pythia-exp / trainer_state.json
TinyPixel's picture
Upload folder using huggingface_hub
8acd751
raw
history blame
8.98 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.953846153846154,
"eval_steps": 500,
"global_step": 144,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04,
"learning_rate": 8e-05,
"loss": 2.2151,
"step": 2
},
{
"epoch": 0.08,
"learning_rate": 0.00016,
"loss": 2.3087,
"step": 4
},
{
"epoch": 0.12,
"learning_rate": 0.0001999744599547812,
"loss": 2.3667,
"step": 6
},
{
"epoch": 0.16,
"learning_rate": 0.00019977021786163598,
"loss": 2.5011,
"step": 8
},
{
"epoch": 0.21,
"learning_rate": 0.00019936215093023884,
"loss": 2.4286,
"step": 10
},
{
"epoch": 0.25,
"learning_rate": 0.00019875109281794825,
"loss": 2.4203,
"step": 12
},
{
"epoch": 0.29,
"learning_rate": 0.00019793829188147406,
"loss": 2.2626,
"step": 14
},
{
"epoch": 0.33,
"learning_rate": 0.00019692540862655585,
"loss": 2.2,
"step": 16
},
{
"epoch": 0.37,
"learning_rate": 0.00019571451231564525,
"loss": 2.5432,
"step": 18
},
{
"epoch": 0.41,
"learning_rate": 0.00019430807674052092,
"loss": 2.399,
"step": 20
},
{
"epoch": 0.45,
"learning_rate": 0.00019270897516847403,
"loss": 2.4603,
"step": 22
},
{
"epoch": 0.49,
"learning_rate": 0.00019092047447238773,
"loss": 2.2575,
"step": 24
},
{
"epoch": 0.53,
"learning_rate": 0.00018894622845670283,
"loss": 2.2481,
"step": 26
},
{
"epoch": 0.57,
"learning_rate": 0.00018679027039290497,
"loss": 2.2629,
"step": 28
},
{
"epoch": 0.62,
"learning_rate": 0.00018445700477978205,
"loss": 2.5683,
"step": 30
},
{
"epoch": 0.66,
"learning_rate": 0.00018195119834528534,
"loss": 2.3422,
"step": 32
},
{
"epoch": 0.7,
"learning_rate": 0.00017927797030837768,
"loss": 2.3204,
"step": 34
},
{
"epoch": 0.74,
"learning_rate": 0.0001764427819207624,
"loss": 2.318,
"step": 36
},
{
"epoch": 0.78,
"learning_rate": 0.00017345142530985887,
"loss": 2.2508,
"step": 38
},
{
"epoch": 0.82,
"learning_rate": 0.00017031001164581828,
"loss": 2.2968,
"step": 40
},
{
"epoch": 0.86,
"learning_rate": 0.0001670249586567531,
"loss": 2.2603,
"step": 42
},
{
"epoch": 0.9,
"learning_rate": 0.0001636029775176862,
"loss": 2.4402,
"step": 44
},
{
"epoch": 0.94,
"learning_rate": 0.00016005105914000507,
"loss": 2.3397,
"step": 46
},
{
"epoch": 0.98,
"learning_rate": 0.0001563764598894301,
"loss": 2.2608,
"step": 48
},
{
"epoch": 1.03,
"learning_rate": 0.00015258668676167546,
"loss": 2.0417,
"step": 50
},
{
"epoch": 1.07,
"learning_rate": 0.000148689482046087,
"loss": 2.297,
"step": 52
},
{
"epoch": 1.11,
"learning_rate": 0.00014469280750858854,
"loss": 2.1616,
"step": 54
},
{
"epoch": 1.15,
"learning_rate": 0.00014060482812625055,
"loss": 2.2691,
"step": 56
},
{
"epoch": 1.19,
"learning_rate": 0.00013643389540670962,
"loss": 2.2967,
"step": 58
},
{
"epoch": 1.23,
"learning_rate": 0.0001321885303265172,
"loss": 2.1486,
"step": 60
},
{
"epoch": 1.27,
"learning_rate": 0.0001278774059232723,
"loss": 2.0864,
"step": 62
},
{
"epoch": 1.31,
"learning_rate": 0.0001235093295771032,
"loss": 2.044,
"step": 64
},
{
"epoch": 1.35,
"learning_rate": 0.00011909322501769406,
"loss": 2.3136,
"step": 66
},
{
"epoch": 1.39,
"learning_rate": 0.00011463811409361667,
"loss": 2.3556,
"step": 68
},
{
"epoch": 1.44,
"learning_rate": 0.00011015309834121081,
"loss": 2.4312,
"step": 70
},
{
"epoch": 1.48,
"learning_rate": 0.00010564734039066699,
"loss": 2.1922,
"step": 72
},
{
"epoch": 1.52,
"learning_rate": 0.00010113004524729799,
"loss": 2.0871,
"step": 74
},
{
"epoch": 1.56,
"learning_rate": 9.661044148624037e-05,
"loss": 2.1988,
"step": 76
},
{
"epoch": 1.6,
"learning_rate": 9.209776239900453e-05,
"loss": 2.255,
"step": 78
},
{
"epoch": 1.64,
"learning_rate": 8.760122713038881e-05,
"loss": 2.3782,
"step": 80
},
{
"epoch": 1.68,
"learning_rate": 8.313002184429529e-05,
"loss": 2.196,
"step": 82
},
{
"epoch": 1.72,
"learning_rate": 7.869328095692312e-05,
"loss": 2.3759,
"step": 84
},
{
"epoch": 1.76,
"learning_rate": 7.430006847567972e-05,
"loss": 2.1787,
"step": 86
},
{
"epoch": 1.81,
"learning_rate": 6.995935948193294e-05,
"loss": 2.2547,
"step": 88
},
{
"epoch": 1.85,
"learning_rate": 6.568002179543409e-05,
"loss": 2.4197,
"step": 90
},
{
"epoch": 1.89,
"learning_rate": 6.147079785787038e-05,
"loss": 2.3039,
"step": 92
},
{
"epoch": 1.93,
"learning_rate": 5.734028687255751e-05,
"loss": 2.2513,
"step": 94
},
{
"epoch": 1.97,
"learning_rate": 5.329692723675994e-05,
"loss": 2.1533,
"step": 96
},
{
"epoch": 2.01,
"learning_rate": 4.934897930252886e-05,
"loss": 2.0451,
"step": 98
},
{
"epoch": 2.05,
"learning_rate": 4.550450850127625e-05,
"loss": 2.02,
"step": 100
},
{
"epoch": 2.09,
"learning_rate": 4.1771368866560665e-05,
"loss": 2.2731,
"step": 102
},
{
"epoch": 2.13,
"learning_rate": 3.815718698874672e-05,
"loss": 2.4117,
"step": 104
},
{
"epoch": 2.17,
"learning_rate": 3.466934643431795e-05,
"loss": 2.2761,
"step": 106
},
{
"epoch": 2.22,
"learning_rate": 3.131497266167357e-05,
"loss": 2.3457,
"step": 108
},
{
"epoch": 2.26,
"learning_rate": 2.81009184642253e-05,
"loss": 1.9155,
"step": 110
},
{
"epoch": 2.3,
"learning_rate": 2.5033749970533015e-05,
"loss": 2.1173,
"step": 112
},
{
"epoch": 2.34,
"learning_rate": 2.2119733230080408e-05,
"loss": 2.2136,
"step": 114
},
{
"epoch": 2.38,
"learning_rate": 1.9364821412094857e-05,
"loss": 2.432,
"step": 116
},
{
"epoch": 2.42,
"learning_rate": 1.6774642643563953e-05,
"loss": 2.2785,
"step": 118
},
{
"epoch": 2.46,
"learning_rate": 1.4354488511294417e-05,
"loss": 2.1617,
"step": 120
},
{
"epoch": 2.5,
"learning_rate": 1.2109303251503434e-05,
"loss": 2.1157,
"step": 122
},
{
"epoch": 2.54,
"learning_rate": 1.0043673649027518e-05,
"loss": 2.1812,
"step": 124
},
{
"epoch": 2.58,
"learning_rate": 8.161819666783888e-06,
"loss": 2.0722,
"step": 126
},
{
"epoch": 2.63,
"learning_rate": 6.467585824627887e-06,
"loss": 2.3153,
"step": 128
},
{
"epoch": 2.67,
"learning_rate": 4.964433345219355e-06,
"loss": 2.2884,
"step": 130
},
{
"epoch": 2.71,
"learning_rate": 3.655433082942972e-06,
"loss": 2.0102,
"step": 132
},
{
"epoch": 2.75,
"learning_rate": 2.5432592503288e-06,
"loss": 1.9512,
"step": 134
},
{
"epoch": 2.79,
"learning_rate": 1.6301839547892328e-06,
"loss": 2.2504,
"step": 136
},
{
"epoch": 2.83,
"learning_rate": 9.180725568338044e-07,
"loss": 2.217,
"step": 138
},
{
"epoch": 2.87,
"learning_rate": 4.0837985924448984e-07,
"loss": 2.331,
"step": 140
},
{
"epoch": 2.91,
"learning_rate": 1.0214713499706597e-07,
"loss": 2.1635,
"step": 142
},
{
"epoch": 2.95,
"learning_rate": 0.0,
"loss": 2.3516,
"step": 144
}
],
"logging_steps": 2,
"max_steps": 144,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 6393487599157248.0,
"trial_name": null,
"trial_params": null
}