qwen-exp3 / trainer_state.json
TinyPixel's picture
Upload folder using huggingface_hub
f22e9b2
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.976,
"eval_steps": 500,
"global_step": 186,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 6.666666666666667e-06,
"loss": 1.1758,
"step": 2
},
{
"epoch": 0.06,
"learning_rate": 1.3333333333333333e-05,
"loss": 1.1009,
"step": 4
},
{
"epoch": 0.1,
"learning_rate": 2e-05,
"loss": 1.1151,
"step": 6
},
{
"epoch": 0.13,
"learning_rate": 1.999390827019096e-05,
"loss": 1.2375,
"step": 8
},
{
"epoch": 0.16,
"learning_rate": 1.9975640502598243e-05,
"loss": 1.2594,
"step": 10
},
{
"epoch": 0.19,
"learning_rate": 1.9945218953682736e-05,
"loss": 1.4222,
"step": 12
},
{
"epoch": 0.22,
"learning_rate": 1.9902680687415704e-05,
"loss": 1.2825,
"step": 14
},
{
"epoch": 0.26,
"learning_rate": 1.9848077530122083e-05,
"loss": 1.4058,
"step": 16
},
{
"epoch": 0.29,
"learning_rate": 1.9781476007338058e-05,
"loss": 1.052,
"step": 18
},
{
"epoch": 0.32,
"learning_rate": 1.9702957262759964e-05,
"loss": 1.0289,
"step": 20
},
{
"epoch": 0.35,
"learning_rate": 1.961261695938319e-05,
"loss": 1.1117,
"step": 22
},
{
"epoch": 0.38,
"learning_rate": 1.9510565162951538e-05,
"loss": 1.122,
"step": 24
},
{
"epoch": 0.42,
"learning_rate": 1.9396926207859085e-05,
"loss": 1.2279,
"step": 26
},
{
"epoch": 0.45,
"learning_rate": 1.9271838545667876e-05,
"loss": 1.3184,
"step": 28
},
{
"epoch": 0.48,
"learning_rate": 1.913545457642601e-05,
"loss": 1.4265,
"step": 30
},
{
"epoch": 0.51,
"learning_rate": 1.8987940462991673e-05,
"loss": 1.0538,
"step": 32
},
{
"epoch": 0.54,
"learning_rate": 1.8829475928589272e-05,
"loss": 1.0852,
"step": 34
},
{
"epoch": 0.58,
"learning_rate": 1.866025403784439e-05,
"loss": 0.9961,
"step": 36
},
{
"epoch": 0.61,
"learning_rate": 1.848048096156426e-05,
"loss": 0.9976,
"step": 38
},
{
"epoch": 0.64,
"learning_rate": 1.8290375725550417e-05,
"loss": 1.0792,
"step": 40
},
{
"epoch": 0.67,
"learning_rate": 1.8090169943749477e-05,
"loss": 1.1499,
"step": 42
},
{
"epoch": 0.7,
"learning_rate": 1.788010753606722e-05,
"loss": 1.2072,
"step": 44
},
{
"epoch": 0.74,
"learning_rate": 1.766044443118978e-05,
"loss": 1.204,
"step": 46
},
{
"epoch": 0.77,
"learning_rate": 1.7431448254773943e-05,
"loss": 1.0748,
"step": 48
},
{
"epoch": 0.8,
"learning_rate": 1.7193398003386514e-05,
"loss": 0.8873,
"step": 50
},
{
"epoch": 0.83,
"learning_rate": 1.6946583704589973e-05,
"loss": 1.0552,
"step": 52
},
{
"epoch": 0.86,
"learning_rate": 1.6691306063588583e-05,
"loss": 0.9658,
"step": 54
},
{
"epoch": 0.9,
"learning_rate": 1.6427876096865394e-05,
"loss": 1.0036,
"step": 56
},
{
"epoch": 0.93,
"learning_rate": 1.6156614753256583e-05,
"loss": 1.0127,
"step": 58
},
{
"epoch": 0.96,
"learning_rate": 1.5877852522924733e-05,
"loss": 1.2397,
"step": 60
},
{
"epoch": 0.99,
"learning_rate": 1.5591929034707468e-05,
"loss": 1.0287,
"step": 62
},
{
"epoch": 1.02,
"learning_rate": 1.529919264233205e-05,
"loss": 1.2013,
"step": 64
},
{
"epoch": 1.06,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.9782,
"step": 66
},
{
"epoch": 1.09,
"learning_rate": 1.469471562785891e-05,
"loss": 0.9667,
"step": 68
},
{
"epoch": 1.12,
"learning_rate": 1.4383711467890776e-05,
"loss": 1.1078,
"step": 70
},
{
"epoch": 1.15,
"learning_rate": 1.4067366430758004e-05,
"loss": 0.987,
"step": 72
},
{
"epoch": 1.18,
"learning_rate": 1.3746065934159123e-05,
"loss": 1.074,
"step": 74
},
{
"epoch": 1.22,
"learning_rate": 1.342020143325669e-05,
"loss": 1.0974,
"step": 76
},
{
"epoch": 1.25,
"learning_rate": 1.3090169943749475e-05,
"loss": 1.1005,
"step": 78
},
{
"epoch": 1.28,
"learning_rate": 1.2756373558169992e-05,
"loss": 0.9147,
"step": 80
},
{
"epoch": 1.31,
"learning_rate": 1.2419218955996677e-05,
"loss": 0.9503,
"step": 82
},
{
"epoch": 1.34,
"learning_rate": 1.2079116908177592e-05,
"loss": 0.9222,
"step": 84
},
{
"epoch": 1.38,
"learning_rate": 1.1736481776669307e-05,
"loss": 0.956,
"step": 86
},
{
"epoch": 1.41,
"learning_rate": 1.1391731009600655e-05,
"loss": 1.0116,
"step": 88
},
{
"epoch": 1.44,
"learning_rate": 1.1045284632676535e-05,
"loss": 1.0863,
"step": 90
},
{
"epoch": 1.47,
"learning_rate": 1.0697564737441254e-05,
"loss": 1.0045,
"step": 92
},
{
"epoch": 1.5,
"learning_rate": 1.0348994967025012e-05,
"loss": 1.0713,
"step": 94
},
{
"epoch": 1.54,
"learning_rate": 1e-05,
"loss": 0.9072,
"step": 96
},
{
"epoch": 1.57,
"learning_rate": 9.651005032974994e-06,
"loss": 0.9231,
"step": 98
},
{
"epoch": 1.6,
"learning_rate": 9.302435262558748e-06,
"loss": 0.9426,
"step": 100
},
{
"epoch": 1.63,
"learning_rate": 8.954715367323468e-06,
"loss": 0.957,
"step": 102
},
{
"epoch": 1.66,
"learning_rate": 8.60826899039935e-06,
"loss": 0.992,
"step": 104
},
{
"epoch": 1.7,
"learning_rate": 8.263518223330698e-06,
"loss": 1.0506,
"step": 106
},
{
"epoch": 1.73,
"learning_rate": 7.92088309182241e-06,
"loss": 1.0666,
"step": 108
},
{
"epoch": 1.76,
"learning_rate": 7.580781044003324e-06,
"loss": 0.9937,
"step": 110
},
{
"epoch": 1.79,
"learning_rate": 7.243626441830009e-06,
"loss": 0.898,
"step": 112
},
{
"epoch": 1.82,
"learning_rate": 6.909830056250527e-06,
"loss": 0.9504,
"step": 114
},
{
"epoch": 1.86,
"learning_rate": 6.579798566743314e-06,
"loss": 0.9121,
"step": 116
},
{
"epoch": 1.89,
"learning_rate": 6.25393406584088e-06,
"loss": 1.0717,
"step": 118
},
{
"epoch": 1.92,
"learning_rate": 5.932633569242e-06,
"loss": 0.9389,
"step": 120
},
{
"epoch": 1.95,
"learning_rate": 5.616288532109225e-06,
"loss": 1.0696,
"step": 122
},
{
"epoch": 1.98,
"learning_rate": 5.305284372141095e-06,
"loss": 1.0083,
"step": 124
},
{
"epoch": 2.02,
"learning_rate": 5.000000000000003e-06,
"loss": 1.1655,
"step": 126
},
{
"epoch": 2.05,
"learning_rate": 4.700807357667953e-06,
"loss": 0.9755,
"step": 128
},
{
"epoch": 2.08,
"learning_rate": 4.408070965292534e-06,
"loss": 0.9875,
"step": 130
},
{
"epoch": 2.11,
"learning_rate": 4.12214747707527e-06,
"loss": 1.0502,
"step": 132
},
{
"epoch": 2.14,
"learning_rate": 3.8433852467434175e-06,
"loss": 0.9327,
"step": 134
},
{
"epoch": 2.18,
"learning_rate": 3.5721239031346067e-06,
"loss": 1.0175,
"step": 136
},
{
"epoch": 2.21,
"learning_rate": 3.308693936411421e-06,
"loss": 0.9728,
"step": 138
},
{
"epoch": 2.24,
"learning_rate": 3.0534162954100264e-06,
"loss": 1.1364,
"step": 140
},
{
"epoch": 2.27,
"learning_rate": 2.8066019966134907e-06,
"loss": 0.9489,
"step": 142
},
{
"epoch": 2.3,
"learning_rate": 2.5685517452260566e-06,
"loss": 0.8962,
"step": 144
},
{
"epoch": 2.34,
"learning_rate": 2.339555568810221e-06,
"loss": 0.9396,
"step": 146
},
{
"epoch": 2.37,
"learning_rate": 2.119892463932781e-06,
"loss": 0.9996,
"step": 148
},
{
"epoch": 2.4,
"learning_rate": 1.9098300562505266e-06,
"loss": 1.0633,
"step": 150
},
{
"epoch": 2.43,
"learning_rate": 1.709624274449584e-06,
"loss": 1.092,
"step": 152
},
{
"epoch": 2.46,
"learning_rate": 1.5195190384357405e-06,
"loss": 0.8942,
"step": 154
},
{
"epoch": 2.5,
"learning_rate": 1.339745962155613e-06,
"loss": 0.945,
"step": 156
},
{
"epoch": 2.53,
"learning_rate": 1.1705240714107301e-06,
"loss": 0.9411,
"step": 158
},
{
"epoch": 2.56,
"learning_rate": 1.012059537008332e-06,
"loss": 0.941,
"step": 160
},
{
"epoch": 2.59,
"learning_rate": 8.645454235739903e-07,
"loss": 0.8895,
"step": 162
},
{
"epoch": 2.62,
"learning_rate": 7.281614543321269e-07,
"loss": 1.0295,
"step": 164
},
{
"epoch": 2.66,
"learning_rate": 6.030737921409169e-07,
"loss": 0.9887,
"step": 166
},
{
"epoch": 2.69,
"learning_rate": 4.894348370484648e-07,
"loss": 0.9458,
"step": 168
},
{
"epoch": 2.72,
"learning_rate": 3.8738304061681107e-07,
"loss": 1.0044,
"step": 170
},
{
"epoch": 2.75,
"learning_rate": 2.970427372400353e-07,
"loss": 1.085,
"step": 172
},
{
"epoch": 2.78,
"learning_rate": 2.1852399266194312e-07,
"loss": 0.8603,
"step": 174
},
{
"epoch": 2.82,
"learning_rate": 1.519224698779198e-07,
"loss": 0.8817,
"step": 176
},
{
"epoch": 2.85,
"learning_rate": 9.731931258429638e-08,
"loss": 0.9777,
"step": 178
},
{
"epoch": 2.88,
"learning_rate": 5.4781046317267103e-08,
"loss": 0.933,
"step": 180
},
{
"epoch": 2.91,
"learning_rate": 2.4359497401758026e-08,
"loss": 1.0482,
"step": 182
},
{
"epoch": 2.94,
"learning_rate": 6.091729809042379e-09,
"loss": 1.0416,
"step": 184
},
{
"epoch": 2.98,
"learning_rate": 0.0,
"loss": 1.1137,
"step": 186
}
],
"logging_steps": 2,
"max_steps": 186,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 6703216867602432.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}