system's picture
system HF staff
Update log_history.json
2550851
[
{
"loss": 0.712146484375,
"learning_rate": 9.526784024228659e-05,
"epoch": 0.1419547164454539,
"total_flos": 3042241413120000,
"step": 500
},
{
"loss": 0.421217041015625,
"learning_rate": 9.053568048457316e-05,
"epoch": 0.2839094328909078,
"total_flos": 6084482826240000,
"step": 1000
},
{
"loss": 0.39531640625,
"learning_rate": 8.580352072685975e-05,
"epoch": 0.4258641493363617,
"total_flos": 9126724239360000,
"step": 1500
},
{
"loss": 0.3591341552734375,
"learning_rate": 8.107136096914632e-05,
"epoch": 0.5678188657818156,
"total_flos": 12168965652480000,
"step": 2000
},
{
"loss": 0.3376422119140625,
"learning_rate": 7.63392012114329e-05,
"epoch": 0.7097735822272695,
"total_flos": 15211207065600000,
"step": 2500
},
{
"loss": 0.328197998046875,
"learning_rate": 7.160704145371948e-05,
"epoch": 0.8517282986727234,
"total_flos": 18253448478720000,
"step": 3000
},
{
"loss": 0.3190537109375,
"learning_rate": 6.687488169600607e-05,
"epoch": 0.9936830151181772,
"total_flos": 21295689891840000,
"step": 3500
},
{
"loss": 0.28114892578125,
"learning_rate": 6.214272193829264e-05,
"epoch": 1.1357087089218538,
"total_flos": 24339072145489920,
"step": 4000
},
{
"loss": 0.2707734375,
"learning_rate": 5.7410562180579217e-05,
"epoch": 1.2776634253673078,
"total_flos": 27381313558609920,
"step": 4500
},
{
"loss": 0.26517333984375,
"learning_rate": 5.26784024228658e-05,
"epoch": 1.4196181418127618,
"total_flos": 30423554971729920,
"step": 5000
},
{
"loss": 0.262806884765625,
"learning_rate": 4.794624266515238e-05,
"epoch": 1.5615728582582156,
"total_flos": 33465796384849920,
"step": 5500
},
{
"loss": 0.255599853515625,
"learning_rate": 4.321408290743896e-05,
"epoch": 1.7035275747036696,
"total_flos": 36508037797969920,
"step": 6000
},
{
"loss": 0.2491875,
"learning_rate": 3.848192314972553e-05,
"epoch": 1.8454822911491235,
"total_flos": 39550279211089920,
"step": 6500
},
{
"loss": 0.25085498046875,
"learning_rate": 3.374976339201212e-05,
"epoch": 1.9874370075945773,
"total_flos": 42592520624209920,
"step": 7000
},
{
"loss": 0.22507177734375,
"learning_rate": 2.9017603634298694e-05,
"epoch": 2.129462701398254,
"total_flos": 45635902877859840,
"step": 7500
},
{
"loss": 0.2233544921875,
"learning_rate": 2.4285443876585277e-05,
"epoch": 2.2714174178437077,
"total_flos": 48678144290979840,
"step": 8000
},
{
"loss": 0.21958740234375,
"learning_rate": 1.9553284118871853e-05,
"epoch": 2.413372134289162,
"total_flos": 51720385704099840,
"step": 8500
},
{
"loss": 0.22100439453125,
"learning_rate": 1.4821124361158433e-05,
"epoch": 2.5553268507346156,
"total_flos": 54762627117219840,
"step": 9000
},
{
"loss": 0.21701953125,
"learning_rate": 1.0088964603445012e-05,
"epoch": 2.6972815671800694,
"total_flos": 57804868530339840,
"step": 9500
},
{
"loss": 0.21920361328125,
"learning_rate": 5.356804845731592e-06,
"epoch": 2.8392362836255236,
"total_flos": 60847109943459840,
"step": 10000
},
{
"loss": 0.21878466796875,
"learning_rate": 6.246450880181715e-07,
"epoch": 2.9811910000709774,
"total_flos": 63889351356579840,
"step": 10500
}
]