gpt54-mini-standalone-qwen3-4b-sft-textcraft-20260920

Qwen/Qwen3-4B trained with SFT using teacher gpt-5.4-mini. This is the final checkpoint of a completed textcraft stage: five epochs, 55 optimizer updates in that stage.

Standalone training initialized independently from the base model; this is not a sequential checkpoint.

Training-completion evidence: Historical audit verified all expected optimizer updates and all five epoch checkpoint exports; these runs predate stage-manifest.json.

Evaluation uses avg@4: mean success across four attempts per official test task, not best-of-four success. Temperature 0.4, top-p 1.0, top-k 20, thinking disabled, and 512 generated tokens per turn.

Environment Successes / attempts avg@4 success Episode errors
textcraft 318 / 400 79.5000% 0

Saved-result checks verified exact task/sample coverage and score consistency. Zero episode errors does not imply every generated turn was well formed.

Provenance and interpretation notes:

  • This is one trained checkpoint, not evidence of a general method advantage or replication across training seeds.
  • The selection inventory records file names, sizes and modification times. It is not a tensor-byte hash binding to historical evaluation responses.
  • Use the complete repaired evaluation, not the original error-excluding summary. Some repaired artifacts reuse complete original rollouts; historical serving logs are incomplete.
  • Historical SFT and ROSE recipes differ in learning-rate scheduling, weight decay, parameter precision, formatting, and some training turn caps. This is not an objective-only ablation.
  • TextCraft-4B repaired evaluation used different recipe ordering and distractor sets from the original server instance; available repaired comparisons share observations within that lane.

The HF export is stored at the repository root; configuration, tokenizer, and all weight shards are included. Optimizer state, raw logs, and teacher trajectories are not included. Machine-readable source references and checksums are in experiment.json.

from transformers import AutoTokenizer, AutoModelForCausalLM
repo_id = "Diluner/gpt54-mini-standalone-qwen3-4b-sft-textcraft-20260920"
tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForCausalLM.from_pretrained(repo_id, torch_dtype="auto")

Repository access is public, as authorized by the experiment owner. No license is asserted here; consult the base model and applicable terms.

Downloads last month
15
Safetensors
Model size
4B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Diluner/gpt54-mini-standalone-qwen3-4b-sft-textcraft-20260920

Finetuned
Qwen/Qwen3-4B
Finetuned
(1,305)
this model