Autonomous Space trainer update

README.md

@@ -2,182 +2,23 @@
 language:
 - en
 library_name: transformers
-pipeline_tag: text-generation
 datasets:
 - NorthernTribe-Research/UMSR-v1
 tags:
 - reasoning
-- instruction-following
-- structured-output
-- math
-- science
-- logic
-- strategy
+- autonomous-training
 ---
 
-# UMSR-Reasoner-7B
+# UMSR Reasoner 7B
 
-## Overview
+Standalone reasoning model trained from UMSR-v1 using the autonomous trainer Space.
 
-UMSR-Reasoner-7B is a standalone 7B reasoning model for structured multi-step problem solving.
-
-It is optimized for tasks that require:
-
-- explicit reasoning traces
-- deterministic final-answer formatting
-- consistent performance across math, science, logic, and strategy domains
-
-## Dataset
-
-- Primary dataset: https://huggingface.co/datasets/NorthernTribe-Research/UMSR-v1
-
-## Training Strategy
-
-- student architecture: `NorthernTribe-Research/UMSR-Reasoner-7B`
-- teacher architecture: `NorthernTribe-Research/UMSR-Reasoner-7B` self-distillation (default)
-- objective: blended CE + KL distillation with temperature and weight scheduling
-- continuity: checkpointed autonomous training cycles with resume support
+- Dataset: https://huggingface.co/datasets/NorthernTribe-Research/UMSR-v1
+- Base model: `sshleifer/tiny-gpt2`
+- Model repo: `https://huggingface.co/NorthernTribe-Research/UMSR-Reasoner-7B`
 
 ## Output Contract
 
-For best reliability, prompt the model to end with:
-
-```text
-<final_answer>...</final_answer>
-```
-
-Optional reasoning can be requested in:
-
-```text
-<reasoning>...</reasoning>
-```
-
-## Model Tree
-
-| Variant | Repository | Purpose |
-|---|---|---|
-| Base FP model | `NorthernTribe-Research/UMSR-Reasoner-7B` | Primary inference and fine-tuning target |
-| INT8 runtime profile | `NorthernTribe-Research/UMSR-Reasoner-7B-INT8` | Lower-memory deployment |
-| NF4 runtime profile | `NorthernTribe-Research/UMSR-Reasoner-7B-NF4` | Max compression for constrained GPUs |
-| Smoke INT8 profile | `NorthernTribe-Research/UMSR-Reasoner-7B-Smoke-INT8` | Fast CI/smoke validation profile linked to the main model tree |
-
-## Quickstart
-
-```python
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-model_id = "NorthernTribe-Research/UMSR-Reasoner-7B"
-
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(
-    model_id,
-    torch_dtype=torch.bfloat16,
-    device_map="auto",
-)
-
-messages = [
-    {"role": "system", "content": "Solve step by step and finish with <final_answer>...</final_answer>."},
-    {"role": "user", "content": "If 3x + 5 = 20, what is x?"},
-]
-
-inputs = tokenizer.apply_chat_template(
-    messages,
-    add_generation_prompt=True,
-    return_tensors="pt",
-).to(model.device)
-
-outputs = model.generate(
-    inputs,
-    max_new_tokens=256,
-    temperature=0.2,
-    top_p=0.9,
-)
-
-print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))
-```
-
-## Quantized Runtime
-
-### INT8
-
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
-
-model_id = "NorthernTribe-Research/UMSR-Reasoner-7B"
-bnb_config = BitsAndBytesConfig(load_in_8bit=True)
-
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(
-    model_id,
-    device_map="auto",
-    quantization_config=bnb_config,
-)
-```
-
-### NF4
-
-```python
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
-
-model_id = "NorthernTribe-Research/UMSR-Reasoner-7B"
-bnb_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_use_double_quant=True,
-    bnb_4bit_compute_dtype=torch.bfloat16,
-)
-
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(
-    model_id,
-    device_map="auto",
-    quantization_config=bnb_config,
-)
-```
-
-## Llamafile Packaging
-
-For single-binary deployment, use:
-
-```bash
-python scripts/create_llamafile.py \
-  --gguf /path/to/UMSR-Reasoner-7B.Q4_K_M.gguf \
-  --runtime-bin tools/llamafile \
-  --output dist/UMSR-Reasoner-7B.Q4_K_M.llamafile \
-  --force
-```
-
-## Code-Aware Robust Evaluation
-
-`scripts/eval_reasoner.py` supports code-focused robustness checks:
-
-- code-task detection
-- Python code-block syntax validation
-- optional row-level unit-test execution
-- optional TensorFlow-backed multi-candidate scorer
-
-## Trainer Integration
-
-An autonomous trainer Space is available for continuous training cycles against UMSR-v1. It supports:
-
-- teacher-student distillation mode with configurable in-house teacher model
-- live run telemetry (`live_progress.json`, `live_events.jsonl`) for real-time monitoring
-- scheduled or continuous operation
-- checkpoint auto-resume (`UMSR_RESUME_FROM_CHECKPOINT=auto`)
-- warmup-step and warmup-ratio control
-- push-to-hub automation
-- run monitoring through live dashboard and logs
-
-## Best Practices
-
-- keep prompts explicit about output tags
-- validate final answers for high-stakes workflows
-- prefer domain-specific evaluation before production deployment
-
-## Limitations
+Use:
 
-- reasoning text may contain errors even when final format is correct
-- quality depends on prompt clarity and task scope
-- not suitable as a sole decision-maker for legal, medical, or safety-critical use
+`<final_answer>...</final_answer>`

config.json

@@ -18,7 +18,7 @@
   "n_inner": null,
   "n_layer": 2,
   "n_positions": 1024,
-  "pad_token_id": null,
+  "pad_token_id": 50256,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -34,7 +34,7 @@
       "max_length": 50
     }
   },
-  "tie_word_embeddings": true,
+  "tie_word_embeddings": false,
   "transformers_version": "5.2.0",
   "use_cache": false,
   "vocab_size": 50257

metrics/eval_metrics.json

@@ -1,8 +1,8 @@
 {
   "epoch": 1.0,
-  "eval_loss": 5.414119720458984,
-  "eval_runtime": 0.7383,
-  "eval_samples": 8,
-  "eval_samples_per_second": 10.836,
-  "eval_steps_per_second": 10.836
-}
+  "eval_loss": 10.716222763061523,
+  "eval_runtime": 2.0679,
+  "eval_samples": 64,
+  "eval_samples_per_second": 30.95,
+  "eval_steps_per_second": 30.95
+}

metrics/train_metrics.json

@@ -1,16 +1,9 @@
 {
-  "ce_weight_end": 0.5,
-  "ce_weight_start": 0.5,
   "epoch": 1.0,
-  "kd_weight_end": 0.5,
-  "kd_weight_start": 0.5,
-  "teacher_count": 1,
-  "temperature_end": 1.5,
-  "temperature_start": 2.0,
-  "total_flos": 3359425752.0,
-  "train_loss": 5.411877933301423,
-  "train_runtime": 7.7818,
-  "train_samples": 19,
-  "train_samples_per_second": 2.442,
-  "train_steps_per_second": 2.442
-}
+  "total_flos": 39501942396.0,
+  "train_loss": 10.738998085260391,
+  "train_runtime": 49.7234,
+  "train_samples": 256,
+  "train_samples_per_second": 5.148,
+  "train_steps_per_second": 5.148
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b75f6f94d4b470fd42d5cb3c7135ca7c1d669d0514eddce08abe5825cf9d5c48
+oid sha256:8af636bf1ea0ba12e8e0ed9858fe7a4fb9ce267806245af516a5f024c1c370c1
 size 413296

run_summary.json

@@ -1,15 +1,17 @@
 {
-  "ce_weight_end": 0.5,
-  "ce_weight_start": 0.5,
+  "base_model": "sshleifer/tiny-gpt2",
+  "bf16": false,
+  "cuda_available": false,
   "dataset_id": "NorthernTribe-Research/UMSR-v1",
-  "eval_rows": 8,
-  "kd_weight_end": 0.5,
-  "kd_weight_start": 0.5,
-  "output_dir": "outputs/umsr_reasoner_7b_standalone",
-  "student_model": "NorthernTribe-Research/UMSR-Reasoner-7B",
-  "teacher_count": 1,
-  "teacher_model": "NorthernTribe-Research/UMSR-Reasoner-7B",
-  "temperature_end": 1.5,
-  "temperature_start": 2.0,
-  "train_rows": 19
+  "device": "cpu",
+  "eval_rows": 64,
+  "finished_at": "2026-02-23T22:10:16.635458+00:00",
+  "fp16": false,
+  "mps_available": false,
+  "output_dir": "/app/runs/20260223_220918",
+  "target_repo_id": "NorthernTribe-Research/UMSR-Reasoner-7B",
+  "tie_word_embeddings": false,
+  "total_train_steps_estimate": 256,
+  "train_rows": 256,
+  "warmup_steps": 0
 }

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

trainer_state.json

@@ -3,192 +3,282 @@
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 1.0,
-  "eval_steps": 4,
-  "global_step": 19,
+  "eval_steps": 25,
+  "global_step": 256,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.05263157894736842,
-      "grad_norm": 0.374282568693161,
-      "learning_rate": 0.0001,
-      "loss": 5.411169052124023,
-      "step": 1
+      "epoch": 0.0390625,
+      "grad_norm": 0.6599220633506775,
+      "learning_rate": 9.6484375e-05,
+      "loss": 10.769454956054688,
+      "step": 10
     },
     {
-      "epoch": 0.10526315789473684,
-      "grad_norm": 0.4834381341934204,
-      "learning_rate": 9.931806517013612e-05,
-      "loss": 5.413699626922607,
-      "step": 2
+      "epoch": 0.078125,
+      "grad_norm": 0.7802038192749023,
+      "learning_rate": 9.257812500000001e-05,
+      "loss": 10.763140106201172,
+      "step": 20
     },
     {
-      "epoch": 0.15789473684210525,
-      "grad_norm": 1.9866410493850708,
-      "learning_rate": 9.729086208503174e-05,
-      "loss": 5.407270431518555,
-      "step": 3
+      "epoch": 0.09765625,
+      "eval_loss": 10.76131820678711,
+      "eval_runtime": 2.0075,
+      "eval_samples_per_second": 31.881,
+      "eval_steps_per_second": 31.881,
+      "step": 25
     },
     {
-      "epoch": 0.21052631578947367,
-      "grad_norm": 0.13184547424316406,
-      "learning_rate": 9.397368756032445e-05,
-      "loss": 5.411037921905518,
-      "step": 4
+      "epoch": 0.1171875,
+      "grad_norm": 0.17565655708312988,
+      "learning_rate": 8.8671875e-05,
+      "loss": 10.768231201171876,
+      "step": 30
     },
     {
-      "epoch": 0.21052631578947367,
-      "eval_loss": 5.415262222290039,
-      "eval_runtime": 0.6782,
-      "eval_samples_per_second": 11.796,
-      "eval_steps_per_second": 11.796,
-      "step": 4
+      "epoch": 0.15625,
+      "grad_norm": 0.4683985710144043,
+      "learning_rate": 8.4765625e-05,
+      "loss": 10.772106170654297,
+      "step": 40
     },
     {
-      "epoch": 0.2631578947368421,
-      "grad_norm": 0.08807552605867386,
-      "learning_rate": 8.945702546981969e-05,
-      "loss": 5.413403034210205,
-      "step": 5
+      "epoch": 0.1953125,
+      "grad_norm": 0.3628169298171997,
+      "learning_rate": 8.0859375e-05,
+      "loss": 10.764241790771484,
+      "step": 50
     },
     {
-      "epoch": 0.3157894736842105,
-      "grad_norm": 0.3944004476070404,
-      "learning_rate": 8.386407858128706e-05,
-      "loss": 5.411047458648682,
-      "step": 6
+      "epoch": 0.1953125,
+      "eval_loss": 10.752297401428223,
+      "eval_runtime": 1.997,
+      "eval_samples_per_second": 32.049,
+      "eval_steps_per_second": 32.049,
+      "step": 50
     },
     {
-      "epoch": 0.3684210526315789,
-      "grad_norm": 0.19243471324443817,
-      "learning_rate": 7.734740790612136e-05,
-      "loss": 5.410379886627197,
-      "step": 7
+      "epoch": 0.234375,
+      "grad_norm": 0.6150558590888977,
+      "learning_rate": 7.695312500000001e-05,
+      "loss": 10.760368347167969,
+      "step": 60
     },
     {
-      "epoch": 0.42105263157894735,
-      "grad_norm": 1.1386080980300903,
-      "learning_rate": 7.008477123264848e-05,
-      "loss": 5.4107584953308105,
-      "step": 8
+      "epoch": 0.2734375,
+      "grad_norm": 0.605256974697113,
+      "learning_rate": 7.3046875e-05,
+      "loss": 10.758135986328124,
+      "step": 70
     },
     {
-      "epoch": 0.42105263157894735,
-      "eval_loss": 5.414775848388672,
-      "eval_runtime": 0.6096,
-      "eval_samples_per_second": 13.123,
-      "eval_steps_per_second": 13.123,
-      "step": 8
+      "epoch": 0.29296875,
+      "eval_loss": 10.743587493896484,
+      "eval_runtime": 2.0728,
+      "eval_samples_per_second": 30.876,
+      "eval_steps_per_second": 30.876,
+      "step": 75
     },
     {
-      "epoch": 0.47368421052631576,
-      "grad_norm": 1.593002200126648,
-      "learning_rate": 6.227427435703997e-05,
-      "loss": 5.406350135803223,
-      "step": 9
+      "epoch": 0.3125,
+      "grad_norm": 0.3574382960796356,
+      "learning_rate": 6.9140625e-05,
+      "loss": 10.750237274169923,
+      "step": 80
     },
     {
-      "epoch": 0.5263157894736842,
-      "grad_norm": 0.2701893746852875,
-      "learning_rate": 5.4128967273616625e-05,
-      "loss": 5.415624141693115,
-      "step": 10
+      "epoch": 0.3515625,
+      "grad_norm": 0.6408470869064331,
+      "learning_rate": 6.5234375e-05,
+      "loss": 10.751436614990235,
+      "step": 90
     },
     {
-      "epoch": 0.5789473684210527,
-      "grad_norm": 2.5317883491516113,
-      "learning_rate": 4.5871032726383386e-05,
-      "loss": 5.4125213623046875,
-      "step": 11
+      "epoch": 0.390625,
+      "grad_norm": 0.2543087303638458,
+      "learning_rate": 6.132812500000001e-05,
+      "loss": 10.753249359130859,
+      "step": 100
     },
     {
-      "epoch": 0.631578947368421,
-      "grad_norm": 0.18132847547531128,
-      "learning_rate": 3.772572564296005e-05,
-      "loss": 5.411061763763428,
-      "step": 12
+      "epoch": 0.390625,
+      "eval_loss": 10.736135482788086,
+      "eval_runtime": 1.9495,
+      "eval_samples_per_second": 32.828,
+      "eval_steps_per_second": 32.828,
+      "step": 100
     },
     {
-      "epoch": 0.631578947368421,
-      "eval_loss": 5.414316177368164,
-      "eval_runtime": 0.6242,
-      "eval_samples_per_second": 12.817,
-      "eval_steps_per_second": 12.817,
-      "step": 12
+      "epoch": 0.4296875,
+      "grad_norm": 0.29619327187538147,
+      "learning_rate": 5.7421875000000005e-05,
+      "loss": 10.720957946777343,
+      "step": 110
     },
     {
-      "epoch": 0.6842105263157895,
-      "grad_norm": 0.25826773047447205,
-      "learning_rate": 2.991522876735154e-05,
-      "loss": 5.412132740020752,
-      "step": 13
+      "epoch": 0.46875,
+      "grad_norm": 0.19426824152469635,
+      "learning_rate": 5.3515625e-05,
+      "loss": 10.75610580444336,
+      "step": 120
     },
     {
-      "epoch": 0.7368421052631579,
-      "grad_norm": 0.32883742451667786,
-      "learning_rate": 2.2652592093878666e-05,
-      "loss": 5.409476280212402,
-      "step": 14
+      "epoch": 0.48828125,
+      "eval_loss": 10.730175018310547,
+      "eval_runtime": 2.0434,
+      "eval_samples_per_second": 31.32,
+      "eval_steps_per_second": 31.32,
+      "step": 125
     },
     {
-      "epoch": 0.7894736842105263,
-      "grad_norm": 0.15471753478050232,
-      "learning_rate": 1.6135921418712956e-05,
-      "loss": 5.413200855255127,
-      "step": 15
+      "epoch": 0.5078125,
+      "grad_norm": 0.400691419839859,
+      "learning_rate": 4.9609375000000005e-05,
+      "loss": 10.729013061523437,
+      "step": 130
     },
     {
-      "epoch": 0.8421052631578947,
-      "grad_norm": 0.2990401089191437,
-      "learning_rate": 1.0542974530180327e-05,
-      "loss": 5.4155683517456055,
-      "step": 16
+      "epoch": 0.546875,
+      "grad_norm": 0.2926430106163025,
+      "learning_rate": 4.5703125e-05,
+      "loss": 10.718487548828126,
+      "step": 140
     },
     {
-      "epoch": 0.8421052631578947,
-      "eval_loss": 5.414139747619629,
-      "eval_runtime": 0.7326,
-      "eval_samples_per_second": 10.92,
-      "eval_steps_per_second": 10.92,
-      "step": 16
+      "epoch": 0.5859375,
+      "grad_norm": 0.24082393944263458,
+      "learning_rate": 4.1796875000000005e-05,
+      "loss": 10.736891174316407,
+      "step": 150
     },
     {
-      "epoch": 0.8947368421052632,
-      "grad_norm": 2.2788937091827393,
-      "learning_rate": 6.026312439675552e-06,
-      "loss": 5.411947727203369,
-      "step": 17
+      "epoch": 0.5859375,
+      "eval_loss": 10.725324630737305,
+      "eval_runtime": 2.1134,
+      "eval_samples_per_second": 30.283,
+      "eval_steps_per_second": 30.283,
+      "step": 150
     },
     {
-      "epoch": 0.9473684210526315,
-      "grad_norm": 0.20979730784893036,
-      "learning_rate": 2.7091379149682685e-06,
-      "loss": 5.413649082183838,
-      "step": 18
+      "epoch": 0.625,
+      "grad_norm": 0.371867835521698,
+      "learning_rate": 3.7890625e-05,
+      "loss": 10.728065490722656,
+      "step": 160
     },
     {
-      "epoch": 1.0,
-      "grad_norm": 0.20296302437782288,
-      "learning_rate": 6.819348298638839e-07,
-      "loss": 5.415382385253906,
-      "step": 19
+      "epoch": 0.6640625,
+      "grad_norm": 0.3023074269294739,
+      "learning_rate": 3.3984375000000004e-05,
+      "loss": 10.73614501953125,
+      "step": 170
+    },
+    {
+      "epoch": 0.68359375,
+      "eval_loss": 10.721412658691406,
+      "eval_runtime": 2.1412,
+      "eval_samples_per_second": 29.89,
+      "eval_steps_per_second": 29.89,
+      "step": 175
+    },
+    {
+      "epoch": 0.703125,
+      "grad_norm": 0.38127991557121277,
+      "learning_rate": 3.0078125e-05,
+      "loss": 10.722113037109375,
+      "step": 180
+    },
+    {
+      "epoch": 0.7421875,
+      "grad_norm": 0.3930608928203583,
+      "learning_rate": 2.6171875e-05,
+      "loss": 10.726372528076173,
+      "step": 190
+    },
+    {
+      "epoch": 0.78125,
+      "grad_norm": 0.3989920914173126,
+      "learning_rate": 2.2265625e-05,
+      "loss": 10.720677185058594,
+      "step": 200
+    },
+    {
+      "epoch": 0.78125,
+      "eval_loss": 10.718664169311523,
+      "eval_runtime": 2.1839,
+      "eval_samples_per_second": 29.305,
+      "eval_steps_per_second": 29.305,
+      "step": 200
+    },
+    {
+      "epoch": 0.8203125,
+      "grad_norm": 0.20773838460445404,
+      "learning_rate": 1.8359375e-05,
+      "loss": 10.722401428222657,
+      "step": 210
+    },
+    {
+      "epoch": 0.859375,
+      "grad_norm": 0.31527552008628845,
+      "learning_rate": 1.4453125e-05,
+      "loss": 10.71902084350586,
+      "step": 220
+    },
+    {
+      "epoch": 0.87890625,
+      "eval_loss": 10.71699047088623,
+      "eval_runtime": 2.0948,
+      "eval_samples_per_second": 30.552,
+      "eval_steps_per_second": 30.552,
+      "step": 225
+    },
+    {
+      "epoch": 0.8984375,
+      "grad_norm": 0.2394668161869049,
+      "learning_rate": 1.0546875e-05,
+      "loss": 10.706802368164062,
+      "step": 230
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 0.23905383050441742,
+      "learning_rate": 6.6406250000000005e-06,
+      "loss": 10.697933959960938,
+      "step": 240
+    },
+    {
+      "epoch": 0.9765625,
+      "grad_norm": 0.3481399416923523,
+      "learning_rate": 2.734375e-06,
+      "loss": 10.72392578125,
+      "step": 250
+    },
+    {
+      "epoch": 0.9765625,
+      "eval_loss": 10.716254234313965,
+      "eval_runtime": 2.164,
+      "eval_samples_per_second": 29.576,
+      "eval_steps_per_second": 29.576,
+      "step": 250
     },
     {
       "epoch": 1.0,
-      "step": 19,
-      "total_flos": 3359425752.0,
-      "train_loss": 5.411877933301423,
-      "train_runtime": 7.7818,
-      "train_samples_per_second": 2.442,
-      "train_steps_per_second": 2.442
+      "step": 256,
+      "total_flos": 39501942396.0,
+      "train_loss": 10.738998085260391,
+      "train_runtime": 49.7234,
+      "train_samples_per_second": 5.148,
+      "train_steps_per_second": 5.148
     }
   ],
-  "logging_steps": 1,
-  "max_steps": 19,
+  "logging_steps": 10,
+  "max_steps": 256,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 8,
+  "save_steps": 25,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -201,7 +291,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3359425752.0,
+  "total_flos": 39501942396.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a142cd858828160b38820775c31c8d19bc13769b29cdfea16c1835758c53a125
-size 5265
+oid sha256:cd3f671622cfbd73cb8882721494529eb95691b413c227bd5e8e5d124f3ca09e
+size 5201