bdh-scaling / deltanet_25M.json
kacperwikiel's picture
Upload folder using huggingface_hub
2f957bf verified
Raw
History Blame Contribute Delete
2.31 kB
[
{
"step": 0,
"val_loss": 5.626408910751342,
"tok_per_s": 0.0
},
{
"step": 0,
"train_loss": 5.604258060455322,
"lr": 1e-06,
"grad_norm": 13.048460426409413
},
{
"step": 400,
"train_loss": 2.3472392559051514,
"lr": 0.00040100000000000004,
"grad_norm": 2.333641357990838
},
{
"step": 500,
"val_loss": 3.549709665775299,
"tok_per_s": 8749.517639188356
},
{
"step": 800,
"train_loss": 2.07755970954895,
"lr": 0.0008010000000000001,
"grad_norm": 1.2879824739999564
},
{
"step": 1000,
"val_loss": 3.7089839220046996,
"tok_per_s": 13488.365873947118
},
{
"step": 1200,
"train_loss": 2.173725128173828,
"lr": 0.000988964669915361,
"grad_norm": 1.1336315185689552
},
{
"step": 1500,
"val_loss": 3.401188623905182,
"tok_per_s": 16332.442193770717
},
{
"step": 1600,
"train_loss": 1.9094194173812866,
"lr": 0.0009042005118087267,
"grad_norm": 0.8353516258510217
},
{
"step": 2000,
"val_loss": 3.583898830413818,
"tok_per_s": 18350.914261526847
},
{
"step": 2000,
"train_loss": 1.727286696434021,
"lr": 0.0007495464131639923,
"grad_norm": 0.8469397197668344
},
{
"step": 2400,
"train_loss": 1.6775403022766113,
"lr": 0.0005517434726252113,
"grad_norm": 0.6447981898010077
},
{
"step": 2500,
"val_loss": 3.5043333053588865,
"tok_per_s": 19854.004915465615
},
{
"step": 2800,
"train_loss": 1.6345783472061157,
"lr": 0.00034499361559483973,
"grad_norm": 0.7628613935107342
},
{
"step": 3000,
"val_loss": 3.388085734844208,
"tok_per_s": 21025.281583411277
},
{
"step": 3200,
"train_loss": 1.9179948568344116,
"lr": 0.00016504577061691466,
"grad_norm": 0.763405525537365
},
{
"step": 3500,
"val_loss": 3.486909306049347,
"tok_per_s": 21906.183551382397
},
{
"step": 3600,
"train_loss": 1.6130081415176392,
"lr": 4.301455486296946e-05,
"grad_norm": 0.6950398624239266
},
{
"step": 4000,
"val_loss": 3.5643239259719848,
"tok_per_s": 22551.36101932676
},
{
"step": 4000,
"train_loss": 1.6661380529403687,
"lr": 2.741556527352529e-10,
"grad_norm": 0.6963844802259589
}
]