{
  "parameters": 900002,
  "architecture": {
    "vocab_size": 384,
    "hidden_size": 96,
    "num_hidden_layers": 6,
    "num_attention_heads": 6,
    "num_key_value_heads": 2,
    "head_dim": 16,
    "intermediate_size": 380,
    "refresh_layers": [
      3,
      5
    ],
    "refresh_kernel_size": 9,
    "refresh_alpha_init": 0.0,
    "max_position_embeddings": 4096,
    "rope_theta": 100000.0,
    "rms_norm_eps": 1e-06,
    "initializer_range": 0.02,
    "use_cache": true,
    "transformers_version": "5.15.0",
    "architectures": null,
    "output_hidden_states": false,
    "return_dict": true,
    "dtype": null,
    "chunk_size_feed_forward": 0,
    "is_encoder_decoder": false,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "problem_type": null,
    "_name_or_path": "",
    "tie_word_embeddings": true,
    "bos_token_id": 1,
    "eos_token_id": 2,
    "pad_token_id": 0,
    "unk_token_id": 3,
    "model_type": "bananamind2_pico",
    "output_attentions": false
  },
  "training_percent": 70,
  "step": 15708,
  "total_steps": 22439,
  "tokens_seen": 140003770368,
  "target_tokens": 200000000000,
  "trained_token_target": 199996473344,
  "tokens_per_step": 8912896,
  "local_batch": 544,
  "effective_global_batch": 2176,
  "world_size": 4,
  "gpu_name": "NVIDIA H200",
  "optimizer": "Muon + AdamW",
  "muon_peak_lr": 0.07,
  "adamw_peak_lr": 0.004,
  "architecture_revision": "ee5739850035c878ce4d9fc29fc38b075987e03b",
  "tokenizer_revision": "ee5739850035c878ce4d9fc29fc38b075987e03b",
  "dataset_revisions": {
    "fineweb_hq": "e58199cdd52438d94405df1a4d8630cc5f13bf84",
    "cosmopedia_v2": "3ba9d605774198c5868892d7a8deda78031a781f"
  },
  "source_tokens": {
    "fineweb_hq": 104004583424,
    "cosmopedia_v2": 35999186944
  },
  "elapsed_seconds": 18767.246102809906
}