{ "name": "sml-v2-150m-pilot-v1", "data_mode": "hf_stream", "stream": {"prefetch_batches": 4, "read_attempts": 5, "dedup_window": 10000}, "model": {"vocab_size": 32000, "max_seq_len": 2048, "d_model": 768, "n_layers": 20, "n_heads": 12, "n_kv_heads": 4, "mlp_ratio": 4.0, "mlp_multiple_of": 256, "bias": false, "qk_norm": true, "attention_impl": "fast", "loss_dtype": "float32", "ce_impl": "metal", "ffn_impl": "packed-metal"}, "seed": 7337, "batches": [4, 3, 3, 3], "grad_accum": 4, "target_tokens": 500000000, "peak_lr": 0.0003, "warmup_fraction": 0.01, "decay_start_fraction": 0.8, "min_lr_ratio": 0.1, "betas": [0.9, 0.95], "eps": 1e-8, "weight_decay": 0.1, "grad_clip": 1.0, "eval_every_tokens": 25000000, "sample_every_tokens": 50000000, "save_every_tokens": 10000000, "eval_batches_per_source": 16, "eval_batch_size": 2, "keep_checkpoints": 2, "reserve_gib": 8, "log_every": 10, "prompts": [ "The library was closed for repairs, so Maya decided to", "Plants need sunlight because", "A useful way to remember a new word is to", "The train arrived late because of heavy snow. When the passengers stepped outside,", "Clean drinking water is important because" ] }