MarxistLeninist's picture
Publish verified model-only Transformer checkpoints and comparison sources; SSM transfer pending
9dd4895 verified
Raw History Blame Contribute Delete
3.24 kB
{
"step": 5000,
"last_eval": 5000,
"best": 1.2401772355061287,
"history": [
{
"step": 0,
"val_bpc": 8.120714930974401,
"train_bpc": 8.124579314066056,
"eval_seconds": 86.17574295308441
},
{
"step": 250,
"val_bpc": 1.9426932876098857,
"train_bpc": 1.9882185092056397,
"eval_seconds": 89.90058440994471
},
{
"step": 500,
"val_bpc": 1.711670936432297,
"train_bpc": 1.72017869255074,
"eval_seconds": 89.86440288601443
},
{
"step": 750,
"val_bpc": 1.5269934478948264,
"train_bpc": 1.5383562795085994,
"eval_seconds": 84.42872931901366
},
{
"step": 1000,
"val_bpc": 1.4460930360535493,
"train_bpc": 1.4688767987826776,
"eval_seconds": 85.30924095213413
},
{
"step": 1250,
"val_bpc": 1.3978991878265163,
"train_bpc": 1.4164677049055419,
"eval_seconds": 87.70176294795237
},
{
"step": 1500,
"val_bpc": 1.375442339286683,
"train_bpc": 1.3695944004181855,
"eval_seconds": 88.8819454240147
},
{
"step": 1750,
"val_bpc": 1.3431843025562797,
"train_bpc": 1.3378005535690825,
"eval_seconds": 84.99736955715343
},
{
"step": 2000,
"val_bpc": 1.3270683195623556,
"train_bpc": 1.3064812412502402,
"eval_seconds": 89.01641180901788
},
{
"step": 2250,
"val_bpc": 1.3063774800323866,
"train_bpc": 1.281381993755852,
"eval_seconds": 84.51401737192646
},
{
"step": 2500,
"val_bpc": 1.2929188392430837,
"train_bpc": 1.2795939379675059,
"eval_seconds": 84.15434210700914
},
{
"step": 2750,
"val_bpc": 1.2797478125650594,
"train_bpc": 1.2335081963204746,
"eval_seconds": 84.83461578399874
},
{
"step": 3000,
"val_bpc": 1.2646277712132794,
"train_bpc": 1.227596224441451,
"eval_seconds": 86.26529246103019
},
{
"step": 3250,
"val_bpc": 1.2565381182477393,
"train_bpc": 1.2144387938518906,
"eval_seconds": 86.67734512803145
},
{
"step": 3500,
"val_bpc": 1.2563155760296867,
"train_bpc": 1.1803701577397774,
"eval_seconds": 84.47422780212946
},
{
"step": 3750,
"val_bpc": 1.250121944239991,
"train_bpc": 1.1765235765723145,
"eval_seconds": 84.43941144505516
},
{
"step": 4000,
"val_bpc": 1.2401772355061287,
"train_bpc": 1.1617869808595924,
"eval_seconds": 84.26847494090907
},
{
"step": 4250,
"val_bpc": 1.249788509382233,
"train_bpc": 1.1344982098758165,
"eval_seconds": 87.5420548459515
},
{
"step": 4500,
"val_bpc": 1.2512178044163778,
"train_bpc": 1.1127300827909055,
"eval_seconds": 87.88037243206054
},
{
"step": 4750,
"val_bpc": 1.2482063418719436,
"train_bpc": 1.1190378466747692,
"eval_seconds": 88.37729337904602
},
{
"step": 5000,
"val_bpc": 1.257564388922874,
"train_bpc": 1.099137191323192,
"eval_seconds": 84.24452146305703
}
],
"trained_seconds": 8665.858016421553
}