{
  "steps": 60000,
  "session_steps": 30000,
  "session_count": 2,
  "batch_size": 256,
  "grad_accum": 2,
  "seq_len": 1024,
  "model_context": 1024,
  "d_model": 216,
  "n_layers": 10,
  "n_heads": 6,
  "n_kv_heads": 2,
  "chunk": 24,
  "cma_heads": 3,
  "expand": 2,
  "cma_identity_prob": 0.9,
  "lr": 0.0025,
  "linear_decay_start": 30000,
  "cosine_decay_start": 50000,
  "mid_lr": 0.0015,
  "muon_lr": 0.03,
  "muon_momentum": 0.95,
  "muon_ns_steps": 5,
  "muon_adjust_lr_fn": null,
  "warmup": 750,
  "wd": 0.01,
  "grad_clip": 1.0,
  "log_every": 10,
  "diag_every": 1000,
  "eval_every": 10000,
  "val_batch_size": 32,
  "val_batches": 0,
  "val_context": 1024,
  "val_stride": 512,
  "infer_tokens": 512,
  "infer_repeat_penalty": 1.2,
  "infer_prompt": "The process of photosynthesis",
  "lm_eval_tasks": "arc_easy,arc_challenge,hellaswag,piqa",
  "lm_eval_batch_size": "32",
  "lm_eval_device": "cuda",
  "lm_eval_dtype": "bfloat16",
  "lm_eval_softmax_dtype": "float32",
  "lm_eval_expected_version": "0.4.12",
  "lm_eval_retries": 3,
  "lm_eval_export_dir": "CMA_Mini_lm_eval_hf",
  "lm_eval_output_dir": "lm_eval_results_CMA_Mini",
  "arithmark3_choice_batch_size": 64,
  "arithmark3_force_download": false,
  "recipe_version": "CMAMini_Pre_d216_l10_q6_kv2_chunk24_h3_expand2_identity90_train1024_ctx1024_v4k_gpts5m_fullcompile_adam2p5e3_to1p5e3_linear30k50k_cos0_60k_muon3e2_scaled_w750_clip1_31p46B_b256_a2_tpu524k_sessions2x30k_static_fwe55_cos25_fwhq10_math10_interleaved_pinneddata_buf1k_prefetch16_eval1024s512_b32_arithb64_eval10k_diag1k_arithbos_v20",
  "hf_repo_id": "User01110/cma-mini",
  "hf_repo_private": false,
  "hub_upload_retries": 3,
  "resume_branch": "resume-latest",
  "resume_model_file": "resume_model.safetensors",
  "resume_state_file": "resume_state.pt",
  "resume_manifest_file": "resume_manifest.json",
  "tokenizer_name": "AxiomicLabs/GPT-S-5M",
  "tokenizer_revision": "275b9c3ca78736bf6aeb154c7e2d5f5764fe9035",
  "data_seed": 1337,
  "shuffle_buffer": 1024,
  "tokenize_batch_size": 64,
  "prefetch_batches": 16,
  "compile": true
}