bdh-scaling / gptxl_100M.meta.json
kacperwikiel's picture
Upload folder using huggingface_hub
2f957bf verified
Raw
History Blame Contribute Delete
438 Bytes
{
"meta": {
"model": "gptxl",
"size_m": 100,
"steps": 4000,
"seq_len": 1024,
"warmup": 1000,
"seed": 0,
"config": {
"arch": "gptxl",
"size_m": 100,
"n_layer": 15,
"n_embd": 768,
"n_head": 8,
"ff": 3072,
"drop": 0.02
},
"data": "europarl en-pl+en-cs byte stream 398.6MB",
"optimizer": "AdamW lr=1e-3 wd=0.1 cos->1e-4 warmup1000",
"clip": "ZClip"
}
}