model_config.json

{
  "model_family": "Cosmos T2A-low",
  "model_name": "Cosmos T2A-low",
  "model_class_name": "CosmosT2_Accelerate_LLM",
  "hf_repo_id": "wop/Cosmos-T2A-low",
  "tokenizer_name": "Qwen/Qwen2.5-0.5B",
  "dataset_name": "wop/minitron-dataset",
  "dataset_split": "train",
  "dataset_row_limit": 288350,
  "rows_used": 288350,
  "stream_dataset": true,
  "shuffle_buffer_size": 2048,
  "train_val_fraction": 0.1,
  "seed": 42,
  "block_size": 1028,
  "max_len": 1028,
  "d_model": 64,
  "n_layers": 4,
  "n_heads": 4,
  "n_kv_heads": 1,
  "d_ff": 256,
  "rope_base": 10000,
  "dropout": 0.05,
  "use_engram": true,
  "engram_every": 2,
  "engram_buckets": 128,
  "engram_dim": 16,
  "engram_order": 3,
  "epochs": 1,
  "batch_size": 2,
  "lr": 0.0003,
  "weight_decay": 0.1,
  "warmup_steps": 50,
  "grad_clip": 1.0,
  "log_every_steps": 5000,
  "eval_every_steps": 5000,
  "plot_every_epochs": 5000,
  "val_max_batches": 10,
  "early_stopping_patience": 2,
  "tokenization_batch_size": 256,
  "num_workers": 1,
  "pin_memory": true,
  "dataloader_prefetch_factor": 4,
  "persistent_workers": true,
  "use_kv_cache": true,
  "train_steps_per_epoch": 129757,
  "loss_tokens_seen": 46651194,
  "samples_seen": 222956
}