Bloomz_Lora / checkpoint-200 /trainer_state.json
CreatorPhan's picture
Upload folder using huggingface_hub (#1)
fc5ff04
raw
history blame
24.3 kB
{
"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": 0.0001994318181818182,
"loss": 2.7526,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 0.00019886363636363637,
"loss": 2.6231,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 0.00019829545454545455,
"loss": 2.5691,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 0.00019772727272727273,
"loss": 2.5755,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 0.00019715909090909094,
"loss": 2.5077,
"step": 5
},
{
"epoch": 0.02,
"learning_rate": 0.0001965909090909091,
"loss": 2.4698,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 0.00019602272727272727,
"loss": 2.4541,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 0.00019545454545454548,
"loss": 2.4764,
"step": 8
},
{
"epoch": 0.03,
"learning_rate": 0.00019488636363636366,
"loss": 2.4176,
"step": 9
},
{
"epoch": 0.03,
"learning_rate": 0.0001943181818181818,
"loss": 2.396,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 0.00019375000000000002,
"loss": 2.3929,
"step": 11
},
{
"epoch": 0.03,
"learning_rate": 0.0001931818181818182,
"loss": 2.405,
"step": 12
},
{
"epoch": 0.04,
"learning_rate": 0.00019261363636363635,
"loss": 2.3947,
"step": 13
},
{
"epoch": 0.04,
"learning_rate": 0.00019204545454545456,
"loss": 2.4164,
"step": 14
},
{
"epoch": 0.04,
"learning_rate": 0.00019147727272727274,
"loss": 2.373,
"step": 15
},
{
"epoch": 0.05,
"learning_rate": 0.00019090909090909092,
"loss": 2.3552,
"step": 16
},
{
"epoch": 0.05,
"learning_rate": 0.0001903409090909091,
"loss": 2.3988,
"step": 17
},
{
"epoch": 0.05,
"learning_rate": 0.00018977272727272728,
"loss": 2.3826,
"step": 18
},
{
"epoch": 0.05,
"learning_rate": 0.00018920454545454546,
"loss": 2.3672,
"step": 19
},
{
"epoch": 0.06,
"learning_rate": 0.00018863636363636364,
"loss": 2.3885,
"step": 20
},
{
"epoch": 0.06,
"learning_rate": 0.00018806818181818182,
"loss": 2.3043,
"step": 21
},
{
"epoch": 0.06,
"learning_rate": 0.0001875,
"loss": 2.2597,
"step": 22
},
{
"epoch": 0.07,
"learning_rate": 0.00018693181818181818,
"loss": 2.3457,
"step": 23
},
{
"epoch": 0.07,
"learning_rate": 0.00018636363636363636,
"loss": 2.3409,
"step": 24
},
{
"epoch": 0.07,
"learning_rate": 0.00018579545454545454,
"loss": 2.303,
"step": 25
},
{
"epoch": 0.07,
"learning_rate": 0.00018522727272727273,
"loss": 2.3253,
"step": 26
},
{
"epoch": 0.08,
"learning_rate": 0.00018465909090909093,
"loss": 2.3453,
"step": 27
},
{
"epoch": 0.08,
"learning_rate": 0.00018409090909090909,
"loss": 2.3151,
"step": 28
},
{
"epoch": 0.08,
"learning_rate": 0.00018352272727272727,
"loss": 2.3457,
"step": 29
},
{
"epoch": 0.09,
"learning_rate": 0.00018295454545454547,
"loss": 2.2792,
"step": 30
},
{
"epoch": 0.09,
"learning_rate": 0.00018238636363636365,
"loss": 2.3257,
"step": 31
},
{
"epoch": 0.09,
"learning_rate": 0.00018181818181818183,
"loss": 2.353,
"step": 32
},
{
"epoch": 0.09,
"learning_rate": 0.00018125000000000001,
"loss": 2.2633,
"step": 33
},
{
"epoch": 0.1,
"learning_rate": 0.0001806818181818182,
"loss": 2.3089,
"step": 34
},
{
"epoch": 0.1,
"learning_rate": 0.00018011363636363638,
"loss": 2.3085,
"step": 35
},
{
"epoch": 0.1,
"learning_rate": 0.00017954545454545456,
"loss": 2.2746,
"step": 36
},
{
"epoch": 0.1,
"learning_rate": 0.00017897727272727274,
"loss": 2.3212,
"step": 37
},
{
"epoch": 0.11,
"learning_rate": 0.00017840909090909092,
"loss": 2.2991,
"step": 38
},
{
"epoch": 0.11,
"learning_rate": 0.0001778409090909091,
"loss": 2.2807,
"step": 39
},
{
"epoch": 0.11,
"learning_rate": 0.00017727272727272728,
"loss": 2.3342,
"step": 40
},
{
"epoch": 0.12,
"learning_rate": 0.00017670454545454546,
"loss": 2.3144,
"step": 41
},
{
"epoch": 0.12,
"learning_rate": 0.00017613636363636366,
"loss": 2.3084,
"step": 42
},
{
"epoch": 0.12,
"learning_rate": 0.00017556818181818182,
"loss": 2.3032,
"step": 43
},
{
"epoch": 0.12,
"learning_rate": 0.000175,
"loss": 2.3105,
"step": 44
},
{
"epoch": 0.13,
"learning_rate": 0.0001744318181818182,
"loss": 2.3101,
"step": 45
},
{
"epoch": 0.13,
"learning_rate": 0.00017386363636363636,
"loss": 2.313,
"step": 46
},
{
"epoch": 0.13,
"learning_rate": 0.00017329545454545454,
"loss": 2.293,
"step": 47
},
{
"epoch": 0.14,
"learning_rate": 0.00017272727272727275,
"loss": 2.2807,
"step": 48
},
{
"epoch": 0.14,
"learning_rate": 0.00017215909090909093,
"loss": 2.2665,
"step": 49
},
{
"epoch": 0.14,
"learning_rate": 0.00017159090909090908,
"loss": 2.2626,
"step": 50
},
{
"epoch": 0.14,
"learning_rate": 0.0001710227272727273,
"loss": 2.2839,
"step": 51
},
{
"epoch": 0.15,
"learning_rate": 0.00017045454545454547,
"loss": 2.2865,
"step": 52
},
{
"epoch": 0.15,
"learning_rate": 0.00016988636363636365,
"loss": 2.2788,
"step": 53
},
{
"epoch": 0.15,
"learning_rate": 0.00016931818181818183,
"loss": 2.2622,
"step": 54
},
{
"epoch": 0.16,
"learning_rate": 0.00016875,
"loss": 2.3121,
"step": 55
},
{
"epoch": 0.16,
"learning_rate": 0.0001681818181818182,
"loss": 2.2958,
"step": 56
},
{
"epoch": 0.16,
"learning_rate": 0.00016761363636363637,
"loss": 2.2898,
"step": 57
},
{
"epoch": 0.16,
"learning_rate": 0.00016704545454545455,
"loss": 2.2903,
"step": 58
},
{
"epoch": 0.17,
"learning_rate": 0.00016647727272727273,
"loss": 2.3393,
"step": 59
},
{
"epoch": 0.17,
"learning_rate": 0.00016590909090909094,
"loss": 2.3086,
"step": 60
},
{
"epoch": 0.17,
"learning_rate": 0.0001653409090909091,
"loss": 2.2739,
"step": 61
},
{
"epoch": 0.18,
"learning_rate": 0.00016477272727272727,
"loss": 2.252,
"step": 62
},
{
"epoch": 0.18,
"learning_rate": 0.00016420454545454548,
"loss": 2.2868,
"step": 63
},
{
"epoch": 0.18,
"learning_rate": 0.00016363636363636366,
"loss": 2.2301,
"step": 64
},
{
"epoch": 0.18,
"learning_rate": 0.0001630681818181818,
"loss": 2.2563,
"step": 65
},
{
"epoch": 0.19,
"learning_rate": 0.00016250000000000002,
"loss": 2.2552,
"step": 66
},
{
"epoch": 0.19,
"learning_rate": 0.0001619318181818182,
"loss": 2.2615,
"step": 67
},
{
"epoch": 0.19,
"learning_rate": 0.00016136363636363635,
"loss": 2.3237,
"step": 68
},
{
"epoch": 0.2,
"learning_rate": 0.00016079545454545456,
"loss": 2.2741,
"step": 69
},
{
"epoch": 0.2,
"learning_rate": 0.00016022727272727274,
"loss": 2.2152,
"step": 70
},
{
"epoch": 0.2,
"learning_rate": 0.00015965909090909092,
"loss": 2.2558,
"step": 71
},
{
"epoch": 0.2,
"learning_rate": 0.0001590909090909091,
"loss": 2.2293,
"step": 72
},
{
"epoch": 0.21,
"learning_rate": 0.00015852272727272728,
"loss": 2.2278,
"step": 73
},
{
"epoch": 0.21,
"learning_rate": 0.00015795454545454546,
"loss": 2.2583,
"step": 74
},
{
"epoch": 0.21,
"learning_rate": 0.00015738636363636364,
"loss": 2.2609,
"step": 75
},
{
"epoch": 0.22,
"learning_rate": 0.00015681818181818182,
"loss": 2.2955,
"step": 76
},
{
"epoch": 0.22,
"learning_rate": 0.00015625,
"loss": 2.2359,
"step": 77
},
{
"epoch": 0.22,
"learning_rate": 0.00015568181818181818,
"loss": 2.2427,
"step": 78
},
{
"epoch": 0.22,
"learning_rate": 0.00015511363636363636,
"loss": 2.2632,
"step": 79
},
{
"epoch": 0.23,
"learning_rate": 0.00015454545454545454,
"loss": 2.2649,
"step": 80
},
{
"epoch": 0.23,
"learning_rate": 0.00015397727272727272,
"loss": 2.2347,
"step": 81
},
{
"epoch": 0.23,
"learning_rate": 0.00015340909090909093,
"loss": 2.2439,
"step": 82
},
{
"epoch": 0.24,
"learning_rate": 0.00015284090909090909,
"loss": 2.267,
"step": 83
},
{
"epoch": 0.24,
"learning_rate": 0.00015227272727272727,
"loss": 2.2682,
"step": 84
},
{
"epoch": 0.24,
"learning_rate": 0.00015170454545454547,
"loss": 2.2477,
"step": 85
},
{
"epoch": 0.24,
"learning_rate": 0.00015113636363636365,
"loss": 2.2534,
"step": 86
},
{
"epoch": 0.25,
"learning_rate": 0.0001505681818181818,
"loss": 2.2609,
"step": 87
},
{
"epoch": 0.25,
"learning_rate": 0.00015000000000000001,
"loss": 2.2381,
"step": 88
},
{
"epoch": 0.25,
"learning_rate": 0.0001494318181818182,
"loss": 2.2505,
"step": 89
},
{
"epoch": 0.26,
"learning_rate": 0.00014886363636363635,
"loss": 2.2628,
"step": 90
},
{
"epoch": 0.26,
"learning_rate": 0.00014829545454545455,
"loss": 2.1874,
"step": 91
},
{
"epoch": 0.26,
"learning_rate": 0.00014772727272727274,
"loss": 2.2024,
"step": 92
},
{
"epoch": 0.26,
"learning_rate": 0.00014715909090909092,
"loss": 2.2453,
"step": 93
},
{
"epoch": 0.27,
"learning_rate": 0.0001465909090909091,
"loss": 2.259,
"step": 94
},
{
"epoch": 0.27,
"learning_rate": 0.00014602272727272728,
"loss": 2.2304,
"step": 95
},
{
"epoch": 0.27,
"learning_rate": 0.00014545454545454546,
"loss": 2.2179,
"step": 96
},
{
"epoch": 0.28,
"learning_rate": 0.00014488636363636366,
"loss": 2.2497,
"step": 97
},
{
"epoch": 0.28,
"learning_rate": 0.00014431818181818182,
"loss": 2.2458,
"step": 98
},
{
"epoch": 0.28,
"learning_rate": 0.00014375,
"loss": 2.2438,
"step": 99
},
{
"epoch": 0.28,
"learning_rate": 0.0001431818181818182,
"loss": 2.2461,
"step": 100
},
{
"epoch": 0.29,
"learning_rate": 0.00014261363636363636,
"loss": 2.1966,
"step": 101
},
{
"epoch": 0.29,
"learning_rate": 0.00014204545454545454,
"loss": 2.2191,
"step": 102
},
{
"epoch": 0.29,
"learning_rate": 0.00014147727272727275,
"loss": 2.1765,
"step": 103
},
{
"epoch": 0.3,
"learning_rate": 0.00014090909090909093,
"loss": 2.1917,
"step": 104
},
{
"epoch": 0.3,
"learning_rate": 0.00014034090909090908,
"loss": 2.2025,
"step": 105
},
{
"epoch": 0.3,
"learning_rate": 0.0001397727272727273,
"loss": 2.2496,
"step": 106
},
{
"epoch": 0.3,
"learning_rate": 0.00013920454545454547,
"loss": 2.2012,
"step": 107
},
{
"epoch": 0.31,
"learning_rate": 0.00013863636363636365,
"loss": 2.2051,
"step": 108
},
{
"epoch": 0.31,
"learning_rate": 0.00013806818181818183,
"loss": 2.2027,
"step": 109
},
{
"epoch": 0.31,
"learning_rate": 0.0001375,
"loss": 2.21,
"step": 110
},
{
"epoch": 0.31,
"learning_rate": 0.0001369318181818182,
"loss": 2.2501,
"step": 111
},
{
"epoch": 0.32,
"learning_rate": 0.00013636363636363637,
"loss": 2.1916,
"step": 112
},
{
"epoch": 0.32,
"learning_rate": 0.00013579545454545455,
"loss": 2.1972,
"step": 113
},
{
"epoch": 0.32,
"learning_rate": 0.00013522727272727273,
"loss": 2.1821,
"step": 114
},
{
"epoch": 0.33,
"learning_rate": 0.00013465909090909094,
"loss": 2.2448,
"step": 115
},
{
"epoch": 0.33,
"learning_rate": 0.0001340909090909091,
"loss": 2.2253,
"step": 116
},
{
"epoch": 0.33,
"learning_rate": 0.00013352272727272727,
"loss": 2.2088,
"step": 117
},
{
"epoch": 0.33,
"learning_rate": 0.00013295454545454548,
"loss": 2.2203,
"step": 118
},
{
"epoch": 0.34,
"learning_rate": 0.00013238636363636366,
"loss": 2.2236,
"step": 119
},
{
"epoch": 0.34,
"learning_rate": 0.0001318181818181818,
"loss": 2.2074,
"step": 120
},
{
"epoch": 0.34,
"learning_rate": 0.00013125000000000002,
"loss": 2.2355,
"step": 121
},
{
"epoch": 0.35,
"learning_rate": 0.0001306818181818182,
"loss": 2.2215,
"step": 122
},
{
"epoch": 0.35,
"learning_rate": 0.00013011363636363635,
"loss": 2.1854,
"step": 123
},
{
"epoch": 0.35,
"learning_rate": 0.00012954545454545456,
"loss": 2.2046,
"step": 124
},
{
"epoch": 0.35,
"learning_rate": 0.00012897727272727274,
"loss": 2.2079,
"step": 125
},
{
"epoch": 0.36,
"learning_rate": 0.00012840909090909092,
"loss": 2.2204,
"step": 126
},
{
"epoch": 0.36,
"learning_rate": 0.0001278409090909091,
"loss": 2.2223,
"step": 127
},
{
"epoch": 0.36,
"learning_rate": 0.00012727272727272728,
"loss": 2.2149,
"step": 128
},
{
"epoch": 0.37,
"learning_rate": 0.00012670454545454546,
"loss": 2.1887,
"step": 129
},
{
"epoch": 0.37,
"learning_rate": 0.00012613636363636364,
"loss": 2.1908,
"step": 130
},
{
"epoch": 0.37,
"learning_rate": 0.00012556818181818182,
"loss": 2.2434,
"step": 131
},
{
"epoch": 0.37,
"learning_rate": 0.000125,
"loss": 2.2169,
"step": 132
},
{
"epoch": 0.38,
"learning_rate": 0.00012443181818181818,
"loss": 2.2113,
"step": 133
},
{
"epoch": 0.38,
"learning_rate": 0.00012386363636363636,
"loss": 2.2334,
"step": 134
},
{
"epoch": 0.38,
"learning_rate": 0.00012329545454545454,
"loss": 2.2034,
"step": 135
},
{
"epoch": 0.39,
"learning_rate": 0.00012272727272727272,
"loss": 2.2297,
"step": 136
},
{
"epoch": 0.39,
"learning_rate": 0.00012215909090909093,
"loss": 2.2049,
"step": 137
},
{
"epoch": 0.39,
"learning_rate": 0.00012159090909090908,
"loss": 2.1773,
"step": 138
},
{
"epoch": 0.39,
"learning_rate": 0.00012102272727272728,
"loss": 2.2057,
"step": 139
},
{
"epoch": 0.4,
"learning_rate": 0.00012045454545454546,
"loss": 2.1652,
"step": 140
},
{
"epoch": 0.4,
"learning_rate": 0.00011988636363636365,
"loss": 2.2157,
"step": 141
},
{
"epoch": 0.4,
"learning_rate": 0.00011931818181818182,
"loss": 2.1987,
"step": 142
},
{
"epoch": 0.41,
"learning_rate": 0.00011875,
"loss": 2.1666,
"step": 143
},
{
"epoch": 0.41,
"learning_rate": 0.0001181818181818182,
"loss": 2.1734,
"step": 144
},
{
"epoch": 0.41,
"learning_rate": 0.00011761363636363636,
"loss": 2.2221,
"step": 145
},
{
"epoch": 0.41,
"learning_rate": 0.00011704545454545454,
"loss": 2.1488,
"step": 146
},
{
"epoch": 0.42,
"learning_rate": 0.00011647727272727273,
"loss": 2.1487,
"step": 147
},
{
"epoch": 0.42,
"learning_rate": 0.00011590909090909093,
"loss": 2.1678,
"step": 148
},
{
"epoch": 0.42,
"learning_rate": 0.00011534090909090908,
"loss": 2.1988,
"step": 149
},
{
"epoch": 0.43,
"learning_rate": 0.00011477272727272728,
"loss": 2.1803,
"step": 150
},
{
"epoch": 0.43,
"learning_rate": 0.00011420454545454547,
"loss": 2.1671,
"step": 151
},
{
"epoch": 0.43,
"learning_rate": 0.00011363636363636365,
"loss": 2.1472,
"step": 152
},
{
"epoch": 0.43,
"learning_rate": 0.00011306818181818182,
"loss": 2.1456,
"step": 153
},
{
"epoch": 0.44,
"learning_rate": 0.00011250000000000001,
"loss": 2.1769,
"step": 154
},
{
"epoch": 0.44,
"learning_rate": 0.00011193181818181819,
"loss": 2.1484,
"step": 155
},
{
"epoch": 0.44,
"learning_rate": 0.00011136363636363636,
"loss": 2.1862,
"step": 156
},
{
"epoch": 0.45,
"learning_rate": 0.00011079545454545455,
"loss": 2.1088,
"step": 157
},
{
"epoch": 0.45,
"learning_rate": 0.00011022727272727273,
"loss": 2.1746,
"step": 158
},
{
"epoch": 0.45,
"learning_rate": 0.00010965909090909093,
"loss": 2.1609,
"step": 159
},
{
"epoch": 0.45,
"learning_rate": 0.00010909090909090909,
"loss": 2.2089,
"step": 160
},
{
"epoch": 0.46,
"learning_rate": 0.00010852272727272727,
"loss": 2.1862,
"step": 161
},
{
"epoch": 0.46,
"learning_rate": 0.00010795454545454547,
"loss": 2.1844,
"step": 162
},
{
"epoch": 0.46,
"learning_rate": 0.00010738636363636365,
"loss": 2.1717,
"step": 163
},
{
"epoch": 0.47,
"learning_rate": 0.00010681818181818181,
"loss": 2.1764,
"step": 164
},
{
"epoch": 0.47,
"learning_rate": 0.00010625000000000001,
"loss": 2.1642,
"step": 165
},
{
"epoch": 0.47,
"learning_rate": 0.00010568181818181819,
"loss": 2.164,
"step": 166
},
{
"epoch": 0.47,
"learning_rate": 0.00010511363636363635,
"loss": 2.1743,
"step": 167
},
{
"epoch": 0.48,
"learning_rate": 0.00010454545454545455,
"loss": 2.1688,
"step": 168
},
{
"epoch": 0.48,
"learning_rate": 0.00010397727272727273,
"loss": 2.1756,
"step": 169
},
{
"epoch": 0.48,
"learning_rate": 0.00010340909090909092,
"loss": 2.1488,
"step": 170
},
{
"epoch": 0.49,
"learning_rate": 0.00010284090909090909,
"loss": 2.1558,
"step": 171
},
{
"epoch": 0.49,
"learning_rate": 0.00010227272727272727,
"loss": 2.1551,
"step": 172
},
{
"epoch": 0.49,
"learning_rate": 0.00010170454545454546,
"loss": 2.1462,
"step": 173
},
{
"epoch": 0.49,
"learning_rate": 0.00010113636363636366,
"loss": 2.134,
"step": 174
},
{
"epoch": 0.5,
"learning_rate": 0.00010056818181818181,
"loss": 2.1278,
"step": 175
},
{
"epoch": 0.5,
"learning_rate": 0.0001,
"loss": 2.1436,
"step": 176
},
{
"epoch": 0.5,
"learning_rate": 9.943181818181819e-05,
"loss": 2.142,
"step": 177
},
{
"epoch": 0.5,
"learning_rate": 9.886363636363637e-05,
"loss": 2.1481,
"step": 178
},
{
"epoch": 0.51,
"learning_rate": 9.829545454545455e-05,
"loss": 2.1406,
"step": 179
},
{
"epoch": 0.51,
"learning_rate": 9.772727272727274e-05,
"loss": 2.1555,
"step": 180
},
{
"epoch": 0.51,
"learning_rate": 9.71590909090909e-05,
"loss": 2.1667,
"step": 181
},
{
"epoch": 0.52,
"learning_rate": 9.65909090909091e-05,
"loss": 2.1455,
"step": 182
},
{
"epoch": 0.52,
"learning_rate": 9.602272727272728e-05,
"loss": 2.1447,
"step": 183
},
{
"epoch": 0.52,
"learning_rate": 9.545454545454546e-05,
"loss": 2.1642,
"step": 184
},
{
"epoch": 0.52,
"learning_rate": 9.488636363636364e-05,
"loss": 2.1278,
"step": 185
},
{
"epoch": 0.53,
"learning_rate": 9.431818181818182e-05,
"loss": 2.1548,
"step": 186
},
{
"epoch": 0.53,
"learning_rate": 9.375e-05,
"loss": 2.1506,
"step": 187
},
{
"epoch": 0.53,
"learning_rate": 9.318181818181818e-05,
"loss": 2.1649,
"step": 188
},
{
"epoch": 0.54,
"learning_rate": 9.261363636363636e-05,
"loss": 2.1824,
"step": 189
},
{
"epoch": 0.54,
"learning_rate": 9.204545454545454e-05,
"loss": 2.1451,
"step": 190
},
{
"epoch": 0.54,
"learning_rate": 9.147727272727274e-05,
"loss": 2.089,
"step": 191
},
{
"epoch": 0.54,
"learning_rate": 9.090909090909092e-05,
"loss": 2.1457,
"step": 192
},
{
"epoch": 0.55,
"learning_rate": 9.03409090909091e-05,
"loss": 2.1647,
"step": 193
},
{
"epoch": 0.55,
"learning_rate": 8.977272727272728e-05,
"loss": 2.1464,
"step": 194
},
{
"epoch": 0.55,
"learning_rate": 8.920454545454546e-05,
"loss": 2.116,
"step": 195
},
{
"epoch": 0.56,
"learning_rate": 8.863636363636364e-05,
"loss": 2.1326,
"step": 196
},
{
"epoch": 0.56,
"learning_rate": 8.806818181818183e-05,
"loss": 2.1248,
"step": 197
},
{
"epoch": 0.56,
"learning_rate": 8.75e-05,
"loss": 2.172,
"step": 198
},
{
"epoch": 0.56,
"learning_rate": 8.693181818181818e-05,
"loss": 2.1478,
"step": 199
},
{
"epoch": 0.57,
"learning_rate": 8.636363636363637e-05,
"loss": 2.1691,
"step": 200
}
],
"logging_steps": 1,
"max_steps": 352,
"num_train_epochs": 1,
"save_steps": 100,
"total_flos": 5.0683926177970176e+17,
"trial_name": null,
"trial_params": null
}