bdh-scaling / deltanet_50M.json
kacperwikiel's picture
Upload folder using huggingface_hub
2f957bf verified
Raw
History Blame Contribute Delete
2.31 kB
[
{
"step": 0,
"val_loss": 5.621358013153076,
"tok_per_s": 0.0
},
{
"step": 0,
"train_loss": 5.64911413192749,
"lr": 1e-06,
"grad_norm": 27.099479357510347
},
{
"step": 400,
"train_loss": 2.398966073989868,
"lr": 0.00040100000000000004,
"grad_norm": 2.196135251811181
},
{
"step": 500,
"val_loss": 3.640947675704956,
"tok_per_s": 9535.600203354274
},
{
"step": 800,
"train_loss": 2.0833027362823486,
"lr": 0.0008010000000000001,
"grad_norm": 1.1349175481398261
},
{
"step": 1000,
"val_loss": 3.780544173717499,
"tok_per_s": 11725.258262928171
},
{
"step": 1200,
"train_loss": 2.1644351482391357,
"lr": 0.000988964669915361,
"grad_norm": 1.017884968533845
},
{
"step": 1500,
"val_loss": 3.493694770336151,
"tok_per_s": 12755.04477964051
},
{
"step": 1600,
"train_loss": 1.934144139289856,
"lr": 0.0009042005118087267,
"grad_norm": 0.7603376712222735
},
{
"step": 2000,
"val_loss": 3.551745867729187,
"tok_per_s": 13343.406266130558
},
{
"step": 2000,
"train_loss": 1.740228295326233,
"lr": 0.0007495464131639923,
"grad_norm": 0.7555832625902893
},
{
"step": 2400,
"train_loss": 1.6871309280395508,
"lr": 0.0005517434726252113,
"grad_norm": 0.5830700367704018
},
{
"step": 2500,
"val_loss": 3.4994417428970337,
"tok_per_s": 13724.312075793581
},
{
"step": 2800,
"train_loss": 1.6141437292099,
"lr": 0.00034499361559483973,
"grad_norm": 0.5706124296306655
},
{
"step": 3000,
"val_loss": 3.3726165175437925,
"tok_per_s": 13991.385343435013
},
{
"step": 3200,
"train_loss": 1.9143563508987427,
"lr": 0.00016504577061691466,
"grad_norm": 0.6791111654355323
},
{
"step": 3500,
"val_loss": 3.4791015148162843,
"tok_per_s": 14186.548234148084
},
{
"step": 3600,
"train_loss": 1.626238465309143,
"lr": 4.301455486296946e-05,
"grad_norm": 0.617041260884856
},
{
"step": 4000,
"val_loss": 3.520080554485321,
"tok_per_s": 14312.999280690912
},
{
"step": 4000,
"train_loss": 1.661009430885315,
"lr": 2.741556527352529e-10,
"grad_norm": 0.6085785012195996
}
]