{
  "accum_steps": 8,
  "arch_version": 2,
  "auto_map": {
    "AutoConfig": "configuration_fwkv.FWKVConfig",
    "AutoModel": "modeling_fwkv.FWKVLanguageModel",
    "AutoModelForCausalLM": "modeling_fwkv.FWKVLanguageModel"
  },
  "architectures": [
    "FWKVLanguageModel"
  ],
  "batch_size": 4,
  "ce_chunk": 512,
  "chinchilla_scale": true,
  "d_emb": 384,
  "d_model": 768,
  "dtype": "float32",
  "early_stop_patience": 2,
  "epochs": 1,
  "eval_every_opt_steps": 100,
  "ffn_mult": 4,
  "grad_clip": 1.0,
  "head_size": 64,
  "keep_last_ckpts": 2,
  "log_every": 50,
  "lr": 0.0004,
  "max_val_examples": 128,
  "min_lr_ratio": 0.1,
  "model_type": "fwkv",
  "n_layers": 13,
  "prefetch_chunks": 512,
  "save_every_steps": 500,
  "seq_len": 1024,
  "sft_epochs": 3,
  "sft_lr": 5e-05,
  "sft_max_train_examples": 40000,
  "sft_max_val_examples": 1000,
  "sft_val_skip_rows": 2000,
  "shuffle_buffer_size": 10000,
  "tau_max": 1000.0,
  "tau_min": 2.0,
  "tie_word_embeddings": true,
  "train_tokens": 20000000000,
  "transformers_version": "5.16.1",
  "use_amp": true,
  "vocab_size": 50280,
  "warmup_steps": 1000,
  "weight_decay": 0.1,
  "wikitext_max_chunks": 128,
  "wikitext_val": true,
  "wkv_ceil": 0.999,
  "wkv_floor": 0.1
}