_display": "+100.00%",
1351
- "last": 13.279157161712646,
1352
- "late_mean": 13.279157161712646,
1353
- "mid_mean": 13.279059082097401,
1354
- "pressure": "pressure_up",
1355
- "pressure_arrow": "\u2197",
1356
- "pressure_display": "goal \u2248 | \u2197 +100.00% improving",
1357
- "pressure_score": 1.0,
1358
- "trend_label": "improving"
1359
- },
1360
- "grad_norm": {
1361
- "desired_direction": "stable",
1362
- "early_mean": 4.638080189338309,
1363
- "goal_display": "goal \u2248",
1364
- "improvement_pct": -100.0,
1365
- "improvement_pct_display": "-100.00%",
1366
- "last": 1.7659728527069092,
1367
- "late_mean": 6.072961742165445,
1368
- "mid_mean": 4.979553528603791,
1369
- "pressure": "pressure_down",
1370
- "pressure_arrow": "\u2198",
1371
- "pressure_display": "goal \u2248 | \u2198 -100.00% worsening",
1372
- "pressure_score": -1.0,
1373
- "trend_label": "worsening"
1374
- },
1375
- "samples_per_sec": {
1376
- "desired_direction": "higher",
1377
- "early_mean": 1575.5664566260843,
1378
- "goal_display": "goal \u2191",
1379
- "improvement_pct": -2.8825714693532967,
1380
- "improvement_pct_display": "-2.88%",
1381
- "last": 1399.0203442084614,
1382
- "late_mean": 1530.1496274666802,
1383
- "mid_mean": 1531.3735887168505,
1384
- "pressure": "pressure_down",
1385
- "pressure_arrow": "\u2198",
1386
- "pressure_display": "goal \u2191 | \u2198 -2.88% worsening",
1387
- "pressure_score": -1.0,
1388
- "trend_label": "worsening"
1389
- },
1390
- "structure_bce_loss": {
1391
- "desired_direction": "lower",
1392
- "early_mean": 0.12293951650489272,
1393
- "goal_display": "goal \u2193",
1394
- "improvement_pct": 39.749156913940595,
1395
- "improvement_pct_display": "+39.75%",
1396
- "last": 0.08383000642061234,
1397
- "late_mean": 0.07407209518012302,
1398
- "mid_mean": 0.07652380578004556,
1399
- "pressure": "pressure_up",
1400
- "pressure_arrow": "\u2197",
1401
- "pressure_display": "goal \u2193 | \u2197 +39.75% improving",
1402
- "pressure_score": 1.0,
1403
- "trend_label": "improving"
1404
- },
1405
- "structure_confidence_separation": {
1406
- "desired_direction": "higher",
1407
- "early_mean": -0.007918493679557749,
1408
- "goal_display": "goal \u2191",
1409
- "improvement_pct": -531.5617836245987,
1410
- "improvement_pct_clipped": -100.0,
1411
- "improvement_pct_clipped_display": "-100.00%",
1412
- "improvement_pct_display": "-531.56%",
1413
- "last": -0.0040241447277367115,
1414
- "late_mean": -0.05001017991881603,
1415
- "mid_mean": -0.032136323077151974,
1416
- "pressure": "pressure_down",
1417
- "pressure_arrow": "\u2198",
1418
- "pressure_display": "goal \u2191 | \u2198 -531.56% worsening",
1419
- "pressure_score": -1.0,
1420
- "trend_label": "worsening"
1421
- },
1422
- "structure_correct_logit_mean": {
1423
- "desired_direction": "higher",
1424
- "early_mean": 6.134031791907514,
1425
- "goal_display": "goal \u2191",
1426
- "improvement_pct": 47.305071917778086,
1427
- "improvement_pct_display": "+47.31%",
1428
- "last": 9.1875,
1429
- "late_mean": 9.035739942528735,
1430
- "mid_mean": 9.474891618497109,
1431
- "pressure": "pressure_up",
1432
- "pressure_arrow": "\u2197",
1433
- "pressure_display": "goal \u2191 | \u2197 +47.31% improving",
1434
- "pressure_score": 1.0,
1435
- "trend_label": "improving"
1436
- },
1437
- "structure_fingerprint_cosine": {
1438
- "desired_direction": "higher",
1439
- "early_mean": 0.3965519580968543,
1440
- "goal_display": "goal \u2191",
1441
- "improvement_pct": 17.58747890372286,
1442
- "improvement_pct_display": "+17.59%",
1443
- "last": 0.46021854877471924,
1444
- "late_mean": 0.46629545006943846,
1445
- "mid_mean": 0.4464927057310336,
1446
- "pressure": "pressure_up",
1447
- "pressure_arrow": "\u2197",
1448
- "pressure_display": "goal \u2191 | \u2197 +17.59% improving",
1449
- "pressure_score": 1.0,
1450
- "trend_label": "improving"
1451
- },
1452
- "structure_hit_at_1": {
1453
- "desired_direction": "higher",
1454
- "early_mean": 0.007880238439306358,
1455
- "goal_display": "goal \u2191",
1456
- "improvement_pct": 549.6830023383724,
1457
- "improvement_pct_clipped": 100.0,
1458
- "improvement_pct_clipped_display": "+100.00%",
1459
- "improvement_pct_display": "+549.68%",
1460
- "last": 0.00390625,
1461
- "late_mean": 0.051196569683908046,
1462
- "mid_mean": 0.032706376445086706,
1463
- "pressure": "pressure_up",
1464
- "pressure_arrow": "\u2197",
1465
- "pressure_display": "goal \u2191 | \u2197 +549.68% improving",
1466
- "pressure_score": 1.0,
1467
- "trend_label": "improving"
1468
- },
1469
- "structure_hit_at_20": {
1470
- "desired_direction": "higher",
1471
- "early_mean": 0.10721865968208093,
1472
- "goal_display": "goal \u2191",
1473
- "improvement_pct": 239.4614028144399,
1474
- "improvement_pct_clipped": 100.0,
1475
- "improvement_pct_clipped_display": "+100.00%",
1476
- "improvement_pct_display": "+239.46%",
1477
- "last": 0.1171875,
1478
- "late_mean": 0.3639659662356322,
1479
- "mid_mean": 0.28105807442196534,
1480
- "pressure": "pressure_up",
1481
- "pressure_arrow": "\u2197",
1482
- "pressure_display": "goal \u2191 | \u2197 +239.46% improving",
1483
- "pressure_score": 1.0,
1484
- "trend_label": "improving"
1485
- },
1486
- "structure_hit_at_5": {
1487
- "desired_direction": "higher",
1488
- "early_mean": 0.03360955563583815,
1489
- "goal_display": "goal \u2191",
1490
- "improvement_pct": 402.47008675709174,
1491
- "improvement_pct_clipped": 100.0,
1492
- "improvement_pct_clipped_display": "+100.00%",
1493
- "improvement_pct_display": "+402.47%",
1494
- "last": 0.029296875,
1495
- "late_mean": 0.16887796336206898,
1496
- "mid_mean": 0.11673591040462428,
1497
- "pressure": "pressure_up",
1498
- "pressure_arrow": "\u2197",
1499
- "pressure_display": "goal \u2191 | \u2197 +402.47% improving",
1500
- "pressure_score": 1.0,
1501
- "trend_label": "improving"
1502
- },
1503
- "structure_logit_margin_mean": {
1504
- "desired_direction": "higher",
1505
- "early_mean": -1.1263999277456647,
1506
- "goal_display": "goal \u2191",
1507
- "improvement_pct": 1.2274364862230593,
1508
- "improvement_pct_display": "+1.23%",
1509
- "last": -1.0078125,
1510
- "late_mean": -1.1125740840517242,
1511
- "mid_mean": -1.0154725885115607,
1512
- "pressure": "pressure_none",
1513
- "pressure_arrow": "\u2192",
1514
- "pressure_display": "goal \u2191 | \u2192 +1.23% flat",
1515
- "trend_label": "flat"
1516
- },
1517
- "structure_retrieval_logit_std": {
1518
- "desired_direction": "higher",
1519
- "early_mean": 1.0455416592559375,
1520
- "goal_display": "goal \u2191",
1521
- "improvement_pct": 112.05988926255111,
1522
- "improvement_pct_clipped": 100.0,
1523
- "improvement_pct_clipped_display": "+100.00%",
1524
- "improvement_pct_display": "+112.06%",
1525
- "last": 0.9839304089546204,
1526
- "late_mean": 2.2171744848119803,
1527
- "mid_mean": 2.0036371215919537,
1528
- "pressure": "pressure_up",
1529
- "pressure_arrow": "\u2197",
1530
- "pressure_display": "goal \u2191 | \u2197 +112.06% improving",
1531
- "pressure_score": 1.0,
1532
- "trend_label": "improving"
1533
- },
1534
- "structure_retrieval_loss": {
1535
- "desired_direction": "lower",
1536
- "early_mean": 10.237479978903181,
1537
- "goal_display": "goal \u2193",
1538
- "improvement_pct": 10.094066619063353,
1539
- "improvement_pct_display": "+10.09%",
1540
- "last": 10.630162239074707,
1541
- "late_mean": 9.204101929719421,
1542
- "mid_mean": 9.41523380775672,
1543
- "pressure": "pressure_up",
1544
- "pressure_arrow": "\u2197",
1545
- "pressure_display": "goal \u2193 | \u2197 +10.09% improving",
1546
- "pressure_score": 1.0,
1547
- "trend_label": "improving"
1548
- },
1549
- "structure_target_rank_mean": {
1550
- "desired_direction": "lower",
1551
- "early_mean": 351.84337743858384,
1552
- "goal_display": "goal \u2193",
1553
- "improvement_pct": 58.80171764880722,
1554
- "improvement_pct_display": "+58.80%",
1555
- "last": 314.703125,
1556
- "late_mean": 144.9534280711207,
1557
- "mid_mean": 176.16389315390174,
1558
- "pressure": "pressure_up",
1559
- "pressure_arrow": "\u2197",
1560
- "pressure_display": "goal \u2193 | \u2197 +58.80% improving",
1561
- "pressure_score": 1.0,
1562
- "trend_label": "improving"
1563
- },
1564
- "structure_top1_top2_gap_mean": {
1565
- "desired_direction": "higher",
1566
- "early_mean": 0.09793567106213873,
1567
- "goal_display": "goal \u2191",
1568
- "improvement_pct": 59.221149173532794,
1569
- "improvement_pct_display": "+59.22%",
1570
- "last": 0.0986328125,
1571
- "late_mean": 0.1559343009159483,
1572
- "mid_mean": 0.12284365968208093,
1573
- "pressure": "pressure_up",
1574
- "pressure_arrow": "\u2197",
1575
- "pressure_display": "goal \u2191 | \u2197 +59.22% improving",
1576
- "pressure_score": 1.0,
1577
- "trend_label": "improving"
1578
- },
1579
- "structure_top1_top2_gap_norm_mean": {
1580
- "desired_direction": "higher",
1581
- "early_mean": 0.12215662799301864,
1582
- "goal_display": "goal \u2191",
1583
- "improvement_pct": -35.653274040957065,
1584
- "improvement_pct_display": "-35.65%",
1585
- "last": 0.10155132412910461,
1586
- "late_mean": 0.07860379065547524,
1587
- "mid_mean": 0.07032911504236604,
1588
- "pressure": "pressure_down",
1589
- "pressure_arrow": "\u2198",
1590
- "pressure_display": "goal \u2191 | \u2198 -35.65% worsening",
1591
- "pressure_score": -1.0,
1592
- "trend_label": "worsening"
1593
- },
1594
- "structure_top_negative_logit_mean": {
1595
- "desired_direction": "lower",
1596
- "early_mean": 7.262102601156069,
1597
- "goal_display": "goal \u2193",
1598
- "improvement_pct": -39.724147080005764,
1599
- "improvement_pct_display": "-39.72%",
1600
- "last": 10.1875,
1601
- "late_mean": 10.14691091954023,
1602
- "mid_mean": 10.490606936416185,
1603
- "pressure": "pressure_down",
1604
- "pressure_arrow": "\u2198",
1605
- "pressure_display": "goal \u2193 | \u2198 -39.72% worsening",
1606
- "pressure_score": -1.0,
1607
- "trend_label": "worsening"
1608
- },
1609
- "structure_uncertain_fraction": {
1610
- "desired_direction": "lower",
1611
- "early_mean": 0.924663565751445,
1612
- "goal_display": "goal \u2193",
1613
- "improvement_pct": -6.108024336610137,
1614
- "improvement_pct_display": "-6.11%",
1615
- "last": 0.970703125,
1616
- "late_mean": 0.9811422413793104,
1617
- "mid_mean": 0.984747561416185,
1618
- "pressure": "pressure_down",
1619
- "pressure_arrow": "\u2198",
1620
- "pressure_display": "goal \u2193 | \u2198 -6.11% worsening",
1621
- "pressure_score": -1.0,
1622
- "trend_label": "worsening"
1623
- },
1624
- "train_loss": {
1625
- "desired_direction": "lower",
1626
- "early_mean": 6.340343519442343,
1627
- "goal_display": "goal \u2193",
1628
- "improvement_pct": 10.566866163080938,
1629
- "improvement_pct_display": "+10.57%",
1630
- "last": 6.491608619689941,
1631
- "late_mean": 5.670367905463295,
1632
- "mid_mean": 5.795929590401622,
1633
- "pressure": "pressure_up",
1634
- "pressure_arrow": "\u2197",
1635
- "pressure_display": "goal \u2193 | \u2197 +10.57% improving",
1636
- "pressure_score": 1.0,
1637
- "trend_label": "improving"
1638
- },
1639
- "train_loss_ema": {
1640
- "desired_direction": "lower",
1641
- "early_mean": 6.265581717362126,
1642
- "goal_display": "goal \u2193",
1643
- "improvement_pct": 10.455707205061195,
1644
- "improvement_pct_display": "+10.46%",
1645
- "last": 6.519052214060582,
1646
- "late_mean": 5.610470838300897,
1647
- "mid_mean": 5.8371378655061745,
1648
- "pressure": "pressure_up",
1649
- "pressure_arrow": "\u2197",
1650
- "pressure_display": "goal \u2193 | \u2197 +10.46% improving",
1651
- "pressure_score": 1.0,
1652
- "trend_label": "improving"
1653
- },
1654
- "val_hit_at_1": {
1655
- "desired_direction": "higher",
1656
- "early_mean": 0.0079345703125,
1657
- "goal_display": "goal \u2191",
1658
- "improvement_pct": 207.78846153846155,
1659
- "improvement_pct_clipped": 100.0,
1660
- "improvement_pct_clipped_display": "+100.00%",
1661
- "improvement_pct_display": "+207.79%",
1662
- "last": 0.0282135009765625,
1663
- "late_mean": 0.02442169189453125,
1664
- "mid_mean": 0.01372528076171875,
1665
- "pressure": "pressure_none",
1666
- "pressure_arrow": "\u2192",
1667
- "pressure_display": "goal \u2191 | \u2192 +207.79% flat",
1668
- "trend_label": "flat"
1669
- },
1670
- "val_hit_at_20": {
1671
- "desired_direction": "higher",
1672
- "early_mean": 0.08158111572265625,
1673
- "goal_display": "goal \u2191",
1674
- "improvement_pct": 76.67165435331526,
1675
- "improvement_pct_display": "+76.67%",
1676
- "last": 0.15270233154296875,
1677
- "late_mean": 0.14413070678710938,
1678
- "mid_mean": 0.094146728515625,
1679
- "pressure": "pressure_up",
1680
- "pressure_arrow": "\u2197",
1681
- "pressure_display": "goal \u2191 | \u2197 +76.67% improving",
1682
- "pressure_score": 1.0,
1683
- "trend_label": "improving"
1684
- },
1685
- "val_hit_at_5": {
1686
- "desired_direction": "higher",
1687
- "early_mean": 0.0288543701171875,
1688
- "goal_display": "goal \u2191",
1689
- "improvement_pct": 134.8492860920148,
1690
- "improvement_pct_clipped": 100.0,
1691
- "improvement_pct_clipped_display": "+100.00%",
1692
- "improvement_pct_display": "+134.85%",
1693
- "last": 0.0726776123046875,
1694
- "late_mean": 0.0677642822265625,
1695
- "mid_mean": 0.0425567626953125,
1696
- "pressure": "pressure_up",
1697
- "pressure_arrow": "\u2197",
1698
- "pressure_display": "goal \u2191 | \u2197 +134.85% improving",
1699
- "pressure_score": 1.0,
1700
- "trend_label": "improving"
1701
- },
1702
- "val_loss": {
1703
- "desired_direction": "lower",
1704
- "early_mean": 1.2876316868363775,
1705
- "goal_display": "goal \u2193",
1706
- "improvement_pct": -55.82459156154955,
1707
- "improvement_pct_display": "-55.82%",
1708
- "last": 6.646750174145564,
1709
- "late_mean": 2.006446816829876,
1710
- "mid_mean": 2.20697861268016,
1711
- "pressure": "pressure_down",
1712
- "pressure_arrow": "\u2198",
1713
- "pressure_display": "goal \u2193 | \u2198 -55.82% worsening",
1714
- "pressure_score": -1.0,
1715
- "trend_label": "worsening"
1716
- },
1717
- "val_ssl_loss": {
1718
- "desired_direction": "lower",
1719
- "early_mean": 1.0849772497183745,
1720
- "goal_display": "goal \u2193",
1721
- "improvement_pct": 2.3192742421198114,
1722
- "improvement_pct_display": "+2.32%",
1723
- "last": 1.0397093277424574,
1724
- "late_mean": 1.0598136518327963,
1725
- "mid_mean": 1.0747967428483425,
1726
- "pressure": "pressure_none",
1727
- "pressure_arrow": "\u2192",
1728
- "pressure_display": "goal \u2193 | \u2192 +2.32% flat",
1729
- "trend_label": "flat"
1730
- },
1731
- "val_structure_bce_loss": {
1732
- "desired_direction": "lower",
1733
- "early_mean": 0.0771060927848642,
1734
- "goal_display": "goal \u2193",
1735
- "improvement_pct": 12.199713989530546,
1736
- "improvement_pct_display": "+12.20%",
1737
- "last": 0.06532714269997086,
1738
- "late_mean": 0.06769936999660872,
1739
- "mid_mean": 0.07029345531468391,
1740
- "pressure": "pressure_up",
1741
- "pressure_arrow": "\u2197",
1742
- "pressure_display": "goal \u2193 | \u2197 +12.20% improving",
1743
- "pressure_score": 1.0,
1744
- "trend_label": "improving"
1745
- },
1746
- "val_structure_confidence_separation": {
1747
- "desired_direction": "higher",
1748
- "early_mean": -0.00795668972114072,
1749
- "goal_display": "goal \u2191",
1750
- "improvement_pct": -204.85499246505236,
1751
- "improvement_pct_clipped": -100.0,
1752
- "improvement_pct_clipped_display": "-100.00%",
1753
- "improvement_pct_display": "-204.85%",
1754
- "last": -0.027957430157584895,
1755
- "late_mean": -0.024256365849851136,
1756
- "mid_mean": -0.01309866098972634,
1757
- "pressure": "pressure_down",
1758
- "pressure_arrow": "\u2198",
1759
- "pressure_display": "goal \u2191 | \u2198 -204.85% worsening",
1760
- "pressure_score": -1.0,
1761
- "trend_label": "worsening"
1762
- },
1763
- "val_structure_correct_logit_mean": {
1764
- "desired_direction": "higher",
1765
- "early_mean": 8.0311279296875,
1766
- "goal_display": "goal \u2191",
1767
- "improvement_pct": 16.44145855816145,
1768
- "improvement_pct_display": "+16.44%",
1769
- "last": 9.49462890625,
1770
- "late_mean": 9.3515625,
1771
- "mid_mean": 8.441162109375,
1772
- "pressure": "pressure_up",
1773
- "pressure_arrow": "\u2197",
1774
- "pressure_display": "goal \u2191 | \u2197 +16.44% improving",
1775
- "pressure_score": 1.0,
1776
- "trend_label": "improving"
1777
- },
1778
- "val_structure_fingerprint_cosine": {
1779
- "desired_direction": "higher",
1780
- "early_mean": 0.4147872725734487,
1781
- "goal_display": "goal \u2191",
1782
- "improvement_pct": 0.17175282510408285,
1783
- "improvement_pct_display": "+0.17%",
1784
- "last": 0.4255251376889646,
1785
- "late_mean": 0.4154996814322658,
1786
- "mid_mean": 0.4204998221830465,
1787
- "pressure": "pressure_none",
1788
- "pressure_arrow": "\u2192",
1789
- "pressure_display": "goal \u2191 | \u2192 +0.17% flat",
1790
- "trend_label": "flat"
1791
- },
1792
- "val_structure_logit_margin_mean": {
1793
- "desired_direction": "higher",
1794
- "early_mean": -1.194091796875,
1795
- "goal_display": "goal \u2191",
1796
- "improvement_pct": -13.669239419341647,
1797
- "improvement_pct_display": "-13.67%",
1798
- "last": -1.221923828125,
1799
- "late_mean": -1.3573150634765625,
1800
- "mid_mean": -2.0707931518554688,
1801
- "pressure": "pressure_down",
1802
- "pressure_arrow": "\u2198",
1803
- "pressure_display": "goal \u2191 | \u2198 -13.67% worsening",
1804
- "pressure_score": -1.0,
1805
- "trend_label": "worsening"
1806
- },
1807
- "val_structure_retrieval_logit_std": {
1808
- "desired_direction": "higher",
1809
- "early_mean": 1.2326001720502973,
1810
- "goal_display": "goal \u2191",
1811
- "improvement_pct": 102.32641409365677,
1812
- "improvement_pct_clipped": 100.0,
1813
- "improvement_pct_clipped_display": "+100.00%",
1814
- "improvement_pct_display": "+102.33%",
1815
- "last": 2.6622845763340592,
1816
- "late_mean": 2.49387572822161,
1817
- "mid_mean": 2.022283688886091,
1818
- "pressure": "pressure_up",
1819
- "pressure_arrow": "\u2197",
1820
- "pressure_display": "goal \u2191 | \u2197 +102.33% improving",
1821
- "pressure_score": 1.0,
1822
- "trend_label": "improving"
1823
- },
1824
- "val_structure_retrieval_loss": {
1825
- "desired_direction": "lower",
1826
- "early_mean": 11.562767315655947,
1827
- "goal_display": "goal \u2193",
1828
- "improvement_pct": 4.864921250164783,
1829
- "improvement_pct_display": "+4.86%",
1830
- "last": 10.882395941764116,
1831
- "late_mean": 11.000247791409492,
1832
- "mid_mean": 12.150514367967844,
1833
- "pressure": "pressure_none",
1834
- "pressure_arrow": "\u2192",
1835
- "pressure_display": "goal \u2193 | \u2192 +4.86% flat",
1836
- "trend_label": "flat"
1837
- },
1838
- "val_structure_target_rank_mean": {
1839
- "desired_direction": "lower",
1840
- "early_mean": 760.7540435791016,
1841
- "goal_display": "goal \u2193",
1842
- "improvement_pct": 45.44775026271755,
1843
- "improvement_pct_display": "+45.45%",
1844
- "last": 379.8781280517578,
1845
- "late_mean": 415.0084457397461,
1846
- "mid_mean": 683.3385162353516,
1847
- "pressure": "pressure_up",
1848
- "pressure_arrow": "\u2197",
1849
- "pressure_display": "goal \u2193 | \u2197 +45.45% improving",
1850
- "pressure_score": 1.0,
1851
- "trend_label": "improving"
1852
- },
1853
- "val_structure_top1_top2_gap_mean": {
1854
- "desired_direction": "higher",
1855
- "early_mean": 0.07839679718017578,
1856
- "goal_display": "goal \u2191",
1857
- "improvement_pct": 54.90785232041847,
1858
- "improvement_pct_display": "+54.91%",
1859
- "last": 0.11855697631835938,
1860
- "late_mean": 0.12144279479980469,
1861
- "mid_mean": 0.1310901641845703,
1862
- "pressure": "pressure_up",
1863
- "pressure_arrow": "\u2197",
1864
- "pressure_display": "goal \u2191 | \u2197 +54.91% improving",
1865
- "pressure_score": 1.0,
1866
- "trend_label": "improving"
1867
- },
1868
- "val_structure_top1_top2_gap_norm_mean": {
1869
- "desired_direction": "higher",
1870
- "early_mean": 0.06950851557485294,
1871
- "goal_display": "goal \u2191",
1872
- "improvement_pct": -16.826381575968767,
1873
- "improvement_pct_display": "-16.83%",
1874
- "last": 0.05411380449368153,
1875
- "late_mean": 0.0578127475164365,
1876
- "mid_mean": 0.07577372609375743,
1877
- "pressure": "pressure_down",
1878
- "pressure_arrow": "\u2198",
1879
- "pressure_display": "goal \u2191 | \u2198 -16.83% worsening",
1880
- "pressure_score": -1.0,
1881
- "trend_label": "worsening"
1882
- },
1883
- "val_structure_top_negative_logit_mean": {
1884
- "desired_direction": "lower",
1885
- "early_mean": 9.2255859375,
1886
- "goal_display": "goal \u2193",
1887
- "improvement_pct": -16.07653223245475,
1888
- "improvement_pct_display": "-16.08%",
1889
- "last": 10.714599609375,
1890
- "late_mean": 10.708740234375,
1891
- "mid_mean": 10.51171875,
1892
- "pressure": "pressure_down",
1893
- "pressure_arrow": "\u2198",
1894
- "pressure_display": "goal \u2193 | \u2198 -16.08% worsening",
1895
- "pressure_score": -1.0,
1896
- "trend_label": "worsening"
1897
- },
1898
- "val_structure_uncertain_fraction": {
1899
- "desired_direction": "lower",
1900
- "early_mean": 0.9941177368164062,
1901
- "goal_display": "goal \u2193",
1902
- "improvement_pct": -0.03261678728482514,
1903
- "improvement_pct_display": "-0.03%",
1904
- "last": 0.9922027587890625,
1905
- "late_mean": 0.9944419860839844,
1906
- "mid_mean": 0.9762382507324219,
1907
- "pressure": "pressure_none",
1908
- "pressure_arrow": "\u2192",
1909
- "pressure_display": "goal \u2193 | \u2192 -0.03% flat",
1910
- "trend_label": "flat"
1911
- },
1912
- "weighted_regularizer_to_contrastive_ratio": {
1913
- "desired_direction": "lower",
1914
- "early_mean": 0.0667222202939108,
1915
- "goal_display": "goal \u2193",
1916
- "improvement_pct": 54.60656419810926,
1917
- "improvement_pct_display": "+54.61%",
1918
- "last": 0.028996589606316913,
1919
- "late_mean": 0.03028750823471251,
1920
- "mid_mean": 0.0329437448262181,
1921
- "pressure": "pressure_up",
1922
- "pressure_arrow": "\u2197",
1923
- "pressure_display": "goal \u2193 | \u2197 +54.61% improving",
1924
- "pressure_score": 1.0,
1925
- "trend_label": "improving"
1926
- }
1927
- },
1928
- "metrics": {
1929
- "backbone_lr": 3.886130904636371e-06,
1930
- "checkpoint_path": "/home/ubuntu/artifacts/nexa_mol/final_v3_structure_alignment/v26_r1/current_checkpoint.pt",
1931
- "checkpoint_reloaded": 1.0,
1932
- "contrastive_loss": 0.5768923759460449,
1933
- "covariance_loss": 10.012618064880371,
1934
- "covariance_to_contrastive_ratio": 17.356128252623712,
1935
- "covariance_weight": 0.0015,
1936
- "dataloader_time_sec": 0.00035174899676349014,
1937
- "dataloader_wait_pct_300s": 0.0382592069912683,
1938
- "dataloader_wait_pct_60s": 0.0961140629935623,
1939
- "dataloader_wait_pct_900s": 0.066640439237091,
1940
- "dataloader_wait_pct_run": 0.06717802801040498,
1941
- "different_inchikey_mean_cosine": 0.004679911238535274,
1942
- "distributed_rank": 0.0,
1943
- "distributed_world_size": 1.0,
1944
- "effective_batch_size": 512.0,
1945
- "effective_hard_negative_scale": 1.0,
1946
- "effective_retrieval_weight": 0.6,
1947
- "effective_structure_bce_weight": 1.0,
1948
- "embedding_mean_norm": 1.0,
1949
- "embedding_offdiag_mean_cosine": 0.009513536468148232,
1950
- "embedding_std": 0.07216806709766388,
1951
- "global_batch_size": 512.0,
1952
- "gpu_active_fraction": 1.0,
1953
- "gpu_count_observed": 2.0,
1954
- "gpu_max_memory_gb": 13.279157161712646,
1955
- "gpu_mem_used_mean_gb": 14.1943359375,
1956
- "gpu_mem_util_mean_pct": 14.848754175733243,
1957
- "gpu_memory_stable": true,
1958
- "gpu_memory_utilization": 0.13982381154325935,
1959
- "gpu_snapshot_available": 1.0,
1960
- "gpu_util_max_pct": 54.0,
1961
- "gpu_util_mean_pct": 36.0,
1962
- "gpu_util_min_pct": 18.0,
1963
- "grad_norm": 1.7659728527069092,
1964
- "holdout_full_coverage": 0.0,
1965
- "local_batch_size": 512.0,
1966
- "lr": 3.886130904636371e-06,
1967
- "mfu_estimate": 0.06267708747552383,
1968
- "msms_objective": "hybrid",
1969
- "optimizer_step": 1.0,
1970
- "regularizer_ramp": 1.0,
1971
- "resume_checkpoint_path": "/home/ubuntu/artifacts/nexa_mol/final_v3_structure_alignment/v26_r1/current_checkpoint.pt",
1972
- "resume_start_step": 81002.0,
1973
- "resumed_from_checkpoint": 1.0,
1974
- "retrieval_head_lr": 1.9430654523181854e-05,
1975
- "same_inchikey_mean_cosine": 0.16267980930137343,
1976
- "samples_per_sec": 1399.0203442084614,
1977
- "samples_per_sec_300s": 1547.033197547462,
1978
- "samples_per_sec_60s": 1399.0203442084614,
1979
- "samples_per_sec_900s": 1512.7885250414204,
1980
- "samples_per_sec_run_mean": 1533.0231795943853,
1981
- "step_time_cv_300s": 0.06743440395418321,
1982
- "step_time_cv_60s": 0.0,
1983
- "step_time_cv_900s": 0.09218780075615579,
1984
- "step_time_sec": 0.3659703749981418,
1985
- "structure_bce_locked": 0.0,
1986
- "structure_bce_loss": 0.08383000642061234,
1987
- "structure_candidate_count": 2126.0,
1988
- "structure_clear_fraction": 0.0,
1989
- "structure_clear_hit_at_1": 0.0,
1990
- "structure_close_fraction": 0.029296875,
1991
- "structure_close_hit_at_1": 0.0,
1992
- "structure_confidence_bucket_score_mean": 0.10155132412910461,
1993
- "structure_confidence_bucket_score_mode": "normalized_gap",
1994
- "structure_confidence_candidate_count": 2126.0,
1995
- "structure_confidence_clear_threshold": 1.0,
1996
- "structure_confidence_close_threshold": 0.35,
1997
- "structure_confidence_eval_key_mode": "target_identity",
1998
- "structure_confidence_separation": -0.0040241447277367115,
1999
- "structure_correct_logit_mean": 9.1875,
2000
- "structure_fingerprint_cosine": 0.46021854877471924,
2001
- "structure_hard_negative_bonus_applied": 1.0,
2002
- "structure_hard_negative_bonus_mean": 0.060302734375,
2003
- "structure_hard_negative_scale": 1.0,
2004
- "structure_head_lr": 1.9430654523181854e-05,
2005
- "structure_hit_at_1": 0.00390625,
2006
- "structure_hit_at_20": 0.1171875,
2007
- "structure_hit_at_5": 0.029296875,
2008
- "structure_local_ce_loss": 3.545562744140625,
2009
- "structure_local_ce_loss_weight": 0.4,
2010
- "structure_local_rerank_loss": 0.0,
2011
- "structure_local_rerank_loss_weight": 0.0,
2012
- "structure_local_rerank_score_scale": 1.0,
2013
- "structure_logit_margin_mean": -1.0078125,
2014
- "structure_margin_loss": 0.0,
2015
- "structure_margin_loss_weight": 0.0,
2016
- "structure_missing_formula_fraction": 0.0,
2017
- "structure_missing_inchikey_fraction": 0.0,
2018
- "structure_pairwise_logistic_loss": 0.0,
2019
- "structure_pairwise_logistic_loss_weight": 0.0,
2020
- "structure_positive_count_mean": 1.0,
2021
- "structure_post_label_candidate_count": 2126.0,
2022
- "structure_post_precursor_candidate_count": 2128.0,
2023
- "structure_prefilter_candidate_count": 2128.0,
2024
- "structure_retrieval_logit_std": 0.9839304089546204,
2025
- "structure_retrieval_loss": 10.630162239074707,
2026
- "structure_retrieval_scorer": "projected_dot",
2027
- "structure_retrieval_target_mode": "sample",
2028
- "structure_skipped_query_fraction": 0.0,
2029
- "structure_soft_target_exact_mix": 0.4,
2030
- "structure_soft_target_loss": 7.523618221282959,
2031
- "structure_soft_target_loss_weight": 0.3,
2032
- "structure_target_backend": "rdkit_morgan",
2033
- "structure_target_equivalent_count_mean": 1.0,
2034
- "structure_target_identity_collision_count": 0.0,
2035
- "structure_target_rank_mean": 314.703125,
2036
- "structure_to_ssl_ratio": 217.7124787233957,
2037
- "structure_top1_top2_gap_mean": 0.0986328125,
2038
- "structure_top1_top2_gap_norm_mean": 0.10155132412910461,
2039
- "structure_top_negative_logit_mean": 10.1875,
2040
- "structure_uncertain_fraction": 0.970703125,
2041
- "structure_uncertain_hit_at_1": 0.0040241447277367115,
2042
- "structure_valid_query_fraction": 1.0,
2043
- "test_expected_shard_count": 2.0,
2044
- "test_full_coverage": 0.0,
2045
- "test_observed_shard_count": 0.0,
2046
- "train_loss": 6.491608619689941,
2047
- "train_loss_ema": 6.519052214060582,
2048
- "train_retrieval_bank_size": 4096.0,
2049
- "val_deep_eval_single_view": 0.0,
2050
- "val_deep_eval_structure_only": 0.0,
2051
- "val_effective_structure_bce_weight": 1.0,
2052
- "val_eval_loader_mode": "stream",
2053
- "val_eval_mode": "deep",
2054
- "val_expected_shard_count": 2.0,
2055
- "val_full_coverage": 1.0,
2056
- "val_hit_at_1": 0.0282135009765625,
2057
- "val_hit_at_20": 0.15270233154296875,
2058
- "val_hit_at_5": 0.0726776123046875,
2059
- "val_loss": 6.646750174145564,
2060
- "val_observed_eval_batches": 256.0,
2061
- "val_observed_shard_count": 2.0,
2062
- "val_ssl_loss": 1.0397093277424574,
2063
- "val_structure_bce_loss": 0.06532714269997086,
2064
- "val_structure_candidate_count": 4119.69140625,
2065
- "val_structure_clear_fraction": 0.0,
2066
- "val_structure_clear_hit_at_1": 0.0,
2067
- "val_structure_close_fraction": 0.0077972412109375,
2068
- "val_structure_close_hit_at_1": 0.014835291571216658,
2069
- "val_structure_confidence_candidate_count": 4096.0,
2070
- "val_structure_confidence_separation": -0.027957430157584895,
2071
- "val_structure_correct_logit_mean": 9.49462890625,
2072
- "val_structure_fingerprint_cosine": 0.4255251376889646,
2073
- "val_structure_logit_margin_mean": -1.221923828125,
2074
- "val_structure_missing_formula_fraction": 0.0,
2075
- "val_structure_missing_inchikey_fraction": 0.0,
2076
- "val_structure_retrieval_logit_std": 2.6622845763340592,
2077
- "val_structure_retrieval_loss": 10.882395941764116,
2078
- "val_structure_target_equivalent_count_mean": 1.0,
2079
- "val_structure_target_identity_collision_count": 23.69140625,
2080
- "val_structure_target_rank_mean": 379.8781280517578,
2081
- "val_structure_top1_top2_gap_mean": 0.11855697631835938,
2082
- "val_structure_top1_top2_gap_norm_mean": 0.05411380449368153,
2083
- "val_structure_top_negative_logit_mean": 10.714599609375,
2084
- "val_structure_uncertain_fraction": 0.9922027587890625,
2085
- "val_structure_uncertain_hit_at_1": 0.027957430157584895,
2086
- "variance_loss": 0.00213623046875,
2087
- "variance_weight": 0.8,
2088
- "weighted_covariance_loss": 0.015018927097320557,
2089
- "weighted_regularizer_to_contrastive_ratio": 0.028996589606316913,
2090
- "weighted_ssl_loss": 0.02968101501464844,
2091
- "weighted_structure_bce_loss": 0.08383000642061234,
2092
- "weighted_structure_retrieval_loss": 6.378097343444824,
2093
- "weighted_variance_loss": 0.001708984375
2094
- },
2095
- "primary_metric_pressure_summary": {
2096
- "average_improvement_pct": -14.247321653690681,
2097
- "metric_count": 12,
2098
- "overall_arrow": "\u2197",
2099
- "overall_pressure": "pressure_up",
2100
- "pressure_down_count": 4,
2101
- "pressure_none_count": 3,
2102
- "pressure_up_count": 5,
2103
- "pressure_up_fraction": 0.4166666666666667,
2104
- "weighted_improvement_pct": -4.446275812252011,
2105
- "weighted_pressure_score": 0.1702127659574468
2106
- },
2107
- "primary_metric_pressure_summary_display": {
2108
- "average_improvement_pct": -14.247321653690681,
2109
- "average_improvement_pct_display": "-14.25%",
2110
- "metric_count": 12,
2111
- "overall_arrow": "\u2197",
2112
- "overall_display": "\u2197 improving (-4.45% weighted)",
2113
- "overall_label": "improving",
2114
- "overall_pressure": "pressure_up",
2115
- "pressure_down_count": 4,
2116
- "pressure_none_count": 3,
2117
- "pressure_up_count": 5,
2118
- "pressure_up_fraction": 0.4166666666666667,
2119
- "pressure_up_fraction_display": "+41.67%",
2120
- "weighted_improvement_pct": -4.446275812252011,
2121
- "weighted_improvement_pct_display": "-4.45%",
2122
- "weighted_pressure_score": 0.1702127659574468
2123
- },
2124
- "primary_metric_pressures": {
2125
- "contrastive_loss": {
2126
- "desired_direction": "lower",
2127
- "early_mean": 1.409792113166324,
2128
- "improvement_pct": -1.6400841264380104,
2129
- "improvement_pct_clipped": -1.6400841264380104,
2130
- "last": 0.5768923759460449,
2131
- "late_mean": 1.43291388983014,
2132
- "mid_mean": 1.3598130204084982,
2133
- "pressure": "pressure_none",
2134
- "pressure_arrow": "\u2192",
2135
- "pressure_score": 0.0
2136
- },
2137
- "grad_norm": {
2138
- "desired_direction": "stable",
2139
- "early_mean": 4.638080189338309,
2140
- "improvement_pct": -100.0,
2141
- "improvement_pct_clipped": -100.0,
2142
- "last": 1.7659728527069092,
2143
- "late_mean": 6.072961742165445,
2144
- "mid_mean": 4.979553528603791,
2145
- "pressure": "pressure_down",
2146
- "pressure_arrow": "\u2198",
2147
- "pressure_score": -1.0
2148
- },
2149
- "samples_per_sec": {
2150
- "desired_direction": "higher",
2151
- "early_mean": 1575.5664566260843,
2152
- "improvement_pct": -2.8825714693532967,
2153
- "improvement_pct_clipped": -2.8825714693532967,
2154
- "last": 1399.0203442084614,
2155
- "late_mean": 1530.1496274666802,
2156
- "mid_mean": 1531.3735887168505,
2157
- "pressure": "pressure_down",
2158
- "pressure_arrow": "\u2198",
2159
- "pressure_score": -1.0
2160
- },
2161
- "structure_bce_loss": {
2162
- "desired_direction": "lower",
2163
- "early_mean": 0.12293951650489272,
2164
- "improvement_pct": 39.749156913940595,
2165
- "improvement_pct_clipped": 39.749156913940595,
2166
- "last": 0.08383000642061234,
2167
- "late_mean": 0.07407209518012302,
2168
- "mid_mean": 0.07652380578004556,
2169
- "pressure": "pressure_up",
2170
- "pressure_arrow": "\u2197",
2171
- "pressure_score": 1.0
2172
- },
2173
- "train_loss": {
2174
- "desired_direction": "lower",
2175
- "early_mean": 6.340343519442343,
2176
- "improvement_pct": 10.566866163080938,
2177
- "improvement_pct_clipped": 10.566866163080938,
2178
- "last": 6.491608619689941,
2179
- "late_mean": 5.670367905463295,
2180
- "mid_mean": 5.795929590401622,
2181
- "pressure": "pressure_up",
2182
- "pressure_arrow": "\u2197",
2183
- "pressure_score": 1.0
2184
- },
2185
- "val_hit_at_20": {
2186
- "desired_direction": "higher",
2187
- "early_mean": 0.08158111572265625,
2188
- "improvement_pct": 76.67165435331526,
2189
- "improvement_pct_clipped": 76.67165435331526,
2190
- "last": 0.15270233154296875,
2191
- "late_mean": 0.14413070678710938,
2192
- "mid_mean": 0.094146728515625,
2193
- "pressure": "pressure_up",
2194
- "pressure_arrow": "\u2197",
2195
- "pressure_score": 1.0
2196
- },
2197
- "val_loss": {
2198
- "desired_direction": "lower",
2199
- "early_mean": 1.2876316868363775,
2200
- "improvement_pct": -55.82459156154955,
2201
- "improvement_pct_clipped": -55.82459156154955,
2202
- "last": 6.646750174145564,
2203
- "late_mean": 2.006446816829876,
2204
- "mid_mean": 2.20697861268016,
2205
- "pressure": "pressure_down",
2206
- "pressure_arrow": "\u2198",
2207
- "pressure_score": -1.0
2208
- },
2209
- "val_structure_bce_loss": {
2210
- "desired_direction": "lower",
2211
- "early_mean": 0.0771060927848642,
2212
- "improvement_pct": 12.199713989530546,
2213
- "improvement_pct_clipped": 12.199713989530546,
2214
- "last": 0.06532714269997086,
2215
- "late_mean": 0.06769936999660872,
2216
- "mid_mean": 0.07029345531468391,
2217
- "pressure": "pressure_up",
2218
- "pressure_arrow": "\u2197",
2219
- "pressure_score": 1.0
2220
- },
2221
- "val_structure_confidence_separation": {
2222
- "desired_direction": "higher",
2223
- "early_mean": -0.00795668972114072,
2224
- "improvement_pct": -204.85499246505236,
2225
- "improvement_pct_clipped": -100.0,
2226
- "last": -0.027957430157584895,
2227
- "late_mean": -0.024256365849851136,
2228
- "mid_mean": -0.01309866098972634,
2229
- "pressure": "pressure_down",
2230
- "pressure_arrow": "\u2198",
2231
- "pressure_score": -1.0
2232
- },
2233
- "val_structure_fingerprint_cosine": {
2234
- "desired_direction": "higher",
2235
- "early_mean": 0.4147872725734487,
2236
- "improvement_pct": 0.17175282510408285,
2237
- "improvement_pct_clipped": 0.17175282510408285,
2238
- "last": 0.4255251376889646,
2239
- "late_mean": 0.4154996814322658,
2240
- "mid_mean": 0.4204998221830465,
2241
- "pressure": "pressure_none",
2242
- "pressure_arrow": "\u2192",
2243
- "pressure_score": 0.0
2244
- },
2245
- "val_structure_top1_top2_gap_mean": {
2246
- "desired_direction": "higher",
2247
- "early_mean": 0.07839679718017578,
2248
- "improvement_pct": 54.90785232041847,
2249
- "improvement_pct_clipped": 54.90785232041847,
2250
- "last": 0.11855697631835938,
2251
- "late_mean": 0.12144279479980469,
2252
- "mid_mean": 0.1310901641845703,
2253
- "pressure": "pressure_up",
2254
- "pressure_arrow": "\u2197",
2255
- "pressure_score": 1.0
2256
- },
2257
- "val_structure_uncertain_fraction": {
2258
- "desired_direction": "lower",
2259
- "early_mean": 0.9941177368164062,
2260
- "improvement_pct": -0.03261678728482514,
2261
- "improvement_pct_clipped": -0.03261678728482514,
2262
- "last": 0.9922027587890625,
2263
- "late_mean": 0.9944419860839844,
2264
- "mid_mean": 0.9762382507324219,
2265
- "pressure": "pressure_none",
2266
- "pressure_arrow": "\u2192",
2267
- "pressure_score": 0.0
2268
- }
2269
- },
2270
- "primary_metric_pressures_display": {
2271
- "contrastive_loss": {
2272
- "desired_direction": "lower",
2273
- "early_mean": 1.409792113166324,
2274
- "goal_display": "goal \u2193",
2275
- "improvement_pct": -1.6400841264380104,
2276
- "improvement_pct_display": "-1.64%",
2277
- "last": 0.5768923759460449,
2278
- "late_mean": 1.43291388983014,
2279
- "mid_mean": 1.3598130204084982,
2280
- "pressure": "pressure_none",
2281
- "pressure_arrow": "\u2192",
2282
- "pressure_display": "goal \u2193 | \u2192 -1.64% flat",
2283
- "trend_label": "flat"
2284
- },
2285
- "grad_norm": {
2286
- "desired_direction": "stable",
2287
- "early_mean": 4.638080189338309,
2288
- "goal_display": "goal \u2248",
2289
- "improvement_pct": -100.0,
2290
- "improvement_pct_display": "-100.00%",
2291
- "last": 1.7659728527069092,
2292
- "late_mean": 6.072961742165445,
2293
- "mid_mean": 4.979553528603791,
2294
- "pressure": "pressure_down",
2295
- "pressure_arrow": "\u2198",
2296
- "pressure_display": "goal \u2248 | \u2198 -100.00% worsening",
2297
- "pressure_score": -1.0,
2298
- "trend_label": "worsening"
2299
- },
2300
- "samples_per_sec": {
2301
- "desired_direction": "higher",
2302
- "early_mean": 1575.5664566260843,
2303
- "goal_display": "goal \u2191",
2304
- "improvement_pct": -2.8825714693532967,
2305
- "improvement_pct_display": "-2.88%",
2306
- "last": 1399.0203442084614,
2307
- "late_mean": 1530.1496274666802,
2308
- "mid_mean": 1531.3735887168505,
2309
- "pressure": "pressure_down",
2310
- "pressure_arrow": "\u2198",
2311
- "pressure_display": "goal \u2191 | \u2198 -2.88% worsening",
2312
- "pressure_score": -1.0,
2313
- "trend_label": "worsening"
2314
- },
2315
- "structure_bce_loss": {
2316
- "desired_direction": "lower",
2317
- "early_mean": 0.12293951650489272,
2318
- "goal_display": "goal \u2193",
2319
- "improvement_pct": 39.749156913940595,
2320
- "improvement_pct_display": "+39.75%",
2321
- "last": 0.08383000642061234,
2322
- "late_mean": 0.07407209518012302,
2323
- "mid_mean": 0.07652380578004556,
2324
- "pressure": "pressure_up",
2325
- "pressure_arrow": "\u2197",
2326
- "pressure_display": "goal \u2193 | \u2197 +39.75% improving",
2327
- "pressure_score": 1.0,
2328
- "trend_label": "improving"
2329
- },
2330
- "train_loss": {
2331
- "desired_direction": "lower",
2332
- "early_mean": 6.340343519442343,
2333
- "goal_display": "goal \u2193",
2334
- "improvement_pct": 10.566866163080938,
2335
- "improvement_pct_display": "+10.57%",
2336
- "last": 6.491608619689941,
2337
- "late_mean": 5.670367905463295,
2338
- "mid_mean": 5.795929590401622,
2339
- "pressure": "pressure_up",
2340
- "pressure_arrow": "\u2197",
2341
- "pressure_display": "goal \u2193 | \u2197 +10.57% improving",
2342
- "pressure_score": 1.0,
2343
- "trend_label": "improving"
2344
- },
2345
- "val_hit_at_20": {
2346
- "desired_direction": "higher",
2347
- "early_mean": 0.08158111572265625,
2348
- "goal_display": "goal \u2191",
2349
- "improvement_pct": 76.67165435331526,
2350
- "improvement_pct_display": "+76.67%",
2351
- "last": 0.15270233154296875,
2352
- "late_mean": 0.14413070678710938,
2353
- "mid_mean": 0.094146728515625,
2354
- "pressure": "pressure_up",
2355
- "pressure_arrow": "\u2197",
2356
- "pressure_display": "goal \u2191 | \u2197 +76.67% improving",
2357
- "pressure_score": 1.0,
2358
- "trend_label": "improving"
2359
- },
2360
- "val_loss": {
2361
- "desired_direction": "lower",
2362
- "early_mean": 1.2876316868363775,
2363
- "goal_display": "goal \u2193",
2364
- "improvement_pct": -55.82459156154955,
2365
- "improvement_pct_display": "-55.82%",
2366
- "last": 6.646750174145564,
2367
- "late_mean": 2.006446816829876,
2368
- "mid_mean": 2.20697861268016,
2369
- "pressure": "pressure_down",
2370
- "pressure_arrow": "\u2198",
2371
- "pressure_display": "goal \u2193 | \u2198 -55.82% worsening",
2372
- "pressure_score": -1.0,
2373
- "trend_label": "worsening"
2374
- },
2375
- "val_structure_bce_loss": {
2376
- "desired_direction": "lower",
2377
- "early_mean": 0.0771060927848642,
2378
- "goal_display": "goal \u2193",
2379
- "improvement_pct": 12.199713989530546,
2380
- "improvement_pct_display": "+12.20%",
2381
- "last": 0.06532714269997086,
2382
- "late_mean": 0.06769936999660872,
2383
- "mid_mean": 0.07029345531468391,
2384
- "pressure": "pressure_up",
2385
- "pressure_arrow": "\u2197",
2386
- "pressure_display": "goal \u2193 | \u2197 +12.20% improving",
2387
- "pressure_score": 1.0,
2388
- "trend_label": "improving"
2389
- },
2390
- "val_structure_confidence_separation": {
2391
- "desired_direction": "higher",
2392
- "early_mean": -0.00795668972114072,
2393
- "goal_display": "goal \u2191",
2394
- "improvement_pct": -204.85499246505236,
2395
- "improvement_pct_clipped": -100.0,
2396
- "improvement_pct_clipped_display": "-100.00%",
2397
- "improvement_pct_display": "-204.85%",
2398
- "last": -0.027957430157584895,
2399
- "late_mean": -0.024256365849851136,
2400
- "mid_mean": -0.01309866098972634,
2401
- "pressure": "pressure_down",
2402
- "pressure_arrow": "\u2198",
2403
- "pressure_display": "goal \u2191 | \u2198 -204.85% worsening",
2404
- "pressure_score": -1.0,
2405
- "trend_label": "worsening"
2406
- },
2407
- "val_structure_fingerprint_cosine": {
2408
- "desired_direction": "higher",
2409
- "early_mean": 0.4147872725734487,
2410
- "goal_display": "goal \u2191",
2411
- "improvement_pct": 0.17175282510408285,
2412
- "improvement_pct_display": "+0.17%",
2413
- "last": 0.4255251376889646,
2414
- "late_mean": 0.4154996814322658,
2415
- "mid_mean": 0.4204998221830465,
2416
- "pressure": "pressure_none",
2417
- "pressure_arrow": "\u2192",
2418
- "pressure_display": "goal \u2191 | \u2192 +0.17% flat",
2419
- "trend_label": "flat"
2420
- },
2421
- "val_structure_top1_top2_gap_mean": {
2422
- "desired_direction": "higher",
2423
- "early_mean": 0.07839679718017578,
2424
- "goal_display": "goal \u2191",
2425
- "improvement_pct": 54.90785232041847,
2426
- "improvement_pct_display": "+54.91%",
2427
- "last": 0.11855697631835938,
2428
- "late_mean": 0.12144279479980469,
2429
- "mid_mean": 0.1310901641845703,
2430
- "pressure": "pressure_up",
2431
- "pressure_arrow": "\u2197",
2432
- "pressure_display": "goal \u2191 | \u2197 +54.91% improving",
2433
- "pressure_score": 1.0,
2434
- "trend_label": "improving"
2435
- },
2436
- "val_structure_uncertain_fraction": {
2437
- "desired_direction": "lower",
2438
- "early_mean": 0.9941177368164062,
2439
- "goal_display": "goal \u2193",
2440
- "improvement_pct": -0.03261678728482514,
2441
- "improvement_pct_display": "-0.03%",
2442
- "last": 0.9922027587890625,
2443
- "late_mean": 0.9944419860839844,
2444
- "mid_mean": 0.9762382507324219,
2445
- "pressure": "pressure_none",
2446
- "pressure_arrow": "\u2192",
2447
- "pressure_display": "goal \u2193 | \u2192 -0.03% flat",
2448
- "trend_label": "flat"
2449
- }
2450
- },
2451
- "primary_metrics": {
2452
- "contrastive_loss": 0.5768923759460449,
2453
- "different_inchikey_mean_cosine": 0.004679911238535274,
2454
- "embedding_std": 0.07216806709766388,
2455
- "grad_norm": 1.7659728527069092,
2456
- "samples_per_sec": 1399.0203442084614,
2457
- "structure_bce_loss": 0.08383000642061234,
2458
- "train_loss": 6.491608619689941,
2459
- "val_hit_at_20": 0.15270233154296875,
2460
- "val_loss": 6.646750174145564,
2461
- "val_structure_bce_loss": 0.06532714269997086,
2462
- "val_structure_candidate_count": 4119.69140625,
2463
- "val_structure_clear_hit_at_1": 0.0,
2464
- "val_structure_confidence_separation": -0.027957430157584895,
2465
- "val_structure_fingerprint_cosine": 0.4255251376889646,
2466
- "val_structure_top1_top2_gap_mean": 0.11855697631835938,
2467
- "val_structure_uncertain_fraction": 0.9922027587890625
2468
- },
2469
- "run_name": "final_v3_structure_alignment_v26_r1",
2470
- "shard_counts": {
2471
- "test": 2,
2472
- "train": 4,
2473
- "val": 2
2474
- }
2475
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
metadata/eval_coverage.json DELETED
@@ -1,46 +0,0 @@
1
- {
2
- "created_at": "2026-04-13T21:36:17Z",
3
- "step": 91001,
4
- "run_step": 10000,
5
- "eval_mode": "deep",
6
- "eval_loader_mode": "stream",
7
- "eval_batch_limit": 256,
8
- "eval_batches_per_shard_limit": 0,
9
- "full_holdout_sweep": false,
10
- "configured_val_shard_count": 2,
11
- "configured_val_shards": [
12
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051433_00000.parquet",
13
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051454_00000.parquet"
14
- ],
15
- "configured_test_shard_count": 2,
16
- "configured_test_shards": [
17
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/test/shard_20260313_051433_00000.parquet",
18
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/test/shard_20260313_051454_00000.parquet"
19
- ],
20
- "observed_val_shard_count": 2,
21
- "observed_val_shards": [
22
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051433_00000.parquet",
23
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051454_00000.parquet"
24
- ],
25
- "missing_val_shards": [],
26
- "observed_test_shard_count": 0,
27
- "observed_test_shards": [],
28
- "missing_test_shards": [
29
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/test/shard_20260313_051433_00000.parquet",
30
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/test/shard_20260313_051454_00000.parquet"
31
- ],
32
- "unexpected_eval_shards": [],
33
- "observed_eval_batches": 256,
34
- "observed_eval_samples": 131072,
35
- "per_shard_batch_count": {
36
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051433_00000.parquet": 128,
37
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051454_00000.parquet": 128
38
- },
39
- "per_shard_sample_count": {
40
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051433_00000.parquet": 65536,
41
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051454_00000.parquet": 65536
42
- },
43
- "full_val_coverage": 1.0,
44
- "full_test_coverage": 0.0,
45
- "full_holdout_coverage": 0.0
46
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
metadata/fast_eval_surface.json DELETED
@@ -1,14 +0,0 @@
1
- {
2
- "created_at": "2026-04-13T20:20:58Z",
3
- "loader_mode": "stream",
4
- "configured_val_shard_count": 2,
5
- "configured_val_shards": [
6
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051433_00000.parquet",
7
- "/home/ubuntu/data/gems_v1_handoff_labeled_v26/shards/val/shard_20260313_051454_00000.parquet"
8
- ],
9
- "batches_per_shard": 0,
10
- "batch_size": 512,
11
- "row_count": 0,
12
- "per_shard_row_count": {},
13
- "per_shard_batch_count": {}
14
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
metadata/latest_checkpoint.txt DELETED
@@ -1 +0,0 @@
1
- /home/ubuntu/artifacts/nexa_mol/final_v3_structure_alignment/v26_r1/current_checkpoint.pt
 
 
metadata/latest_metrics.json DELETED
@@ -1,169 +0,0 @@
1
- {
2
- "backbone_lr": 3.886130904636371e-06,
3
- "checkpoint_path": "/home/ubuntu/artifacts/nexa_mol/final_v3_structure_alignment/v26_r1/current_checkpoint.pt",
4
- "checkpoint_reloaded": 1.0,
5
- "contrastive_loss": 0.5768923759460449,
6
- "covariance_loss": 10.012618064880371,
7
- "covariance_to_contrastive_ratio": 17.356128252623712,
8
- "covariance_weight": 0.0015,
9
- "dataloader_time_sec": 0.00035174899676349014,
10
- "dataloader_wait_pct_300s": 0.0382592069912683,
11
- "dataloader_wait_pct_60s": 0.0961140629935623,
12
- "dataloader_wait_pct_900s": 0.066640439237091,
13
- "dataloader_wait_pct_run": 0.06717802801040498,
14
- "different_inchikey_mean_cosine": 0.004679911238535274,
15
- "distributed_rank": 0.0,
16
- "distributed_world_size": 1.0,
17
- "effective_batch_size": 512.0,
18
- "effective_hard_negative_scale": 1.0,
19
- "effective_retrieval_weight": 0.6,
20
- "effective_structure_bce_weight": 1.0,
21
- "embedding_mean_norm": 1.0,
22
- "embedding_offdiag_mean_cosine": 0.009513536468148232,
23
- "embedding_std": 0.07216806709766388,
24
- "final_report": 1.0,
25
- "global_batch_size": 512.0,
26
- "gpu_active_fraction": 1.0,
27
- "gpu_count_observed": 2.0,
28
- "gpu_max_memory_gb": 13.279157161712646,
29
- "gpu_mem_used_mean_gb": 14.1943359375,
30
- "gpu_mem_util_mean_pct": 14.848754175733243,
31
- "gpu_memory_stable": true,
32
- "gpu_memory_utilization": 0.13982381154325935,
33
- "gpu_snapshot_available": 1.0,
34
- "gpu_util_max_pct": 54.0,
35
- "gpu_util_mean_pct": 36.0,
36
- "gpu_util_min_pct": 18.0,
37
- "grad_norm": 1.7659728527069092,
38
- "holdout_full_coverage": 0.0,
39
- "local_batch_size": 512.0,
40
- "lr": 3.886130904636371e-06,
41
- "mfu_estimate": 0.06267708747552383,
42
- "msms_objective": "hybrid",
43
- "optimizer_step": 1.0,
44
- "regularizer_ramp": 1.0,
45
- "resume_checkpoint_path": "/home/ubuntu/artifacts/nexa_mol/final_v3_structure_alignment/v26_r1/current_checkpoint.pt",
46
- "resume_start_step": 81002.0,
47
- "resumed_from_checkpoint": 1.0,
48
- "retrieval_head_lr": 1.9430654523181854e-05,
49
- "same_inchikey_mean_cosine": 0.16267980930137343,
50
- "samples_per_sec": 1399.0203442084614,
51
- "samples_per_sec_300s": 1547.033197547462,
52
- "samples_per_sec_60s": 1399.0203442084614,
53
- "samples_per_sec_900s": 1512.7885250414204,
54
- "samples_per_sec_run_mean": 1533.0231795943853,
55
- "step": 91001,
56
- "step_time_cv_300s": 0.06743440395418321,
57
- "step_time_cv_60s": 0.0,
58
- "step_time_cv_900s": 0.09218780075615579,
59
- "step_time_sec": 0.3659703749981418,
60
- "structure_bce_locked": 0.0,
61
- "structure_bce_loss": 0.08383000642061234,
62
- "structure_candidate_count": 2126.0,
63
- "structure_clear_fraction": 0.0,
64
- "structure_clear_hit_at_1": 0.0,
65
- "structure_close_fraction": 0.029296875,
66
- "structure_close_hit_at_1": 0.0,
67
- "structure_confidence_bucket_score_mean": 0.10155132412910461,
68
- "structure_confidence_bucket_score_mode": "normalized_gap",
69
- "structure_confidence_candidate_count": 2126.0,
70
- "structure_confidence_clear_threshold": 1.0,
71
- "structure_confidence_close_threshold": 0.35,
72
- "structure_confidence_eval_key_mode": "target_identity",
73
- "structure_confidence_separation": -0.0040241447277367115,
74
- "structure_correct_logit_mean": 9.1875,
75
- "structure_fingerprint_cosine": 0.46021854877471924,
76
- "structure_hard_negative_bonus_applied": 1.0,
77
- "structure_hard_negative_bonus_mean": 0.060302734375,
78
- "structure_hard_negative_scale": 1.0,
79
- "structure_head_lr": 1.9430654523181854e-05,
80
- "structure_hit_at_1": 0.00390625,
81
- "structure_hit_at_20": 0.1171875,
82
- "structure_hit_at_5": 0.029296875,
83
- "structure_local_ce_loss": 3.545562744140625,
84
- "structure_local_ce_loss_weight": 0.4,
85
- "structure_local_rerank_loss": 0.0,
86
- "structure_local_rerank_loss_weight": 0.0,
87
- "structure_local_rerank_score_scale": 1.0,
88
- "structure_logit_margin_mean": -1.0078125,
89
- "structure_margin_loss": 0.0,
90
- "structure_margin_loss_weight": 0.0,
91
- "structure_missing_formula_fraction": 0.0,
92
- "structure_missing_inchikey_fraction": 0.0,
93
- "structure_pairwise_logistic_loss": 0.0,
94
- "structure_pairwise_logistic_loss_weight": 0.0,
95
- "structure_positive_count_mean": 1.0,
96
- "structure_post_label_candidate_count": 2126.0,
97
- "structure_post_precursor_candidate_count": 2128.0,
98
- "structure_prefilter_candidate_count": 2128.0,
99
- "structure_retrieval_logit_std": 0.9839304089546204,
100
- "structure_retrieval_loss": 10.630162239074707,
101
- "structure_retrieval_scorer": "projected_dot",
102
- "structure_retrieval_target_mode": "sample",
103
- "structure_skipped_query_fraction": 0.0,
104
- "structure_soft_target_exact_mix": 0.4,
105
- "structure_soft_target_loss": 7.523618221282959,
106
- "structure_soft_target_loss_weight": 0.3,
107
- "structure_target_backend": "rdkit_morgan",
108
- "structure_target_equivalent_count_mean": 1.0,
109
- "structure_target_identity_collision_count": 0.0,
110
- "structure_target_rank_mean": 314.703125,
111
- "structure_to_ssl_ratio": 217.7124787233957,
112
- "structure_top1_top2_gap_mean": 0.0986328125,
113
- "structure_top1_top2_gap_norm_mean": 0.10155132412910461,
114
- "structure_top_negative_logit_mean": 10.1875,
115
- "structure_uncertain_fraction": 0.970703125,
116
- "structure_uncertain_hit_at_1": 0.0040241447277367115,
117
- "structure_valid_query_fraction": 1.0,
118
- "test_expected_shard_count": 2.0,
119
- "test_full_coverage": 0.0,
120
- "test_observed_shard_count": 0.0,
121
- "train_loss": 6.491608619689941,
122
- "train_loss_ema": 6.519052214060582,
123
- "train_retrieval_bank_size": 4096.0,
124
- "val_deep_eval_single_view": 0.0,
125
- "val_deep_eval_structure_only": 0.0,
126
- "val_effective_structure_bce_weight": 1.0,
127
- "val_eval_loader_mode": "stream",
128
- "val_eval_mode": "deep",
129
- "val_expected_shard_count": 2.0,
130
- "val_full_coverage": 1.0,
131
- "val_hit_at_1": 0.0282135009765625,
132
- "val_hit_at_20": 0.15270233154296875,
133
- "val_hit_at_5": 0.0726776123046875,
134
- "val_loss": 6.646750174145564,
135
- "val_observed_eval_batches": 256.0,
136
- "val_observed_shard_count": 2.0,
137
- "val_ssl_loss": 1.0397093277424574,
138
- "val_structure_bce_loss": 0.06532714269997086,
139
- "val_structure_candidate_count": 4119.69140625,
140
- "val_structure_clear_fraction": 0.0,
141
- "val_structure_clear_hit_at_1": 0.0,
142
- "val_structure_close_fraction": 0.0077972412109375,
143
- "val_structure_close_hit_at_1": 0.014835291571216658,
144
- "val_structure_confidence_candidate_count": 4096.0,
145
- "val_structure_confidence_separation": -0.027957430157584895,
146
- "val_structure_correct_logit_mean": 9.49462890625,
147
- "val_structure_fingerprint_cosine": 0.4255251376889646,
148
- "val_structure_logit_margin_mean": -1.221923828125,
149
- "val_structure_missing_formula_fraction": 0.0,
150
- "val_structure_missing_inchikey_fraction": 0.0,
151
- "val_structure_retrieval_logit_std": 2.6622845763340592,
152
- "val_structure_retrieval_loss": 10.882395941764116,
153
- "val_structure_target_equivalent_count_mean": 1.0,
154
- "val_structure_target_identity_collision_count": 23.69140625,
155
- "val_structure_target_rank_mean": 379.8781280517578,
156
- "val_structure_top1_top2_gap_mean": 0.11855697631835938,
157
- "val_structure_top1_top2_gap_norm_mean": 0.05411380449368153,
158
- "val_structure_top_negative_logit_mean": 10.714599609375,
159
- "val_structure_uncertain_fraction": 0.9922027587890625,
160
- "val_structure_uncertain_hit_at_1": 0.027957430157584895,
161
- "variance_loss": 0.00213623046875,
162
- "variance_weight": 0.8,
163
- "weighted_covariance_loss": 0.015018927097320557,
164
- "weighted_regularizer_to_contrastive_ratio": 0.028996589606316913,
165
- "weighted_ssl_loss": 0.02968101501464844,
166
- "weighted_structure_bce_loss": 0.08383000642061234,
167
- "weighted_structure_retrieval_loss": 6.378097343444824,
168
- "weighted_variance_loss": 0.001708984375
169
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
metadata/perf_summary.json DELETED
@@ -1,16 +0,0 @@
1
- {
2
- "logged_points": 521,
3
- "train_loss_min": 3.2278988361358643,
4
- "train_loss_max": 7.677141189575195,
5
- "train_loss_last": 6.491608619689941,
6
- "train_loss_ema_last": 6.519052214060582,
7
- "weighted_regularizer_ratio_median": 0.02686493425176378,
8
- "weighted_regularizer_ratio_p90": 0.09558363904110317,
9
- "samples_per_sec_mean": 1545.3851888056406,
10
- "samples_per_sec_min": 930.5498563655322,
11
- "samples_per_sec_max": 2247.460787425693,
12
- "step_time_mean": 0.33468720350667036,
13
- "mfu_mean": 0.06923433462788683,
14
- "mfu_max": 0.10068781126337953,
15
- "gpu_mem_max_gb": 13.279157161712646
16
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
metadata/results.md DELETED
@@ -1,171 +0,0 @@
1
- # MS/MS Training Run Result
2
-
3
- - Run name: `final_v3_structure_alignment_v26_r1`
4
- - Created at: `2026-04-13T21:36:19Z`
5
- - Dataset root: `/home/ubuntu/data/gems_v1_handoff_labeled_v26`
6
- - Shard counts: `{'train': 4, 'val': 2, 'test': 2}`
7
-
8
- ## Primary Metrics
9
-
10
- - `train_loss`: `6.491608619689941`
11
- - `val_loss`: `6.646750174145564`
12
- - `grad_norm`: `1.7659728527069092`
13
- - `contrastive_loss`: `0.5768923759460449`
14
- - `structure_bce_loss`: `0.08383000642061234`
15
- - `val_structure_bce_loss`: `0.06532714269997086`
16
- - `val_structure_fingerprint_cosine`: `0.4255251376889646`
17
- - `different_inchikey_mean_cosine`: `0.004679911238535274`
18
- - `embedding_std`: `0.07216806709766388`
19
- - `val_hit_at_20`: `0.15270233154296875`
20
- - `val_structure_candidate_count`: `4119.69140625`
21
- - `val_structure_top1_top2_gap_mean`: `0.11855697631835938`
22
- - `val_structure_uncertain_fraction`: `0.9922027587890625`
23
- - `val_structure_clear_hit_at_1`: `0.0`
24
- - `val_structure_confidence_separation`: `-0.027957430157584895`
25
- - `samples_per_sec`: `1399.0203442084614`
26
-
27
- ## Failure Mode Assessment
28
-
29
- - `dataset_shards_accessible`: pass. Observed shard counts {'train': 4, 'val': 2, 'test': 2}; the canonical Day 1 loader contract requires all splits to be readable.
30
- - `dataloader_streaming_stable`: pass. Training batches continued to arrive with positive throughput and no iterator stall.
31
- - `non_finite_loss_or_tensor_failure`: pass. Technical_Plan requires zero NaN or Inf tensors and finite train/val loss.
32
- - `validation_observability_gap`: pass. Engineering.md expects slope-aware monitoring; missing validation or retrieval metrics make trend judgment weaker.
33
- - `gpu_memory_instability`: pass. Technical_Plan Day 1 success requires stable GPU memory through the bounded run.
34
- - `checkpoint_save_reload_failure`: pass. Checkpoint save and reload is an explicit Day 1 success criterion.
35
- - `embedding_collapse`: pass. Engineering.md expects embedding variance monitoring and non-collapsed representations.
36
- - `regularizer_dominance`: pass. The current instability mode is regularization overpowering the SSL objective and producing jagged total loss.
37
- - `structure_supervision_gap`: pass. Once the bridge phase begins, Technical_Plan requires retrieval-oriented validation rather than only augmented contrastive loss.
38
- - `confidence_surface_gap`: pass. Structure-first qualification now requires explicit confidence diagnostics such as top-1/top-2 separation and uncertainty buckets, not just broader retrieval metrics.
39
- - `chemistry_target_backend_gap`: pass. The bridge phase should prefer chemistry-grounded fingerprint targets; hashed fallback targets weaken the retrieval signal.
40
- - `bridge_fit_without_ranking`: pass. Bridge runs must improve retrieval after fingerprint fit saturates; fitting BCE while val Hit@20 stays at candidate-bank baseline means ranking is not generalizing.
41
- - `metadata_shortcutting`: watch. Engineering.md flags acquisition-artefact shortcut risk; adduct and instrument embeddings remain deliberately down-scaled.
42
-
43
- ## Pressure Summary
44
-
45
- - all metrics overall: `↗ improving (+21.89% weighted)`
46
- - all metrics weighted improvement: `+21.89%`
47
- - all metrics average improvement: `+34.52%`
48
- - all metrics weighted pressure score: `0.284`
49
- - all metrics counts: `up=21` `none=7` `down=11` `up_fraction=+53.85%`
50
- - primary metrics overall: `↗ improving (-4.45% weighted)`
51
- - primary metrics weighted improvement: `-4.45%`
52
-
53
- ## Metric Pressure
54
-
55
- - `train_loss`: `goal ↓ | ↗ +10.57% improving` (early `6.340343519442343`, mid `5.795929590401622`, late `5.670367905463295`, last `6.491608619689941`)
56
- - `train_loss_ema`: `goal ↓ | ↗ +10.46% improving` (early `6.265581717362126`, mid `5.8371378655061745`, late `5.610470838300897`, last `6.519052214060582`)
57
- - `contrastive_loss`: `goal ↓ | → -1.64% flat` (early `1.409792113166324`, mid `1.3598130204084982`, late `1.43291388983014`, last `0.5768923759460449`)
58
- - `val_loss`: `goal ↓ | ↘ -55.82% worsening` (early `1.2876316868363775`, mid `2.20697861268016`, late `2.006446816829876`, last `6.646750174145564`)
59
- - `val_ssl_loss`: `goal ↓ | → +2.32% flat` (early `1.0849772497183745`, mid `1.0747967428483425`, late `1.0598136518327963`, last `1.0397093277424574`)
60
- - `structure_bce_loss`: `goal ↓ | ↗ +39.75% improving` (early `0.12293951650489272`, mid `0.07652380578004556`, late `0.07407209518012302`, last `0.08383000642061234`)
61
- - `val_structure_bce_loss`: `goal ↓ | ↗ +12.20% improving` (early `0.0771060927848642`, mid `0.07029345531468391`, late `0.06769936999660872`, last `0.06532714269997086`)
62
- - `structure_retrieval_loss`: `goal ↓ | ↗ +10.09% improving` (early `10.237479978903181`, mid `9.41523380775672`, late `9.204101929719421`, last `10.630162239074707`)
63
- - `val_structure_retrieval_loss`: `goal ↓ | → +4.86% flat` (early `11.562767315655947`, mid `12.150514367967844`, late `11.000247791409492`, last `10.882395941764116`)
64
- - `structure_fingerprint_cosine`: `goal ↑ | ↗ +17.59% improving` (early `0.3965519580968543`, mid `0.4464927057310336`, late `0.46629545006943846`, last `0.46021854877471924`)
65
- - `val_structure_fingerprint_cosine`: `goal ↑ | → +0.17% flat` (early `0.4147872725734487`, mid `0.4204998221830465`, late `0.4154996814322658`, last `0.4255251376889646`)
66
- - `structure_target_rank_mean`: `goal ↓ | ↗ +58.80% improving` (early `351.84337743858384`, mid `176.16389315390174`, late `144.9534280711207`, last `314.703125`)
67
- - `val_structure_target_rank_mean`: `goal ↓ | ↗ +45.45% improving` (early `760.7540435791016`, mid `683.3385162353516`, late `415.0084457397461`, last `379.8781280517578`)
68
- - `structure_correct_logit_mean`: `goal ↑ | ↗ +47.31% improving` (early `6.134031791907514`, mid `9.474891618497109`, late `9.035739942528735`, last `9.1875`)
69
- - `val_structure_correct_logit_mean`: `goal ↑ | ↗ +16.44% improving` (early `8.0311279296875`, mid `8.441162109375`, late `9.3515625`, last `9.49462890625`)
70
- - `structure_top_negative_logit_mean`: `goal ↓ | ↘ -39.72% worsening` (early `7.262102601156069`, mid `10.490606936416185`, late `10.14691091954023`, last `10.1875`)
71
- - `val_structure_top_negative_logit_mean`: `goal ↓ | ↘ -16.08% worsening` (early `9.2255859375`, mid `10.51171875`, late `10.708740234375`, last `10.714599609375`)
72
- - `structure_logit_margin_mean`: `goal ↑ | → +1.23% flat` (early `-1.1263999277456647`, mid `-1.0154725885115607`, late `-1.1125740840517242`, last `-1.0078125`)
73
- - `val_structure_logit_margin_mean`: `goal ↑ | ↘ -13.67% worsening` (early `-1.194091796875`, mid `-2.0707931518554688`, late `-1.3573150634765625`, last `-1.221923828125`)
74
- - `structure_retrieval_logit_std`: `goal ↑ | ↗ +112.06% improving` (early `1.0455416592559375`, mid `2.0036371215919537`, late `2.2171744848119803`, last `0.9839304089546204`)
75
- - `val_structure_retrieval_logit_std`: `goal ↑ | ↗ +102.33% improving` (early `1.2326001720502973`, mid `2.022283688886091`, late `2.49387572822161`, last `2.6622845763340592`)
76
- - `structure_top1_top2_gap_mean`: `goal ↑ | ↗ +59.22% improving` (early `0.09793567106213873`, mid `0.12284365968208093`, late `0.1559343009159483`, last `0.0986328125`)
77
- - `val_structure_top1_top2_gap_mean`: `goal ↑ | ↗ +54.91% improving` (early `0.07839679718017578`, mid `0.1310901641845703`, late `0.12144279479980469`, last `0.11855697631835938`)
78
- - `structure_top1_top2_gap_norm_mean`: `goal ↑ | ↘ -35.65% worsening` (early `0.12215662799301864`, mid `0.07032911504236604`, late `0.07860379065547524`, last `0.10155132412910461`)
79
- - `val_structure_top1_top2_gap_norm_mean`: `goal ↑ | ↘ -16.83% worsening` (early `0.06950851557485294`, mid `0.07577372609375743`, late `0.0578127475164365`, last `0.05411380449368153`)
80
- - `structure_uncertain_fraction`: `goal ↓ | ↘ -6.11% worsening` (early `0.924663565751445`, mid `0.984747561416185`, late `0.9811422413793104`, last `0.970703125`)
81
- - `val_structure_uncertain_fraction`: `goal ↓ | → -0.03% flat` (early `0.9941177368164062`, mid `0.9762382507324219`, late `0.9944419860839844`, last `0.9922027587890625`)
82
- - `structure_confidence_separation`: `goal ↑ | ↘ -531.56% worsening` (early `-0.007918493679557749`, mid `-0.032136323077151974`, late `-0.05001017991881603`, last `-0.0040241447277367115`)
83
- - `val_structure_confidence_separation`: `goal ↑ | ↘ -204.85% worsening` (early `-0.00795668972114072`, mid `-0.01309866098972634`, late `-0.024256365849851136`, last `-0.027957430157584895`)
84
- - `structure_hit_at_1`: `goal ↑ | ↗ +549.68% improving` (early `0.007880238439306358`, mid `0.032706376445086706`, late `0.051196569683908046`, last `0.00390625`)
85
- - `structure_hit_at_5`: `goal ↑ | ↗ +402.47% improving` (early `0.03360955563583815`, mid `0.11673591040462428`, late `0.16887796336206898`, last `0.029296875`)
86
- - `structure_hit_at_20`: `goal ↑ | ↗ +239.46% improving` (early `0.10721865968208093`, mid `0.28105807442196534`, late `0.3639659662356322`, last `0.1171875`)
87
- - `val_hit_at_1`: `goal ↑ | → +207.79% flat` (early `0.0079345703125`, mid `0.01372528076171875`, late `0.02442169189453125`, last `0.0282135009765625`)
88
- - `val_hit_at_5`: `goal ↑ | ↗ +134.85% improving` (early `0.0288543701171875`, mid `0.0425567626953125`, late `0.0677642822265625`, last `0.0726776123046875`)
89
- - `val_hit_at_20`: `goal ↑ | ↗ +76.67% improving` (early `0.08158111572265625`, mid `0.094146728515625`, late `0.14413070678710938`, last `0.15270233154296875`)
90
- - `weighted_regularizer_to_contrastive_ratio`: `goal ↓ | ↗ +54.61% improving` (early `0.0667222202939108`, mid `0.0329437448262181`, late `0.03028750823471251`, last `0.028996589606316913`)
91
- - `samples_per_sec`: `goal ↑ | ↘ -2.88% worsening` (early `1575.5664566260843`, mid `1531.3735887168505`, late `1530.1496274666802`, last `1399.0203442084614`)
92
- - `gpu_max_memory_gb`: `goal ≈ | ↗ +100.00% improving` (early `13.252925169950275`, mid `13.279059082097401`, late `13.279157161712646`, last `13.279157161712646`)
93
- - `grad_norm`: `goal ≈ | ↘ -100.00% worsening` (early `4.638080189338309`, mid `4.979553528603791`, late `6.072961742165445`, last `1.7659728527069092`)
94
-
95
- ## Primary Metric Pressure
96
-
97
- - `train_loss`: `goal ↓ | ↗ +10.57% improving` (early `6.340343519442343`, mid `5.795929590401622`, late `5.670367905463295`, last `6.491608619689941`)
98
- - `val_loss`: `goal ↓ | ↘ -55.82% worsening` (early `1.2876316868363775`, mid `2.20697861268016`, late `2.006446816829876`, last `6.646750174145564`)
99
- - `grad_norm`: `goal ≈ | ↘ -100.00% worsening` (early `4.638080189338309`, mid `4.979553528603791`, late `6.072961742165445`, last `1.7659728527069092`)
100
- - `contrastive_loss`: `goal ↓ | → -1.64% flat` (early `1.409792113166324`, mid `1.3598130204084982`, late `1.43291388983014`, last `0.5768923759460449`)
101
- - `structure_bce_loss`: `goal ↓ | ↗ +39.75% improving` (early `0.12293951650489272`, mid `0.07652380578004556`, late `0.07407209518012302`, last `0.08383000642061234`)
102
- - `val_structure_bce_loss`: `goal ↓ | ↗ +12.20% improving` (early `0.0771060927848642`, mid `0.07029345531468391`, late `0.06769936999660872`, last `0.06532714269997086`)
103
- - `val_structure_fingerprint_cosine`: `goal ↑ | → +0.17% flat` (early `0.4147872725734487`, mid `0.4204998221830465`, late `0.4154996814322658`, last `0.4255251376889646`)
104
- - `val_hit_at_20`: `goal ↑ | ↗ +76.67% improving` (early `0.08158111572265625`, mid `0.094146728515625`, late `0.14413070678710938`, last `0.15270233154296875`)
105
- - `val_structure_top1_top2_gap_mean`: `goal ↑ | ↗ +54.91% improving` (early `0.07839679718017578`, mid `0.1310901641845703`, late `0.12144279479980469`, last `0.11855697631835938`)
106
- - `val_structure_uncertain_fraction`: `goal ↓ | → -0.03% flat` (early `0.9941177368164062`, mid `0.9762382507324219`, late `0.9944419860839844`, last `0.9922027587890625`)
107
- - `val_structure_confidence_separation`: `goal ↑ | ↘ -204.85% worsening` (early `-0.00795668972114072`, mid `-0.01309866098972634`, late `-0.024256365849851136`, last `-0.027957430157584895`)
108
- - `samples_per_sec`: `goal ↑ | ↘ -2.88% worsening` (early `1575.5664566260843`, mid `1531.3735887168505`, late `1530.1496274666802`, last `1399.0203442084614`)
109
-
110
- ## Debug Metrics
111
-
112
- - `train_loss`: `6.491608619689941`
113
- - `train_loss_ema`: `6.519052214060582`
114
- - `val_loss`: `6.646750174145564`
115
- - `contrastive_loss`: `0.5768923759460449`
116
- - `val_ssl_loss`: `1.0397093277424574`
117
- - `variance_loss`: `0.00213623046875`
118
- - `covariance_loss`: `10.012618064880371`
119
- - `structure_bce_loss`: `0.08383000642061234`
120
- - `structure_retrieval_loss`: `10.630162239074707`
121
- - `val_structure_retrieval_loss`: `10.882395941764116`
122
- - `structure_fingerprint_cosine`: `0.46021854877471924`
123
- - `structure_hit_at_1`: `0.00390625`
124
- - `structure_hit_at_5`: `0.029296875`
125
- - `structure_hit_at_20`: `0.1171875`
126
- - `structure_target_rank_mean`: `314.703125`
127
- - `structure_logit_margin_mean`: `-1.0078125`
128
- - `structure_retrieval_logit_std`: `0.9839304089546204`
129
- - `val_structure_retrieval_logit_std`: `2.6622845763340592`
130
- - `structure_correct_logit_mean`: `9.1875`
131
- - `structure_top_negative_logit_mean`: `10.1875`
132
- - `val_structure_correct_logit_mean`: `9.49462890625`
133
- - `val_structure_top_negative_logit_mean`: `10.714599609375`
134
- - `structure_top1_top2_gap_mean`: `0.0986328125`
135
- - `structure_top1_top2_gap_norm_mean`: `0.10155132412910461`
136
- - `structure_confidence_candidate_count`: `2126.0`
137
- - `structure_close_fraction`: `0.029296875`
138
- - `structure_uncertain_fraction`: `0.970703125`
139
- - `structure_uncertain_hit_at_1`: `0.0040241447277367115`
140
- - `structure_confidence_separation`: `-0.0040241447277367115`
141
- - `val_structure_top1_top2_gap_mean`: `0.11855697631835938`
142
- - `val_structure_top1_top2_gap_norm_mean`: `0.05411380449368153`
143
- - `val_structure_confidence_candidate_count`: `4096.0`
144
- - `val_structure_close_fraction`: `0.0077972412109375`
145
- - `val_structure_uncertain_fraction`: `0.9922027587890625`
146
- - `val_structure_close_hit_at_1`: `0.014835291571216658`
147
- - `val_structure_uncertain_hit_at_1`: `0.027957430157584895`
148
- - `val_structure_confidence_separation`: `-0.027957430157584895`
149
- - `grad_norm`: `1.7659728527069092`
150
- - `weighted_regularizer_to_contrastive_ratio`: `0.028996589606316913`
151
- - `samples_per_sec`: `1399.0203442084614`
152
- - `samples_per_sec_60s`: `1399.0203442084614`
153
- - `samples_per_sec_300s`: `1547.033197547462`
154
- - `samples_per_sec_900s`: `1512.7885250414204`
155
- - `samples_per_sec_run_mean`: `1533.0231795943853`
156
- - `gpu_max_memory_gb`: `13.279157161712646`
157
- - `gpu_util_mean_pct`: `36.0`
158
- - `gpu_util_min_pct`: `18.0`
159
- - `gpu_util_max_pct`: `54.0`
160
- - `gpu_active_fraction`: `1.0`
161
- - `gpu_mem_used_mean_gb`: `14.1943359375`
162
- - `gpu_mem_util_mean_pct`: `14.848754175733243`
163
- - `gpu_snapshot_available`: `1.0`
164
- - `step_time_sec`: `0.3659703749981418`
165
- - `step_time_cv_300s`: `0.06743440395418321`
166
- - `step_time_cv_900s`: `0.09218780075615579`
167
- - `dataloader_wait_pct_60s`: `0.0961140629935623`
168
- - `dataloader_wait_pct_300s`: `0.0382592069912683`
169
- - `dataloader_wait_pct_900s`: `0.066640439237091`
170
- - `dataloader_wait_pct_run`: `0.06717802801040498`
171
- - `mfu_estimate`: `0.06267708747552383`
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
metadata/training_surface.json DELETED
@@ -1,68 +0,0 @@
1
- {
2
- "created_at": "2026-04-13T20:20:55Z",
3
- "run_name": "final_v3_structure_alignment_v26_r1",
4
- "wandb_project": "Nexa_Mol",
5
- "wandb_run_name": "final_v3_structure_alignment_v26_r1",
6
- "wandb_group": "Structure-Alignment",
7
- "dataset_root": "/home/ubuntu/data/gems_v1_handoff_labeled_v26",
8
- "selected_shards_json": "/home/ubuntu/data/gems_v1_handoff_labeled_v26/selected_shards.json",
9
- "selected_shards_exists": true,
10
- "phase_ready_marker": "",
11
- "phase_ready_exists": false,
12
- "phase_receipt_path": "",
13
- "phase_receipt_exists": false,
14
- "train_shard_surface_mode": "train_only",
15
- "refresh_selected_shards_on_iterator_reset": false,
16
- "parent_policy": "local_only",
17
- "labeled_eval_root": "",
18
- "query_dataset_root": "",
19
- "bank_dataset_root": "",
20
- "primary_checkpoint_run_name": "",
21
- "fallback_checkpoint_run_name": "",
22
- "local_parent_checkpoint": "/home/ubuntu/artifacts/nexa_mol/v1_full_pretrain/phase1_blackwell_v3/Final_V3.pt",
23
- "current_checkpoint_path": "",
24
- "current_checkpoint_exists": true,
25
- "disable_auto_resume": true,
26
- "resume_model_only": true,
27
- "objective": "hybrid",
28
- "ssl_weight": 0.05,
29
- "structure_weight": 1.0,
30
- "structure_post_saturation_weight": 0.0,
31
- "structure_threshold": 0.0,
32
- "structure_lock_patience": 0,
33
- "train_retrieval_watch_only": false,
34
- "freeze_retrieval_head": false,
35
- "retrieval_weight": 0.6,
36
- "batch_size": 512,
37
- "eval_batch_size": 512,
38
- "num_workers": 12,
39
- "grad_accum_steps": 1,
40
- "loader_prefetch_factor": 4,
41
- "log_every": 20,
42
- "sync_every": 1000,
43
- "amp_mode": "",
44
- "additional_steps": 10000,
45
- "max_steps": 91001,
46
- "eval_batches": 24,
47
- "eval_batches_per_shard": 0,
48
- "eval_start_after_steps": 0,
49
- "deep_eval_every": 2000,
50
- "deep_eval_start_after_steps": 2000,
51
- "deep_eval_batches": 256,
52
- "deep_eval_single_view": false,
53
- "deep_eval_structure_only": false,
54
- "active_train_shards": 0,
55
- "prefetch_train_shards": 0,
56
- "val_shards": 0,
57
- "test_shards": 0,
58
- "train_offset": 0,
59
- "val_offset": 0,
60
- "test_offset": 0,
61
- "selected_shards_summary": {
62
- "train_count": 4,
63
- "val_count": 2,
64
- "test_count": 2,
65
- "prefetch_count": 0,
66
- "subset_strategy": "v26_native_confidence_policy_subset"
67
- }
68
- }