6035 lines
164 KiB
JSON
6035 lines
164 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.17559262510974538,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 3000,
|
||
|
|
"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
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.972944545745849,
|
||
|
|
"epoch": 0.029558091893473807,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000252,
|
||
|
|
"loss": 7.5516,
|
||
|
|
"mean_token_accuracy": 0.0878017283976078,
|
||
|
|
"num_tokens": 1024991.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.899525737762451,
|
||
|
|
"epoch": 0.029850746268656716,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0002545,
|
||
|
|
"loss": 7.5796,
|
||
|
|
"mean_token_accuracy": 0.08802613019943237,
|
||
|
|
"num_tokens": 1036697.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.065279579162597,
|
||
|
|
"epoch": 0.030143400643839625,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000257,
|
||
|
|
"loss": 7.6774,
|
||
|
|
"mean_token_accuracy": 0.07723400816321373,
|
||
|
|
"num_tokens": 1046245.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.788718843460083,
|
||
|
|
"epoch": 0.030436055019022534,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0002595,
|
||
|
|
"loss": 7.5633,
|
||
|
|
"mean_token_accuracy": 0.08955003842711448,
|
||
|
|
"num_tokens": 1056232.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.821068525314331,
|
||
|
|
"epoch": 0.030728709394205442,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000262,
|
||
|
|
"loss": 7.4477,
|
||
|
|
"mean_token_accuracy": 0.09515074491500855,
|
||
|
|
"num_tokens": 1065536.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.05577802658081,
|
||
|
|
"epoch": 0.03102136376938835,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00026450000000000003,
|
||
|
|
"loss": 7.5794,
|
||
|
|
"mean_token_accuracy": 0.08964744806289673,
|
||
|
|
"num_tokens": 1075135.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.835528612136841,
|
||
|
|
"epoch": 0.031314018144571264,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00026700000000000004,
|
||
|
|
"loss": 7.5717,
|
||
|
|
"mean_token_accuracy": 0.0826539345085621,
|
||
|
|
"num_tokens": 1085498.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.983124303817749,
|
||
|
|
"epoch": 0.03160667251975417,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.00026950000000000005,
|
||
|
|
"loss": 7.6005,
|
||
|
|
"mean_token_accuracy": 0.08875111043453217,
|
||
|
|
"num_tokens": 1095559.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.931251287460327,
|
||
|
|
"epoch": 0.03189932689493708,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00027200000000000005,
|
||
|
|
"loss": 7.5456,
|
||
|
|
"mean_token_accuracy": 0.08640314042568206,
|
||
|
|
"num_tokens": 1105701.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.889260959625244,
|
||
|
|
"epoch": 0.03219198127011999,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0002745,
|
||
|
|
"loss": 7.5431,
|
||
|
|
"mean_token_accuracy": 0.08784606605768204,
|
||
|
|
"num_tokens": 1116455.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.8568816661834715,
|
||
|
|
"epoch": 0.0324846356453029,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.000277,
|
||
|
|
"loss": 7.5697,
|
||
|
|
"mean_token_accuracy": 0.08820039629936219,
|
||
|
|
"num_tokens": 1126596.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.986862754821777,
|
||
|
|
"epoch": 0.03277729002048581,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0002795,
|
||
|
|
"loss": 7.5865,
|
||
|
|
"mean_token_accuracy": 0.08685005903244018,
|
||
|
|
"num_tokens": 1136969.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.84932541847229,
|
||
|
|
"epoch": 0.03306994439566872,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00028199999999999997,
|
||
|
|
"loss": 7.5699,
|
||
|
|
"mean_token_accuracy": 0.08707550391554833,
|
||
|
|
"num_tokens": 1147175.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.847287702560425,
|
||
|
|
"epoch": 0.033362598770851626,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0002845,
|
||
|
|
"loss": 7.527,
|
||
|
|
"mean_token_accuracy": 0.09069008976221085,
|
||
|
|
"num_tokens": 1156539.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.910270690917969,
|
||
|
|
"epoch": 0.033655253146034535,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.000287,
|
||
|
|
"loss": 7.5107,
|
||
|
|
"mean_token_accuracy": 0.0893574945628643,
|
||
|
|
"num_tokens": 1166630.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.857235383987427,
|
||
|
|
"epoch": 0.033947907521217444,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0002895,
|
||
|
|
"loss": 7.5453,
|
||
|
|
"mean_token_accuracy": 0.08516263216733932,
|
||
|
|
"num_tokens": 1176279.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.920040893554687,
|
||
|
|
"epoch": 0.03424056189640035,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.000292,
|
||
|
|
"loss": 7.543,
|
||
|
|
"mean_token_accuracy": 0.08200450427830219,
|
||
|
|
"num_tokens": 1186321.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.912441968917847,
|
||
|
|
"epoch": 0.03453321627158326,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0002945,
|
||
|
|
"loss": 7.5193,
|
||
|
|
"mean_token_accuracy": 0.08341860473155975,
|
||
|
|
"num_tokens": 1198287.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.7401360988616945,
|
||
|
|
"epoch": 0.03482587064676617,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000297,
|
||
|
|
"loss": 7.5164,
|
||
|
|
"mean_token_accuracy": 0.08626452758908272,
|
||
|
|
"num_tokens": 1208618.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.83452959060669,
|
||
|
|
"epoch": 0.03511852502194908,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0002995,
|
||
|
|
"loss": 7.5024,
|
||
|
|
"mean_token_accuracy": 0.08562399223446845,
|
||
|
|
"num_tokens": 1217932.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.012685871124267,
|
||
|
|
"epoch": 0.03541117939713199,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.000302,
|
||
|
|
"loss": 7.5414,
|
||
|
|
"mean_token_accuracy": 0.08212736770510673,
|
||
|
|
"num_tokens": 1227965.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.799877643585205,
|
||
|
|
"epoch": 0.0357038337723149,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0003045,
|
||
|
|
"loss": 7.485,
|
||
|
|
"mean_token_accuracy": 0.08530130311846733,
|
||
|
|
"num_tokens": 1237879.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.793827056884766,
|
||
|
|
"epoch": 0.035996488147497806,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.000307,
|
||
|
|
"loss": 7.4804,
|
||
|
|
"mean_token_accuracy": 0.0855767272412777,
|
||
|
|
"num_tokens": 1248547.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.876594161987304,
|
||
|
|
"epoch": 0.036289142522680715,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0003095,
|
||
|
|
"loss": 7.5034,
|
||
|
|
"mean_token_accuracy": 0.08643778935074806,
|
||
|
|
"num_tokens": 1259462.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.922547101974487,
|
||
|
|
"epoch": 0.036581796897863623,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000312,
|
||
|
|
"loss": 7.5425,
|
||
|
|
"mean_token_accuracy": 0.0930032640695572,
|
||
|
|
"num_tokens": 1270668.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.821293497085572,
|
||
|
|
"epoch": 0.03687445127304653,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0003145,
|
||
|
|
"loss": 7.506,
|
||
|
|
"mean_token_accuracy": 0.08481546565890312,
|
||
|
|
"num_tokens": 1280459.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.859448432922363,
|
||
|
|
"epoch": 0.03716710564822944,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.000317,
|
||
|
|
"loss": 7.4332,
|
||
|
|
"mean_token_accuracy": 0.0836933895945549,
|
||
|
|
"num_tokens": 1291114.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.879277753829956,
|
||
|
|
"epoch": 0.03745976002341235,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0003195,
|
||
|
|
"loss": 7.5801,
|
||
|
|
"mean_token_accuracy": 0.07807724177837372,
|
||
|
|
"num_tokens": 1301442.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.79024305343628,
|
||
|
|
"epoch": 0.03775241439859526,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000322,
|
||
|
|
"loss": 7.3892,
|
||
|
|
"mean_token_accuracy": 0.09089659005403519,
|
||
|
|
"num_tokens": 1311315.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.697639131546021,
|
||
|
|
"epoch": 0.03804506877377817,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00032450000000000003,
|
||
|
|
"loss": 7.4088,
|
||
|
|
"mean_token_accuracy": 0.09008980989456176,
|
||
|
|
"num_tokens": 1320962.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.803319597244263,
|
||
|
|
"epoch": 0.03833772314896108,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00032700000000000003,
|
||
|
|
"loss": 7.4448,
|
||
|
|
"mean_token_accuracy": 0.08984620422124863,
|
||
|
|
"num_tokens": 1331006.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.771277570724488,
|
||
|
|
"epoch": 0.038630377524143986,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00032950000000000004,
|
||
|
|
"loss": 7.425,
|
||
|
|
"mean_token_accuracy": 0.08424968719482422,
|
||
|
|
"num_tokens": 1341342.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.751668787002563,
|
||
|
|
"epoch": 0.038923031899326895,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00033200000000000005,
|
||
|
|
"loss": 7.3853,
|
||
|
|
"mean_token_accuracy": 0.08578916639089584,
|
||
|
|
"num_tokens": 1350484.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.757629871368408,
|
||
|
|
"epoch": 0.0392156862745098,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00033450000000000005,
|
||
|
|
"loss": 7.4261,
|
||
|
|
"mean_token_accuracy": 0.08848872929811477,
|
||
|
|
"num_tokens": 1360422.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.717638921737671,
|
||
|
|
"epoch": 0.03950834064969271,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.000337,
|
||
|
|
"loss": 7.3313,
|
||
|
|
"mean_token_accuracy": 0.0953003279864788,
|
||
|
|
"num_tokens": 1370653.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.675066566467285,
|
||
|
|
"epoch": 0.03980099502487562,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0003395,
|
||
|
|
"loss": 7.4036,
|
||
|
|
"mean_token_accuracy": 0.08738565891981125,
|
||
|
|
"num_tokens": 1379904.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.810481309890747,
|
||
|
|
"epoch": 0.04009364940005853,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.000342,
|
||
|
|
"loss": 7.3752,
|
||
|
|
"mean_token_accuracy": 0.088729477673769,
|
||
|
|
"num_tokens": 1390292.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.815591716766358,
|
||
|
|
"epoch": 0.04038630377524144,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00034449999999999997,
|
||
|
|
"loss": 7.3868,
|
||
|
|
"mean_token_accuracy": 0.09195382669568061,
|
||
|
|
"num_tokens": 1400089.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.60293927192688,
|
||
|
|
"epoch": 0.04067895815042435,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000347,
|
||
|
|
"loss": 7.4062,
|
||
|
|
"mean_token_accuracy": 0.08808108903467655,
|
||
|
|
"num_tokens": 1409486.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.7336822032928465,
|
||
|
|
"epoch": 0.04097161252560726,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0003495,
|
||
|
|
"loss": 7.4036,
|
||
|
|
"mean_token_accuracy": 0.09051820784807205,
|
||
|
|
"num_tokens": 1419834.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.825760173797607,
|
||
|
|
"epoch": 0.041264266900790166,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.000352,
|
||
|
|
"loss": 7.4213,
|
||
|
|
"mean_token_accuracy": 0.08384566307067871,
|
||
|
|
"num_tokens": 1430045.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.65966100692749,
|
||
|
|
"epoch": 0.041556921275973074,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.0003545,
|
||
|
|
"loss": 7.3022,
|
||
|
|
"mean_token_accuracy": 0.09362379759550095,
|
||
|
|
"num_tokens": 1439394.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.688346433639526,
|
||
|
|
"epoch": 0.04184957565115598,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.000357,
|
||
|
|
"loss": 7.4215,
|
||
|
|
"mean_token_accuracy": 0.09055223762989044,
|
||
|
|
"num_tokens": 1449768.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.685902833938599,
|
||
|
|
"epoch": 0.04214223002633889,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0003595,
|
||
|
|
"loss": 7.3477,
|
||
|
|
"mean_token_accuracy": 0.09224402233958244,
|
||
|
|
"num_tokens": 1460716.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.657220983505249,
|
||
|
|
"epoch": 0.0424348844015218,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.000362,
|
||
|
|
"loss": 7.3045,
|
||
|
|
"mean_token_accuracy": 0.09458784088492393,
|
||
|
|
"num_tokens": 1470447.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.609696722030639,
|
||
|
|
"epoch": 0.04272753877670471,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0003645,
|
||
|
|
"loss": 7.3177,
|
||
|
|
"mean_token_accuracy": 0.09160968512296677,
|
||
|
|
"num_tokens": 1481195.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.631748199462891,
|
||
|
|
"epoch": 0.04302019315188762,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000367,
|
||
|
|
"loss": 7.3056,
|
||
|
|
"mean_token_accuracy": 0.0939846970140934,
|
||
|
|
"num_tokens": 1491679.0,
|
||
|
|
"step": 735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.620209503173828,
|
||
|
|
"epoch": 0.04331284752707053,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0003695,
|
||
|
|
"loss": 7.2829,
|
||
|
|
"mean_token_accuracy": 0.09510877132415771,
|
||
|
|
"num_tokens": 1501444.0,
|
||
|
|
"step": 740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.611186599731445,
|
||
|
|
"epoch": 0.043605501902253437,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000372,
|
||
|
|
"loss": 7.2859,
|
||
|
|
"mean_token_accuracy": 0.09353157803416252,
|
||
|
|
"num_tokens": 1511299.0,
|
||
|
|
"step": 745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.654992341995239,
|
||
|
|
"epoch": 0.043898156277436345,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0003745,
|
||
|
|
"loss": 7.3184,
|
||
|
|
"mean_token_accuracy": 0.08825154900550843,
|
||
|
|
"num_tokens": 1522389.0,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.5400854587554935,
|
||
|
|
"epoch": 0.044190810652619254,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.000377,
|
||
|
|
"loss": 7.2799,
|
||
|
|
"mean_token_accuracy": 0.08888843208551407,
|
||
|
|
"num_tokens": 1533493.0,
|
||
|
|
"step": 755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.710229063034058,
|
||
|
|
"epoch": 0.04448346502780216,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0003795,
|
||
|
|
"loss": 7.3453,
|
||
|
|
"mean_token_accuracy": 0.08668449223041534,
|
||
|
|
"num_tokens": 1542668.0,
|
||
|
|
"step": 760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.633497714996338,
|
||
|
|
"epoch": 0.04477611940298507,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000382,
|
||
|
|
"loss": 7.2267,
|
||
|
|
"mean_token_accuracy": 0.09399316534399986,
|
||
|
|
"num_tokens": 1552221.0,
|
||
|
|
"step": 765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.639019966125488,
|
||
|
|
"epoch": 0.04506877377816798,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0003845,
|
||
|
|
"loss": 7.3691,
|
||
|
|
"mean_token_accuracy": 0.08336025923490524,
|
||
|
|
"num_tokens": 1562807.0,
|
||
|
|
"step": 770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.568796062469483,
|
||
|
|
"epoch": 0.04536142815335089,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00038700000000000003,
|
||
|
|
"loss": 7.3082,
|
||
|
|
"mean_token_accuracy": 0.08972151428461075,
|
||
|
|
"num_tokens": 1572751.0,
|
||
|
|
"step": 775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.611496067047119,
|
||
|
|
"epoch": 0.0456540825285338,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00038950000000000003,
|
||
|
|
"loss": 7.3434,
|
||
|
|
"mean_token_accuracy": 0.08387525528669357,
|
||
|
|
"num_tokens": 1582802.0,
|
||
|
|
"step": 780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.618696594238282,
|
||
|
|
"epoch": 0.04594673690371671,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00039200000000000004,
|
||
|
|
"loss": 7.2633,
|
||
|
|
"mean_token_accuracy": 0.0899326853454113,
|
||
|
|
"num_tokens": 1593780.0,
|
||
|
|
"step": 785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.53293023109436,
|
||
|
|
"epoch": 0.046239391278899616,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.00039450000000000005,
|
||
|
|
"loss": 7.3148,
|
||
|
|
"mean_token_accuracy": 0.09066571295261383,
|
||
|
|
"num_tokens": 1604386.0,
|
||
|
|
"step": 790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6753880977630615,
|
||
|
|
"epoch": 0.046532045654082525,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00039700000000000005,
|
||
|
|
"loss": 7.295,
|
||
|
|
"mean_token_accuracy": 0.0937283106148243,
|
||
|
|
"num_tokens": 1614359.0,
|
||
|
|
"step": 795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.544372034072876,
|
||
|
|
"epoch": 0.046824700029265434,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0003995,
|
||
|
|
"loss": 7.176,
|
||
|
|
"mean_token_accuracy": 0.09263980463147163,
|
||
|
|
"num_tokens": 1624389.0,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.56023473739624,
|
||
|
|
"epoch": 0.04711735440444834,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.000402,
|
||
|
|
"loss": 7.2833,
|
||
|
|
"mean_token_accuracy": 0.09009978026151658,
|
||
|
|
"num_tokens": 1634608.0,
|
||
|
|
"step": 805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.455692481994629,
|
||
|
|
"epoch": 0.04741000877963126,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004045,
|
||
|
|
"loss": 7.2045,
|
||
|
|
"mean_token_accuracy": 0.09845735877752304,
|
||
|
|
"num_tokens": 1645723.0,
|
||
|
|
"step": 810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.554573822021484,
|
||
|
|
"epoch": 0.04770266315481417,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.00040699999999999997,
|
||
|
|
"loss": 7.1817,
|
||
|
|
"mean_token_accuracy": 0.10012574419379235,
|
||
|
|
"num_tokens": 1655182.0,
|
||
|
|
"step": 815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.52402024269104,
|
||
|
|
"epoch": 0.04799531752999708,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004095,
|
||
|
|
"loss": 7.1881,
|
||
|
|
"mean_token_accuracy": 0.09166754521429539,
|
||
|
|
"num_tokens": 1664597.0,
|
||
|
|
"step": 820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.551714515686035,
|
||
|
|
"epoch": 0.048287971905179985,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000412,
|
||
|
|
"loss": 7.2815,
|
||
|
|
"mean_token_accuracy": 0.09629782885313035,
|
||
|
|
"num_tokens": 1674809.0,
|
||
|
|
"step": 825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4392908096313475,
|
||
|
|
"epoch": 0.048580626280362894,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004145,
|
||
|
|
"loss": 7.1535,
|
||
|
|
"mean_token_accuracy": 0.09503219947218895,
|
||
|
|
"num_tokens": 1684082.0,
|
||
|
|
"step": 830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.506573343276978,
|
||
|
|
"epoch": 0.0488732806555458,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.000417,
|
||
|
|
"loss": 7.2511,
|
||
|
|
"mean_token_accuracy": 0.09144405052065849,
|
||
|
|
"num_tokens": 1695547.0,
|
||
|
|
"step": 835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.713369989395142,
|
||
|
|
"epoch": 0.04916593503072871,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004195,
|
||
|
|
"loss": 7.2906,
|
||
|
|
"mean_token_accuracy": 0.097728531062603,
|
||
|
|
"num_tokens": 1706434.0,
|
||
|
|
"step": 840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.475108194351196,
|
||
|
|
"epoch": 0.04945858940591162,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.000422,
|
||
|
|
"loss": 7.226,
|
||
|
|
"mean_token_accuracy": 0.0920279160141945,
|
||
|
|
"num_tokens": 1718063.0,
|
||
|
|
"step": 845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.463070058822632,
|
||
|
|
"epoch": 0.04975124378109453,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004245,
|
||
|
|
"loss": 7.2122,
|
||
|
|
"mean_token_accuracy": 0.08780092373490334,
|
||
|
|
"num_tokens": 1728594.0,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.555836248397827,
|
||
|
|
"epoch": 0.05004389815627744,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.000427,
|
||
|
|
"loss": 7.2233,
|
||
|
|
"mean_token_accuracy": 0.09364095106720924,
|
||
|
|
"num_tokens": 1738879.0,
|
||
|
|
"step": 855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.437271451950073,
|
||
|
|
"epoch": 0.05033655253146035,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004295,
|
||
|
|
"loss": 7.1784,
|
||
|
|
"mean_token_accuracy": 0.09283483177423477,
|
||
|
|
"num_tokens": 1748850.0,
|
||
|
|
"step": 860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.491488265991211,
|
||
|
|
"epoch": 0.050629206906643257,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000432,
|
||
|
|
"loss": 7.23,
|
||
|
|
"mean_token_accuracy": 0.09758371859788895,
|
||
|
|
"num_tokens": 1759992.0,
|
||
|
|
"step": 865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6118079662323,
|
||
|
|
"epoch": 0.050921861281826165,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004345,
|
||
|
|
"loss": 7.2323,
|
||
|
|
"mean_token_accuracy": 0.09015733227133751,
|
||
|
|
"num_tokens": 1769879.0,
|
||
|
|
"step": 870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.352298641204834,
|
||
|
|
"epoch": 0.051214515657009074,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.000437,
|
||
|
|
"loss": 7.1161,
|
||
|
|
"mean_token_accuracy": 0.10056154727935791,
|
||
|
|
"num_tokens": 1779429.0,
|
||
|
|
"step": 875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.476632738113404,
|
||
|
|
"epoch": 0.05150717003219198,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004395,
|
||
|
|
"loss": 7.2185,
|
||
|
|
"mean_token_accuracy": 0.08883849456906319,
|
||
|
|
"num_tokens": 1788655.0,
|
||
|
|
"step": 880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.499739456176758,
|
||
|
|
"epoch": 0.05179982440737489,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.000442,
|
||
|
|
"loss": 7.2176,
|
||
|
|
"mean_token_accuracy": 0.0874781295657158,
|
||
|
|
"num_tokens": 1798454.0,
|
||
|
|
"step": 885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.425588893890381,
|
||
|
|
"epoch": 0.0520924787825578,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004445,
|
||
|
|
"loss": 7.1901,
|
||
|
|
"mean_token_accuracy": 0.09141783937811851,
|
||
|
|
"num_tokens": 1809016.0,
|
||
|
|
"step": 890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4348835945129395,
|
||
|
|
"epoch": 0.05238513315774071,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.000447,
|
||
|
|
"loss": 7.0729,
|
||
|
|
"mean_token_accuracy": 0.10189558044075966,
|
||
|
|
"num_tokens": 1819992.0,
|
||
|
|
"step": 895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.461593580245972,
|
||
|
|
"epoch": 0.05267778753292362,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00044950000000000003,
|
||
|
|
"loss": 7.1446,
|
||
|
|
"mean_token_accuracy": 0.0971047930419445,
|
||
|
|
"num_tokens": 1829932.0,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.391701364517212,
|
||
|
|
"epoch": 0.05297044190810653,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00045200000000000004,
|
||
|
|
"loss": 7.106,
|
||
|
|
"mean_token_accuracy": 0.09629447236657143,
|
||
|
|
"num_tokens": 1839877.0,
|
||
|
|
"step": 905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.366179513931274,
|
||
|
|
"epoch": 0.053263096283289436,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00045450000000000004,
|
||
|
|
"loss": 7.1228,
|
||
|
|
"mean_token_accuracy": 0.09160000830888748,
|
||
|
|
"num_tokens": 1849619.0,
|
||
|
|
"step": 910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.25721960067749,
|
||
|
|
"epoch": 0.053555750658472345,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00045700000000000005,
|
||
|
|
"loss": 7.0871,
|
||
|
|
"mean_token_accuracy": 0.10284551829099656,
|
||
|
|
"num_tokens": 1859513.0,
|
||
|
|
"step": 915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4424947738647464,
|
||
|
|
"epoch": 0.053848405033655254,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00045950000000000006,
|
||
|
|
"loss": 7.0591,
|
||
|
|
"mean_token_accuracy": 0.09884816706180573,
|
||
|
|
"num_tokens": 1869849.0,
|
||
|
|
"step": 920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.435005235671997,
|
||
|
|
"epoch": 0.05414105940883816,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000462,
|
||
|
|
"loss": 7.174,
|
||
|
|
"mean_token_accuracy": 0.09173808693885803,
|
||
|
|
"num_tokens": 1879385.0,
|
||
|
|
"step": 925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.384939336776734,
|
||
|
|
"epoch": 0.05443371378402107,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004645,
|
||
|
|
"loss": 7.1714,
|
||
|
|
"mean_token_accuracy": 0.0962887905538082,
|
||
|
|
"num_tokens": 1889415.0,
|
||
|
|
"step": 930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.449399948120117,
|
||
|
|
"epoch": 0.05472636815920398,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.000467,
|
||
|
|
"loss": 7.2205,
|
||
|
|
"mean_token_accuracy": 0.09307129457592964,
|
||
|
|
"num_tokens": 1901145.0,
|
||
|
|
"step": 935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3746397495269775,
|
||
|
|
"epoch": 0.05501902253438689,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004695,
|
||
|
|
"loss": 7.0894,
|
||
|
|
"mean_token_accuracy": 0.10347672551870346,
|
||
|
|
"num_tokens": 1910355.0,
|
||
|
|
"step": 940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.481390714645386,
|
||
|
|
"epoch": 0.0553116769095698,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000472,
|
||
|
|
"loss": 7.1573,
|
||
|
|
"mean_token_accuracy": 0.09576819315552712,
|
||
|
|
"num_tokens": 1920526.0,
|
||
|
|
"step": 945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3511247634887695,
|
||
|
|
"epoch": 0.05560433128475271,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004745,
|
||
|
|
"loss": 7.1049,
|
||
|
|
"mean_token_accuracy": 0.09833246991038322,
|
||
|
|
"num_tokens": 1929884.0,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.348301696777344,
|
||
|
|
"epoch": 0.055896985659935616,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.000477,
|
||
|
|
"loss": 7.1044,
|
||
|
|
"mean_token_accuracy": 0.09435090646147729,
|
||
|
|
"num_tokens": 1940707.0,
|
||
|
|
"step": 955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.472948408126831,
|
||
|
|
"epoch": 0.056189640035118525,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004795,
|
||
|
|
"loss": 7.1739,
|
||
|
|
"mean_token_accuracy": 0.09039252474904061,
|
||
|
|
"num_tokens": 1951024.0,
|
||
|
|
"step": 960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3457207679748535,
|
||
|
|
"epoch": 0.056482294410301434,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.000482,
|
||
|
|
"loss": 7.0498,
|
||
|
|
"mean_token_accuracy": 0.09302077516913414,
|
||
|
|
"num_tokens": 1961553.0,
|
||
|
|
"step": 965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3738847255706785,
|
||
|
|
"epoch": 0.05677494878548434,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004845,
|
||
|
|
"loss": 7.1534,
|
||
|
|
"mean_token_accuracy": 0.09500665068626404,
|
||
|
|
"num_tokens": 1971297.0,
|
||
|
|
"step": 970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.282409811019898,
|
||
|
|
"epoch": 0.05706760316066725,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000487,
|
||
|
|
"loss": 7.0597,
|
||
|
|
"mean_token_accuracy": 0.09678901359438896,
|
||
|
|
"num_tokens": 1981753.0,
|
||
|
|
"step": 975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.471026945114136,
|
||
|
|
"epoch": 0.05736025753585016,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004895,
|
||
|
|
"loss": 7.1558,
|
||
|
|
"mean_token_accuracy": 0.10005593970417977,
|
||
|
|
"num_tokens": 1992590.0,
|
||
|
|
"step": 980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.350202465057373,
|
||
|
|
"epoch": 0.05765291191103307,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000492,
|
||
|
|
"loss": 7.1311,
|
||
|
|
"mean_token_accuracy": 0.09674226641654968,
|
||
|
|
"num_tokens": 2001745.0,
|
||
|
|
"step": 985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.262063264846802,
|
||
|
|
"epoch": 0.05794556628621598,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004945,
|
||
|
|
"loss": 7.0455,
|
||
|
|
"mean_token_accuracy": 0.09895217716693878,
|
||
|
|
"num_tokens": 2011171.0,
|
||
|
|
"step": 990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.362540626525879,
|
||
|
|
"epoch": 0.05823822066139889,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000497,
|
||
|
|
"loss": 7.0169,
|
||
|
|
"mean_token_accuracy": 0.0997674971818924,
|
||
|
|
"num_tokens": 2020732.0,
|
||
|
|
"step": 995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.338001441955567,
|
||
|
|
"epoch": 0.058530875036581796,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004995,
|
||
|
|
"loss": 7.0761,
|
||
|
|
"mean_token_accuracy": 0.09528696537017822,
|
||
|
|
"num_tokens": 2030702.0,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.215022277832031,
|
||
|
|
"epoch": 0.058823529411764705,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000499998026082006,
|
||
|
|
"loss": 7.0855,
|
||
|
|
"mean_token_accuracy": 0.09225433394312858,
|
||
|
|
"num_tokens": 2040933.0,
|
||
|
|
"step": 1005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.375273084640503,
|
||
|
|
"epoch": 0.059116183786947614,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999900070995136,
|
||
|
|
"loss": 7.1447,
|
||
|
|
"mean_token_accuracy": 0.09505715742707252,
|
||
|
|
"num_tokens": 2051083.0,
|
||
|
|
"step": 1010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.354562759399414,
|
||
|
|
"epoch": 0.05940883816213052,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004999758199023239,
|
||
|
|
"loss": 7.0474,
|
||
|
|
"mean_token_accuracy": 0.09751659147441387,
|
||
|
|
"num_tokens": 2060290.0,
|
||
|
|
"step": 1015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2843845844268795,
|
||
|
|
"epoch": 0.05970149253731343,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0004999554648793858,
|
||
|
|
"loss": 7.0758,
|
||
|
|
"mean_token_accuracy": 0.10457687452435493,
|
||
|
|
"num_tokens": 2070537.0,
|
||
|
|
"step": 1020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.208773374557495,
|
||
|
|
"epoch": 0.05999414691249634,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999289425887425,
|
||
|
|
"loss": 7.0188,
|
||
|
|
"mean_token_accuracy": 0.09619513675570487,
|
||
|
|
"num_tokens": 2081020.0,
|
||
|
|
"step": 1025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.309514284133911,
|
||
|
|
"epoch": 0.06028680128767925,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004998962537575161,
|
||
|
|
"loss": 7.0259,
|
||
|
|
"mean_token_accuracy": 0.10205215588212013,
|
||
|
|
"num_tokens": 2090731.0,
|
||
|
|
"step": 1030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4033431053161625,
|
||
|
|
"epoch": 0.06057945566286216,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004998573992818874,
|
||
|
|
"loss": 7.1142,
|
||
|
|
"mean_token_accuracy": 0.09757147133350372,
|
||
|
|
"num_tokens": 2100248.0,
|
||
|
|
"step": 1035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.219016265869141,
|
||
|
|
"epoch": 0.06087211003804507,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004998123802270715,
|
||
|
|
"loss": 7.0196,
|
||
|
|
"mean_token_accuracy": 0.09904577806591988,
|
||
|
|
"num_tokens": 2110518.0,
|
||
|
|
"step": 1040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.363824844360352,
|
||
|
|
"epoch": 0.061164764413227976,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004997611978272886,
|
||
|
|
"loss": 7.0895,
|
||
|
|
"mean_token_accuracy": 0.0941918708384037,
|
||
|
|
"num_tokens": 2121424.0,
|
||
|
|
"step": 1045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.209250974655151,
|
||
|
|
"epoch": 0.061457418788410885,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004997038534857298,
|
||
|
|
"loss": 7.0093,
|
||
|
|
"mean_token_accuracy": 0.1055798962712288,
|
||
|
|
"num_tokens": 2130904.0,
|
||
|
|
"step": 1050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.318933916091919,
|
||
|
|
"epoch": 0.061750073163593794,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004996403487745194,
|
||
|
|
"loss": 7.0483,
|
||
|
|
"mean_token_accuracy": 0.10186817795038224,
|
||
|
|
"num_tokens": 2140710.0,
|
||
|
|
"step": 1055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.373817396163941,
|
||
|
|
"epoch": 0.0620427275387767,
|
||
|
|
"grad_norm": 1.4765625,
|
||
|
|
"learning_rate": 0.000499570685434671,
|
||
|
|
"loss": 7.1132,
|
||
|
|
"mean_token_accuracy": 0.0974596157670021,
|
||
|
|
"num_tokens": 2150767.0,
|
||
|
|
"step": 1060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.216788959503174,
|
||
|
|
"epoch": 0.06233538191395961,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004994948653760405,
|
||
|
|
"loss": 7.0526,
|
||
|
|
"mean_token_accuracy": 0.09709591269493104,
|
||
|
|
"num_tokens": 2161414.0,
|
||
|
|
"step": 1065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.242707395553589,
|
||
|
|
"epoch": 0.06262803628914253,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004994128906772729,
|
||
|
|
"loss": 6.9802,
|
||
|
|
"mean_token_accuracy": 0.10571711510419846,
|
||
|
|
"num_tokens": 2171960.0,
|
||
|
|
"step": 1070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.240592432022095,
|
||
|
|
"epoch": 0.06292069066432543,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.000499324763585746,
|
||
|
|
"loss": 6.9542,
|
||
|
|
"mean_token_accuracy": 0.09980396181344986,
|
||
|
|
"num_tokens": 2182344.0,
|
||
|
|
"step": 1075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.144010734558106,
|
||
|
|
"epoch": 0.06321334503950835,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004992304865175085,
|
||
|
|
"loss": 6.9743,
|
||
|
|
"mean_token_accuracy": 0.09961154088377952,
|
||
|
|
"num_tokens": 2194829.0,
|
||
|
|
"step": 1080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1723168849945065,
|
||
|
|
"epoch": 0.06350599941469125,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004991300620572138,
|
||
|
|
"loss": 6.9419,
|
||
|
|
"mean_token_accuracy": 0.10114665776491165,
|
||
|
|
"num_tokens": 2204662.0,
|
||
|
|
"step": 1085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.227386426925659,
|
||
|
|
"epoch": 0.06379865378987416,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004990234929580494,
|
||
|
|
"loss": 6.9674,
|
||
|
|
"mean_token_accuracy": 0.10895995870232582,
|
||
|
|
"num_tokens": 2213815.0,
|
||
|
|
"step": 1090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.223431777954102,
|
||
|
|
"epoch": 0.06409130816505706,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004989107821416609,
|
||
|
|
"loss": 6.9819,
|
||
|
|
"mean_token_accuracy": 0.10199102833867073,
|
||
|
|
"num_tokens": 2223026.0,
|
||
|
|
"step": 1095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.193548965454101,
|
||
|
|
"epoch": 0.06438396254023998,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004987919326980723,
|
||
|
|
"loss": 7.0315,
|
||
|
|
"mean_token_accuracy": 0.09989764392375947,
|
||
|
|
"num_tokens": 2233575.0,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.221850919723511,
|
||
|
|
"epoch": 0.06467661691542288,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004986669478856011,
|
||
|
|
"loss": 6.9146,
|
||
|
|
"mean_token_accuracy": 0.10782215669751168,
|
||
|
|
"num_tokens": 2244171.0,
|
||
|
|
"step": 1105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2020580768585205,
|
||
|
|
"epoch": 0.0649692712906058,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004985358311307688,
|
||
|
|
"loss": 6.9815,
|
||
|
|
"mean_token_accuracy": 0.0972609356045723,
|
||
|
|
"num_tokens": 2253972.0,
|
||
|
|
"step": 1110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1520631313323975,
|
||
|
|
"epoch": 0.0652619256657887,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004983985860282081,
|
||
|
|
"loss": 7.0108,
|
||
|
|
"mean_token_accuracy": 0.10005398914217949,
|
||
|
|
"num_tokens": 2264699.0,
|
||
|
|
"step": 1115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.216694593429565,
|
||
|
|
"epoch": 0.06555458004097162,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004982552163405623,
|
||
|
|
"loss": 6.9772,
|
||
|
|
"mean_token_accuracy": 0.10254745483398438,
|
||
|
|
"num_tokens": 2274894.0,
|
||
|
|
"step": 1120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.193087959289551,
|
||
|
|
"epoch": 0.06584723441615452,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004981057259983839,
|
||
|
|
"loss": 7.0038,
|
||
|
|
"mean_token_accuracy": 0.09882058501243592,
|
||
|
|
"num_tokens": 2285541.0,
|
||
|
|
"step": 1125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2195906162261965,
|
||
|
|
"epoch": 0.06613988879133743,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004979501191000262,
|
||
|
|
"loss": 6.9395,
|
||
|
|
"mean_token_accuracy": 0.10300094708800316,
|
||
|
|
"num_tokens": 2295443.0,
|
||
|
|
"step": 1130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.242094087600708,
|
||
|
|
"epoch": 0.06643254316652034,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004977883999115311,
|
||
|
|
"loss": 7.0233,
|
||
|
|
"mean_token_accuracy": 0.09846225753426552,
|
||
|
|
"num_tokens": 2306149.0,
|
||
|
|
"step": 1135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.102969694137573,
|
||
|
|
"epoch": 0.06672519754170325,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004976205728665113,
|
||
|
|
"loss": 6.9776,
|
||
|
|
"mean_token_accuracy": 0.09972455576062203,
|
||
|
|
"num_tokens": 2316589.0,
|
||
|
|
"step": 1140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.240374565124512,
|
||
|
|
"epoch": 0.06701785191688615,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004974466425660307,
|
||
|
|
"loss": 6.9679,
|
||
|
|
"mean_token_accuracy": 0.10801631659269333,
|
||
|
|
"num_tokens": 2326340.0,
|
||
|
|
"step": 1145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.192791986465454,
|
||
|
|
"epoch": 0.06731050629206907,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004972666137784759,
|
||
|
|
"loss": 6.9389,
|
||
|
|
"mean_token_accuracy": 0.10559422895312309,
|
||
|
|
"num_tokens": 2336078.0,
|
||
|
|
"step": 1150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1362364292144775,
|
||
|
|
"epoch": 0.06760316066725197,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004970804914394271,
|
||
|
|
"loss": 6.8247,
|
||
|
|
"mean_token_accuracy": 0.10476716533303261,
|
||
|
|
"num_tokens": 2346017.0,
|
||
|
|
"step": 1155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.143903064727783,
|
||
|
|
"epoch": 0.06789581504243489,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004968882806515225,
|
||
|
|
"loss": 6.9748,
|
||
|
|
"mean_token_accuracy": 0.09448844268918037,
|
||
|
|
"num_tokens": 2355970.0,
|
||
|
|
"step": 1160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.164862585067749,
|
||
|
|
"epoch": 0.06818846941761779,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004966899866843177,
|
||
|
|
"loss": 6.9061,
|
||
|
|
"mean_token_accuracy": 0.09887387901544571,
|
||
|
|
"num_tokens": 2366010.0,
|
||
|
|
"step": 1165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.173722934722901,
|
||
|
|
"epoch": 0.0684811237928007,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000496485614974142,
|
||
|
|
"loss": 6.9059,
|
||
|
|
"mean_token_accuracy": 0.10019839331507682,
|
||
|
|
"num_tokens": 2376431.0,
|
||
|
|
"step": 1170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.145708847045898,
|
||
|
|
"epoch": 0.0687737781679836,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004962751711239492,
|
||
|
|
"loss": 6.9018,
|
||
|
|
"mean_token_accuracy": 0.10499030724167824,
|
||
|
|
"num_tokens": 2387027.0,
|
||
|
|
"step": 1175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.116997337341308,
|
||
|
|
"epoch": 0.06906643254316652,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004960586609031636,
|
||
|
|
"loss": 6.9054,
|
||
|
|
"mean_token_accuracy": 0.10259901955723763,
|
||
|
|
"num_tokens": 2396746.0,
|
||
|
|
"step": 1180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.146070146560669,
|
||
|
|
"epoch": 0.06935908691834942,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004958360902475224,
|
||
|
|
"loss": 6.917,
|
||
|
|
"mean_token_accuracy": 0.10224924832582474,
|
||
|
|
"num_tokens": 2406340.0,
|
||
|
|
"step": 1185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.133272552490235,
|
||
|
|
"epoch": 0.06965174129353234,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004956074652589125,
|
||
|
|
"loss": 6.9518,
|
||
|
|
"mean_token_accuracy": 0.10214994624257087,
|
||
|
|
"num_tokens": 2417441.0,
|
||
|
|
"step": 1190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.15489559173584,
|
||
|
|
"epoch": 0.06994439566871524,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004953727922052035,
|
||
|
|
"loss": 6.843,
|
||
|
|
"mean_token_accuracy": 0.10828633531928063,
|
||
|
|
"num_tokens": 2427365.0,
|
||
|
|
"step": 1195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.020367860794067,
|
||
|
|
"epoch": 0.07023705004389816,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004951320775200756,
|
||
|
|
"loss": 6.8627,
|
||
|
|
"mean_token_accuracy": 0.10394505336880684,
|
||
|
|
"num_tokens": 2437236.0,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1537285327911375,
|
||
|
|
"epoch": 0.07052970441908106,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004948853278028436,
|
||
|
|
"loss": 6.9642,
|
||
|
|
"mean_token_accuracy": 0.09915822148323059,
|
||
|
|
"num_tokens": 2448000.0,
|
||
|
|
"step": 1205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.071624374389648,
|
||
|
|
"epoch": 0.07082235879426398,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004946325498182755,
|
||
|
|
"loss": 6.8886,
|
||
|
|
"mean_token_accuracy": 0.10841592401266098,
|
||
|
|
"num_tokens": 2458627.0,
|
||
|
|
"step": 1210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.154271030426026,
|
||
|
|
"epoch": 0.07111501316944688,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004943737504964076,
|
||
|
|
"loss": 6.8187,
|
||
|
|
"mean_token_accuracy": 0.11104752346873284,
|
||
|
|
"num_tokens": 2468110.0,
|
||
|
|
"step": 1215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.091701221466065,
|
||
|
|
"epoch": 0.0714076675446298,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.000494108936932354,
|
||
|
|
"loss": 6.9753,
|
||
|
|
"mean_token_accuracy": 0.09984883964061737,
|
||
|
|
"num_tokens": 2479527.0,
|
||
|
|
"step": 1220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.113129329681397,
|
||
|
|
"epoch": 0.0717003219198127,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004938381163861124,
|
||
|
|
"loss": 6.857,
|
||
|
|
"mean_token_accuracy": 0.11230505779385566,
|
||
|
|
"num_tokens": 2489856.0,
|
||
|
|
"step": 1225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.067525911331177,
|
||
|
|
"epoch": 0.07199297629499561,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004935612962823645,
|
||
|
|
"loss": 6.9131,
|
||
|
|
"mean_token_accuracy": 0.10126614049077035,
|
||
|
|
"num_tokens": 2500164.0,
|
||
|
|
"step": 1230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.203033304214477,
|
||
|
|
"epoch": 0.07228563067017851,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004932784842102739,
|
||
|
|
"loss": 6.9133,
|
||
|
|
"mean_token_accuracy": 0.10488039031624793,
|
||
|
|
"num_tokens": 2510535.0,
|
||
|
|
"step": 1235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.032154607772827,
|
||
|
|
"epoch": 0.07257828504536143,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004929896879232758,
|
||
|
|
"loss": 6.8737,
|
||
|
|
"mean_token_accuracy": 0.10379046872258187,
|
||
|
|
"num_tokens": 2521334.0,
|
||
|
|
"step": 1240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.104176473617554,
|
||
|
|
"epoch": 0.07287093942054433,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004926949153388668,
|
||
|
|
"loss": 6.8486,
|
||
|
|
"mean_token_accuracy": 0.10444203391671181,
|
||
|
|
"num_tokens": 2531990.0,
|
||
|
|
"step": 1245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.063020420074463,
|
||
|
|
"epoch": 0.07316359379572725,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004923941745383859,
|
||
|
|
"loss": 6.9315,
|
||
|
|
"mean_token_accuracy": 0.10278217419981957,
|
||
|
|
"num_tokens": 2542418.0,
|
||
|
|
"step": 1250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.165763187408447,
|
||
|
|
"epoch": 0.07345624817091015,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.000492087473766794,
|
||
|
|
"loss": 6.9004,
|
||
|
|
"mean_token_accuracy": 0.10728387162089348,
|
||
|
|
"num_tokens": 2553944.0,
|
||
|
|
"step": 1255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.088944149017334,
|
||
|
|
"epoch": 0.07374890254609306,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.000491774821432448,
|
||
|
|
"loss": 6.8639,
|
||
|
|
"mean_token_accuracy": 0.10208542868494988,
|
||
|
|
"num_tokens": 2564577.0,
|
||
|
|
"step": 1260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.134335517883301,
|
||
|
|
"epoch": 0.07404155692127597,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004914562261068693,
|
||
|
|
"loss": 6.9696,
|
||
|
|
"mean_token_accuracy": 0.09385665506124496,
|
||
|
|
"num_tokens": 2574003.0,
|
||
|
|
"step": 1265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.100490999221802,
|
||
|
|
"epoch": 0.07433421129645888,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004911316965245098,
|
||
|
|
"loss": 6.8053,
|
||
|
|
"mean_token_accuracy": 0.10951183810830116,
|
||
|
|
"num_tokens": 2585367.0,
|
||
|
|
"step": 1270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.030397129058838,
|
||
|
|
"epoch": 0.07462686567164178,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.000490801241582512,
|
||
|
|
"loss": 6.7917,
|
||
|
|
"mean_token_accuracy": 0.10875893980264664,
|
||
|
|
"num_tokens": 2595282.0,
|
||
|
|
"step": 1275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.015108489990235,
|
||
|
|
"epoch": 0.0749195200468247,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.000490464870340465,
|
||
|
|
"loss": 6.7653,
|
||
|
|
"mean_token_accuracy": 0.11425828039646149,
|
||
|
|
"num_tokens": 2605220.0,
|
||
|
|
"step": 1280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.989345264434815,
|
||
|
|
"epoch": 0.0752121744220076,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004901225920201563,
|
||
|
|
"loss": 6.8498,
|
||
|
|
"mean_token_accuracy": 0.10785233229398727,
|
||
|
|
"num_tokens": 2616492.0,
|
||
|
|
"step": 1285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.082758522033691,
|
||
|
|
"epoch": 0.07550482879719052,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000489774416005319,
|
||
|
|
"loss": 6.8475,
|
||
|
|
"mean_token_accuracy": 0.10241246297955513,
|
||
|
|
"num_tokens": 2626133.0,
|
||
|
|
"step": 1290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.978100776672363,
|
||
|
|
"epoch": 0.07579748317237343,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004894203518413742,
|
||
|
|
"loss": 6.8281,
|
||
|
|
"mean_token_accuracy": 0.10710375010967255,
|
||
|
|
"num_tokens": 2636661.0,
|
||
|
|
"step": 1295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.118194580078125,
|
||
|
|
"epoch": 0.07609013754755634,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004890604092351701,
|
||
|
|
"loss": 6.8386,
|
||
|
|
"mean_token_accuracy": 0.10455987602472305,
|
||
|
|
"num_tokens": 2647598.0,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.000920104980469,
|
||
|
|
"epoch": 0.07638279192273925,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000488694598054715,
|
||
|
|
"loss": 6.7492,
|
||
|
|
"mean_token_accuracy": 0.10895679742097855,
|
||
|
|
"num_tokens": 2657267.0,
|
||
|
|
"step": 1305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.016765689849853,
|
||
|
|
"epoch": 0.07667544629792215,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004883229283289071,
|
||
|
|
"loss": 6.8488,
|
||
|
|
"mean_token_accuracy": 0.11024482920765877,
|
||
|
|
"num_tokens": 2667048.0,
|
||
|
|
"step": 1310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.150480651855469,
|
||
|
|
"epoch": 0.07696810067310507,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00048794541024725993,
|
||
|
|
"loss": 6.8433,
|
||
|
|
"mean_token_accuracy": 0.09998077973723411,
|
||
|
|
"num_tokens": 2677386.0,
|
||
|
|
"step": 1315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.942998266220092,
|
||
|
|
"epoch": 0.07726075504828797,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004875620541596221,
|
||
|
|
"loss": 6.8162,
|
||
|
|
"mean_token_accuracy": 0.10883545204997062,
|
||
|
|
"num_tokens": 2687655.0,
|
||
|
|
"step": 1320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.089137840270996,
|
||
|
|
"epoch": 0.07755340942347089,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00048717287057589454,
|
||
|
|
"loss": 6.8018,
|
||
|
|
"mean_token_accuracy": 0.11154846027493477,
|
||
|
|
"num_tokens": 2698098.0,
|
||
|
|
"step": 1325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.039312267303467,
|
||
|
|
"epoch": 0.07784606379865379,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004867778701657417,
|
||
|
|
"loss": 6.7993,
|
||
|
|
"mean_token_accuracy": 0.10543053150177002,
|
||
|
|
"num_tokens": 2708119.0,
|
||
|
|
"step": 1330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.011804723739624,
|
||
|
|
"epoch": 0.0781387181738367,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.00048637706375829955,
|
||
|
|
"loss": 6.7769,
|
||
|
|
"mean_token_accuracy": 0.11111046820878982,
|
||
|
|
"num_tokens": 2717036.0,
|
||
|
|
"step": 1335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.052466917037964,
|
||
|
|
"epoch": 0.0784313725490196,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.000485970462341878,
|
||
|
|
"loss": 6.9079,
|
||
|
|
"mean_token_accuracy": 0.10972103923559189,
|
||
|
|
"num_tokens": 2728290.0,
|
||
|
|
"step": 1340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.033558797836304,
|
||
|
|
"epoch": 0.07872402692420252,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00048555807706366044,
|
||
|
|
"loss": 6.8055,
|
||
|
|
"mean_token_accuracy": 0.1085546374320984,
|
||
|
|
"num_tokens": 2738373.0,
|
||
|
|
"step": 1345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0267448902130125,
|
||
|
|
"epoch": 0.07901668129938542,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00048513991922939756,
|
||
|
|
"loss": 6.8276,
|
||
|
|
"mean_token_accuracy": 0.11423720940947532,
|
||
|
|
"num_tokens": 2748232.0,
|
||
|
|
"step": 1350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0601318359375,
|
||
|
|
"epoch": 0.07930933567456834,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.00048471600030309744,
|
||
|
|
"loss": 6.8273,
|
||
|
|
"mean_token_accuracy": 0.10952704623341561,
|
||
|
|
"num_tokens": 2758138.0,
|
||
|
|
"step": 1355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.004944372177124,
|
||
|
|
"epoch": 0.07960199004975124,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.00048428633190671186,
|
||
|
|
"loss": 6.7868,
|
||
|
|
"mean_token_accuracy": 0.11433181166648865,
|
||
|
|
"num_tokens": 2768497.0,
|
||
|
|
"step": 1360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.992530298233032,
|
||
|
|
"epoch": 0.07989464442493416,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004838509258198167,
|
||
|
|
"loss": 6.8227,
|
||
|
|
"mean_token_accuracy": 0.10943501815199852,
|
||
|
|
"num_tokens": 2778956.0,
|
||
|
|
"step": 1365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0625303268432615,
|
||
|
|
"epoch": 0.08018729880011706,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.00048340979397929,
|
||
|
|
"loss": 6.7757,
|
||
|
|
"mean_token_accuracy": 0.11099240705370902,
|
||
|
|
"num_tokens": 2788295.0,
|
||
|
|
"step": 1370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.017833948135376,
|
||
|
|
"epoch": 0.08047995317529998,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00048296294847898386,
|
||
|
|
"loss": 6.7851,
|
||
|
|
"mean_token_accuracy": 0.10521746203303337,
|
||
|
|
"num_tokens": 2797736.0,
|
||
|
|
"step": 1375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.936165142059326,
|
||
|
|
"epoch": 0.08077260755048288,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004825104015693934,
|
||
|
|
"loss": 6.6646,
|
||
|
|
"mean_token_accuracy": 0.11661427244544029,
|
||
|
|
"num_tokens": 2806933.0,
|
||
|
|
"step": 1380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9978080749511715,
|
||
|
|
"epoch": 0.0810652619256658,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004820521656573208,
|
||
|
|
"loss": 6.829,
|
||
|
|
"mean_token_accuracy": 0.10937268137931824,
|
||
|
|
"num_tokens": 2817471.0,
|
||
|
|
"step": 1385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.003310823440552,
|
||
|
|
"epoch": 0.0813579163008487,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00048158825330553505,
|
||
|
|
"loss": 6.9589,
|
||
|
|
"mean_token_accuracy": 0.10846946313977242,
|
||
|
|
"num_tokens": 2828016.0,
|
||
|
|
"step": 1390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.050713396072387,
|
||
|
|
"epoch": 0.08165057067603161,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00048111867723242763,
|
||
|
|
"loss": 6.7987,
|
||
|
|
"mean_token_accuracy": 0.10719454810023307,
|
||
|
|
"num_tokens": 2838011.0,
|
||
|
|
"step": 1395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.951278257369995,
|
||
|
|
"epoch": 0.08194322505121451,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004806434503116637,
|
||
|
|
"loss": 6.68,
|
||
|
|
"mean_token_accuracy": 0.11497046947479247,
|
||
|
|
"num_tokens": 2848281.0,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.931306600570679,
|
||
|
|
"epoch": 0.08223587942639743,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004801625855718296,
|
||
|
|
"loss": 6.7977,
|
||
|
|
"mean_token_accuracy": 0.11288361549377442,
|
||
|
|
"num_tokens": 2859338.0,
|
||
|
|
"step": 1405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.084950971603393,
|
||
|
|
"epoch": 0.08252853380158033,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00047967609619607477,
|
||
|
|
"loss": 6.7972,
|
||
|
|
"mean_token_accuracy": 0.1125359758734703,
|
||
|
|
"num_tokens": 2869238.0,
|
||
|
|
"step": 1410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.982119035720825,
|
||
|
|
"epoch": 0.08282118817676325,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004791839955217513,
|
||
|
|
"loss": 6.7834,
|
||
|
|
"mean_token_accuracy": 0.1123705931007862,
|
||
|
|
"num_tokens": 2879312.0,
|
||
|
|
"step": 1415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.892581462860107,
|
||
|
|
"epoch": 0.08311384255194615,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.00047868629704004786,
|
||
|
|
"loss": 6.7231,
|
||
|
|
"mean_token_accuracy": 0.10808718279004097,
|
||
|
|
"num_tokens": 2888974.0,
|
||
|
|
"step": 1420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.027051877975464,
|
||
|
|
"epoch": 0.08340649692712906,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00047818301439561965,
|
||
|
|
"loss": 6.7598,
|
||
|
|
"mean_token_accuracy": 0.1084697999060154,
|
||
|
|
"num_tokens": 2899501.0,
|
||
|
|
"step": 1425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.986096715927124,
|
||
|
|
"epoch": 0.08369915130231197,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.00047767416138621454,
|
||
|
|
"loss": 6.7968,
|
||
|
|
"mean_token_accuracy": 0.10647018775343894,
|
||
|
|
"num_tokens": 2909210.0,
|
||
|
|
"step": 1430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.951934385299682,
|
||
|
|
"epoch": 0.08399180567749488,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000477159751962295,
|
||
|
|
"loss": 6.7246,
|
||
|
|
"mean_token_accuracy": 0.10852879583835602,
|
||
|
|
"num_tokens": 2919470.0,
|
||
|
|
"step": 1435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.909590435028076,
|
||
|
|
"epoch": 0.08428446005267778,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00047663980022665507,
|
||
|
|
"loss": 6.6972,
|
||
|
|
"mean_token_accuracy": 0.1139543168246746,
|
||
|
|
"num_tokens": 2929526.0,
|
||
|
|
"step": 1440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.91973295211792,
|
||
|
|
"epoch": 0.0845771144278607,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00047611432043403437,
|
||
|
|
"loss": 6.7107,
|
||
|
|
"mean_token_accuracy": 0.1111906498670578,
|
||
|
|
"num_tokens": 2938944.0,
|
||
|
|
"step": 1445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.030971336364746,
|
||
|
|
"epoch": 0.0848697688030436,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004755833269907267,
|
||
|
|
"loss": 6.7415,
|
||
|
|
"mean_token_accuracy": 0.11075187176465988,
|
||
|
|
"num_tokens": 2948334.0,
|
||
|
|
"step": 1450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.899282360076905,
|
||
|
|
"epoch": 0.08516242317822652,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004750468344541857,
|
||
|
|
"loss": 6.6948,
|
||
|
|
"mean_token_accuracy": 0.11553604677319526,
|
||
|
|
"num_tokens": 2957687.0,
|
||
|
|
"step": 1455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.967754316329956,
|
||
|
|
"epoch": 0.08545507755340942,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00047450485753262525,
|
||
|
|
"loss": 6.6961,
|
||
|
|
"mean_token_accuracy": 0.11643371209502221,
|
||
|
|
"num_tokens": 2968291.0,
|
||
|
|
"step": 1460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.844262170791626,
|
||
|
|
"epoch": 0.08574773192859234,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00047395741108461633,
|
||
|
|
"loss": 6.6833,
|
||
|
|
"mean_token_accuracy": 0.11676188111305237,
|
||
|
|
"num_tokens": 2978809.0,
|
||
|
|
"step": 1465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.051819658279419,
|
||
|
|
"epoch": 0.08604038630377524,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00047340451011867985,
|
||
|
|
"loss": 6.828,
|
||
|
|
"mean_token_accuracy": 0.10943237319588661,
|
||
|
|
"num_tokens": 2988839.0,
|
||
|
|
"step": 1470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.964070463180542,
|
||
|
|
"epoch": 0.08633304067895815,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00047284616979287515,
|
||
|
|
"loss": 6.7741,
|
||
|
|
"mean_token_accuracy": 0.11031899750232696,
|
||
|
|
"num_tokens": 2999380.0,
|
||
|
|
"step": 1475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.931664991378784,
|
||
|
|
"epoch": 0.08662569505414106,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.00047228240541438433,
|
||
|
|
"loss": 6.6807,
|
||
|
|
"mean_token_accuracy": 0.11252299547195435,
|
||
|
|
"num_tokens": 3009298.0,
|
||
|
|
"step": 1480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.891529750823975,
|
||
|
|
"epoch": 0.08691834942932397,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.00047171323243909257,
|
||
|
|
"loss": 6.6839,
|
||
|
|
"mean_token_accuracy": 0.11446837261319161,
|
||
|
|
"num_tokens": 3019747.0,
|
||
|
|
"step": 1485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.922841024398804,
|
||
|
|
"epoch": 0.08721100380450687,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00047113866647116457,
|
||
|
|
"loss": 6.6891,
|
||
|
|
"mean_token_accuracy": 0.11496640294790268,
|
||
|
|
"num_tokens": 3029777.0,
|
||
|
|
"step": 1490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.863205766677856,
|
||
|
|
"epoch": 0.08750365817968979,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004705587232626164,
|
||
|
|
"loss": 6.8019,
|
||
|
|
"mean_token_accuracy": 0.10379430875182152,
|
||
|
|
"num_tokens": 3040184.0,
|
||
|
|
"step": 1495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.04589695930481,
|
||
|
|
"epoch": 0.08779631255487269,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00046997341871288424,
|
||
|
|
"loss": 6.6707,
|
||
|
|
"mean_token_accuracy": 0.1120702162384987,
|
||
|
|
"num_tokens": 3049183.0,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.905271196365357,
|
||
|
|
"epoch": 0.0880889669300556,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004693827688683879,
|
||
|
|
"loss": 6.6779,
|
||
|
|
"mean_token_accuracy": 0.11167440935969353,
|
||
|
|
"num_tokens": 3059102.0,
|
||
|
|
"step": 1505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.918920421600342,
|
||
|
|
"epoch": 0.08838162130523851,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004687867899220914,
|
||
|
|
"loss": 6.7624,
|
||
|
|
"mean_token_accuracy": 0.10838631615042686,
|
||
|
|
"num_tokens": 3069644.0,
|
||
|
|
"step": 1510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.977838325500488,
|
||
|
|
"epoch": 0.08867427568042142,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.00046818549821305846,
|
||
|
|
"loss": 6.7574,
|
||
|
|
"mean_token_accuracy": 0.10591690614819527,
|
||
|
|
"num_tokens": 3079299.0,
|
||
|
|
"step": 1515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.885261201858521,
|
||
|
|
"epoch": 0.08896693005560433,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.00046757891022600494,
|
||
|
|
"loss": 6.5884,
|
||
|
|
"mean_token_accuracy": 0.1182774156332016,
|
||
|
|
"num_tokens": 3088236.0,
|
||
|
|
"step": 1520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.761987543106079,
|
||
|
|
"epoch": 0.08925958443078724,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004669670425908471,
|
||
|
|
"loss": 6.6051,
|
||
|
|
"mean_token_accuracy": 0.12321883291006089,
|
||
|
|
"num_tokens": 3098657.0,
|
||
|
|
"step": 1525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.878669929504395,
|
||
|
|
"epoch": 0.08955223880597014,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004663499120822451,
|
||
|
|
"loss": 6.7157,
|
||
|
|
"mean_token_accuracy": 0.11686875000596046,
|
||
|
|
"num_tokens": 3109579.0,
|
||
|
|
"step": 1530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.951480770111084,
|
||
|
|
"epoch": 0.08984489318115306,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004657275356191437,
|
||
|
|
"loss": 6.6881,
|
||
|
|
"mean_token_accuracy": 0.12061331272125245,
|
||
|
|
"num_tokens": 3118464.0,
|
||
|
|
"step": 1535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.888629722595215,
|
||
|
|
"epoch": 0.09013754755633596,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.00046509993026430804,
|
||
|
|
"loss": 6.6855,
|
||
|
|
"mean_token_accuracy": 0.1155958354473114,
|
||
|
|
"num_tokens": 3128378.0,
|
||
|
|
"step": 1540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.916952276229859,
|
||
|
|
"epoch": 0.09043020193151888,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004644671132238558,
|
||
|
|
"loss": 6.6026,
|
||
|
|
"mean_token_accuracy": 0.1169995129108429,
|
||
|
|
"num_tokens": 3137334.0,
|
||
|
|
"step": 1545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.800655460357666,
|
||
|
|
"epoch": 0.09072285630670178,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00046382910184678585,
|
||
|
|
"loss": 6.6777,
|
||
|
|
"mean_token_accuracy": 0.10771318525075912,
|
||
|
|
"num_tokens": 3147173.0,
|
||
|
|
"step": 1550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.041066694259643,
|
||
|
|
"epoch": 0.0910155106818847,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004631859136245025,
|
||
|
|
"loss": 6.7158,
|
||
|
|
"mean_token_accuracy": 0.11159913316369056,
|
||
|
|
"num_tokens": 3158377.0,
|
||
|
|
"step": 1555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.773977136611938,
|
||
|
|
"epoch": 0.0913081650570676,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004625375661903357,
|
||
|
|
"loss": 6.6389,
|
||
|
|
"mean_token_accuracy": 0.11442811414599419,
|
||
|
|
"num_tokens": 3168126.0,
|
||
|
|
"step": 1560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.914021968841553,
|
||
|
|
"epoch": 0.09160081943225051,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00046188407731905787,
|
||
|
|
"loss": 6.6691,
|
||
|
|
"mean_token_accuracy": 0.11170838549733161,
|
||
|
|
"num_tokens": 3177517.0,
|
||
|
|
"step": 1565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.850327825546264,
|
||
|
|
"epoch": 0.09189347380743342,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.00046122546492639643,
|
||
|
|
"loss": 6.6788,
|
||
|
|
"mean_token_accuracy": 0.11249028444290161,
|
||
|
|
"num_tokens": 3188695.0,
|
||
|
|
"step": 1570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.923885011672974,
|
||
|
|
"epoch": 0.09218612818261633,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.000460561747068543,
|
||
|
|
"loss": 6.6452,
|
||
|
|
"mean_token_accuracy": 0.11729705110192298,
|
||
|
|
"num_tokens": 3199112.0,
|
||
|
|
"step": 1575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.860661792755127,
|
||
|
|
"epoch": 0.09247878255779923,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004598929419416578,
|
||
|
|
"loss": 6.7081,
|
||
|
|
"mean_token_accuracy": 0.11345864906907081,
|
||
|
|
"num_tokens": 3210806.0,
|
||
|
|
"step": 1580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.947086048126221,
|
||
|
|
"epoch": 0.09277143693298215,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00045921906788137123,
|
||
|
|
"loss": 6.6775,
|
||
|
|
"mean_token_accuracy": 0.11352947279810906,
|
||
|
|
"num_tokens": 3220492.0,
|
||
|
|
"step": 1585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.790587997436523,
|
||
|
|
"epoch": 0.09306409130816505,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00045854014336228115,
|
||
|
|
"loss": 6.6172,
|
||
|
|
"mean_token_accuracy": 0.12552082911133766,
|
||
|
|
"num_tokens": 3231181.0,
|
||
|
|
"step": 1590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8179422378540036,
|
||
|
|
"epoch": 0.09335674568334797,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.00045785618699744615,
|
||
|
|
"loss": 6.6511,
|
||
|
|
"mean_token_accuracy": 0.11615164056420327,
|
||
|
|
"num_tokens": 3241774.0,
|
||
|
|
"step": 1595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.899714183807373,
|
||
|
|
"epoch": 0.09364940005853087,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.00045716721753787543,
|
||
|
|
"loss": 6.6428,
|
||
|
|
"mean_token_accuracy": 0.12186415120959282,
|
||
|
|
"num_tokens": 3252893.0,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8200184345245365,
|
||
|
|
"epoch": 0.09394205443371378,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004564732538720148,
|
||
|
|
"loss": 6.7214,
|
||
|
|
"mean_token_accuracy": 0.11590429842472076,
|
||
|
|
"num_tokens": 3263003.0,
|
||
|
|
"step": 1605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.955989170074463,
|
||
|
|
"epoch": 0.09423470880889669,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00045577431502522877,
|
||
|
|
"loss": 6.7006,
|
||
|
|
"mean_token_accuracy": 0.11095896661281586,
|
||
|
|
"num_tokens": 3273034.0,
|
||
|
|
"step": 1610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.817434358596802,
|
||
|
|
"epoch": 0.0945273631840796,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004550704201592787,
|
||
|
|
"loss": 6.5645,
|
||
|
|
"mean_token_accuracy": 0.12096277251839638,
|
||
|
|
"num_tokens": 3282708.0,
|
||
|
|
"step": 1615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.91120400428772,
|
||
|
|
"epoch": 0.09482001755926252,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004543615885717981,
|
||
|
|
"loss": 6.707,
|
||
|
|
"mean_token_accuracy": 0.11070387437939644,
|
||
|
|
"num_tokens": 3293339.0,
|
||
|
|
"step": 1620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8873271465301515,
|
||
|
|
"epoch": 0.09511267193444542,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.00045364783969576296,
|
||
|
|
"loss": 6.5973,
|
||
|
|
"mean_token_accuracy": 0.12349895909428596,
|
||
|
|
"num_tokens": 3303258.0,
|
||
|
|
"step": 1625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.879426050186157,
|
||
|
|
"epoch": 0.09540532630962834,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004529291930989592,
|
||
|
|
"loss": 6.6385,
|
||
|
|
"mean_token_accuracy": 0.11417820826172828,
|
||
|
|
"num_tokens": 3314406.0,
|
||
|
|
"step": 1630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.76143479347229,
|
||
|
|
"epoch": 0.09569798068481124,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004522056684834464,
|
||
|
|
"loss": 6.6133,
|
||
|
|
"mean_token_accuracy": 0.12064159885048867,
|
||
|
|
"num_tokens": 3324517.0,
|
||
|
|
"step": 1635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.818144226074219,
|
||
|
|
"epoch": 0.09599063505999415,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004514772856850173,
|
||
|
|
"loss": 6.6235,
|
||
|
|
"mean_token_accuracy": 0.11605716720223427,
|
||
|
|
"num_tokens": 3334142.0,
|
||
|
|
"step": 1640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8202917098999025,
|
||
|
|
"epoch": 0.09628328943517706,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004507440646726542,
|
||
|
|
"loss": 6.5914,
|
||
|
|
"mean_token_accuracy": 0.12046833410859108,
|
||
|
|
"num_tokens": 3343839.0,
|
||
|
|
"step": 1645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.864968967437744,
|
||
|
|
"epoch": 0.09657594381035997,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004500060255479818,
|
||
|
|
"loss": 6.565,
|
||
|
|
"mean_token_accuracy": 0.11778617948293686,
|
||
|
|
"num_tokens": 3353343.0,
|
||
|
|
"step": 1650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.857561302185059,
|
||
|
|
"epoch": 0.09686859818554287,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004492631885447151,
|
||
|
|
"loss": 6.6513,
|
||
|
|
"mean_token_accuracy": 0.10677931159734726,
|
||
|
|
"num_tokens": 3363998.0,
|
||
|
|
"step": 1655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.783181810379029,
|
||
|
|
"epoch": 0.09716125256072579,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.00044851557402810616,
|
||
|
|
"loss": 6.5557,
|
||
|
|
"mean_token_accuracy": 0.12009415850043297,
|
||
|
|
"num_tokens": 3373359.0,
|
||
|
|
"step": 1660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.807691192626953,
|
||
|
|
"epoch": 0.09745390693590869,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.00044776320249438444,
|
||
|
|
"loss": 6.6102,
|
||
|
|
"mean_token_accuracy": 0.11330483928322792,
|
||
|
|
"num_tokens": 3383590.0,
|
||
|
|
"step": 1665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.794376420974731,
|
||
|
|
"epoch": 0.0977465613110916,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.00044700609457019565,
|
||
|
|
"loss": 6.588,
|
||
|
|
"mean_token_accuracy": 0.11675243452191353,
|
||
|
|
"num_tokens": 3394698.0,
|
||
|
|
"step": 1670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.874130582809448,
|
||
|
|
"epoch": 0.09803921568627451,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004462442710120359,
|
||
|
|
"loss": 6.6664,
|
||
|
|
"mean_token_accuracy": 0.114612428098917,
|
||
|
|
"num_tokens": 3404454.0,
|
||
|
|
"step": 1675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.797354125976563,
|
||
|
|
"epoch": 0.09833187006145742,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000445477752705683,
|
||
|
|
"loss": 6.574,
|
||
|
|
"mean_token_accuracy": 0.11949797347187996,
|
||
|
|
"num_tokens": 3413759.0,
|
||
|
|
"step": 1680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.820459985733033,
|
||
|
|
"epoch": 0.09862452443664033,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.00044470656066562336,
|
||
|
|
"loss": 6.6051,
|
||
|
|
"mean_token_accuracy": 0.11495016440749169,
|
||
|
|
"num_tokens": 3424824.0,
|
||
|
|
"step": 1685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.85875768661499,
|
||
|
|
"epoch": 0.09891717881182324,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004439307160344765,
|
||
|
|
"loss": 6.6359,
|
||
|
|
"mean_token_accuracy": 0.11889533028006553,
|
||
|
|
"num_tokens": 3434735.0,
|
||
|
|
"step": 1690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.809335947036743,
|
||
|
|
"epoch": 0.09920983318700614,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00044315024008241473,
|
||
|
|
"loss": 6.5877,
|
||
|
|
"mean_token_accuracy": 0.12204827964305878,
|
||
|
|
"num_tokens": 3443866.0,
|
||
|
|
"step": 1695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.801813983917237,
|
||
|
|
"epoch": 0.09950248756218906,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004423651542065806,
|
||
|
|
"loss": 6.6343,
|
||
|
|
"mean_token_accuracy": 0.11169317811727524,
|
||
|
|
"num_tokens": 3454875.0,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.84343409538269,
|
||
|
|
"epoch": 0.09979514193737196,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.00044157547993050006,
|
||
|
|
"loss": 6.5097,
|
||
|
|
"mean_token_accuracy": 0.11645138636231422,
|
||
|
|
"num_tokens": 3465035.0,
|
||
|
|
"step": 1705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.770152282714844,
|
||
|
|
"epoch": 0.10008779631255488,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.00044078123890349227,
|
||
|
|
"loss": 6.5561,
|
||
|
|
"mean_token_accuracy": 0.11913573890924453,
|
||
|
|
"num_tokens": 3475905.0,
|
||
|
|
"step": 1710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.872724533081055,
|
||
|
|
"epoch": 0.10038045068773778,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00043998245290007606,
|
||
|
|
"loss": 6.6297,
|
||
|
|
"mean_token_accuracy": 0.11756439507007599,
|
||
|
|
"num_tokens": 3486622.0,
|
||
|
|
"step": 1715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7361010074615475,
|
||
|
|
"epoch": 0.1006731050629207,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00043917914381937323,
|
||
|
|
"loss": 6.5647,
|
||
|
|
"mean_token_accuracy": 0.11896469891071319,
|
||
|
|
"num_tokens": 3496683.0,
|
||
|
|
"step": 1720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.839031124114991,
|
||
|
|
"epoch": 0.1009657594381036,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.00043837133368450815,
|
||
|
|
"loss": 6.5267,
|
||
|
|
"mean_token_accuracy": 0.12196119725704194,
|
||
|
|
"num_tokens": 3507265.0,
|
||
|
|
"step": 1725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.790427541732788,
|
||
|
|
"epoch": 0.10125841381328651,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004375590446420037,
|
||
|
|
"loss": 6.5435,
|
||
|
|
"mean_token_accuracy": 0.11487171053886414,
|
||
|
|
"num_tokens": 3516687.0,
|
||
|
|
"step": 1730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.776448488235474,
|
||
|
|
"epoch": 0.10155106818846941,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004367422989611743,
|
||
|
|
"loss": 6.586,
|
||
|
|
"mean_token_accuracy": 0.11656711176037789,
|
||
|
|
"num_tokens": 3526257.0,
|
||
|
|
"step": 1735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.787727308273316,
|
||
|
|
"epoch": 0.10184372256365233,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004359211190335153,
|
||
|
|
"loss": 6.5154,
|
||
|
|
"mean_token_accuracy": 0.1232883483171463,
|
||
|
|
"num_tokens": 3536467.0,
|
||
|
|
"step": 1740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.754599905014038,
|
||
|
|
"epoch": 0.10213637693883523,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.00043509552737208923,
|
||
|
|
"loss": 6.5504,
|
||
|
|
"mean_token_accuracy": 0.1269164949655533,
|
||
|
|
"num_tokens": 3546852.0,
|
||
|
|
"step": 1745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.800959062576294,
|
||
|
|
"epoch": 0.10242903131401815,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00043426554661090853,
|
||
|
|
"loss": 6.6378,
|
||
|
|
"mean_token_accuracy": 0.11459514498710632,
|
||
|
|
"num_tokens": 3557519.0,
|
||
|
|
"step": 1750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.921309089660644,
|
||
|
|
"epoch": 0.10272168568920105,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00043343119950431516,
|
||
|
|
"loss": 6.6225,
|
||
|
|
"mean_token_accuracy": 0.11688102856278419,
|
||
|
|
"num_tokens": 3567905.0,
|
||
|
|
"step": 1755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.786648559570312,
|
||
|
|
"epoch": 0.10301434006438397,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.00043259250892635644,
|
||
|
|
"loss": 6.5817,
|
||
|
|
"mean_token_accuracy": 0.1215607538819313,
|
||
|
|
"num_tokens": 3579529.0,
|
||
|
|
"step": 1760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.802842855453491,
|
||
|
|
"epoch": 0.10330699443956687,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004317494978701582,
|
||
|
|
"loss": 6.5018,
|
||
|
|
"mean_token_accuracy": 0.12014774978160858,
|
||
|
|
"num_tokens": 3589075.0,
|
||
|
|
"step": 1765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.729494094848633,
|
||
|
|
"epoch": 0.10359964881474978,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004309021894472943,
|
||
|
|
"loss": 6.5588,
|
||
|
|
"mean_token_accuracy": 0.11801389381289482,
|
||
|
|
"num_tokens": 3599093.0,
|
||
|
|
"step": 1770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.733899641036987,
|
||
|
|
"epoch": 0.10389230318993269,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004300506068871534,
|
||
|
|
"loss": 6.5143,
|
||
|
|
"mean_token_accuracy": 0.11827743500471115,
|
||
|
|
"num_tokens": 3609587.0,
|
||
|
|
"step": 1775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.725184535980224,
|
||
|
|
"epoch": 0.1041849575651156,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00042919477353630135,
|
||
|
|
"loss": 6.6055,
|
||
|
|
"mean_token_accuracy": 0.11462670415639878,
|
||
|
|
"num_tokens": 3620228.0,
|
||
|
|
"step": 1780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.799921178817749,
|
||
|
|
"epoch": 0.1044776119402985,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.000428334712857842,
|
||
|
|
"loss": 6.5223,
|
||
|
|
"mean_token_accuracy": 0.12408804297447204,
|
||
|
|
"num_tokens": 3630093.0,
|
||
|
|
"step": 1785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7759123802185055,
|
||
|
|
"epoch": 0.10477026631548142,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.00042747044843077304,
|
||
|
|
"loss": 6.566,
|
||
|
|
"mean_token_accuracy": 0.11505624055862426,
|
||
|
|
"num_tokens": 3640405.0,
|
||
|
|
"step": 1790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.689677095413208,
|
||
|
|
"epoch": 0.10506292069066432,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00042660200394934047,
|
||
|
|
"loss": 6.4802,
|
||
|
|
"mean_token_accuracy": 0.11899327635765075,
|
||
|
|
"num_tokens": 3651001.0,
|
||
|
|
"step": 1795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.871759557723999,
|
||
|
|
"epoch": 0.10535557506584724,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.00042572940322238844,
|
||
|
|
"loss": 6.5688,
|
||
|
|
"mean_token_accuracy": 0.12120393961668015,
|
||
|
|
"num_tokens": 3661024.0,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.759112310409546,
|
||
|
|
"epoch": 0.10564822944103014,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.00042485267017270664,
|
||
|
|
"loss": 6.5589,
|
||
|
|
"mean_token_accuracy": 0.11904018670320511,
|
||
|
|
"num_tokens": 3671271.0,
|
||
|
|
"step": 1805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.795577955245972,
|
||
|
|
"epoch": 0.10594088381621306,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004239718288363745,
|
||
|
|
"loss": 6.5798,
|
||
|
|
"mean_token_accuracy": 0.11667552590370178,
|
||
|
|
"num_tokens": 3682569.0,
|
||
|
|
"step": 1810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.818081903457641,
|
||
|
|
"epoch": 0.10623353819139596,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004230869033621023,
|
||
|
|
"loss": 6.5103,
|
||
|
|
"mean_token_accuracy": 0.12421332746744156,
|
||
|
|
"num_tokens": 3692056.0,
|
||
|
|
"step": 1815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.755850028991699,
|
||
|
|
"epoch": 0.10652619256657887,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004221979180105688,
|
||
|
|
"loss": 6.5716,
|
||
|
|
"mean_token_accuracy": 0.11862044930458068,
|
||
|
|
"num_tokens": 3701828.0,
|
||
|
|
"step": 1820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.827340888977051,
|
||
|
|
"epoch": 0.10681884694176177,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00042130489715375645,
|
||
|
|
"loss": 6.5095,
|
||
|
|
"mean_token_accuracy": 0.1277923844754696,
|
||
|
|
"num_tokens": 3711831.0,
|
||
|
|
"step": 1825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.734691381454468,
|
||
|
|
"epoch": 0.10711150131694469,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00042040786527428335,
|
||
|
|
"loss": 6.5942,
|
||
|
|
"mean_token_accuracy": 0.11365615352988243,
|
||
|
|
"num_tokens": 3722381.0,
|
||
|
|
"step": 1830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.749592113494873,
|
||
|
|
"epoch": 0.10740415569212759,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004195068469647315,
|
||
|
|
"loss": 6.4872,
|
||
|
|
"mean_token_accuracy": 0.1262812778353691,
|
||
|
|
"num_tokens": 3732918.0,
|
||
|
|
"step": 1835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7778829574584964,
|
||
|
|
"epoch": 0.10769681006731051,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.00041860186692697297,
|
||
|
|
"loss": 6.4948,
|
||
|
|
"mean_token_accuracy": 0.12678161934018134,
|
||
|
|
"num_tokens": 3743721.0,
|
||
|
|
"step": 1840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.763736152648926,
|
||
|
|
"epoch": 0.10798946444249341,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.00041769294997149264,
|
||
|
|
"loss": 6.5414,
|
||
|
|
"mean_token_accuracy": 0.11694241538643838,
|
||
|
|
"num_tokens": 3754341.0,
|
||
|
|
"step": 1845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.701714754104614,
|
||
|
|
"epoch": 0.10828211881767633,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004167801210167081,
|
||
|
|
"loss": 6.5124,
|
||
|
|
"mean_token_accuracy": 0.12937195897102355,
|
||
|
|
"num_tokens": 3764461.0,
|
||
|
|
"step": 1850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.889769124984741,
|
||
|
|
"epoch": 0.10857477319285923,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004158634050882861,
|
||
|
|
"loss": 6.5552,
|
||
|
|
"mean_token_accuracy": 0.12245087251067162,
|
||
|
|
"num_tokens": 3774748.0,
|
||
|
|
"step": 1855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.711971855163574,
|
||
|
|
"epoch": 0.10886742756804214,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004149428273184569,
|
||
|
|
"loss": 6.52,
|
||
|
|
"mean_token_accuracy": 0.11850636452436447,
|
||
|
|
"num_tokens": 3785444.0,
|
||
|
|
"step": 1860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.649656295776367,
|
||
|
|
"epoch": 0.10916008194322505,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004140184129453253,
|
||
|
|
"loss": 6.4921,
|
||
|
|
"mean_token_accuracy": 0.12511781528592109,
|
||
|
|
"num_tokens": 3796097.0,
|
||
|
|
"step": 1865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.758572959899903,
|
||
|
|
"epoch": 0.10945273631840796,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000413090187312178,
|
||
|
|
"loss": 6.4889,
|
||
|
|
"mean_token_accuracy": 0.12226529717445374,
|
||
|
|
"num_tokens": 3806769.0,
|
||
|
|
"step": 1870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.712545776367188,
|
||
|
|
"epoch": 0.10974539069359086,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004121581758667898,
|
||
|
|
"loss": 6.4858,
|
||
|
|
"mean_token_accuracy": 0.12765528708696366,
|
||
|
|
"num_tokens": 3816576.0,
|
||
|
|
"step": 1875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.749814748764038,
|
||
|
|
"epoch": 0.11003804506877378,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.00041122240416072533,
|
||
|
|
"loss": 6.4622,
|
||
|
|
"mean_token_accuracy": 0.12702202945947647,
|
||
|
|
"num_tokens": 3826679.0,
|
||
|
|
"step": 1880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.743882846832276,
|
||
|
|
"epoch": 0.11033069944395668,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004102828978486385,
|
||
|
|
"loss": 6.4963,
|
||
|
|
"mean_token_accuracy": 0.12285473719239234,
|
||
|
|
"num_tokens": 3837511.0,
|
||
|
|
"step": 1885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.729692125320435,
|
||
|
|
"epoch": 0.1106233538191396,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0004093396826875695,
|
||
|
|
"loss": 6.4645,
|
||
|
|
"mean_token_accuracy": 0.11870746538043023,
|
||
|
|
"num_tokens": 3847929.0,
|
||
|
|
"step": 1890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.790079021453858,
|
||
|
|
"epoch": 0.1109160081943225,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00040839278453623837,
|
||
|
|
"loss": 6.5163,
|
||
|
|
"mean_token_accuracy": 0.12360096871852874,
|
||
|
|
"num_tokens": 3857460.0,
|
||
|
|
"step": 1895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.764287281036377,
|
||
|
|
"epoch": 0.11120866256950541,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004074422293543363,
|
||
|
|
"loss": 6.4899,
|
||
|
|
"mean_token_accuracy": 0.12144630774855614,
|
||
|
|
"num_tokens": 3868593.0,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.628063678741455,
|
||
|
|
"epoch": 0.11150131694468832,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004064880432018137,
|
||
|
|
"loss": 6.4806,
|
||
|
|
"mean_token_accuracy": 0.12284271195530891,
|
||
|
|
"num_tokens": 3879316.0,
|
||
|
|
"step": 1905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.735889911651611,
|
||
|
|
"epoch": 0.11179397131987123,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00040553025223816615,
|
||
|
|
"loss": 6.4028,
|
||
|
|
"mean_token_accuracy": 0.12710621505975722,
|
||
|
|
"num_tokens": 3888659.0,
|
||
|
|
"step": 1910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.699985361099243,
|
||
|
|
"epoch": 0.11208662569505413,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00040456888272171653,
|
||
|
|
"loss": 6.4641,
|
||
|
|
"mean_token_accuracy": 0.11733812615275382,
|
||
|
|
"num_tokens": 3899524.0,
|
||
|
|
"step": 1915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.791746997833252,
|
||
|
|
"epoch": 0.11237928007023705,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.00040360396100889577,
|
||
|
|
"loss": 6.5622,
|
||
|
|
"mean_token_accuracy": 0.11920542642474174,
|
||
|
|
"num_tokens": 3910600.0,
|
||
|
|
"step": 1920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.747242450714111,
|
||
|
|
"epoch": 0.11267193444541995,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004026355135535202,
|
||
|
|
"loss": 6.5661,
|
||
|
|
"mean_token_accuracy": 0.11491762548685074,
|
||
|
|
"num_tokens": 3920779.0,
|
||
|
|
"step": 1925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.702474117279053,
|
||
|
|
"epoch": 0.11296458882060287,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.000401663566906066,
|
||
|
|
"loss": 6.5071,
|
||
|
|
"mean_token_accuracy": 0.11863285824656486,
|
||
|
|
"num_tokens": 3930966.0,
|
||
|
|
"step": 1930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.712709712982178,
|
||
|
|
"epoch": 0.11325724319578578,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.00040068814771294134,
|
||
|
|
"loss": 6.4858,
|
||
|
|
"mean_token_accuracy": 0.1253066875040531,
|
||
|
|
"num_tokens": 3941846.0,
|
||
|
|
"step": 1935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.730831480026245,
|
||
|
|
"epoch": 0.11354989757096869,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0003997092827157562,
|
||
|
|
"loss": 6.5528,
|
||
|
|
"mean_token_accuracy": 0.11424804329872132,
|
||
|
|
"num_tokens": 3952029.0,
|
||
|
|
"step": 1940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.798965406417847,
|
||
|
|
"epoch": 0.1138425519461516,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000398726998750589,
|
||
|
|
"loss": 6.4762,
|
||
|
|
"mean_token_accuracy": 0.1260433167219162,
|
||
|
|
"num_tokens": 3962378.0,
|
||
|
|
"step": 1945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.653168725967407,
|
||
|
|
"epoch": 0.1141352063213345,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.00039774132274725076,
|
||
|
|
"loss": 6.4222,
|
||
|
|
"mean_token_accuracy": 0.13140382021665573,
|
||
|
|
"num_tokens": 3972516.0,
|
||
|
|
"step": 1950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.758973932266235,
|
||
|
|
"epoch": 0.11442786069651742,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.00039675228172854707,
|
||
|
|
"loss": 6.4358,
|
||
|
|
"mean_token_accuracy": 0.13106181994080543,
|
||
|
|
"num_tokens": 3982018.0,
|
||
|
|
"step": 1955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.694025945663452,
|
||
|
|
"epoch": 0.11472051507170032,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0003957599028095371,
|
||
|
|
"loss": 6.4309,
|
||
|
|
"mean_token_accuracy": 0.127551356703043,
|
||
|
|
"num_tokens": 3991392.0,
|
||
|
|
"step": 1960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.713197708129883,
|
||
|
|
"epoch": 0.11501316944688324,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.00039476421319679017,
|
||
|
|
"loss": 6.572,
|
||
|
|
"mean_token_accuracy": 0.120946604013443,
|
||
|
|
"num_tokens": 4001840.0,
|
||
|
|
"step": 1965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7711381912231445,
|
||
|
|
"epoch": 0.11530582382206614,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00039376524018764,
|
||
|
|
"loss": 6.4604,
|
||
|
|
"mean_token_accuracy": 0.12467103376984597,
|
||
|
|
"num_tokens": 4012352.0,
|
||
|
|
"step": 1970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.632588720321655,
|
||
|
|
"epoch": 0.11559847819724905,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.00039276301116943616,
|
||
|
|
"loss": 6.4884,
|
||
|
|
"mean_token_accuracy": 0.12170003205537797,
|
||
|
|
"num_tokens": 4023696.0,
|
||
|
|
"step": 1975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.738251638412476,
|
||
|
|
"epoch": 0.11589113257243196,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0003917575536187936,
|
||
|
|
"loss": 6.4447,
|
||
|
|
"mean_token_accuracy": 0.12842353954911231,
|
||
|
|
"num_tokens": 4033293.0,
|
||
|
|
"step": 1980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.665024137496948,
|
||
|
|
"epoch": 0.11618378694761487,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00039074889510083894,
|
||
|
|
"loss": 6.4416,
|
||
|
|
"mean_token_accuracy": 0.13035320565104486,
|
||
|
|
"num_tokens": 4042690.0,
|
||
|
|
"step": 1985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.68208417892456,
|
||
|
|
"epoch": 0.11647644132279777,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00038973706326845495,
|
||
|
|
"loss": 6.3884,
|
||
|
|
"mean_token_accuracy": 0.12777606695890426,
|
||
|
|
"num_tokens": 4053114.0,
|
||
|
|
"step": 1990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.640972328186035,
|
||
|
|
"epoch": 0.11676909569798069,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0003887220858615225,
|
||
|
|
"loss": 6.5054,
|
||
|
|
"mean_token_accuracy": 0.11883352771401405,
|
||
|
|
"num_tokens": 4063354.0,
|
||
|
|
"step": 1995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.789265394210815,
|
||
|
|
"epoch": 0.11706175007316359,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0003877039907061597,
|
||
|
|
"loss": 6.5019,
|
||
|
|
"mean_token_accuracy": 0.1184429682791233,
|
||
|
|
"num_tokens": 4073376.0,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.689146900177002,
|
||
|
|
"epoch": 0.11735440444834651,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0003866828057139598,
|
||
|
|
"loss": 6.5813,
|
||
|
|
"mean_token_accuracy": 0.11173970699310302,
|
||
|
|
"num_tokens": 4084980.0,
|
||
|
|
"step": 2005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.754443883895874,
|
||
|
|
"epoch": 0.11764705882352941,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.00038565855888122503,
|
||
|
|
"loss": 6.4852,
|
||
|
|
"mean_token_accuracy": 0.12186115011572837,
|
||
|
|
"num_tokens": 4094011.0,
|
||
|
|
"step": 2010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.764962863922119,
|
||
|
|
"epoch": 0.11793971319871233,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.00038463127828819975,
|
||
|
|
"loss": 6.5133,
|
||
|
|
"mean_token_accuracy": 0.12561107128858567,
|
||
|
|
"num_tokens": 4104993.0,
|
||
|
|
"step": 2015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.692309808731079,
|
||
|
|
"epoch": 0.11823236757389523,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.00038360099209830043,
|
||
|
|
"loss": 6.4687,
|
||
|
|
"mean_token_accuracy": 0.12259510681033134,
|
||
|
|
"num_tokens": 4115639.0,
|
||
|
|
"step": 2020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.732027530670166,
|
||
|
|
"epoch": 0.11852502194907814,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0003825677285573433,
|
||
|
|
"loss": 6.4135,
|
||
|
|
"mean_token_accuracy": 0.1265033908188343,
|
||
|
|
"num_tokens": 4125787.0,
|
||
|
|
"step": 2025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.63936071395874,
|
||
|
|
"epoch": 0.11881767632426105,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.00038153151599277027,
|
||
|
|
"loss": 6.4485,
|
||
|
|
"mean_token_accuracy": 0.12343809232115746,
|
||
|
|
"num_tokens": 4136375.0,
|
||
|
|
"step": 2030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.671218156814575,
|
||
|
|
"epoch": 0.11911033069944396,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0003804923828128723,
|
||
|
|
"loss": 6.4971,
|
||
|
|
"mean_token_accuracy": 0.12380525693297387,
|
||
|
|
"num_tokens": 4146380.0,
|
||
|
|
"step": 2035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.698442792892456,
|
||
|
|
"epoch": 0.11940298507462686,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0003794503575060104,
|
||
|
|
"loss": 6.4711,
|
||
|
|
"mean_token_accuracy": 0.13062296956777572,
|
||
|
|
"num_tokens": 4157131.0,
|
||
|
|
"step": 2040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.722663831710816,
|
||
|
|
"epoch": 0.11969563944980978,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.00037840546863983484,
|
||
|
|
"loss": 6.4323,
|
||
|
|
"mean_token_accuracy": 0.12796600833535193,
|
||
|
|
"num_tokens": 4167104.0,
|
||
|
|
"step": 2045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.761295175552368,
|
||
|
|
"epoch": 0.11998829382499268,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0003773577448605015,
|
||
|
|
"loss": 6.4976,
|
||
|
|
"mean_token_accuracy": 0.12016392797231674,
|
||
|
|
"num_tokens": 4176862.0,
|
||
|
|
"step": 2050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.666880655288696,
|
||
|
|
"epoch": 0.1202809482001756,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0003763072148918872,
|
||
|
|
"loss": 6.3807,
|
||
|
|
"mean_token_accuracy": 0.12986320927739142,
|
||
|
|
"num_tokens": 4186019.0,
|
||
|
|
"step": 2055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.699233484268189,
|
||
|
|
"epoch": 0.1205736025753585,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0003752539075348017,
|
||
|
|
"loss": 6.4914,
|
||
|
|
"mean_token_accuracy": 0.12515649795532227,
|
||
|
|
"num_tokens": 4196513.0,
|
||
|
|
"step": 2060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.700495195388794,
|
||
|
|
"epoch": 0.12086625695054141,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.00037419785166619817,
|
||
|
|
"loss": 6.4784,
|
||
|
|
"mean_token_accuracy": 0.12092648595571517,
|
||
|
|
"num_tokens": 4207726.0,
|
||
|
|
"step": 2065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.755660200119019,
|
||
|
|
"epoch": 0.12115891132572432,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0003731390762383818,
|
||
|
|
"loss": 6.4877,
|
||
|
|
"mean_token_accuracy": 0.12109851315617562,
|
||
|
|
"num_tokens": 4217953.0,
|
||
|
|
"step": 2070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.691427946090698,
|
||
|
|
"epoch": 0.12145156570090723,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0003720776102782158,
|
||
|
|
"loss": 6.3912,
|
||
|
|
"mean_token_accuracy": 0.12726705223321916,
|
||
|
|
"num_tokens": 4227353.0,
|
||
|
|
"step": 2075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.64779372215271,
|
||
|
|
"epoch": 0.12174422007609013,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00037101348288632555,
|
||
|
|
"loss": 6.3456,
|
||
|
|
"mean_token_accuracy": 0.13620738610625266,
|
||
|
|
"num_tokens": 4237336.0,
|
||
|
|
"step": 2080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6663731098175045,
|
||
|
|
"epoch": 0.12203687445127305,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0003699467232363012,
|
||
|
|
"loss": 6.4713,
|
||
|
|
"mean_token_accuracy": 0.12634024024009705,
|
||
|
|
"num_tokens": 4246768.0,
|
||
|
|
"step": 2085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.781217622756958,
|
||
|
|
"epoch": 0.12232952882645595,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0003688773605738973,
|
||
|
|
"loss": 6.387,
|
||
|
|
"mean_token_accuracy": 0.12766596376895906,
|
||
|
|
"num_tokens": 4256796.0,
|
||
|
|
"step": 2090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.582059717178344,
|
||
|
|
"epoch": 0.12262218320163887,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00036780542421623134,
|
||
|
|
"loss": 6.3327,
|
||
|
|
"mean_token_accuracy": 0.14140671789646148,
|
||
|
|
"num_tokens": 4265976.0,
|
||
|
|
"step": 2095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.673408889770508,
|
||
|
|
"epoch": 0.12291483757682177,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0003667309435509802,
|
||
|
|
"loss": 6.3816,
|
||
|
|
"mean_token_accuracy": 0.1286499671638012,
|
||
|
|
"num_tokens": 4275680.0,
|
||
|
|
"step": 2100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.718602418899536,
|
||
|
|
"epoch": 0.12320749195200469,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0003656539480355741,
|
||
|
|
"loss": 6.3998,
|
||
|
|
"mean_token_accuracy": 0.1262201152741909,
|
||
|
|
"num_tokens": 4285855.0,
|
||
|
|
"step": 2105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.626631402969361,
|
||
|
|
"epoch": 0.12350014632718759,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0003645744671963891,
|
||
|
|
"loss": 6.4822,
|
||
|
|
"mean_token_accuracy": 0.12650331631302833,
|
||
|
|
"num_tokens": 4295939.0,
|
||
|
|
"step": 2110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.623495578765869,
|
||
|
|
"epoch": 0.1237928007023705,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0003634925306279376,
|
||
|
|
"loss": 6.3456,
|
||
|
|
"mean_token_accuracy": 0.13147402703762054,
|
||
|
|
"num_tokens": 4305457.0,
|
||
|
|
"step": 2115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6712672233581545,
|
||
|
|
"epoch": 0.1240854550775534,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0003624081679920574,
|
||
|
|
"loss": 6.4646,
|
||
|
|
"mean_token_accuracy": 0.12995418161153793,
|
||
|
|
"num_tokens": 4316447.0,
|
||
|
|
"step": 2120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.725176286697388,
|
||
|
|
"epoch": 0.12437810945273632,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0003613214090170977,
|
||
|
|
"loss": 6.4656,
|
||
|
|
"mean_token_accuracy": 0.1237868271768093,
|
||
|
|
"num_tokens": 4327063.0,
|
||
|
|
"step": 2125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.730049705505371,
|
||
|
|
"epoch": 0.12467076382791922,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0003602322834971048,
|
||
|
|
"loss": 6.4396,
|
||
|
|
"mean_token_accuracy": 0.12165140211582184,
|
||
|
|
"num_tokens": 4337226.0,
|
||
|
|
"step": 2130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.66084623336792,
|
||
|
|
"epoch": 0.12496341820310214,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0003591408212910051,
|
||
|
|
"loss": 6.4564,
|
||
|
|
"mean_token_accuracy": 0.1257864184677601,
|
||
|
|
"num_tokens": 4348076.0,
|
||
|
|
"step": 2135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.652794361114502,
|
||
|
|
"epoch": 0.12525607257828505,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0003580470523217863,
|
||
|
|
"loss": 6.4184,
|
||
|
|
"mean_token_accuracy": 0.12144943475723266,
|
||
|
|
"num_tokens": 4358259.0,
|
||
|
|
"step": 2140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.76425518989563,
|
||
|
|
"epoch": 0.12554872695346794,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.0003569510065756771,
|
||
|
|
"loss": 6.4281,
|
||
|
|
"mean_token_accuracy": 0.12907697334885598,
|
||
|
|
"num_tokens": 4369058.0,
|
||
|
|
"step": 2145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.601361560821533,
|
||
|
|
"epoch": 0.12584138132865086,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0003558527141013254,
|
||
|
|
"loss": 6.3483,
|
||
|
|
"mean_token_accuracy": 0.1359138384461403,
|
||
|
|
"num_tokens": 4380135.0,
|
||
|
|
"step": 2150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.653647613525391,
|
||
|
|
"epoch": 0.12613403570383377,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0003547522050089742,
|
||
|
|
"loss": 6.388,
|
||
|
|
"mean_token_accuracy": 0.1273554138839245,
|
||
|
|
"num_tokens": 4389998.0,
|
||
|
|
"step": 2155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.646863889694214,
|
||
|
|
"epoch": 0.1264266900790167,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.00035364950946963606,
|
||
|
|
"loss": 6.392,
|
||
|
|
"mean_token_accuracy": 0.12970071211457251,
|
||
|
|
"num_tokens": 4400677.0,
|
||
|
|
"step": 2160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.700640773773193,
|
||
|
|
"epoch": 0.12671934445419958,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0003525446577142663,
|
||
|
|
"loss": 6.3826,
|
||
|
|
"mean_token_accuracy": 0.12550389319658278,
|
||
|
|
"num_tokens": 4410491.0,
|
||
|
|
"step": 2165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.686038970947266,
|
||
|
|
"epoch": 0.1270119988293825,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.00035143768003293395,
|
||
|
|
"loss": 6.3873,
|
||
|
|
"mean_token_accuracy": 0.13036831542849542,
|
||
|
|
"num_tokens": 4420367.0,
|
||
|
|
"step": 2170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.635172033309937,
|
||
|
|
"epoch": 0.1273046532045654,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0003503286067739913,
|
||
|
|
"loss": 6.3343,
|
||
|
|
"mean_token_accuracy": 0.13271640241146088,
|
||
|
|
"num_tokens": 4430499.0,
|
||
|
|
"step": 2175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.688625764846802,
|
||
|
|
"epoch": 0.12759730757974833,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.00034921746834324193,
|
||
|
|
"loss": 6.3599,
|
||
|
|
"mean_token_accuracy": 0.12575160786509515,
|
||
|
|
"num_tokens": 4440667.0,
|
||
|
|
"step": 2180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.673585891723633,
|
||
|
|
"epoch": 0.12788996195493121,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0003481042952031072,
|
||
|
|
"loss": 6.4517,
|
||
|
|
"mean_token_accuracy": 0.12898295149207115,
|
||
|
|
"num_tokens": 4450598.0,
|
||
|
|
"step": 2185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.696045923233032,
|
||
|
|
"epoch": 0.12818261633011413,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0003469891178717911,
|
||
|
|
"loss": 6.3704,
|
||
|
|
"mean_token_accuracy": 0.1302775613963604,
|
||
|
|
"num_tokens": 4460644.0,
|
||
|
|
"step": 2190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.598845100402832,
|
||
|
|
"epoch": 0.12847527070529705,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0003458719669224436,
|
||
|
|
"loss": 6.4408,
|
||
|
|
"mean_token_accuracy": 0.12747587859630585,
|
||
|
|
"num_tokens": 4470315.0,
|
||
|
|
"step": 2195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.643047237396241,
|
||
|
|
"epoch": 0.12876792508047996,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0003447528729823221,
|
||
|
|
"loss": 6.3008,
|
||
|
|
"mean_token_accuracy": 0.13260431662201883,
|
||
|
|
"num_tokens": 4480444.0,
|
||
|
|
"step": 2200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.643319511413575,
|
||
|
|
"epoch": 0.12906057945566285,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0003436318667319525,
|
||
|
|
"loss": 6.2865,
|
||
|
|
"mean_token_accuracy": 0.13138291835784913,
|
||
|
|
"num_tokens": 4490826.0,
|
||
|
|
"step": 2205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.563979387283325,
|
||
|
|
"epoch": 0.12935323383084577,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00034250897890428716,
|
||
|
|
"loss": 6.3393,
|
||
|
|
"mean_token_accuracy": 0.13606738969683646,
|
||
|
|
"num_tokens": 4500534.0,
|
||
|
|
"step": 2210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6366644382476805,
|
||
|
|
"epoch": 0.12964588820602868,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0003413842402838633,
|
||
|
|
"loss": 6.2993,
|
||
|
|
"mean_token_accuracy": 0.13520264625549316,
|
||
|
|
"num_tokens": 4510407.0,
|
||
|
|
"step": 2215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.623635864257812,
|
||
|
|
"epoch": 0.1299385425812116,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00034025768170595834,
|
||
|
|
"loss": 6.3841,
|
||
|
|
"mean_token_accuracy": 0.13335896357893945,
|
||
|
|
"num_tokens": 4519562.0,
|
||
|
|
"step": 2220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.692249965667725,
|
||
|
|
"epoch": 0.13023119695639448,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0003391293340557446,
|
||
|
|
"loss": 6.2956,
|
||
|
|
"mean_token_accuracy": 0.13522055745124817,
|
||
|
|
"num_tokens": 4530044.0,
|
||
|
|
"step": 2225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.676627492904663,
|
||
|
|
"epoch": 0.1305238513315774,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0003379992282674431,
|
||
|
|
"loss": 6.3683,
|
||
|
|
"mean_token_accuracy": 0.13091277852654457,
|
||
|
|
"num_tokens": 4539910.0,
|
||
|
|
"step": 2230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.616313171386719,
|
||
|
|
"epoch": 0.13081650570676032,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0003368673953234749,
|
||
|
|
"loss": 6.4038,
|
||
|
|
"mean_token_accuracy": 0.1315946489572525,
|
||
|
|
"num_tokens": 4549054.0,
|
||
|
|
"step": 2235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.638192558288575,
|
||
|
|
"epoch": 0.13110916008194323,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.00033573386625361176,
|
||
|
|
"loss": 6.5186,
|
||
|
|
"mean_token_accuracy": 0.12304450571537018,
|
||
|
|
"num_tokens": 4561420.0,
|
||
|
|
"step": 2240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.724251842498779,
|
||
|
|
"epoch": 0.13140181445712612,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.00033459867213412567,
|
||
|
|
"loss": 6.4011,
|
||
|
|
"mean_token_accuracy": 0.12729023545980453,
|
||
|
|
"num_tokens": 4572249.0,
|
||
|
|
"step": 2245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.636874341964722,
|
||
|
|
"epoch": 0.13169446883230904,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.000333461844086937,
|
||
|
|
"loss": 6.3486,
|
||
|
|
"mean_token_accuracy": 0.13104709312319757,
|
||
|
|
"num_tokens": 4582365.0,
|
||
|
|
"step": 2250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.630363035202026,
|
||
|
|
"epoch": 0.13198712320749195,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.00033232341327876097,
|
||
|
|
"loss": 6.352,
|
||
|
|
"mean_token_accuracy": 0.13636366948485373,
|
||
|
|
"num_tokens": 4592518.0,
|
||
|
|
"step": 2255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.620830345153808,
|
||
|
|
"epoch": 0.13227977758267487,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0003311834109202531,
|
||
|
|
"loss": 6.4375,
|
||
|
|
"mean_token_accuracy": 0.1285679928958416,
|
||
|
|
"num_tokens": 4603405.0,
|
||
|
|
"step": 2260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.591335248947144,
|
||
|
|
"epoch": 0.13257243195785778,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00033004186826515416,
|
||
|
|
"loss": 6.3024,
|
||
|
|
"mean_token_accuracy": 0.1358066976070404,
|
||
|
|
"num_tokens": 4613134.0,
|
||
|
|
"step": 2265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6046994686126705,
|
||
|
|
"epoch": 0.13286508633304067,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0003288988166094324,
|
||
|
|
"loss": 6.307,
|
||
|
|
"mean_token_accuracy": 0.134018661826849,
|
||
|
|
"num_tokens": 4622769.0,
|
||
|
|
"step": 2270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6116033554077145,
|
||
|
|
"epoch": 0.1331577407082236,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.00032775428729042656,
|
||
|
|
"loss": 6.3069,
|
||
|
|
"mean_token_accuracy": 0.13382299169898032,
|
||
|
|
"num_tokens": 4632344.0,
|
||
|
|
"step": 2275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6585752964019775,
|
||
|
|
"epoch": 0.1334503950834065,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000326608311685986,
|
||
|
|
"loss": 6.3437,
|
||
|
|
"mean_token_accuracy": 0.1316613644361496,
|
||
|
|
"num_tokens": 4642336.0,
|
||
|
|
"step": 2280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.593194913864136,
|
||
|
|
"epoch": 0.13374304945858942,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0003254609212136108,
|
||
|
|
"loss": 6.3105,
|
||
|
|
"mean_token_accuracy": 0.12656986117362976,
|
||
|
|
"num_tokens": 4651292.0,
|
||
|
|
"step": 2285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.609660530090332,
|
||
|
|
"epoch": 0.1340357038337723,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00032431214732959036,
|
||
|
|
"loss": 6.3466,
|
||
|
|
"mean_token_accuracy": 0.12910948917269707,
|
||
|
|
"num_tokens": 4661583.0,
|
||
|
|
"step": 2290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.617812919616699,
|
||
|
|
"epoch": 0.13432835820895522,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000323162021528141,
|
||
|
|
"loss": 6.354,
|
||
|
|
"mean_token_accuracy": 0.12989597618579865,
|
||
|
|
"num_tokens": 4672135.0,
|
||
|
|
"step": 2295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.647702980041504,
|
||
|
|
"epoch": 0.13462101258413814,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.00032201057534054264,
|
||
|
|
"loss": 6.3766,
|
||
|
|
"mean_token_accuracy": 0.12548863440752028,
|
||
|
|
"num_tokens": 4682642.0,
|
||
|
|
"step": 2300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.598292827606201,
|
||
|
|
"epoch": 0.13491366695932105,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00032085784033427414,
|
||
|
|
"loss": 6.312,
|
||
|
|
"mean_token_accuracy": 0.12743351757526397,
|
||
|
|
"num_tokens": 4692265.0,
|
||
|
|
"step": 2305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.580078792572022,
|
||
|
|
"epoch": 0.13520632133450394,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0003197038481121478,
|
||
|
|
"loss": 6.3324,
|
||
|
|
"mean_token_accuracy": 0.13632925152778624,
|
||
|
|
"num_tokens": 4701612.0,
|
||
|
|
"step": 2310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.645194482803345,
|
||
|
|
"epoch": 0.13549897570968686,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0003185486303114436,
|
||
|
|
"loss": 6.3568,
|
||
|
|
"mean_token_accuracy": 0.1304594896733761,
|
||
|
|
"num_tokens": 4712510.0,
|
||
|
|
"step": 2315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.665656805038452,
|
||
|
|
"epoch": 0.13579163008486977,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0003173922186030409,
|
||
|
|
"loss": 6.3915,
|
||
|
|
"mean_token_accuracy": 0.1305775336921215,
|
||
|
|
"num_tokens": 4724519.0,
|
||
|
|
"step": 2320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.617322015762329,
|
||
|
|
"epoch": 0.1360842844600527,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.000316234644690551,
|
||
|
|
"loss": 6.2818,
|
||
|
|
"mean_token_accuracy": 0.1356732003390789,
|
||
|
|
"num_tokens": 4735481.0,
|
||
|
|
"step": 2325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.591895818710327,
|
||
|
|
"epoch": 0.13637693883523558,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0003150759403094473,
|
||
|
|
"loss": 6.3447,
|
||
|
|
"mean_token_accuracy": 0.1303927145898342,
|
||
|
|
"num_tokens": 4746407.0,
|
||
|
|
"step": 2330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.515862989425659,
|
||
|
|
"epoch": 0.1366695932104185,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00031391613722619587,
|
||
|
|
"loss": 6.2192,
|
||
|
|
"mean_token_accuracy": 0.1439518079161644,
|
||
|
|
"num_tokens": 4755235.0,
|
||
|
|
"step": 2335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.681423616409302,
|
||
|
|
"epoch": 0.1369622475856014,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.000312755267237384,
|
||
|
|
"loss": 6.3683,
|
||
|
|
"mean_token_accuracy": 0.12859276309609413,
|
||
|
|
"num_tokens": 4765490.0,
|
||
|
|
"step": 2340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6373199939727785,
|
||
|
|
"epoch": 0.13725490196078433,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0003115933621688488,
|
||
|
|
"loss": 6.3857,
|
||
|
|
"mean_token_accuracy": 0.13260382413864136,
|
||
|
|
"num_tokens": 4775738.0,
|
||
|
|
"step": 2345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.616128015518188,
|
||
|
|
"epoch": 0.1375475563359672,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.00031043045387480487,
|
||
|
|
"loss": 6.3049,
|
||
|
|
"mean_token_accuracy": 0.12710103169083595,
|
||
|
|
"num_tokens": 4786101.0,
|
||
|
|
"step": 2350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.654890298843384,
|
||
|
|
"epoch": 0.13784021071115013,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0003092665742369703,
|
||
|
|
"loss": 6.4225,
|
||
|
|
"mean_token_accuracy": 0.12488598376512527,
|
||
|
|
"num_tokens": 4797083.0,
|
||
|
|
"step": 2355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.519471883773804,
|
||
|
|
"epoch": 0.13813286508633305,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00030810175516369343,
|
||
|
|
"loss": 6.2972,
|
||
|
|
"mean_token_accuracy": 0.13746514022350312,
|
||
|
|
"num_tokens": 4806979.0,
|
||
|
|
"step": 2360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.597585725784302,
|
||
|
|
"epoch": 0.13842551946151596,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0003069360285890775,
|
||
|
|
"loss": 6.3586,
|
||
|
|
"mean_token_accuracy": 0.1265510566532612,
|
||
|
|
"num_tokens": 4817456.0,
|
||
|
|
"step": 2365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.688738584518433,
|
||
|
|
"epoch": 0.13871817383669885,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00030576942647210547,
|
||
|
|
"loss": 6.3485,
|
||
|
|
"mean_token_accuracy": 0.13092773035168648,
|
||
|
|
"num_tokens": 4829162.0,
|
||
|
|
"step": 2370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.649426746368408,
|
||
|
|
"epoch": 0.13901082821188177,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00030460198079576355,
|
||
|
|
"loss": 6.3262,
|
||
|
|
"mean_token_accuracy": 0.13880319520831108,
|
||
|
|
"num_tokens": 4840018.0,
|
||
|
|
"step": 2375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.541487836837769,
|
||
|
|
"epoch": 0.13930348258706468,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0003034337235661648,
|
||
|
|
"loss": 6.2363,
|
||
|
|
"mean_token_accuracy": 0.13673475831747056,
|
||
|
|
"num_tokens": 4849839.0,
|
||
|
|
"step": 2380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.580998754501342,
|
||
|
|
"epoch": 0.1395961369622476,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0003022646868116714,
|
||
|
|
"loss": 6.3949,
|
||
|
|
"mean_token_accuracy": 0.12793906554579734,
|
||
|
|
"num_tokens": 4860300.0,
|
||
|
|
"step": 2385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.703210926055908,
|
||
|
|
"epoch": 0.13988879133743048,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0003010949025820163,
|
||
|
|
"loss": 6.3304,
|
||
|
|
"mean_token_accuracy": 0.13649305254220961,
|
||
|
|
"num_tokens": 4870237.0,
|
||
|
|
"step": 2390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.590689945220947,
|
||
|
|
"epoch": 0.1401814457126134,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0002999244029474252,
|
||
|
|
"loss": 6.4002,
|
||
|
|
"mean_token_accuracy": 0.12530083060264588,
|
||
|
|
"num_tokens": 4879954.0,
|
||
|
|
"step": 2395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.548434066772461,
|
||
|
|
"epoch": 0.14047410008779632,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.00029875321999773684,
|
||
|
|
"loss": 6.3316,
|
||
|
|
"mean_token_accuracy": 0.133211962133646,
|
||
|
|
"num_tokens": 4890297.0,
|
||
|
|
"step": 2400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.679122495651245,
|
||
|
|
"epoch": 0.14076675446297923,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.00029758138584152333,
|
||
|
|
"loss": 6.2794,
|
||
|
|
"mean_token_accuracy": 0.1352786011993885,
|
||
|
|
"num_tokens": 4900429.0,
|
||
|
|
"step": 2405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.608310890197754,
|
||
|
|
"epoch": 0.14105940883816212,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0002964089326052102,
|
||
|
|
"loss": 6.277,
|
||
|
|
"mean_token_accuracy": 0.13714320510625838,
|
||
|
|
"num_tokens": 4910553.0,
|
||
|
|
"step": 2410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.568372774124145,
|
||
|
|
"epoch": 0.14135206321334504,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0002952358924321949,
|
||
|
|
"loss": 6.2367,
|
||
|
|
"mean_token_accuracy": 0.13472286239266396,
|
||
|
|
"num_tokens": 4920983.0,
|
||
|
|
"step": 2415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.563381004333496,
|
||
|
|
"epoch": 0.14164471758852795,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.00029406229748196657,
|
||
|
|
"loss": 6.365,
|
||
|
|
"mean_token_accuracy": 0.12762125134468078,
|
||
|
|
"num_tokens": 4932438.0,
|
||
|
|
"step": 2420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.704500579833985,
|
||
|
|
"epoch": 0.14193737196371087,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0002928881799292235,
|
||
|
|
"loss": 6.2754,
|
||
|
|
"mean_token_accuracy": 0.1386060632765293,
|
||
|
|
"num_tokens": 4942239.0,
|
||
|
|
"step": 2425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.550548553466797,
|
||
|
|
"epoch": 0.14223002633889376,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00029171357196299154,
|
||
|
|
"loss": 6.3056,
|
||
|
|
"mean_token_accuracy": 0.132572952657938,
|
||
|
|
"num_tokens": 4951893.0,
|
||
|
|
"step": 2430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.663923120498657,
|
||
|
|
"epoch": 0.14252268071407667,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0002905385057857414,
|
||
|
|
"loss": 6.3186,
|
||
|
|
"mean_token_accuracy": 0.1256115861237049,
|
||
|
|
"num_tokens": 4961873.0,
|
||
|
|
"step": 2435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5535320281982425,
|
||
|
|
"epoch": 0.1428153350892596,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0002893630136125058,
|
||
|
|
"loss": 6.2192,
|
||
|
|
"mean_token_accuracy": 0.14415578544139862,
|
||
|
|
"num_tokens": 4972103.0,
|
||
|
|
"step": 2440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.513900184631348,
|
||
|
|
"epoch": 0.1431079894644425,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0002881871276699967,
|
||
|
|
"loss": 6.3171,
|
||
|
|
"mean_token_accuracy": 0.13082123920321465,
|
||
|
|
"num_tokens": 4982937.0,
|
||
|
|
"step": 2445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6147575855255125,
|
||
|
|
"epoch": 0.1434006438396254,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00028701088019572114,
|
||
|
|
"loss": 6.2689,
|
||
|
|
"mean_token_accuracy": 0.13370759263634682,
|
||
|
|
"num_tokens": 4992173.0,
|
||
|
|
"step": 2450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.583463954925537,
|
||
|
|
"epoch": 0.1436932982148083,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0002858343034370977,
|
||
|
|
"loss": 6.2649,
|
||
|
|
"mean_token_accuracy": 0.14038844481110574,
|
||
|
|
"num_tokens": 5002156.0,
|
||
|
|
"step": 2455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.596443367004395,
|
||
|
|
"epoch": 0.14398595258999122,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.00028465742965057267,
|
||
|
|
"loss": 6.2944,
|
||
|
|
"mean_token_accuracy": 0.13622246980667113,
|
||
|
|
"num_tokens": 5013341.0,
|
||
|
|
"step": 2460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.544248056411743,
|
||
|
|
"epoch": 0.14427860696517414,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.00028348029110073533,
|
||
|
|
"loss": 6.2663,
|
||
|
|
"mean_token_accuracy": 0.14084595143795015,
|
||
|
|
"num_tokens": 5024212.0,
|
||
|
|
"step": 2465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.565490102767944,
|
||
|
|
"epoch": 0.14457126134035703,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00028230292005943365,
|
||
|
|
"loss": 6.2706,
|
||
|
|
"mean_token_accuracy": 0.1421001598238945,
|
||
|
|
"num_tokens": 5033854.0,
|
||
|
|
"step": 2470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.629309463500976,
|
||
|
|
"epoch": 0.14486391571553994,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00028112534880488945,
|
||
|
|
"loss": 6.2248,
|
||
|
|
"mean_token_accuracy": 0.14141243249177932,
|
||
|
|
"num_tokens": 5043875.0,
|
||
|
|
"step": 2475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.545979690551758,
|
||
|
|
"epoch": 0.14515657009072286,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0002799476096208137,
|
||
|
|
"loss": 6.2425,
|
||
|
|
"mean_token_accuracy": 0.13927025198936463,
|
||
|
|
"num_tokens": 5054076.0,
|
||
|
|
"step": 2480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.566827630996704,
|
||
|
|
"epoch": 0.14544922446590577,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00027876973479552087,
|
||
|
|
"loss": 6.378,
|
||
|
|
"mean_token_accuracy": 0.12588516920804976,
|
||
|
|
"num_tokens": 5064285.0,
|
||
|
|
"step": 2485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.623711252212525,
|
||
|
|
"epoch": 0.14574187884108866,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00027759175662104424,
|
||
|
|
"loss": 6.3197,
|
||
|
|
"mean_token_accuracy": 0.13403562009334563,
|
||
|
|
"num_tokens": 5074693.0,
|
||
|
|
"step": 2490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.633525037765503,
|
||
|
|
"epoch": 0.14603453321627158,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 0.0002764137073922508,
|
||
|
|
"loss": 6.3159,
|
||
|
|
"mean_token_accuracy": 0.13227061480283736,
|
||
|
|
"num_tokens": 5083771.0,
|
||
|
|
"step": 2495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.566998767852783,
|
||
|
|
"epoch": 0.1463271875914545,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.00027523561940595505,
|
||
|
|
"loss": 6.3005,
|
||
|
|
"mean_token_accuracy": 0.1315088652074337,
|
||
|
|
"num_tokens": 5093913.0,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.643738174438477,
|
||
|
|
"epoch": 0.1466198419666374,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0002740575249600342,
|
||
|
|
"loss": 6.2872,
|
||
|
|
"mean_token_accuracy": 0.13545941188931465,
|
||
|
|
"num_tokens": 5104670.0,
|
||
|
|
"step": 2505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.588065147399902,
|
||
|
|
"epoch": 0.1469124963418203,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00027287945635254263,
|
||
|
|
"loss": 6.2381,
|
||
|
|
"mean_token_accuracy": 0.13420737609267236,
|
||
|
|
"num_tokens": 5113616.0,
|
||
|
|
"step": 2510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.552692508697509,
|
||
|
|
"epoch": 0.1472051507170032,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00027170144588082635,
|
||
|
|
"loss": 6.2093,
|
||
|
|
"mean_token_accuracy": 0.13239211663603784,
|
||
|
|
"num_tokens": 5124368.0,
|
||
|
|
"step": 2515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.682310914993286,
|
||
|
|
"epoch": 0.14749780509218613,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.00027052352584063763,
|
||
|
|
"loss": 6.3692,
|
||
|
|
"mean_token_accuracy": 0.12207729667425156,
|
||
|
|
"num_tokens": 5135647.0,
|
||
|
|
"step": 2520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.620374870300293,
|
||
|
|
"epoch": 0.14779045946736905,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.00026934572852524907,
|
||
|
|
"loss": 6.2799,
|
||
|
|
"mean_token_accuracy": 0.13331102058291436,
|
||
|
|
"num_tokens": 5146052.0,
|
||
|
|
"step": 2525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.506312036514283,
|
||
|
|
"epoch": 0.14808311384255193,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.00026816808622456937,
|
||
|
|
"loss": 6.2759,
|
||
|
|
"mean_token_accuracy": 0.12836330756545067,
|
||
|
|
"num_tokens": 5156498.0,
|
||
|
|
"step": 2530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.614617729187012,
|
||
|
|
"epoch": 0.14837576821773485,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0002669906312242569,
|
||
|
|
"loss": 6.2076,
|
||
|
|
"mean_token_accuracy": 0.14526754841208459,
|
||
|
|
"num_tokens": 5166043.0,
|
||
|
|
"step": 2535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.542679643630981,
|
||
|
|
"epoch": 0.14866842259291776,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00026581339580483525,
|
||
|
|
"loss": 6.2132,
|
||
|
|
"mean_token_accuracy": 0.14147503301501274,
|
||
|
|
"num_tokens": 5176332.0,
|
||
|
|
"step": 2540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.548535013198853,
|
||
|
|
"epoch": 0.14896107696810068,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0002646364122408082,
|
||
|
|
"loss": 6.2746,
|
||
|
|
"mean_token_accuracy": 0.1390418604016304,
|
||
|
|
"num_tokens": 5186478.0,
|
||
|
|
"step": 2545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.606277847290039,
|
||
|
|
"epoch": 0.14925373134328357,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0002634597127997749,
|
||
|
|
"loss": 6.2389,
|
||
|
|
"mean_token_accuracy": 0.14292193353176116,
|
||
|
|
"num_tokens": 5197074.0,
|
||
|
|
"step": 2550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.611769342422486,
|
||
|
|
"epoch": 0.14954638571846648,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0002622833297415445,
|
||
|
|
"loss": 6.2426,
|
||
|
|
"mean_token_accuracy": 0.13011746779084205,
|
||
|
|
"num_tokens": 5207024.0,
|
||
|
|
"step": 2555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.555798673629761,
|
||
|
|
"epoch": 0.1498390400936494,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0002611072953172531,
|
||
|
|
"loss": 6.2612,
|
||
|
|
"mean_token_accuracy": 0.13632453754544258,
|
||
|
|
"num_tokens": 5218362.0,
|
||
|
|
"step": 2560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.495365476608276,
|
||
|
|
"epoch": 0.15013169446883232,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.00025993164176847845,
|
||
|
|
"loss": 6.1768,
|
||
|
|
"mean_token_accuracy": 0.14391684234142305,
|
||
|
|
"num_tokens": 5228876.0,
|
||
|
|
"step": 2565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.582877111434937,
|
||
|
|
"epoch": 0.1504243488440152,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0002587564013263564,
|
||
|
|
"loss": 6.1715,
|
||
|
|
"mean_token_accuracy": 0.14230633825063704,
|
||
|
|
"num_tokens": 5238815.0,
|
||
|
|
"step": 2570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.503869247436524,
|
||
|
|
"epoch": 0.15071700321919812,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0002575816062106974,
|
||
|
|
"loss": 6.2365,
|
||
|
|
"mean_token_accuracy": 0.1408095084130764,
|
||
|
|
"num_tokens": 5248719.0,
|
||
|
|
"step": 2575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.604321527481079,
|
||
|
|
"epoch": 0.15100965759438104,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.00025640728862910293,
|
||
|
|
"loss": 6.2896,
|
||
|
|
"mean_token_accuracy": 0.12969041988253593,
|
||
|
|
"num_tokens": 5259279.0,
|
||
|
|
"step": 2580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5290830612182615,
|
||
|
|
"epoch": 0.15130231196956395,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.00025523348077608285,
|
||
|
|
"loss": 6.17,
|
||
|
|
"mean_token_accuracy": 0.1386630117893219,
|
||
|
|
"num_tokens": 5268973.0,
|
||
|
|
"step": 2585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.58136396408081,
|
||
|
|
"epoch": 0.15159496634474687,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00025406021483217225,
|
||
|
|
"loss": 6.2357,
|
||
|
|
"mean_token_accuracy": 0.1407373920083046,
|
||
|
|
"num_tokens": 5279574.0,
|
||
|
|
"step": 2590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.559312343597412,
|
||
|
|
"epoch": 0.15188762071992976,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00025288752296304963,
|
||
|
|
"loss": 6.1901,
|
||
|
|
"mean_token_accuracy": 0.14061311781406402,
|
||
|
|
"num_tokens": 5289800.0,
|
||
|
|
"step": 2595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.568912935256958,
|
||
|
|
"epoch": 0.15218027509511267,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.000251715437318655,
|
||
|
|
"loss": 6.2727,
|
||
|
|
"mean_token_accuracy": 0.13524502292275428,
|
||
|
|
"num_tokens": 5300347.0,
|
||
|
|
"step": 2600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.569336652755737,
|
||
|
|
"epoch": 0.1524729294702956,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0002505439900323084,
|
||
|
|
"loss": 6.1779,
|
||
|
|
"mean_token_accuracy": 0.14502978920936585,
|
||
|
|
"num_tokens": 5310522.0,
|
||
|
|
"step": 2605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.596165657043457,
|
||
|
|
"epoch": 0.1527655838454785,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00024937321321982894,
|
||
|
|
"loss": 6.3082,
|
||
|
|
"mean_token_accuracy": 0.13378702104091644,
|
||
|
|
"num_tokens": 5319883.0,
|
||
|
|
"step": 2610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.563585996627808,
|
||
|
|
"epoch": 0.1530582382206614,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00024820313897865433,
|
||
|
|
"loss": 6.2447,
|
||
|
|
"mean_token_accuracy": 0.13910910189151765,
|
||
|
|
"num_tokens": 5329885.0,
|
||
|
|
"step": 2615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.515380430221557,
|
||
|
|
"epoch": 0.1533508925958443,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.00024703379938696105,
|
||
|
|
"loss": 6.1585,
|
||
|
|
"mean_token_accuracy": 0.13748904913663865,
|
||
|
|
"num_tokens": 5340022.0,
|
||
|
|
"step": 2620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.538485479354859,
|
||
|
|
"epoch": 0.15364354697102722,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.00024586522650278447,
|
||
|
|
"loss": 6.3003,
|
||
|
|
"mean_token_accuracy": 0.12908684760332106,
|
||
|
|
"num_tokens": 5349999.0,
|
||
|
|
"step": 2625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.555411386489868,
|
||
|
|
"epoch": 0.15393620134621014,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00024469745236314064,
|
||
|
|
"loss": 6.2629,
|
||
|
|
"mean_token_accuracy": 0.13748588413000107,
|
||
|
|
"num_tokens": 5359763.0,
|
||
|
|
"step": 2630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.544770336151123,
|
||
|
|
"epoch": 0.15422885572139303,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.00024353050898314767,
|
||
|
|
"loss": 6.259,
|
||
|
|
"mean_token_accuracy": 0.13663270324468613,
|
||
|
|
"num_tokens": 5369868.0,
|
||
|
|
"step": 2635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.634533214569092,
|
||
|
|
"epoch": 0.15452151009657594,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00024236442835514743,
|
||
|
|
"loss": 6.2407,
|
||
|
|
"mean_token_accuracy": 0.13900253549218178,
|
||
|
|
"num_tokens": 5379745.0,
|
||
|
|
"step": 2640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.517221736907959,
|
||
|
|
"epoch": 0.15481416447175886,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00024119924244782965,
|
||
|
|
"loss": 6.2349,
|
||
|
|
"mean_token_accuracy": 0.13597667068243027,
|
||
|
|
"num_tokens": 5389081.0,
|
||
|
|
"step": 2645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.544792127609253,
|
||
|
|
"epoch": 0.15510681884694177,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00024003498320535462,
|
||
|
|
"loss": 6.1732,
|
||
|
|
"mean_token_accuracy": 0.14294402599334716,
|
||
|
|
"num_tokens": 5398022.0,
|
||
|
|
"step": 2650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.563321924209594,
|
||
|
|
"epoch": 0.15539947322212466,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.00023887168254647727,
|
||
|
|
"loss": 6.2542,
|
||
|
|
"mean_token_accuracy": 0.13828421756625175,
|
||
|
|
"num_tokens": 5408737.0,
|
||
|
|
"step": 2655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.582010221481323,
|
||
|
|
"epoch": 0.15569212759730758,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.00023770937236367308,
|
||
|
|
"loss": 6.2438,
|
||
|
|
"mean_token_accuracy": 0.12681645080447196,
|
||
|
|
"num_tokens": 5419427.0,
|
||
|
|
"step": 2660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.563237524032592,
|
||
|
|
"epoch": 0.1559847819724905,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.00023654808452226278,
|
||
|
|
"loss": 6.2493,
|
||
|
|
"mean_token_accuracy": 0.13405114859342576,
|
||
|
|
"num_tokens": 5430804.0,
|
||
|
|
"step": 2665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.540554094314575,
|
||
|
|
"epoch": 0.1562774363476734,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00023538785085953912,
|
||
|
|
"loss": 6.2319,
|
||
|
|
"mean_token_accuracy": 0.1424399085342884,
|
||
|
|
"num_tokens": 5440875.0,
|
||
|
|
"step": 2670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.515637540817261,
|
||
|
|
"epoch": 0.1565700907228563,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.00023422870318389404,
|
||
|
|
"loss": 6.2483,
|
||
|
|
"mean_token_accuracy": 0.13843049928545953,
|
||
|
|
"num_tokens": 5451566.0,
|
||
|
|
"step": 2675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.609659481048584,
|
||
|
|
"epoch": 0.1568627450980392,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0002330706732739468,
|
||
|
|
"loss": 6.2541,
|
||
|
|
"mean_token_accuracy": 0.13826142325997354,
|
||
|
|
"num_tokens": 5462037.0,
|
||
|
|
"step": 2680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.50597653388977,
|
||
|
|
"epoch": 0.15715539947322213,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00023191379287767211,
|
||
|
|
"loss": 6.2511,
|
||
|
|
"mean_token_accuracy": 0.14236056357622145,
|
||
|
|
"num_tokens": 5471693.0,
|
||
|
|
"step": 2685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5095006942749025,
|
||
|
|
"epoch": 0.15744805384840505,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0002307580937115305,
|
||
|
|
"loss": 6.221,
|
||
|
|
"mean_token_accuracy": 0.14096224904060364,
|
||
|
|
"num_tokens": 5482120.0,
|
||
|
|
"step": 2690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.594853162765503,
|
||
|
|
"epoch": 0.15774070822358793,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.00022960360745959846,
|
||
|
|
"loss": 6.1798,
|
||
|
|
"mean_token_accuracy": 0.14528884068131448,
|
||
|
|
"num_tokens": 5492801.0,
|
||
|
|
"step": 2695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.555709552764893,
|
||
|
|
"epoch": 0.15803336259877085,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.00022845036577269972,
|
||
|
|
"loss": 6.2376,
|
||
|
|
"mean_token_accuracy": 0.13575117364525796,
|
||
|
|
"num_tokens": 5503874.0,
|
||
|
|
"step": 2700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.609086656570435,
|
||
|
|
"epoch": 0.15832601697395376,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.00022729840026753777,
|
||
|
|
"loss": 6.2636,
|
||
|
|
"mean_token_accuracy": 0.13080462217330932,
|
||
|
|
"num_tokens": 5514379.0,
|
||
|
|
"step": 2705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.561835289001465,
|
||
|
|
"epoch": 0.15861867134913668,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0002261477425258287,
|
||
|
|
"loss": 6.2462,
|
||
|
|
"mean_token_accuracy": 0.13595554530620574,
|
||
|
|
"num_tokens": 5525992.0,
|
||
|
|
"step": 2710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.523668527603149,
|
||
|
|
"epoch": 0.15891132572431957,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0002249984240934358,
|
||
|
|
"loss": 6.0784,
|
||
|
|
"mean_token_accuracy": 0.15397015661001207,
|
||
|
|
"num_tokens": 5536067.0,
|
||
|
|
"step": 2715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.543307256698609,
|
||
|
|
"epoch": 0.15920398009950248,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00022385047647950464,
|
||
|
|
"loss": 6.1518,
|
||
|
|
"mean_token_accuracy": 0.14711069613695144,
|
||
|
|
"num_tokens": 5545504.0,
|
||
|
|
"step": 2720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.477677965164185,
|
||
|
|
"epoch": 0.1594966344746854,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0002227039311555986,
|
||
|
|
"loss": 6.2325,
|
||
|
|
"mean_token_accuracy": 0.13340043202042579,
|
||
|
|
"num_tokens": 5555585.0,
|
||
|
|
"step": 2725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.524174594879151,
|
||
|
|
"epoch": 0.15978928884986832,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0002215588195548372,
|
||
|
|
"loss": 6.1949,
|
||
|
|
"mean_token_accuracy": 0.14020482823252678,
|
||
|
|
"num_tokens": 5566265.0,
|
||
|
|
"step": 2730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.520068836212158,
|
||
|
|
"epoch": 0.1600819432250512,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00022041517307103337,
|
||
|
|
"loss": 6.2517,
|
||
|
|
"mean_token_accuracy": 0.14020458310842515,
|
||
|
|
"num_tokens": 5575987.0,
|
||
|
|
"step": 2735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.568447494506836,
|
||
|
|
"epoch": 0.16037459760023412,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0002192730230578331,
|
||
|
|
"loss": 6.2403,
|
||
|
|
"mean_token_accuracy": 0.13768415600061418,
|
||
|
|
"num_tokens": 5586966.0,
|
||
|
|
"step": 2740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.574257278442383,
|
||
|
|
"epoch": 0.16066725197541704,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0002181324008278559,
|
||
|
|
"loss": 6.2305,
|
||
|
|
"mean_token_accuracy": 0.14161389470100402,
|
||
|
|
"num_tokens": 5597606.0,
|
||
|
|
"step": 2745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5560074806213375,
|
||
|
|
"epoch": 0.16095990635059995,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00021699333765183655,
|
||
|
|
"loss": 6.2349,
|
||
|
|
"mean_token_accuracy": 0.14064271673560141,
|
||
|
|
"num_tokens": 5607025.0,
|
||
|
|
"step": 2750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.589640760421753,
|
||
|
|
"epoch": 0.16125256072578284,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0002158558647577673,
|
||
|
|
"loss": 6.1466,
|
||
|
|
"mean_token_accuracy": 0.1412832483649254,
|
||
|
|
"num_tokens": 5616731.0,
|
||
|
|
"step": 2755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.508824443817138,
|
||
|
|
"epoch": 0.16154521510096576,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.00021472001333004215,
|
||
|
|
"loss": 6.1843,
|
||
|
|
"mean_token_accuracy": 0.14442553371191025,
|
||
|
|
"num_tokens": 5627656.0,
|
||
|
|
"step": 2760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.592014741897583,
|
||
|
|
"epoch": 0.16183786947614867,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.00021358581450860186,
|
||
|
|
"loss": 6.2184,
|
||
|
|
"mean_token_accuracy": 0.1367047280073166,
|
||
|
|
"num_tokens": 5637736.0,
|
||
|
|
"step": 2765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.565477514266968,
|
||
|
|
"epoch": 0.1621305238513316,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0002124532993880799,
|
||
|
|
"loss": 6.1978,
|
||
|
|
"mean_token_accuracy": 0.13717956468462944,
|
||
|
|
"num_tokens": 5648385.0,
|
||
|
|
"step": 2770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.481182193756103,
|
||
|
|
"epoch": 0.16242317822651448,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.00021132249901695044,
|
||
|
|
"loss": 6.2288,
|
||
|
|
"mean_token_accuracy": 0.14161675423383713,
|
||
|
|
"num_tokens": 5659095.0,
|
||
|
|
"step": 2775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.441419792175293,
|
||
|
|
"epoch": 0.1627158326016974,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.00021019344439667705,
|
||
|
|
"loss": 6.1517,
|
||
|
|
"mean_token_accuracy": 0.14889734834432602,
|
||
|
|
"num_tokens": 5669943.0,
|
||
|
|
"step": 2780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5382989883422855,
|
||
|
|
"epoch": 0.1630084869768803,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.00020906616648086213,
|
||
|
|
"loss": 6.234,
|
||
|
|
"mean_token_accuracy": 0.13895118832588196,
|
||
|
|
"num_tokens": 5680744.0,
|
||
|
|
"step": 2785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.543001174926758,
|
||
|
|
"epoch": 0.16330114135206322,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.00020794069617439942,
|
||
|
|
"loss": 6.1645,
|
||
|
|
"mean_token_accuracy": 0.14277639836072922,
|
||
|
|
"num_tokens": 5690576.0,
|
||
|
|
"step": 2790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.557866382598877,
|
||
|
|
"epoch": 0.1635937957272461,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00020681706433262593,
|
||
|
|
"loss": 6.2354,
|
||
|
|
"mean_token_accuracy": 0.14037318527698517,
|
||
|
|
"num_tokens": 5701543.0,
|
||
|
|
"step": 2795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5891295909881595,
|
||
|
|
"epoch": 0.16388645010242903,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.00020569530176047602,
|
||
|
|
"loss": 6.18,
|
||
|
|
"mean_token_accuracy": 0.14461203068494796,
|
||
|
|
"num_tokens": 5710679.0,
|
||
|
|
"step": 2800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.563183069229126,
|
||
|
|
"epoch": 0.16417910447761194,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0002045754392116374,
|
||
|
|
"loss": 6.1984,
|
||
|
|
"mean_token_accuracy": 0.13799943327903746,
|
||
|
|
"num_tokens": 5720905.0,
|
||
|
|
"step": 2805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.492629766464233,
|
||
|
|
"epoch": 0.16447175885279486,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.00020345750738770757,
|
||
|
|
"loss": 6.1707,
|
||
|
|
"mean_token_accuracy": 0.14493964090943337,
|
||
|
|
"num_tokens": 5730535.0,
|
||
|
|
"step": 2810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.549330949783325,
|
||
|
|
"epoch": 0.16476441322797775,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00020234153693735214,
|
||
|
|
"loss": 6.2099,
|
||
|
|
"mean_token_accuracy": 0.14195964187383653,
|
||
|
|
"num_tokens": 5740164.0,
|
||
|
|
"step": 2815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.561571788787842,
|
||
|
|
"epoch": 0.16505706760316066,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0002012275584554647,
|
||
|
|
"loss": 6.1065,
|
||
|
|
"mean_token_accuracy": 0.1453681021928787,
|
||
|
|
"num_tokens": 5750135.0,
|
||
|
|
"step": 2820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.53393874168396,
|
||
|
|
"epoch": 0.16534972197834358,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.00020011560248232803,
|
||
|
|
"loss": 6.1865,
|
||
|
|
"mean_token_accuracy": 0.14639652520418167,
|
||
|
|
"num_tokens": 5760178.0,
|
||
|
|
"step": 2825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.491664886474609,
|
||
|
|
"epoch": 0.1656423763535265,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00019900569950277692,
|
||
|
|
"loss": 6.1992,
|
||
|
|
"mean_token_accuracy": 0.1388210326433182,
|
||
|
|
"num_tokens": 5769526.0,
|
||
|
|
"step": 2830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5162426948547365,
|
||
|
|
"epoch": 0.16593503072870938,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00019789787994536228,
|
||
|
|
"loss": 6.1214,
|
||
|
|
"mean_token_accuracy": 0.1437770828604698,
|
||
|
|
"num_tokens": 5779845.0,
|
||
|
|
"step": 2835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5152748107910154,
|
||
|
|
"epoch": 0.1662276851038923,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.00019679217418151667,
|
||
|
|
"loss": 6.2279,
|
||
|
|
"mean_token_accuracy": 0.14030210599303244,
|
||
|
|
"num_tokens": 5789933.0,
|
||
|
|
"step": 2840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.581371164321899,
|
||
|
|
"epoch": 0.1665203394790752,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00019568861252472236,
|
||
|
|
"loss": 6.1639,
|
||
|
|
"mean_token_accuracy": 0.14704412817955018,
|
||
|
|
"num_tokens": 5800328.0,
|
||
|
|
"step": 2845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.559475040435791,
|
||
|
|
"epoch": 0.16681299385425813,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00019458722522967952,
|
||
|
|
"loss": 6.138,
|
||
|
|
"mean_token_accuracy": 0.14048488736152648,
|
||
|
|
"num_tokens": 5810251.0,
|
||
|
|
"step": 2850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.540503358840942,
|
||
|
|
"epoch": 0.16710564822944102,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00019348804249147723,
|
||
|
|
"loss": 6.1713,
|
||
|
|
"mean_token_accuracy": 0.1412585958838463,
|
||
|
|
"num_tokens": 5820553.0,
|
||
|
|
"step": 2855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.523101282119751,
|
||
|
|
"epoch": 0.16739830260462393,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0001923910944447655,
|
||
|
|
"loss": 6.2363,
|
||
|
|
"mean_token_accuracy": 0.14285853803157805,
|
||
|
|
"num_tokens": 5830417.0,
|
||
|
|
"step": 2860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.514103603363037,
|
||
|
|
"epoch": 0.16769095697980685,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.00019129641116292928,
|
||
|
|
"loss": 6.1715,
|
||
|
|
"mean_token_accuracy": 0.14546340107917785,
|
||
|
|
"num_tokens": 5840247.0,
|
||
|
|
"step": 2865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.554553127288818,
|
||
|
|
"epoch": 0.16798361135498976,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.00019020402265726343,
|
||
|
|
"loss": 6.2257,
|
||
|
|
"mean_token_accuracy": 0.14189708530902861,
|
||
|
|
"num_tokens": 5851642.0,
|
||
|
|
"step": 2870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.61158709526062,
|
||
|
|
"epoch": 0.16827626573017265,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0001891139588761509,
|
||
|
|
"loss": 6.1718,
|
||
|
|
"mean_token_accuracy": 0.1385297231376171,
|
||
|
|
"num_tokens": 5861097.0,
|
||
|
|
"step": 2875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.543722200393677,
|
||
|
|
"epoch": 0.16856892010535557,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00018802624970424076,
|
||
|
|
"loss": 6.2754,
|
||
|
|
"mean_token_accuracy": 0.14373085647821426,
|
||
|
|
"num_tokens": 5871571.0,
|
||
|
|
"step": 2880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.492821073532104,
|
||
|
|
"epoch": 0.16886157448053848,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00018694092496162945,
|
||
|
|
"loss": 6.0871,
|
||
|
|
"mean_token_accuracy": 0.15522033274173735,
|
||
|
|
"num_tokens": 5880963.0,
|
||
|
|
"step": 2885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.523477935791016,
|
||
|
|
"epoch": 0.1691542288557214,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.00018585801440304306,
|
||
|
|
"loss": 6.1977,
|
||
|
|
"mean_token_accuracy": 0.14202016219496727,
|
||
|
|
"num_tokens": 5890412.0,
|
||
|
|
"step": 2890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.576770210266114,
|
||
|
|
"epoch": 0.1694468832309043,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.00018477754771702165,
|
||
|
|
"loss": 6.2478,
|
||
|
|
"mean_token_accuracy": 0.13902766183018683,
|
||
|
|
"num_tokens": 5900562.0,
|
||
|
|
"step": 2895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5775594234466555,
|
||
|
|
"epoch": 0.1697395376060872,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.00018369955452510506,
|
||
|
|
"loss": 6.2034,
|
||
|
|
"mean_token_accuracy": 0.1432963989675045,
|
||
|
|
"num_tokens": 5910559.0,
|
||
|
|
"step": 2900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.540433025360107,
|
||
|
|
"epoch": 0.17003219198127012,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0001826240643810212,
|
||
|
|
"loss": 6.1683,
|
||
|
|
"mean_token_accuracy": 0.14233635291457175,
|
||
|
|
"num_tokens": 5920053.0,
|
||
|
|
"step": 2905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.552840805053711,
|
||
|
|
"epoch": 0.17032484635645304,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0001815511067698758,
|
||
|
|
"loss": 6.2065,
|
||
|
|
"mean_token_accuracy": 0.14341727942228316,
|
||
|
|
"num_tokens": 5929609.0,
|
||
|
|
"step": 2910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.512862491607666,
|
||
|
|
"epoch": 0.17061750073163595,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0001804807111073436,
|
||
|
|
"loss": 6.146,
|
||
|
|
"mean_token_accuracy": 0.1410912036895752,
|
||
|
|
"num_tokens": 5938476.0,
|
||
|
|
"step": 2915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.538678359985352,
|
||
|
|
"epoch": 0.17091015510681884,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0001794129067388625,
|
||
|
|
"loss": 6.2291,
|
||
|
|
"mean_token_accuracy": 0.13625446036458017,
|
||
|
|
"num_tokens": 5948937.0,
|
||
|
|
"step": 2920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.591725206375122,
|
||
|
|
"epoch": 0.17120280948200176,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.00017834772293882868,
|
||
|
|
"loss": 6.1844,
|
||
|
|
"mean_token_accuracy": 0.14061932265758514,
|
||
|
|
"num_tokens": 5959676.0,
|
||
|
|
"step": 2925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.602462911605835,
|
||
|
|
"epoch": 0.17149546385718467,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.000177285188909794,
|
||
|
|
"loss": 6.2164,
|
||
|
|
"mean_token_accuracy": 0.13685814663767815,
|
||
|
|
"num_tokens": 5970374.0,
|
||
|
|
"step": 2930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.558568000793457,
|
||
|
|
"epoch": 0.1717881182323676,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0001762253337816656,
|
||
|
|
"loss": 6.2452,
|
||
|
|
"mean_token_accuracy": 0.13835704773664476,
|
||
|
|
"num_tokens": 5980871.0,
|
||
|
|
"step": 2935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.527994441986084,
|
||
|
|
"epoch": 0.17208077260755048,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.00017516818661090738,
|
||
|
|
"loss": 6.191,
|
||
|
|
"mean_token_accuracy": 0.143326635658741,
|
||
|
|
"num_tokens": 5991834.0,
|
||
|
|
"step": 2940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.54395055770874,
|
||
|
|
"epoch": 0.1723734269827334,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0001741137763797428,
|
||
|
|
"loss": 6.1742,
|
||
|
|
"mean_token_accuracy": 0.13280976191163063,
|
||
|
|
"num_tokens": 6002940.0,
|
||
|
|
"step": 2945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.510257530212402,
|
||
|
|
"epoch": 0.1726660813579163,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00017306213199536115,
|
||
|
|
"loss": 6.1959,
|
||
|
|
"mean_token_accuracy": 0.14354807138442993,
|
||
|
|
"num_tokens": 6014321.0,
|
||
|
|
"step": 2950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5832277774810795,
|
||
|
|
"epoch": 0.17295873573309922,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0001720132822891243,
|
||
|
|
"loss": 6.1143,
|
||
|
|
"mean_token_accuracy": 0.1487345390021801,
|
||
|
|
"num_tokens": 6023676.0,
|
||
|
|
"step": 2955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.539546060562134,
|
||
|
|
"epoch": 0.1732513901082821,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0001709672560157769,
|
||
|
|
"loss": 6.2143,
|
||
|
|
"mean_token_accuracy": 0.14421654716134072,
|
||
|
|
"num_tokens": 6033964.0,
|
||
|
|
"step": 2960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.515758275985718,
|
||
|
|
"epoch": 0.17354404448346503,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.00016992408185265758,
|
||
|
|
"loss": 6.1897,
|
||
|
|
"mean_token_accuracy": 0.1415265567600727,
|
||
|
|
"num_tokens": 6043628.0,
|
||
|
|
"step": 2965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.565539932250976,
|
||
|
|
"epoch": 0.17383669885864794,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00016888378839891298,
|
||
|
|
"loss": 6.1572,
|
||
|
|
"mean_token_accuracy": 0.13887002915143967,
|
||
|
|
"num_tokens": 6053149.0,
|
||
|
|
"step": 2970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.514090728759766,
|
||
|
|
"epoch": 0.17412935323383086,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0001678464041747137,
|
||
|
|
"loss": 6.208,
|
||
|
|
"mean_token_accuracy": 0.13517674133181573,
|
||
|
|
"num_tokens": 6062889.0,
|
||
|
|
"step": 2975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.544496774673462,
|
||
|
|
"epoch": 0.17442200760901375,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.00016681195762047223,
|
||
|
|
"loss": 6.2034,
|
||
|
|
"mean_token_accuracy": 0.13485102504491805,
|
||
|
|
"num_tokens": 6073662.0,
|
||
|
|
"step": 2980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.579607248306274,
|
||
|
|
"epoch": 0.17471466198419666,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.00016578047709606337,
|
||
|
|
"loss": 6.22,
|
||
|
|
"mean_token_accuracy": 0.139206163585186,
|
||
|
|
"num_tokens": 6084039.0,
|
||
|
|
"step": 2985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.57672085762024,
|
||
|
|
"epoch": 0.17500731635937958,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00016475199088004678,
|
||
|
|
"loss": 6.209,
|
||
|
|
"mean_token_accuracy": 0.14772867262363434,
|
||
|
|
"num_tokens": 6093929.0,
|
||
|
|
"step": 2990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.504447555541992,
|
||
|
|
"epoch": 0.1752999707345625,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.00016372652716889163,
|
||
|
|
"loss": 6.1379,
|
||
|
|
"mean_token_accuracy": 0.1399600587785244,
|
||
|
|
"num_tokens": 6104472.0,
|
||
|
|
"step": 2995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.562633895874024,
|
||
|
|
"epoch": 0.17559262510974538,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0001627041140762035,
|
||
|
|
"loss": 6.1841,
|
||
|
|
"mean_token_accuracy": 0.1357189230620861,
|
||
|
|
"num_tokens": 6114233.0,
|
||
|
|
"step": 3000
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"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": 1345065734799360.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|