stash's picture
Upload folder using huggingface_hub
ae21ef2 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.997624703087886,
"global_step": 336,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1.8181818181818182e-05,
"loss": 0.9273,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 3.6363636363636364e-05,
"loss": 0.8935,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 5.4545454545454546e-05,
"loss": 0.8695,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 7.272727272727273e-05,
"loss": 0.7756,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 9.090909090909092e-05,
"loss": 0.67,
"step": 5
},
{
"epoch": 0.02,
"learning_rate": 0.00010909090909090909,
"loss": 0.5996,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 0.00012727272727272728,
"loss": 0.5421,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 0.00014545454545454546,
"loss": 0.488,
"step": 8
},
{
"epoch": 0.03,
"learning_rate": 0.00016363636363636366,
"loss": 0.3799,
"step": 9
},
{
"epoch": 0.03,
"learning_rate": 0.00018181818181818183,
"loss": 0.3241,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.2884,
"step": 11
},
{
"epoch": 0.04,
"learning_rate": 0.0001999953280342959,
"loss": 0.2695,
"step": 12
},
{
"epoch": 0.04,
"learning_rate": 0.00019998131257372876,
"loss": 0.2523,
"step": 13
},
{
"epoch": 0.04,
"learning_rate": 0.0001999579549278937,
"loss": 0.2305,
"step": 14
},
{
"epoch": 0.04,
"learning_rate": 0.00019992525727931303,
"loss": 0.2262,
"step": 15
},
{
"epoch": 0.05,
"learning_rate": 0.00019988322268323268,
"loss": 0.2072,
"step": 16
},
{
"epoch": 0.05,
"learning_rate": 0.0001998318550673364,
"loss": 0.2102,
"step": 17
},
{
"epoch": 0.05,
"learning_rate": 0.00019977115923137912,
"loss": 0.1809,
"step": 18
},
{
"epoch": 0.06,
"learning_rate": 0.00019970114084673796,
"loss": 0.1765,
"step": 19
},
{
"epoch": 0.06,
"learning_rate": 0.0001996218064558829,
"loss": 0.1891,
"step": 20
},
{
"epoch": 0.06,
"learning_rate": 0.00019953316347176488,
"loss": 0.1779,
"step": 21
},
{
"epoch": 0.07,
"learning_rate": 0.00019943522017712358,
"loss": 0.172,
"step": 22
},
{
"epoch": 0.07,
"learning_rate": 0.0001993279857237133,
"loss": 0.1608,
"step": 23
},
{
"epoch": 0.07,
"learning_rate": 0.0001992114701314478,
"loss": 0.1491,
"step": 24
},
{
"epoch": 0.07,
"learning_rate": 0.0001990856842874641,
"loss": 0.1558,
"step": 25
},
{
"epoch": 0.08,
"learning_rate": 0.0001989506399451051,
"loss": 0.1519,
"step": 26
},
{
"epoch": 0.08,
"learning_rate": 0.00019880634972282166,
"loss": 0.1373,
"step": 27
},
{
"epoch": 0.08,
"learning_rate": 0.0001986528271029931,
"loss": 0.1429,
"step": 28
},
{
"epoch": 0.09,
"learning_rate": 0.00019849008643066772,
"loss": 0.1231,
"step": 29
},
{
"epoch": 0.09,
"learning_rate": 0.00019831814291222232,
"loss": 0.1179,
"step": 30
},
{
"epoch": 0.09,
"learning_rate": 0.00019813701261394136,
"loss": 0.1082,
"step": 31
},
{
"epoch": 0.1,
"learning_rate": 0.0001979467124605156,
"loss": 0.1046,
"step": 32
},
{
"epoch": 0.1,
"learning_rate": 0.0001977472602334609,
"loss": 0.0883,
"step": 33
},
{
"epoch": 0.1,
"learning_rate": 0.0001975386745694565,
"loss": 0.0769,
"step": 34
},
{
"epoch": 0.1,
"learning_rate": 0.00019732097495860386,
"loss": 0.0738,
"step": 35
},
{
"epoch": 0.11,
"learning_rate": 0.0001970941817426052,
"loss": 0.0651,
"step": 36
},
{
"epoch": 0.11,
"learning_rate": 0.0001968583161128631,
"loss": 0.0555,
"step": 37
},
{
"epoch": 0.11,
"learning_rate": 0.00019661340010850026,
"loss": 0.0508,
"step": 38
},
{
"epoch": 0.12,
"learning_rate": 0.00019635945661430006,
"loss": 0.0478,
"step": 39
},
{
"epoch": 0.12,
"learning_rate": 0.00019609650935856844,
"loss": 0.0343,
"step": 40
},
{
"epoch": 0.12,
"learning_rate": 0.00019582458291091663,
"loss": 0.0372,
"step": 41
},
{
"epoch": 0.12,
"learning_rate": 0.00019554370267996538,
"loss": 0.0274,
"step": 42
},
{
"epoch": 0.13,
"learning_rate": 0.0001952538949109708,
"loss": 0.0283,
"step": 43
},
{
"epoch": 0.13,
"learning_rate": 0.00019495518668337201,
"loss": 0.0225,
"step": 44
},
{
"epoch": 0.13,
"learning_rate": 0.00019464760590826098,
"loss": 0.0196,
"step": 45
},
{
"epoch": 0.14,
"learning_rate": 0.0001943311813257743,
"loss": 0.0186,
"step": 46
},
{
"epoch": 0.14,
"learning_rate": 0.00019400594250240798,
"loss": 0.0152,
"step": 47
},
{
"epoch": 0.14,
"learning_rate": 0.0001936719198282545,
"loss": 0.0168,
"step": 48
},
{
"epoch": 0.15,
"learning_rate": 0.00019332914451416347,
"loss": 0.0093,
"step": 49
},
{
"epoch": 0.15,
"learning_rate": 0.00019297764858882514,
"loss": 0.0145,
"step": 50
},
{
"epoch": 0.15,
"learning_rate": 0.00019261746489577765,
"loss": 0.0086,
"step": 51
},
{
"epoch": 0.15,
"learning_rate": 0.00019224862709033824,
"loss": 0.0107,
"step": 52
},
{
"epoch": 0.16,
"learning_rate": 0.00019187116963645842,
"loss": 0.0071,
"step": 53
},
{
"epoch": 0.16,
"learning_rate": 0.00019148512780350384,
"loss": 0.0075,
"step": 54
},
{
"epoch": 0.16,
"learning_rate": 0.0001910905376629585,
"loss": 0.0056,
"step": 55
},
{
"epoch": 0.17,
"learning_rate": 0.00019068743608505455,
"loss": 0.0059,
"step": 56
},
{
"epoch": 0.17,
"learning_rate": 0.0001902758607353269,
"loss": 0.0034,
"step": 57
},
{
"epoch": 0.17,
"learning_rate": 0.0001898558500710939,
"loss": 0.0059,
"step": 58
},
{
"epoch": 0.18,
"learning_rate": 0.00018942744333786397,
"loss": 0.0046,
"step": 59
},
{
"epoch": 0.18,
"learning_rate": 0.0001889906805656684,
"loss": 0.0055,
"step": 60
},
{
"epoch": 0.18,
"learning_rate": 0.000188545602565321,
"loss": 0.0039,
"step": 61
},
{
"epoch": 0.18,
"learning_rate": 0.00018809225092460488,
"loss": 0.0023,
"step": 62
},
{
"epoch": 0.19,
"learning_rate": 0.00018763066800438636,
"loss": 0.0032,
"step": 63
},
{
"epoch": 0.19,
"learning_rate": 0.00018716089693465696,
"loss": 0.002,
"step": 64
},
{
"epoch": 0.19,
"learning_rate": 0.00018668298161050309,
"loss": 0.0026,
"step": 65
},
{
"epoch": 0.2,
"learning_rate": 0.00018619696668800492,
"loss": 0.0012,
"step": 66
},
{
"epoch": 0.2,
"learning_rate": 0.00018570289758006346,
"loss": 0.0021,
"step": 67
},
{
"epoch": 0.2,
"learning_rate": 0.0001852008204521572,
"loss": 0.0017,
"step": 68
},
{
"epoch": 0.2,
"learning_rate": 0.0001846907822180286,
"loss": 0.0007,
"step": 69
},
{
"epoch": 0.21,
"learning_rate": 0.00018417283053530044,
"loss": 0.0017,
"step": 70
},
{
"epoch": 0.21,
"learning_rate": 0.00018364701380102266,
"loss": 0.001,
"step": 71
},
{
"epoch": 0.21,
"learning_rate": 0.0001831133811471503,
"loss": 0.001,
"step": 72
},
{
"epoch": 0.22,
"learning_rate": 0.0001825719824359524,
"loss": 0.0012,
"step": 73
},
{
"epoch": 0.22,
"learning_rate": 0.0001820228682553533,
"loss": 0.0004,
"step": 74
},
{
"epoch": 0.22,
"learning_rate": 0.00018146608991420534,
"loss": 0.0013,
"step": 75
},
{
"epoch": 0.23,
"learning_rate": 0.00018090169943749476,
"loss": 0.0009,
"step": 76
},
{
"epoch": 0.23,
"learning_rate": 0.00018032974956148063,
"loss": 0.002,
"step": 77
},
{
"epoch": 0.23,
"learning_rate": 0.00017975029372876706,
"loss": 0.0014,
"step": 78
},
{
"epoch": 0.23,
"learning_rate": 0.0001791633860833096,
"loss": 0.0024,
"step": 79
},
{
"epoch": 0.24,
"learning_rate": 0.00017856908146535603,
"loss": 0.0013,
"step": 80
},
{
"epoch": 0.24,
"learning_rate": 0.00017796743540632223,
"loss": 0.0013,
"step": 81
},
{
"epoch": 0.24,
"learning_rate": 0.00017735850412360331,
"loss": 0.0006,
"step": 82
},
{
"epoch": 0.25,
"learning_rate": 0.00017674234451532065,
"loss": 0.0006,
"step": 83
},
{
"epoch": 0.25,
"learning_rate": 0.00017611901415500535,
"loss": 0.003,
"step": 84
},
{
"epoch": 0.25,
"learning_rate": 0.00017548857128621875,
"loss": 0.002,
"step": 85
},
{
"epoch": 0.26,
"learning_rate": 0.00017485107481711012,
"loss": 0.0013,
"step": 86
},
{
"epoch": 0.26,
"learning_rate": 0.00017420658431491223,
"loss": 0.0038,
"step": 87
},
{
"epoch": 0.26,
"learning_rate": 0.00017355516000037554,
"loss": 0.0015,
"step": 88
},
{
"epoch": 0.26,
"learning_rate": 0.00017289686274214118,
"loss": 0.0041,
"step": 89
},
{
"epoch": 0.27,
"learning_rate": 0.0001722317540510534,
"loss": 0.0013,
"step": 90
},
{
"epoch": 0.27,
"learning_rate": 0.00017155989607441213,
"loss": 0.0022,
"step": 91
},
{
"epoch": 0.27,
"learning_rate": 0.00017088135159016584,
"loss": 0.0033,
"step": 92
},
{
"epoch": 0.28,
"learning_rate": 0.00017019618400104572,
"loss": 0.0012,
"step": 93
},
{
"epoch": 0.28,
"learning_rate": 0.00016950445732864127,
"loss": 0.004,
"step": 94
},
{
"epoch": 0.28,
"learning_rate": 0.00016880623620741842,
"loss": 0.0016,
"step": 95
},
{
"epoch": 0.29,
"learning_rate": 0.00016810158587867973,
"loss": 0.0031,
"step": 96
},
{
"epoch": 0.29,
"learning_rate": 0.0001673905721844686,
"loss": 0.0009,
"step": 97
},
{
"epoch": 0.29,
"learning_rate": 0.00016667326156141692,
"loss": 0.001,
"step": 98
},
{
"epoch": 0.29,
"learning_rate": 0.00016594972103453726,
"loss": 0.0008,
"step": 99
},
{
"epoch": 0.3,
"learning_rate": 0.0001652200182109602,
"loss": 0.0018,
"step": 100
},
{
"epoch": 0.3,
"learning_rate": 0.00016448422127361706,
"loss": 0.0006,
"step": 101
},
{
"epoch": 0.3,
"learning_rate": 0.000163742398974869,
"loss": 0.0007,
"step": 102
},
{
"epoch": 0.31,
"learning_rate": 0.00016299462063008272,
"loss": 0.0013,
"step": 103
},
{
"epoch": 0.31,
"learning_rate": 0.00016224095611115384,
"loss": 0.0007,
"step": 104
},
{
"epoch": 0.31,
"learning_rate": 0.00016148147583997812,
"loss": 0.0004,
"step": 105
},
{
"epoch": 0.31,
"learning_rate": 0.00016071625078187114,
"loss": 0.0007,
"step": 106
},
{
"epoch": 0.32,
"learning_rate": 0.0001599453524389374,
"loss": 0.0005,
"step": 107
},
{
"epoch": 0.32,
"learning_rate": 0.00015916885284338937,
"loss": 0.0004,
"step": 108
},
{
"epoch": 0.32,
"learning_rate": 0.00015838682455081657,
"loss": 0.0003,
"step": 109
},
{
"epoch": 0.33,
"learning_rate": 0.00015759934063340627,
"loss": 0.0003,
"step": 110
},
{
"epoch": 0.33,
"learning_rate": 0.00015680647467311557,
"loss": 0.0003,
"step": 111
},
{
"epoch": 0.33,
"learning_rate": 0.00015600830075479603,
"loss": 0.0002,
"step": 112
},
{
"epoch": 0.34,
"learning_rate": 0.00015520489345927096,
"loss": 0.0002,
"step": 113
},
{
"epoch": 0.34,
"learning_rate": 0.00015439632785636706,
"loss": 0.0002,
"step": 114
},
{
"epoch": 0.34,
"learning_rate": 0.00015358267949789966,
"loss": 0.0001,
"step": 115
},
{
"epoch": 0.34,
"learning_rate": 0.0001527640244106133,
"loss": 0.0002,
"step": 116
},
{
"epoch": 0.35,
"learning_rate": 0.00015194043908907775,
"loss": 0.0002,
"step": 117
},
{
"epoch": 0.35,
"learning_rate": 0.00015111200048854056,
"loss": 0.0003,
"step": 118
},
{
"epoch": 0.35,
"learning_rate": 0.00015027878601773633,
"loss": 0.0001,
"step": 119
},
{
"epoch": 0.36,
"learning_rate": 0.0001494408735316537,
"loss": 0.0001,
"step": 120
},
{
"epoch": 0.36,
"learning_rate": 0.0001485983413242606,
"loss": 0.0001,
"step": 121
},
{
"epoch": 0.36,
"learning_rate": 0.00014775126812118864,
"loss": 0.0001,
"step": 122
},
{
"epoch": 0.37,
"learning_rate": 0.00014689973307237687,
"loss": 0.0001,
"step": 123
},
{
"epoch": 0.37,
"learning_rate": 0.00014604381574467615,
"loss": 0.0001,
"step": 124
},
{
"epoch": 0.37,
"learning_rate": 0.0001451835961144145,
"loss": 0.0001,
"step": 125
},
{
"epoch": 0.37,
"learning_rate": 0.00014431915455992414,
"loss": 0.0001,
"step": 126
},
{
"epoch": 0.38,
"learning_rate": 0.000143450571854031,
"loss": 0.0001,
"step": 127
},
{
"epoch": 0.38,
"learning_rate": 0.00014257792915650728,
"loss": 0.0001,
"step": 128
},
{
"epoch": 0.38,
"learning_rate": 0.00014170130800648814,
"loss": 0.0001,
"step": 129
},
{
"epoch": 0.39,
"learning_rate": 0.0001408207903148525,
"loss": 0.0,
"step": 130
},
{
"epoch": 0.39,
"learning_rate": 0.00013993645835656953,
"loss": 0.0,
"step": 131
},
{
"epoch": 0.39,
"learning_rate": 0.0001390483947630109,
"loss": 0.0,
"step": 132
},
{
"epoch": 0.39,
"learning_rate": 0.00013815668251422952,
"loss": 0.0,
"step": 133
},
{
"epoch": 0.4,
"learning_rate": 0.0001372614049312064,
"loss": 0.0,
"step": 134
},
{
"epoch": 0.4,
"learning_rate": 0.0001363626456680647,
"loss": 0.0,
"step": 135
},
{
"epoch": 0.4,
"learning_rate": 0.00013546048870425356,
"loss": 0.0,
"step": 136
},
{
"epoch": 0.41,
"learning_rate": 0.00013455501833670088,
"loss": 0.0,
"step": 137
},
{
"epoch": 0.41,
"learning_rate": 0.0001336463191719367,
"loss": 0.0,
"step": 138
},
{
"epoch": 0.41,
"learning_rate": 0.00013273447611818767,
"loss": 0.0,
"step": 139
},
{
"epoch": 0.42,
"learning_rate": 0.00013181957437744332,
"loss": 0.0,
"step": 140
},
{
"epoch": 0.42,
"learning_rate": 0.00013090169943749476,
"loss": 0.0,
"step": 141
},
{
"epoch": 0.42,
"learning_rate": 0.00012998093706394675,
"loss": 0.0,
"step": 142
},
{
"epoch": 0.42,
"learning_rate": 0.00012905737329220392,
"loss": 0.0,
"step": 143
},
{
"epoch": 0.43,
"learning_rate": 0.00012813109441943166,
"loss": 0.0,
"step": 144
},
{
"epoch": 0.43,
"learning_rate": 0.00012720218699649243,
"loss": 0.0,
"step": 145
},
{
"epoch": 0.43,
"learning_rate": 0.0001262707378198587,
"loss": 0.0,
"step": 146
},
{
"epoch": 0.44,
"learning_rate": 0.00012533683392350263,
"loss": 0.0,
"step": 147
},
{
"epoch": 0.44,
"learning_rate": 0.00012440056257076375,
"loss": 0.0,
"step": 148
},
{
"epoch": 0.44,
"learning_rate": 0.00012346201124619502,
"loss": 0.0,
"step": 149
},
{
"epoch": 0.45,
"learning_rate": 0.00012252126764738844,
"loss": 0.0,
"step": 150
},
{
"epoch": 0.45,
"learning_rate": 0.00012157841967678063,
"loss": 0.0,
"step": 151
},
{
"epoch": 0.45,
"learning_rate": 0.00012063355543343924,
"loss": 0.0,
"step": 152
},
{
"epoch": 0.45,
"learning_rate": 0.00011968676320483103,
"loss": 0.0,
"step": 153
},
{
"epoch": 0.46,
"learning_rate": 0.00011873813145857249,
"loss": 0.0,
"step": 154
},
{
"epoch": 0.46,
"learning_rate": 0.00011778774883416323,
"loss": 0.0,
"step": 155
},
{
"epoch": 0.46,
"learning_rate": 0.00011683570413470383,
"loss": 0.0,
"step": 156
},
{
"epoch": 0.47,
"learning_rate": 0.00011588208631859807,
"loss": 0.0,
"step": 157
},
{
"epoch": 0.47,
"learning_rate": 0.00011492698449124042,
"loss": 0.0,
"step": 158
},
{
"epoch": 0.47,
"learning_rate": 0.0001139704878966906,
"loss": 0.0,
"step": 159
},
{
"epoch": 0.48,
"learning_rate": 0.00011301268590933434,
"loss": 0.0,
"step": 160
},
{
"epoch": 0.48,
"learning_rate": 0.0001120536680255323,
"loss": 0.0,
"step": 161
},
{
"epoch": 0.48,
"learning_rate": 0.00011109352385525783,
"loss": 0.0,
"step": 162
},
{
"epoch": 0.48,
"learning_rate": 0.00011013234311372353,
"loss": 0.0,
"step": 163
},
{
"epoch": 0.49,
"learning_rate": 0.00010917021561299863,
"loss": 0.0,
"step": 164
},
{
"epoch": 0.49,
"learning_rate": 0.00010820723125361684,
"loss": 0.0,
"step": 165
},
{
"epoch": 0.49,
"learning_rate": 0.00010724348001617625,
"loss": 0.0,
"step": 166
},
{
"epoch": 0.5,
"learning_rate": 0.00010627905195293135,
"loss": 0.0,
"step": 167
},
{
"epoch": 0.5,
"learning_rate": 0.00010531403717937887,
"loss": 0.0,
"step": 168
},
{
"epoch": 0.5,
"learning_rate": 0.00010434852586583736,
"loss": 0.0,
"step": 169
},
{
"epoch": 0.5,
"learning_rate": 0.00010338260822902167,
"loss": 0.0,
"step": 170
},
{
"epoch": 0.51,
"learning_rate": 0.00010241637452361323,
"loss": 0.0,
"step": 171
},
{
"epoch": 0.51,
"learning_rate": 0.00010144991503382674,
"loss": 0.0,
"step": 172
},
{
"epoch": 0.51,
"learning_rate": 0.00010048332006497406,
"loss": 0.0,
"step": 173
},
{
"epoch": 0.52,
"learning_rate": 9.9516679935026e-05,
"loss": 0.0,
"step": 174
},
{
"epoch": 0.52,
"learning_rate": 9.855008496617327e-05,
"loss": 0.0,
"step": 175
},
{
"epoch": 0.52,
"learning_rate": 9.75836254763868e-05,
"loss": 0.0,
"step": 176
},
{
"epoch": 0.53,
"learning_rate": 9.661739177097836e-05,
"loss": 0.0,
"step": 177
},
{
"epoch": 0.53,
"learning_rate": 9.565147413416266e-05,
"loss": 0.0,
"step": 178
},
{
"epoch": 0.53,
"learning_rate": 9.468596282062114e-05,
"loss": 0.0,
"step": 179
},
{
"epoch": 0.53,
"learning_rate": 9.372094804706867e-05,
"loss": 0.0,
"step": 180
},
{
"epoch": 0.54,
"learning_rate": 9.275651998382377e-05,
"loss": 0.0,
"step": 181
},
{
"epoch": 0.54,
"learning_rate": 9.179276874638315e-05,
"loss": 0.0,
"step": 182
},
{
"epoch": 0.54,
"learning_rate": 9.082978438700138e-05,
"loss": 0.0,
"step": 183
},
{
"epoch": 0.55,
"learning_rate": 8.986765688627652e-05,
"loss": 0.0,
"step": 184
},
{
"epoch": 0.55,
"learning_rate": 8.890647614474224e-05,
"loss": 0.0,
"step": 185
},
{
"epoch": 0.55,
"learning_rate": 8.79463319744677e-05,
"loss": 0.0,
"step": 186
},
{
"epoch": 0.56,
"learning_rate": 8.698731409066568e-05,
"loss": 0.0,
"step": 187
},
{
"epoch": 0.56,
"learning_rate": 8.602951210330942e-05,
"loss": 0.0,
"step": 188
},
{
"epoch": 0.56,
"learning_rate": 8.50730155087596e-05,
"loss": 0.0,
"step": 189
},
{
"epoch": 0.56,
"learning_rate": 8.411791368140196e-05,
"loss": 0.0,
"step": 190
},
{
"epoch": 0.57,
"learning_rate": 8.316429586529615e-05,
"loss": 0.0,
"step": 191
},
{
"epoch": 0.57,
"learning_rate": 8.221225116583678e-05,
"loss": 0.0,
"step": 192
},
{
"epoch": 0.57,
"learning_rate": 8.126186854142752e-05,
"loss": 0.0,
"step": 193
},
{
"epoch": 0.58,
"learning_rate": 8.0313236795169e-05,
"loss": 0.0,
"step": 194
},
{
"epoch": 0.58,
"learning_rate": 7.936644456656081e-05,
"loss": 0.0,
"step": 195
},
{
"epoch": 0.58,
"learning_rate": 7.84215803232194e-05,
"loss": 0.0,
"step": 196
},
{
"epoch": 0.58,
"learning_rate": 7.747873235261157e-05,
"loss": 0.0,
"step": 197
},
{
"epoch": 0.59,
"learning_rate": 7.6537988753805e-05,
"loss": 0.0,
"step": 198
},
{
"epoch": 0.59,
"learning_rate": 7.559943742923626e-05,
"loss": 0.0,
"step": 199
},
{
"epoch": 0.59,
"learning_rate": 7.466316607649738e-05,
"loss": 0.0,
"step": 200
},
{
"epoch": 0.6,
"learning_rate": 7.372926218014131e-05,
"loss": 0.0,
"step": 201
},
{
"epoch": 0.6,
"learning_rate": 7.279781300350758e-05,
"loss": 0.0,
"step": 202
},
{
"epoch": 0.6,
"learning_rate": 7.186890558056836e-05,
"loss": 0.0,
"step": 203
},
{
"epoch": 0.61,
"learning_rate": 7.094262670779612e-05,
"loss": 0.0,
"step": 204
},
{
"epoch": 0.61,
"learning_rate": 7.00190629360533e-05,
"loss": 0.0,
"step": 205
},
{
"epoch": 0.61,
"learning_rate": 6.909830056250527e-05,
"loss": 0.0,
"step": 206
},
{
"epoch": 0.61,
"learning_rate": 6.81804256225567e-05,
"loss": 0.0,
"step": 207
},
{
"epoch": 0.62,
"learning_rate": 6.726552388181233e-05,
"loss": 0.0,
"step": 208
},
{
"epoch": 0.62,
"learning_rate": 6.63536808280633e-05,
"loss": 0.0,
"step": 209
},
{
"epoch": 0.62,
"learning_rate": 6.544498166329913e-05,
"loss": 0.0,
"step": 210
},
{
"epoch": 0.63,
"learning_rate": 6.453951129574644e-05,
"loss": 0.0,
"step": 211
},
{
"epoch": 0.63,
"learning_rate": 6.36373543319353e-05,
"loss": 0.0,
"step": 212
},
{
"epoch": 0.63,
"learning_rate": 6.273859506879365e-05,
"loss": 0.0,
"step": 213
},
{
"epoch": 0.64,
"learning_rate": 6.18433174857705e-05,
"loss": 0.0,
"step": 214
},
{
"epoch": 0.64,
"learning_rate": 6.095160523698913e-05,
"loss": 0.0,
"step": 215
},
{
"epoch": 0.64,
"learning_rate": 6.006354164343046e-05,
"loss": 0.0,
"step": 216
},
{
"epoch": 0.64,
"learning_rate": 5.917920968514752e-05,
"loss": 0.0,
"step": 217
},
{
"epoch": 0.65,
"learning_rate": 5.829869199351188e-05,
"loss": 0.0,
"step": 218
},
{
"epoch": 0.65,
"learning_rate": 5.7422070843492734e-05,
"loss": 0.0,
"step": 219
},
{
"epoch": 0.65,
"learning_rate": 5.654942814596902e-05,
"loss": 0.0,
"step": 220
},
{
"epoch": 0.66,
"learning_rate": 5.568084544007588e-05,
"loss": 0.0,
"step": 221
},
{
"epoch": 0.66,
"learning_rate": 5.481640388558551e-05,
"loss": 0.0,
"step": 222
},
{
"epoch": 0.66,
"learning_rate": 5.395618425532389e-05,
"loss": 0.0,
"step": 223
},
{
"epoch": 0.67,
"learning_rate": 5.3100266927623156e-05,
"loss": 0.0,
"step": 224
},
{
"epoch": 0.67,
"learning_rate": 5.2248731878811365e-05,
"loss": 0.0,
"step": 225
},
{
"epoch": 0.67,
"learning_rate": 5.14016586757394e-05,
"loss": 0.0,
"step": 226
},
{
"epoch": 0.67,
"learning_rate": 5.055912646834635e-05,
"loss": 0.0,
"step": 227
},
{
"epoch": 0.68,
"learning_rate": 4.972121398226371e-05,
"loss": 0.0,
"step": 228
},
{
"epoch": 0.68,
"learning_rate": 4.888799951145948e-05,
"loss": 0.0,
"step": 229
},
{
"epoch": 0.68,
"learning_rate": 4.805956091092227e-05,
"loss": 0.0,
"step": 230
},
{
"epoch": 0.69,
"learning_rate": 4.723597558938672e-05,
"loss": 0.0,
"step": 231
},
{
"epoch": 0.69,
"learning_rate": 4.6417320502100316e-05,
"loss": 0.0,
"step": 232
},
{
"epoch": 0.69,
"learning_rate": 4.5603672143632944e-05,
"loss": 0.0,
"step": 233
},
{
"epoch": 0.69,
"learning_rate": 4.479510654072909e-05,
"loss": 0.0,
"step": 234
},
{
"epoch": 0.7,
"learning_rate": 4.399169924520403e-05,
"loss": 0.0,
"step": 235
},
{
"epoch": 0.7,
"learning_rate": 4.3193525326884435e-05,
"loss": 0.0,
"step": 236
},
{
"epoch": 0.7,
"learning_rate": 4.240065936659374e-05,
"loss": 0.0,
"step": 237
},
{
"epoch": 0.71,
"learning_rate": 4.161317544918345e-05,
"loss": 0.0,
"step": 238
},
{
"epoch": 0.71,
"learning_rate": 4.0831147156610684e-05,
"loss": 0.0,
"step": 239
},
{
"epoch": 0.71,
"learning_rate": 4.005464756106262e-05,
"loss": 0.0,
"step": 240
},
{
"epoch": 0.72,
"learning_rate": 3.9283749218128885e-05,
"loss": 0.0,
"step": 241
},
{
"epoch": 0.72,
"learning_rate": 3.851852416002187e-05,
"loss": 0.0,
"step": 242
},
{
"epoch": 0.72,
"learning_rate": 3.775904388884618e-05,
"loss": 0.0,
"step": 243
},
{
"epoch": 0.72,
"learning_rate": 3.7005379369917325e-05,
"loss": 0.0,
"step": 244
},
{
"epoch": 0.73,
"learning_rate": 3.6257601025131026e-05,
"loss": 0.0,
"step": 245
},
{
"epoch": 0.73,
"learning_rate": 3.5515778726382966e-05,
"loss": 0.0,
"step": 246
},
{
"epoch": 0.73,
"learning_rate": 3.477998178903982e-05,
"loss": 0.0,
"step": 247
},
{
"epoch": 0.74,
"learning_rate": 3.4050278965462764e-05,
"loss": 0.0,
"step": 248
},
{
"epoch": 0.74,
"learning_rate": 3.3326738438583114e-05,
"loss": 0.0,
"step": 249
},
{
"epoch": 0.74,
"learning_rate": 3.2609427815531426e-05,
"loss": 0.0,
"step": 250
},
{
"epoch": 0.75,
"learning_rate": 3.1898414121320276e-05,
"loss": 0.0,
"step": 251
},
{
"epoch": 0.75,
"learning_rate": 3.11937637925816e-05,
"loss": 0.0,
"step": 252
},
{
"epoch": 0.75,
"learning_rate": 3.0495542671358746e-05,
"loss": 0.0,
"step": 253
},
{
"epoch": 0.75,
"learning_rate": 2.9803815998954332e-05,
"loss": 0.0,
"step": 254
},
{
"epoch": 0.76,
"learning_rate": 2.9118648409834205e-05,
"loss": 0.0,
"step": 255
},
{
"epoch": 0.76,
"learning_rate": 2.84401039255879e-05,
"loss": 0.0,
"step": 256
},
{
"epoch": 0.76,
"learning_rate": 2.7768245948946612e-05,
"loss": 0.0,
"step": 257
},
{
"epoch": 0.77,
"learning_rate": 2.7103137257858868e-05,
"loss": 0.0,
"step": 258
},
{
"epoch": 0.77,
"learning_rate": 2.6444839999624494e-05,
"loss": 0.0,
"step": 259
},
{
"epoch": 0.77,
"learning_rate": 2.5793415685087797e-05,
"loss": 0.0,
"step": 260
},
{
"epoch": 0.77,
"learning_rate": 2.514892518288988e-05,
"loss": 0.0,
"step": 261
},
{
"epoch": 0.78,
"learning_rate": 2.4511428713781238e-05,
"loss": 0.0,
"step": 262
},
{
"epoch": 0.78,
"learning_rate": 2.3880985844994674e-05,
"loss": 0.0,
"step": 263
},
{
"epoch": 0.78,
"learning_rate": 2.3257655484679374e-05,
"loss": 0.0,
"step": 264
},
{
"epoch": 0.79,
"learning_rate": 2.2641495876396713e-05,
"loss": 0.0,
"step": 265
},
{
"epoch": 0.79,
"learning_rate": 2.2032564593677774e-05,
"loss": 0.0,
"step": 266
},
{
"epoch": 0.79,
"learning_rate": 2.1430918534643996e-05,
"loss": 0.0,
"step": 267
},
{
"epoch": 0.8,
"learning_rate": 2.0836613916690428e-05,
"loss": 0.0,
"step": 268
},
{
"epoch": 0.8,
"learning_rate": 2.024970627123295e-05,
"loss": 0.0,
"step": 269
},
{
"epoch": 0.8,
"learning_rate": 1.967025043851939e-05,
"loss": 0.0,
"step": 270
},
{
"epoch": 0.8,
"learning_rate": 1.9098300562505266e-05,
"loss": 0.0,
"step": 271
},
{
"epoch": 0.81,
"learning_rate": 1.8533910085794713e-05,
"loss": 0.0,
"step": 272
},
{
"epoch": 0.81,
"learning_rate": 1.7977131744646724e-05,
"loss": 0.0,
"step": 273
},
{
"epoch": 0.81,
"learning_rate": 1.7428017564047594e-05,
"loss": 0.0,
"step": 274
},
{
"epoch": 0.82,
"learning_rate": 1.6886618852849724e-05,
"loss": 0.0,
"step": 275
},
{
"epoch": 0.82,
"learning_rate": 1.6352986198977325e-05,
"loss": 0.0,
"step": 276
},
{
"epoch": 0.82,
"learning_rate": 1.5827169464699576e-05,
"loss": 0.0,
"step": 277
},
{
"epoch": 0.83,
"learning_rate": 1.530921778197142e-05,
"loss": 0.0,
"step": 278
},
{
"epoch": 0.83,
"learning_rate": 1.4799179547842822e-05,
"loss": 0.0,
"step": 279
},
{
"epoch": 0.83,
"learning_rate": 1.429710241993656e-05,
"loss": 0.0,
"step": 280
},
{
"epoch": 0.83,
"learning_rate": 1.3803033311995072e-05,
"loss": 0.0,
"step": 281
},
{
"epoch": 0.84,
"learning_rate": 1.3317018389496927e-05,
"loss": 0.0,
"step": 282
},
{
"epoch": 0.84,
"learning_rate": 1.2839103065343083e-05,
"loss": 0.0,
"step": 283
},
{
"epoch": 0.84,
"learning_rate": 1.2369331995613665e-05,
"loss": 0.0,
"step": 284
},
{
"epoch": 0.85,
"learning_rate": 1.1907749075395147e-05,
"loss": 0.0,
"step": 285
},
{
"epoch": 0.85,
"learning_rate": 1.1454397434679021e-05,
"loss": 0.0,
"step": 286
},
{
"epoch": 0.85,
"learning_rate": 1.1009319434331622e-05,
"loss": 0.0,
"step": 287
},
{
"epoch": 0.86,
"learning_rate": 1.0572556662136035e-05,
"loss": 0.0,
"step": 288
},
{
"epoch": 0.86,
"learning_rate": 1.014414992890611e-05,
"loss": 0.0,
"step": 289
},
{
"epoch": 0.86,
"learning_rate": 9.724139264673116e-06,
"loss": 0.0,
"step": 290
},
{
"epoch": 0.86,
"learning_rate": 9.31256391494546e-06,
"loss": 0.0,
"step": 291
},
{
"epoch": 0.87,
"learning_rate": 8.909462337041507e-06,
"loss": 0.0,
"step": 292
},
{
"epoch": 0.87,
"learning_rate": 8.514872196496183e-06,
"loss": 0.0,
"step": 293
},
{
"epoch": 0.87,
"learning_rate": 8.128830363541574e-06,
"loss": 0.0,
"step": 294
},
{
"epoch": 0.88,
"learning_rate": 7.751372909661769e-06,
"loss": 0.0,
"step": 295
},
{
"epoch": 0.88,
"learning_rate": 7.382535104222366e-06,
"loss": 0.0,
"step": 296
},
{
"epoch": 0.88,
"learning_rate": 7.022351411174866e-06,
"loss": 0.0,
"step": 297
},
{
"epoch": 0.88,
"learning_rate": 6.670855485836525e-06,
"loss": 0.0,
"step": 298
},
{
"epoch": 0.89,
"learning_rate": 6.32808017174551e-06,
"loss": 0.0,
"step": 299
},
{
"epoch": 0.89,
"learning_rate": 5.994057497592031e-06,
"loss": 0.0,
"step": 300
},
{
"epoch": 0.89,
"learning_rate": 5.668818674225685e-06,
"loss": 0.0,
"step": 301
},
{
"epoch": 0.9,
"learning_rate": 5.3523940917390215e-06,
"loss": 0.0,
"step": 302
},
{
"epoch": 0.9,
"learning_rate": 5.0448133166279944e-06,
"loss": 0.0,
"step": 303
},
{
"epoch": 0.9,
"learning_rate": 4.746105089029229e-06,
"loss": 0.0,
"step": 304
},
{
"epoch": 0.91,
"learning_rate": 4.4562973200346416e-06,
"loss": 0.0,
"step": 305
},
{
"epoch": 0.91,
"learning_rate": 4.175417089083378e-06,
"loss": 0.0,
"step": 306
},
{
"epoch": 0.91,
"learning_rate": 3.903490641431573e-06,
"loss": 0.0,
"step": 307
},
{
"epoch": 0.91,
"learning_rate": 3.6405433856999684e-06,
"loss": 0.0,
"step": 308
},
{
"epoch": 0.92,
"learning_rate": 3.3865998914997643e-06,
"loss": 0.0,
"step": 309
},
{
"epoch": 0.92,
"learning_rate": 3.1416838871368924e-06,
"loss": 0.0,
"step": 310
},
{
"epoch": 0.92,
"learning_rate": 2.905818257394799e-06,
"loss": 0.0,
"step": 311
},
{
"epoch": 0.93,
"learning_rate": 2.679025041396155e-06,
"loss": 0.0,
"step": 312
},
{
"epoch": 0.93,
"learning_rate": 2.461325430543482e-06,
"loss": 0.0,
"step": 313
},
{
"epoch": 0.93,
"learning_rate": 2.2527397665391027e-06,
"loss": 0.0,
"step": 314
},
{
"epoch": 0.94,
"learning_rate": 2.053287539484405e-06,
"loss": 0.0,
"step": 315
},
{
"epoch": 0.94,
"learning_rate": 1.8629873860586566e-06,
"loss": 0.0,
"step": 316
},
{
"epoch": 0.94,
"learning_rate": 1.6818570877776718e-06,
"loss": 0.0,
"step": 317
},
{
"epoch": 0.94,
"learning_rate": 1.5099135693322774e-06,
"loss": 0.0,
"step": 318
},
{
"epoch": 0.95,
"learning_rate": 1.3471728970068987e-06,
"loss": 0.0,
"step": 319
},
{
"epoch": 0.95,
"learning_rate": 1.1936502771783486e-06,
"loss": 0.0,
"step": 320
},
{
"epoch": 0.95,
"learning_rate": 1.0493600548948878e-06,
"loss": 0.0,
"step": 321
},
{
"epoch": 0.96,
"learning_rate": 9.143157125359514e-07,
"loss": 0.0,
"step": 322
},
{
"epoch": 0.96,
"learning_rate": 7.885298685522235e-07,
"loss": 0.0,
"step": 323
},
{
"epoch": 0.96,
"learning_rate": 6.720142762867032e-07,
"loss": 0.0,
"step": 324
},
{
"epoch": 0.96,
"learning_rate": 5.647798228764156e-07,
"loss": 0.0,
"step": 325
},
{
"epoch": 0.97,
"learning_rate": 4.668365282351372e-07,
"loss": 0.0,
"step": 326
},
{
"epoch": 0.97,
"learning_rate": 3.781935441171336e-07,
"loss": 0.0,
"step": 327
},
{
"epoch": 0.97,
"learning_rate": 2.988591532620322e-07,
"loss": 0.0,
"step": 328
},
{
"epoch": 0.98,
"learning_rate": 2.288407686208971e-07,
"loss": 0.0,
"step": 329
},
{
"epoch": 0.98,
"learning_rate": 1.68144932663572e-07,
"loss": 0.0,
"step": 330
},
{
"epoch": 0.98,
"learning_rate": 1.1677731676733584e-07,
"loss": 0.0,
"step": 331
},
{
"epoch": 0.99,
"learning_rate": 7.474272068698218e-08,
"loss": 0.0,
"step": 332
},
{
"epoch": 0.99,
"learning_rate": 4.2045072106333684e-08,
"loss": 0.0,
"step": 333
},
{
"epoch": 0.99,
"learning_rate": 1.8687426271246645e-08,
"loss": 0.0,
"step": 334
},
{
"epoch": 0.99,
"learning_rate": 4.6719657041283114e-09,
"loss": 0.0,
"step": 335
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 0.0,
"step": 336
},
{
"epoch": 1.0,
"eval_loss": 1.0666293746908195e-05,
"eval_runtime": 11898.68,
"eval_samples_per_second": 2.641,
"eval_steps_per_second": 0.33,
"step": 336
},
{
"epoch": 1.0,
"step": 336,
"total_flos": 653027262332928.0,
"train_loss": 0.033493353224400835,
"train_runtime": 25159.3445,
"train_samples_per_second": 0.535,
"train_steps_per_second": 0.013
}
],
"max_steps": 336,
"num_train_epochs": 1,
"total_flos": 653027262332928.0,
"trial_name": null,
"trial_params": null
}