Initial pi0.5 minimal validation
This commit is contained in:
@@ -0,0 +1,296 @@
|
||||
[
|
||||
{
|
||||
"stage": "pretrain",
|
||||
"step": 1,
|
||||
"loss": 78.87449645996094,
|
||||
"text_loss": 78.87449645996094,
|
||||
"flow_loss": null
|
||||
},
|
||||
{
|
||||
"stage": "pretrain",
|
||||
"step": 20,
|
||||
"loss": 2.475086212158203,
|
||||
"text_loss": 2.475086212158203,
|
||||
"flow_loss": null
|
||||
},
|
||||
{
|
||||
"stage": "pretrain",
|
||||
"step": 40,
|
||||
"loss": 1.1025534868240356,
|
||||
"text_loss": 1.1025534868240356,
|
||||
"flow_loss": null
|
||||
},
|
||||
{
|
||||
"stage": "pretrain",
|
||||
"step": 60,
|
||||
"loss": 0.601564884185791,
|
||||
"text_loss": 0.601564884185791,
|
||||
"flow_loss": null
|
||||
},
|
||||
{
|
||||
"stage": "pretrain",
|
||||
"step": 80,
|
||||
"loss": 0.25571808218955994,
|
||||
"text_loss": 0.25571808218955994,
|
||||
"flow_loss": null
|
||||
},
|
||||
{
|
||||
"stage": "pretrain",
|
||||
"step": 100,
|
||||
"loss": 0.03314117714762688,
|
||||
"text_loss": 0.03314117714762688,
|
||||
"flow_loss": null
|
||||
},
|
||||
{
|
||||
"stage": "pretrain",
|
||||
"step": 120,
|
||||
"loss": 0.005310459993779659,
|
||||
"text_loss": 0.005310459993779659,
|
||||
"flow_loss": null
|
||||
},
|
||||
{
|
||||
"stage": "pretrain",
|
||||
"step": 140,
|
||||
"loss": 3.0251239877543412e-05,
|
||||
"text_loss": 3.0251239877543412e-05,
|
||||
"flow_loss": null
|
||||
},
|
||||
{
|
||||
"stage": "pretrain",
|
||||
"step": 160,
|
||||
"loss": 1.1354763955750968e-05,
|
||||
"text_loss": 1.1354763955750968e-05,
|
||||
"flow_loss": null
|
||||
},
|
||||
{
|
||||
"stage": "pretrain",
|
||||
"step": 180,
|
||||
"loss": 6.638075319642667e-06,
|
||||
"text_loss": 6.638075319642667e-06,
|
||||
"flow_loss": null
|
||||
},
|
||||
{
|
||||
"stage": "pretrain",
|
||||
"step": 200,
|
||||
"loss": 5.348983449948719e-06,
|
||||
"text_loss": 5.348983449948719e-06,
|
||||
"flow_loss": null
|
||||
},
|
||||
{
|
||||
"stage": "pretrain",
|
||||
"step": 220,
|
||||
"loss": 4.736786195280729e-06,
|
||||
"text_loss": 4.736786195280729e-06,
|
||||
"flow_loss": null
|
||||
},
|
||||
{
|
||||
"stage": "pretrain",
|
||||
"step": 240,
|
||||
"loss": 4.316162630857434e-06,
|
||||
"text_loss": 4.316162630857434e-06,
|
||||
"flow_loss": null
|
||||
},
|
||||
{
|
||||
"stage": "pretrain",
|
||||
"step": 260,
|
||||
"loss": 3.975574600190157e-06,
|
||||
"text_loss": 3.975574600190157e-06,
|
||||
"flow_loss": null
|
||||
},
|
||||
{
|
||||
"stage": "pretrain",
|
||||
"step": 280,
|
||||
"loss": 3.6877775073662633e-06,
|
||||
"text_loss": 3.6877775073662633e-06,
|
||||
"flow_loss": null
|
||||
},
|
||||
{
|
||||
"stage": "pretrain",
|
||||
"step": 300,
|
||||
"loss": 3.4408508327032905e-06,
|
||||
"text_loss": 3.4408508327032905e-06,
|
||||
"flow_loss": null
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 1,
|
||||
"loss": 8.707193374633789,
|
||||
"text_loss": 3.428078571232618e-06,
|
||||
"flow_loss": 4.353594779968262
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 20,
|
||||
"loss": 3.533726453781128,
|
||||
"text_loss": 0.14151602983474731,
|
||||
"flow_loss": 1.6961052417755127
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 40,
|
||||
"loss": 3.0850143432617188,
|
||||
"text_loss": 0.00014649856893811375,
|
||||
"flow_loss": 1.5424339771270752
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 60,
|
||||
"loss": 1.3556954860687256,
|
||||
"text_loss": 0.00011281041224719957,
|
||||
"flow_loss": 0.6777913570404053
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 80,
|
||||
"loss": 1.4165724515914917,
|
||||
"text_loss": 6.599419066333212e-06,
|
||||
"flow_loss": 0.7082829475402832
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 100,
|
||||
"loss": 0.8609042167663574,
|
||||
"text_loss": 8.11900736152893e-06,
|
||||
"flow_loss": 0.430448055267334
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 120,
|
||||
"loss": 0.5642163753509521,
|
||||
"text_loss": 7.576879397674929e-06,
|
||||
"flow_loss": 0.28210440278053284
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 140,
|
||||
"loss": 0.7110214233398438,
|
||||
"text_loss": 6.249698344618082e-06,
|
||||
"flow_loss": 0.35550758242607117
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 160,
|
||||
"loss": 0.18725578486919403,
|
||||
"text_loss": 2.876289045161684e-06,
|
||||
"flow_loss": 0.09362645447254181
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 180,
|
||||
"loss": 0.33923929929733276,
|
||||
"text_loss": 6.748496616637567e-06,
|
||||
"flow_loss": 0.16961628198623657
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 200,
|
||||
"loss": 0.3003162443637848,
|
||||
"text_loss": 9.495882295595948e-06,
|
||||
"flow_loss": 0.15015336871147156
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 220,
|
||||
"loss": 0.23716998100280762,
|
||||
"text_loss": 5.660519946104614e-06,
|
||||
"flow_loss": 0.11858215928077698
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 240,
|
||||
"loss": 0.42717865109443665,
|
||||
"text_loss": 8.400202204938978e-06,
|
||||
"flow_loss": 0.21358512341976166
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 260,
|
||||
"loss": 0.11702287942171097,
|
||||
"text_loss": 4.122769951209193e-06,
|
||||
"flow_loss": 0.058509379625320435
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 280,
|
||||
"loss": 0.19245445728302002,
|
||||
"text_loss": 5.941245035501197e-06,
|
||||
"flow_loss": 0.09622425585985184
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 300,
|
||||
"loss": 0.18475297093391418,
|
||||
"text_loss": 4.744139005197212e-06,
|
||||
"flow_loss": 0.09237411618232727
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 320,
|
||||
"loss": 0.38481318950653076,
|
||||
"text_loss": 3.1461640901397914e-06,
|
||||
"flow_loss": 0.19240501523017883
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 340,
|
||||
"loss": 0.2163764089345932,
|
||||
"text_loss": 4.1934181354008615e-06,
|
||||
"flow_loss": 0.10818611085414886
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 360,
|
||||
"loss": 0.23533868789672852,
|
||||
"text_loss": 3.3019753118423978e-06,
|
||||
"flow_loss": 0.11766768991947174
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 380,
|
||||
"loss": 0.08397223055362701,
|
||||
"text_loss": 8.292082384286914e-06,
|
||||
"flow_loss": 0.04198196902871132
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 400,
|
||||
"loss": 0.13249839842319489,
|
||||
"text_loss": 1.0871653103095014e-05,
|
||||
"flow_loss": 0.06624376028776169
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 420,
|
||||
"loss": 0.4479130506515503,
|
||||
"text_loss": 1.0128642315976322e-05,
|
||||
"flow_loss": 0.22395145893096924
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 440,
|
||||
"loss": 0.22416232526302338,
|
||||
"text_loss": 2.6114355478057405e-06,
|
||||
"flow_loss": 0.11207985877990723
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 460,
|
||||
"loss": 0.06346385926008224,
|
||||
"text_loss": 3.1035808660817565e-06,
|
||||
"flow_loss": 0.031730376183986664
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 480,
|
||||
"loss": 0.385486900806427,
|
||||
"text_loss": 2.184032382501755e-06,
|
||||
"flow_loss": 0.19274236261844635
|
||||
},
|
||||
{
|
||||
"stage": "posttrain",
|
||||
"step": 500,
|
||||
"loss": 0.12353827804327011,
|
||||
"text_loss": 3.1691649837739533e-06,
|
||||
"flow_loss": 0.06176755577325821
|
||||
}
|
||||
]
|
||||
Reference in New Issue
Block a user