pszemraj's picture
add wip15
95c446c
raw
history blame
14 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.3807365439093484,
"global_step": 228,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.00016,
"loss": 2.092,
"step": 2
},
{
"epoch": 0.02,
"learning_rate": 0.00032,
"loss": 2.0773,
"step": 4
},
{
"epoch": 0.04,
"learning_rate": 0.0003999958893916732,
"loss": 1.9915,
"step": 6
},
{
"epoch": 0.05,
"learning_rate": 0.00039996300553887804,
"loss": 2.1242,
"step": 8
},
{
"epoch": 0.06,
"learning_rate": 0.0003998972432401376,
"loss": 2.0798,
"step": 10
},
{
"epoch": 0.07,
"learning_rate": 0.00039979861330826294,
"loss": 2.099,
"step": 12
},
{
"epoch": 0.08,
"learning_rate": 0.0003996671319602482,
"loss": 2.0562,
"step": 14
},
{
"epoch": 0.1,
"learning_rate": 0.00039950282081460415,
"loss": 2.0909,
"step": 16
},
{
"epoch": 0.11,
"learning_rate": 0.0003993057068878037,
"loss": 2.0784,
"step": 18
},
{
"epoch": 0.12,
"learning_rate": 0.00039907582258983965,
"loss": 2.0465,
"step": 20
},
{
"epoch": 0.13,
"learning_rate": 0.00039881320571889605,
"loss": 2.173,
"step": 22
},
{
"epoch": 0.15,
"learning_rate": 0.000398517899455133,
"loss": 2.0897,
"step": 24
},
{
"epoch": 0.16,
"learning_rate": 0.00039818995235358696,
"loss": 2.057,
"step": 26
},
{
"epoch": 0.17,
"learning_rate": 0.00039782941833618724,
"loss": 2.0833,
"step": 28
},
{
"epoch": 0.18,
"learning_rate": 0.00039743635668289007,
"loss": 2.0256,
"step": 30
},
{
"epoch": 0.19,
"learning_rate": 0.0003970108320219314,
"loss": 2.0925,
"step": 32
},
{
"epoch": 0.21,
"learning_rate": 0.0003965529143192008,
"loss": 2.0337,
"step": 34
},
{
"epoch": 0.22,
"learning_rate": 0.0003960626788667375,
"loss": 2.0865,
"step": 36
},
{
"epoch": 0.23,
"learning_rate": 0.00039554020627035035,
"loss": 2.164,
"step": 38
},
{
"epoch": 0.24,
"learning_rate": 0.0003949855824363647,
"loss": 2.1327,
"step": 40
},
{
"epoch": 0.25,
"learning_rate": 0.00039439889855749763,
"loss": 2.171,
"step": 42
},
{
"epoch": 0.27,
"learning_rate": 0.0003937802510978631,
"loss": 2.0629,
"step": 44
},
{
"epoch": 0.28,
"learning_rate": 0.00039312974177711183,
"loss": 2.0344,
"step": 46
},
{
"epoch": 0.29,
"learning_rate": 0.0003924474775537058,
"loss": 2.071,
"step": 48
},
{
"epoch": 0.3,
"learning_rate": 0.0003917335706073321,
"loss": 2.11,
"step": 50
},
{
"epoch": 0.31,
"learning_rate": 0.0003909881383204581,
"loss": 2.1477,
"step": 52
},
{
"epoch": 0.33,
"learning_rate": 0.00039021130325903074,
"loss": 2.087,
"step": 54
},
{
"epoch": 0.34,
"learning_rate": 0.0003894031931523243,
"loss": 2.0943,
"step": 56
},
{
"epoch": 0.35,
"learning_rate": 0.0003885639408719386,
"loss": 2.0061,
"step": 58
},
{
"epoch": 0.36,
"learning_rate": 0.0003876936844099521,
"loss": 2.0888,
"step": 60
},
{
"epoch": 0.37,
"learning_rate": 0.00038679256685623264,
"loss": 2.1795,
"step": 62
},
{
"epoch": 0.39,
"learning_rate": 0.0003858607363749104,
"loss": 2.1248,
"step": 64
},
{
"epoch": 0.4,
"learning_rate": 0.00038489834618001635,
"loss": 2.0761,
"step": 66
},
{
"epoch": 0.41,
"learning_rate": 0.0003839055545102902,
"loss": 2.1293,
"step": 68
},
{
"epoch": 0.42,
"learning_rate": 0.00038288252460316253,
"loss": 2.0532,
"step": 70
},
{
"epoch": 0.44,
"learning_rate": 0.000381829424667915,
"loss": 2.1937,
"step": 72
},
{
"epoch": 0.45,
"learning_rate": 0.0003807464278580227,
"loss": 2.1357,
"step": 74
},
{
"epoch": 0.46,
"learning_rate": 0.0003796337122426838,
"loss": 2.132,
"step": 76
},
{
"epoch": 0.47,
"learning_rate": 0.0003784914607775412,
"loss": 2.0785,
"step": 78
},
{
"epoch": 0.48,
"learning_rate": 0.00037731986127460007,
"loss": 2.1671,
"step": 80
},
{
"epoch": 0.5,
"learning_rate": 0.0003761191063713476,
"loss": 2.1016,
"step": 82
},
{
"epoch": 0.51,
"learning_rate": 0.00037488939349907913,
"loss": 2.1284,
"step": 84
},
{
"epoch": 0.52,
"learning_rate": 0.0003736309248504357,
"loss": 2.1275,
"step": 86
},
{
"epoch": 0.53,
"learning_rate": 0.000372343907346159,
"loss": 2.0667,
"step": 88
},
{
"epoch": 0.54,
"learning_rate": 0.00037102855260106926,
"loss": 2.1596,
"step": 90
},
{
"epoch": 0.56,
"learning_rate": 0.0003696850768892705,
"loss": 2.1802,
"step": 92
},
{
"epoch": 0.57,
"learning_rate": 0.00036831370110859067,
"loss": 2.0789,
"step": 94
},
{
"epoch": 0.58,
"learning_rate": 0.00036691465074426054,
"loss": 2.1284,
"step": 96
},
{
"epoch": 0.59,
"learning_rate": 0.0003654881558318393,
"loss": 2.1499,
"step": 98
},
{
"epoch": 0.6,
"learning_rate": 0.0003640344509193912,
"loss": 2.063,
"step": 100
},
{
"epoch": 0.62,
"learning_rate": 0.00036255377502892054,
"loss": 2.0843,
"step": 102
},
{
"epoch": 0.63,
"learning_rate": 0.0003610463716170712,
"loss": 2.0807,
"step": 104
},
{
"epoch": 0.64,
"learning_rate": 0.00035951248853509696,
"loss": 2.0838,
"step": 106
},
{
"epoch": 0.65,
"learning_rate": 0.00035795237798810846,
"loss": 2.1357,
"step": 108
},
{
"epoch": 0.66,
"learning_rate": 0.000356366296493606,
"loss": 2.1482,
"step": 110
},
{
"epoch": 0.68,
"learning_rate": 0.00035475450483930137,
"loss": 2.0468,
"step": 112
},
{
"epoch": 0.69,
"learning_rate": 0.00035311726804023894,
"loss": 2.0996,
"step": 114
},
{
"epoch": 0.7,
"learning_rate": 0.0003514548552952211,
"loss": 2.1049,
"step": 116
},
{
"epoch": 0.71,
"learning_rate": 0.00034976753994254566,
"loss": 2.07,
"step": 118
},
{
"epoch": 0.73,
"learning_rate": 0.0003480555994150631,
"loss": 2.1217,
"step": 120
},
{
"epoch": 0.74,
"learning_rate": 0.0003463193151945603,
"loss": 2.0953,
"step": 122
},
{
"epoch": 0.75,
"learning_rate": 0.0003445589727654783,
"loss": 2.1044,
"step": 124
},
{
"epoch": 0.76,
"learning_rate": 0.0003427748615679726,
"loss": 2.0992,
"step": 126
},
{
"epoch": 0.77,
"learning_rate": 0.00034096727495032235,
"loss": 2.1416,
"step": 128
},
{
"epoch": 0.79,
"learning_rate": 0.00033913651012069734,
"loss": 2.1709,
"step": 130
},
{
"epoch": 0.8,
"learning_rate": 0.0003372828680982901,
"loss": 2.1202,
"step": 132
},
{
"epoch": 0.81,
"learning_rate": 0.0003354066536638219,
"loss": 2.145,
"step": 134
},
{
"epoch": 0.82,
"learning_rate": 0.0003335081753094296,
"loss": 2.1667,
"step": 136
},
{
"epoch": 0.83,
"learning_rate": 0.00033158774518794254,
"loss": 2.0619,
"step": 138
},
{
"epoch": 0.85,
"learning_rate": 0.00032964567906155774,
"loss": 2.0791,
"step": 140
},
{
"epoch": 0.86,
"learning_rate": 0.0003276822962499211,
"loss": 2.1484,
"step": 142
},
{
"epoch": 0.87,
"learning_rate": 0.0003256979195776247,
"loss": 2.1358,
"step": 144
},
{
"epoch": 0.88,
"learning_rate": 0.00032369287532112634,
"loss": 2.0854,
"step": 146
},
{
"epoch": 0.89,
"learning_rate": 0.0003216674931551027,
"loss": 2.1297,
"step": 148
},
{
"epoch": 0.91,
"learning_rate": 0.00031962210609824324,
"loss": 2.0643,
"step": 150
},
{
"epoch": 0.92,
"learning_rate": 0.00031755705045849464,
"loss": 2.1189,
"step": 152
},
{
"epoch": 0.93,
"learning_rate": 0.00031547266577776394,
"loss": 2.1361,
"step": 154
},
{
"epoch": 0.94,
"learning_rate": 0.00031336929477609,
"loss": 2.0426,
"step": 156
},
{
"epoch": 0.95,
"learning_rate": 0.000311247283295293,
"loss": 2.0954,
"step": 158
},
{
"epoch": 0.97,
"learning_rate": 0.0003091069802421097,
"loss": 2.1072,
"step": 160
},
{
"epoch": 0.98,
"learning_rate": 0.00030694873753082594,
"loss": 2.1506,
"step": 162
},
{
"epoch": 0.99,
"learning_rate": 0.0003047729100254131,
"loss": 2.1293,
"step": 164
},
{
"epoch": 1.01,
"learning_rate": 0.00030257985548118126,
"loss": 2.5226,
"step": 166
},
{
"epoch": 1.02,
"learning_rate": 0.00030036993448595556,
"loss": 2.0338,
"step": 168
},
{
"epoch": 1.03,
"learning_rate": 0.0002981435104007876,
"loss": 2.0049,
"step": 170
},
{
"epoch": 1.04,
"learning_rate": 0.0002959009493002108,
"loss": 2.0443,
"step": 172
},
{
"epoch": 1.05,
"learning_rate": 0.0002936426199120492,
"loss": 2.0638,
"step": 174
},
{
"epoch": 1.07,
"learning_rate": 0.0002913688935567903,
"loss": 2.039,
"step": 176
},
{
"epoch": 1.08,
"learning_rate": 0.0002890801440865318,
"loss": 1.9961,
"step": 178
},
{
"epoch": 1.09,
"learning_rate": 0.00028677674782351165,
"loss": 1.9829,
"step": 180
},
{
"epoch": 1.1,
"learning_rate": 0.000284459083498232,
"loss": 1.9802,
"step": 182
},
{
"epoch": 1.11,
"learning_rate": 0.0002821275321871876,
"loss": 2.012,
"step": 184
},
{
"epoch": 1.13,
"learning_rate": 0.0002797824772502084,
"loss": 1.9602,
"step": 186
},
{
"epoch": 1.14,
"learning_rate": 0.00027742430426742567,
"loss": 2.1046,
"step": 188
},
{
"epoch": 1.15,
"learning_rate": 0.0002750534009758749,
"loss": 2.046,
"step": 190
},
{
"epoch": 1.16,
"learning_rate": 0.0002726701572057423,
"loss": 2.0335,
"step": 192
},
{
"epoch": 1.18,
"learning_rate": 0.0002702749648162686,
"loss": 1.9656,
"step": 194
},
{
"epoch": 1.19,
"learning_rate": 0.0002678682176313175,
"loss": 1.9843,
"step": 196
},
{
"epoch": 1.2,
"learning_rate": 0.0002654503113746234,
"loss": 2.0132,
"step": 198
},
{
"epoch": 1.21,
"learning_rate": 0.0002630216436047242,
"loss": 2.0522,
"step": 200
},
{
"epoch": 1.22,
"learning_rate": 0.00026058261364959444,
"loss": 2.0108,
"step": 202
},
{
"epoch": 1.24,
"learning_rate": 0.00025813362254098677,
"loss": 2.0582,
"step": 204
},
{
"epoch": 1.25,
"learning_rate": 0.0002556750729484927,
"loss": 1.9982,
"step": 206
},
{
"epoch": 1.26,
"learning_rate": 0.00025320736911333503,
"loss": 2.0753,
"step": 208
},
{
"epoch": 1.27,
"learning_rate": 0.0002507309167819015,
"loss": 2.04,
"step": 210
},
{
"epoch": 1.28,
"learning_rate": 0.00024824612313903053,
"loss": 1.9574,
"step": 212
},
{
"epoch": 1.3,
"learning_rate": 0.0002457533967410611,
"loss": 2.06,
"step": 214
},
{
"epoch": 1.31,
"learning_rate": 0.00024325314744865672,
"loss": 2.0338,
"step": 216
},
{
"epoch": 1.32,
"learning_rate": 0.00024074578635941514,
"loss": 2.012,
"step": 218
},
{
"epoch": 1.33,
"learning_rate": 0.0002382317257402745,
"loss": 2.0156,
"step": 220
},
{
"epoch": 1.34,
"learning_rate": 0.00023571137895972733,
"loss": 2.0225,
"step": 222
},
{
"epoch": 1.36,
"learning_rate": 0.0002331851604198536,
"loss": 2.0278,
"step": 224
},
{
"epoch": 1.37,
"learning_rate": 0.00023065348548818317,
"loss": 2.1048,
"step": 226
},
{
"epoch": 1.38,
"learning_rate": 0.00022811677042940058,
"loss": 1.9557,
"step": 228
}
],
"max_steps": 495,
"num_train_epochs": 3,
"total_flos": 1.0784042558129439e+18,
"trial_name": null,
"trial_params": null
}