Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,12 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+round1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+adapters/pi1_phaseB/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+adapters/pi2_phaseB/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+final/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+adapters/pi3_phaseA/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+adapters/pi1_phaseA/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+adapters/pi2_phaseA/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+adapters/pi3_phaseB/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+round2/tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapters/pi1_phaseA/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /workspace/ThinkingWithoutWordsRepro/runs/qwen3-4b-abs/base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/workspace/ThinkingWithoutWordsRepro/runs/qwen3-4b-abs/base
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

adapters/pi1_phaseA/adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/ThinkingWithoutWordsRepro/runs/qwen3-4b-abs/base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapters/pi1_phaseA/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd679cc7b11ce79788b9cddff6b71ef81082b828f5d9bb41880675e018ee8f76
+size 1818075528

adapters/pi1_phaseA/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

adapters/pi1_phaseA/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c60a2ea77104115b88753d3a7a341035634636f804ea3f85624df8aefc7a325
+size 11434974

adapters/pi1_phaseA/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

adapters/pi1_phaseB/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e55c05feb537ec57d7fda3a1d69292a83f0683e7693557e31d31cecafbf01d03
+size 1818075528

adapters/pi1_phaseB/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c60a2ea77104115b88753d3a7a341035634636f804ea3f85624df8aefc7a325
+size 11434974

adapters/pi2_phaseA/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b20bc6250a5c1f437704c3a694ddffa40f0973176011d8332c3db0723ba721
+size 1818075528

adapters/pi2_phaseA/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c60a2ea77104115b88753d3a7a341035634636f804ea3f85624df8aefc7a325
+size 11434974

adapters/pi2_phaseB/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d790f3eecb4cd9f44408ed40ba620df60d6c68708fffa593a26b15e107a49bad
+size 1818075528

adapters/pi2_phaseB/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c60a2ea77104115b88753d3a7a341035634636f804ea3f85624df8aefc7a325
+size 11434974

adapters/pi3_phaseA/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a578363ceb85b312e0dc697c3a655ba0a4e655d55e6941d02aa0a7a7a698f05
+size 1818075528

adapters/pi3_phaseA/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c60a2ea77104115b88753d3a7a341035634636f804ea3f85624df8aefc7a325
+size 11434974

adapters/pi3_phaseB/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdbe06f599f543838a6d7bd568a13422f423afd882b39bf1a71f6d737bebf4c9
+size 1818075528

adapters/pi3_phaseB/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c60a2ea77104115b88753d3a7a341035634636f804ea3f85624df8aefc7a325
+size 11434974

docs/20260511_reader.md

@@ -0,0 +1,89 @@
+# Abstract-CoT on Qwen3-4B — Reader Report
+
+## What we ran
+
+Three policy-iteration (PI) rounds of the paper's Abstract-CoT warm-up on Qwen3-4B / MATH-500. The idea: replace the model's normal verbal chain-of-thought with a short sequence of tokens from a reserved 64-symbol "abstract" vocabulary `V_abs = {<TOKEN_A>, ..., <TOKEN_BL>}`. The model is taught to use this short discrete trace as its "reasoning scratchpad" before emitting the answer.
+
+```
+prompt  ─►  <beginabstract>  z_1 ... z_m  <endabstract>  answer
+            └─────── z̃ ∈ V_abs^m, m ≤ 128 ───────┘
+```
+
+Each PI round has two phases, both trained as standard SFT against the Dolci-Think dataset:
+
+- **Phase A — Bottleneck SFT.** Train on the packed sequence `[prompt; verbal-CoT; z̃; answer]` with a custom attention mask: the answer is **forbidden from attending to the verbal CoT**. So any information from the CoT that the answer needs must flow through `z̃`. This is what teaches the abstract trace to act as a compressed reasoning bridge.
+  - Round 1: `z̃` is just random V_abs tokens (no signal yet).
+  - Rounds 2+: `z̃` is sampled on-policy from the previous round's model, conditioned on `(prompt, CoT)`. Now the bottleneck has a real teacher signal.
+
+- **Phase B — Self-distillation.** Train on `[prompt; z̃; answer]` with normal causal attention, where `z̃` is now generated from the prompt alone (no CoT in context). This teaches the model to *produce* the abstract trace directly from the question, not just consume one provided by a teacher.
+
+After T=3 rounds of A→B→A→B→A→B, the model can in principle take a math problem, emit ~20 abstract tokens, then emit the answer — using the abstract trace as its only thinking.
+
+## Results
+
+| Run | MATH-500 acc | Mean tokens |
+|---|---|---|
+| Paper Baseline (verbal CoT) | 83.2 | 1087 |
+| **Our Baseline** (Qwen3-4B, verbal CoT) | **84.60** | **1045** |
+| Paper Abstract-CoT Warm-up | 86.2 | 168 |
+| Prior smoke (T=1, 5k, 1 epoch) | 73.20 | 433 |
+| **This run** (T=3, 5k, 1 epoch) | **72.00** | **432** |
+
+## GPU resources — this run vs. prior smoke vs. paper
+
+| | This run | Prior smoke (paper repo) | Paper |
+|---|---|---|---|
+| GPUs for SFT | **2× A100-SXM4-80GB** | 2× A100-SXM4-40GB | 8× H100-80GB |
+| Total VRAM | 160 GB | 80 GB | 640 GB |
+| Total GPU-hours used | **~22 GPU-hr** (11 hr × 2) | ~2 GPU-hr (1 hr × 2) | not stated, RL adds 32× H100 |
+| Training memory headroom | comfortable at seq 8k, LoRA | smoke hit ZeRO-3 OOM at seq>1024 | full FT @ seq ~16k probably |
+
+What having 80 GB cards unlocked vs. the smoke's 40 GB:
+
+1. **seq_len 8192** for Phase A (vs the smoke's 2048). At 2k, 98% of Dolci CoTs got truncated from the right, so the bottleneck mostly compressed a problem statement. At 8k, ~60% of CoTs fit fully and the actual reasoning makes it into training.
+2. **vLLM at TP=2 for inference** without idling a card. The smoke ran on 3× 40GB; Qwen3-4B has 32 heads so TP must divide 32, forcing TP=2 with one GPU idle during eval. On our 2-GPU box, both cards work.
+3. **Full fine-tuning is now feasible** (paper's path). Adam fp32 states for the full 4.86 B params (~40 GB) fit in ZeRO-3 across 2× 80GB without needing CPU offload. We didn't use this — kept LoRA per the smoke's recommendation for the 12 hr budget — but it's the obvious next experiment, and it would not have been possible on the smoke hardware.
+
+What we *didn't* get from the bigger cards: per-step training speed. Both A100-40GB and A100-80GB are the same GA100 silicon — same SM count, same clock. The 80GB version has ~25% more HBM bandwidth, which slightly helps inference (memory-bound) but not training (compute-bound on bf16 tensor cores). Measured per-step time at seq 2k matched the smoke (~12 s/step); at seq 8k we measured ~72 s/step (~5.7× slower due to attention scaling quadratically).
+
+## What the numbers tell us
+
+**Baseline reproduces the paper.** Our 84.6 vs paper 83.2 is within evaluation noise — the verbal-CoT pipeline is calibrated correctly.
+
+**Three rounds didn't beat one.** This is the most interesting finding. The paper's signature result is that on-policy iteration (T=3) lifts accuracy substantially over T=1. We saw no lift: 72.0 vs 73.2 is within the temp=0.7 sampling noise of the abstract trace stage.
+
+**But the optimizer was clearly working.** Each round started from a lower loss than the previous one:
+
+| Round | Phase A start loss | Phase B start loss |
+|---|---|---|
+| 1 (random abstract traces) | 3.49 | 0.49 |
+| 2 (on-policy traces from round 1) | 0.35 | 0.29 |
+| 3 (on-policy traces from round 2) | 0.27 | 0.21 |
+
+The model is absorbing the on-policy abstract traces — they're carrying real signal by round 3. That signal just isn't translating to MATH-500 accuracy.
+
+**Token count converged.** Mean total tokens stayed flat at ~432 (vs paper's 168). The model isn't learning to be as terse as the paper's, but it's also not bloating responses round-over-round.
+
+## Why T=3 didn't lift accuracy — most-likely explanations
+
+1. **LoRA is the binding constraint.** With ~17% of parameters trainable (mostly the new abstract-token embeddings, plus rank-32 adapters), the model's existing "answer-from-prompt" reflex is too strong for a short discrete bottleneck to redirect. The paper does full fine-tuning, where the existing math knowledge can be *reshaped* to actually route through the abstract trace. We can't reshape with LoRA — we can only nudge.
+
+2. **5k samples is far below the paper's 600k.** On-policy iteration needs enough novel `(problem, CoT)` pairs that each round produces meaningfully different abstract traces. At 5k, rounds 2 and 3 mostly revisit the same examples with mild trace variations — not much new pressure on the bottleneck.
+
+3. **Eval stochasticity.** The abstract trace is sampled at temperature 0.7 (the m_min=16 length floor requires some sampling). Run-to-run variance on N=500 examples is 1–2 points. Both 73.2 (smoke) and 72.0 (this run) are within that band.
+
+4. **Possible counterintuitive seq_len effect.** We bumped max sequence length from 2048 to 8192 so the model could see full CoTs during Phase A bottleneck training. But the bottleneck's "quality" depends on the *gap* between what reaches the abstract trace and what the answer can reconstruct from prompt alone. Letting more CoT into the training context may have made it easier for the model to learn shortcuts that don't depend on Z̃. Worth ablating.
+
+## What would move the number
+
+In rough order of expected lift:
+
+1. **Full fine-tuning** instead of LoRA. This is the smoke report's #1 recommendation and our experience confirms it — the paper's gap is most plausibly explained by representation capacity, not data scale.
+2. **More data** (30k–100k). Probably needed to actually exploit T=3.
+3. **More epochs per phase** (paper uses 3, we used 1).
+
+Of these, **full-FT at 5k** is the cheapest diagnostic — if it lifts accuracy substantially, data scaling is the next lever; if not, we know the issue is elsewhere (e.g., reward shaping, which the paper's RL stage handles but we skipped).
+
+## Bottom line
+
+The pipeline works end-to-end and reproduces the smoke result. The on-policy iteration is doing what it's supposed to mechanically (per the per-round loss curves), but the LoRA + 5k-data regime caps the accuracy delta at noise level. The gap to the paper's 86.2 is real and consistent with the known scope reductions (LoRA, 1/120 the data, 1/3 the epochs, no RL).

final/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae0238201e28f026d6000c124dcd5c123ec576c72f3836bed06262412d9d1a5f
+size 8820836280

final/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c60a2ea77104115b88753d3a7a341035634636f804ea3f85624df8aefc7a325
+size 11434974

round1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd3a7600bc2e6044fd79f4f3a18bf9cd3181bf0757622a973a6b6a4956876d74
+size 8820836280

round1/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c60a2ea77104115b88753d3a7a341035634636f804ea3f85624df8aefc7a325
+size 11434974

round2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9c08b2a3b56e83eef794dfe369054e1b5dd815e5470c4f8992eea4e12342533
+size 8820836280

round2/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c60a2ea77104115b88753d3a7a341035634636f804ea3f85624df8aefc7a325
+size 11434974

train_logs/pi3_phaseA.json

@@ -0,0 +1,75 @@
+{
+  "losses": [
+    0.2751981415989576,
+    0.22893165266577853,
+    0.24834042781731114,
+    0.2638388895960816,
+    0.23417620072723366,
+    0.24215587118524126,
+    0.2851439667691011,
+    0.2613255390126142,
+    0.29196599322604017,
+    0.27143954291314004,
+    0.2879517031600699,
+    0.28859320177070913,
+    0.28058985095995015,
+    0.32684289703611286,
+    0.2814401665353216,
+    0.316986553161405,
+    0.29619569072965535,
+    0.31013335563475264,
+    0.3364840148482472,
+    0.3246558667509817,
+    0.3450019852258265,
+    0.36042039859457875,
+    0.359003718016902,
+    0.33632316675502805,
+    0.34056199092883616,
+    0.4061928411683766,
+    0.3674649982713163,
+    0.3189254213997629,
+    0.3698235720337834,
+    0.3649632065091282,
+    0.34908437901176514
+  ],
+  "lrs": [
+    6.666666666666667e-05,
+    9.993008576227247e-05,
+    9.937194443381972e-05,
+    9.826190093588563e-05,
+    9.661236384224129e-05,
+    9.444177243274618e-05,
+    9.177439057064683e-05,
+    8.864003547001915e-05,
+    8.507374438531607e-05,
+    8.111538294891684e-05,
+    7.680919953486048e-05,
+    7.220333063028872e-05,
+    6.734926274378312e-05,
+    6.230125686563068e-05,
+    5.7115741913664264e-05,
+    5.185068394501791e-05,
+    4.6564938185035956e-05,
+    4.131759111665349e-05,
+    3.616729998467365e-05,
+    3.1171637098265064e-05,
+    2.638644626136587e-05,
+    2.1865218525109495e-05,
+    1.7658494240397126e-05,
+    1.3813298094746491e-05,
+    1.037261344883343e-05,
+    7.374901848832683e-06,
+    4.853673085668947e-06,
+    2.8371106072518195e-06,
+    1.3477564710088098e-06,
+    4.02259358460233e-07,
+    1.1188468644907079e-08
+  ],
+  "wallclock_s": 10572,
+  "n_examples": 5000,
+  "epochs": 1,
+  "mode": "bottleneck",
+  "lora_rank": 32,
+  "total_opt_steps": 156,
+  "num_processes": 2
+}

train_logs/pi3_phaseB.json

@@ -0,0 +1,75 @@
+{
+  "losses": [
+    0.24705615827115252,
+    0.19863037412578705,
+    0.20961245244543533,
+    0.23088445312132536,
+    0.20231807196396404,
+    0.21607737393860588,
+    0.2541877782714437,
+    0.23250892728756298,
+    0.26798237174225503,
+    0.2450843573300517,
+    0.26578180299547965,
+    0.26796957241640484,
+    0.25621661408949875,
+    0.30977868895424765,
+    0.26767159106384497,
+    0.3011666447739117,
+    0.2829906645929441,
+    0.2978396859412896,
+    0.3276536007644609,
+    0.3177644655283075,
+    0.3392833017860539,
+    0.35701846808369736,
+    0.3581092601059936,
+    0.3342221752507612,
+    0.34096981105394664,
+    0.4076683118997607,
+    0.36950865692924706,
+    0.32229581456631423,
+    0.37231990886793936,
+    0.36889135412639007,
+    0.35545787583687344
+  ],
+  "lrs": [
+    6.666666666666667e-05,
+    9.993008576227247e-05,
+    9.937194443381972e-05,
+    9.826190093588563e-05,
+    9.661236384224129e-05,
+    9.444177243274618e-05,
+    9.177439057064683e-05,
+    8.864003547001915e-05,
+    8.507374438531607e-05,
+    8.111538294891684e-05,
+    7.680919953486048e-05,
+    7.220333063028872e-05,
+    6.734926274378312e-05,
+    6.230125686563068e-05,
+    5.7115741913664264e-05,
+    5.185068394501791e-05,
+    4.6564938185035956e-05,
+    4.131759111665349e-05,
+    3.616729998467365e-05,
+    3.1171637098265064e-05,
+    2.638644626136587e-05,
+    2.1865218525109495e-05,
+    1.7658494240397126e-05,
+    1.3813298094746491e-05,
+    1.037261344883343e-05,
+    7.374901848832683e-06,
+    4.853673085668947e-06,
+    2.8371106072518195e-06,
+    1.3477564710088098e-06,
+    4.02259358460233e-07,
+    1.1188468644907079e-08
+  ],
+  "wallclock_s": 947,
+  "n_examples": 5000,
+  "epochs": 1,
+  "mode": "distill",
+  "lora_rank": 32,
+  "total_opt_steps": 156,
+  "num_processes": 2
+}