bdh-scaling / gptxl_100M.json
kacperwikiel's picture
Upload folder using huggingface_hub
2f957bf verified
Raw
History Blame Contribute Delete
2.31 kB
[
{
"step": 0,
"val_loss": 5.6596427917480465,
"tok_per_s": 0.0
},
{
"step": 0,
"train_loss": 5.6980743408203125,
"lr": 1e-06,
"grad_norm": 6.812654622584365
},
{
"step": 400,
"train_loss": 2.5596842765808105,
"lr": 0.00040100000000000004,
"grad_norm": 1.4871683888219858
},
{
"step": 500,
"val_loss": 3.4652376890182497,
"tok_per_s": 6094.801815061978
},
{
"step": 800,
"train_loss": 2.494938850402832,
"lr": 0.0008010000000000001,
"grad_norm": 1.2415186781831968
},
{
"step": 1000,
"val_loss": 3.4046719431877137,
"tok_per_s": 6166.613800891438
},
{
"step": 1200,
"train_loss": 2.5608506202697754,
"lr": 0.000988964669915361,
"grad_norm": 0.9910638825668165
},
{
"step": 1500,
"val_loss": 3.7543918251991273,
"tok_per_s": 6200.059159937738
},
{
"step": 1600,
"train_loss": 2.5627622604370117,
"lr": 0.0009042005118087267,
"grad_norm": 0.7332589467031237
},
{
"step": 2000,
"val_loss": 3.495138716697693,
"tok_per_s": 6218.522078978638
},
{
"step": 2000,
"train_loss": 2.5756995677948,
"lr": 0.0007495464131639923,
"grad_norm": 0.6796354906098467
},
{
"step": 2400,
"train_loss": 2.586728572845459,
"lr": 0.0005517434726252113,
"grad_norm": 0.8395008697152312
},
{
"step": 2500,
"val_loss": 3.4730632424354555,
"tok_per_s": 6229.251830010614
},
{
"step": 2800,
"train_loss": 2.449960947036743,
"lr": 0.00034499361559483973,
"grad_norm": 0.68896226064563
},
{
"step": 3000,
"val_loss": 3.2845374941825867,
"tok_per_s": 6235.777896193986
},
{
"step": 3200,
"train_loss": 2.518332004547119,
"lr": 0.00016504577061691466,
"grad_norm": 0.6054645964415646
},
{
"step": 3500,
"val_loss": 3.2842100739479063,
"tok_per_s": 6239.96753812375
},
{
"step": 3600,
"train_loss": 2.58005428314209,
"lr": 4.301455486296946e-05,
"grad_norm": 0.7789419776654517
},
{
"step": 4000,
"val_loss": 3.336404061317444,
"tok_per_s": 6244.50056187448
},
{
"step": 4000,
"train_loss": 2.5519471168518066,
"lr": 2.741556527352529e-10,
"grad_norm": 0.5962078033408024
}
]