bdh-scaling / gla_50M.meta.json
kacperwikiel's picture
Upload folder using huggingface_hub
2f957bf verified
Raw
History Blame Contribute Delete
401 Bytes
{
"meta": {
"model": "gla",
"size_m": 50,
"steps": 4000,
"seq_len": 2048,
"warmup": 1000,
"seed": 0,
"config": {
"arch": "gla",
"size_m": 50,
"n_layer": 20,
"hidden": 384,
"params": 49627264
},
"data": "europarl en-pl+en-cs byte stream 398.6MB",
"optimizer": "AdamW lr=1e-3 wd=0.1 cos->1e-4 warmup1000",
"clip": "ZClip"
}
}