Add technical model card and step-510 release metadata

COMPATIBILITY.md

@@ -0,0 +1,23 @@
+# Compatibility and provenance notice
+
+This repository distributes only modified Qwen3-VL text-encoder weights derived from the Apache-2.0
+`Comfy-Org/Qwen3-VL` checkpoint whose SHA-256 is:
+
+```text
+4ba424cf62e51392e4d1a39933e803706f4e823c1065f36aaf149c6453f66bcd
+```
+
+No Ideogram model weights, parameters, code, VAE, sampler, or tokenizer implementation are included.
+
+The training harness connected this Qwen text encoder to a separately obtained, frozen Ideogram 4 model
+through the model's ordinary conditioning interface. Ideogram was used as a differentiable downstream
+evaluator for velocity loss. Ideogram parameters were never trainable and are not present in the LoRA or
+merged text encoder.
+
+These Qwen weights cannot generate images or replace Ideogram on their own. Ideogram 4 is a separately
+distributed third-party model. Users who combine the components must obtain Ideogram separately and are
+responsible for its license and usage requirements.
+
+This project is independent and is not affiliated with, endorsed by, approved by, or validated by
+Ideogram, Inc., Alibaba/Qwen, or Comfy Org.
+

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,241 @@
+---
+license: apache-2.0
+base_model: Comfy-Org/Qwen3-VL
+pipeline_tag: text-to-image
+tags:
+  - comfyui
+  - ideogram4
+  - qwen3-vl
+  - text-encoder
+  - lora
+  - fp8
+  - flow-matching
+  - experimental
+---
+
+# Ideogram 4 Natural-Language Text Encoder — S020 v1
+
+This repository contains an experimental, stock-shaped replacement for the Qwen3-VL 8B text encoder
+used by Ideogram 4, plus the matching training LoRA. It is intended to make Ideogram 4 respond to
+ordinary natural-language prompts more like the stock model responds to structured Magic-Prompt JSON,
+without a runtime prompt rewriter, custom node, companion language model, or patched ComfyUI.
+
+This release is the first strength-0.2 milestone. The nominal 500-step milestone resolved to the first
+complete checkpoint in that checkpoint band, **optimizer step 510**.
+
+## Files
+
+| File | Purpose | Size | SHA-256 |
+|---|---|---:|---|
+| `text_encoders/qwen3vl_8b_ideogram4_nl_s020_v1_step_00000510_fp8_scaled.safetensors` | Standalone drop-in scaled-FP8 text encoder | 10,588,637,800 bytes | `f0d1009af7407b60bda169967bb5e4c3e8ea264042b70f3d7b667bb0c2404ece` |
+| `loras/qwen3vl_8b_ideogram4_nl_s020_v1_step_00000510_r64_a64.safetensors` | Matching unmerged research LoRA | 698,404,608 bytes | `85359811e619276f85742072c2b3327915bbb56bcefb874f2f3101a5d1216eef` |
+| `manifests/checkpoint_step_00000510.json` | Training checkpoint and controller metadata | — | See `SHA256SUMS` |
+| `manifests/merge_step_00000510.json` | Merge inputs, output hash, and per-projection quantization metrics | — | See `SHA256SUMS` |
+| `COMPATIBILITY.md` | Component boundary, provenance, and third-party compatibility notice | — | See `SHA256SUMS` |
+
+The LoRA uses this project's native tensor names (`layers.N.<projection>.lora_a` and `lora_b`) and is
+not advertised as a PEFT or generic ComfyUI LoRA. Most users should use the merged text encoder.
+
+## Installation
+
+Download the merged file into the normal ComfyUI text-encoder directory:
+
+```text
+ComfyUI/models/text_encoders/
+```
+
+Select it in the same Ideogram 4 text-encoder loader used for the stock
+`qwen3vl_8b_fp8_scaled.safetensors`. No inference-time LoRA loader or source-code modification is
+required.
+
+## What was trained
+
+### Task definition
+
+Observed stock behavior motivated the following target:
+
+```text
+short natural language       -> weak/broken stock conditioning
+detailed natural language    -> weak/broken stock conditioning
+structured Magic-Prompt JSON -> functional stock conditioning
+```
+
+Each natural-language prompt therefore has a structured teacher target. The adapted text encoder is
+not trained to reproduce the teacher's token sequence or Qwen activations. Natural-language and JSON
+sequences differ in length, so the student is instead optimized at Ideogram's image-side response:
+
+```text
+c_T = stock_text_encoder(teacher_json)
+c_S = adapted_text_encoder(natural_language)
+
+v_T = ideogram_conditional(z_t, t, c_T)
+v_S = ideogram_conditional(z_t, t, c_S)
+
+loss = mean((v_S - v_T) ** 2)
+```
+
+Ideogram parameters are frozen, but gradients remain enabled through the student conditional forward
+so the velocity loss can update the text-encoder adapters. There is no stock-natural-language retention
+term: preserving stock NL behavior would preserve the behavior this project is replacing.
+
+### Stock text-encoder path
+
+The stock Ideogram path uses Qwen3-VL 8B as a contextual feature extractor. Hidden states from 13 taps
+(`0, 3, 6, 9, 12, 15, 18, 21, 24, 27, 30, 33, 35`) are concatenated to 53,248 features per text token,
+then projected to the 4,608-wide Ideogram DiT. The student preserves this architecture and tensor layout.
+
+### Dataset and teacher
+
+- 4,000 source prompts from public Civitai generation metadata.
+- Exactly 1,000 prompts from each source rating group: SFW, R, X, and XXX.
+- Exact MaxMin diversity selection in Ideogram's own conditioning space, after literal cleanup,
+  provenance filtering, and exclusion of edit/image-input records.
+- 3,900 training prompts and 100 deterministic owner-reviewed holdouts (25 per rating group).
+- Eight cached behavior states per training prompt: 31,200 training examples.
+- Teacher JSON generated by `accounts/fireworks/models/nemotron-3-ultra-nvfp4` through Fireworks,
+  temperature 0, high reasoning effort, using the project's Magic-Prompt system instructions.
+- Teacher conditioning encoded through the exact stock Comfy tokenizer, Qwen taps, and Ideogram ingress
+  projection, stored as float16.
+
+The source prompts, teacher JSON, and adult-content corpus are not distributed in this model repository.
+
+### Eight-state trajectory supervision
+
+Teacher trajectories use the stock `V4_DEFAULT_20` 20-step schedule at 512×512. Eight deterministic
+pre-step states are captured at loop indices:
+
+```text
+[19, 16, 14, 11, 8, 5, 3, 0]
+```
+
+Each cache entry stores the pre-step latent and exact positive conditional teacher velocity. All eight
+states are independent velocity-matching examples during training. The unconditional branch is a
+separate text-free model and is identical for teacher and student, so conditional velocity matching is
+sufficient for the text-encoder objective.
+
+### Strength-0.2 first-step steering target
+
+The teacher trajectory includes one first-conditional-pass spatial correction derived from the
+authoritative Ideogram 4 debanner direction:
+
+- correction tensor SHA-256: `5ce873adae5701e9d5f05ebfa8f8b923a1622745c6e9a2bcb3e22fd090ed30c3`;
+- Ideogram blocks: 25, 26, 27, and 28;
+- distillation strength: `0.2`;
+- first denoising step and first positive conditional pass only;
+- image tokens only;
+- subtract the nearest-neighbor-resized 8×8 spatial direction, then restore each image token's
+  original L2 norm;
+- unconditional model unchanged.
+
+Only the first cached target velocity is directly corrected. The later seven target velocities are
+uncorrected but evaluated on the trajectory produced by the corrected first update. The student always
+uses an unpatched stock Ideogram conditional model; the behavior is distilled into the text encoder.
+
+The cache contract fingerprints the correction tensor, metadata, strength, block set, schedule,
+resolution, conditional checkpoint, conditioning, and all eight target velocities. Incompatible caches
+are rejected before model loading.
+
+## Adapter geometry
+
+The geometry is fixed and was not reduced for this checkpoint:
+
+- rank: 64;
+- alpha: 64;
+- blocks: all 36 Qwen text blocks (`0–35`);
+- projections per block: `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`;
+- adapted projections: 252;
+- trainable parameters: 174,587,904;
+- LoRA tensors: 504.
+
+Per block, the adapter contains 4,849,664 parameters. The all-block topology is intentional: the task is
+a distributed change in how the 13 tapped Qwen layers express conditioning, not memorization in a small
+upper-block adapter.
+
+## Optimization and numerics
+
+- Optimizer: AdamW, FP32 adapter parameters and optimizer state.
+- Weight decay: `0.01`.
+- Physical batch size: 2.
+- Gradient accumulation: 8.
+- Effective optimizer batch: 16 behavior examples.
+- Adaptive packing: batch 2 through 1,017 student tokens; longer examples use singleton microbatches.
+- Gradient clipping: global norm `1.0`.
+- Optimizer state is held on CPU between updates.
+- Unused multimodal Qwen components are pruned from the training graph; all 36 text blocks remain.
+- Initial learning rate: `3.2e-4`.
+
+Training is quantization-aware for the final deployment format. For each adapted projection, the forward
+path forms the dequantized stock weight plus the LoRA delta, then requantizes using the stock per-tensor
+scale to `float8_e4m3fn`. A straight-through estimator supplies LoRA gradients without constructing a
+dense base-weight gradient.
+
+Learning rate is not tied to a fixed step horizon. A transactional controller evaluates fixed 50-step
+windows every 10 steps, estimates log-loss descent relative to robust residual noise, confirms a failed
+window for 20 additional steps, locates the elbow, restores the complete optimizer/sampler/RNG state at
+the rollback boundary, and continues at half the LR. A rollback is issued only when both deterministic
+held-out loss and interval-averaged training loss fail their descent tests. The LR floor is positive and
+does not terminate training.
+
+## Step-510 checkpoint metrics
+
+| Metric | Value |
+|---|---:|
+| Optimizer step | 510 |
+| Training velocity MSE | 0.0179036569 |
+| Held-out velocity MSE | 0.0171197626 |
+| Learning rate | `8e-5` |
+| LR reductions completed | 2 |
+| Gradient norm | 0.0149142 |
+| Step time on RTX 5090 | 12.94 s |
+| Peak reserved VRAM | 24.463 GiB |
+| Behavior microbatches | 8 batch-2, 0 singleton |
+
+Velocity MSE is a training/health proxy, not a complete image-quality metric. The release decision was
+made from fixed-seed stock/teacher/checkpoint image comparisons and owner visual review. No standardized
+perceptual benchmark, OCR benchmark, or broad safety evaluation is claimed for this checkpoint.
+
+## Merge and deployment format
+
+The standalone file was merged on CPU into the exact stock Comfy scaled-FP8 checkpoint layout:
+
+- stock base SHA-256: `4ba424cf62e51392e4d1a39933e803706f4e823c1065f36aaf149c6453f66bcd`;
+- adapter SHA-256: `85359811e619276f85742072c2b3327915bbb56bcefb874f2f3101a5d1216eef`;
+- output SHA-256: `f0d1009af7407b60bda169967bb5e4c3e8ea264042b70f3d7b667bb0c2404ece`;
+- output tensors: 1,254;
+- merged projections: 252;
+- stock per-tensor FP8 scales preserved;
+- no training-only adapter keys added to the merged file.
+
+The base file is byte-identical to the text encoder published in `Comfy-Org/Qwen3-VL` and
+`Comfy-Org/Ideogram-4` under the base SHA above.
+
+## Limitations
+
+- This is an early step-510 research checkpoint, not the end of the longer training lineage.
+- The learned conditioning is specific to Ideogram 4's frozen conditional model and Comfy text-encoder
+  ingress path. It is not a general-purpose Qwen3-VL chat model.
+- Training and validation use cached 512×512 trajectories from one fixed sampler contract. Behavior at
+  other resolutions, schedules, samplers, and seeds requires independent evaluation.
+- Teacher targets can be imperfect or semantically inconsistent despite validation.
+- The corpus deliberately spans adult source-rating groups. The model has not been safety-aligned or
+  certified for unrestricted deployment.
+- Static text conditioning may only approximate a first-step, latent-dependent spatial intervention.
+- FP8 requantization does not retain every low-magnitude LoRA delta exactly; per-projection retention
+  metrics are included in the merge manifest.
+
+## Component and licensing boundary
+
+The files in this repository contain only modified Qwen3-VL text-encoder parameters. They start from
+the independently published `Comfy-Org/Qwen3-VL` scaled-FP8 checkpoint and are released under its
+Apache-2.0 license. They contain no Ideogram DiT, VAE, sampler, tokenizer implementation, source code,
+or other Ideogram model parameters.
+
+During training, a separately obtained, frozen Ideogram 4 model was used as a differentiable downstream
+evaluator of the conditioning interface. Its weights were never trainable, copied into the adapter, or
+included in either release file. The released text encoder cannot generate images or substitute for
+Ideogram by itself.
+
+Ideogram 4 is third-party software/modeling infrastructure and is not distributed here. Anyone choosing
+to use these Qwen weights with Ideogram must obtain Ideogram separately and is independently responsible
+for reviewing and complying with Ideogram's license and usage policy. This repository is not affiliated
+with or endorsed by Ideogram, Inc.

configs/phase2_8state_s020_v1.yaml

@@ -0,0 +1,90 @@
+project:
+  seed: 12345
+  resolution: [512, 512]
+  output_dir: artifacts/phase2_balanced_4000_8state
+
+paths:
+  comfyui: vendor/ComfyUI
+  ideogram4: vendor/ideogram4
+  stock_text_encoder: checkpoints/text_encoders/qwen3vl_8b_fp8_scaled.safetensors
+  conditional: checkpoints/diffusion_models/ideogram4_fp8_scaled.safetensors
+  teacher_pairs: artifacts/civitai_balanced_teacher_generation/nemotron_3_ultra_nvfp4_v1/teacher_pairs_4000.jsonl
+  holdout_approval: data/civitai_balanced/teacher_v1/teacher_pairs_sfw_r_x_xxx_4000.approval.json
+  training_index: artifacts/phase2_balanced_4000_training_dataset/index.jsonl
+
+teacher:
+  provider: fireworks
+  base_url: https://api.fireworks.ai/inference/v1
+  model: accounts/fireworks/models/nemotron-3-ultra-nvfp4
+  temperature: 0.0
+  max_tokens: 16384
+  reasoning_effort: high
+  aspect_ratio_placeholder: "1:1"
+  strip_bboxes: true
+
+conditioning:
+  dtype: float16
+  taps: [0, 3, 6, 9, 12, 15, 18, 21, 24, 27, 30, 33, 35]
+  cache_dir: artifacts/phase2_balanced_4000_teacher_conditioning
+
+trajectory:
+  # Full-trajectory contract: eight evenly distributed pre-step states from
+  # V4_DEFAULT_20. The computed capture steps are [19, 16, 14, 11, 8, 5, 3, 0].
+  # Cache manifests are checked before model load, so one-state data is rejected.
+  state_mode: trajectory
+  states_per_prompt: 8
+  sampling_steps: 20
+  sampler_preset: V4_DEFAULT_20
+  seed: 12345
+  cache_dir: artifacts/phase2_balanced_4000_teacher_trajectories_8state_debanner_s020_v1
+  generation_batch_size: 1
+  parallel_cfg: true
+  correction:
+    tensor: checkpoints/debanner/ideogram4_correction_v1.safetensors
+    metadata: checkpoints/debanner/ideogram4_correction_v1.json
+    # Same authoritative direction and operation, explicitly downscaled for
+    # distillation after the 0.6 target produced an excessive first-state bias.
+    strength: 0.2
+
+training:
+  # Adapter geometry is invariant across all production runs: rank/alpha 64,
+  # all seven projection families, and all 36 Qwen blocks (inclusive range).
+  lora_rank: 64
+  lora_alpha: 64
+  qwen_blocks: [0, 35]
+  deployment_quantization: scaled_fp8_ste
+  batch_size: 2
+  gradient_accumulation: 8
+  adaptive_behavior_batching:
+    enabled: true
+    max_padded_student_tokens: 1017
+    first_oom_student_tokens: 1223
+    benchmark_dir: artifacts/phase2_microbatch_cutoff
+  optimizer: adamw
+  optimizer_state_offload: cpu
+  prune_unused_multimodal: true
+  learning_rate: 0.00032
+  weight_decay: 0.01
+  default_session_steps: 50
+  lr_control:
+    mode: windowed_descent_rollback
+    factor: 0.5
+    minimum_learning_rate: 0.000001
+    window_steps: 50
+    probe_every_steps: 10
+    confirmation_steps: 20
+    minimum_descent_to_noise: 1.0
+    minimum_relative_descent: 0.0
+  validation_every: 50
+  validation_states_per_record: 1
+  gradient_clip_norm: 1.0
+  lambda_velocity: 1.0
+  lambda_states: 0.0
+
+checkpointing:
+  directory: artifacts/phase2_balanced_4000_8state_debanner_s020_v1_checkpoints
+  every_optimizer_steps: 50
+  save_first_optimizer_step: true
+  save_on_interrupt: true
+  resume: auto
+  optimizer_boundary_only: true

manifests/checkpoint_step_00000510.json

@@ -0,0 +1,115 @@
+{
+  "schema_version": 1,
+  "status": "complete",
+  "config_fingerprint": "0667d4ea7a9eeb08101909c8f4b52860faadd491ce6d4ceb8094405e04a5f75e",
+  "dataset_fingerprint": "6cf9eb3d777a338eb007dcc5606b2aac6605bf899a191ea399ccd77d5527acfb",
+  "cursor": {
+    "global_step": 510,
+    "micro_step": 4094,
+    "dataset_epoch": 0,
+    "sample_offset": 8160,
+    "accumulation_step": 0
+  },
+  "extra": {
+    "last_metrics": {
+      "global_step": 510,
+      "behavior_loss": 0.017903656873386353,
+      "behavior_microbatches": 8,
+      "behavior_singleton_microbatches": 0,
+      "oom_replayed_as_singletons": false,
+      "gradient_norm": 0.014914182014763355,
+      "learning_rate_used": 8e-05,
+      "step_seconds": 12.94,
+      "peak_reserved_gib": 24.463,
+      "optimizer_state_device": "cpu_between_updates",
+      "weighted_behavior_objective": 0.017903656873386353,
+      "validation_behavior_loss": 0.017119762562215327,
+      "lr_window_phase": "continue",
+      "lr_window_start_step": 460,
+      "lr_window_end_step": 510,
+      "lr_window_point_count": 6,
+      "lr_window_log_slope_per_step": -0.00037796895479860206,
+      "lr_window_fitted_log_descent": 0.018898447739930102,
+      "lr_window_relative_descent": 0.018720991715869606,
+      "lr_window_residual_mad_scale": 0.0037479312671825525,
+      "lr_window_descent_to_noise": 5.0423677470843025,
+      "lr_window_accepted": true,
+      "lr_window_elbow_step": 510,
+      "lr_training_window_start_step": 470,
+      "lr_training_window_end_step": 510,
+      "lr_training_window_point_count": 5,
+      "lr_training_window_log_slope_per_step": 0.0058621381370863365,
+      "lr_training_window_fitted_log_descent": -0.23448552548345347,
+      "lr_training_window_relative_descent": -0.2642581727774924,
+      "lr_training_window_residual_mad_scale": 0.05576780509580324,
+      "lr_training_window_descent_to_noise": -4.204675530633345,
+      "lr_training_window_accepted": false,
+      "lr_training_window_elbow_step": 480,
+      "lr_window_any_signal_accepted": true,
+      "validation_interval": 10,
+      "next_validation_step": 520,
+      "learning_rate": 8e-05
+    },
+    "reason": "periodic",
+    "parent": null,
+    "lr_control": {
+      "version": 3,
+      "config": {
+        "factor": 0.5,
+        "minimum_learning_rate": 1e-06,
+        "window_steps": 50,
+        "probe_every_steps": 10,
+        "confirmation_steps": 20,
+        "minimum_descent_to_noise": 1.0,
+        "minimum_relative_descent": 0.0
+      },
+      "state": {
+        "learning_rate": 8e-05,
+        "points": [
+          {
+            "step": 510,
+            "loss": 0.017119762562215327
+          }
+        ],
+        "training_points": [],
+        "training_loss_sum": 0.0,
+        "training_loss_count": 0,
+        "last_training_step": 510,
+        "window_start_step": 510,
+        "next_validation_step": 520,
+        "last_analysis": {
+          "start_step": 460,
+          "end_step": 510,
+          "point_count": 6,
+          "log_slope_per_step": -0.00037796895479860206,
+          "fitted_log_descent": 0.018898447739930102,
+          "relative_descent": 0.018720991715869606,
+          "residual_mad_scale": 0.0037479312671825525,
+          "descent_to_noise": 5.0423677470843025,
+          "accepted": true,
+          "elbow_step": 510
+        },
+        "last_training_analysis": {
+          "start_step": 470,
+          "end_step": 510,
+          "point_count": 5,
+          "log_slope_per_step": 0.0058621381370863365,
+          "fitted_log_descent": -0.23448552548345347,
+          "relative_descent": -0.2642581727774924,
+          "residual_mad_scale": 0.05576780509580324,
+          "descent_to_noise": -4.204675530633345,
+          "accepted": false,
+          "elbow_step": 480
+        },
+        "confirming": false,
+        "pending_rollback": null,
+        "reductions": 2
+      }
+    },
+    "rollback_replay": null
+  },
+  "files": {
+    "adapters.safetensors": "85359811e619276f85742072c2b3327915bbb56bcefb874f2f3101a5d1216eef",
+    "training_state.pt": "ddf75f2fc8f599e9fa4ad7c14e3a807b5c1f4e8c3b639796819485b7fc20840f"
+  }
+}