bdh-scaling / gptxl_25M.json
kacperwikiel's picture
Upload folder using huggingface_hub
2f957bf verified
Raw
History Blame Contribute Delete
2.33 kB
[
{
"step": 0,
"val_loss": 5.645234680175781,
"tok_per_s": 0.0
},
{
"step": 0,
"train_loss": 5.6187896728515625,
"lr": 1e-06,
"grad_norm": 3.9997430103145035
},
{
"step": 400,
"train_loss": 2.5888192653656006,
"lr": 0.00040100000000000004,
"grad_norm": 0.6801968187336246
},
{
"step": 500,
"val_loss": 3.2440637707710267,
"tok_per_s": 15307.808244900336
},
{
"step": 800,
"train_loss": 2.5374417304992676,
"lr": 0.0008010000000000001,
"grad_norm": 0.6071088524293848
},
{
"step": 1000,
"val_loss": 3.4290844678878782,
"tok_per_s": 15467.497743749367
},
{
"step": 1200,
"train_loss": 2.593106269836426,
"lr": 0.000988964669915361,
"grad_norm": 0.537434440879202
},
{
"step": 1500,
"val_loss": 3.2820756435394287,
"tok_per_s": 15521.383825757934
},
{
"step": 1600,
"train_loss": 2.5404372215270996,
"lr": 0.0009042005118087267,
"grad_norm": 0.6397086163729014
},
{
"step": 2000,
"val_loss": 3.3991117000579836,
"tok_per_s": 15545.080029807583
},
{
"step": 2000,
"train_loss": 2.582529306411743,
"lr": 0.0007495464131639923,
"grad_norm": 0.6453869964287425
},
{
"step": 2400,
"train_loss": 2.4693706035614014,
"lr": 0.0005517434726252113,
"grad_norm": 0.44898042682437667
},
{
"step": 2500,
"val_loss": 3.4165297031402586,
"tok_per_s": 15566.889908296098
},
{
"step": 2800,
"train_loss": 2.5144152641296387,
"lr": 0.00034499361559483973,
"grad_norm": 0.3683215301707224
},
{
"step": 3000,
"val_loss": 3.2657894492149353,
"tok_per_s": 15581.273628312976
},
{
"step": 3200,
"train_loss": 2.5290699005126953,
"lr": 0.00016504577061691466,
"grad_norm": 0.5046250119691038
},
{
"step": 3500,
"val_loss": 3.3603868961334227,
"tok_per_s": 15590.568493710476
},
{
"step": 3600,
"train_loss": 2.528745412826538,
"lr": 4.301455486296946e-05,
"grad_norm": 0.36686653376681755
},
{
"step": 4000,
"val_loss": 3.400707244873047,
"tok_per_s": 15598.718880719514
},
{
"step": 4000,
"train_loss": 2.5966501235961914,
"lr": 2.741556527352529e-10,
"grad_norm": 0.3640087477220863
}
]