1035 lines
27 KiB
JSON
1035 lines
27 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.029265437518290898,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 500,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 10.742569732666016,
|
||
|
|
"epoch": 0.000292654375182909,
|
||
|
|
"grad_norm": 4.8125,
|
||
|
|
"learning_rate": 2e-06,
|
||
|
|
"loss": 10.776,
|
||
|
|
"mean_token_accuracy": 0.00037909409729763865,
|
||
|
|
"num_tokens": 10517.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742593669891358,
|
||
|
|
"epoch": 0.000585308750365818,
|
||
|
|
"grad_norm": 4.78125,
|
||
|
|
"learning_rate": 4.5e-06,
|
||
|
|
"loss": 10.7562,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 20499.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.74259843826294,
|
||
|
|
"epoch": 0.000877963125548727,
|
||
|
|
"grad_norm": 5.53125,
|
||
|
|
"learning_rate": 7e-06,
|
||
|
|
"loss": 10.7254,
|
||
|
|
"mean_token_accuracy": 0.00031158956699073315,
|
||
|
|
"num_tokens": 30396.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742587089538574,
|
||
|
|
"epoch": 0.001170617500731636,
|
||
|
|
"grad_norm": 5.21875,
|
||
|
|
"learning_rate": 9.5e-06,
|
||
|
|
"loss": 10.6813,
|
||
|
|
"mean_token_accuracy": 0.0014116012142039835,
|
||
|
|
"num_tokens": 40862.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742495727539062,
|
||
|
|
"epoch": 0.0014632718759145448,
|
||
|
|
"grad_norm": 4.46875,
|
||
|
|
"learning_rate": 1.2e-05,
|
||
|
|
"loss": 10.573,
|
||
|
|
"mean_token_accuracy": 0.015958905406296253,
|
||
|
|
"num_tokens": 50482.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.74194974899292,
|
||
|
|
"epoch": 0.001755926251097454,
|
||
|
|
"grad_norm": 3.9375,
|
||
|
|
"learning_rate": 1.4500000000000002e-05,
|
||
|
|
"loss": 10.4277,
|
||
|
|
"mean_token_accuracy": 0.046428434550762177,
|
||
|
|
"num_tokens": 59557.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.739844131469727,
|
||
|
|
"epoch": 0.002048580626280363,
|
||
|
|
"grad_norm": 3.4375,
|
||
|
|
"learning_rate": 1.7000000000000003e-05,
|
||
|
|
"loss": 10.3155,
|
||
|
|
"mean_token_accuracy": 0.04745985008776188,
|
||
|
|
"num_tokens": 69864.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.732469940185547,
|
||
|
|
"epoch": 0.002341235001463272,
|
||
|
|
"grad_norm": 2.484375,
|
||
|
|
"learning_rate": 1.95e-05,
|
||
|
|
"loss": 10.1801,
|
||
|
|
"mean_token_accuracy": 0.056155404448509215,
|
||
|
|
"num_tokens": 80632.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.719615936279297,
|
||
|
|
"epoch": 0.0026338893766461808,
|
||
|
|
"grad_norm": 2.21875,
|
||
|
|
"learning_rate": 2.2e-05,
|
||
|
|
"loss": 10.0892,
|
||
|
|
"mean_token_accuracy": 0.049328677356243134,
|
||
|
|
"num_tokens": 90889.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.709369468688966,
|
||
|
|
"epoch": 0.0029265437518290896,
|
||
|
|
"grad_norm": 2.109375,
|
||
|
|
"learning_rate": 2.4500000000000003e-05,
|
||
|
|
"loss": 9.9839,
|
||
|
|
"mean_token_accuracy": 0.05372027605772019,
|
||
|
|
"num_tokens": 101136.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.702022743225097,
|
||
|
|
"epoch": 0.003219198127011999,
|
||
|
|
"grad_norm": 2.046875,
|
||
|
|
"learning_rate": 2.7e-05,
|
||
|
|
"loss": 9.9529,
|
||
|
|
"mean_token_accuracy": 0.05223828963935375,
|
||
|
|
"num_tokens": 111743.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.692447948455811,
|
||
|
|
"epoch": 0.003511852502194908,
|
||
|
|
"grad_norm": 1.8203125,
|
||
|
|
"learning_rate": 2.95e-05,
|
||
|
|
"loss": 9.9212,
|
||
|
|
"mean_token_accuracy": 0.050166602805256845,
|
||
|
|
"num_tokens": 121968.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.686018753051759,
|
||
|
|
"epoch": 0.0038045068773778167,
|
||
|
|
"grad_norm": 1.75,
|
||
|
|
"learning_rate": 3.2e-05,
|
||
|
|
"loss": 9.8286,
|
||
|
|
"mean_token_accuracy": 0.055526862666010854,
|
||
|
|
"num_tokens": 131917.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.676072120666504,
|
||
|
|
"epoch": 0.004097161252560726,
|
||
|
|
"grad_norm": 1.8359375,
|
||
|
|
"learning_rate": 3.4500000000000005e-05,
|
||
|
|
"loss": 9.7736,
|
||
|
|
"mean_token_accuracy": 0.05640910603106022,
|
||
|
|
"num_tokens": 141562.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.663375949859619,
|
||
|
|
"epoch": 0.004389815627743635,
|
||
|
|
"grad_norm": 1.7109375,
|
||
|
|
"learning_rate": 3.7e-05,
|
||
|
|
"loss": 9.755,
|
||
|
|
"mean_token_accuracy": 0.05814168080687523,
|
||
|
|
"num_tokens": 152163.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.652446174621582,
|
||
|
|
"epoch": 0.004682470002926544,
|
||
|
|
"grad_norm": 1.9609375,
|
||
|
|
"learning_rate": 3.95e-05,
|
||
|
|
"loss": 9.7531,
|
||
|
|
"mean_token_accuracy": 0.05046718679368496,
|
||
|
|
"num_tokens": 162684.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.65147132873535,
|
||
|
|
"epoch": 0.004975124378109453,
|
||
|
|
"grad_norm": 1.8515625,
|
||
|
|
"learning_rate": 4.2000000000000004e-05,
|
||
|
|
"loss": 9.6277,
|
||
|
|
"mean_token_accuracy": 0.055151918530464174,
|
||
|
|
"num_tokens": 173234.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.643102264404297,
|
||
|
|
"epoch": 0.0052677787532923615,
|
||
|
|
"grad_norm": 1.6953125,
|
||
|
|
"learning_rate": 4.45e-05,
|
||
|
|
"loss": 9.6174,
|
||
|
|
"mean_token_accuracy": 0.05056312084197998,
|
||
|
|
"num_tokens": 183645.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.629851245880127,
|
||
|
|
"epoch": 0.00556043312847527,
|
||
|
|
"grad_norm": 1.671875,
|
||
|
|
"learning_rate": 4.7000000000000004e-05,
|
||
|
|
"loss": 9.5472,
|
||
|
|
"mean_token_accuracy": 0.05371568165719509,
|
||
|
|
"num_tokens": 193874.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.60717601776123,
|
||
|
|
"epoch": 0.005853087503658179,
|
||
|
|
"grad_norm": 1.625,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"loss": 9.4433,
|
||
|
|
"mean_token_accuracy": 0.05704141147434712,
|
||
|
|
"num_tokens": 203965.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.582340145111084,
|
||
|
|
"epoch": 0.006145741878841089,
|
||
|
|
"grad_norm": 1.5625,
|
||
|
|
"learning_rate": 5.2e-05,
|
||
|
|
"loss": 9.3847,
|
||
|
|
"mean_token_accuracy": 0.05947887413203716,
|
||
|
|
"num_tokens": 214334.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.55553674697876,
|
||
|
|
"epoch": 0.006438396254023998,
|
||
|
|
"grad_norm": 1.59375,
|
||
|
|
"learning_rate": 5.45e-05,
|
||
|
|
"loss": 9.3073,
|
||
|
|
"mean_token_accuracy": 0.06609507203102112,
|
||
|
|
"num_tokens": 225435.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.51070203781128,
|
||
|
|
"epoch": 0.006731050629206907,
|
||
|
|
"grad_norm": 1.6328125,
|
||
|
|
"learning_rate": 5.7e-05,
|
||
|
|
"loss": 9.1764,
|
||
|
|
"mean_token_accuracy": 0.06483110673725605,
|
||
|
|
"num_tokens": 235107.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.439863014221192,
|
||
|
|
"epoch": 0.007023705004389816,
|
||
|
|
"grad_norm": 1.5,
|
||
|
|
"learning_rate": 5.9499999999999996e-05,
|
||
|
|
"loss": 9.1014,
|
||
|
|
"mean_token_accuracy": 0.06455096490681171,
|
||
|
|
"num_tokens": 245660.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.376344776153564,
|
||
|
|
"epoch": 0.0073163593795727245,
|
||
|
|
"grad_norm": 1.5625,
|
||
|
|
"learning_rate": 6.2e-05,
|
||
|
|
"loss": 9.0183,
|
||
|
|
"mean_token_accuracy": 0.06346280165016652,
|
||
|
|
"num_tokens": 256077.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.332421588897706,
|
||
|
|
"epoch": 0.007609013754755633,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 6.450000000000001e-05,
|
||
|
|
"loss": 8.9453,
|
||
|
|
"mean_token_accuracy": 0.0634394098073244,
|
||
|
|
"num_tokens": 265702.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.269437503814697,
|
||
|
|
"epoch": 0.007901668129938543,
|
||
|
|
"grad_norm": 1.5625,
|
||
|
|
"learning_rate": 6.7e-05,
|
||
|
|
"loss": 8.88,
|
||
|
|
"mean_token_accuracy": 0.06306366845965386,
|
||
|
|
"num_tokens": 276739.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.201168727874755,
|
||
|
|
"epoch": 0.008194322505121452,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 6.950000000000001e-05,
|
||
|
|
"loss": 8.7255,
|
||
|
|
"mean_token_accuracy": 0.06702562645077706,
|
||
|
|
"num_tokens": 285370.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.072903537750244,
|
||
|
|
"epoch": 0.008486976880304361,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 7.2e-05,
|
||
|
|
"loss": 8.6633,
|
||
|
|
"mean_token_accuracy": 0.06559402719140053,
|
||
|
|
"num_tokens": 295080.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.988585090637207,
|
||
|
|
"epoch": 0.00877963125548727,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 7.45e-05,
|
||
|
|
"loss": 8.5425,
|
||
|
|
"mean_token_accuracy": 0.06815728284418583,
|
||
|
|
"num_tokens": 304509.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.857632827758788,
|
||
|
|
"epoch": 0.009072285630670179,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 7.7e-05,
|
||
|
|
"loss": 8.4977,
|
||
|
|
"mean_token_accuracy": 0.06578324660658837,
|
||
|
|
"num_tokens": 315214.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.758829021453858,
|
||
|
|
"epoch": 0.009364940005853088,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 7.950000000000001e-05,
|
||
|
|
"loss": 8.4204,
|
||
|
|
"mean_token_accuracy": 0.06578456349670887,
|
||
|
|
"num_tokens": 325865.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.577184200286865,
|
||
|
|
"epoch": 0.009657594381035996,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 8.2e-05,
|
||
|
|
"loss": 8.3182,
|
||
|
|
"mean_token_accuracy": 0.06833198070526122,
|
||
|
|
"num_tokens": 335490.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.448071479797363,
|
||
|
|
"epoch": 0.009950248756218905,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 8.450000000000001e-05,
|
||
|
|
"loss": 8.3465,
|
||
|
|
"mean_token_accuracy": 0.0624022550880909,
|
||
|
|
"num_tokens": 345507.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.283161449432374,
|
||
|
|
"epoch": 0.010242903131401814,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 8.7e-05,
|
||
|
|
"loss": 8.2345,
|
||
|
|
"mean_token_accuracy": 0.06619864143431187,
|
||
|
|
"num_tokens": 355129.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.061387634277343,
|
||
|
|
"epoch": 0.010535557506584723,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 8.95e-05,
|
||
|
|
"loss": 8.1198,
|
||
|
|
"mean_token_accuracy": 0.0754898265004158,
|
||
|
|
"num_tokens": 364700.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.924063873291015,
|
||
|
|
"epoch": 0.010828211881767632,
|
||
|
|
"grad_norm": 0.74609375,
|
||
|
|
"learning_rate": 9.2e-05,
|
||
|
|
"loss": 8.1966,
|
||
|
|
"mean_token_accuracy": 0.07078267820179462,
|
||
|
|
"num_tokens": 374920.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.817254543304443,
|
||
|
|
"epoch": 0.01112086625695054,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 9.45e-05,
|
||
|
|
"loss": 7.9958,
|
||
|
|
"mean_token_accuracy": 0.0730692483484745,
|
||
|
|
"num_tokens": 384517.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.686346626281738,
|
||
|
|
"epoch": 0.01141352063213345,
|
||
|
|
"grad_norm": 0.75390625,
|
||
|
|
"learning_rate": 9.7e-05,
|
||
|
|
"loss": 8.1191,
|
||
|
|
"mean_token_accuracy": 0.07759304121136665,
|
||
|
|
"num_tokens": 394118.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.639398574829102,
|
||
|
|
"epoch": 0.011706175007316359,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 9.95e-05,
|
||
|
|
"loss": 8.1035,
|
||
|
|
"mean_token_accuracy": 0.07444557547569275,
|
||
|
|
"num_tokens": 404135.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.65887680053711,
|
||
|
|
"epoch": 0.01199882938249927,
|
||
|
|
"grad_norm": 0.75,
|
||
|
|
"learning_rate": 0.000102,
|
||
|
|
"loss": 8.0896,
|
||
|
|
"mean_token_accuracy": 0.07085032351315021,
|
||
|
|
"num_tokens": 414198.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.562304019927979,
|
||
|
|
"epoch": 0.012291483757682178,
|
||
|
|
"grad_norm": 0.62109375,
|
||
|
|
"learning_rate": 0.00010449999999999999,
|
||
|
|
"loss": 8.0473,
|
||
|
|
"mean_token_accuracy": 0.07471234947443009,
|
||
|
|
"num_tokens": 424747.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.543915939331054,
|
||
|
|
"epoch": 0.012584138132865087,
|
||
|
|
"grad_norm": 0.74609375,
|
||
|
|
"learning_rate": 0.000107,
|
||
|
|
"loss": 8.0208,
|
||
|
|
"mean_token_accuracy": 0.07326471023261547,
|
||
|
|
"num_tokens": 435597.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.513623428344726,
|
||
|
|
"epoch": 0.012876792508047996,
|
||
|
|
"grad_norm": 0.77734375,
|
||
|
|
"learning_rate": 0.0001095,
|
||
|
|
"loss": 8.064,
|
||
|
|
"mean_token_accuracy": 0.07332713790237903,
|
||
|
|
"num_tokens": 445262.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.550195503234864,
|
||
|
|
"epoch": 0.013169446883230905,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000112,
|
||
|
|
"loss": 8.094,
|
||
|
|
"mean_token_accuracy": 0.0686261247843504,
|
||
|
|
"num_tokens": 456455.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.483574199676514,
|
||
|
|
"epoch": 0.013462101258413814,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0001145,
|
||
|
|
"loss": 7.9287,
|
||
|
|
"mean_token_accuracy": 0.07206557914614678,
|
||
|
|
"num_tokens": 465696.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.426221942901611,
|
||
|
|
"epoch": 0.013754755633596722,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00011700000000000001,
|
||
|
|
"loss": 7.9791,
|
||
|
|
"mean_token_accuracy": 0.07656441517174244,
|
||
|
|
"num_tokens": 475171.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.437851619720458,
|
||
|
|
"epoch": 0.014047410008779631,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.00011949999999999999,
|
||
|
|
"loss": 7.9953,
|
||
|
|
"mean_token_accuracy": 0.07377254441380501,
|
||
|
|
"num_tokens": 484852.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.439754581451416,
|
||
|
|
"epoch": 0.01434006438396254,
|
||
|
|
"grad_norm": 0.765625,
|
||
|
|
"learning_rate": 0.000122,
|
||
|
|
"loss": 8.0016,
|
||
|
|
"mean_token_accuracy": 0.07172177135944366,
|
||
|
|
"num_tokens": 494539.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.422525405883789,
|
||
|
|
"epoch": 0.014632718759145449,
|
||
|
|
"grad_norm": 0.73046875,
|
||
|
|
"learning_rate": 0.0001245,
|
||
|
|
"loss": 7.9657,
|
||
|
|
"mean_token_accuracy": 0.06861439161002636,
|
||
|
|
"num_tokens": 504406.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.499318695068359,
|
||
|
|
"epoch": 0.014925373134328358,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.000127,
|
||
|
|
"loss": 7.9752,
|
||
|
|
"mean_token_accuracy": 0.07367737665772438,
|
||
|
|
"num_tokens": 514905.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.41889181137085,
|
||
|
|
"epoch": 0.015218027509511267,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.0001295,
|
||
|
|
"loss": 7.936,
|
||
|
|
"mean_token_accuracy": 0.08054133653640747,
|
||
|
|
"num_tokens": 524904.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.374094104766845,
|
||
|
|
"epoch": 0.015510681884694176,
|
||
|
|
"grad_norm": 1.609375,
|
||
|
|
"learning_rate": 0.000132,
|
||
|
|
"loss": 7.9791,
|
||
|
|
"mean_token_accuracy": 0.07328154221177101,
|
||
|
|
"num_tokens": 534423.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.391270446777344,
|
||
|
|
"epoch": 0.015803336259877086,
|
||
|
|
"grad_norm": 0.765625,
|
||
|
|
"learning_rate": 0.00013450000000000002,
|
||
|
|
"loss": 8.0123,
|
||
|
|
"mean_token_accuracy": 0.06913212612271309,
|
||
|
|
"num_tokens": 544468.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.460853576660156,
|
||
|
|
"epoch": 0.016095990635059995,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.00013700000000000002,
|
||
|
|
"loss": 7.9631,
|
||
|
|
"mean_token_accuracy": 0.07310855686664582,
|
||
|
|
"num_tokens": 555873.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.311201095581055,
|
||
|
|
"epoch": 0.016388645010242904,
|
||
|
|
"grad_norm": 0.69921875,
|
||
|
|
"learning_rate": 0.0001395,
|
||
|
|
"loss": 7.9352,
|
||
|
|
"mean_token_accuracy": 0.07407794632017613,
|
||
|
|
"num_tokens": 566228.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.375296783447265,
|
||
|
|
"epoch": 0.016681299385425813,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.00014199999999999998,
|
||
|
|
"loss": 7.8366,
|
||
|
|
"mean_token_accuracy": 0.07612851671874524,
|
||
|
|
"num_tokens": 576087.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.290613842010497,
|
||
|
|
"epoch": 0.016973953760608722,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0001445,
|
||
|
|
"loss": 7.9593,
|
||
|
|
"mean_token_accuracy": 0.07361815236508847,
|
||
|
|
"num_tokens": 586768.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.414975547790528,
|
||
|
|
"epoch": 0.01726660813579163,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.000147,
|
||
|
|
"loss": 7.9496,
|
||
|
|
"mean_token_accuracy": 0.07182935290038586,
|
||
|
|
"num_tokens": 597352.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.286548233032226,
|
||
|
|
"epoch": 0.01755926251097454,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0001495,
|
||
|
|
"loss": 7.8397,
|
||
|
|
"mean_token_accuracy": 0.07391503937542439,
|
||
|
|
"num_tokens": 607460.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.280863857269287,
|
||
|
|
"epoch": 0.01785191688615745,
|
||
|
|
"grad_norm": 0.78125,
|
||
|
|
"learning_rate": 0.000152,
|
||
|
|
"loss": 7.8721,
|
||
|
|
"mean_token_accuracy": 0.07399217337369919,
|
||
|
|
"num_tokens": 618882.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.382979774475098,
|
||
|
|
"epoch": 0.018144571261340357,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00015450000000000001,
|
||
|
|
"loss": 7.9746,
|
||
|
|
"mean_token_accuracy": 0.06754698418080807,
|
||
|
|
"num_tokens": 628378.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.238453578948974,
|
||
|
|
"epoch": 0.018437225636523266,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000157,
|
||
|
|
"loss": 7.913,
|
||
|
|
"mean_token_accuracy": 0.07458860278129578,
|
||
|
|
"num_tokens": 637339.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.266683578491211,
|
||
|
|
"epoch": 0.018729880011706175,
|
||
|
|
"grad_norm": 0.6953125,
|
||
|
|
"learning_rate": 0.0001595,
|
||
|
|
"loss": 7.9179,
|
||
|
|
"mean_token_accuracy": 0.07612942159175873,
|
||
|
|
"num_tokens": 648190.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.325155258178711,
|
||
|
|
"epoch": 0.019022534386889084,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.000162,
|
||
|
|
"loss": 7.8386,
|
||
|
|
"mean_token_accuracy": 0.07890116423368454,
|
||
|
|
"num_tokens": 658704.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.223814582824707,
|
||
|
|
"epoch": 0.019315188762071993,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.00016450000000000001,
|
||
|
|
"loss": 7.835,
|
||
|
|
"mean_token_accuracy": 0.0768560890108347,
|
||
|
|
"num_tokens": 668888.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.254367637634278,
|
||
|
|
"epoch": 0.0196078431372549,
|
||
|
|
"grad_norm": 0.79296875,
|
||
|
|
"learning_rate": 0.00016700000000000002,
|
||
|
|
"loss": 7.8646,
|
||
|
|
"mean_token_accuracy": 0.07014993466436863,
|
||
|
|
"num_tokens": 679294.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.180438041687012,
|
||
|
|
"epoch": 0.01990049751243781,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.00016950000000000003,
|
||
|
|
"loss": 7.8385,
|
||
|
|
"mean_token_accuracy": 0.07648964524269104,
|
||
|
|
"num_tokens": 689662.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.204143142700195,
|
||
|
|
"epoch": 0.02019315188762072,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.00017199999999999998,
|
||
|
|
"loss": 7.8542,
|
||
|
|
"mean_token_accuracy": 0.07869461253285408,
|
||
|
|
"num_tokens": 700356.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.173739433288574,
|
||
|
|
"epoch": 0.02048580626280363,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.00017449999999999999,
|
||
|
|
"loss": 7.7786,
|
||
|
|
"mean_token_accuracy": 0.07795644551515579,
|
||
|
|
"num_tokens": 710831.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.16906099319458,
|
||
|
|
"epoch": 0.020778460637986537,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.000177,
|
||
|
|
"loss": 7.7646,
|
||
|
|
"mean_token_accuracy": 0.07683240249752998,
|
||
|
|
"num_tokens": 720445.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.170342254638673,
|
||
|
|
"epoch": 0.021071115013169446,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0001795,
|
||
|
|
"loss": 7.7871,
|
||
|
|
"mean_token_accuracy": 0.08130665272474288,
|
||
|
|
"num_tokens": 730355.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.122212743759155,
|
||
|
|
"epoch": 0.021363769388352355,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.000182,
|
||
|
|
"loss": 7.7918,
|
||
|
|
"mean_token_accuracy": 0.08222091645002365,
|
||
|
|
"num_tokens": 740397.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.200673866271973,
|
||
|
|
"epoch": 0.021656423763535264,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0001845,
|
||
|
|
"loss": 7.7934,
|
||
|
|
"mean_token_accuracy": 0.0756984956562519,
|
||
|
|
"num_tokens": 750277.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.109900617599488,
|
||
|
|
"epoch": 0.021949078138718173,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.000187,
|
||
|
|
"loss": 7.7735,
|
||
|
|
"mean_token_accuracy": 0.07954552099108696,
|
||
|
|
"num_tokens": 759764.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.258574295043946,
|
||
|
|
"epoch": 0.02224173251390108,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0001895,
|
||
|
|
"loss": 7.8364,
|
||
|
|
"mean_token_accuracy": 0.0779568761587143,
|
||
|
|
"num_tokens": 769709.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.177908420562744,
|
||
|
|
"epoch": 0.02253438688908399,
|
||
|
|
"grad_norm": 0.75390625,
|
||
|
|
"learning_rate": 0.000192,
|
||
|
|
"loss": 7.7721,
|
||
|
|
"mean_token_accuracy": 0.0785105787217617,
|
||
|
|
"num_tokens": 780267.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.026059818267822,
|
||
|
|
"epoch": 0.0228270412642669,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.0001945,
|
||
|
|
"loss": 7.7254,
|
||
|
|
"mean_token_accuracy": 0.0828751116991043,
|
||
|
|
"num_tokens": 790184.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.152198600769044,
|
||
|
|
"epoch": 0.023119695639449808,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.00019700000000000002,
|
||
|
|
"loss": 7.8261,
|
||
|
|
"mean_token_accuracy": 0.07748916000127792,
|
||
|
|
"num_tokens": 800645.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.190797138214112,
|
||
|
|
"epoch": 0.023412350014632717,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.00019950000000000002,
|
||
|
|
"loss": 7.7524,
|
||
|
|
"mean_token_accuracy": 0.08283478766679764,
|
||
|
|
"num_tokens": 810873.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.11506757736206,
|
||
|
|
"epoch": 0.02370500438981563,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.000202,
|
||
|
|
"loss": 7.7456,
|
||
|
|
"mean_token_accuracy": 0.07929125241935253,
|
||
|
|
"num_tokens": 821661.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.140167808532714,
|
||
|
|
"epoch": 0.02399765876499854,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00020449999999999998,
|
||
|
|
"loss": 7.7449,
|
||
|
|
"mean_token_accuracy": 0.07854388505220414,
|
||
|
|
"num_tokens": 831818.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.042124271392822,
|
||
|
|
"epoch": 0.024290313140181447,
|
||
|
|
"grad_norm": 0.78515625,
|
||
|
|
"learning_rate": 0.000207,
|
||
|
|
"loss": 7.7535,
|
||
|
|
"mean_token_accuracy": 0.08163447454571723,
|
||
|
|
"num_tokens": 843030.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.099297571182252,
|
||
|
|
"epoch": 0.024582967515364356,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0002095,
|
||
|
|
"loss": 7.7175,
|
||
|
|
"mean_token_accuracy": 0.08631875067949295,
|
||
|
|
"num_tokens": 852477.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.106180906295776,
|
||
|
|
"epoch": 0.024875621890547265,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.000212,
|
||
|
|
"loss": 7.7318,
|
||
|
|
"mean_token_accuracy": 0.08200445771217346,
|
||
|
|
"num_tokens": 863018.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.047952270507812,
|
||
|
|
"epoch": 0.025168276265730174,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0002145,
|
||
|
|
"loss": 7.6688,
|
||
|
|
"mean_token_accuracy": 0.082207240909338,
|
||
|
|
"num_tokens": 872732.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.055245399475098,
|
||
|
|
"epoch": 0.025460930640913083,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.00021700000000000002,
|
||
|
|
"loss": 7.7356,
|
||
|
|
"mean_token_accuracy": 0.0770014464855194,
|
||
|
|
"num_tokens": 883189.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.050556993484497,
|
||
|
|
"epoch": 0.02575358501609599,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.0002195,
|
||
|
|
"loss": 7.7489,
|
||
|
|
"mean_token_accuracy": 0.0801065780222416,
|
||
|
|
"num_tokens": 893874.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.03118143081665,
|
||
|
|
"epoch": 0.0260462393912789,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.000222,
|
||
|
|
"loss": 7.6741,
|
||
|
|
"mean_token_accuracy": 0.08284056335687637,
|
||
|
|
"num_tokens": 904424.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.11718683242798,
|
||
|
|
"epoch": 0.02633889376646181,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0002245,
|
||
|
|
"loss": 7.7431,
|
||
|
|
"mean_token_accuracy": 0.07791092544794083,
|
||
|
|
"num_tokens": 914601.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.059693479537964,
|
||
|
|
"epoch": 0.026631548141644718,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.00022700000000000002,
|
||
|
|
"loss": 7.7462,
|
||
|
|
"mean_token_accuracy": 0.07850845158100128,
|
||
|
|
"num_tokens": 925162.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.002055263519287,
|
||
|
|
"epoch": 0.026924202516827627,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00022950000000000002,
|
||
|
|
"loss": 7.6594,
|
||
|
|
"mean_token_accuracy": 0.08002852946519852,
|
||
|
|
"num_tokens": 935182.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.099039840698243,
|
||
|
|
"epoch": 0.027216856892010536,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00023200000000000003,
|
||
|
|
"loss": 7.6897,
|
||
|
|
"mean_token_accuracy": 0.08213006183505059,
|
||
|
|
"num_tokens": 944812.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.961377811431885,
|
||
|
|
"epoch": 0.027509511267193445,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.00023449999999999998,
|
||
|
|
"loss": 7.6964,
|
||
|
|
"mean_token_accuracy": 0.07877071015536785,
|
||
|
|
"num_tokens": 954532.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.022741889953613,
|
||
|
|
"epoch": 0.027802165642376354,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000237,
|
||
|
|
"loss": 7.639,
|
||
|
|
"mean_token_accuracy": 0.08602378293871879,
|
||
|
|
"num_tokens": 963611.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.00587968826294,
|
||
|
|
"epoch": 0.028094820017559263,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0002395,
|
||
|
|
"loss": 7.688,
|
||
|
|
"mean_token_accuracy": 0.08180306293070316,
|
||
|
|
"num_tokens": 973177.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.030350875854491,
|
||
|
|
"epoch": 0.02838747439274217,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.000242,
|
||
|
|
"loss": 7.6898,
|
||
|
|
"mean_token_accuracy": 0.0791365496814251,
|
||
|
|
"num_tokens": 983623.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.03669090270996,
|
||
|
|
"epoch": 0.02868012876792508,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.0002445,
|
||
|
|
"loss": 7.7472,
|
||
|
|
"mean_token_accuracy": 0.08025188818573951,
|
||
|
|
"num_tokens": 993810.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.088376188278199,
|
||
|
|
"epoch": 0.02897278314310799,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.000247,
|
||
|
|
"loss": 7.6529,
|
||
|
|
"mean_token_accuracy": 0.0789113201200962,
|
||
|
|
"num_tokens": 1004155.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.990477657318115,
|
||
|
|
"epoch": 0.029265437518290898,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0002495,
|
||
|
|
"loss": 7.612,
|
||
|
|
"mean_token_accuracy": 0.08940722271800042,
|
||
|
|
"num_tokens": 1014896.0,
|
||
|
|
"step": 500
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 4000,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 1,
|
||
|
|
"save_steps": 500,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 225142683402240.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|