{
  "step": 387,
  "val_bpb": 0.3020884011575493,
  "model_config": {
    "sequence_len": 4096,
    "vocab_size": 32768,
    "n_layer": 24,
    "n_head": 12,
    "n_kv_head": 12,
    "n_embd": 1536,
    "window_pattern": "SSSL"
  },
  "user_config": {
    "run": "rost-d24-production",
    "mixture": "romanian",
    "identity_name": "rost",
    "device_type": "",
    "compile_mode": "default",
    "serial_compile_warmup": true,
    "eager_optimizer": true,
    "init_source": "base",
    "model_tag": null,
    "model_step": null,
    "output_model_tag": null,
    "load_optimizer": 1,
    "num_iterations": -1,
    "max_seq_len": null,
    "device_batch_size": 8,
    "total_batch_size": null,
    "embedding_lr": null,
    "unembedding_lr": null,
    "matrix_lr": null,
    "init_lr_frac": 0.8,
    "warmup_ratio": 0.0,
    "warmdown_ratio": 0.5,
    "final_lr_frac": 0.0,
    "grad_clip": 0.0,
    "eval_every": 200,
    "eval_tokens": 20971520,
    "save_every": 100,
    "eval_device_batch_size": 4,
    "chatcore_batch_size": -1,
    "eval_oom_policy": "contain",
    "chatcore_every": 200,
    "chatcore_max_cat": -1,
    "chatcore_max_sample": 24,
    "dialogue_frac": 0.0,
    "english_frac": 0.25,
    "ro_gsm8k_epochs": 0,
    "agent_traces": null,
    "agent_epochs": 1,
    "agent_frac": 0.0,
    "agent_max_repeats": 1000,
    "mmlu_epochs": 3,
    "gsm8k_epochs": 4
  }
}