QA_6_2048 / checkpoint-200 /trainer_state.json
CreatorPhan's picture
Upload folder using huggingface_hub (#2)
f44f5e1
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.5673758865248227,
"eval_steps": 500,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.00019981060606060605,
"loss": 2.9206,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 0.00019962121212121212,
"loss": 2.7609,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 0.0001994318181818182,
"loss": 2.6878,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 0.00019924242424242426,
"loss": 2.6697,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 0.0001990530303030303,
"loss": 2.5818,
"step": 5
},
{
"epoch": 0.02,
"learning_rate": 0.00019886363636363637,
"loss": 2.5396,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 0.00019867424242424244,
"loss": 2.5265,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 0.0001984848484848485,
"loss": 2.5475,
"step": 8
},
{
"epoch": 0.03,
"learning_rate": 0.00019829545454545455,
"loss": 2.4835,
"step": 9
},
{
"epoch": 0.03,
"learning_rate": 0.0001981060606060606,
"loss": 2.4559,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 0.0001979166666666667,
"loss": 2.4511,
"step": 11
},
{
"epoch": 0.03,
"learning_rate": 0.00019772727272727273,
"loss": 2.4592,
"step": 12
},
{
"epoch": 0.04,
"learning_rate": 0.0001975378787878788,
"loss": 2.4495,
"step": 13
},
{
"epoch": 0.04,
"learning_rate": 0.00019734848484848484,
"loss": 2.4714,
"step": 14
},
{
"epoch": 0.04,
"learning_rate": 0.00019715909090909094,
"loss": 2.4302,
"step": 15
},
{
"epoch": 0.05,
"learning_rate": 0.00019696969696969698,
"loss": 2.4097,
"step": 16
},
{
"epoch": 0.05,
"learning_rate": 0.00019678030303030305,
"loss": 2.4523,
"step": 17
},
{
"epoch": 0.05,
"learning_rate": 0.0001965909090909091,
"loss": 2.4325,
"step": 18
},
{
"epoch": 0.05,
"learning_rate": 0.00019640151515151516,
"loss": 2.4125,
"step": 19
},
{
"epoch": 0.06,
"learning_rate": 0.00019621212121212123,
"loss": 2.4329,
"step": 20
},
{
"epoch": 0.06,
"learning_rate": 0.00019602272727272727,
"loss": 2.3471,
"step": 21
},
{
"epoch": 0.06,
"learning_rate": 0.00019583333333333334,
"loss": 2.3012,
"step": 22
},
{
"epoch": 0.07,
"learning_rate": 0.0001956439393939394,
"loss": 2.3869,
"step": 23
},
{
"epoch": 0.07,
"learning_rate": 0.00019545454545454548,
"loss": 2.3822,
"step": 24
},
{
"epoch": 0.07,
"learning_rate": 0.00019526515151515152,
"loss": 2.3427,
"step": 25
},
{
"epoch": 0.07,
"learning_rate": 0.0001950757575757576,
"loss": 2.3659,
"step": 26
},
{
"epoch": 0.08,
"learning_rate": 0.00019488636363636366,
"loss": 2.3826,
"step": 27
},
{
"epoch": 0.08,
"learning_rate": 0.0001946969696969697,
"loss": 2.3532,
"step": 28
},
{
"epoch": 0.08,
"learning_rate": 0.00019450757575757577,
"loss": 2.3828,
"step": 29
},
{
"epoch": 0.09,
"learning_rate": 0.0001943181818181818,
"loss": 2.3133,
"step": 30
},
{
"epoch": 0.09,
"learning_rate": 0.0001941287878787879,
"loss": 2.3613,
"step": 31
},
{
"epoch": 0.09,
"learning_rate": 0.00019393939393939395,
"loss": 2.3867,
"step": 32
},
{
"epoch": 0.09,
"learning_rate": 0.00019375000000000002,
"loss": 2.2966,
"step": 33
},
{
"epoch": 0.1,
"learning_rate": 0.00019356060606060606,
"loss": 2.3436,
"step": 34
},
{
"epoch": 0.1,
"learning_rate": 0.00019337121212121213,
"loss": 2.3425,
"step": 35
},
{
"epoch": 0.1,
"learning_rate": 0.0001931818181818182,
"loss": 2.307,
"step": 36
},
{
"epoch": 0.1,
"learning_rate": 0.00019299242424242424,
"loss": 2.3521,
"step": 37
},
{
"epoch": 0.11,
"learning_rate": 0.0001928030303030303,
"loss": 2.3302,
"step": 38
},
{
"epoch": 0.11,
"learning_rate": 0.00019261363636363635,
"loss": 2.312,
"step": 39
},
{
"epoch": 0.11,
"learning_rate": 0.00019242424242424245,
"loss": 2.3655,
"step": 40
},
{
"epoch": 0.12,
"learning_rate": 0.0001922348484848485,
"loss": 2.344,
"step": 41
},
{
"epoch": 0.12,
"learning_rate": 0.00019204545454545456,
"loss": 2.3373,
"step": 42
},
{
"epoch": 0.12,
"learning_rate": 0.0001918560606060606,
"loss": 2.3331,
"step": 43
},
{
"epoch": 0.12,
"learning_rate": 0.00019166666666666667,
"loss": 2.3376,
"step": 44
},
{
"epoch": 0.13,
"learning_rate": 0.00019147727272727274,
"loss": 2.3369,
"step": 45
},
{
"epoch": 0.13,
"learning_rate": 0.00019128787878787878,
"loss": 2.3413,
"step": 46
},
{
"epoch": 0.13,
"learning_rate": 0.00019109848484848485,
"loss": 2.3212,
"step": 47
},
{
"epoch": 0.14,
"learning_rate": 0.00019090909090909092,
"loss": 2.307,
"step": 48
},
{
"epoch": 0.14,
"learning_rate": 0.000190719696969697,
"loss": 2.2929,
"step": 49
},
{
"epoch": 0.14,
"learning_rate": 0.00019053030303030303,
"loss": 2.2873,
"step": 50
},
{
"epoch": 0.14,
"learning_rate": 0.0001903409090909091,
"loss": 2.3098,
"step": 51
},
{
"epoch": 0.15,
"learning_rate": 0.00019015151515151517,
"loss": 2.3129,
"step": 52
},
{
"epoch": 0.15,
"learning_rate": 0.0001899621212121212,
"loss": 2.3038,
"step": 53
},
{
"epoch": 0.15,
"learning_rate": 0.00018977272727272728,
"loss": 2.286,
"step": 54
},
{
"epoch": 0.16,
"learning_rate": 0.00018958333333333332,
"loss": 2.3388,
"step": 55
},
{
"epoch": 0.16,
"learning_rate": 0.00018939393939393942,
"loss": 2.3193,
"step": 56
},
{
"epoch": 0.16,
"learning_rate": 0.00018920454545454546,
"loss": 2.3136,
"step": 57
},
{
"epoch": 0.16,
"learning_rate": 0.00018901515151515153,
"loss": 2.3141,
"step": 58
},
{
"epoch": 0.17,
"learning_rate": 0.00018882575757575757,
"loss": 2.3646,
"step": 59
},
{
"epoch": 0.17,
"learning_rate": 0.00018863636363636364,
"loss": 2.3318,
"step": 60
},
{
"epoch": 0.17,
"learning_rate": 0.0001884469696969697,
"loss": 2.2977,
"step": 61
},
{
"epoch": 0.18,
"learning_rate": 0.00018825757575757575,
"loss": 2.2764,
"step": 62
},
{
"epoch": 0.18,
"learning_rate": 0.00018806818181818182,
"loss": 2.3095,
"step": 63
},
{
"epoch": 0.18,
"learning_rate": 0.0001878787878787879,
"loss": 2.252,
"step": 64
},
{
"epoch": 0.18,
"learning_rate": 0.00018768939393939396,
"loss": 2.2786,
"step": 65
},
{
"epoch": 0.19,
"learning_rate": 0.0001875,
"loss": 2.2789,
"step": 66
},
{
"epoch": 0.19,
"learning_rate": 0.00018731060606060607,
"loss": 2.2841,
"step": 67
},
{
"epoch": 0.19,
"learning_rate": 0.00018712121212121212,
"loss": 2.3436,
"step": 68
},
{
"epoch": 0.2,
"learning_rate": 0.00018693181818181818,
"loss": 2.2956,
"step": 69
},
{
"epoch": 0.2,
"learning_rate": 0.00018674242424242425,
"loss": 2.2353,
"step": 70
},
{
"epoch": 0.2,
"learning_rate": 0.0001865530303030303,
"loss": 2.2772,
"step": 71
},
{
"epoch": 0.2,
"learning_rate": 0.00018636363636363636,
"loss": 2.2496,
"step": 72
},
{
"epoch": 0.21,
"learning_rate": 0.00018617424242424243,
"loss": 2.2477,
"step": 73
},
{
"epoch": 0.21,
"learning_rate": 0.0001859848484848485,
"loss": 2.2791,
"step": 74
},
{
"epoch": 0.21,
"learning_rate": 0.00018579545454545454,
"loss": 2.2799,
"step": 75
},
{
"epoch": 0.22,
"learning_rate": 0.00018560606060606061,
"loss": 2.3132,
"step": 76
},
{
"epoch": 0.22,
"learning_rate": 0.00018541666666666668,
"loss": 2.2542,
"step": 77
},
{
"epoch": 0.22,
"learning_rate": 0.00018522727272727273,
"loss": 2.2609,
"step": 78
},
{
"epoch": 0.22,
"learning_rate": 0.0001850378787878788,
"loss": 2.2819,
"step": 79
},
{
"epoch": 0.23,
"learning_rate": 0.00018484848484848484,
"loss": 2.2844,
"step": 80
},
{
"epoch": 0.23,
"learning_rate": 0.00018465909090909093,
"loss": 2.2542,
"step": 81
},
{
"epoch": 0.23,
"learning_rate": 0.00018446969696969697,
"loss": 2.2603,
"step": 82
},
{
"epoch": 0.24,
"learning_rate": 0.00018428030303030304,
"loss": 2.2832,
"step": 83
},
{
"epoch": 0.24,
"learning_rate": 0.00018409090909090909,
"loss": 2.2869,
"step": 84
},
{
"epoch": 0.24,
"learning_rate": 0.00018390151515151518,
"loss": 2.2646,
"step": 85
},
{
"epoch": 0.24,
"learning_rate": 0.00018371212121212122,
"loss": 2.2698,
"step": 86
},
{
"epoch": 0.25,
"learning_rate": 0.00018352272727272727,
"loss": 2.2757,
"step": 87
},
{
"epoch": 0.25,
"learning_rate": 0.00018333333333333334,
"loss": 2.2544,
"step": 88
},
{
"epoch": 0.25,
"learning_rate": 0.0001831439393939394,
"loss": 2.2678,
"step": 89
},
{
"epoch": 0.26,
"learning_rate": 0.00018295454545454547,
"loss": 2.2778,
"step": 90
},
{
"epoch": 0.26,
"learning_rate": 0.00018276515151515152,
"loss": 2.2027,
"step": 91
},
{
"epoch": 0.26,
"learning_rate": 0.00018257575757575758,
"loss": 2.2167,
"step": 92
},
{
"epoch": 0.26,
"learning_rate": 0.00018238636363636365,
"loss": 2.2602,
"step": 93
},
{
"epoch": 0.27,
"learning_rate": 0.00018219696969696972,
"loss": 2.2736,
"step": 94
},
{
"epoch": 0.27,
"learning_rate": 0.00018200757575757577,
"loss": 2.2443,
"step": 95
},
{
"epoch": 0.27,
"learning_rate": 0.00018181818181818183,
"loss": 2.2299,
"step": 96
},
{
"epoch": 0.28,
"learning_rate": 0.0001816287878787879,
"loss": 2.2644,
"step": 97
},
{
"epoch": 0.28,
"learning_rate": 0.00018143939393939395,
"loss": 2.259,
"step": 98
},
{
"epoch": 0.28,
"learning_rate": 0.00018125000000000001,
"loss": 2.2567,
"step": 99
},
{
"epoch": 0.28,
"learning_rate": 0.00018106060606060606,
"loss": 2.2599,
"step": 100
},
{
"epoch": 0.29,
"learning_rate": 0.00018087121212121213,
"loss": 2.2091,
"step": 101
},
{
"epoch": 0.29,
"learning_rate": 0.0001806818181818182,
"loss": 2.2312,
"step": 102
},
{
"epoch": 0.29,
"learning_rate": 0.00018049242424242426,
"loss": 2.1869,
"step": 103
},
{
"epoch": 0.3,
"learning_rate": 0.0001803030303030303,
"loss": 2.2023,
"step": 104
},
{
"epoch": 0.3,
"learning_rate": 0.00018011363636363638,
"loss": 2.2132,
"step": 105
},
{
"epoch": 0.3,
"learning_rate": 0.00017992424242424244,
"loss": 2.2612,
"step": 106
},
{
"epoch": 0.3,
"learning_rate": 0.0001797348484848485,
"loss": 2.2109,
"step": 107
},
{
"epoch": 0.31,
"learning_rate": 0.00017954545454545456,
"loss": 2.215,
"step": 108
},
{
"epoch": 0.31,
"learning_rate": 0.0001793560606060606,
"loss": 2.2114,
"step": 109
},
{
"epoch": 0.31,
"learning_rate": 0.0001791666666666667,
"loss": 2.2203,
"step": 110
},
{
"epoch": 0.31,
"learning_rate": 0.00017897727272727274,
"loss": 2.2594,
"step": 111
},
{
"epoch": 0.32,
"learning_rate": 0.0001787878787878788,
"loss": 2.2001,
"step": 112
},
{
"epoch": 0.32,
"learning_rate": 0.00017859848484848485,
"loss": 2.2046,
"step": 113
},
{
"epoch": 0.32,
"learning_rate": 0.00017840909090909092,
"loss": 2.1907,
"step": 114
},
{
"epoch": 0.33,
"learning_rate": 0.00017821969696969699,
"loss": 2.2539,
"step": 115
},
{
"epoch": 0.33,
"learning_rate": 0.00017803030303030303,
"loss": 2.2335,
"step": 116
},
{
"epoch": 0.33,
"learning_rate": 0.0001778409090909091,
"loss": 2.2171,
"step": 117
},
{
"epoch": 0.33,
"learning_rate": 0.00017765151515151517,
"loss": 2.2278,
"step": 118
},
{
"epoch": 0.34,
"learning_rate": 0.00017746212121212123,
"loss": 2.231,
"step": 119
},
{
"epoch": 0.34,
"learning_rate": 0.00017727272727272728,
"loss": 2.2141,
"step": 120
},
{
"epoch": 0.34,
"learning_rate": 0.00017708333333333335,
"loss": 2.2432,
"step": 121
},
{
"epoch": 0.35,
"learning_rate": 0.00017689393939393942,
"loss": 2.2266,
"step": 122
},
{
"epoch": 0.35,
"learning_rate": 0.00017670454545454546,
"loss": 2.1929,
"step": 123
},
{
"epoch": 0.35,
"learning_rate": 0.00017651515151515153,
"loss": 2.2077,
"step": 124
},
{
"epoch": 0.35,
"learning_rate": 0.00017632575757575757,
"loss": 2.2133,
"step": 125
},
{
"epoch": 0.36,
"learning_rate": 0.00017613636363636366,
"loss": 2.2251,
"step": 126
},
{
"epoch": 0.36,
"learning_rate": 0.0001759469696969697,
"loss": 2.2265,
"step": 127
},
{
"epoch": 0.36,
"learning_rate": 0.00017575757575757578,
"loss": 2.2186,
"step": 128
},
{
"epoch": 0.37,
"learning_rate": 0.00017556818181818182,
"loss": 2.1925,
"step": 129
},
{
"epoch": 0.37,
"learning_rate": 0.0001753787878787879,
"loss": 2.1956,
"step": 130
},
{
"epoch": 0.37,
"learning_rate": 0.00017518939393939396,
"loss": 2.2459,
"step": 131
},
{
"epoch": 0.37,
"learning_rate": 0.000175,
"loss": 2.22,
"step": 132
},
{
"epoch": 0.38,
"learning_rate": 0.00017481060606060607,
"loss": 2.2143,
"step": 133
},
{
"epoch": 0.38,
"learning_rate": 0.0001746212121212121,
"loss": 2.2359,
"step": 134
},
{
"epoch": 0.38,
"learning_rate": 0.0001744318181818182,
"loss": 2.2058,
"step": 135
},
{
"epoch": 0.39,
"learning_rate": 0.00017424242424242425,
"loss": 2.2307,
"step": 136
},
{
"epoch": 0.39,
"learning_rate": 0.00017405303030303032,
"loss": 2.2062,
"step": 137
},
{
"epoch": 0.39,
"learning_rate": 0.00017386363636363636,
"loss": 2.1796,
"step": 138
},
{
"epoch": 0.39,
"learning_rate": 0.00017367424242424243,
"loss": 2.2054,
"step": 139
},
{
"epoch": 0.4,
"learning_rate": 0.0001734848484848485,
"loss": 2.1651,
"step": 140
},
{
"epoch": 0.4,
"learning_rate": 0.00017329545454545454,
"loss": 2.2159,
"step": 141
},
{
"epoch": 0.4,
"learning_rate": 0.0001731060606060606,
"loss": 2.1988,
"step": 142
},
{
"epoch": 0.41,
"learning_rate": 0.00017291666666666668,
"loss": 2.1676,
"step": 143
},
{
"epoch": 0.41,
"learning_rate": 0.00017272727272727275,
"loss": 2.1725,
"step": 144
},
{
"epoch": 0.41,
"learning_rate": 0.0001725378787878788,
"loss": 2.2205,
"step": 145
},
{
"epoch": 0.41,
"learning_rate": 0.00017234848484848486,
"loss": 2.1486,
"step": 146
},
{
"epoch": 0.42,
"learning_rate": 0.00017215909090909093,
"loss": 2.147,
"step": 147
},
{
"epoch": 0.42,
"learning_rate": 0.00017196969696969697,
"loss": 2.1651,
"step": 148
},
{
"epoch": 0.42,
"learning_rate": 0.00017178030303030304,
"loss": 2.1983,
"step": 149
},
{
"epoch": 0.43,
"learning_rate": 0.00017159090909090908,
"loss": 2.1778,
"step": 150
},
{
"epoch": 0.43,
"learning_rate": 0.00017140151515151518,
"loss": 2.1631,
"step": 151
},
{
"epoch": 0.43,
"learning_rate": 0.00017121212121212122,
"loss": 2.1442,
"step": 152
},
{
"epoch": 0.43,
"learning_rate": 0.0001710227272727273,
"loss": 2.1397,
"step": 153
},
{
"epoch": 0.44,
"learning_rate": 0.00017083333333333333,
"loss": 2.1697,
"step": 154
},
{
"epoch": 0.44,
"learning_rate": 0.0001706439393939394,
"loss": 2.1451,
"step": 155
},
{
"epoch": 0.44,
"learning_rate": 0.00017045454545454547,
"loss": 2.1789,
"step": 156
},
{
"epoch": 0.45,
"learning_rate": 0.0001702651515151515,
"loss": 2.1037,
"step": 157
},
{
"epoch": 0.45,
"learning_rate": 0.00017007575757575758,
"loss": 2.1698,
"step": 158
},
{
"epoch": 0.45,
"learning_rate": 0.00016988636363636365,
"loss": 2.1538,
"step": 159
},
{
"epoch": 0.45,
"learning_rate": 0.00016969696969696972,
"loss": 2.2015,
"step": 160
},
{
"epoch": 0.46,
"learning_rate": 0.00016950757575757576,
"loss": 2.179,
"step": 161
},
{
"epoch": 0.46,
"learning_rate": 0.00016931818181818183,
"loss": 2.1766,
"step": 162
},
{
"epoch": 0.46,
"learning_rate": 0.0001691287878787879,
"loss": 2.1646,
"step": 163
},
{
"epoch": 0.47,
"learning_rate": 0.00016893939393939394,
"loss": 2.1694,
"step": 164
},
{
"epoch": 0.47,
"learning_rate": 0.00016875,
"loss": 2.1562,
"step": 165
},
{
"epoch": 0.47,
"learning_rate": 0.00016856060606060605,
"loss": 2.1551,
"step": 166
},
{
"epoch": 0.47,
"learning_rate": 0.00016837121212121212,
"loss": 2.1652,
"step": 167
},
{
"epoch": 0.48,
"learning_rate": 0.0001681818181818182,
"loss": 2.1594,
"step": 168
},
{
"epoch": 0.48,
"learning_rate": 0.00016799242424242426,
"loss": 2.1674,
"step": 169
},
{
"epoch": 0.48,
"learning_rate": 0.0001678030303030303,
"loss": 2.1378,
"step": 170
},
{
"epoch": 0.49,
"learning_rate": 0.00016761363636363637,
"loss": 2.1447,
"step": 171
},
{
"epoch": 0.49,
"learning_rate": 0.00016742424242424244,
"loss": 2.1451,
"step": 172
},
{
"epoch": 0.49,
"learning_rate": 0.00016723484848484848,
"loss": 2.1336,
"step": 173
},
{
"epoch": 0.49,
"learning_rate": 0.00016704545454545455,
"loss": 2.1231,
"step": 174
},
{
"epoch": 0.5,
"learning_rate": 0.0001668560606060606,
"loss": 2.1143,
"step": 175
},
{
"epoch": 0.5,
"learning_rate": 0.0001666666666666667,
"loss": 2.1316,
"step": 176
},
{
"epoch": 0.5,
"learning_rate": 0.00016647727272727273,
"loss": 2.1281,
"step": 177
},
{
"epoch": 0.5,
"learning_rate": 0.0001662878787878788,
"loss": 2.136,
"step": 178
},
{
"epoch": 0.51,
"learning_rate": 0.00016609848484848484,
"loss": 2.1279,
"step": 179
},
{
"epoch": 0.51,
"learning_rate": 0.00016590909090909094,
"loss": 2.1421,
"step": 180
},
{
"epoch": 0.51,
"learning_rate": 0.00016571969696969698,
"loss": 2.1541,
"step": 181
},
{
"epoch": 0.52,
"learning_rate": 0.00016553030303030305,
"loss": 2.1293,
"step": 182
},
{
"epoch": 0.52,
"learning_rate": 0.0001653409090909091,
"loss": 2.1294,
"step": 183
},
{
"epoch": 0.52,
"learning_rate": 0.00016515151515151516,
"loss": 2.1459,
"step": 184
},
{
"epoch": 0.52,
"learning_rate": 0.00016496212121212123,
"loss": 2.1113,
"step": 185
},
{
"epoch": 0.53,
"learning_rate": 0.00016477272727272727,
"loss": 2.1394,
"step": 186
},
{
"epoch": 0.53,
"learning_rate": 0.00016458333333333334,
"loss": 2.1321,
"step": 187
},
{
"epoch": 0.53,
"learning_rate": 0.0001643939393939394,
"loss": 2.148,
"step": 188
},
{
"epoch": 0.54,
"learning_rate": 0.00016420454545454548,
"loss": 2.1631,
"step": 189
},
{
"epoch": 0.54,
"learning_rate": 0.00016401515151515152,
"loss": 2.1276,
"step": 190
},
{
"epoch": 0.54,
"learning_rate": 0.0001638257575757576,
"loss": 2.0706,
"step": 191
},
{
"epoch": 0.54,
"learning_rate": 0.00016363636363636366,
"loss": 2.127,
"step": 192
},
{
"epoch": 0.55,
"learning_rate": 0.0001634469696969697,
"loss": 2.1449,
"step": 193
},
{
"epoch": 0.55,
"learning_rate": 0.00016325757575757577,
"loss": 2.1204,
"step": 194
},
{
"epoch": 0.55,
"learning_rate": 0.0001630681818181818,
"loss": 2.0904,
"step": 195
},
{
"epoch": 0.56,
"learning_rate": 0.0001628787878787879,
"loss": 2.1129,
"step": 196
},
{
"epoch": 0.56,
"learning_rate": 0.00016268939393939395,
"loss": 2.1036,
"step": 197
},
{
"epoch": 0.56,
"learning_rate": 0.00016250000000000002,
"loss": 2.1509,
"step": 198
},
{
"epoch": 0.56,
"learning_rate": 0.00016231060606060606,
"loss": 2.1239,
"step": 199
},
{
"epoch": 0.57,
"learning_rate": 0.00016212121212121213,
"loss": 2.145,
"step": 200
}
],
"logging_steps": 1,
"max_steps": 1056,
"num_train_epochs": 3,
"save_steps": 100,
"total_flos": 5.0683926177970176e+17,
"trial_name": null,
"trial_params": null
}