{ "meta": { "model": "gptxl", "size_m": 25, "steps": 4000, "seq_len": 2048, "warmup": 1000, "seed": 0, "config": { "arch": "gptxl", "size_m": 25, "n_layer": 9, "n_embd": 480, "n_head": 5, "ff": 1920, "drop": 0.01 }, "data": "europarl en-pl+en-cs byte stream 398.6MB", "optimizer": "AdamW lr=1e-3 wd=0.1 cos->1e-4 warmup1000", "clip": "ZClip" } }