d2120b5eda
Model: fpadovani/tur-latn-100mb-after-ppt-Dp-10mb-ckpt500_seed10 Source: Original Platform
20245 lines
553 KiB
JSON
20245 lines
553 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 9.990551964196918,
|
|
"eval_steps": 1000,
|
|
"global_step": 10050,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 8.122408580780029,
|
|
"epoch": 0.004972650422675286,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 2e-06,
|
|
"loss": 7.8555,
|
|
"mean_token_accuracy": 0.08926185071468354,
|
|
"num_tokens": 9311.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 8.126056098937989,
|
|
"epoch": 0.009945300845350571,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 7.9328,
|
|
"mean_token_accuracy": 0.08018440753221512,
|
|
"num_tokens": 20562.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 8.05552430152893,
|
|
"epoch": 0.014917951268025857,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 7e-06,
|
|
"loss": 7.898,
|
|
"mean_token_accuracy": 0.0867466501891613,
|
|
"num_tokens": 31490.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 8.07232894897461,
|
|
"epoch": 0.019890601690701143,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 7.7975,
|
|
"mean_token_accuracy": 0.09018379971385002,
|
|
"num_tokens": 40741.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 8.081013774871826,
|
|
"epoch": 0.02486325211337643,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 7.7822,
|
|
"mean_token_accuracy": 0.09092294126749038,
|
|
"num_tokens": 50749.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 8.060551881790161,
|
|
"epoch": 0.029835902536051714,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 7.8658,
|
|
"mean_token_accuracy": 0.09334692656993866,
|
|
"num_tokens": 60296.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 8.036958074569702,
|
|
"epoch": 0.034808552958727,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 7.8272,
|
|
"mean_token_accuracy": 0.0933995120227337,
|
|
"num_tokens": 70797.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 8.074491786956788,
|
|
"epoch": 0.039781203381402286,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 7.8404,
|
|
"mean_token_accuracy": 0.08989858850836754,
|
|
"num_tokens": 80815.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 8.017825746536255,
|
|
"epoch": 0.04475385380407757,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 7.813,
|
|
"mean_token_accuracy": 0.0953871764242649,
|
|
"num_tokens": 90326.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 8.046491861343384,
|
|
"epoch": 0.04972650422675286,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 7.8112,
|
|
"mean_token_accuracy": 0.08890505433082581,
|
|
"num_tokens": 99800.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 8.046163415908813,
|
|
"epoch": 0.05469915464942814,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 7.921,
|
|
"mean_token_accuracy": 0.09161711558699608,
|
|
"num_tokens": 110636.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 8.105820083618164,
|
|
"epoch": 0.05967180507210343,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 7.8157,
|
|
"mean_token_accuracy": 0.09141169264912605,
|
|
"num_tokens": 120269.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 8.087437438964844,
|
|
"epoch": 0.06464445549477872,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 7.8186,
|
|
"mean_token_accuracy": 0.08604214638471604,
|
|
"num_tokens": 130176.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 8.022943496704102,
|
|
"epoch": 0.069617105917454,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 7.7724,
|
|
"mean_token_accuracy": 0.09266669675707817,
|
|
"num_tokens": 140020.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 8.029492521286011,
|
|
"epoch": 0.07458975634012929,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 7.8566,
|
|
"mean_token_accuracy": 0.09054757431149482,
|
|
"num_tokens": 150713.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 8.057504415512085,
|
|
"epoch": 0.07956240676280457,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 7.7773,
|
|
"mean_token_accuracy": 0.08817628473043441,
|
|
"num_tokens": 159828.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 8.043695306777954,
|
|
"epoch": 0.08453505718547986,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 7.808,
|
|
"mean_token_accuracy": 0.0962263211607933,
|
|
"num_tokens": 169909.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 8.03000283241272,
|
|
"epoch": 0.08950770760815514,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 7.8599,
|
|
"mean_token_accuracy": 0.0911699652671814,
|
|
"num_tokens": 179462.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 8.082845211029053,
|
|
"epoch": 0.09448035803083044,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 7.8531,
|
|
"mean_token_accuracy": 0.08622325584292412,
|
|
"num_tokens": 188965.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 8.165623950958253,
|
|
"epoch": 0.09945300845350571,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 7.8427,
|
|
"mean_token_accuracy": 0.08928864933550358,
|
|
"num_tokens": 200382.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 8.097312736511231,
|
|
"epoch": 0.10442565887618101,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 7.7246,
|
|
"mean_token_accuracy": 0.09705447182059287,
|
|
"num_tokens": 209718.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.990663337707519,
|
|
"epoch": 0.10939830929885629,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 7.724,
|
|
"mean_token_accuracy": 0.09378693476319314,
|
|
"num_tokens": 219216.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 8.002191734313964,
|
|
"epoch": 0.11437095972153158,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 7.7805,
|
|
"mean_token_accuracy": 0.0973575845360756,
|
|
"num_tokens": 228219.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 8.117930793762207,
|
|
"epoch": 0.11934361014420686,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 7.7441,
|
|
"mean_token_accuracy": 0.08997285291552544,
|
|
"num_tokens": 237776.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.958203458786011,
|
|
"epoch": 0.12431626056688215,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 7.7335,
|
|
"mean_token_accuracy": 0.09299578815698624,
|
|
"num_tokens": 248411.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 8.043806886672973,
|
|
"epoch": 0.12928891098955744,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.8195,
|
|
"mean_token_accuracy": 0.08543559387326241,
|
|
"num_tokens": 258797.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 8.126793479919433,
|
|
"epoch": 0.13426156141223272,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.7469,
|
|
"mean_token_accuracy": 0.09252887964248657,
|
|
"num_tokens": 269228.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.956741619110107,
|
|
"epoch": 0.139234211834908,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.8359,
|
|
"mean_token_accuracy": 0.09155542254447938,
|
|
"num_tokens": 279191.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 8.055004549026489,
|
|
"epoch": 0.14420686225758328,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.7325,
|
|
"mean_token_accuracy": 0.09122926145792007,
|
|
"num_tokens": 289382.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.072270679473878,
|
|
"epoch": 0.14917951268025859,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.6913,
|
|
"mean_token_accuracy": 0.09444988965988159,
|
|
"num_tokens": 299163.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.007786178588868,
|
|
"epoch": 0.15415216310293386,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.7736,
|
|
"mean_token_accuracy": 0.08923879414796829,
|
|
"num_tokens": 308551.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.080718994140625,
|
|
"epoch": 0.15912481352560914,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.736,
|
|
"mean_token_accuracy": 0.08449316844344139,
|
|
"num_tokens": 318427.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.999086856842041,
|
|
"epoch": 0.16409746394828442,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.8093,
|
|
"mean_token_accuracy": 0.08699049055576324,
|
|
"num_tokens": 327539.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.11481409072876,
|
|
"epoch": 0.16907011437095973,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.7423,
|
|
"mean_token_accuracy": 0.09079778492450714,
|
|
"num_tokens": 336676.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.016329479217529,
|
|
"epoch": 0.174042764793635,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.738,
|
|
"mean_token_accuracy": 0.10277078524231911,
|
|
"num_tokens": 345914.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.019076776504516,
|
|
"epoch": 0.1790154152163103,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.7036,
|
|
"mean_token_accuracy": 0.09528676047921181,
|
|
"num_tokens": 355982.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.040568590164185,
|
|
"epoch": 0.1839880656389856,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.7516,
|
|
"mean_token_accuracy": 0.08857373371720315,
|
|
"num_tokens": 365398.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.110048770904541,
|
|
"epoch": 0.18896071606166087,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.755,
|
|
"mean_token_accuracy": 0.0934124194085598,
|
|
"num_tokens": 374519.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.9319648265838625,
|
|
"epoch": 0.19393336648433615,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.6904,
|
|
"mean_token_accuracy": 0.09402457699179649,
|
|
"num_tokens": 383536.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.176937437057495,
|
|
"epoch": 0.19890601690701143,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.77,
|
|
"mean_token_accuracy": 0.0955814115703106,
|
|
"num_tokens": 393703.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.964634227752685,
|
|
"epoch": 0.20387866732968674,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.8693,
|
|
"mean_token_accuracy": 0.08404051922261715,
|
|
"num_tokens": 404065.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.064677190780639,
|
|
"epoch": 0.20885131775236201,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.7777,
|
|
"mean_token_accuracy": 0.0903236448764801,
|
|
"num_tokens": 413869.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.066971015930175,
|
|
"epoch": 0.2138239681750373,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.7805,
|
|
"mean_token_accuracy": 0.0898888312280178,
|
|
"num_tokens": 424251.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.01867208480835,
|
|
"epoch": 0.21879661859771257,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.7275,
|
|
"mean_token_accuracy": 0.09023677036166192,
|
|
"num_tokens": 432530.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.00871753692627,
|
|
"epoch": 0.22376926902038788,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.6977,
|
|
"mean_token_accuracy": 0.09342340901494026,
|
|
"num_tokens": 442335.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.094160842895509,
|
|
"epoch": 0.22874191944306316,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.7204,
|
|
"mean_token_accuracy": 0.09416243061423302,
|
|
"num_tokens": 452048.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.901502513885498,
|
|
"epoch": 0.23371456986573844,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.646,
|
|
"mean_token_accuracy": 0.09958525598049164,
|
|
"num_tokens": 460840.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.078534698486328,
|
|
"epoch": 0.23868722028841372,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.7572,
|
|
"mean_token_accuracy": 0.09259009286761284,
|
|
"num_tokens": 470198.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.032262182235717,
|
|
"epoch": 0.24365987071108902,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.7012,
|
|
"mean_token_accuracy": 0.09810718074440956,
|
|
"num_tokens": 481030.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.884334325790405,
|
|
"epoch": 0.2486325211337643,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.6662,
|
|
"mean_token_accuracy": 0.0929951898753643,
|
|
"num_tokens": 490411.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.049663257598876,
|
|
"epoch": 0.2536051715564396,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.681,
|
|
"mean_token_accuracy": 0.09713885933160782,
|
|
"num_tokens": 499551.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.01776294708252,
|
|
"epoch": 0.2585778219791149,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.7379,
|
|
"mean_token_accuracy": 0.08942644819617271,
|
|
"num_tokens": 508885.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.009857130050658,
|
|
"epoch": 0.26355047240179014,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.7463,
|
|
"mean_token_accuracy": 0.08858433440327644,
|
|
"num_tokens": 518291.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.004399061203003,
|
|
"epoch": 0.26852312282446544,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.6323,
|
|
"mean_token_accuracy": 0.0969871662557125,
|
|
"num_tokens": 528035.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.935997676849365,
|
|
"epoch": 0.27349577324714075,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.6993,
|
|
"mean_token_accuracy": 0.09522532522678376,
|
|
"num_tokens": 538410.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.997100067138672,
|
|
"epoch": 0.278468423669816,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.6389,
|
|
"mean_token_accuracy": 0.09725429192185402,
|
|
"num_tokens": 549697.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.946566820144653,
|
|
"epoch": 0.2834410740924913,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.5314,
|
|
"mean_token_accuracy": 0.10031294599175453,
|
|
"num_tokens": 558932.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.803422832489014,
|
|
"epoch": 0.28841372451516656,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.6543,
|
|
"mean_token_accuracy": 0.0901026301085949,
|
|
"num_tokens": 568441.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.110786485671998,
|
|
"epoch": 0.29338637493784187,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.755,
|
|
"mean_token_accuracy": 0.09423976689577103,
|
|
"num_tokens": 577861.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.907559442520141,
|
|
"epoch": 0.29835902536051717,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.731,
|
|
"mean_token_accuracy": 0.09102459624409676,
|
|
"num_tokens": 587858.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.018079805374146,
|
|
"epoch": 0.3033316757831924,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.7284,
|
|
"mean_token_accuracy": 0.09751355946063996,
|
|
"num_tokens": 597806.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.010554122924805,
|
|
"epoch": 0.30830432620586773,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.6704,
|
|
"mean_token_accuracy": 0.10095374062657356,
|
|
"num_tokens": 607408.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.945669937133789,
|
|
"epoch": 0.31327697662854304,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.6148,
|
|
"mean_token_accuracy": 0.09937258884310722,
|
|
"num_tokens": 617862.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.973281812667847,
|
|
"epoch": 0.3182496270512183,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.6229,
|
|
"mean_token_accuracy": 0.09138860106468201,
|
|
"num_tokens": 627128.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.833469247817993,
|
|
"epoch": 0.3232222774738936,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.627,
|
|
"mean_token_accuracy": 0.09354910627007484,
|
|
"num_tokens": 636775.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.112251043319702,
|
|
"epoch": 0.32819492789656884,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.6205,
|
|
"mean_token_accuracy": 0.09625474289059639,
|
|
"num_tokens": 645906.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.940666913986206,
|
|
"epoch": 0.33316757831924415,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.5624,
|
|
"mean_token_accuracy": 0.09025543108582497,
|
|
"num_tokens": 655601.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.98874797821045,
|
|
"epoch": 0.33814022874191946,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.6814,
|
|
"mean_token_accuracy": 0.09709643945097923,
|
|
"num_tokens": 665682.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.868845844268799,
|
|
"epoch": 0.3431128791645947,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.6302,
|
|
"mean_token_accuracy": 0.09729701802134513,
|
|
"num_tokens": 675200.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.9250412940979,
|
|
"epoch": 0.34808552958727,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.6475,
|
|
"mean_token_accuracy": 0.09828538969159126,
|
|
"num_tokens": 685590.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.931744909286499,
|
|
"epoch": 0.3530581800099453,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.6064,
|
|
"mean_token_accuracy": 0.10055591687560081,
|
|
"num_tokens": 695665.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.942970275878906,
|
|
"epoch": 0.3580308304326206,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.664,
|
|
"mean_token_accuracy": 0.09400481581687928,
|
|
"num_tokens": 705850.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.049799823760987,
|
|
"epoch": 0.3630034808552959,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.6738,
|
|
"mean_token_accuracy": 0.0901768684387207,
|
|
"num_tokens": 716010.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.923341178894043,
|
|
"epoch": 0.3679761312779712,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.6223,
|
|
"mean_token_accuracy": 0.09590414240956306,
|
|
"num_tokens": 724908.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.7986541271209715,
|
|
"epoch": 0.37294878170064644,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.5942,
|
|
"mean_token_accuracy": 0.09819011092185974,
|
|
"num_tokens": 733479.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.961906242370605,
|
|
"epoch": 0.37792143212332174,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.6145,
|
|
"mean_token_accuracy": 0.09582870304584504,
|
|
"num_tokens": 743365.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.91075963973999,
|
|
"epoch": 0.382894082545997,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.6664,
|
|
"mean_token_accuracy": 0.09616638831794262,
|
|
"num_tokens": 753720.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.916628408432007,
|
|
"epoch": 0.3878667329686723,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.5311,
|
|
"mean_token_accuracy": 0.0964023895561695,
|
|
"num_tokens": 762524.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.922145891189575,
|
|
"epoch": 0.3928393833913476,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.6111,
|
|
"mean_token_accuracy": 0.09766499325633049,
|
|
"num_tokens": 772549.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.79258098602295,
|
|
"epoch": 0.39781203381402286,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.6114,
|
|
"mean_token_accuracy": 0.09619558006525039,
|
|
"num_tokens": 782304.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.05925145149231,
|
|
"epoch": 0.40278468423669817,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.7212,
|
|
"mean_token_accuracy": 0.09696372747421264,
|
|
"num_tokens": 792010.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.807120895385742,
|
|
"epoch": 0.40775733465937347,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.5492,
|
|
"mean_token_accuracy": 0.10038653984665871,
|
|
"num_tokens": 801667.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.899970769882202,
|
|
"epoch": 0.4127299850820487,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.6252,
|
|
"mean_token_accuracy": 0.09784654006361962,
|
|
"num_tokens": 812385.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.8692365169525145,
|
|
"epoch": 0.41770263550472403,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.535,
|
|
"mean_token_accuracy": 0.10144751518964767,
|
|
"num_tokens": 822177.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.8849406242370605,
|
|
"epoch": 0.4226752859273993,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.5996,
|
|
"mean_token_accuracy": 0.09166432395577431,
|
|
"num_tokens": 832576.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.780496835708618,
|
|
"epoch": 0.4276479363500746,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.566,
|
|
"mean_token_accuracy": 0.09900226145982742,
|
|
"num_tokens": 842290.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.872547626495361,
|
|
"epoch": 0.4326205867727499,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.585,
|
|
"mean_token_accuracy": 0.09592773094773292,
|
|
"num_tokens": 852500.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.809439420700073,
|
|
"epoch": 0.43759323719542514,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.4945,
|
|
"mean_token_accuracy": 0.09826857671141624,
|
|
"num_tokens": 861401.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.860213375091552,
|
|
"epoch": 0.44256588761810045,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.5047,
|
|
"mean_token_accuracy": 0.10223424881696701,
|
|
"num_tokens": 871523.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.898686456680298,
|
|
"epoch": 0.44753853804077576,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.605,
|
|
"mean_token_accuracy": 0.090828076004982,
|
|
"num_tokens": 881384.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.867025518417359,
|
|
"epoch": 0.452511188463451,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.6307,
|
|
"mean_token_accuracy": 0.09517297595739364,
|
|
"num_tokens": 890511.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.833306884765625,
|
|
"epoch": 0.4574838388861263,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.563,
|
|
"mean_token_accuracy": 0.09683875888586044,
|
|
"num_tokens": 900064.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.857913303375244,
|
|
"epoch": 0.46245648930880157,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.6161,
|
|
"mean_token_accuracy": 0.09450365006923675,
|
|
"num_tokens": 910892.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.899250507354736,
|
|
"epoch": 0.4674291397314769,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.6154,
|
|
"mean_token_accuracy": 0.09202362224459648,
|
|
"num_tokens": 920566.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.7721343517303465,
|
|
"epoch": 0.4724017901541522,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.5319,
|
|
"mean_token_accuracy": 0.09768470898270606,
|
|
"num_tokens": 930609.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.801538562774658,
|
|
"epoch": 0.47737444057682743,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.565,
|
|
"mean_token_accuracy": 0.09313339218497277,
|
|
"num_tokens": 940383.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.941165828704834,
|
|
"epoch": 0.48234709099950274,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.5122,
|
|
"mean_token_accuracy": 0.09608981050550938,
|
|
"num_tokens": 951302.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.788536548614502,
|
|
"epoch": 0.48731974142217804,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.4818,
|
|
"mean_token_accuracy": 0.10193300023674964,
|
|
"num_tokens": 961126.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.839777183532715,
|
|
"epoch": 0.4922923918448533,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.5032,
|
|
"mean_token_accuracy": 0.09682125523686409,
|
|
"num_tokens": 970845.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.721405076980591,
|
|
"epoch": 0.4972650422675286,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.427,
|
|
"mean_token_accuracy": 0.10273272842168808,
|
|
"num_tokens": 980919.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.719191455841065,
|
|
"epoch": 0.5022376926902039,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.4516,
|
|
"mean_token_accuracy": 0.1017610639333725,
|
|
"num_tokens": 990659.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.737829732894897,
|
|
"epoch": 0.5072103431128792,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.514,
|
|
"mean_token_accuracy": 0.1017485462129116,
|
|
"num_tokens": 999540.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.7914680480957035,
|
|
"epoch": 0.5121829935355544,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.5122,
|
|
"mean_token_accuracy": 0.09308664873242378,
|
|
"num_tokens": 1008688.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.721870851516724,
|
|
"epoch": 0.5171556439582298,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.4086,
|
|
"mean_token_accuracy": 0.1110854797065258,
|
|
"num_tokens": 1018310.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.716399812698365,
|
|
"epoch": 0.522128294380905,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.5061,
|
|
"mean_token_accuracy": 0.0994237333536148,
|
|
"num_tokens": 1027973.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.801226186752319,
|
|
"epoch": 0.5271009448035803,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.4382,
|
|
"mean_token_accuracy": 0.1021985501050949,
|
|
"num_tokens": 1038141.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.658663749694824,
|
|
"epoch": 0.5320735952262556,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.5474,
|
|
"mean_token_accuracy": 0.09069671258330345,
|
|
"num_tokens": 1047932.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.632207870483398,
|
|
"epoch": 0.5370462456489309,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.3242,
|
|
"mean_token_accuracy": 0.10905587524175644,
|
|
"num_tokens": 1056826.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.736492490768432,
|
|
"epoch": 0.5420188960716061,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.4832,
|
|
"mean_token_accuracy": 0.10051515996456147,
|
|
"num_tokens": 1066025.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.75524320602417,
|
|
"epoch": 0.5469915464942815,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.4987,
|
|
"mean_token_accuracy": 0.09955808669328689,
|
|
"num_tokens": 1075452.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.787500476837158,
|
|
"epoch": 0.5519641969169568,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.5126,
|
|
"mean_token_accuracy": 0.09939858093857765,
|
|
"num_tokens": 1085300.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.606941556930542,
|
|
"epoch": 0.556936847339632,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.3578,
|
|
"mean_token_accuracy": 0.10578031092882156,
|
|
"num_tokens": 1094548.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.804773807525635,
|
|
"epoch": 0.5619094977623074,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.4029,
|
|
"mean_token_accuracy": 0.09974669739603996,
|
|
"num_tokens": 1104321.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.712262105941773,
|
|
"epoch": 0.5668821481849826,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.544,
|
|
"mean_token_accuracy": 0.0965195819735527,
|
|
"num_tokens": 1115047.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.739543342590332,
|
|
"epoch": 0.5718547986076579,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.5043,
|
|
"mean_token_accuracy": 0.10095428079366683,
|
|
"num_tokens": 1124757.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.72175817489624,
|
|
"epoch": 0.5768274490303331,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.4489,
|
|
"mean_token_accuracy": 0.09865402802824974,
|
|
"num_tokens": 1134255.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.810949993133545,
|
|
"epoch": 0.5818000994530085,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.5124,
|
|
"mean_token_accuracy": 0.09687942638993263,
|
|
"num_tokens": 1143117.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.622174072265625,
|
|
"epoch": 0.5867727498756837,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.3751,
|
|
"mean_token_accuracy": 0.10171565413475037,
|
|
"num_tokens": 1153203.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.735700798034668,
|
|
"epoch": 0.591745400298359,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.416,
|
|
"mean_token_accuracy": 0.10218172967433929,
|
|
"num_tokens": 1162839.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.567971992492676,
|
|
"epoch": 0.5967180507210343,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.3696,
|
|
"mean_token_accuracy": 0.1032779723405838,
|
|
"num_tokens": 1172580.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.7000068664550785,
|
|
"epoch": 0.6016907011437096,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.3688,
|
|
"mean_token_accuracy": 0.10539614930748939,
|
|
"num_tokens": 1183715.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.688623571395874,
|
|
"epoch": 0.6066633515663848,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.5444,
|
|
"mean_token_accuracy": 0.09419808611273765,
|
|
"num_tokens": 1194217.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.695876932144165,
|
|
"epoch": 0.6116360019890602,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.4023,
|
|
"mean_token_accuracy": 0.10362396463751793,
|
|
"num_tokens": 1203297.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.752481842041016,
|
|
"epoch": 0.6166086524117355,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.5044,
|
|
"mean_token_accuracy": 0.09252066910266876,
|
|
"num_tokens": 1213394.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.600792169570923,
|
|
"epoch": 0.6215813028344107,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.485,
|
|
"mean_token_accuracy": 0.10286026149988174,
|
|
"num_tokens": 1222771.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.684136581420899,
|
|
"epoch": 0.6265539532570861,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.4382,
|
|
"mean_token_accuracy": 0.09525436088442803,
|
|
"num_tokens": 1232171.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.607944822311401,
|
|
"epoch": 0.6315266036797613,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.3756,
|
|
"mean_token_accuracy": 0.1039860226213932,
|
|
"num_tokens": 1241640.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.603791999816894,
|
|
"epoch": 0.6364992541024366,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.3979,
|
|
"mean_token_accuracy": 0.10446851849555969,
|
|
"num_tokens": 1251785.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.632256364822387,
|
|
"epoch": 0.6414719045251119,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.3945,
|
|
"mean_token_accuracy": 0.09782340601086617,
|
|
"num_tokens": 1262327.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.627688646316528,
|
|
"epoch": 0.6464445549477872,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.3077,
|
|
"mean_token_accuracy": 0.10489342957735062,
|
|
"num_tokens": 1270871.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.533834218978882,
|
|
"epoch": 0.6514172053704624,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.3627,
|
|
"mean_token_accuracy": 0.10482602864503861,
|
|
"num_tokens": 1281563.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.566735506057739,
|
|
"epoch": 0.6563898557931377,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.3783,
|
|
"mean_token_accuracy": 0.09988497495651245,
|
|
"num_tokens": 1290867.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.6221600532531735,
|
|
"epoch": 0.661362506215813,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.3859,
|
|
"mean_token_accuracy": 0.10277852416038513,
|
|
"num_tokens": 1300384.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.620599699020386,
|
|
"epoch": 0.6663351566384883,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.3065,
|
|
"mean_token_accuracy": 0.10421342998743058,
|
|
"num_tokens": 1310443.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.551718235015869,
|
|
"epoch": 0.6713078070611636,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.2883,
|
|
"mean_token_accuracy": 0.10518570244312286,
|
|
"num_tokens": 1320345.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.555121326446534,
|
|
"epoch": 0.6762804574838389,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.4677,
|
|
"mean_token_accuracy": 0.09977790042757988,
|
|
"num_tokens": 1330868.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.603720664978027,
|
|
"epoch": 0.6812531079065142,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.3716,
|
|
"mean_token_accuracy": 0.10149549767374992,
|
|
"num_tokens": 1340605.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.610010147094727,
|
|
"epoch": 0.6862257583291894,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.3887,
|
|
"mean_token_accuracy": 0.1037661112844944,
|
|
"num_tokens": 1350248.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.414504098892212,
|
|
"epoch": 0.6911984087518648,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.3681,
|
|
"mean_token_accuracy": 0.10223357081413269,
|
|
"num_tokens": 1360251.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.644025135040283,
|
|
"epoch": 0.69617105917454,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.295,
|
|
"mean_token_accuracy": 0.10866039916872978,
|
|
"num_tokens": 1370156.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.5345031261444095,
|
|
"epoch": 0.7011437095972153,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.4874,
|
|
"mean_token_accuracy": 0.09497825279831887,
|
|
"num_tokens": 1380346.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.57585654258728,
|
|
"epoch": 0.7061163600198906,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.3459,
|
|
"mean_token_accuracy": 0.10090088471770287,
|
|
"num_tokens": 1390958.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.568233871459961,
|
|
"epoch": 0.7110890104425659,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.4193,
|
|
"mean_token_accuracy": 0.10254513472318649,
|
|
"num_tokens": 1400324.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.632588481903076,
|
|
"epoch": 0.7160616608652411,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.3289,
|
|
"mean_token_accuracy": 0.10863603204488755,
|
|
"num_tokens": 1410272.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.395322036743164,
|
|
"epoch": 0.7210343112879165,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.3459,
|
|
"mean_token_accuracy": 0.1074515551328659,
|
|
"num_tokens": 1420061.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.52363076210022,
|
|
"epoch": 0.7260069617105918,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.3027,
|
|
"mean_token_accuracy": 0.10952795967459679,
|
|
"num_tokens": 1428771.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.477725315093994,
|
|
"epoch": 0.730979612133267,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.3102,
|
|
"mean_token_accuracy": 0.1064012736082077,
|
|
"num_tokens": 1438154.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.440126705169678,
|
|
"epoch": 0.7359522625559424,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.2848,
|
|
"mean_token_accuracy": 0.10690619945526122,
|
|
"num_tokens": 1447403.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.531488990783691,
|
|
"epoch": 0.7409249129786176,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.3787,
|
|
"mean_token_accuracy": 0.09951569363474846,
|
|
"num_tokens": 1457443.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.509539699554443,
|
|
"epoch": 0.7458975634012929,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.3605,
|
|
"mean_token_accuracy": 0.10302009806036949,
|
|
"num_tokens": 1466783.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.600085258483887,
|
|
"epoch": 0.7508702138239681,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.3581,
|
|
"mean_token_accuracy": 0.10676125213503837,
|
|
"num_tokens": 1476320.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.455271196365357,
|
|
"epoch": 0.7558428642466435,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.2729,
|
|
"mean_token_accuracy": 0.10698438361287117,
|
|
"num_tokens": 1487581.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.526057958602905,
|
|
"epoch": 0.7608155146693187,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.4161,
|
|
"mean_token_accuracy": 0.0985928162932396,
|
|
"num_tokens": 1496455.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.511812591552735,
|
|
"epoch": 0.765788165091994,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.348,
|
|
"mean_token_accuracy": 0.10783538296818733,
|
|
"num_tokens": 1506422.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.514915466308594,
|
|
"epoch": 0.7707608155146694,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.3114,
|
|
"mean_token_accuracy": 0.10534781441092492,
|
|
"num_tokens": 1516593.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.418980598449707,
|
|
"epoch": 0.7757334659373446,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.3705,
|
|
"mean_token_accuracy": 0.10273290202021598,
|
|
"num_tokens": 1526011.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.522382354736328,
|
|
"epoch": 0.7807061163600199,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.2848,
|
|
"mean_token_accuracy": 0.1055482119321823,
|
|
"num_tokens": 1536018.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.341956090927124,
|
|
"epoch": 0.7856787667826952,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.224,
|
|
"mean_token_accuracy": 0.10807310789823532,
|
|
"num_tokens": 1545568.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.458911895751953,
|
|
"epoch": 0.7906514172053705,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.2246,
|
|
"mean_token_accuracy": 0.10711941570043564,
|
|
"num_tokens": 1556389.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.578403520584106,
|
|
"epoch": 0.7956240676280457,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.3641,
|
|
"mean_token_accuracy": 0.10444995686411858,
|
|
"num_tokens": 1565587.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.33792815208435,
|
|
"epoch": 0.8005967180507211,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.2441,
|
|
"mean_token_accuracy": 0.10755613222718238,
|
|
"num_tokens": 1574911.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.365066766738892,
|
|
"epoch": 0.8055693684733963,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.2242,
|
|
"mean_token_accuracy": 0.11039689257740974,
|
|
"num_tokens": 1584477.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.408384799957275,
|
|
"epoch": 0.8105420188960716,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.2922,
|
|
"mean_token_accuracy": 0.1128959059715271,
|
|
"num_tokens": 1594408.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.360699558258057,
|
|
"epoch": 0.8155146693187469,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.247,
|
|
"mean_token_accuracy": 0.10692444741725922,
|
|
"num_tokens": 1603494.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.462933492660523,
|
|
"epoch": 0.8204873197414222,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.35,
|
|
"mean_token_accuracy": 0.10176746174693108,
|
|
"num_tokens": 1612994.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.455133867263794,
|
|
"epoch": 0.8254599701640974,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.2032,
|
|
"mean_token_accuracy": 0.10662396997213364,
|
|
"num_tokens": 1622150.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.382295083999634,
|
|
"epoch": 0.8304326205867727,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.2319,
|
|
"mean_token_accuracy": 0.1111760102212429,
|
|
"num_tokens": 1631040.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.31751708984375,
|
|
"epoch": 0.8354052710094481,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.192,
|
|
"mean_token_accuracy": 0.11513797119259835,
|
|
"num_tokens": 1641519.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.354842281341552,
|
|
"epoch": 0.8403779214321233,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.2668,
|
|
"mean_token_accuracy": 0.10789724364876747,
|
|
"num_tokens": 1652218.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.601192665100098,
|
|
"epoch": 0.8453505718547986,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.3301,
|
|
"mean_token_accuracy": 0.09921003803610802,
|
|
"num_tokens": 1663763.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.362071323394775,
|
|
"epoch": 0.8503232222774739,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.2763,
|
|
"mean_token_accuracy": 0.10137885957956314,
|
|
"num_tokens": 1674160.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.43802547454834,
|
|
"epoch": 0.8552958727001492,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.4024,
|
|
"mean_token_accuracy": 0.10859992802143097,
|
|
"num_tokens": 1685138.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.443594169616699,
|
|
"epoch": 0.8602685231228244,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.2993,
|
|
"mean_token_accuracy": 0.10044958740472794,
|
|
"num_tokens": 1694847.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.433558607101441,
|
|
"epoch": 0.8652411735454998,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.2772,
|
|
"mean_token_accuracy": 0.10592831820249557,
|
|
"num_tokens": 1704503.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.368968296051025,
|
|
"epoch": 0.870213823968175,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.2668,
|
|
"mean_token_accuracy": 0.10812032371759414,
|
|
"num_tokens": 1714011.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.3641283988952635,
|
|
"epoch": 0.8751864743908503,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.2193,
|
|
"mean_token_accuracy": 0.10835571512579918,
|
|
"num_tokens": 1724254.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.2866339683532715,
|
|
"epoch": 0.8801591248135257,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.2739,
|
|
"mean_token_accuracy": 0.10235930308699608,
|
|
"num_tokens": 1734696.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.365292119979858,
|
|
"epoch": 0.8851317752362009,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.2165,
|
|
"mean_token_accuracy": 0.11037806496024131,
|
|
"num_tokens": 1743650.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.375092315673828,
|
|
"epoch": 0.8901044256588762,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.175,
|
|
"mean_token_accuracy": 0.11102150678634644,
|
|
"num_tokens": 1753449.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.370843553543091,
|
|
"epoch": 0.8950770760815515,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.322,
|
|
"mean_token_accuracy": 0.10787996426224708,
|
|
"num_tokens": 1764104.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.183559894561768,
|
|
"epoch": 0.9000497265042268,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.0971,
|
|
"mean_token_accuracy": 0.11445347592234612,
|
|
"num_tokens": 1773172.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.315752792358398,
|
|
"epoch": 0.905022376926902,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.1655,
|
|
"mean_token_accuracy": 0.1090462140738964,
|
|
"num_tokens": 1783268.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.2884824752807615,
|
|
"epoch": 0.9099950273495774,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.2384,
|
|
"mean_token_accuracy": 0.1040517307817936,
|
|
"num_tokens": 1792169.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.355252885818482,
|
|
"epoch": 0.9149676777722526,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.2273,
|
|
"mean_token_accuracy": 0.10773444548249245,
|
|
"num_tokens": 1802280.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.304852056503296,
|
|
"epoch": 0.9199403281949279,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.2212,
|
|
"mean_token_accuracy": 0.10946610048413277,
|
|
"num_tokens": 1812086.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.223779201507568,
|
|
"epoch": 0.9249129786176031,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.2053,
|
|
"mean_token_accuracy": 0.11222834661602973,
|
|
"num_tokens": 1821554.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.391703653335571,
|
|
"epoch": 0.9298856290402785,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.2522,
|
|
"mean_token_accuracy": 0.1073651947081089,
|
|
"num_tokens": 1831088.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.282382965087891,
|
|
"epoch": 0.9348582794629537,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.2627,
|
|
"mean_token_accuracy": 0.11030717194080353,
|
|
"num_tokens": 1840606.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.240512847900391,
|
|
"epoch": 0.939830929885629,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.1708,
|
|
"mean_token_accuracy": 0.11626142486929894,
|
|
"num_tokens": 1850343.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.2862786769866945,
|
|
"epoch": 0.9448035803083044,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.2798,
|
|
"mean_token_accuracy": 0.10937313660979271,
|
|
"num_tokens": 1860727.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.274987268447876,
|
|
"epoch": 0.9497762307309796,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.1902,
|
|
"mean_token_accuracy": 0.10906597152352333,
|
|
"num_tokens": 1870703.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.29812650680542,
|
|
"epoch": 0.9547488811536549,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.2196,
|
|
"mean_token_accuracy": 0.10876635760068894,
|
|
"num_tokens": 1880694.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.354408121109008,
|
|
"epoch": 0.9597215315763302,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.163,
|
|
"mean_token_accuracy": 0.1110567644238472,
|
|
"num_tokens": 1890195.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.202347040176392,
|
|
"epoch": 0.9646941819990055,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.1253,
|
|
"mean_token_accuracy": 0.11104833781719207,
|
|
"num_tokens": 1900221.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.143579006195068,
|
|
"epoch": 0.9696668324216807,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.1785,
|
|
"mean_token_accuracy": 0.11059431210160256,
|
|
"num_tokens": 1910122.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.353754472732544,
|
|
"epoch": 0.9746394828443561,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.1831,
|
|
"mean_token_accuracy": 0.11084778457880021,
|
|
"num_tokens": 1918814.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.168116044998169,
|
|
"epoch": 0.9796121332670313,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.1749,
|
|
"mean_token_accuracy": 0.11735359057784081,
|
|
"num_tokens": 1928446.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.272993516921997,
|
|
"epoch": 0.9845847836897066,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.1308,
|
|
"mean_token_accuracy": 0.1103288859128952,
|
|
"num_tokens": 1939060.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.2277168273925785,
|
|
"epoch": 0.989557434112382,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.1353,
|
|
"mean_token_accuracy": 0.11369294598698616,
|
|
"num_tokens": 1948809.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.233875274658203,
|
|
"epoch": 0.9945300845350572,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.1353,
|
|
"mean_token_accuracy": 0.11033130958676338,
|
|
"num_tokens": 1959232.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"epoch": 0.9945300845350572,
|
|
"eval_entropy": 7.227099574655981,
|
|
"eval_loss": 7.268585205078125,
|
|
"eval_mean_token_accuracy": 0.10413067842820822,
|
|
"eval_num_tokens": 1959232.0,
|
|
"eval_runtime": 2.5901,
|
|
"eval_samples_per_second": 1337.795,
|
|
"eval_steps_per_second": 167.562,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.177479839324951,
|
|
"epoch": 0.9995027349577325,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999997830922735,
|
|
"loss": 7.0681,
|
|
"mean_token_accuracy": 0.11539435237646103,
|
|
"num_tokens": 1969117.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.297568957010905,
|
|
"epoch": 1.0039781203381402,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999989019053515,
|
|
"loss": 7.1097,
|
|
"mean_token_accuracy": 0.11202286763323678,
|
|
"num_tokens": 1978202.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.039242362976074,
|
|
"epoch": 1.0089507707608154,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999973428851536,
|
|
"loss": 6.8775,
|
|
"mean_token_accuracy": 0.12471100017428398,
|
|
"num_tokens": 1988085.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.2135011672973635,
|
|
"epoch": 1.0139234211834909,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999951060363766,
|
|
"loss": 6.8566,
|
|
"mean_token_accuracy": 0.12106488719582557,
|
|
"num_tokens": 1996977.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.1463054656982425,
|
|
"epoch": 1.0188960716061661,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999921913657592,
|
|
"loss": 6.9291,
|
|
"mean_token_accuracy": 0.11656595915555953,
|
|
"num_tokens": 2006622.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.221590375900268,
|
|
"epoch": 1.0238687220288414,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999885988820821,
|
|
"loss": 7.0479,
|
|
"mean_token_accuracy": 0.11268379613757133,
|
|
"num_tokens": 2016390.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.181693983078003,
|
|
"epoch": 1.0288413724515166,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999843285961683,
|
|
"loss": 6.8967,
|
|
"mean_token_accuracy": 0.11597555577754974,
|
|
"num_tokens": 2026439.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.143760633468628,
|
|
"epoch": 1.0338140228741919,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999793805208822,
|
|
"loss": 6.9743,
|
|
"mean_token_accuracy": 0.12400304973125457,
|
|
"num_tokens": 2035611.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.12859525680542,
|
|
"epoch": 1.0387866732968671,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999737546711305,
|
|
"loss": 6.9878,
|
|
"mean_token_accuracy": 0.11458344608545304,
|
|
"num_tokens": 2047166.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.1092852592468265,
|
|
"epoch": 1.0437593237195426,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999674510638618,
|
|
"loss": 6.9031,
|
|
"mean_token_accuracy": 0.11905743703246116,
|
|
"num_tokens": 2057216.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.121430969238281,
|
|
"epoch": 1.0487319741422179,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999604697180661,
|
|
"loss": 6.9688,
|
|
"mean_token_accuracy": 0.11538073271512986,
|
|
"num_tokens": 2067339.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.104109287261963,
|
|
"epoch": 1.053704624564893,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999528106547759,
|
|
"loss": 6.851,
|
|
"mean_token_accuracy": 0.11959391385316849,
|
|
"num_tokens": 2077815.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.016418695449829,
|
|
"epoch": 1.0586772749875684,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999444738970644,
|
|
"loss": 6.9525,
|
|
"mean_token_accuracy": 0.11269129067659378,
|
|
"num_tokens": 2087738.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.061359930038452,
|
|
"epoch": 1.0636499254102436,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999354594700474,
|
|
"loss": 6.885,
|
|
"mean_token_accuracy": 0.11644371598958969,
|
|
"num_tokens": 2097246.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.8907383441925045,
|
|
"epoch": 1.0686225758329189,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999257674008817,
|
|
"loss": 6.8094,
|
|
"mean_token_accuracy": 0.12704239040613174,
|
|
"num_tokens": 2106415.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.081757068634033,
|
|
"epoch": 1.0735952262555943,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999153977187656,
|
|
"loss": 6.7604,
|
|
"mean_token_accuracy": 0.12543603628873826,
|
|
"num_tokens": 2115950.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.131565284729004,
|
|
"epoch": 1.0785678766782696,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499904350454939,
|
|
"loss": 7.0008,
|
|
"mean_token_accuracy": 0.12020133659243584,
|
|
"num_tokens": 2127896.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.041161298751831,
|
|
"epoch": 1.0835405271009448,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998926256426829,
|
|
"loss": 6.9288,
|
|
"mean_token_accuracy": 0.11448188871145248,
|
|
"num_tokens": 2137238.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.940253067016601,
|
|
"epoch": 1.08851317752362,
|
|
"grad_norm": 3.796875,
|
|
"learning_rate": 0.0004998802233173196,
|
|
"loss": 6.9006,
|
|
"mean_token_accuracy": 0.1144180566072464,
|
|
"num_tokens": 2147107.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.133631563186645,
|
|
"epoch": 1.0934858279462953,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998671435162123,
|
|
"loss": 6.9704,
|
|
"mean_token_accuracy": 0.11777857169508935,
|
|
"num_tokens": 2157128.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.987091588973999,
|
|
"epoch": 1.0984584783689706,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998533862787657,
|
|
"loss": 6.9113,
|
|
"mean_token_accuracy": 0.11355555281043053,
|
|
"num_tokens": 2167981.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.0585156917572025,
|
|
"epoch": 1.1034311287916458,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998389516464244,
|
|
"loss": 6.8561,
|
|
"mean_token_accuracy": 0.11993846967816353,
|
|
"num_tokens": 2177659.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.066860008239746,
|
|
"epoch": 1.1084037792143213,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998238396626746,
|
|
"loss": 6.8788,
|
|
"mean_token_accuracy": 0.1190800815820694,
|
|
"num_tokens": 2186936.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.104629707336426,
|
|
"epoch": 1.1133764296369966,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998080503730427,
|
|
"loss": 6.9139,
|
|
"mean_token_accuracy": 0.12040532752871513,
|
|
"num_tokens": 2197126.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.996875047683716,
|
|
"epoch": 1.1183490800596718,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997915838250956,
|
|
"loss": 6.9362,
|
|
"mean_token_accuracy": 0.11848222240805625,
|
|
"num_tokens": 2206337.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.024795484542847,
|
|
"epoch": 1.123321730482347,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997744400684406,
|
|
"loss": 6.8698,
|
|
"mean_token_accuracy": 0.115912526845932,
|
|
"num_tokens": 2217112.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.095630693435669,
|
|
"epoch": 1.1282943809050223,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997566191547251,
|
|
"loss": 6.9678,
|
|
"mean_token_accuracy": 0.11383809894323349,
|
|
"num_tokens": 2226239.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.096014213562012,
|
|
"epoch": 1.1332670313276976,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997381211376364,
|
|
"loss": 6.9894,
|
|
"mean_token_accuracy": 0.11798062771558762,
|
|
"num_tokens": 2235702.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.03745436668396,
|
|
"epoch": 1.138239681750373,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997189460729019,
|
|
"loss": 6.9407,
|
|
"mean_token_accuracy": 0.12207928895950318,
|
|
"num_tokens": 2246005.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.008592653274536,
|
|
"epoch": 1.1432123321730483,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996990940182884,
|
|
"loss": 6.903,
|
|
"mean_token_accuracy": 0.12116350829601288,
|
|
"num_tokens": 2255534.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.113993358612061,
|
|
"epoch": 1.1481849825957235,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996785650336024,
|
|
"loss": 6.977,
|
|
"mean_token_accuracy": 0.1165345698595047,
|
|
"num_tokens": 2266374.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.927402591705322,
|
|
"epoch": 1.1531576330183988,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996573591806898,
|
|
"loss": 6.7571,
|
|
"mean_token_accuracy": 0.12876896783709527,
|
|
"num_tokens": 2275614.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.9787169933319095,
|
|
"epoch": 1.158130283441074,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996354765234353,
|
|
"loss": 6.8386,
|
|
"mean_token_accuracy": 0.13057343736290933,
|
|
"num_tokens": 2284403.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.033973646163941,
|
|
"epoch": 1.1631029338637493,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996129171277628,
|
|
"loss": 6.9209,
|
|
"mean_token_accuracy": 0.11778316348791122,
|
|
"num_tokens": 2294153.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.958228731155396,
|
|
"epoch": 1.1680755842864246,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995896810616349,
|
|
"loss": 6.8837,
|
|
"mean_token_accuracy": 0.12165310680866241,
|
|
"num_tokens": 2302897.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.121665811538696,
|
|
"epoch": 1.1730482347091,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995657683950528,
|
|
"loss": 6.9827,
|
|
"mean_token_accuracy": 0.11410253793001175,
|
|
"num_tokens": 2312483.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.747711133956909,
|
|
"epoch": 1.1780208851317753,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995411792000559,
|
|
"loss": 6.779,
|
|
"mean_token_accuracy": 0.12839893773198127,
|
|
"num_tokens": 2321911.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.108477783203125,
|
|
"epoch": 1.1829935355544505,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995159135507218,
|
|
"loss": 7.0208,
|
|
"mean_token_accuracy": 0.12018021941184998,
|
|
"num_tokens": 2331932.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.837444925308228,
|
|
"epoch": 1.1879661859771258,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499489971523166,
|
|
"loss": 6.8088,
|
|
"mean_token_accuracy": 0.126504997164011,
|
|
"num_tokens": 2342264.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.097235155105591,
|
|
"epoch": 1.192938836399801,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004994633531955415,
|
|
"loss": 6.9754,
|
|
"mean_token_accuracy": 0.11833128929138184,
|
|
"num_tokens": 2353068.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.940999603271484,
|
|
"epoch": 1.1979114868224765,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994360586480391,
|
|
"loss": 6.7782,
|
|
"mean_token_accuracy": 0.12161566987633705,
|
|
"num_tokens": 2361765.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.015862894058228,
|
|
"epoch": 1.2028841372451518,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994080879628864,
|
|
"loss": 6.8349,
|
|
"mean_token_accuracy": 0.11880438923835754,
|
|
"num_tokens": 2372721.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.931281423568725,
|
|
"epoch": 1.207856787667827,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004993794412243481,
|
|
"loss": 6.9136,
|
|
"mean_token_accuracy": 0.1202242910861969,
|
|
"num_tokens": 2382288.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.987937498092651,
|
|
"epoch": 1.2128294380905023,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993501185187255,
|
|
"loss": 6.9225,
|
|
"mean_token_accuracy": 0.1201055109500885,
|
|
"num_tokens": 2391953.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.024634742736817,
|
|
"epoch": 1.2178020885131775,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993201199343565,
|
|
"loss": 6.9557,
|
|
"mean_token_accuracy": 0.11614167094230651,
|
|
"num_tokens": 2402705.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.973006725311279,
|
|
"epoch": 1.2227747389358528,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992894455616149,
|
|
"loss": 6.9007,
|
|
"mean_token_accuracy": 0.11774003282189369,
|
|
"num_tokens": 2412654.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.076304149627686,
|
|
"epoch": 1.227747389358528,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992580954929108,
|
|
"loss": 7.0036,
|
|
"mean_token_accuracy": 0.12298540249466897,
|
|
"num_tokens": 2422958.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.919585371017456,
|
|
"epoch": 1.2327200397812033,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004992260698226894,
|
|
"loss": 6.8278,
|
|
"mean_token_accuracy": 0.1256534494459629,
|
|
"num_tokens": 2432274.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.986346006393433,
|
|
"epoch": 1.2376926902038787,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004991933686474315,
|
|
"loss": 6.9947,
|
|
"mean_token_accuracy": 0.11662818863987923,
|
|
"num_tokens": 2443818.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.016325521469116,
|
|
"epoch": 1.242665340626554,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991599920656529,
|
|
"loss": 6.8953,
|
|
"mean_token_accuracy": 0.11740255281329155,
|
|
"num_tokens": 2453474.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.8944995403289795,
|
|
"epoch": 1.2476379910492292,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991259401779042,
|
|
"loss": 6.835,
|
|
"mean_token_accuracy": 0.12458662986755371,
|
|
"num_tokens": 2462715.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.846959495544434,
|
|
"epoch": 1.2526106414719045,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004990912130867704,
|
|
"loss": 6.7497,
|
|
"mean_token_accuracy": 0.1315823934972286,
|
|
"num_tokens": 2473256.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.0362790584564205,
|
|
"epoch": 1.2575832918945797,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990558108968703,
|
|
"loss": 6.7982,
|
|
"mean_token_accuracy": 0.11804969012737274,
|
|
"num_tokens": 2482475.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.89988112449646,
|
|
"epoch": 1.2625559423172552,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004990197337148571,
|
|
"loss": 6.8586,
|
|
"mean_token_accuracy": 0.12154440209269524,
|
|
"num_tokens": 2493163.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.071360063552857,
|
|
"epoch": 1.2675285927399305,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000498982981649417,
|
|
"loss": 6.8924,
|
|
"mean_token_accuracy": 0.12033604830503464,
|
|
"num_tokens": 2502062.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.961255645751953,
|
|
"epoch": 1.2725012431626057,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004989455548112695,
|
|
"loss": 6.8963,
|
|
"mean_token_accuracy": 0.12024620845913887,
|
|
"num_tokens": 2511196.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.960355758666992,
|
|
"epoch": 1.277473893585281,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004989074533131671,
|
|
"loss": 6.8045,
|
|
"mean_token_accuracy": 0.12246129810810089,
|
|
"num_tokens": 2520492.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.869314336776734,
|
|
"epoch": 1.2824465440079562,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004988686772698945,
|
|
"loss": 6.8433,
|
|
"mean_token_accuracy": 0.12053112015128135,
|
|
"num_tokens": 2530368.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.951426267623901,
|
|
"epoch": 1.2874191944306315,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004988292267982689,
|
|
"loss": 6.8433,
|
|
"mean_token_accuracy": 0.11951586231589317,
|
|
"num_tokens": 2540734.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.865332794189453,
|
|
"epoch": 1.2923918448533067,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004987891020171387,
|
|
"loss": 6.8849,
|
|
"mean_token_accuracy": 0.11997138857841491,
|
|
"num_tokens": 2550907.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.091476535797119,
|
|
"epoch": 1.297364495275982,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004987483030473845,
|
|
"loss": 6.9347,
|
|
"mean_token_accuracy": 0.12072236984968185,
|
|
"num_tokens": 2560062.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.950492095947266,
|
|
"epoch": 1.3023371456986574,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004987068300119173,
|
|
"loss": 6.8496,
|
|
"mean_token_accuracy": 0.11858923509716987,
|
|
"num_tokens": 2568840.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.028611564636231,
|
|
"epoch": 1.3073097961213327,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004986646830356792,
|
|
"loss": 6.9239,
|
|
"mean_token_accuracy": 0.11663276925683022,
|
|
"num_tokens": 2578566.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.926668787002564,
|
|
"epoch": 1.312282446544008,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004986218622456423,
|
|
"loss": 6.9353,
|
|
"mean_token_accuracy": 0.1164866603910923,
|
|
"num_tokens": 2589853.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.004153776168823,
|
|
"epoch": 1.3172550969666832,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000498578367770809,
|
|
"loss": 6.8875,
|
|
"mean_token_accuracy": 0.11925893649458885,
|
|
"num_tokens": 2600848.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.871169805526733,
|
|
"epoch": 1.3222277473893587,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004985341997422111,
|
|
"loss": 6.8388,
|
|
"mean_token_accuracy": 0.11952893510460853,
|
|
"num_tokens": 2610730.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.973673725128174,
|
|
"epoch": 1.327200397812034,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004984893582929093,
|
|
"loss": 6.9268,
|
|
"mean_token_accuracy": 0.11996840909123421,
|
|
"num_tokens": 2621129.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.997471475601197,
|
|
"epoch": 1.3321730482347092,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004984438435579933,
|
|
"loss": 6.8324,
|
|
"mean_token_accuracy": 0.12776239216327667,
|
|
"num_tokens": 2630306.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.920943546295166,
|
|
"epoch": 1.3371456986573844,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004983976556745812,
|
|
"loss": 6.9681,
|
|
"mean_token_accuracy": 0.11704278215765954,
|
|
"num_tokens": 2639874.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.954730463027954,
|
|
"epoch": 1.3421183490800597,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000498350794781819,
|
|
"loss": 6.9154,
|
|
"mean_token_accuracy": 0.11681979894638062,
|
|
"num_tokens": 2650340.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.899462127685547,
|
|
"epoch": 1.347090999502735,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004983032610208801,
|
|
"loss": 6.6792,
|
|
"mean_token_accuracy": 0.13105636909604074,
|
|
"num_tokens": 2659541.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.897839117050171,
|
|
"epoch": 1.3520636499254102,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004982550545349649,
|
|
"loss": 6.891,
|
|
"mean_token_accuracy": 0.119564588367939,
|
|
"num_tokens": 2669151.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.863831377029419,
|
|
"epoch": 1.3570363003480854,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004982061754693008,
|
|
"loss": 6.7588,
|
|
"mean_token_accuracy": 0.13353405073285102,
|
|
"num_tokens": 2678867.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.90164623260498,
|
|
"epoch": 1.362008950770761,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004981566239711412,
|
|
"loss": 6.8977,
|
|
"mean_token_accuracy": 0.11816785335540772,
|
|
"num_tokens": 2687572.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.916720294952393,
|
|
"epoch": 1.3669816011934361,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004981064001897651,
|
|
"loss": 6.8263,
|
|
"mean_token_accuracy": 0.11733598187565804,
|
|
"num_tokens": 2696922.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.887785625457764,
|
|
"epoch": 1.3719542516161114,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004980555042764772,
|
|
"loss": 6.8546,
|
|
"mean_token_accuracy": 0.12436464950442314,
|
|
"num_tokens": 2707465.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.900615215301514,
|
|
"epoch": 1.3769269020387866,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004980039363846069,
|
|
"loss": 6.7507,
|
|
"mean_token_accuracy": 0.12554468885064124,
|
|
"num_tokens": 2718708.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.850574159622193,
|
|
"epoch": 1.381899552461462,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000497951696669508,
|
|
"loss": 6.8303,
|
|
"mean_token_accuracy": 0.11606418639421463,
|
|
"num_tokens": 2728862.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.966866397857666,
|
|
"epoch": 1.3868722028841374,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004978987852885579,
|
|
"loss": 6.7908,
|
|
"mean_token_accuracy": 0.12374083399772644,
|
|
"num_tokens": 2738546.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.810509490966797,
|
|
"epoch": 1.3918448533068126,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004978452024011582,
|
|
"loss": 6.7312,
|
|
"mean_token_accuracy": 0.1258455790579319,
|
|
"num_tokens": 2747885.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.827880191802978,
|
|
"epoch": 1.3968175037294879,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000497790948168733,
|
|
"loss": 6.7847,
|
|
"mean_token_accuracy": 0.12803196012973786,
|
|
"num_tokens": 2756851.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.945564031600952,
|
|
"epoch": 1.4017901541521631,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004977360227547288,
|
|
"loss": 6.8056,
|
|
"mean_token_accuracy": 0.12532249093055725,
|
|
"num_tokens": 2766309.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.826288318634033,
|
|
"epoch": 1.4067628045748384,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004976804263246146,
|
|
"loss": 6.7852,
|
|
"mean_token_accuracy": 0.12112483680248261,
|
|
"num_tokens": 2775679.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.870833444595337,
|
|
"epoch": 1.4117354549975136,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004976241590458803,
|
|
"loss": 6.749,
|
|
"mean_token_accuracy": 0.12467086315155029,
|
|
"num_tokens": 2784610.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.896092796325684,
|
|
"epoch": 1.4167081054201889,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004975672210880372,
|
|
"loss": 6.8682,
|
|
"mean_token_accuracy": 0.1267649620771408,
|
|
"num_tokens": 2793969.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.831112432479858,
|
|
"epoch": 1.4216807558428641,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004975096126226171,
|
|
"loss": 6.6917,
|
|
"mean_token_accuracy": 0.12754441648721696,
|
|
"num_tokens": 2803096.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.769429063796997,
|
|
"epoch": 1.4266534062655396,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004974513338231715,
|
|
"loss": 6.7791,
|
|
"mean_token_accuracy": 0.12707841470837594,
|
|
"num_tokens": 2812320.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.009070777893067,
|
|
"epoch": 1.4316260566882149,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004973923848652715,
|
|
"loss": 6.8511,
|
|
"mean_token_accuracy": 0.12180934101343155,
|
|
"num_tokens": 2821393.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.779871034622192,
|
|
"epoch": 1.43659870711089,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004973327659265073,
|
|
"loss": 6.8115,
|
|
"mean_token_accuracy": 0.13057589083909987,
|
|
"num_tokens": 2831182.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.900580501556396,
|
|
"epoch": 1.4415713575335654,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004972724771864874,
|
|
"loss": 6.7846,
|
|
"mean_token_accuracy": 0.12680001556873322,
|
|
"num_tokens": 2840429.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.815707778930664,
|
|
"epoch": 1.4465440079562406,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004972115188268378,
|
|
"loss": 6.7595,
|
|
"mean_token_accuracy": 0.13107500970363617,
|
|
"num_tokens": 2849443.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.8182614803314205,
|
|
"epoch": 1.451516658378916,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004971498910312024,
|
|
"loss": 6.7516,
|
|
"mean_token_accuracy": 0.12866144329309465,
|
|
"num_tokens": 2858908.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.914551210403443,
|
|
"epoch": 1.4564893088015913,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004970875939852412,
|
|
"loss": 6.8311,
|
|
"mean_token_accuracy": 0.12273252010345459,
|
|
"num_tokens": 2869615.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.870243167877197,
|
|
"epoch": 1.4614619592242666,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000497024627876631,
|
|
"loss": 6.7585,
|
|
"mean_token_accuracy": 0.12355621457099915,
|
|
"num_tokens": 2879007.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.766189193725586,
|
|
"epoch": 1.4664346096469418,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004969609928950639,
|
|
"loss": 6.6833,
|
|
"mean_token_accuracy": 0.13059235736727715,
|
|
"num_tokens": 2887527.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.728798818588257,
|
|
"epoch": 1.471407260069617,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004968966892322468,
|
|
"loss": 6.723,
|
|
"mean_token_accuracy": 0.1263209819793701,
|
|
"num_tokens": 2897137.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.824571895599365,
|
|
"epoch": 1.4763799104922923,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004968317170819018,
|
|
"loss": 6.8092,
|
|
"mean_token_accuracy": 0.1324581488966942,
|
|
"num_tokens": 2908346.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.87175030708313,
|
|
"epoch": 1.4813525609149676,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004967660766397642,
|
|
"loss": 6.8296,
|
|
"mean_token_accuracy": 0.1234806202352047,
|
|
"num_tokens": 2918438.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.954668474197388,
|
|
"epoch": 1.4863252113376428,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004966997681035829,
|
|
"loss": 6.945,
|
|
"mean_token_accuracy": 0.11962197124958038,
|
|
"num_tokens": 2928096.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.853156518936157,
|
|
"epoch": 1.4912978617603183,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004966327916731195,
|
|
"loss": 6.7823,
|
|
"mean_token_accuracy": 0.12796442881226539,
|
|
"num_tokens": 2938150.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.786738729476928,
|
|
"epoch": 1.4962705121829936,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004965651475501476,
|
|
"loss": 6.7274,
|
|
"mean_token_accuracy": 0.1297776661813259,
|
|
"num_tokens": 2949410.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.7901389598846436,
|
|
"epoch": 1.5012431626056688,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004964968359384524,
|
|
"loss": 6.6949,
|
|
"mean_token_accuracy": 0.13579546809196472,
|
|
"num_tokens": 2958564.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.7910431861877445,
|
|
"epoch": 1.506215813028344,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004964278570438299,
|
|
"loss": 6.7786,
|
|
"mean_token_accuracy": 0.1290195368230343,
|
|
"num_tokens": 2968750.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.848161697387695,
|
|
"epoch": 1.5111884634510195,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004963582110740865,
|
|
"loss": 6.7246,
|
|
"mean_token_accuracy": 0.13478757292032242,
|
|
"num_tokens": 2978397.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.8014851093292235,
|
|
"epoch": 1.5161611138736948,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004962878982390381,
|
|
"loss": 6.8567,
|
|
"mean_token_accuracy": 0.12458442598581314,
|
|
"num_tokens": 2987625.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.826836442947387,
|
|
"epoch": 1.52113376429637,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004962169187505097,
|
|
"loss": 6.7898,
|
|
"mean_token_accuracy": 0.12829354032874107,
|
|
"num_tokens": 2997266.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.847477674484253,
|
|
"epoch": 1.5261064147190453,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004961452728223343,
|
|
"loss": 6.7884,
|
|
"mean_token_accuracy": 0.12614995688199998,
|
|
"num_tokens": 3007474.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.923624086380005,
|
|
"epoch": 1.5310790651417205,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004960729606703535,
|
|
"loss": 6.7673,
|
|
"mean_token_accuracy": 0.123389732837677,
|
|
"num_tokens": 3016270.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.7074995040893555,
|
|
"epoch": 1.5360517155643958,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004959999825124147,
|
|
"loss": 6.7666,
|
|
"mean_token_accuracy": 0.12175339832901955,
|
|
"num_tokens": 3027397.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.9206921577453615,
|
|
"epoch": 1.541024365987071,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000495926338568373,
|
|
"loss": 6.7898,
|
|
"mean_token_accuracy": 0.12787529453635216,
|
|
"num_tokens": 3037324.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.7620690822601315,
|
|
"epoch": 1.5459970164097463,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004958520290600884,
|
|
"loss": 6.7484,
|
|
"mean_token_accuracy": 0.12835074141621589,
|
|
"num_tokens": 3048315.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.7305238246917725,
|
|
"epoch": 1.5509696668324215,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004957770542114262,
|
|
"loss": 6.6496,
|
|
"mean_token_accuracy": 0.13294167146086694,
|
|
"num_tokens": 3057875.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.8799608707427975,
|
|
"epoch": 1.555942317255097,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004957014142482563,
|
|
"loss": 6.7548,
|
|
"mean_token_accuracy": 0.125601577013731,
|
|
"num_tokens": 3068006.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.78745174407959,
|
|
"epoch": 1.5609149676777723,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004956251093984521,
|
|
"loss": 6.7997,
|
|
"mean_token_accuracy": 0.1332696110010147,
|
|
"num_tokens": 3079450.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.740923690795898,
|
|
"epoch": 1.5658876181004475,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004955481398918902,
|
|
"loss": 6.5381,
|
|
"mean_token_accuracy": 0.13897247165441512,
|
|
"num_tokens": 3088385.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.808420610427857,
|
|
"epoch": 1.5708602685231228,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004954705059604495,
|
|
"loss": 6.7121,
|
|
"mean_token_accuracy": 0.12634384483098984,
|
|
"num_tokens": 3097854.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.894461917877197,
|
|
"epoch": 1.5758329189457982,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004953922078380104,
|
|
"loss": 6.8638,
|
|
"mean_token_accuracy": 0.11956453770399093,
|
|
"num_tokens": 3107877.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.788162040710449,
|
|
"epoch": 1.5808055693684735,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004953132457604544,
|
|
"loss": 6.8179,
|
|
"mean_token_accuracy": 0.12026642337441444,
|
|
"num_tokens": 3117967.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.7056066513061525,
|
|
"epoch": 1.5857782197911487,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004952336199656632,
|
|
"loss": 6.7008,
|
|
"mean_token_accuracy": 0.1319211445748806,
|
|
"num_tokens": 3129827.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.832995510101318,
|
|
"epoch": 1.590750870213824,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004951533306935181,
|
|
"loss": 6.6689,
|
|
"mean_token_accuracy": 0.12922804206609725,
|
|
"num_tokens": 3138779.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.703251361846924,
|
|
"epoch": 1.5957235206364992,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004950723781858991,
|
|
"loss": 6.7135,
|
|
"mean_token_accuracy": 0.1345683753490448,
|
|
"num_tokens": 3148741.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.753573036193847,
|
|
"epoch": 1.6006961710591745,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004949907626866844,
|
|
"loss": 6.7635,
|
|
"mean_token_accuracy": 0.133981604129076,
|
|
"num_tokens": 3158964.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.690367984771728,
|
|
"epoch": 1.6056688214818498,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004949084844417493,
|
|
"loss": 6.5609,
|
|
"mean_token_accuracy": 0.13681313022971153,
|
|
"num_tokens": 3168347.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.72955288887024,
|
|
"epoch": 1.610641471904525,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004948255436989657,
|
|
"loss": 6.774,
|
|
"mean_token_accuracy": 0.12525363489985467,
|
|
"num_tokens": 3178276.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.75451922416687,
|
|
"epoch": 1.6156141223272003,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004947419407082017,
|
|
"loss": 6.7262,
|
|
"mean_token_accuracy": 0.12230646312236786,
|
|
"num_tokens": 3186975.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.737055873870849,
|
|
"epoch": 1.6205867727498757,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004946576757213202,
|
|
"loss": 6.5717,
|
|
"mean_token_accuracy": 0.14679480865597724,
|
|
"num_tokens": 3197311.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.6865979671478275,
|
|
"epoch": 1.625559423172551,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004945727489921784,
|
|
"loss": 6.7164,
|
|
"mean_token_accuracy": 0.1300855614244938,
|
|
"num_tokens": 3208534.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.861715793609619,
|
|
"epoch": 1.6305320735952262,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004944871607766273,
|
|
"loss": 6.6607,
|
|
"mean_token_accuracy": 0.13207977190613746,
|
|
"num_tokens": 3217440.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.711705112457276,
|
|
"epoch": 1.6355047240179017,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004944009113325104,
|
|
"loss": 6.7775,
|
|
"mean_token_accuracy": 0.126724024862051,
|
|
"num_tokens": 3225858.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.6331892013549805,
|
|
"epoch": 1.640477374440577,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004943140009196635,
|
|
"loss": 6.5618,
|
|
"mean_token_accuracy": 0.14867160394787787,
|
|
"num_tokens": 3235921.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.721046876907349,
|
|
"epoch": 1.6454500248632522,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004942264297999135,
|
|
"loss": 6.6597,
|
|
"mean_token_accuracy": 0.1392642341554165,
|
|
"num_tokens": 3245123.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.782358407974243,
|
|
"epoch": 1.6504226752859275,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004941381982370778,
|
|
"loss": 6.6534,
|
|
"mean_token_accuracy": 0.13713510632514953,
|
|
"num_tokens": 3254246.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.758942079544068,
|
|
"epoch": 1.6553953257086027,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004940493064969633,
|
|
"loss": 6.6484,
|
|
"mean_token_accuracy": 0.1331721879541874,
|
|
"num_tokens": 3263602.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.770178031921387,
|
|
"epoch": 1.660367976131278,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000493959754847366,
|
|
"loss": 6.8251,
|
|
"mean_token_accuracy": 0.12867565378546714,
|
|
"num_tokens": 3274430.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.788376569747925,
|
|
"epoch": 1.6653406265539532,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004938695435580698,
|
|
"loss": 6.5735,
|
|
"mean_token_accuracy": 0.13186567202210425,
|
|
"num_tokens": 3283587.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.684832429885864,
|
|
"epoch": 1.6703132769766285,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004937786729008459,
|
|
"loss": 6.7188,
|
|
"mean_token_accuracy": 0.12207710668444634,
|
|
"num_tokens": 3294165.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.785898447036743,
|
|
"epoch": 1.6752859273993037,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004936871431494517,
|
|
"loss": 6.6989,
|
|
"mean_token_accuracy": 0.13502319902181625,
|
|
"num_tokens": 3302756.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.692429256439209,
|
|
"epoch": 1.680258577821979,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004935949545796307,
|
|
"loss": 6.6267,
|
|
"mean_token_accuracy": 0.13172637969255446,
|
|
"num_tokens": 3313108.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.766379261016846,
|
|
"epoch": 1.6852312282446544,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004935021074691106,
|
|
"loss": 6.7195,
|
|
"mean_token_accuracy": 0.1308559313416481,
|
|
"num_tokens": 3323008.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.7030027389526365,
|
|
"epoch": 1.6902038786673297,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004934086020976032,
|
|
"loss": 6.638,
|
|
"mean_token_accuracy": 0.13223350718617438,
|
|
"num_tokens": 3332490.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.676813220977783,
|
|
"epoch": 1.695176529090005,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004933144387468037,
|
|
"loss": 6.6968,
|
|
"mean_token_accuracy": 0.1267889440059662,
|
|
"num_tokens": 3343069.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.711957550048828,
|
|
"epoch": 1.7001491795126804,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004932196177003891,
|
|
"loss": 6.7402,
|
|
"mean_token_accuracy": 0.1320636212825775,
|
|
"num_tokens": 3351834.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.790498113632202,
|
|
"epoch": 1.7051218299353557,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000493124139244018,
|
|
"loss": 6.6777,
|
|
"mean_token_accuracy": 0.1267648383975029,
|
|
"num_tokens": 3360915.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.693454313278198,
|
|
"epoch": 1.710094480358031,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004930280036653294,
|
|
"loss": 6.6693,
|
|
"mean_token_accuracy": 0.13222509175539016,
|
|
"num_tokens": 3370184.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.74412693977356,
|
|
"epoch": 1.7150671307807062,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000492931211253942,
|
|
"loss": 6.7416,
|
|
"mean_token_accuracy": 0.1286899082362652,
|
|
"num_tokens": 3379545.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.738655376434326,
|
|
"epoch": 1.7200397812033814,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004928337623014535,
|
|
"loss": 6.692,
|
|
"mean_token_accuracy": 0.1320427715778351,
|
|
"num_tokens": 3390238.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.755091857910156,
|
|
"epoch": 1.7250124316260567,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000492735657101439,
|
|
"loss": 6.6941,
|
|
"mean_token_accuracy": 0.13341115564107894,
|
|
"num_tokens": 3400437.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.583831262588501,
|
|
"epoch": 1.729985082048732,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004926368959494513,
|
|
"loss": 6.6544,
|
|
"mean_token_accuracy": 0.13529954701662064,
|
|
"num_tokens": 3410982.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.798423385620117,
|
|
"epoch": 1.7349577324714072,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004925374791430186,
|
|
"loss": 6.7576,
|
|
"mean_token_accuracy": 0.12626220062375068,
|
|
"num_tokens": 3420898.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.699107265472412,
|
|
"epoch": 1.7399303828940824,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004924374069816448,
|
|
"loss": 6.6068,
|
|
"mean_token_accuracy": 0.13776216059923171,
|
|
"num_tokens": 3429144.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.696451807022095,
|
|
"epoch": 1.7449030333167577,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004923366797668081,
|
|
"loss": 6.6618,
|
|
"mean_token_accuracy": 0.1360717937350273,
|
|
"num_tokens": 3439427.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.782762908935547,
|
|
"epoch": 1.7498756837394331,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004922352978019597,
|
|
"loss": 6.6461,
|
|
"mean_token_accuracy": 0.13736561238765715,
|
|
"num_tokens": 3448218.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.727622175216675,
|
|
"epoch": 1.7548483341621084,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004921332613925239,
|
|
"loss": 6.7015,
|
|
"mean_token_accuracy": 0.1316203609108925,
|
|
"num_tokens": 3457656.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.7920112133026125,
|
|
"epoch": 1.7598209845847836,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004920305708458964,
|
|
"loss": 6.68,
|
|
"mean_token_accuracy": 0.13132236450910567,
|
|
"num_tokens": 3467414.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.60561580657959,
|
|
"epoch": 1.7647936350074591,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004919272264714431,
|
|
"loss": 6.6319,
|
|
"mean_token_accuracy": 0.13211813122034072,
|
|
"num_tokens": 3477195.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.766419887542725,
|
|
"epoch": 1.7697662854301344,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004918232285805004,
|
|
"loss": 6.7036,
|
|
"mean_token_accuracy": 0.12701989114284515,
|
|
"num_tokens": 3487497.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.729431629180908,
|
|
"epoch": 1.7747389358528096,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004917185774863727,
|
|
"loss": 6.6678,
|
|
"mean_token_accuracy": 0.1326162837445736,
|
|
"num_tokens": 3497363.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.664000749588013,
|
|
"epoch": 1.7797115862754849,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004916132735043329,
|
|
"loss": 6.6669,
|
|
"mean_token_accuracy": 0.13428003191947938,
|
|
"num_tokens": 3506969.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.758932733535767,
|
|
"epoch": 1.7846842366981601,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004915073169516204,
|
|
"loss": 6.6374,
|
|
"mean_token_accuracy": 0.133426945656538,
|
|
"num_tokens": 3516418.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.646256637573242,
|
|
"epoch": 1.7896568871208354,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004914007081474406,
|
|
"loss": 6.579,
|
|
"mean_token_accuracy": 0.13459737226366997,
|
|
"num_tokens": 3528023.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.680403089523315,
|
|
"epoch": 1.7946295375435106,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004912934474129641,
|
|
"loss": 6.6791,
|
|
"mean_token_accuracy": 0.126181248575449,
|
|
"num_tokens": 3537946.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.629174423217774,
|
|
"epoch": 1.7996021879661859,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004911855350713251,
|
|
"loss": 6.6441,
|
|
"mean_token_accuracy": 0.1346987560391426,
|
|
"num_tokens": 3547299.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.778659057617188,
|
|
"epoch": 1.8045748383888611,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004910769714476214,
|
|
"loss": 6.719,
|
|
"mean_token_accuracy": 0.13088061064481735,
|
|
"num_tokens": 3556075.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.693529462814331,
|
|
"epoch": 1.8095474888115366,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004909677568689122,
|
|
"loss": 6.6839,
|
|
"mean_token_accuracy": 0.13213445693254472,
|
|
"num_tokens": 3566314.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.683442831039429,
|
|
"epoch": 1.8145201392342118,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004908578916642183,
|
|
"loss": 6.5771,
|
|
"mean_token_accuracy": 0.1374658614397049,
|
|
"num_tokens": 3575095.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.673960494995117,
|
|
"epoch": 1.819492789656887,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004907473761645205,
|
|
"loss": 6.6844,
|
|
"mean_token_accuracy": 0.13227922096848488,
|
|
"num_tokens": 3584375.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.6529711246490475,
|
|
"epoch": 1.8244654400795626,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004906362107027583,
|
|
"loss": 6.5489,
|
|
"mean_token_accuracy": 0.1394191190600395,
|
|
"num_tokens": 3594504.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.631583499908447,
|
|
"epoch": 1.8294380905022378,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004905243956138298,
|
|
"loss": 6.69,
|
|
"mean_token_accuracy": 0.12915903329849243,
|
|
"num_tokens": 3604050.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.778188943862915,
|
|
"epoch": 1.834410740924913,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004904119312345896,
|
|
"loss": 6.5926,
|
|
"mean_token_accuracy": 0.1395821340382099,
|
|
"num_tokens": 3613388.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.655749797821045,
|
|
"epoch": 1.8393833913475883,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004902988179038492,
|
|
"loss": 6.7733,
|
|
"mean_token_accuracy": 0.12011321932077408,
|
|
"num_tokens": 3623758.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.818503284454346,
|
|
"epoch": 1.8443560417702636,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000490185055962374,
|
|
"loss": 6.6445,
|
|
"mean_token_accuracy": 0.13539304807782174,
|
|
"num_tokens": 3633040.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.634677410125732,
|
|
"epoch": 1.8493286921929388,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004900706457528845,
|
|
"loss": 6.5565,
|
|
"mean_token_accuracy": 0.13505534678697587,
|
|
"num_tokens": 3642980.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.705596256256103,
|
|
"epoch": 1.854301342615614,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004899555876200535,
|
|
"loss": 6.7149,
|
|
"mean_token_accuracy": 0.13585179373621942,
|
|
"num_tokens": 3653817.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.733653402328491,
|
|
"epoch": 1.8592739930382893,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004898398819105059,
|
|
"loss": 6.6359,
|
|
"mean_token_accuracy": 0.130605985224247,
|
|
"num_tokens": 3664460.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.723941230773926,
|
|
"epoch": 1.8642466434609646,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004897235289728178,
|
|
"loss": 6.6779,
|
|
"mean_token_accuracy": 0.12275734916329384,
|
|
"num_tokens": 3674221.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.593170547485352,
|
|
"epoch": 1.8692192938836398,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004896065291575145,
|
|
"loss": 6.5576,
|
|
"mean_token_accuracy": 0.14246022552251816,
|
|
"num_tokens": 3683130.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.71184229850769,
|
|
"epoch": 1.8741919443063153,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004894888828170708,
|
|
"loss": 6.5075,
|
|
"mean_token_accuracy": 0.13699922263622283,
|
|
"num_tokens": 3694544.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.519984292984009,
|
|
"epoch": 1.8791645947289906,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004893705903059087,
|
|
"loss": 6.468,
|
|
"mean_token_accuracy": 0.13796097338199614,
|
|
"num_tokens": 3704857.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.704261016845703,
|
|
"epoch": 1.8841372451516658,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004892516519803971,
|
|
"loss": 6.6079,
|
|
"mean_token_accuracy": 0.13686281070113182,
|
|
"num_tokens": 3714623.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.6676782131195065,
|
|
"epoch": 1.8891098955743413,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004891320681988504,
|
|
"loss": 6.5741,
|
|
"mean_token_accuracy": 0.14162902683019638,
|
|
"num_tokens": 3723349.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.558374261856079,
|
|
"epoch": 1.8940825459970165,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004890118393215277,
|
|
"loss": 6.5519,
|
|
"mean_token_accuracy": 0.1372409552335739,
|
|
"num_tokens": 3732990.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.652611255645752,
|
|
"epoch": 1.8990551964196918,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004888909657106311,
|
|
"loss": 6.5476,
|
|
"mean_token_accuracy": 0.13684199526906013,
|
|
"num_tokens": 3742343.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.596817064285278,
|
|
"epoch": 1.904027846842367,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004887694477303055,
|
|
"loss": 6.5754,
|
|
"mean_token_accuracy": 0.13304830119013786,
|
|
"num_tokens": 3752128.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.615978622436524,
|
|
"epoch": 1.9090004972650423,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004886472857466368,
|
|
"loss": 6.4941,
|
|
"mean_token_accuracy": 0.1367519110441208,
|
|
"num_tokens": 3760431.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.6409385204315186,
|
|
"epoch": 1.9139731476877175,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004885244801276509,
|
|
"loss": 6.5984,
|
|
"mean_token_accuracy": 0.1343713827431202,
|
|
"num_tokens": 3769623.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.536288595199585,
|
|
"epoch": 1.9189457981103928,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004884010312433131,
|
|
"loss": 6.5451,
|
|
"mean_token_accuracy": 0.13436267524957657,
|
|
"num_tokens": 3779383.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.681822633743286,
|
|
"epoch": 1.923918448533068,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048827693946552615,
|
|
"loss": 6.7086,
|
|
"mean_token_accuracy": 0.12788542956113816,
|
|
"num_tokens": 3788847.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.528082084655762,
|
|
"epoch": 1.9288910989557433,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048815220516813004,
|
|
"loss": 6.5596,
|
|
"mean_token_accuracy": 0.14175273850560188,
|
|
"num_tokens": 3798711.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.6422826766967775,
|
|
"epoch": 1.9338637493784185,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004880268287269,
|
|
"loss": 6.5227,
|
|
"mean_token_accuracy": 0.13906078785657883,
|
|
"num_tokens": 3808837.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.590198564529419,
|
|
"epoch": 1.938836399801094,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048790081051954605,
|
|
"loss": 6.4968,
|
|
"mean_token_accuracy": 0.13925287276506423,
|
|
"num_tokens": 3818261.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.578291654586792,
|
|
"epoch": 1.9438090502237693,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004877741509257116,
|
|
"loss": 6.5356,
|
|
"mean_token_accuracy": 0.13477599993348122,
|
|
"num_tokens": 3828146.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.733463144302368,
|
|
"epoch": 1.9487817006464445,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004876468503269721,
|
|
"loss": 6.7972,
|
|
"mean_token_accuracy": 0.12044794335961342,
|
|
"num_tokens": 3838658.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.618522310256958,
|
|
"epoch": 1.95375435106912,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048751890910683434,
|
|
"loss": 6.5364,
|
|
"mean_token_accuracy": 0.13059837222099305,
|
|
"num_tokens": 3849097.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.653698873519898,
|
|
"epoch": 1.9587270014917952,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048739032765073487,
|
|
"loss": 6.6806,
|
|
"mean_token_accuracy": 0.12555816173553466,
|
|
"num_tokens": 3858645.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.6428728103637695,
|
|
"epoch": 1.9636996519144705,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048726110634603913,
|
|
"loss": 6.5302,
|
|
"mean_token_accuracy": 0.14176158830523491,
|
|
"num_tokens": 3869232.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.662562847137451,
|
|
"epoch": 1.9686723023371457,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048713124558204013,
|
|
"loss": 6.6339,
|
|
"mean_token_accuracy": 0.13388122096657754,
|
|
"num_tokens": 3879453.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.6446600437164305,
|
|
"epoch": 1.973644952759821,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004870007457499573,
|
|
"loss": 6.5457,
|
|
"mean_token_accuracy": 0.13349285572767258,
|
|
"num_tokens": 3888257.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.642933034896851,
|
|
"epoch": 1.9786176031824962,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048686960724293537,
|
|
"loss": 6.5935,
|
|
"mean_token_accuracy": 0.1399511255323887,
|
|
"num_tokens": 3897980.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.54600772857666,
|
|
"epoch": 1.9835902536051715,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004867378304560432,
|
|
"loss": 6.4067,
|
|
"mean_token_accuracy": 0.14303143247961997,
|
|
"num_tokens": 3907479.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.577399110794067,
|
|
"epoch": 1.9885629040278467,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004866054157862723,
|
|
"loss": 6.6357,
|
|
"mean_token_accuracy": 0.13481335565447808,
|
|
"num_tokens": 3917249.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"epoch": 1.9885629040278467,
|
|
"eval_entropy": 6.484592456422094,
|
|
"eval_loss": 6.79269552230835,
|
|
"eval_mean_token_accuracy": 0.12670518923980026,
|
|
"eval_num_tokens": 3917249.0,
|
|
"eval_runtime": 2.6856,
|
|
"eval_samples_per_second": 1290.212,
|
|
"eval_steps_per_second": 161.602,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.557495021820069,
|
|
"epoch": 1.993535554450522,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004864723636325361,
|
|
"loss": 6.5398,
|
|
"mean_token_accuracy": 0.14420684278011323,
|
|
"num_tokens": 3928388.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.616270208358765,
|
|
"epoch": 1.9985082048731975,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048633867439566855,
|
|
"loss": 6.5804,
|
|
"mean_token_accuracy": 0.13147736638784407,
|
|
"num_tokens": 3937323.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.587894651624891,
|
|
"epoch": 2.002983590253605,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004862043484784227,
|
|
"loss": 6.4284,
|
|
"mean_token_accuracy": 0.13917528092861176,
|
|
"num_tokens": 3946815.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.638849973678589,
|
|
"epoch": 2.0079562406762803,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048606938628546975,
|
|
"loss": 6.1845,
|
|
"mean_token_accuracy": 0.1440080411732197,
|
|
"num_tokens": 3956125.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.604666423797608,
|
|
"epoch": 2.0129288910989556,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004859337882233978,
|
|
"loss": 6.1993,
|
|
"mean_token_accuracy": 0.14808306768536567,
|
|
"num_tokens": 3966543.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.509889841079712,
|
|
"epoch": 2.017901541521631,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004857975547007106,
|
|
"loss": 6.2405,
|
|
"mean_token_accuracy": 0.14003218561410904,
|
|
"num_tokens": 3978200.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.528255414962769,
|
|
"epoch": 2.0228741919443065,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048566068612782595,
|
|
"loss": 6.1076,
|
|
"mean_token_accuracy": 0.14900389760732652,
|
|
"num_tokens": 3988331.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.54871563911438,
|
|
"epoch": 2.0278468423669818,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048552318291707533,
|
|
"loss": 6.1528,
|
|
"mean_token_accuracy": 0.14669630602002143,
|
|
"num_tokens": 3998976.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.435534429550171,
|
|
"epoch": 2.032819492789657,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048538504548270177,
|
|
"loss": 6.1747,
|
|
"mean_token_accuracy": 0.14789161682128907,
|
|
"num_tokens": 4008354.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.573101377487182,
|
|
"epoch": 2.0377921432123323,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048524627424085913,
|
|
"loss": 6.1197,
|
|
"mean_token_accuracy": 0.15076259300112724,
|
|
"num_tokens": 4018045.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.410332202911377,
|
|
"epoch": 2.0427647936350075,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048510686960961057,
|
|
"loss": 6.1388,
|
|
"mean_token_accuracy": 0.15670369416475297,
|
|
"num_tokens": 4027884.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.483384847640991,
|
|
"epoch": 2.0477374440576828,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004849668320089276,
|
|
"loss": 6.1596,
|
|
"mean_token_accuracy": 0.1491243988275528,
|
|
"num_tokens": 4037866.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.528685569763184,
|
|
"epoch": 2.052710094480358,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048482616186068826,
|
|
"loss": 6.1649,
|
|
"mean_token_accuracy": 0.14608012810349463,
|
|
"num_tokens": 4048126.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.4547028064727785,
|
|
"epoch": 2.0576827449030333,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048468485958867664,
|
|
"loss": 6.2129,
|
|
"mean_token_accuracy": 0.14369071424007415,
|
|
"num_tokens": 4058179.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.483941555023193,
|
|
"epoch": 2.0626553953257085,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048454292561858083,
|
|
"loss": 6.0776,
|
|
"mean_token_accuracy": 0.14888638854026795,
|
|
"num_tokens": 4067479.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.500030565261841,
|
|
"epoch": 2.0676280457483838,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004844003603779921,
|
|
"loss": 6.2109,
|
|
"mean_token_accuracy": 0.14867587983608246,
|
|
"num_tokens": 4076624.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.459650468826294,
|
|
"epoch": 2.072600696171059,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004842571642964036,
|
|
"loss": 6.1343,
|
|
"mean_token_accuracy": 0.14853780716657639,
|
|
"num_tokens": 4085752.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.438293170928955,
|
|
"epoch": 2.0775733465937343,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048411333780520876,
|
|
"loss": 6.1798,
|
|
"mean_token_accuracy": 0.14991149306297302,
|
|
"num_tokens": 4095026.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.463499355316162,
|
|
"epoch": 2.0825459970164095,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048396888133770034,
|
|
"loss": 6.173,
|
|
"mean_token_accuracy": 0.1478162333369255,
|
|
"num_tokens": 4104589.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.443518495559692,
|
|
"epoch": 2.087518647439085,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048382379532906897,
|
|
"loss": 6.1217,
|
|
"mean_token_accuracy": 0.14708847403526307,
|
|
"num_tokens": 4114550.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.499040174484253,
|
|
"epoch": 2.0924912978617605,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004836780802164016,
|
|
"loss": 6.2426,
|
|
"mean_token_accuracy": 0.14630289226770402,
|
|
"num_tokens": 4125491.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.468936109542847,
|
|
"epoch": 2.0974639482844357,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048353173643868064,
|
|
"loss": 6.1383,
|
|
"mean_token_accuracy": 0.14840174168348313,
|
|
"num_tokens": 4134599.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.3696067333221436,
|
|
"epoch": 2.102436598707111,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004833847644367826,
|
|
"loss": 6.0934,
|
|
"mean_token_accuracy": 0.15614720582962036,
|
|
"num_tokens": 4143640.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.480792665481568,
|
|
"epoch": 2.107409249129786,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048323716465347615,
|
|
"loss": 6.173,
|
|
"mean_token_accuracy": 0.153205943107605,
|
|
"num_tokens": 4152558.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.31861367225647,
|
|
"epoch": 2.1123818995524615,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004830889375334215,
|
|
"loss": 6.0195,
|
|
"mean_token_accuracy": 0.16545322090387343,
|
|
"num_tokens": 4162238.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.456029605865479,
|
|
"epoch": 2.1173545499751367,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048294008352316875,
|
|
"loss": 6.1407,
|
|
"mean_token_accuracy": 0.15071416795253753,
|
|
"num_tokens": 4171437.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.363879442214966,
|
|
"epoch": 2.122327200397812,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004827906030711564,
|
|
"loss": 6.1392,
|
|
"mean_token_accuracy": 0.15137670040130616,
|
|
"num_tokens": 4181584.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.313394451141358,
|
|
"epoch": 2.1272998508204872,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048264049662771053,
|
|
"loss": 6.0363,
|
|
"mean_token_accuracy": 0.15970928370952606,
|
|
"num_tokens": 4191756.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.347188806533813,
|
|
"epoch": 2.1322725012431625,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048248976464504266,
|
|
"loss": 6.0808,
|
|
"mean_token_accuracy": 0.15753274857997895,
|
|
"num_tokens": 4202864.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.5057830810546875,
|
|
"epoch": 2.1372451516658377,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048233840757724926,
|
|
"loss": 6.1702,
|
|
"mean_token_accuracy": 0.14166584759950637,
|
|
"num_tokens": 4212839.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.394610071182251,
|
|
"epoch": 2.142217802088513,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048218642588030943,
|
|
"loss": 6.1842,
|
|
"mean_token_accuracy": 0.1455588959157467,
|
|
"num_tokens": 4223150.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.459643602371216,
|
|
"epoch": 2.1471904525111887,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048203382001208453,
|
|
"loss": 6.1882,
|
|
"mean_token_accuracy": 0.1514824315905571,
|
|
"num_tokens": 4232206.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.4893444061279295,
|
|
"epoch": 2.152163102933864,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048188059043231585,
|
|
"loss": 6.1615,
|
|
"mean_token_accuracy": 0.14690615832805634,
|
|
"num_tokens": 4240992.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.341883182525635,
|
|
"epoch": 2.157135753356539,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048172673760262414,
|
|
"loss": 6.1585,
|
|
"mean_token_accuracy": 0.14410844817757607,
|
|
"num_tokens": 4250371.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.451261854171753,
|
|
"epoch": 2.1621084037792144,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048157226198650735,
|
|
"loss": 6.1948,
|
|
"mean_token_accuracy": 0.14702774211764336,
|
|
"num_tokens": 4260606.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.427395629882812,
|
|
"epoch": 2.1670810542018897,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004814171640493398,
|
|
"loss": 6.163,
|
|
"mean_token_accuracy": 0.1501906156539917,
|
|
"num_tokens": 4269753.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.278026151657104,
|
|
"epoch": 2.172053704624565,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004812614442583708,
|
|
"loss": 6.0718,
|
|
"mean_token_accuracy": 0.15257282108068465,
|
|
"num_tokens": 4279485.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.492680358886719,
|
|
"epoch": 2.17702635504724,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004811051030827227,
|
|
"loss": 6.203,
|
|
"mean_token_accuracy": 0.1438272513449192,
|
|
"num_tokens": 4289491.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.3938604354858395,
|
|
"epoch": 2.1819990054699154,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048094814099339006,
|
|
"loss": 6.2264,
|
|
"mean_token_accuracy": 0.15491946786642075,
|
|
"num_tokens": 4300536.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.533280515670777,
|
|
"epoch": 2.1869716558925907,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004807905584632381,
|
|
"loss": 6.2774,
|
|
"mean_token_accuracy": 0.1336774557828903,
|
|
"num_tokens": 4311804.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.517438888549805,
|
|
"epoch": 2.191944306315266,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048063235596700087,
|
|
"loss": 6.2489,
|
|
"mean_token_accuracy": 0.14206167161464692,
|
|
"num_tokens": 4320662.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.4713146686553955,
|
|
"epoch": 2.196916956737941,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048047353398128056,
|
|
"loss": 6.2389,
|
|
"mean_token_accuracy": 0.14068502560257912,
|
|
"num_tokens": 4330414.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.378249454498291,
|
|
"epoch": 2.2018896071606164,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004803140929845452,
|
|
"loss": 6.205,
|
|
"mean_token_accuracy": 0.15056732147932053,
|
|
"num_tokens": 4340478.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.410696792602539,
|
|
"epoch": 2.2068622575832917,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048015403345712796,
|
|
"loss": 6.1393,
|
|
"mean_token_accuracy": 0.1527056336402893,
|
|
"num_tokens": 4350688.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.305073022842407,
|
|
"epoch": 2.2118349080059674,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004799933558812252,
|
|
"loss": 6.0585,
|
|
"mean_token_accuracy": 0.1618402160704136,
|
|
"num_tokens": 4360554.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.392449760437012,
|
|
"epoch": 2.2168075584286426,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047983206074089546,
|
|
"loss": 6.1037,
|
|
"mean_token_accuracy": 0.15870184302330018,
|
|
"num_tokens": 4370723.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.319252014160156,
|
|
"epoch": 2.221780208851318,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004796701485220576,
|
|
"loss": 6.189,
|
|
"mean_token_accuracy": 0.15078892409801484,
|
|
"num_tokens": 4380383.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.436127376556397,
|
|
"epoch": 2.226752859273993,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004795076197124893,
|
|
"loss": 6.3143,
|
|
"mean_token_accuracy": 0.13552723079919815,
|
|
"num_tokens": 4390408.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.407538557052613,
|
|
"epoch": 2.2317255096966684,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047934447480182626,
|
|
"loss": 6.1685,
|
|
"mean_token_accuracy": 0.1469875156879425,
|
|
"num_tokens": 4400043.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.409034729003906,
|
|
"epoch": 2.2366981601193436,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004791807142815598,
|
|
"loss": 6.2273,
|
|
"mean_token_accuracy": 0.14622812569141388,
|
|
"num_tokens": 4409420.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.40499210357666,
|
|
"epoch": 2.241670810542019,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047901633864503614,
|
|
"loss": 6.1139,
|
|
"mean_token_accuracy": 0.15082721784710884,
|
|
"num_tokens": 4418742.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.44884729385376,
|
|
"epoch": 2.246643460964694,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047885134838745433,
|
|
"loss": 6.1365,
|
|
"mean_token_accuracy": 0.1545293524861336,
|
|
"num_tokens": 4427921.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.311364841461182,
|
|
"epoch": 2.2516161113873694,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004786857440058654,
|
|
"loss": 6.1875,
|
|
"mean_token_accuracy": 0.1473423272371292,
|
|
"num_tokens": 4438029.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.409182405471801,
|
|
"epoch": 2.2565887618100446,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004785195259991701,
|
|
"loss": 6.1515,
|
|
"mean_token_accuracy": 0.15750665217638016,
|
|
"num_tokens": 4446967.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.394099378585816,
|
|
"epoch": 2.26156141223272,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000478352694868118,
|
|
"loss": 6.0994,
|
|
"mean_token_accuracy": 0.15111790969967842,
|
|
"num_tokens": 4456469.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.373833847045899,
|
|
"epoch": 2.266534062655395,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004781852511153058,
|
|
"loss": 6.23,
|
|
"mean_token_accuracy": 0.1536203071475029,
|
|
"num_tokens": 4465949.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.426255512237549,
|
|
"epoch": 2.271506713078071,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047801719524517573,
|
|
"loss": 6.0399,
|
|
"mean_token_accuracy": 0.15422955006361008,
|
|
"num_tokens": 4475460.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.333284711837768,
|
|
"epoch": 2.276479363500746,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047784852776401403,
|
|
"loss": 6.1857,
|
|
"mean_token_accuracy": 0.14476593285799028,
|
|
"num_tokens": 4485540.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.420295476913452,
|
|
"epoch": 2.2814520139234213,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004776792491799495,
|
|
"loss": 6.1534,
|
|
"mean_token_accuracy": 0.1550514131784439,
|
|
"num_tokens": 4495545.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.387951326370239,
|
|
"epoch": 2.2864246643460966,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047750936000295213,
|
|
"loss": 6.108,
|
|
"mean_token_accuracy": 0.15061453878879547,
|
|
"num_tokens": 4505527.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.330194807052612,
|
|
"epoch": 2.291397314768772,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047733886074483115,
|
|
"loss": 6.1243,
|
|
"mean_token_accuracy": 0.15444055199623108,
|
|
"num_tokens": 4515366.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.439748811721802,
|
|
"epoch": 2.296369965191447,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004771677519192339,
|
|
"loss": 6.228,
|
|
"mean_token_accuracy": 0.1486752897500992,
|
|
"num_tokens": 4525273.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.398458099365234,
|
|
"epoch": 2.3013426156141223,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004769960340416439,
|
|
"loss": 6.1807,
|
|
"mean_token_accuracy": 0.1472474992275238,
|
|
"num_tokens": 4533568.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.41317195892334,
|
|
"epoch": 2.3063152660367976,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047682370762937976,
|
|
"loss": 6.3656,
|
|
"mean_token_accuracy": 0.14059623777866365,
|
|
"num_tokens": 4544508.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.451664638519287,
|
|
"epoch": 2.311287916459473,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047665077320159315,
|
|
"loss": 6.0726,
|
|
"mean_token_accuracy": 0.14956745356321335,
|
|
"num_tokens": 4554586.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.287236452102661,
|
|
"epoch": 2.316260566882148,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047647723127926765,
|
|
"loss": 6.1304,
|
|
"mean_token_accuracy": 0.14848051071166993,
|
|
"num_tokens": 4563883.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.315356063842773,
|
|
"epoch": 2.3212332173048233,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004763030823852168,
|
|
"loss": 6.1498,
|
|
"mean_token_accuracy": 0.15514332801103592,
|
|
"num_tokens": 4573675.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.425148248672485,
|
|
"epoch": 2.3262058677274986,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004761283270440829,
|
|
"loss": 6.1697,
|
|
"mean_token_accuracy": 0.14114801958203316,
|
|
"num_tokens": 4583617.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.384911727905274,
|
|
"epoch": 2.331178518150174,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004759529657823349,
|
|
"loss": 6.1962,
|
|
"mean_token_accuracy": 0.15303058177232742,
|
|
"num_tokens": 4593792.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.370932006835938,
|
|
"epoch": 2.336151168572849,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047577699912826755,
|
|
"loss": 6.189,
|
|
"mean_token_accuracy": 0.14846591800451278,
|
|
"num_tokens": 4603324.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.398054742813111,
|
|
"epoch": 2.341123818995525,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047560042761199915,
|
|
"loss": 6.1254,
|
|
"mean_token_accuracy": 0.15129619389772414,
|
|
"num_tokens": 4613509.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.282456398010254,
|
|
"epoch": 2.3460964694182,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004754232517654704,
|
|
"loss": 6.1399,
|
|
"mean_token_accuracy": 0.15746210590004922,
|
|
"num_tokens": 4624282.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.273229885101318,
|
|
"epoch": 2.3510691198408753,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004752454721224424,
|
|
"loss": 6.0857,
|
|
"mean_token_accuracy": 0.1550448179244995,
|
|
"num_tokens": 4633217.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.333545398712158,
|
|
"epoch": 2.3560417702635505,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047506708921849535,
|
|
"loss": 6.1191,
|
|
"mean_token_accuracy": 0.15754763782024384,
|
|
"num_tokens": 4642824.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.363737010955811,
|
|
"epoch": 2.361014420686226,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004748881035910269,
|
|
"loss": 6.1591,
|
|
"mean_token_accuracy": 0.15156819224357604,
|
|
"num_tokens": 4651938.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.2889176368713375,
|
|
"epoch": 2.365987071108901,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004747085157792504,
|
|
"loss": 6.1238,
|
|
"mean_token_accuracy": 0.15418949574232102,
|
|
"num_tokens": 4661695.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.443801403045654,
|
|
"epoch": 2.3709597215315763,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004745283263241933,
|
|
"loss": 6.2225,
|
|
"mean_token_accuracy": 0.1484076738357544,
|
|
"num_tokens": 4671354.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.190524911880493,
|
|
"epoch": 2.3759323719542516,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004743475357686957,
|
|
"loss": 6.0836,
|
|
"mean_token_accuracy": 0.1642414502799511,
|
|
"num_tokens": 4681795.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.401231718063355,
|
|
"epoch": 2.380905022376927,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047416614465740843,
|
|
"loss": 6.1969,
|
|
"mean_token_accuracy": 0.15543957948684692,
|
|
"num_tokens": 4691229.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.307444143295288,
|
|
"epoch": 2.385877672799602,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047398415353679167,
|
|
"loss": 6.2428,
|
|
"mean_token_accuracy": 0.1464916780591011,
|
|
"num_tokens": 4701880.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.43255934715271,
|
|
"epoch": 2.3908503232222773,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004738015629551132,
|
|
"loss": 6.1665,
|
|
"mean_token_accuracy": 0.1466479629278183,
|
|
"num_tokens": 4712041.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.222315692901612,
|
|
"epoch": 2.395822973644953,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047361837346244655,
|
|
"loss": 5.9364,
|
|
"mean_token_accuracy": 0.16421663165092468,
|
|
"num_tokens": 4722576.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.338772583007812,
|
|
"epoch": 2.4007956240676283,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004734345856106698,
|
|
"loss": 6.2025,
|
|
"mean_token_accuracy": 0.1502015396952629,
|
|
"num_tokens": 4732569.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.429965591430664,
|
|
"epoch": 2.4057682744903035,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047325019995346355,
|
|
"loss": 6.2339,
|
|
"mean_token_accuracy": 0.1491033747792244,
|
|
"num_tokens": 4741973.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.505489349365234,
|
|
"epoch": 2.4107409249129788,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004730652170463091,
|
|
"loss": 6.2085,
|
|
"mean_token_accuracy": 0.1496612921357155,
|
|
"num_tokens": 4751550.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.276806449890136,
|
|
"epoch": 2.415713575335654,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004728796374464875,
|
|
"loss": 6.1226,
|
|
"mean_token_accuracy": 0.15632066056132315,
|
|
"num_tokens": 4761620.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.318710136413574,
|
|
"epoch": 2.4206862257583293,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047269346171307716,
|
|
"loss": 6.1404,
|
|
"mean_token_accuracy": 0.14804664701223375,
|
|
"num_tokens": 4771893.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.414186906814575,
|
|
"epoch": 2.4256588761810045,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004725066904069523,
|
|
"loss": 6.1795,
|
|
"mean_token_accuracy": 0.14920975118875504,
|
|
"num_tokens": 4781094.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.290204620361328,
|
|
"epoch": 2.4306315266036798,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004723193240907814,
|
|
"loss": 6.1335,
|
|
"mean_token_accuracy": 0.14848116487264634,
|
|
"num_tokens": 4790337.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.322016954421997,
|
|
"epoch": 2.435604177026355,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004721313633290257,
|
|
"loss": 6.1845,
|
|
"mean_token_accuracy": 0.15368174016475677,
|
|
"num_tokens": 4801758.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.385703992843628,
|
|
"epoch": 2.4405768274490303,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000471942808687937,
|
|
"loss": 6.2738,
|
|
"mean_token_accuracy": 0.1427849277853966,
|
|
"num_tokens": 4811040.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.325768709182739,
|
|
"epoch": 2.4455494778717055,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047175366073555654,
|
|
"loss": 6.1334,
|
|
"mean_token_accuracy": 0.14720245748758315,
|
|
"num_tokens": 4821361.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.387405014038086,
|
|
"epoch": 2.4505221282943808,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004715639200417125,
|
|
"loss": 6.1544,
|
|
"mean_token_accuracy": 0.1459880717098713,
|
|
"num_tokens": 4830919.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.220270490646362,
|
|
"epoch": 2.455494778717056,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004713735871780192,
|
|
"loss": 5.9763,
|
|
"mean_token_accuracy": 0.17090498358011247,
|
|
"num_tokens": 4840364.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.279631805419922,
|
|
"epoch": 2.4604674291397313,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004711826627178747,
|
|
"loss": 6.1697,
|
|
"mean_token_accuracy": 0.1522266760468483,
|
|
"num_tokens": 4849044.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.343340730667114,
|
|
"epoch": 2.4654400795624065,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047099114723645944,
|
|
"loss": 6.1609,
|
|
"mean_token_accuracy": 0.1498938038945198,
|
|
"num_tokens": 4859183.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.299566459655762,
|
|
"epoch": 2.470412729985082,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047079904131073434,
|
|
"loss": 6.1222,
|
|
"mean_token_accuracy": 0.14881330281496047,
|
|
"num_tokens": 4869625.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.307638883590698,
|
|
"epoch": 2.4753853804077575,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004706063455194389,
|
|
"loss": 6.117,
|
|
"mean_token_accuracy": 0.15830245167016982,
|
|
"num_tokens": 4880089.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.334252738952637,
|
|
"epoch": 2.4803580308304327,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047041306044308986,
|
|
"loss": 6.2406,
|
|
"mean_token_accuracy": 0.14898033291101456,
|
|
"num_tokens": 4890673.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.250637340545654,
|
|
"epoch": 2.485330681253108,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004702191866639792,
|
|
"loss": 6.0741,
|
|
"mean_token_accuracy": 0.15462934374809265,
|
|
"num_tokens": 4899444.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.3585422992706295,
|
|
"epoch": 2.490303331675783,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004700247247661726,
|
|
"loss": 6.221,
|
|
"mean_token_accuracy": 0.14708278700709343,
|
|
"num_tokens": 4909186.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.306670808792115,
|
|
"epoch": 2.4952759820984585,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004698296753355072,
|
|
"loss": 6.0286,
|
|
"mean_token_accuracy": 0.16564324349164963,
|
|
"num_tokens": 4918886.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.390728521347046,
|
|
"epoch": 2.5002486325211337,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004696340389595903,
|
|
"loss": 6.2257,
|
|
"mean_token_accuracy": 0.14931683242321014,
|
|
"num_tokens": 4929157.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.305367040634155,
|
|
"epoch": 2.505221282943809,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046943781622779733,
|
|
"loss": 6.03,
|
|
"mean_token_accuracy": 0.15918946117162705,
|
|
"num_tokens": 4938127.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.267340660095215,
|
|
"epoch": 2.510193933366484,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046924100773127055,
|
|
"loss": 6.0501,
|
|
"mean_token_accuracy": 0.16451887041330338,
|
|
"num_tokens": 4947849.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.254082298278808,
|
|
"epoch": 2.5151665837891595,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046904361406291633,
|
|
"loss": 6.131,
|
|
"mean_token_accuracy": 0.15335376411676407,
|
|
"num_tokens": 4957046.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.291847276687622,
|
|
"epoch": 2.520139234211835,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004688456358174044,
|
|
"loss": 6.1421,
|
|
"mean_token_accuracy": 0.1539437621831894,
|
|
"num_tokens": 4967128.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.373083019256592,
|
|
"epoch": 2.5251118846345104,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004686470735911653,
|
|
"loss": 6.2393,
|
|
"mean_token_accuracy": 0.144418303668499,
|
|
"num_tokens": 4976817.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.3636922359466555,
|
|
"epoch": 2.5300845350571857,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004684479279823891,
|
|
"loss": 6.1718,
|
|
"mean_token_accuracy": 0.15101566314697265,
|
|
"num_tokens": 4985908.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.348957252502442,
|
|
"epoch": 2.535057185479861,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004682481995910232,
|
|
"loss": 6.0886,
|
|
"mean_token_accuracy": 0.15929078161716462,
|
|
"num_tokens": 4995218.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.280660629272461,
|
|
"epoch": 2.540029835902536,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046804788901877084,
|
|
"loss": 6.244,
|
|
"mean_token_accuracy": 0.14518138021230698,
|
|
"num_tokens": 5004197.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.387739849090576,
|
|
"epoch": 2.5450024863252114,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046784699686908886,
|
|
"loss": 6.1812,
|
|
"mean_token_accuracy": 0.14685312211513518,
|
|
"num_tokens": 5015408.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.336242055892944,
|
|
"epoch": 2.5499751367478867,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046764552374718656,
|
|
"loss": 6.1515,
|
|
"mean_token_accuracy": 0.15117971003055572,
|
|
"num_tokens": 5025138.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.302519941329956,
|
|
"epoch": 2.554947787170562,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046744347026002315,
|
|
"loss": 6.1742,
|
|
"mean_token_accuracy": 0.15080280005931854,
|
|
"num_tokens": 5034638.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.337027454376221,
|
|
"epoch": 2.559920437593237,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004672408370163066,
|
|
"loss": 6.2637,
|
|
"mean_token_accuracy": 0.1479930877685547,
|
|
"num_tokens": 5044826.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.4419121742248535,
|
|
"epoch": 2.5648930880159124,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000467037624626491,
|
|
"loss": 6.3596,
|
|
"mean_token_accuracy": 0.13942843079566955,
|
|
"num_tokens": 5054914.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.150164222717285,
|
|
"epoch": 2.5698657384385877,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046683383370277554,
|
|
"loss": 6.0755,
|
|
"mean_token_accuracy": 0.16460661292076112,
|
|
"num_tokens": 5066689.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.392885541915893,
|
|
"epoch": 2.574838388861263,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046662946485910226,
|
|
"loss": 6.2382,
|
|
"mean_token_accuracy": 0.15109140202403068,
|
|
"num_tokens": 5076170.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.359324789047241,
|
|
"epoch": 2.579811039283938,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000466424518711154,
|
|
"loss": 6.0753,
|
|
"mean_token_accuracy": 0.15616871267557145,
|
|
"num_tokens": 5085433.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.276824522018432,
|
|
"epoch": 2.5847836897066134,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004662189958763531,
|
|
"loss": 6.0771,
|
|
"mean_token_accuracy": 0.15208711326122284,
|
|
"num_tokens": 5095692.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.261534404754639,
|
|
"epoch": 2.5897563401292887,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004660128969738591,
|
|
"loss": 6.1712,
|
|
"mean_token_accuracy": 0.14797401651740075,
|
|
"num_tokens": 5105037.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.278675174713134,
|
|
"epoch": 2.594728990551964,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004658062226245668,
|
|
"loss": 6.116,
|
|
"mean_token_accuracy": 0.15553598254919052,
|
|
"num_tokens": 5113868.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.42035608291626,
|
|
"epoch": 2.5997016409746396,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004655989734511052,
|
|
"loss": 6.1526,
|
|
"mean_token_accuracy": 0.14935576766729355,
|
|
"num_tokens": 5123136.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.218199110031128,
|
|
"epoch": 2.604674291397315,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004653911500778343,
|
|
"loss": 6.0272,
|
|
"mean_token_accuracy": 0.15916819721460343,
|
|
"num_tokens": 5133869.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.299799966812134,
|
|
"epoch": 2.60964694181999,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004651827531308443,
|
|
"loss": 6.1342,
|
|
"mean_token_accuracy": 0.1547848805785179,
|
|
"num_tokens": 5143119.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.166619205474854,
|
|
"epoch": 2.6146195922426654,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004649737832379534,
|
|
"loss": 5.9498,
|
|
"mean_token_accuracy": 0.16994276344776155,
|
|
"num_tokens": 5152167.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.329884004592896,
|
|
"epoch": 2.6195922426653406,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004647642410287057,
|
|
"loss": 6.244,
|
|
"mean_token_accuracy": 0.15419655293226242,
|
|
"num_tokens": 5161962.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.248636674880982,
|
|
"epoch": 2.624564893088016,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004645541271343696,
|
|
"loss": 6.0852,
|
|
"mean_token_accuracy": 0.15108563750982285,
|
|
"num_tokens": 5171637.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.1749248027801515,
|
|
"epoch": 2.629537543510691,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046434344218793566,
|
|
"loss": 6.0404,
|
|
"mean_token_accuracy": 0.15902187973260878,
|
|
"num_tokens": 5181839.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.266619348526001,
|
|
"epoch": 2.6345101939333664,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046413218682411485,
|
|
"loss": 6.1311,
|
|
"mean_token_accuracy": 0.1541195422410965,
|
|
"num_tokens": 5192237.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.326601648330689,
|
|
"epoch": 2.6394828443560416,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004639203616793365,
|
|
"loss": 6.2928,
|
|
"mean_token_accuracy": 0.14335640370845795,
|
|
"num_tokens": 5203879.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.32307915687561,
|
|
"epoch": 2.6444554947787173,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046370796739174657,
|
|
"loss": 6.1411,
|
|
"mean_token_accuracy": 0.14719850048422814,
|
|
"num_tokens": 5213456.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.233912086486816,
|
|
"epoch": 2.6494281452013926,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046349500460120556,
|
|
"loss": 6.0779,
|
|
"mean_token_accuracy": 0.15484897941350936,
|
|
"num_tokens": 5222234.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.240962743759155,
|
|
"epoch": 2.654400795624068,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046328147394928684,
|
|
"loss": 6.13,
|
|
"mean_token_accuracy": 0.15236740410327912,
|
|
"num_tokens": 5230989.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.336632585525512,
|
|
"epoch": 2.659373446046743,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004630673760792741,
|
|
"loss": 6.1406,
|
|
"mean_token_accuracy": 0.14780201390385628,
|
|
"num_tokens": 5240607.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.3712399959564205,
|
|
"epoch": 2.6643460964694183,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004628527116361603,
|
|
"loss": 6.2463,
|
|
"mean_token_accuracy": 0.14455514252185822,
|
|
"num_tokens": 5250837.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.269100046157837,
|
|
"epoch": 2.6693187468920936,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004626374812666449,
|
|
"loss": 6.1615,
|
|
"mean_token_accuracy": 0.15395133197307587,
|
|
"num_tokens": 5260542.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.22268967628479,
|
|
"epoch": 2.674291397314769,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046242168561913256,
|
|
"loss": 6.03,
|
|
"mean_token_accuracy": 0.15913075655698777,
|
|
"num_tokens": 5272327.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.289228439331055,
|
|
"epoch": 2.679264047737444,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046220532534373067,
|
|
"loss": 6.1723,
|
|
"mean_token_accuracy": 0.1534484177827835,
|
|
"num_tokens": 5281407.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.307604598999023,
|
|
"epoch": 2.6842366981601193,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004619884010922477,
|
|
"loss": 6.1245,
|
|
"mean_token_accuracy": 0.14651363641023635,
|
|
"num_tokens": 5291617.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.324279689788819,
|
|
"epoch": 2.6892093485827946,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004617709135181913,
|
|
"loss": 6.1783,
|
|
"mean_token_accuracy": 0.15019302517175676,
|
|
"num_tokens": 5301174.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.340631198883057,
|
|
"epoch": 2.69418199900547,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046155286327676594,
|
|
"loss": 6.1781,
|
|
"mean_token_accuracy": 0.14791998863220215,
|
|
"num_tokens": 5311211.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.273455476760864,
|
|
"epoch": 2.699154649428145,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046133425102487134,
|
|
"loss": 6.1892,
|
|
"mean_token_accuracy": 0.14950599595904351,
|
|
"num_tokens": 5321343.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.278795337677002,
|
|
"epoch": 2.7041272998508203,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046111507742110035,
|
|
"loss": 6.1215,
|
|
"mean_token_accuracy": 0.16036065071821212,
|
|
"num_tokens": 5330849.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.339806461334229,
|
|
"epoch": 2.7090999502734956,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000460895343125737,
|
|
"loss": 6.2345,
|
|
"mean_token_accuracy": 0.14596203789114953,
|
|
"num_tokens": 5340836.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.311350917816162,
|
|
"epoch": 2.714072600696171,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046067504880075425,
|
|
"loss": 6.0926,
|
|
"mean_token_accuracy": 0.1574402444064617,
|
|
"num_tokens": 5351093.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.218340301513672,
|
|
"epoch": 2.719045251118846,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004604541951098122,
|
|
"loss": 6.1403,
|
|
"mean_token_accuracy": 0.14954117313027382,
|
|
"num_tokens": 5360859.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.204424667358398,
|
|
"epoch": 2.724017901541522,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004602327827182565,
|
|
"loss": 5.924,
|
|
"mean_token_accuracy": 0.16559789180755616,
|
|
"num_tokens": 5370591.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.25838623046875,
|
|
"epoch": 2.728990551964197,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004600108122931156,
|
|
"loss": 6.0475,
|
|
"mean_token_accuracy": 0.16185160130262374,
|
|
"num_tokens": 5380019.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.219852018356323,
|
|
"epoch": 2.7339632023868723,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045978828450309907,
|
|
"loss": 6.1342,
|
|
"mean_token_accuracy": 0.14812708795070648,
|
|
"num_tokens": 5389558.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.2615550518035885,
|
|
"epoch": 2.7389358528095475,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004595652000185958,
|
|
"loss": 6.1533,
|
|
"mean_token_accuracy": 0.15487857162952423,
|
|
"num_tokens": 5398305.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.368145608901978,
|
|
"epoch": 2.743908503232223,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045934155951167163,
|
|
"loss": 6.241,
|
|
"mean_token_accuracy": 0.14805518761277198,
|
|
"num_tokens": 5406886.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.309777784347534,
|
|
"epoch": 2.748881153654898,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004591173636560675,
|
|
"loss": 6.2275,
|
|
"mean_token_accuracy": 0.15173901617527008,
|
|
"num_tokens": 5416404.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.298162364959717,
|
|
"epoch": 2.7538538040775733,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004588926131271974,
|
|
"loss": 6.1211,
|
|
"mean_token_accuracy": 0.15658542960882188,
|
|
"num_tokens": 5425746.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.290420818328857,
|
|
"epoch": 2.7588264545002485,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045866730860214655,
|
|
"loss": 6.1817,
|
|
"mean_token_accuracy": 0.15295832753181457,
|
|
"num_tokens": 5436089.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.2482075691223145,
|
|
"epoch": 2.763799104922924,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004584414507596687,
|
|
"loss": 6.1133,
|
|
"mean_token_accuracy": 0.1538049101829529,
|
|
"num_tokens": 5446270.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.300816583633423,
|
|
"epoch": 2.768771755345599,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045821504028018494,
|
|
"loss": 6.1252,
|
|
"mean_token_accuracy": 0.1530563622713089,
|
|
"num_tokens": 5455476.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.342614698410034,
|
|
"epoch": 2.7737444057682747,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004579880778457811,
|
|
"loss": 6.161,
|
|
"mean_token_accuracy": 0.15088774859905243,
|
|
"num_tokens": 5463813.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.264906406402588,
|
|
"epoch": 2.77871705619095,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004577605641402056,
|
|
"loss": 6.1214,
|
|
"mean_token_accuracy": 0.15249574482440947,
|
|
"num_tokens": 5473127.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.195119762420655,
|
|
"epoch": 2.7836897066136252,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004575324998488681,
|
|
"loss": 6.0973,
|
|
"mean_token_accuracy": 0.15503255426883697,
|
|
"num_tokens": 5481595.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.23312520980835,
|
|
"epoch": 2.7886623570363005,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004573038856588364,
|
|
"loss": 6.1589,
|
|
"mean_token_accuracy": 0.15163869336247443,
|
|
"num_tokens": 5491495.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.233642053604126,
|
|
"epoch": 2.7936350074589757,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004570747222588354,
|
|
"loss": 6.1375,
|
|
"mean_token_accuracy": 0.15815336257219315,
|
|
"num_tokens": 5500702.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.332838773727417,
|
|
"epoch": 2.798607657881651,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045684501033924443,
|
|
"loss": 6.0571,
|
|
"mean_token_accuracy": 0.15646361336112022,
|
|
"num_tokens": 5510223.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.277385902404785,
|
|
"epoch": 2.8035803083043263,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045661475059209503,
|
|
"loss": 6.2527,
|
|
"mean_token_accuracy": 0.1458101563155651,
|
|
"num_tokens": 5522063.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.262352466583252,
|
|
"epoch": 2.8085529587270015,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004563839437110695,
|
|
"loss": 6.1179,
|
|
"mean_token_accuracy": 0.15994191616773606,
|
|
"num_tokens": 5531323.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.303058433532715,
|
|
"epoch": 2.8135256091496768,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045615259039149826,
|
|
"loss": 6.1344,
|
|
"mean_token_accuracy": 0.15833210796117783,
|
|
"num_tokens": 5540637.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.218224239349365,
|
|
"epoch": 2.818498259572352,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045592069133035783,
|
|
"loss": 6.0437,
|
|
"mean_token_accuracy": 0.16324926018714905,
|
|
"num_tokens": 5550992.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.221521615982056,
|
|
"epoch": 2.8234709099950273,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004556882472262691,
|
|
"loss": 6.0942,
|
|
"mean_token_accuracy": 0.1546429857611656,
|
|
"num_tokens": 5561140.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.262024307250977,
|
|
"epoch": 2.8284435604177025,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004554552587794948,
|
|
"loss": 6.1298,
|
|
"mean_token_accuracy": 0.1518692798912525,
|
|
"num_tokens": 5570457.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.281118297576905,
|
|
"epoch": 2.8334162108403778,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004552217266919375,
|
|
"loss": 6.2724,
|
|
"mean_token_accuracy": 0.13877538815140725,
|
|
"num_tokens": 5579950.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.34550142288208,
|
|
"epoch": 2.838388861263053,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004549876516671376,
|
|
"loss": 6.1736,
|
|
"mean_token_accuracy": 0.1522243782877922,
|
|
"num_tokens": 5589441.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.24541449546814,
|
|
"epoch": 2.8433615116857283,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045475303441027114,
|
|
"loss": 6.0001,
|
|
"mean_token_accuracy": 0.16179976090788842,
|
|
"num_tokens": 5598583.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.197868585586548,
|
|
"epoch": 2.8483341621084035,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004545178756281479,
|
|
"loss": 6.0722,
|
|
"mean_token_accuracy": 0.1597920760512352,
|
|
"num_tokens": 5609198.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.275570058822632,
|
|
"epoch": 2.853306812531079,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00045428217602920876,
|
|
"loss": 6.0939,
|
|
"mean_token_accuracy": 0.15120761543512345,
|
|
"num_tokens": 5620425.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.177303600311279,
|
|
"epoch": 2.8582794629537545,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00045404593632352385,
|
|
"loss": 5.9309,
|
|
"mean_token_accuracy": 0.16411565393209457,
|
|
"num_tokens": 5629578.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.238070917129517,
|
|
"epoch": 2.8632521133764297,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004538091572227909,
|
|
"loss": 6.1092,
|
|
"mean_token_accuracy": 0.1509953185915947,
|
|
"num_tokens": 5639817.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.356387042999268,
|
|
"epoch": 2.868224763799105,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004535718394403319,
|
|
"loss": 6.2349,
|
|
"mean_token_accuracy": 0.15656870305538179,
|
|
"num_tokens": 5649130.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.26152286529541,
|
|
"epoch": 2.87319741422178,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004533339836910924,
|
|
"loss": 6.1611,
|
|
"mean_token_accuracy": 0.15411016643047332,
|
|
"num_tokens": 5659672.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.266425228118896,
|
|
"epoch": 2.8781700646444555,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004530955906916382,
|
|
"loss": 6.2171,
|
|
"mean_token_accuracy": 0.14910464882850646,
|
|
"num_tokens": 5669491.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.126580810546875,
|
|
"epoch": 2.8831427150671307,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004528566611601536,
|
|
"loss": 5.9217,
|
|
"mean_token_accuracy": 0.1706739604473114,
|
|
"num_tokens": 5679444.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.302479934692383,
|
|
"epoch": 2.888115365489806,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004526171958164396,
|
|
"loss": 6.2261,
|
|
"mean_token_accuracy": 0.1430768460035324,
|
|
"num_tokens": 5690997.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.302704954147339,
|
|
"epoch": 2.893088015912481,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045237719538191107,
|
|
"loss": 6.129,
|
|
"mean_token_accuracy": 0.15047723799943924,
|
|
"num_tokens": 5700727.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.270546340942383,
|
|
"epoch": 2.898060666335157,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000452136660579595,
|
|
"loss": 6.1047,
|
|
"mean_token_accuracy": 0.15459212064743041,
|
|
"num_tokens": 5710809.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.1122133255004885,
|
|
"epoch": 2.903033316757832,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045189559213412825,
|
|
"loss": 6.0173,
|
|
"mean_token_accuracy": 0.16419658437371254,
|
|
"num_tokens": 5720286.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.243424415588379,
|
|
"epoch": 2.9080059671805074,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004516539907717553,
|
|
"loss": 6.1125,
|
|
"mean_token_accuracy": 0.1565114364027977,
|
|
"num_tokens": 5730627.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.211738872528076,
|
|
"epoch": 2.9129786176031827,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045141185722032617,
|
|
"loss": 6.0074,
|
|
"mean_token_accuracy": 0.1612328827381134,
|
|
"num_tokens": 5739752.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.244409227371216,
|
|
"epoch": 2.917951268025858,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045116919220929407,
|
|
"loss": 6.0784,
|
|
"mean_token_accuracy": 0.15862237215042113,
|
|
"num_tokens": 5748277.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.106018590927124,
|
|
"epoch": 2.922923918448533,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004509259964697133,
|
|
"loss": 5.917,
|
|
"mean_token_accuracy": 0.1734441339969635,
|
|
"num_tokens": 5758632.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.209386110305786,
|
|
"epoch": 2.9278965688712084,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000450682270734237,
|
|
"loss": 6.087,
|
|
"mean_token_accuracy": 0.1576337471604347,
|
|
"num_tokens": 5769107.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.230212020874023,
|
|
"epoch": 2.9328692192938837,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004504380157371152,
|
|
"loss": 6.1095,
|
|
"mean_token_accuracy": 0.1542981445789337,
|
|
"num_tokens": 5779051.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.21975679397583,
|
|
"epoch": 2.937841869716559,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045019323221419204,
|
|
"loss": 6.0874,
|
|
"mean_token_accuracy": 0.15395583361387252,
|
|
"num_tokens": 5788826.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.176873874664307,
|
|
"epoch": 2.942814520139234,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044994792090290425,
|
|
"loss": 6.1269,
|
|
"mean_token_accuracy": 0.15007320269942284,
|
|
"num_tokens": 5798003.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.236095952987671,
|
|
"epoch": 2.9477871705619094,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044970208254227836,
|
|
"loss": 6.0991,
|
|
"mean_token_accuracy": 0.1531677395105362,
|
|
"num_tokens": 5807215.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.261950445175171,
|
|
"epoch": 2.9527598209845847,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044945571787292866,
|
|
"loss": 6.1121,
|
|
"mean_token_accuracy": 0.15661653727293015,
|
|
"num_tokens": 5816629.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.19658408164978,
|
|
"epoch": 2.95773247140726,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004492088276370552,
|
|
"loss": 6.0662,
|
|
"mean_token_accuracy": 0.15904722437262536,
|
|
"num_tokens": 5825840.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.311341953277588,
|
|
"epoch": 2.962705121829935,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004489614125784411,
|
|
"loss": 6.2456,
|
|
"mean_token_accuracy": 0.14235614463686944,
|
|
"num_tokens": 5835754.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.203617811203003,
|
|
"epoch": 2.9676777722526104,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004487134734424509,
|
|
"loss": 6.1485,
|
|
"mean_token_accuracy": 0.15674863159656524,
|
|
"num_tokens": 5846062.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.288834047317505,
|
|
"epoch": 2.9726504226752857,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004484650109760276,
|
|
"loss": 6.2099,
|
|
"mean_token_accuracy": 0.14974870532751083,
|
|
"num_tokens": 5855589.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.257716512680053,
|
|
"epoch": 2.9776230730979614,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004482160259276911,
|
|
"loss": 5.9889,
|
|
"mean_token_accuracy": 0.16585026681423187,
|
|
"num_tokens": 5864917.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.2388365268707275,
|
|
"epoch": 2.9825957235206366,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004479665190475355,
|
|
"loss": 6.1129,
|
|
"mean_token_accuracy": 0.1574447013437748,
|
|
"num_tokens": 5875530.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 2.9825957235206366,
|
|
"eval_entropy": 6.1082542140363,
|
|
"eval_loss": 6.617149829864502,
|
|
"eval_mean_token_accuracy": 0.13689831483782985,
|
|
"eval_num_tokens": 5875530.0,
|
|
"eval_runtime": 2.5136,
|
|
"eval_samples_per_second": 1378.514,
|
|
"eval_steps_per_second": 172.662,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 6.276051568984985,
|
|
"epoch": 2.987568373943312,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044771649108722695,
|
|
"loss": 6.1815,
|
|
"mean_token_accuracy": 0.15346652269363403,
|
|
"num_tokens": 5885363.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 6.320553874969482,
|
|
"epoch": 2.992541024365987,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004474659428000014,
|
|
"loss": 6.1861,
|
|
"mean_token_accuracy": 0.15063076391816138,
|
|
"num_tokens": 5895318.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 6.252550363540649,
|
|
"epoch": 2.9975136747886624,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044721487494066254,
|
|
"loss": 6.2027,
|
|
"mean_token_accuracy": 0.15004834532737732,
|
|
"num_tokens": 5905742.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 6.197555965847439,
|
|
"epoch": 3.00198906016907,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000446963288265579,
|
|
"loss": 5.9369,
|
|
"mean_token_accuracy": 0.1680561469660865,
|
|
"num_tokens": 5913844.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 6.250605726242066,
|
|
"epoch": 3.0069617105917454,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044671118353268257,
|
|
"loss": 5.7563,
|
|
"mean_token_accuracy": 0.15910323560237885,
|
|
"num_tokens": 5923724.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 6.17890157699585,
|
|
"epoch": 3.0119343610144207,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044645856150146593,
|
|
"loss": 5.7944,
|
|
"mean_token_accuracy": 0.1605706363916397,
|
|
"num_tokens": 5933787.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 6.302218437194824,
|
|
"epoch": 3.016907011437096,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044620542293297974,
|
|
"loss": 5.7963,
|
|
"mean_token_accuracy": 0.1592818409204483,
|
|
"num_tokens": 5944186.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 6.198193550109863,
|
|
"epoch": 3.021879661859771,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004459517685898312,
|
|
"loss": 5.7543,
|
|
"mean_token_accuracy": 0.16684997975826263,
|
|
"num_tokens": 5954465.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 6.30923056602478,
|
|
"epoch": 3.0268523122824464,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044569759923618113,
|
|
"loss": 5.8087,
|
|
"mean_token_accuracy": 0.16614169329404832,
|
|
"num_tokens": 5965047.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 6.0891632556915285,
|
|
"epoch": 3.0318249627051217,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004454429156377419,
|
|
"loss": 5.615,
|
|
"mean_token_accuracy": 0.18128216713666917,
|
|
"num_tokens": 5974855.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 6.092777156829834,
|
|
"epoch": 3.036797613127797,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004451877185617751,
|
|
"loss": 5.6229,
|
|
"mean_token_accuracy": 0.17165209650993346,
|
|
"num_tokens": 5985965.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 6.303160572052002,
|
|
"epoch": 3.041770263550472,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004449320087770894,
|
|
"loss": 5.8376,
|
|
"mean_token_accuracy": 0.1646388754248619,
|
|
"num_tokens": 5996646.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 6.158918333053589,
|
|
"epoch": 3.046742913973148,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004446757870540376,
|
|
"loss": 5.6418,
|
|
"mean_token_accuracy": 0.17871743589639663,
|
|
"num_tokens": 6005825.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.0633245468139645,
|
|
"epoch": 3.051715564395823,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004444190541645153,
|
|
"loss": 5.5875,
|
|
"mean_token_accuracy": 0.17701890617609023,
|
|
"num_tokens": 6016909.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 6.25791916847229,
|
|
"epoch": 3.0566882148184984,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044416181088195776,
|
|
"loss": 5.7807,
|
|
"mean_token_accuracy": 0.16531898379325866,
|
|
"num_tokens": 6025511.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 6.1637708187103275,
|
|
"epoch": 3.0616608652411736,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004439040579813379,
|
|
"loss": 5.698,
|
|
"mean_token_accuracy": 0.17304742932319642,
|
|
"num_tokens": 6035114.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 6.151741170883179,
|
|
"epoch": 3.066633515663849,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044364579623916385,
|
|
"loss": 5.7466,
|
|
"mean_token_accuracy": 0.1662996828556061,
|
|
"num_tokens": 6044963.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 6.07142596244812,
|
|
"epoch": 3.071606166086524,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004433870264334767,
|
|
"loss": 5.5833,
|
|
"mean_token_accuracy": 0.1800165668129921,
|
|
"num_tokens": 6054660.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 6.145099639892578,
|
|
"epoch": 3.0765788165091994,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004431277493438484,
|
|
"loss": 5.6888,
|
|
"mean_token_accuracy": 0.17005201578140258,
|
|
"num_tokens": 6064288.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 6.119443082809449,
|
|
"epoch": 3.0815514669318746,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004428679657513789,
|
|
"loss": 5.7118,
|
|
"mean_token_accuracy": 0.16573365181684493,
|
|
"num_tokens": 6074133.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 6.1205555438995365,
|
|
"epoch": 3.08652411735455,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004426076764386939,
|
|
"loss": 5.7313,
|
|
"mean_token_accuracy": 0.17093567848205565,
|
|
"num_tokens": 6084314.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 6.100643348693848,
|
|
"epoch": 3.091496767777225,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044234688218994293,
|
|
"loss": 5.695,
|
|
"mean_token_accuracy": 0.1725090891122818,
|
|
"num_tokens": 6094616.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 6.123282814025879,
|
|
"epoch": 3.0964694181999004,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004420855837907967,
|
|
"loss": 5.736,
|
|
"mean_token_accuracy": 0.1623416319489479,
|
|
"num_tokens": 6104167.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.970840072631836,
|
|
"epoch": 3.1014420686225757,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044182378202844427,
|
|
"loss": 5.5012,
|
|
"mean_token_accuracy": 0.18685950040817262,
|
|
"num_tokens": 6113970.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 6.152586126327515,
|
|
"epoch": 3.106414719045251,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044156147769159183,
|
|
"loss": 5.7041,
|
|
"mean_token_accuracy": 0.16574736982583999,
|
|
"num_tokens": 6123482.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 6.122572517395019,
|
|
"epoch": 3.1113873694679266,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004412986715704591,
|
|
"loss": 5.6719,
|
|
"mean_token_accuracy": 0.17441177368164062,
|
|
"num_tokens": 6133682.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 6.059462308883667,
|
|
"epoch": 3.116360019890602,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004410353644567777,
|
|
"loss": 5.6912,
|
|
"mean_token_accuracy": 0.17087724059820175,
|
|
"num_tokens": 6143876.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 6.134020471572876,
|
|
"epoch": 3.121332670313277,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044077155714378836,
|
|
"loss": 5.8121,
|
|
"mean_token_accuracy": 0.16391794085502626,
|
|
"num_tokens": 6153615.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 6.155704545974731,
|
|
"epoch": 3.1263053207359524,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004405072504262391,
|
|
"loss": 5.7033,
|
|
"mean_token_accuracy": 0.1777438759803772,
|
|
"num_tokens": 6163572.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 6.03270263671875,
|
|
"epoch": 3.1312779711586276,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000440242445100382,
|
|
"loss": 5.6761,
|
|
"mean_token_accuracy": 0.17295461893081665,
|
|
"num_tokens": 6173085.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 6.1938488483428955,
|
|
"epoch": 3.136250621581303,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043997714196397143,
|
|
"loss": 5.749,
|
|
"mean_token_accuracy": 0.1609796665608883,
|
|
"num_tokens": 6183124.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 6.1891954898834225,
|
|
"epoch": 3.141223272003978,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043971134181626173,
|
|
"loss": 5.7812,
|
|
"mean_token_accuracy": 0.1642882704734802,
|
|
"num_tokens": 6192817.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 6.11192045211792,
|
|
"epoch": 3.1461959224266534,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00043944504545800396,
|
|
"loss": 5.7387,
|
|
"mean_token_accuracy": 0.173209448158741,
|
|
"num_tokens": 6203643.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 6.144415330886841,
|
|
"epoch": 3.1511685728493286,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004391782536914447,
|
|
"loss": 5.7627,
|
|
"mean_token_accuracy": 0.16663320660591124,
|
|
"num_tokens": 6213712.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 6.117935562133789,
|
|
"epoch": 3.156141223272004,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00043891096732032257,
|
|
"loss": 5.8434,
|
|
"mean_token_accuracy": 0.16059125065803528,
|
|
"num_tokens": 6223962.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 6.182265186309815,
|
|
"epoch": 3.161113873694679,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043864318714986625,
|
|
"loss": 5.8194,
|
|
"mean_token_accuracy": 0.16386526674032212,
|
|
"num_tokens": 6235273.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 6.133540630340576,
|
|
"epoch": 3.1660865241173544,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043837491398679234,
|
|
"loss": 5.5974,
|
|
"mean_token_accuracy": 0.1745193913578987,
|
|
"num_tokens": 6245161.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 6.039244842529297,
|
|
"epoch": 3.17105917454003,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004381061486393025,
|
|
"loss": 5.691,
|
|
"mean_token_accuracy": 0.16741855144500734,
|
|
"num_tokens": 6253300.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 6.076604557037354,
|
|
"epoch": 3.1760318249627053,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004378368919170809,
|
|
"loss": 5.7181,
|
|
"mean_token_accuracy": 0.17458892613649368,
|
|
"num_tokens": 6263525.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 6.1078320980072025,
|
|
"epoch": 3.1810044753853806,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043756714463129244,
|
|
"loss": 5.7092,
|
|
"mean_token_accuracy": 0.16688139140605926,
|
|
"num_tokens": 6274010.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 6.1255927085876465,
|
|
"epoch": 3.185977125808056,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004372969075945796,
|
|
"loss": 5.7578,
|
|
"mean_token_accuracy": 0.16886054128408431,
|
|
"num_tokens": 6283442.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 6.051163005828857,
|
|
"epoch": 3.190949776230731,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004370261816210604,
|
|
"loss": 5.7135,
|
|
"mean_token_accuracy": 0.1748140722513199,
|
|
"num_tokens": 6293498.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.991288852691651,
|
|
"epoch": 3.1959224266534063,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004367549675263258,
|
|
"loss": 5.5656,
|
|
"mean_token_accuracy": 0.18583164364099503,
|
|
"num_tokens": 6303557.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 6.201500082015992,
|
|
"epoch": 3.2008950770760816,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004364832661274373,
|
|
"loss": 5.9089,
|
|
"mean_token_accuracy": 0.15793548077344893,
|
|
"num_tokens": 6314304.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 6.1190080642700195,
|
|
"epoch": 3.205867727498757,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043621107824292444,
|
|
"loss": 5.7628,
|
|
"mean_token_accuracy": 0.16341807544231415,
|
|
"num_tokens": 6324959.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.9546692848205565,
|
|
"epoch": 3.210840377921432,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004359384046927824,
|
|
"loss": 5.5319,
|
|
"mean_token_accuracy": 0.18841264992952347,
|
|
"num_tokens": 6335909.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 6.121433973312378,
|
|
"epoch": 3.2158130283441073,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004356652462984693,
|
|
"loss": 5.786,
|
|
"mean_token_accuracy": 0.16254806965589524,
|
|
"num_tokens": 6346659.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 6.033808755874634,
|
|
"epoch": 3.2207856787667826,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043539160388290416,
|
|
"loss": 5.5818,
|
|
"mean_token_accuracy": 0.1895093724131584,
|
|
"num_tokens": 6357264.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 6.101437711715699,
|
|
"epoch": 3.225758329189458,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004351174782704641,
|
|
"loss": 5.8264,
|
|
"mean_token_accuracy": 0.16124693155288697,
|
|
"num_tokens": 6366107.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 6.022504091262817,
|
|
"epoch": 3.230730979612133,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043484287028698176,
|
|
"loss": 5.6198,
|
|
"mean_token_accuracy": 0.17807340621948242,
|
|
"num_tokens": 6375505.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 6.1405885219573975,
|
|
"epoch": 3.2357036300348083,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043456778075974306,
|
|
"loss": 5.8519,
|
|
"mean_token_accuracy": 0.15565126836299897,
|
|
"num_tokens": 6384701.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 6.144344425201416,
|
|
"epoch": 3.240676280457484,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043429221051748487,
|
|
"loss": 5.6763,
|
|
"mean_token_accuracy": 0.17359301894903184,
|
|
"num_tokens": 6393707.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 6.045299673080445,
|
|
"epoch": 3.2456489308801593,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043401616039039174,
|
|
"loss": 5.7729,
|
|
"mean_token_accuracy": 0.16360995769500733,
|
|
"num_tokens": 6404277.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 6.139099788665772,
|
|
"epoch": 3.2506215813028345,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004337396312100944,
|
|
"loss": 5.8281,
|
|
"mean_token_accuracy": 0.1589790999889374,
|
|
"num_tokens": 6415275.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 6.124218511581421,
|
|
"epoch": 3.2555942317255098,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004334626238096665,
|
|
"loss": 5.7301,
|
|
"mean_token_accuracy": 0.16668106019496917,
|
|
"num_tokens": 6425598.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 6.071162414550781,
|
|
"epoch": 3.260566882148185,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004331851390236227,
|
|
"loss": 5.6719,
|
|
"mean_token_accuracy": 0.16784296184778214,
|
|
"num_tokens": 6435685.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 6.054525232315063,
|
|
"epoch": 3.2655395325708603,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043290717768791533,
|
|
"loss": 5.6686,
|
|
"mean_token_accuracy": 0.17824159562587738,
|
|
"num_tokens": 6444950.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 6.04873685836792,
|
|
"epoch": 3.2705121829935355,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043262874063993285,
|
|
"loss": 5.7045,
|
|
"mean_token_accuracy": 0.16980573385953904,
|
|
"num_tokens": 6454066.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 6.103368091583252,
|
|
"epoch": 3.2754848334162108,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004323498287184967,
|
|
"loss": 5.8233,
|
|
"mean_token_accuracy": 0.16557388603687287,
|
|
"num_tokens": 6464912.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 6.1594908237457275,
|
|
"epoch": 3.280457483838886,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043207044276385884,
|
|
"loss": 5.8336,
|
|
"mean_token_accuracy": 0.16242281198501587,
|
|
"num_tokens": 6474178.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.927899026870728,
|
|
"epoch": 3.2854301342615613,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043179058361769924,
|
|
"loss": 5.5725,
|
|
"mean_token_accuracy": 0.18530458360910415,
|
|
"num_tokens": 6485703.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 6.068869590759277,
|
|
"epoch": 3.2904027846842365,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004315102521231237,
|
|
"loss": 5.7017,
|
|
"mean_token_accuracy": 0.17006365358829498,
|
|
"num_tokens": 6495309.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 6.094325685501099,
|
|
"epoch": 3.295375435106912,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004312294491246609,
|
|
"loss": 5.6474,
|
|
"mean_token_accuracy": 0.1737009346485138,
|
|
"num_tokens": 6505498.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.989164018630982,
|
|
"epoch": 3.3003480855295875,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004309481754682597,
|
|
"loss": 5.6886,
|
|
"mean_token_accuracy": 0.17401858568191528,
|
|
"num_tokens": 6514656.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 6.081707572937011,
|
|
"epoch": 3.3053207359522627,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043066643200128724,
|
|
"loss": 5.7326,
|
|
"mean_token_accuracy": 0.1706549659371376,
|
|
"num_tokens": 6524549.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 6.033634614944458,
|
|
"epoch": 3.310293386374938,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004303842195725259,
|
|
"loss": 5.6557,
|
|
"mean_token_accuracy": 0.17347126007080077,
|
|
"num_tokens": 6533861.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 6.127212762832642,
|
|
"epoch": 3.3152660367976132,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043010153903217074,
|
|
"loss": 5.84,
|
|
"mean_token_accuracy": 0.16723482608795165,
|
|
"num_tokens": 6543676.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 6.155271530151367,
|
|
"epoch": 3.3202386872202885,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004298183912318273,
|
|
"loss": 5.7306,
|
|
"mean_token_accuracy": 0.16943766176700592,
|
|
"num_tokens": 6552263.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.987417697906494,
|
|
"epoch": 3.3252113376429637,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042953477702450845,
|
|
"loss": 5.6993,
|
|
"mean_token_accuracy": 0.17505183964967727,
|
|
"num_tokens": 6560960.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 6.019518613815308,
|
|
"epoch": 3.330183988065639,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004292506972646324,
|
|
"loss": 5.6074,
|
|
"mean_token_accuracy": 0.18462952822446824,
|
|
"num_tokens": 6572345.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 6.111158037185669,
|
|
"epoch": 3.3351566384883142,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042896615280802006,
|
|
"loss": 5.7641,
|
|
"mean_token_accuracy": 0.1648932471871376,
|
|
"num_tokens": 6582274.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 6.010473299026489,
|
|
"epoch": 3.3401292889109895,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00042868114451189164,
|
|
"loss": 5.6968,
|
|
"mean_token_accuracy": 0.17124658972024917,
|
|
"num_tokens": 6592486.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 6.009715127944946,
|
|
"epoch": 3.3451019393336647,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004283956732348655,
|
|
"loss": 5.6297,
|
|
"mean_token_accuracy": 0.1823193609714508,
|
|
"num_tokens": 6600876.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 6.024749279022217,
|
|
"epoch": 3.35007458975634,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042810973983695426,
|
|
"loss": 5.6259,
|
|
"mean_token_accuracy": 0.17926731407642366,
|
|
"num_tokens": 6610679.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 6.101885843276977,
|
|
"epoch": 3.3550472401790152,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004278233451795629,
|
|
"loss": 5.7717,
|
|
"mean_token_accuracy": 0.1684168428182602,
|
|
"num_tokens": 6620779.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 6.121217823028564,
|
|
"epoch": 3.3600198906016905,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000427536490125486,
|
|
"loss": 5.7201,
|
|
"mean_token_accuracy": 0.17498980164527894,
|
|
"num_tokens": 6630807.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.966057157516479,
|
|
"epoch": 3.364992541024366,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042724917553890507,
|
|
"loss": 5.6161,
|
|
"mean_token_accuracy": 0.1832486942410469,
|
|
"num_tokens": 6640530.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 6.053667449951172,
|
|
"epoch": 3.3699651914470414,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042696140228538616,
|
|
"loss": 5.6732,
|
|
"mean_token_accuracy": 0.17446995675563812,
|
|
"num_tokens": 6650845.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 6.05461106300354,
|
|
"epoch": 3.3749378418697167,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042667317123187696,
|
|
"loss": 5.7149,
|
|
"mean_token_accuracy": 0.1680520161986351,
|
|
"num_tokens": 6660455.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.996423959732056,
|
|
"epoch": 3.379910492292392,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042638448324670424,
|
|
"loss": 5.6631,
|
|
"mean_token_accuracy": 0.17386710047721862,
|
|
"num_tokens": 6670493.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 6.067140531539917,
|
|
"epoch": 3.384883142715067,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004260953391995716,
|
|
"loss": 5.7832,
|
|
"mean_token_accuracy": 0.16583538800477982,
|
|
"num_tokens": 6680598.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.905293130874634,
|
|
"epoch": 3.3898557931377424,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042580573996155646,
|
|
"loss": 5.5394,
|
|
"mean_token_accuracy": 0.18978741616010666,
|
|
"num_tokens": 6691569.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 6.091068077087402,
|
|
"epoch": 3.3948284435604177,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004255156864051074,
|
|
"loss": 5.8335,
|
|
"mean_token_accuracy": 0.16865168064832686,
|
|
"num_tokens": 6702570.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.90501651763916,
|
|
"epoch": 3.399801093983093,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042522517940404186,
|
|
"loss": 5.5189,
|
|
"mean_token_accuracy": 0.196772438287735,
|
|
"num_tokens": 6711628.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 6.109512138366699,
|
|
"epoch": 3.404773744405768,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004249342198335433,
|
|
"loss": 5.7062,
|
|
"mean_token_accuracy": 0.16897250413894654,
|
|
"num_tokens": 6721828.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.887783002853394,
|
|
"epoch": 3.4097463948284434,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042464280857015856,
|
|
"loss": 5.5786,
|
|
"mean_token_accuracy": 0.1893717646598816,
|
|
"num_tokens": 6731903.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.98098464012146,
|
|
"epoch": 3.4147190452511187,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042435094649179525,
|
|
"loss": 5.7555,
|
|
"mean_token_accuracy": 0.17771680355072023,
|
|
"num_tokens": 6743236.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.9573582172393795,
|
|
"epoch": 3.419691695673794,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004240586344777191,
|
|
"loss": 5.5599,
|
|
"mean_token_accuracy": 0.18280196487903594,
|
|
"num_tokens": 6753291.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 6.13610463142395,
|
|
"epoch": 3.4246643460964696,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004237658734085514,
|
|
"loss": 5.7682,
|
|
"mean_token_accuracy": 0.16798161566257477,
|
|
"num_tokens": 6762635.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 6.010785102844238,
|
|
"epoch": 3.429636996519145,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042347266416626624,
|
|
"loss": 5.7252,
|
|
"mean_token_accuracy": 0.17165041118860244,
|
|
"num_tokens": 6772101.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 6.04913363456726,
|
|
"epoch": 3.43460964694182,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004231790076341877,
|
|
"loss": 5.7458,
|
|
"mean_token_accuracy": 0.16925113499164582,
|
|
"num_tokens": 6781563.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 6.046193361282349,
|
|
"epoch": 3.4395822973644954,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004228849046969876,
|
|
"loss": 5.709,
|
|
"mean_token_accuracy": 0.1734888657927513,
|
|
"num_tokens": 6790589.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 6.014021015167236,
|
|
"epoch": 3.4445549477871706,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004225903562406826,
|
|
"loss": 5.7087,
|
|
"mean_token_accuracy": 0.17345761954784394,
|
|
"num_tokens": 6799842.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 6.088991594314575,
|
|
"epoch": 3.449527598209846,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004222953631526313,
|
|
"loss": 5.7885,
|
|
"mean_token_accuracy": 0.16932941377162933,
|
|
"num_tokens": 6809166.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 6.0506579875946045,
|
|
"epoch": 3.454500248632521,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000421999926321532,
|
|
"loss": 5.7823,
|
|
"mean_token_accuracy": 0.16928314715623854,
|
|
"num_tokens": 6818255.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 6.070717859268188,
|
|
"epoch": 3.4594728990551964,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004217040466374199,
|
|
"loss": 5.6664,
|
|
"mean_token_accuracy": 0.17864044457674028,
|
|
"num_tokens": 6828628.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 6.036036777496338,
|
|
"epoch": 3.4644455494778716,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042140772499166403,
|
|
"loss": 5.822,
|
|
"mean_token_accuracy": 0.16856673806905748,
|
|
"num_tokens": 6839053.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 6.050028657913208,
|
|
"epoch": 3.469418199900547,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004211109622769652,
|
|
"loss": 5.7524,
|
|
"mean_token_accuracy": 0.1661965563893318,
|
|
"num_tokens": 6849226.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 6.04726767539978,
|
|
"epoch": 3.474390850323222,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042081375938735283,
|
|
"loss": 5.7198,
|
|
"mean_token_accuracy": 0.17447879761457444,
|
|
"num_tokens": 6858867.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 6.034285545349121,
|
|
"epoch": 3.4793635007458974,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00042051611721818233,
|
|
"loss": 5.7476,
|
|
"mean_token_accuracy": 0.1753674179315567,
|
|
"num_tokens": 6869171.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 6.082628870010376,
|
|
"epoch": 3.4843361511685726,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042021803666613273,
|
|
"loss": 5.7182,
|
|
"mean_token_accuracy": 0.17003970444202424,
|
|
"num_tokens": 6878582.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 6.034718465805054,
|
|
"epoch": 3.489308801591248,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00041991951862920365,
|
|
"loss": 5.7663,
|
|
"mean_token_accuracy": 0.17114875912666322,
|
|
"num_tokens": 6887522.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 6.0207751274108885,
|
|
"epoch": 3.4942814520139236,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004196205640067124,
|
|
"loss": 5.6642,
|
|
"mean_token_accuracy": 0.17363226115703584,
|
|
"num_tokens": 6897556.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 6.028400039672851,
|
|
"epoch": 3.499254102436599,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000419321173699292,
|
|
"loss": 5.7361,
|
|
"mean_token_accuracy": 0.17644919753074645,
|
|
"num_tokens": 6908219.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 6.048381328582764,
|
|
"epoch": 3.504226752859274,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004190213486088877,
|
|
"loss": 5.7532,
|
|
"mean_token_accuracy": 0.164937561750412,
|
|
"num_tokens": 6918175.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 6.066301250457764,
|
|
"epoch": 3.5091994032819493,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004187210896387546,
|
|
"loss": 5.8547,
|
|
"mean_token_accuracy": 0.16665040403604509,
|
|
"num_tokens": 6927076.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 6.104689693450927,
|
|
"epoch": 3.5141720537046246,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004184203976934552,
|
|
"loss": 5.7655,
|
|
"mean_token_accuracy": 0.17511976063251494,
|
|
"num_tokens": 6936568.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.989154624938965,
|
|
"epoch": 3.5191447041273,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00041811927367885605,
|
|
"loss": 5.719,
|
|
"mean_token_accuracy": 0.17178210765123367,
|
|
"num_tokens": 6945494.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 6.076043939590454,
|
|
"epoch": 3.524117354549975,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004178177185021254,
|
|
"loss": 5.6882,
|
|
"mean_token_accuracy": 0.18165635615587233,
|
|
"num_tokens": 6955397.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 6.061611557006836,
|
|
"epoch": 3.5290900049726504,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004175157330717305,
|
|
"loss": 5.8171,
|
|
"mean_token_accuracy": 0.16348701268434523,
|
|
"num_tokens": 6965431.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.99527587890625,
|
|
"epoch": 3.5340626553953256,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000417213318297435,
|
|
"loss": 5.6638,
|
|
"mean_token_accuracy": 0.17533465027809142,
|
|
"num_tokens": 6975457.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.955399513244629,
|
|
"epoch": 3.539035305818001,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00041691047509029555,
|
|
"loss": 5.5683,
|
|
"mean_token_accuracy": 0.18708720207214355,
|
|
"num_tokens": 6984691.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.894686317443847,
|
|
"epoch": 3.5440079562406765,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00041660720436265987,
|
|
"loss": 5.6176,
|
|
"mean_token_accuracy": 0.18430614322423935,
|
|
"num_tokens": 6994052.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 6.05457239151001,
|
|
"epoch": 3.548980606663352,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004163035070281634,
|
|
"loss": 5.7513,
|
|
"mean_token_accuracy": 0.16968111991882323,
|
|
"num_tokens": 7003625.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 6.010856437683105,
|
|
"epoch": 3.553953257086027,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00041599938400172686,
|
|
"loss": 5.8072,
|
|
"mean_token_accuracy": 0.16901623085141182,
|
|
"num_tokens": 7011967.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 6.086786699295044,
|
|
"epoch": 3.5589259075087023,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041569483619955354,
|
|
"loss": 5.8085,
|
|
"mean_token_accuracy": 0.16925800144672393,
|
|
"num_tokens": 7021722.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 6.134664630889892,
|
|
"epoch": 3.5638985579313776,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041538986453912616,
|
|
"loss": 5.8534,
|
|
"mean_token_accuracy": 0.1607050135731697,
|
|
"num_tokens": 7031720.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 6.0486665725708,
|
|
"epoch": 3.568871208354053,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004150844699392045,
|
|
"loss": 5.7878,
|
|
"mean_token_accuracy": 0.16425765603780745,
|
|
"num_tokens": 7040575.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 6.211868190765381,
|
|
"epoch": 3.573843858776728,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00041477865331982264,
|
|
"loss": 5.7754,
|
|
"mean_token_accuracy": 0.16845039874315262,
|
|
"num_tokens": 7050035.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.903217840194702,
|
|
"epoch": 3.5788165091994033,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004144724156022857,
|
|
"loss": 5.5944,
|
|
"mean_token_accuracy": 0.18823051154613496,
|
|
"num_tokens": 7060950.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.985196781158447,
|
|
"epoch": 3.5837891596220786,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041416575770916763,
|
|
"loss": 5.7496,
|
|
"mean_token_accuracy": 0.16748472452163696,
|
|
"num_tokens": 7070384.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 6.111241674423217,
|
|
"epoch": 3.588761810044754,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041385868056430827,
|
|
"loss": 5.8689,
|
|
"mean_token_accuracy": 0.15785489976406097,
|
|
"num_tokens": 7081118.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 6.086476516723633,
|
|
"epoch": 3.593734460467429,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004135511850928102,
|
|
"loss": 5.8279,
|
|
"mean_token_accuracy": 0.1625514581799507,
|
|
"num_tokens": 7091157.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 6.065000295639038,
|
|
"epoch": 3.5987071108901043,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041324327222103655,
|
|
"loss": 5.7929,
|
|
"mean_token_accuracy": 0.1664402335882187,
|
|
"num_tokens": 7101005.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.970553398132324,
|
|
"epoch": 3.6036797613127796,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041293494287660785,
|
|
"loss": 5.7591,
|
|
"mean_token_accuracy": 0.16669861674308778,
|
|
"num_tokens": 7109944.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 6.114343643188477,
|
|
"epoch": 3.608652411735455,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00041262619798839914,
|
|
"loss": 5.8102,
|
|
"mean_token_accuracy": 0.1587171107530594,
|
|
"num_tokens": 7119073.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 6.11523060798645,
|
|
"epoch": 3.61362506215813,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041231703848653746,
|
|
"loss": 5.8142,
|
|
"mean_token_accuracy": 0.1592143803834915,
|
|
"num_tokens": 7128920.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 6.039280986785888,
|
|
"epoch": 3.6185977125808053,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00041200746530239903,
|
|
"loss": 5.8326,
|
|
"mean_token_accuracy": 0.16038841307163237,
|
|
"num_tokens": 7138691.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 6.09878716468811,
|
|
"epoch": 3.623570363003481,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004116974793686061,
|
|
"loss": 5.7552,
|
|
"mean_token_accuracy": 0.17601397931575774,
|
|
"num_tokens": 7148362.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 6.0114881038665775,
|
|
"epoch": 3.6285430134261563,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004113870816190244,
|
|
"loss": 5.7259,
|
|
"mean_token_accuracy": 0.17077140510082245,
|
|
"num_tokens": 7157138.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 6.070823240280151,
|
|
"epoch": 3.6335156638488315,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004110762729887605,
|
|
"loss": 5.8796,
|
|
"mean_token_accuracy": 0.1611786887049675,
|
|
"num_tokens": 7167425.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 6.0405271530151365,
|
|
"epoch": 3.6384883142715068,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00041076505441415873,
|
|
"loss": 5.7665,
|
|
"mean_token_accuracy": 0.17101671695709228,
|
|
"num_tokens": 7177059.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 6.158518362045288,
|
|
"epoch": 3.643460964694182,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004104534268327982,
|
|
"loss": 5.8156,
|
|
"mean_token_accuracy": 0.16653167605400085,
|
|
"num_tokens": 7186435.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 6.037448501586914,
|
|
"epoch": 3.6484336151168573,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004101413911834904,
|
|
"loss": 5.7991,
|
|
"mean_token_accuracy": 0.16928482204675674,
|
|
"num_tokens": 7197248.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 6.019806718826294,
|
|
"epoch": 3.6534062655395325,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040982894840627614,
|
|
"loss": 5.7425,
|
|
"mean_token_accuracy": 0.16435276120901107,
|
|
"num_tokens": 7206042.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 6.093596982955932,
|
|
"epoch": 3.6583789159622078,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004095160994424228,
|
|
"loss": 5.8039,
|
|
"mean_token_accuracy": 0.16714893877506257,
|
|
"num_tokens": 7215822.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 6.056409597396851,
|
|
"epoch": 3.663351566384883,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040920284523442125,
|
|
"loss": 5.8164,
|
|
"mean_token_accuracy": 0.1657966986298561,
|
|
"num_tokens": 7226131.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 6.011003732681274,
|
|
"epoch": 3.6683242168075583,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00040888918672598337,
|
|
"loss": 5.715,
|
|
"mean_token_accuracy": 0.17126342356204988,
|
|
"num_tokens": 7234095.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 6.005457639694214,
|
|
"epoch": 3.673296867230234,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000408575124862039,
|
|
"loss": 5.6556,
|
|
"mean_token_accuracy": 0.18683372735977172,
|
|
"num_tokens": 7243184.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 6.0760244846344,
|
|
"epoch": 3.678269517652909,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004082606605887331,
|
|
"loss": 5.7811,
|
|
"mean_token_accuracy": 0.1627069041132927,
|
|
"num_tokens": 7253654.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.981401824951172,
|
|
"epoch": 3.6832421680755845,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040794579485342304,
|
|
"loss": 5.6315,
|
|
"mean_token_accuracy": 0.1688546806573868,
|
|
"num_tokens": 7262063.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.932995223999024,
|
|
"epoch": 3.6882148184982597,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00040763052860467547,
|
|
"loss": 5.6458,
|
|
"mean_token_accuracy": 0.18471641093492508,
|
|
"num_tokens": 7272490.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 6.048797559738159,
|
|
"epoch": 3.693187468920935,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004073148627922637,
|
|
"loss": 5.8742,
|
|
"mean_token_accuracy": 0.15992219895124435,
|
|
"num_tokens": 7282938.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 6.036251211166382,
|
|
"epoch": 3.69816011934361,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004069987983671648,
|
|
"loss": 5.7142,
|
|
"mean_token_accuracy": 0.17161259651184083,
|
|
"num_tokens": 7293486.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 6.042434024810791,
|
|
"epoch": 3.7031327697662855,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00040668233628155664,
|
|
"loss": 5.7154,
|
|
"mean_token_accuracy": 0.1698968753218651,
|
|
"num_tokens": 7302806.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.987484264373779,
|
|
"epoch": 3.7081054201889607,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004063654774888153,
|
|
"loss": 5.8016,
|
|
"mean_token_accuracy": 0.1699465900659561,
|
|
"num_tokens": 7312250.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 6.142599105834961,
|
|
"epoch": 3.713078070611636,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004060482229435116,
|
|
"loss": 5.7159,
|
|
"mean_token_accuracy": 0.17830608785152435,
|
|
"num_tokens": 7321512.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.989974117279052,
|
|
"epoch": 3.7180507210343112,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004057305736014089,
|
|
"loss": 5.7699,
|
|
"mean_token_accuracy": 0.17657275199890138,
|
|
"num_tokens": 7331467.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 6.013858318328857,
|
|
"epoch": 3.7230233714569865,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004054125304194598,
|
|
"loss": 5.7067,
|
|
"mean_token_accuracy": 0.17274003028869628,
|
|
"num_tokens": 7340064.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.983120393753052,
|
|
"epoch": 3.7279960218796617,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040509409435580355,
|
|
"loss": 5.7185,
|
|
"mean_token_accuracy": 0.17572370916604996,
|
|
"num_tokens": 7350138.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 6.033293676376343,
|
|
"epoch": 3.732968672302337,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004047752663697627,
|
|
"loss": 5.7974,
|
|
"mean_token_accuracy": 0.16884278655052185,
|
|
"num_tokens": 7359613.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 6.01333179473877,
|
|
"epoch": 3.7379413227250122,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004044560474218409,
|
|
"loss": 5.7137,
|
|
"mean_token_accuracy": 0.1764787495136261,
|
|
"num_tokens": 7368754.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 6.01878547668457,
|
|
"epoch": 3.7429139731476875,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00040413643847371923,
|
|
"loss": 5.7042,
|
|
"mean_token_accuracy": 0.1711568094789982,
|
|
"num_tokens": 7378930.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 6.04103798866272,
|
|
"epoch": 3.7478866235703627,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004038164404882539,
|
|
"loss": 5.7758,
|
|
"mean_token_accuracy": 0.16100075840950012,
|
|
"num_tokens": 7387281.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 6.025457763671875,
|
|
"epoch": 3.7528592739930384,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004034960544294731,
|
|
"loss": 5.6666,
|
|
"mean_token_accuracy": 0.17651643306016923,
|
|
"num_tokens": 7397039.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.951560688018799,
|
|
"epoch": 3.7578319244157137,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00040317528126257413,
|
|
"loss": 5.7598,
|
|
"mean_token_accuracy": 0.17415926307439805,
|
|
"num_tokens": 7406771.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 6.0234838962554935,
|
|
"epoch": 3.762804574838389,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004028541219539205,
|
|
"loss": 5.7058,
|
|
"mean_token_accuracy": 0.18072424232959747,
|
|
"num_tokens": 7415743.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.85155725479126,
|
|
"epoch": 3.767777225261064,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004025325774710391,
|
|
"loss": 5.5112,
|
|
"mean_token_accuracy": 0.18594044595956802,
|
|
"num_tokens": 7424243.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 6.002374935150146,
|
|
"epoch": 3.7727498756837394,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040221064878261684,
|
|
"loss": 5.803,
|
|
"mean_token_accuracy": 0.16520698443055154,
|
|
"num_tokens": 7434273.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 6.040292358398437,
|
|
"epoch": 3.7777225261064147,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004018883368584985,
|
|
"loss": 5.7409,
|
|
"mean_token_accuracy": 0.16955991834402084,
|
|
"num_tokens": 7444640.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.979375267028809,
|
|
"epoch": 3.78269517652909,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00040156564266968336,
|
|
"loss": 5.5976,
|
|
"mean_token_accuracy": 0.17540031522512436,
|
|
"num_tokens": 7453774.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 6.033125495910644,
|
|
"epoch": 3.787667826951765,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040124256718832214,
|
|
"loss": 5.7297,
|
|
"mean_token_accuracy": 0.17008136063814164,
|
|
"num_tokens": 7464288.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 6.0769726753234865,
|
|
"epoch": 3.7926404773744404,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004009191113877141,
|
|
"loss": 5.793,
|
|
"mean_token_accuracy": 0.17005982846021653,
|
|
"num_tokens": 7474626.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 6.048680400848388,
|
|
"epoch": 3.797613127797116,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004005952762423048,
|
|
"loss": 5.7675,
|
|
"mean_token_accuracy": 0.18045601844787598,
|
|
"num_tokens": 7483393.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 6.024804353713989,
|
|
"epoch": 3.8025857782197914,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004002710627276821,
|
|
"loss": 5.7936,
|
|
"mean_token_accuracy": 0.16404973864555358,
|
|
"num_tokens": 7492197.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.973055696487426,
|
|
"epoch": 3.8075584286424666,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003999464718205739,
|
|
"loss": 5.7677,
|
|
"mean_token_accuracy": 0.1735682725906372,
|
|
"num_tokens": 7501822.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.927748394012451,
|
|
"epoch": 3.812531079065142,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003996215044988451,
|
|
"loss": 5.6516,
|
|
"mean_token_accuracy": 0.18202109932899474,
|
|
"num_tokens": 7512686.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 6.061821508407593,
|
|
"epoch": 3.817503729487817,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039929616174149454,
|
|
"loss": 5.7741,
|
|
"mean_token_accuracy": 0.1649671360850334,
|
|
"num_tokens": 7522593.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 6.006787252426148,
|
|
"epoch": 3.8224763799104924,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039897044452865207,
|
|
"loss": 5.8212,
|
|
"mean_token_accuracy": 0.16416242718696594,
|
|
"num_tokens": 7532448.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.926284313201904,
|
|
"epoch": 3.8274490303331676,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003986443538415756,
|
|
"loss": 5.5516,
|
|
"mean_token_accuracy": 0.19510907977819442,
|
|
"num_tokens": 7543008.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.945953130722046,
|
|
"epoch": 3.832421680755843,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003983178906626484,
|
|
"loss": 5.6404,
|
|
"mean_token_accuracy": 0.17782956808805467,
|
|
"num_tokens": 7553236.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 6.011856889724731,
|
|
"epoch": 3.837394331178518,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039799105597537564,
|
|
"loss": 5.7944,
|
|
"mean_token_accuracy": 0.17167262732982635,
|
|
"num_tokens": 7561583.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 6.07290301322937,
|
|
"epoch": 3.8423669816011934,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003976638507643818,
|
|
"loss": 5.7768,
|
|
"mean_token_accuracy": 0.16563078314065932,
|
|
"num_tokens": 7571290.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 6.026663732528687,
|
|
"epoch": 3.8473396320238686,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003973362760154076,
|
|
"loss": 5.7805,
|
|
"mean_token_accuracy": 0.16347938179969787,
|
|
"num_tokens": 7579976.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.971474885940552,
|
|
"epoch": 3.852312282446544,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003970083327153071,
|
|
"loss": 5.7308,
|
|
"mean_token_accuracy": 0.16538184732198716,
|
|
"num_tokens": 7589796.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.985939168930054,
|
|
"epoch": 3.857284932869219,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003966800218520445,
|
|
"loss": 5.6782,
|
|
"mean_token_accuracy": 0.1746913820505142,
|
|
"num_tokens": 7598976.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 6.084162616729737,
|
|
"epoch": 3.8622575832918944,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003963513444146914,
|
|
"loss": 5.844,
|
|
"mean_token_accuracy": 0.16418759971857072,
|
|
"num_tokens": 7607955.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.981510066986084,
|
|
"epoch": 3.8672302337145696,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003960223013934239,
|
|
"loss": 5.7188,
|
|
"mean_token_accuracy": 0.16986412853002547,
|
|
"num_tokens": 7619822.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.946630764007568,
|
|
"epoch": 3.872202884137245,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003956928937795192,
|
|
"loss": 5.6446,
|
|
"mean_token_accuracy": 0.18194590359926224,
|
|
"num_tokens": 7630481.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 6.035385942459106,
|
|
"epoch": 3.8771755345599206,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000395363122565353,
|
|
"loss": 5.728,
|
|
"mean_token_accuracy": 0.1690193846821785,
|
|
"num_tokens": 7640312.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 6.183091831207276,
|
|
"epoch": 3.882148184982596,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039503298874439655,
|
|
"loss": 6.0033,
|
|
"mean_token_accuracy": 0.1514565907418728,
|
|
"num_tokens": 7649792.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 6.025466346740723,
|
|
"epoch": 3.887120835405271,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003947024933112131,
|
|
"loss": 5.6988,
|
|
"mean_token_accuracy": 0.1801825925707817,
|
|
"num_tokens": 7659458.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.982737684249878,
|
|
"epoch": 3.8920934858279463,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003943716372614556,
|
|
"loss": 5.7234,
|
|
"mean_token_accuracy": 0.17692274004220962,
|
|
"num_tokens": 7668770.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.972765111923218,
|
|
"epoch": 3.8970661362506216,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003940404215918634,
|
|
"loss": 5.6492,
|
|
"mean_token_accuracy": 0.18124958425760268,
|
|
"num_tokens": 7677067.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.940464353561401,
|
|
"epoch": 3.902038786673297,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039370884730025897,
|
|
"loss": 5.7174,
|
|
"mean_token_accuracy": 0.1715057075023651,
|
|
"num_tokens": 7687723.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 6.0613950252532955,
|
|
"epoch": 3.907011437095972,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003933769153855455,
|
|
"loss": 5.8789,
|
|
"mean_token_accuracy": 0.16839688867330552,
|
|
"num_tokens": 7696706.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 6.075004720687867,
|
|
"epoch": 3.9119840875186473,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003930446268477034,
|
|
"loss": 5.7536,
|
|
"mean_token_accuracy": 0.16607760936021804,
|
|
"num_tokens": 7706356.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 6.00281867980957,
|
|
"epoch": 3.9169567379413226,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003927119826877875,
|
|
"loss": 5.7742,
|
|
"mean_token_accuracy": 0.17431652545928955,
|
|
"num_tokens": 7717255.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.988306093215942,
|
|
"epoch": 3.921929388363998,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003923789839079238,
|
|
"loss": 5.7933,
|
|
"mean_token_accuracy": 0.1671350672841072,
|
|
"num_tokens": 7728493.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 6.079870128631592,
|
|
"epoch": 3.9269020387866735,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039204563151130683,
|
|
"loss": 5.7321,
|
|
"mean_token_accuracy": 0.1667914792895317,
|
|
"num_tokens": 7738582.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 6.0593396663665775,
|
|
"epoch": 3.931874689209349,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003917119265021965,
|
|
"loss": 5.8372,
|
|
"mean_token_accuracy": 0.1693793088197708,
|
|
"num_tokens": 7748486.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.893445682525635,
|
|
"epoch": 3.936847339632024,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0003913778698859146,
|
|
"loss": 5.5674,
|
|
"mean_token_accuracy": 0.18689510449767113,
|
|
"num_tokens": 7758033.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 6.0197525978088375,
|
|
"epoch": 3.9418199900546993,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003910434626688427,
|
|
"loss": 5.6421,
|
|
"mean_token_accuracy": 0.1734244108200073,
|
|
"num_tokens": 7768577.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.985113525390625,
|
|
"epoch": 3.9467926404773745,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003907087058584183,
|
|
"loss": 5.76,
|
|
"mean_token_accuracy": 0.16587879955768586,
|
|
"num_tokens": 7778546.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.997487258911133,
|
|
"epoch": 3.95176529090005,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039037360046313186,
|
|
"loss": 5.7569,
|
|
"mean_token_accuracy": 0.1734464555978775,
|
|
"num_tokens": 7787523.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 6.086761808395385,
|
|
"epoch": 3.956737941322725,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039003814749252454,
|
|
"loss": 5.7175,
|
|
"mean_token_accuracy": 0.17700511515140532,
|
|
"num_tokens": 7798198.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 6.098475313186645,
|
|
"epoch": 3.9617105917454003,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038970234795718424,
|
|
"loss": 5.8597,
|
|
"mean_token_accuracy": 0.16218929439783097,
|
|
"num_tokens": 7808137.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.953400754928589,
|
|
"epoch": 3.9666832421680756,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000389366202868743,
|
|
"loss": 5.7507,
|
|
"mean_token_accuracy": 0.17570445388555528,
|
|
"num_tokens": 7817367.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.850185298919678,
|
|
"epoch": 3.971655892590751,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003890297132398739,
|
|
"loss": 5.5747,
|
|
"mean_token_accuracy": 0.19131145179271697,
|
|
"num_tokens": 7826419.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 6.048769998550415,
|
|
"epoch": 3.976628543013426,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003886928800842879,
|
|
"loss": 5.7503,
|
|
"mean_token_accuracy": 0.1701797991991043,
|
|
"num_tokens": 7834984.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"epoch": 3.976628543013426,
|
|
"eval_entropy": 5.962670287778301,
|
|
"eval_loss": 6.520203113555908,
|
|
"eval_mean_token_accuracy": 0.14399389114042033,
|
|
"eval_num_tokens": 7834984.0,
|
|
"eval_runtime": 2.5027,
|
|
"eval_samples_per_second": 1384.496,
|
|
"eval_steps_per_second": 173.412,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 6.003405618667602,
|
|
"epoch": 3.9816011934361013,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00038835570441673095,
|
|
"loss": 5.7202,
|
|
"mean_token_accuracy": 0.17171710729599,
|
|
"num_tokens": 7844781.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 6.048596334457398,
|
|
"epoch": 3.9865738438587766,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003880181872529809,
|
|
"loss": 5.7954,
|
|
"mean_token_accuracy": 0.17341204583644867,
|
|
"num_tokens": 7854553.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 6.063149166107178,
|
|
"epoch": 3.991546494281452,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003876803296098443,
|
|
"loss": 5.7459,
|
|
"mean_token_accuracy": 0.1701970785856247,
|
|
"num_tokens": 7863900.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 6.048019456863403,
|
|
"epoch": 3.996519144704127,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003873421325051535,
|
|
"loss": 5.7194,
|
|
"mean_token_accuracy": 0.1756090134382248,
|
|
"num_tokens": 7873008.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.95560884475708,
|
|
"epoch": 4.000994530084535,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038700359695776346,
|
|
"loss": 5.6897,
|
|
"mean_token_accuracy": 0.1685895091957516,
|
|
"num_tokens": 7882489.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.945594835281372,
|
|
"epoch": 4.00596718050721,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003866647239875487,
|
|
"loss": 5.4321,
|
|
"mean_token_accuracy": 0.17848863452672958,
|
|
"num_tokens": 7893370.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.998771715164184,
|
|
"epoch": 4.010939830929885,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00038632551461540023,
|
|
"loss": 5.3354,
|
|
"mean_token_accuracy": 0.19647165685892104,
|
|
"num_tokens": 7903815.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 6.0648658752441404,
|
|
"epoch": 4.015912481352561,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003859859698632228,
|
|
"loss": 5.4455,
|
|
"mean_token_accuracy": 0.1789711207151413,
|
|
"num_tokens": 7913365.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.995429182052613,
|
|
"epoch": 4.020885131775236,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003856460907539312,
|
|
"loss": 5.4089,
|
|
"mean_token_accuracy": 0.1905644491314888,
|
|
"num_tokens": 7922973.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 6.030227899551392,
|
|
"epoch": 4.025857782197911,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003853058783114478,
|
|
"loss": 5.3636,
|
|
"mean_token_accuracy": 0.19061112999916077,
|
|
"num_tokens": 7932860.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 6.01555871963501,
|
|
"epoch": 4.030830432620586,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003849653335606987,
|
|
"loss": 5.3815,
|
|
"mean_token_accuracy": 0.1874824583530426,
|
|
"num_tokens": 7942524.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 6.016945266723633,
|
|
"epoch": 4.035803083043262,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003846244575276117,
|
|
"loss": 5.4861,
|
|
"mean_token_accuracy": 0.17812152355909347,
|
|
"num_tokens": 7952289.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.885750198364258,
|
|
"epoch": 4.040775733465938,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038428325123911205,
|
|
"loss": 5.3514,
|
|
"mean_token_accuracy": 0.19400051832199097,
|
|
"num_tokens": 7962176.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 6.025964212417603,
|
|
"epoch": 4.045748383888613,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003839417157231205,
|
|
"loss": 5.4661,
|
|
"mean_token_accuracy": 0.1793301969766617,
|
|
"num_tokens": 7971300.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.9139196395874025,
|
|
"epoch": 4.050721034311288,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003835998520085492,
|
|
"loss": 5.3521,
|
|
"mean_token_accuracy": 0.19512623995542527,
|
|
"num_tokens": 7981135.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.891085577011109,
|
|
"epoch": 4.0556936847339635,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003832576611252993,
|
|
"loss": 5.35,
|
|
"mean_token_accuracy": 0.19576306790113449,
|
|
"num_tokens": 7991327.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 6.024784088134766,
|
|
"epoch": 4.060666335156639,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003829151441042572,
|
|
"loss": 5.427,
|
|
"mean_token_accuracy": 0.1815014585852623,
|
|
"num_tokens": 8001318.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.880774688720703,
|
|
"epoch": 4.065638985579314,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00038257230197729237,
|
|
"loss": 5.2406,
|
|
"mean_token_accuracy": 0.1995137646794319,
|
|
"num_tokens": 8010964.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.872264194488525,
|
|
"epoch": 4.070611636001989,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038222913577725325,
|
|
"loss": 5.3998,
|
|
"mean_token_accuracy": 0.19192698299884797,
|
|
"num_tokens": 8020894.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.919008064270019,
|
|
"epoch": 4.0755842864246645,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038188564653796487,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.18565013706684114,
|
|
"num_tokens": 8030635.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.954873037338257,
|
|
"epoch": 4.08055693684734,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003815418352942252,
|
|
"loss": 5.3104,
|
|
"mean_token_accuracy": 0.19444982707500458,
|
|
"num_tokens": 8040626.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.6787200450897215,
|
|
"epoch": 4.085529587270015,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003811977030818026,
|
|
"loss": 5.0421,
|
|
"mean_token_accuracy": 0.2275480732321739,
|
|
"num_tokens": 8051835.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.878461837768555,
|
|
"epoch": 4.09050223769269,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000380853250937432,
|
|
"loss": 5.4018,
|
|
"mean_token_accuracy": 0.18876250237226486,
|
|
"num_tokens": 8061818.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.993345546722412,
|
|
"epoch": 4.0954748881153655,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00038050847989881236,
|
|
"loss": 5.4802,
|
|
"mean_token_accuracy": 0.18292125016450883,
|
|
"num_tokens": 8071693.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.831725645065307,
|
|
"epoch": 4.100447538538041,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003801633910046035,
|
|
"loss": 5.2388,
|
|
"mean_token_accuracy": 0.20439237952232361,
|
|
"num_tokens": 8082304.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.929430437088013,
|
|
"epoch": 4.105420188960716,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003798179852944225,
|
|
"loss": 5.3587,
|
|
"mean_token_accuracy": 0.18733773976564408,
|
|
"num_tokens": 8092319.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.9393223285675045,
|
|
"epoch": 4.110392839383391,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00037947226380884115,
|
|
"loss": 5.3662,
|
|
"mean_token_accuracy": 0.19536537379026414,
|
|
"num_tokens": 8100894.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.93992280960083,
|
|
"epoch": 4.1153654898060665,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00037912622758938243,
|
|
"loss": 5.5033,
|
|
"mean_token_accuracy": 0.17557998299598693,
|
|
"num_tokens": 8110029.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.936153173446655,
|
|
"epoch": 4.120338140228742,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003787798776785174,
|
|
"loss": 5.3779,
|
|
"mean_token_accuracy": 0.1822320595383644,
|
|
"num_tokens": 8118715.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.899742126464844,
|
|
"epoch": 4.125310790651417,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003784332151196622,
|
|
"loss": 5.3631,
|
|
"mean_token_accuracy": 0.20078185945749283,
|
|
"num_tokens": 8128778.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.882680511474609,
|
|
"epoch": 4.130283441074092,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00037808624095717503,
|
|
"loss": 5.3709,
|
|
"mean_token_accuracy": 0.19015274792909623,
|
|
"num_tokens": 8138126.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.915459203720093,
|
|
"epoch": 4.1352560914967675,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003777389562363526,
|
|
"loss": 5.3529,
|
|
"mean_token_accuracy": 0.19739349335432052,
|
|
"num_tokens": 8147971.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.973155307769775,
|
|
"epoch": 4.140228741919443,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00037739136200342743,
|
|
"loss": 5.4369,
|
|
"mean_token_accuracy": 0.18710529804229736,
|
|
"num_tokens": 8157853.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.87147216796875,
|
|
"epoch": 4.145201392342118,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00037704345930556426,
|
|
"loss": 5.3381,
|
|
"mean_token_accuracy": 0.19316548109054565,
|
|
"num_tokens": 8167187.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.843489360809326,
|
|
"epoch": 4.150174042764793,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00037669524919085716,
|
|
"loss": 5.3335,
|
|
"mean_token_accuracy": 0.1979242369532585,
|
|
"num_tokens": 8175492.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.879776906967163,
|
|
"epoch": 4.1551466931874685,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003763467327083264,
|
|
"loss": 5.4234,
|
|
"mean_token_accuracy": 0.18643297553062438,
|
|
"num_tokens": 8185356.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.8869095802307125,
|
|
"epoch": 4.160119343610144,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00037599791090791527,
|
|
"loss": 5.2471,
|
|
"mean_token_accuracy": 0.19870311319828032,
|
|
"num_tokens": 8194833.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 6.004298686981201,
|
|
"epoch": 4.165091994032819,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003756487848404868,
|
|
"loss": 5.4716,
|
|
"mean_token_accuracy": 0.17983096987009048,
|
|
"num_tokens": 8205040.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.979325437545777,
|
|
"epoch": 4.170064644455495,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003752993555578205,
|
|
"loss": 5.4624,
|
|
"mean_token_accuracy": 0.1851775676012039,
|
|
"num_tokens": 8214769.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.7807151794433596,
|
|
"epoch": 4.17503729487817,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003749496241126095,
|
|
"loss": 5.2835,
|
|
"mean_token_accuracy": 0.20558047145605088,
|
|
"num_tokens": 8225007.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.987300872802734,
|
|
"epoch": 4.180009945300846,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00037459959155845726,
|
|
"loss": 5.4217,
|
|
"mean_token_accuracy": 0.18637282401323318,
|
|
"num_tokens": 8234543.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.887851524353027,
|
|
"epoch": 4.184982595723521,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003742492589498744,
|
|
"loss": 5.2925,
|
|
"mean_token_accuracy": 0.19493667930364608,
|
|
"num_tokens": 8243790.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.891241502761841,
|
|
"epoch": 4.189955246146196,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00037389862734227525,
|
|
"loss": 5.3938,
|
|
"mean_token_accuracy": 0.1892183616757393,
|
|
"num_tokens": 8253144.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.911381387710572,
|
|
"epoch": 4.194927896568871,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00037354769779197514,
|
|
"loss": 5.3899,
|
|
"mean_token_accuracy": 0.18784193843603134,
|
|
"num_tokens": 8262782.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.898515367507935,
|
|
"epoch": 4.199900546991547,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00037319647135618695,
|
|
"loss": 5.3963,
|
|
"mean_token_accuracy": 0.18600946366786958,
|
|
"num_tokens": 8271544.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.878818845748901,
|
|
"epoch": 4.204873197414222,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00037284494909301793,
|
|
"loss": 5.3626,
|
|
"mean_token_accuracy": 0.19844991266727446,
|
|
"num_tokens": 8280574.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.894140195846558,
|
|
"epoch": 4.209845847836897,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003724931320614663,
|
|
"loss": 5.3328,
|
|
"mean_token_accuracy": 0.19895944893360137,
|
|
"num_tokens": 8290318.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.889474868774414,
|
|
"epoch": 4.214818498259572,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037214102132141874,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.19183834046125411,
|
|
"num_tokens": 8299619.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.8442848205566404,
|
|
"epoch": 4.219791148682248,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003717886179336465,
|
|
"loss": 5.3455,
|
|
"mean_token_accuracy": 0.1981261670589447,
|
|
"num_tokens": 8310085.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.8485801219940186,
|
|
"epoch": 4.224763799104923,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037143592295980243,
|
|
"loss": 5.3995,
|
|
"mean_token_accuracy": 0.19096325039863588,
|
|
"num_tokens": 8320673.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.905794286727906,
|
|
"epoch": 4.229736449527598,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003710829374624181,
|
|
"loss": 5.3569,
|
|
"mean_token_accuracy": 0.1922583684325218,
|
|
"num_tokens": 8331073.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.917673921585083,
|
|
"epoch": 4.2347090999502734,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003707296625048999,
|
|
"loss": 5.4456,
|
|
"mean_token_accuracy": 0.1841329514980316,
|
|
"num_tokens": 8341313.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.956054449081421,
|
|
"epoch": 4.239681750372949,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003703760991515264,
|
|
"loss": 5.4668,
|
|
"mean_token_accuracy": 0.18037177622318268,
|
|
"num_tokens": 8351004.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.76927695274353,
|
|
"epoch": 4.244654400795624,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00037002224846744526,
|
|
"loss": 5.2182,
|
|
"mean_token_accuracy": 0.20843558013439178,
|
|
"num_tokens": 8361083.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.93443455696106,
|
|
"epoch": 4.249627051218299,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00036966811151866943,
|
|
"loss": 5.468,
|
|
"mean_token_accuracy": 0.18635163307189942,
|
|
"num_tokens": 8372162.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.956264209747315,
|
|
"epoch": 4.2545997016409745,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00036931368937207436,
|
|
"loss": 5.4779,
|
|
"mean_token_accuracy": 0.17701288163661957,
|
|
"num_tokens": 8382259.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.987959718704223,
|
|
"epoch": 4.25957235206365,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003689589830953948,
|
|
"loss": 5.4371,
|
|
"mean_token_accuracy": 0.19074794203042983,
|
|
"num_tokens": 8392275.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.83184847831726,
|
|
"epoch": 4.264545002486325,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003686039937572213,
|
|
"loss": 5.3958,
|
|
"mean_token_accuracy": 0.1859956830739975,
|
|
"num_tokens": 8402481.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.859698247909546,
|
|
"epoch": 4.269517652909,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003682487224269972,
|
|
"loss": 5.4123,
|
|
"mean_token_accuracy": 0.1881951555609703,
|
|
"num_tokens": 8412609.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.894608211517334,
|
|
"epoch": 4.2744903033316755,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003678931701750155,
|
|
"loss": 5.4515,
|
|
"mean_token_accuracy": 0.18313271850347518,
|
|
"num_tokens": 8421396.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.843251085281372,
|
|
"epoch": 4.279462953754351,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00036753733807241536,
|
|
"loss": 5.3742,
|
|
"mean_token_accuracy": 0.19237405806779861,
|
|
"num_tokens": 8430076.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.85640664100647,
|
|
"epoch": 4.284435604177026,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00036718122719117907,
|
|
"loss": 5.1795,
|
|
"mean_token_accuracy": 0.21181759983301163,
|
|
"num_tokens": 8440199.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.91298828125,
|
|
"epoch": 4.289408254599701,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003668248386041288,
|
|
"loss": 5.3747,
|
|
"mean_token_accuracy": 0.1910881370306015,
|
|
"num_tokens": 8449463.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.864219665527344,
|
|
"epoch": 4.294380905022377,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00036646817338492334,
|
|
"loss": 5.229,
|
|
"mean_token_accuracy": 0.20353687256574632,
|
|
"num_tokens": 8459824.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.966132974624633,
|
|
"epoch": 4.299353555445053,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003661112326080548,
|
|
"loss": 5.4195,
|
|
"mean_token_accuracy": 0.18635123670101167,
|
|
"num_tokens": 8468778.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.909238529205322,
|
|
"epoch": 4.304326205867728,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003657540173488455,
|
|
"loss": 5.3577,
|
|
"mean_token_accuracy": 0.18936066180467606,
|
|
"num_tokens": 8478542.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.748991632461548,
|
|
"epoch": 4.309298856290403,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003653965286834446,
|
|
"loss": 5.2799,
|
|
"mean_token_accuracy": 0.20102232396602632,
|
|
"num_tokens": 8489652.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.967244720458984,
|
|
"epoch": 4.314271506713078,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003650387676888251,
|
|
"loss": 5.4603,
|
|
"mean_token_accuracy": 0.1860087290406227,
|
|
"num_tokens": 8499951.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.995985603332519,
|
|
"epoch": 4.319244157135754,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003646807354427802,
|
|
"loss": 5.5945,
|
|
"mean_token_accuracy": 0.17615066170692445,
|
|
"num_tokens": 8510664.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.960317516326905,
|
|
"epoch": 4.324216807558429,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00036432243302392025,
|
|
"loss": 5.4378,
|
|
"mean_token_accuracy": 0.18379307091236113,
|
|
"num_tokens": 8519768.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.953316020965576,
|
|
"epoch": 4.329189457981104,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00036396386151166975,
|
|
"loss": 5.4933,
|
|
"mean_token_accuracy": 0.1817129746079445,
|
|
"num_tokens": 8530909.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.91386046409607,
|
|
"epoch": 4.334162108403779,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003636050219862638,
|
|
"loss": 5.5369,
|
|
"mean_token_accuracy": 0.17666635066270828,
|
|
"num_tokens": 8541357.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.9526103973388675,
|
|
"epoch": 4.339134758826455,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00036324591552874493,
|
|
"loss": 5.4234,
|
|
"mean_token_accuracy": 0.18435925543308257,
|
|
"num_tokens": 8550819.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.9362691879272464,
|
|
"epoch": 4.34410740924913,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00036288654322095973,
|
|
"loss": 5.4706,
|
|
"mean_token_accuracy": 0.19011012762784957,
|
|
"num_tokens": 8561577.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.938501310348511,
|
|
"epoch": 4.349080059671805,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00036252690614555557,
|
|
"loss": 5.4864,
|
|
"mean_token_accuracy": 0.1771440774202347,
|
|
"num_tokens": 8572590.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.873106670379639,
|
|
"epoch": 4.35405271009448,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003621670053859778,
|
|
"loss": 5.4546,
|
|
"mean_token_accuracy": 0.18414154648780823,
|
|
"num_tokens": 8583559.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.978318452835083,
|
|
"epoch": 4.359025360517156,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000361806842026466,
|
|
"loss": 5.4925,
|
|
"mean_token_accuracy": 0.17937661707401276,
|
|
"num_tokens": 8592845.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.7171440601348875,
|
|
"epoch": 4.363998010939831,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00036144641715205077,
|
|
"loss": 5.2123,
|
|
"mean_token_accuracy": 0.20424636006355285,
|
|
"num_tokens": 8602862.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.746177339553833,
|
|
"epoch": 4.368970661362506,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003610857318485507,
|
|
"loss": 5.3281,
|
|
"mean_token_accuracy": 0.2046421691775322,
|
|
"num_tokens": 8613793.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.790445613861084,
|
|
"epoch": 4.373943311785181,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00036072478720256885,
|
|
"loss": 5.1812,
|
|
"mean_token_accuracy": 0.21194539666175843,
|
|
"num_tokens": 8623086.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.794614982604981,
|
|
"epoch": 4.378915962207857,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003603635843014895,
|
|
"loss": 5.2635,
|
|
"mean_token_accuracy": 0.20463584661483764,
|
|
"num_tokens": 8632392.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.924400663375854,
|
|
"epoch": 4.383888612630532,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00036000212423347523,
|
|
"loss": 5.5266,
|
|
"mean_token_accuracy": 0.18056900948286056,
|
|
"num_tokens": 8642452.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.9315591812133786,
|
|
"epoch": 4.388861263053207,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000359640408087463,
|
|
"loss": 5.4991,
|
|
"mean_token_accuracy": 0.18047668933868408,
|
|
"num_tokens": 8651431.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.998552417755127,
|
|
"epoch": 4.393833913475882,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003592784369531615,
|
|
"loss": 5.5731,
|
|
"mean_token_accuracy": 0.1736118495464325,
|
|
"num_tokens": 8661348.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.964708662033081,
|
|
"epoch": 4.398806563898558,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00035891621192104764,
|
|
"loss": 5.4773,
|
|
"mean_token_accuracy": 0.18011598736047746,
|
|
"num_tokens": 8671038.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.882650852203369,
|
|
"epoch": 4.403779214321233,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00035855373408236294,
|
|
"loss": 5.4391,
|
|
"mean_token_accuracy": 0.18579429984092713,
|
|
"num_tokens": 8680115.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.913854646682739,
|
|
"epoch": 4.408751864743908,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003581910045291107,
|
|
"loss": 5.4875,
|
|
"mean_token_accuracy": 0.1826659172773361,
|
|
"num_tokens": 8689665.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.909512901306153,
|
|
"epoch": 4.413724515166583,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003578280243540526,
|
|
"loss": 5.4583,
|
|
"mean_token_accuracy": 0.179430727660656,
|
|
"num_tokens": 8700114.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.741852426528931,
|
|
"epoch": 4.4186971655892595,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00035746479465070515,
|
|
"loss": 5.2343,
|
|
"mean_token_accuracy": 0.209817510843277,
|
|
"num_tokens": 8710154.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.931866884231567,
|
|
"epoch": 4.423669816011935,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00035710131651333683,
|
|
"loss": 5.5538,
|
|
"mean_token_accuracy": 0.17602647095918655,
|
|
"num_tokens": 8720787.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.831311988830566,
|
|
"epoch": 4.42864246643461,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00035673759103696447,
|
|
"loss": 5.3815,
|
|
"mean_token_accuracy": 0.19679782688617706,
|
|
"num_tokens": 8731069.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.925876092910767,
|
|
"epoch": 4.433615116857285,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003563736193173499,
|
|
"loss": 5.3996,
|
|
"mean_token_accuracy": 0.19299463778734208,
|
|
"num_tokens": 8740149.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.993027210235596,
|
|
"epoch": 4.4385877672799605,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003560094024509969,
|
|
"loss": 5.4918,
|
|
"mean_token_accuracy": 0.1811365455389023,
|
|
"num_tokens": 8749622.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.820945739746094,
|
|
"epoch": 4.443560417702636,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00035564494153514777,
|
|
"loss": 5.4125,
|
|
"mean_token_accuracy": 0.1836025595664978,
|
|
"num_tokens": 8759521.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.850789785385132,
|
|
"epoch": 4.448533068125311,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00035528023766778,
|
|
"loss": 5.4691,
|
|
"mean_token_accuracy": 0.19274427890777587,
|
|
"num_tokens": 8769387.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.945690870285034,
|
|
"epoch": 4.453505718547986,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003549152919476031,
|
|
"loss": 5.4121,
|
|
"mean_token_accuracy": 0.19621959179639817,
|
|
"num_tokens": 8777871.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.904716110229492,
|
|
"epoch": 4.4584783689706615,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00035455010547405513,
|
|
"loss": 5.4823,
|
|
"mean_token_accuracy": 0.19021692126989365,
|
|
"num_tokens": 8787613.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.899028253555298,
|
|
"epoch": 4.463451019393337,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00035418467934729934,
|
|
"loss": 5.4659,
|
|
"mean_token_accuracy": 0.17141338288784028,
|
|
"num_tokens": 8797075.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.9270336627960205,
|
|
"epoch": 4.468423669816012,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00035381901466822113,
|
|
"loss": 5.524,
|
|
"mean_token_accuracy": 0.17887892574071884,
|
|
"num_tokens": 8806087.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.9473260879516605,
|
|
"epoch": 4.473396320238687,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003534531125384244,
|
|
"loss": 5.4727,
|
|
"mean_token_accuracy": 0.18114038556814194,
|
|
"num_tokens": 8815358.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.950448942184448,
|
|
"epoch": 4.4783689706613625,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00035308697406022865,
|
|
"loss": 5.4754,
|
|
"mean_token_accuracy": 0.18940823823213576,
|
|
"num_tokens": 8825559.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.868340349197387,
|
|
"epoch": 4.483341621084038,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00035272060033666503,
|
|
"loss": 5.3906,
|
|
"mean_token_accuracy": 0.18251107037067413,
|
|
"num_tokens": 8835136.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.8804347038269045,
|
|
"epoch": 4.488314271506713,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003523539924714738,
|
|
"loss": 5.4388,
|
|
"mean_token_accuracy": 0.19427087157964706,
|
|
"num_tokens": 8843936.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.981853914260864,
|
|
"epoch": 4.493286921929388,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00035198715156910016,
|
|
"loss": 5.5528,
|
|
"mean_token_accuracy": 0.174890199303627,
|
|
"num_tokens": 8853990.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.873616361618042,
|
|
"epoch": 4.4982595723520635,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00035162007873469175,
|
|
"loss": 5.5219,
|
|
"mean_token_accuracy": 0.1821427971124649,
|
|
"num_tokens": 8863856.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.958400726318359,
|
|
"epoch": 4.503232222774739,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00035125277507409483,
|
|
"loss": 5.4448,
|
|
"mean_token_accuracy": 0.1823832020163536,
|
|
"num_tokens": 8872846.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.77593207359314,
|
|
"epoch": 4.508204873197414,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00035088524169385075,
|
|
"loss": 5.3143,
|
|
"mean_token_accuracy": 0.2008400559425354,
|
|
"num_tokens": 8883323.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.942329931259155,
|
|
"epoch": 4.513177523620089,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00035051747970119354,
|
|
"loss": 5.5602,
|
|
"mean_token_accuracy": 0.1786314994096756,
|
|
"num_tokens": 8893346.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.978811597824096,
|
|
"epoch": 4.5181501740427645,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00035014949020404523,
|
|
"loss": 5.4677,
|
|
"mean_token_accuracy": 0.18910984098911285,
|
|
"num_tokens": 8902480.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.840927076339722,
|
|
"epoch": 4.52312282446544,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00034978127431101365,
|
|
"loss": 5.3499,
|
|
"mean_token_accuracy": 0.1864204913377762,
|
|
"num_tokens": 8913496.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.876546382904053,
|
|
"epoch": 4.528095474888115,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00034941283313138865,
|
|
"loss": 5.4963,
|
|
"mean_token_accuracy": 0.17928870320320128,
|
|
"num_tokens": 8924344.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.830368995666504,
|
|
"epoch": 4.53306812531079,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003490441677751387,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.19318098127841948,
|
|
"num_tokens": 8933602.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.947137784957886,
|
|
"epoch": 4.5380407757334655,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00034867527935290773,
|
|
"loss": 5.4501,
|
|
"mean_token_accuracy": 0.18834314048290252,
|
|
"num_tokens": 8943722.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.874055624008179,
|
|
"epoch": 4.543013426156142,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00034830616897601146,
|
|
"loss": 5.3631,
|
|
"mean_token_accuracy": 0.19746258854866028,
|
|
"num_tokens": 8953535.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.715547800064087,
|
|
"epoch": 4.547986076578816,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003479368377564344,
|
|
"loss": 5.2393,
|
|
"mean_token_accuracy": 0.20070111900568008,
|
|
"num_tokens": 8963775.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.849143075942993,
|
|
"epoch": 4.552958727001492,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003475672868068265,
|
|
"loss": 5.3349,
|
|
"mean_token_accuracy": 0.1932750090956688,
|
|
"num_tokens": 8972822.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.822935104370117,
|
|
"epoch": 4.557931377424167,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00034719751724049955,
|
|
"loss": 5.4836,
|
|
"mean_token_accuracy": 0.18407146483659745,
|
|
"num_tokens": 8983058.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.837916707992553,
|
|
"epoch": 4.562904027846843,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00034682753017142387,
|
|
"loss": 5.5156,
|
|
"mean_token_accuracy": 0.18311800062656403,
|
|
"num_tokens": 8993069.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.965630626678466,
|
|
"epoch": 4.567876678269518,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00034645732671422517,
|
|
"loss": 5.5384,
|
|
"mean_token_accuracy": 0.1817454308271408,
|
|
"num_tokens": 9001471.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.904621934890747,
|
|
"epoch": 4.572849328692193,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003460869079841809,
|
|
"loss": 5.4772,
|
|
"mean_token_accuracy": 0.18578291833400726,
|
|
"num_tokens": 9012411.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.853311491012573,
|
|
"epoch": 4.577821979114868,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003457162750972172,
|
|
"loss": 5.3665,
|
|
"mean_token_accuracy": 0.19754083901643754,
|
|
"num_tokens": 9024126.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.810020780563354,
|
|
"epoch": 4.582794629537544,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00034534542916990534,
|
|
"loss": 5.3511,
|
|
"mean_token_accuracy": 0.19251820743083953,
|
|
"num_tokens": 9034355.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.880029344558716,
|
|
"epoch": 4.587767279960219,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00034497437131945837,
|
|
"loss": 5.4038,
|
|
"mean_token_accuracy": 0.19193727672100067,
|
|
"num_tokens": 9043772.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.895597505569458,
|
|
"epoch": 4.592739930382894,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003446031026637277,
|
|
"loss": 5.4144,
|
|
"mean_token_accuracy": 0.19010578393936156,
|
|
"num_tokens": 9053397.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.838545656204223,
|
|
"epoch": 4.597712580805569,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00034423162432119995,
|
|
"loss": 5.3663,
|
|
"mean_token_accuracy": 0.18703157752752303,
|
|
"num_tokens": 9063904.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.850715923309326,
|
|
"epoch": 4.602685231228245,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003438599374109934,
|
|
"loss": 5.3922,
|
|
"mean_token_accuracy": 0.18911081403493882,
|
|
"num_tokens": 9073146.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.740733003616333,
|
|
"epoch": 4.60765788165092,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00034348804305285466,
|
|
"loss": 5.2518,
|
|
"mean_token_accuracy": 0.2128966897726059,
|
|
"num_tokens": 9083617.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.900501298904419,
|
|
"epoch": 4.612630532073595,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003431159423671552,
|
|
"loss": 5.4512,
|
|
"mean_token_accuracy": 0.1853829637169838,
|
|
"num_tokens": 9092639.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.8973517417907715,
|
|
"epoch": 4.61760318249627,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00034274363647488826,
|
|
"loss": 5.5268,
|
|
"mean_token_accuracy": 0.17949637472629548,
|
|
"num_tokens": 9103377.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.842409563064575,
|
|
"epoch": 4.622575832918946,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003423711264976652,
|
|
"loss": 5.3458,
|
|
"mean_token_accuracy": 0.19642200618982314,
|
|
"num_tokens": 9112681.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.871553945541382,
|
|
"epoch": 4.627548483341621,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00034199841355771226,
|
|
"loss": 5.3988,
|
|
"mean_token_accuracy": 0.18963741958141328,
|
|
"num_tokens": 9121079.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.869504594802857,
|
|
"epoch": 4.632521133764296,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00034162549877786685,
|
|
"loss": 5.479,
|
|
"mean_token_accuracy": 0.18844185620546341,
|
|
"num_tokens": 9131121.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.962266349792481,
|
|
"epoch": 4.6374937841869714,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003412523832815748,
|
|
"loss": 5.4932,
|
|
"mean_token_accuracy": 0.18142132014036177,
|
|
"num_tokens": 9140352.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.93990044593811,
|
|
"epoch": 4.642466434609647,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003408790681928865,
|
|
"loss": 5.4943,
|
|
"mean_token_accuracy": 0.1757787987589836,
|
|
"num_tokens": 9150892.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.898201179504395,
|
|
"epoch": 4.647439085032322,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003405055546364535,
|
|
"loss": 5.5297,
|
|
"mean_token_accuracy": 0.18384838551282884,
|
|
"num_tokens": 9160943.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.955027532577515,
|
|
"epoch": 4.652411735454997,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00034013184373752557,
|
|
"loss": 5.5666,
|
|
"mean_token_accuracy": 0.18027430027723312,
|
|
"num_tokens": 9171461.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.87320499420166,
|
|
"epoch": 4.6573843858776725,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003397579366219466,
|
|
"loss": 5.4967,
|
|
"mean_token_accuracy": 0.1866219475865364,
|
|
"num_tokens": 9181991.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.833327341079712,
|
|
"epoch": 4.662357036300348,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003393838344161519,
|
|
"loss": 5.3058,
|
|
"mean_token_accuracy": 0.1965544417500496,
|
|
"num_tokens": 9191715.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.926972913742065,
|
|
"epoch": 4.667329686723024,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00033900953824716443,
|
|
"loss": 5.3797,
|
|
"mean_token_accuracy": 0.1915975719690323,
|
|
"num_tokens": 9201338.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.89835114479065,
|
|
"epoch": 4.672302337145698,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003386350492425913,
|
|
"loss": 5.4976,
|
|
"mean_token_accuracy": 0.18690872937440872,
|
|
"num_tokens": 9210970.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.869890308380127,
|
|
"epoch": 4.677274987568374,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00033826036853062095,
|
|
"loss": 5.4788,
|
|
"mean_token_accuracy": 0.18185838013887407,
|
|
"num_tokens": 9221304.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.915933084487915,
|
|
"epoch": 4.68224763799105,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00033788549724001897,
|
|
"loss": 5.4124,
|
|
"mean_token_accuracy": 0.18624513745307922,
|
|
"num_tokens": 9231386.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.938113212585449,
|
|
"epoch": 4.687220288413725,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00033751043650012534,
|
|
"loss": 5.5121,
|
|
"mean_token_accuracy": 0.1839986339211464,
|
|
"num_tokens": 9240203.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.905422306060791,
|
|
"epoch": 4.6921929388364,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003371351874408506,
|
|
"loss": 5.4524,
|
|
"mean_token_accuracy": 0.18554041236639024,
|
|
"num_tokens": 9249623.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.879531908035278,
|
|
"epoch": 4.697165589259075,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003367597511926728,
|
|
"loss": 5.5314,
|
|
"mean_token_accuracy": 0.1752038151025772,
|
|
"num_tokens": 9259359.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.85360689163208,
|
|
"epoch": 4.702138239681751,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00033638412888663374,
|
|
"loss": 5.3728,
|
|
"mean_token_accuracy": 0.18922638893127441,
|
|
"num_tokens": 9267897.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.835423278808594,
|
|
"epoch": 4.707110890104426,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003360083216543358,
|
|
"loss": 5.339,
|
|
"mean_token_accuracy": 0.19326829612255098,
|
|
"num_tokens": 9277520.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 6.005183744430542,
|
|
"epoch": 4.712083540527101,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003356323306279387,
|
|
"loss": 5.6536,
|
|
"mean_token_accuracy": 0.16877929717302323,
|
|
"num_tokens": 9288157.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.9063770294189455,
|
|
"epoch": 4.717056190949776,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00033525615694015545,
|
|
"loss": 5.3955,
|
|
"mean_token_accuracy": 0.19225145280361175,
|
|
"num_tokens": 9296698.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.941886472702026,
|
|
"epoch": 4.722028841372452,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00033487980172424955,
|
|
"loss": 5.4892,
|
|
"mean_token_accuracy": 0.18401226848363877,
|
|
"num_tokens": 9305880.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.93439679145813,
|
|
"epoch": 4.727001491795127,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00033450326611403136,
|
|
"loss": 5.532,
|
|
"mean_token_accuracy": 0.17904066443443298,
|
|
"num_tokens": 9316123.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.96362042427063,
|
|
"epoch": 4.731974142217802,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00033412655124385494,
|
|
"loss": 5.534,
|
|
"mean_token_accuracy": 0.1806185096502304,
|
|
"num_tokens": 9325914.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.779970693588257,
|
|
"epoch": 4.736946792640477,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003337496582486139,
|
|
"loss": 5.4162,
|
|
"mean_token_accuracy": 0.19264306724071503,
|
|
"num_tokens": 9336330.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.87610011100769,
|
|
"epoch": 4.741919443063153,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00033337258826373896,
|
|
"loss": 5.4912,
|
|
"mean_token_accuracy": 0.17968950420618057,
|
|
"num_tokens": 9345358.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.884526109695434,
|
|
"epoch": 4.746892093485828,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00033299534242519355,
|
|
"loss": 5.3836,
|
|
"mean_token_accuracy": 0.18542483299970627,
|
|
"num_tokens": 9355610.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.945293951034546,
|
|
"epoch": 4.751864743908503,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00033261792186947133,
|
|
"loss": 5.491,
|
|
"mean_token_accuracy": 0.19200346767902374,
|
|
"num_tokens": 9364450.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.894235706329345,
|
|
"epoch": 4.756837394331178,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00033224032773359203,
|
|
"loss": 5.5111,
|
|
"mean_token_accuracy": 0.1806864008307457,
|
|
"num_tokens": 9374426.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.762930917739868,
|
|
"epoch": 4.761810044753854,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00033186256115509845,
|
|
"loss": 5.2688,
|
|
"mean_token_accuracy": 0.20555205643177032,
|
|
"num_tokens": 9384067.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.795357656478882,
|
|
"epoch": 4.766782695176529,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003314846232720528,
|
|
"loss": 5.2233,
|
|
"mean_token_accuracy": 0.20715044289827347,
|
|
"num_tokens": 9394269.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.87306580543518,
|
|
"epoch": 4.771755345599204,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00033110651522303346,
|
|
"loss": 5.3774,
|
|
"mean_token_accuracy": 0.19462908059358597,
|
|
"num_tokens": 9403930.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.875179576873779,
|
|
"epoch": 4.776727996021879,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003307282381471314,
|
|
"loss": 5.4508,
|
|
"mean_token_accuracy": 0.17877860963344575,
|
|
"num_tokens": 9413520.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.850796747207641,
|
|
"epoch": 4.781700646444555,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00033034979318394676,
|
|
"loss": 5.4382,
|
|
"mean_token_accuracy": 0.18995507657527924,
|
|
"num_tokens": 9423945.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.89980001449585,
|
|
"epoch": 4.78667329686723,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00032997118147358554,
|
|
"loss": 5.4838,
|
|
"mean_token_accuracy": 0.19131601601839066,
|
|
"num_tokens": 9434139.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.8833537101745605,
|
|
"epoch": 4.791645947289906,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000329592404156656,
|
|
"loss": 5.4817,
|
|
"mean_token_accuracy": 0.19117371439933778,
|
|
"num_tokens": 9443807.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.946074295043945,
|
|
"epoch": 4.79661859771258,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00032921346237426536,
|
|
"loss": 5.4812,
|
|
"mean_token_accuracy": 0.17604123502969743,
|
|
"num_tokens": 9452608.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.885581970214844,
|
|
"epoch": 4.8015912481352565,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00032883435726801635,
|
|
"loss": 5.5055,
|
|
"mean_token_accuracy": 0.17613787353038787,
|
|
"num_tokens": 9462233.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.918665218353271,
|
|
"epoch": 4.806563898557932,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003284550899800036,
|
|
"loss": 5.4979,
|
|
"mean_token_accuracy": 0.17677292972803116,
|
|
"num_tokens": 9472926.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.92775444984436,
|
|
"epoch": 4.811536548980607,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00032807566165281055,
|
|
"loss": 5.4317,
|
|
"mean_token_accuracy": 0.18829160928726196,
|
|
"num_tokens": 9481711.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.871554803848267,
|
|
"epoch": 4.816509199403282,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003276960734295054,
|
|
"loss": 5.3649,
|
|
"mean_token_accuracy": 0.18814170509576797,
|
|
"num_tokens": 9492655.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.859645175933838,
|
|
"epoch": 4.8214818498259575,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00032731632645363856,
|
|
"loss": 5.3718,
|
|
"mean_token_accuracy": 0.1918995350599289,
|
|
"num_tokens": 9502852.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.785514068603516,
|
|
"epoch": 4.826454500248633,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003269364218692384,
|
|
"loss": 5.3415,
|
|
"mean_token_accuracy": 0.19935033470392227,
|
|
"num_tokens": 9511781.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.836499643325806,
|
|
"epoch": 4.831427150671308,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003265563608208081,
|
|
"loss": 5.4365,
|
|
"mean_token_accuracy": 0.1911339581012726,
|
|
"num_tokens": 9521436.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.887146520614624,
|
|
"epoch": 4.836399801093983,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003261761444533221,
|
|
"loss": 5.3741,
|
|
"mean_token_accuracy": 0.20131263732910157,
|
|
"num_tokens": 9531432.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.891670513153076,
|
|
"epoch": 4.8413724515166585,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003257957739122231,
|
|
"loss": 5.554,
|
|
"mean_token_accuracy": 0.18015375286340712,
|
|
"num_tokens": 9540976.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.881342458724975,
|
|
"epoch": 4.846345101939334,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00032541525034341805,
|
|
"loss": 5.3023,
|
|
"mean_token_accuracy": 0.19716116189956664,
|
|
"num_tokens": 9549566.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.826106357574463,
|
|
"epoch": 4.851317752362009,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003250345748932749,
|
|
"loss": 5.4129,
|
|
"mean_token_accuracy": 0.18715371787548066,
|
|
"num_tokens": 9558937.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.825011253356934,
|
|
"epoch": 4.856290402784684,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00032465374870861913,
|
|
"loss": 5.4083,
|
|
"mean_token_accuracy": 0.19638795256614686,
|
|
"num_tokens": 9568374.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.7620134353637695,
|
|
"epoch": 4.8612630532073595,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00032427277293673053,
|
|
"loss": 5.2897,
|
|
"mean_token_accuracy": 0.19554771333932877,
|
|
"num_tokens": 9577835.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.862675189971924,
|
|
"epoch": 4.866235703630035,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003238916487253393,
|
|
"loss": 5.4624,
|
|
"mean_token_accuracy": 0.18035597652196883,
|
|
"num_tokens": 9586787.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.875672388076782,
|
|
"epoch": 4.87120835405271,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003235103772226229,
|
|
"loss": 5.4879,
|
|
"mean_token_accuracy": 0.18254643380641938,
|
|
"num_tokens": 9597669.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.881231641769409,
|
|
"epoch": 4.876181004475385,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003231289595772026,
|
|
"loss": 5.3667,
|
|
"mean_token_accuracy": 0.19067698568105698,
|
|
"num_tokens": 9607535.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.882389307022095,
|
|
"epoch": 4.8811536548980605,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003227473969381398,
|
|
"loss": 5.4517,
|
|
"mean_token_accuracy": 0.17894863188266755,
|
|
"num_tokens": 9616745.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.839171123504639,
|
|
"epoch": 4.886126305320736,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00032236569045493283,
|
|
"loss": 5.5294,
|
|
"mean_token_accuracy": 0.17884794175624846,
|
|
"num_tokens": 9626445.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.868555974960327,
|
|
"epoch": 4.891098955743411,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00032198384127751344,
|
|
"loss": 5.3536,
|
|
"mean_token_accuracy": 0.1960189387202263,
|
|
"num_tokens": 9635083.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.913266134262085,
|
|
"epoch": 4.896071606166086,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000321601850556243,
|
|
"loss": 5.516,
|
|
"mean_token_accuracy": 0.17870334684848785,
|
|
"num_tokens": 9645410.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.887542009353638,
|
|
"epoch": 4.9010442565887615,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003212197194419095,
|
|
"loss": 5.4373,
|
|
"mean_token_accuracy": 0.17912518233060837,
|
|
"num_tokens": 9654826.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.93075385093689,
|
|
"epoch": 4.906016907011437,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003208374490857238,
|
|
"loss": 5.4796,
|
|
"mean_token_accuracy": 0.17959253787994384,
|
|
"num_tokens": 9664609.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.721231889724732,
|
|
"epoch": 4.910989557434112,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003204550406393164,
|
|
"loss": 5.2646,
|
|
"mean_token_accuracy": 0.20368422120809554,
|
|
"num_tokens": 9672963.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.855158901214599,
|
|
"epoch": 4.915962207856787,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003200724952547335,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.1948773130774498,
|
|
"num_tokens": 9681662.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.82068943977356,
|
|
"epoch": 4.9209348582794625,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003196898140844341,
|
|
"loss": 5.3019,
|
|
"mean_token_accuracy": 0.20382699221372605,
|
|
"num_tokens": 9693204.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.831747770309448,
|
|
"epoch": 4.925907508702139,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00031930699828128614,
|
|
"loss": 5.3688,
|
|
"mean_token_accuracy": 0.18988267332315445,
|
|
"num_tokens": 9702964.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.843282079696655,
|
|
"epoch": 4.930880159124813,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003189240489985633,
|
|
"loss": 5.3996,
|
|
"mean_token_accuracy": 0.20004380941390992,
|
|
"num_tokens": 9712407.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.916817903518677,
|
|
"epoch": 4.935852809547489,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003185409673899412,
|
|
"loss": 5.4647,
|
|
"mean_token_accuracy": 0.18164324015378952,
|
|
"num_tokens": 9722123.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.9033407211303714,
|
|
"epoch": 4.940825459970164,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00031815775460949426,
|
|
"loss": 5.4017,
|
|
"mean_token_accuracy": 0.18917561769485475,
|
|
"num_tokens": 9732641.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.886028385162353,
|
|
"epoch": 4.94579811039284,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003177744118116919,
|
|
"loss": 5.4794,
|
|
"mean_token_accuracy": 0.1812136083841324,
|
|
"num_tokens": 9741498.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.931825971603393,
|
|
"epoch": 4.950770760815515,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003173909401513954,
|
|
"loss": 5.4688,
|
|
"mean_token_accuracy": 0.18740302175283433,
|
|
"num_tokens": 9750811.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.6915112972259525,
|
|
"epoch": 4.95574341123819,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00031700734078385416,
|
|
"loss": 5.3031,
|
|
"mean_token_accuracy": 0.20615119934082032,
|
|
"num_tokens": 9761233.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.837051296234131,
|
|
"epoch": 4.960716061660865,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00031662361486470243,
|
|
"loss": 5.3691,
|
|
"mean_token_accuracy": 0.18879131674766542,
|
|
"num_tokens": 9771258.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.779915142059326,
|
|
"epoch": 4.965688712083541,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003162397635499555,
|
|
"loss": 5.3517,
|
|
"mean_token_accuracy": 0.19663332104682923,
|
|
"num_tokens": 9781501.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.911988067626953,
|
|
"epoch": 4.970661362506216,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00031585578799600653,
|
|
"loss": 5.6475,
|
|
"mean_token_accuracy": 0.1716962844133377,
|
|
"num_tokens": 9792488.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"epoch": 4.970661362506216,
|
|
"eval_entropy": 5.862914783064671,
|
|
"eval_loss": 6.4795002937316895,
|
|
"eval_mean_token_accuracy": 0.14703713767745527,
|
|
"eval_num_tokens": 9792488.0,
|
|
"eval_runtime": 2.5202,
|
|
"eval_samples_per_second": 1374.913,
|
|
"eval_steps_per_second": 172.211,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.90335750579834,
|
|
"epoch": 4.975634012928891,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00031547168935962304,
|
|
"loss": 5.3728,
|
|
"mean_token_accuracy": 0.19073981642723084,
|
|
"num_tokens": 9802711.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.888716077804565,
|
|
"epoch": 4.980606663351566,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003150874687979433,
|
|
"loss": 5.4431,
|
|
"mean_token_accuracy": 0.19160304367542266,
|
|
"num_tokens": 9812668.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.81664628982544,
|
|
"epoch": 4.985579313774242,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00031470312746847284,
|
|
"loss": 5.4171,
|
|
"mean_token_accuracy": 0.19401047229766846,
|
|
"num_tokens": 9822466.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.844345283508301,
|
|
"epoch": 4.990551964196917,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00031431866652908107,
|
|
"loss": 5.4228,
|
|
"mean_token_accuracy": 0.1938529208302498,
|
|
"num_tokens": 9831529.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.868397378921509,
|
|
"epoch": 4.995524614619592,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003139340871379977,
|
|
"loss": 5.4884,
|
|
"mean_token_accuracy": 0.1941350743174553,
|
|
"num_tokens": 9842321.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.923683431413439,
|
|
"epoch": 5.0,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0003135493904538093,
|
|
"loss": 5.4792,
|
|
"mean_token_accuracy": 0.1909417857726415,
|
|
"num_tokens": 9850520.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.866790819168091,
|
|
"epoch": 5.004972650422675,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003131645776354559,
|
|
"loss": 5.0325,
|
|
"mean_token_accuracy": 0.21582279801368714,
|
|
"num_tokens": 9859880.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.847674417495727,
|
|
"epoch": 5.0099453008453505,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003127796498422272,
|
|
"loss": 5.178,
|
|
"mean_token_accuracy": 0.20201209634542466,
|
|
"num_tokens": 9869409.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.84120020866394,
|
|
"epoch": 5.014917951268026,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00031239460823375933,
|
|
"loss": 5.1681,
|
|
"mean_token_accuracy": 0.1999741181731224,
|
|
"num_tokens": 9879558.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.874317407608032,
|
|
"epoch": 5.019890601690701,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00031200945397003157,
|
|
"loss": 5.1258,
|
|
"mean_token_accuracy": 0.2051900953054428,
|
|
"num_tokens": 9890612.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.877995777130127,
|
|
"epoch": 5.024863252113376,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003116241882113623,
|
|
"loss": 5.1229,
|
|
"mean_token_accuracy": 0.20525515973567962,
|
|
"num_tokens": 9900928.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.898334598541259,
|
|
"epoch": 5.0298359025360515,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00031123881211840565,
|
|
"loss": 5.1916,
|
|
"mean_token_accuracy": 0.20045825690031052,
|
|
"num_tokens": 9910627.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.868521595001221,
|
|
"epoch": 5.034808552958727,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003108533268521485,
|
|
"loss": 5.1281,
|
|
"mean_token_accuracy": 0.20166875869035722,
|
|
"num_tokens": 9921250.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.764728927612305,
|
|
"epoch": 5.039781203381402,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003104677335739065,
|
|
"loss": 5.0685,
|
|
"mean_token_accuracy": 0.2199634298682213,
|
|
"num_tokens": 9931213.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.839258623123169,
|
|
"epoch": 5.044753853804077,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00031008203344532067,
|
|
"loss": 5.1409,
|
|
"mean_token_accuracy": 0.20706344544887542,
|
|
"num_tokens": 9941385.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.7947992324829105,
|
|
"epoch": 5.0497265042267525,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000309696227628354,
|
|
"loss": 5.004,
|
|
"mean_token_accuracy": 0.2163021057844162,
|
|
"num_tokens": 9951547.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.896687126159668,
|
|
"epoch": 5.054699154649428,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00030931031728528754,
|
|
"loss": 5.1887,
|
|
"mean_token_accuracy": 0.19568733870983124,
|
|
"num_tokens": 9960855.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.9021240234375,
|
|
"epoch": 5.059671805072103,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003089243035787178,
|
|
"loss": 5.2228,
|
|
"mean_token_accuracy": 0.19905087798833848,
|
|
"num_tokens": 9970116.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.672735500335693,
|
|
"epoch": 5.064644455494779,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00030853818767155225,
|
|
"loss": 4.9463,
|
|
"mean_token_accuracy": 0.22875631600618362,
|
|
"num_tokens": 9980488.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.830287599563599,
|
|
"epoch": 5.069617105917454,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003081519707270065,
|
|
"loss": 5.2142,
|
|
"mean_token_accuracy": 0.2004164218902588,
|
|
"num_tokens": 9990677.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.673852157592774,
|
|
"epoch": 5.07458975634013,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00030776565390860017,
|
|
"loss": 4.9056,
|
|
"mean_token_accuracy": 0.22738662958145142,
|
|
"num_tokens": 10000218.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.818862533569336,
|
|
"epoch": 5.079562406762805,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003073792383801543,
|
|
"loss": 5.1112,
|
|
"mean_token_accuracy": 0.20804362297058104,
|
|
"num_tokens": 10008720.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.812814092636108,
|
|
"epoch": 5.08453505718548,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00030699272530578697,
|
|
"loss": 5.1703,
|
|
"mean_token_accuracy": 0.21158573031425476,
|
|
"num_tokens": 10018648.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.796617650985718,
|
|
"epoch": 5.089507707608155,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00030660611584991013,
|
|
"loss": 5.0911,
|
|
"mean_token_accuracy": 0.21609750092029573,
|
|
"num_tokens": 10028639.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.8395185470581055,
|
|
"epoch": 5.094480358030831,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00030621941117722615,
|
|
"loss": 5.1345,
|
|
"mean_token_accuracy": 0.20189028084278107,
|
|
"num_tokens": 10038136.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.752219533920288,
|
|
"epoch": 5.099453008453506,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003058326124527243,
|
|
"loss": 5.1161,
|
|
"mean_token_accuracy": 0.21008213311433793,
|
|
"num_tokens": 10048503.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.782375526428223,
|
|
"epoch": 5.104425658876181,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003054457208416771,
|
|
"loss": 5.079,
|
|
"mean_token_accuracy": 0.21362434178590775,
|
|
"num_tokens": 10059088.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.804659223556518,
|
|
"epoch": 5.109398309298856,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00030505873750963705,
|
|
"loss": 5.0991,
|
|
"mean_token_accuracy": 0.21074110567569732,
|
|
"num_tokens": 10069655.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.855256795883179,
|
|
"epoch": 5.114370959721532,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003046716636224327,
|
|
"loss": 5.0941,
|
|
"mean_token_accuracy": 0.20548264682292938,
|
|
"num_tokens": 10079748.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.814743709564209,
|
|
"epoch": 5.119343610144207,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003042845003461657,
|
|
"loss": 5.0884,
|
|
"mean_token_accuracy": 0.20611886978149413,
|
|
"num_tokens": 10088877.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.851698207855224,
|
|
"epoch": 5.124316260566882,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00030389724884720664,
|
|
"loss": 5.167,
|
|
"mean_token_accuracy": 0.20678431987762452,
|
|
"num_tokens": 10098699.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.554758787155151,
|
|
"epoch": 5.129288910989557,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00030350991029219236,
|
|
"loss": 4.8102,
|
|
"mean_token_accuracy": 0.24814414083957673,
|
|
"num_tokens": 10110084.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.784569358825683,
|
|
"epoch": 5.134261561412233,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00030312248584802166,
|
|
"loss": 5.1656,
|
|
"mean_token_accuracy": 0.20212665796279908,
|
|
"num_tokens": 10119553.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.846065378189087,
|
|
"epoch": 5.139234211834908,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003027349766818521,
|
|
"loss": 5.1001,
|
|
"mean_token_accuracy": 0.20986706167459487,
|
|
"num_tokens": 10128332.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.8525307178497314,
|
|
"epoch": 5.144206862257583,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003023473839610965,
|
|
"loss": 5.1762,
|
|
"mean_token_accuracy": 0.2019294172525406,
|
|
"num_tokens": 10138109.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.8858836650848385,
|
|
"epoch": 5.149179512680258,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003019597088534195,
|
|
"loss": 5.259,
|
|
"mean_token_accuracy": 0.1993210047483444,
|
|
"num_tokens": 10148103.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.927030181884765,
|
|
"epoch": 5.154152163102934,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003015719525267338,
|
|
"loss": 5.2818,
|
|
"mean_token_accuracy": 0.1950878992676735,
|
|
"num_tokens": 10158189.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.856090831756592,
|
|
"epoch": 5.159124813525609,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003011841161491969,
|
|
"loss": 5.2011,
|
|
"mean_token_accuracy": 0.20232284665107728,
|
|
"num_tokens": 10169048.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.776122617721557,
|
|
"epoch": 5.164097463948284,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00030079620088920727,
|
|
"loss": 5.1467,
|
|
"mean_token_accuracy": 0.20870514065027237,
|
|
"num_tokens": 10178067.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.84952940940857,
|
|
"epoch": 5.169070114370959,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003004082079154013,
|
|
"loss": 5.2425,
|
|
"mean_token_accuracy": 0.20080292373895645,
|
|
"num_tokens": 10186952.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.885237407684326,
|
|
"epoch": 5.174042764793635,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00030002013839664925,
|
|
"loss": 5.2397,
|
|
"mean_token_accuracy": 0.19706978350877763,
|
|
"num_tokens": 10196699.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.816967535018921,
|
|
"epoch": 5.17901541521631,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002996319935020522,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.20547159463167192,
|
|
"num_tokens": 10206198.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.812828779220581,
|
|
"epoch": 5.183988065638985,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002992437744009381,
|
|
"loss": 5.1619,
|
|
"mean_token_accuracy": 0.20052988082170486,
|
|
"num_tokens": 10215698.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.8976668357849125,
|
|
"epoch": 5.188960716061661,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00029885548226285855,
|
|
"loss": 5.269,
|
|
"mean_token_accuracy": 0.19984466433525086,
|
|
"num_tokens": 10225732.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.83613953590393,
|
|
"epoch": 5.193933366484337,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002984671182575851,
|
|
"loss": 5.1497,
|
|
"mean_token_accuracy": 0.21297089755535126,
|
|
"num_tokens": 10235691.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.770741033554077,
|
|
"epoch": 5.198906016907012,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002980786835551061,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.21194411367177962,
|
|
"num_tokens": 10246066.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.870838165283203,
|
|
"epoch": 5.203878667329687,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002976901793256225,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.2161896750330925,
|
|
"num_tokens": 10254968.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.819249439239502,
|
|
"epoch": 5.208851317752362,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000297301606739545,
|
|
"loss": 5.1654,
|
|
"mean_token_accuracy": 0.19957413673400878,
|
|
"num_tokens": 10263800.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.7848070621490475,
|
|
"epoch": 5.213823968175038,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00029691296696748994,
|
|
"loss": 5.2192,
|
|
"mean_token_accuracy": 0.19962984025478364,
|
|
"num_tokens": 10274044.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.864133977890015,
|
|
"epoch": 5.218796618597713,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00029652426118027635,
|
|
"loss": 5.2381,
|
|
"mean_token_accuracy": 0.19754933714866638,
|
|
"num_tokens": 10284429.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.842308139801025,
|
|
"epoch": 5.223769269020388,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00029613549054892206,
|
|
"loss": 5.2139,
|
|
"mean_token_accuracy": 0.197903111577034,
|
|
"num_tokens": 10293968.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.651908612251281,
|
|
"epoch": 5.228741919443063,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0002957466562446401,
|
|
"loss": 4.9848,
|
|
"mean_token_accuracy": 0.22819563895463943,
|
|
"num_tokens": 10303497.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.82825198173523,
|
|
"epoch": 5.233714569865739,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002953577594388355,
|
|
"loss": 5.2506,
|
|
"mean_token_accuracy": 0.19393800050020218,
|
|
"num_tokens": 10312766.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.778246068954468,
|
|
"epoch": 5.238687220288414,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00029496880130310145,
|
|
"loss": 5.0886,
|
|
"mean_token_accuracy": 0.20355061888694764,
|
|
"num_tokens": 10323604.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.856961965560913,
|
|
"epoch": 5.243659870711089,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002945797830092161,
|
|
"loss": 5.1673,
|
|
"mean_token_accuracy": 0.20535585433244705,
|
|
"num_tokens": 10333620.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.801625061035156,
|
|
"epoch": 5.248632521133764,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002941907057291386,
|
|
"loss": 5.1702,
|
|
"mean_token_accuracy": 0.20043203681707383,
|
|
"num_tokens": 10344078.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.827210426330566,
|
|
"epoch": 5.25360517155644,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00029380157063500594,
|
|
"loss": 5.1302,
|
|
"mean_token_accuracy": 0.20770183354616165,
|
|
"num_tokens": 10353254.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.782610511779785,
|
|
"epoch": 5.258577821979115,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002934123788991291,
|
|
"loss": 5.1619,
|
|
"mean_token_accuracy": 0.20738246738910676,
|
|
"num_tokens": 10362310.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.904792308807373,
|
|
"epoch": 5.26355047240179,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00029302313169399,
|
|
"loss": 5.3531,
|
|
"mean_token_accuracy": 0.19059746861457824,
|
|
"num_tokens": 10373252.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.878888463973999,
|
|
"epoch": 5.268523122824465,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0002926338301922376,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.2044663742184639,
|
|
"num_tokens": 10381682.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.891276550292969,
|
|
"epoch": 5.273495773247141,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00029224447556668417,
|
|
"loss": 5.3103,
|
|
"mean_token_accuracy": 0.18660085648298264,
|
|
"num_tokens": 10391567.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.8774964809417725,
|
|
"epoch": 5.278468423669816,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0002918550689903022,
|
|
"loss": 5.2569,
|
|
"mean_token_accuracy": 0.19933062195777893,
|
|
"num_tokens": 10401820.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.839586400985718,
|
|
"epoch": 5.283441074092491,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00029146561163622076,
|
|
"loss": 5.1753,
|
|
"mean_token_accuracy": 0.21006162464618683,
|
|
"num_tokens": 10413378.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.807059049606323,
|
|
"epoch": 5.288413724515166,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002910761046777218,
|
|
"loss": 5.132,
|
|
"mean_token_accuracy": 0.212266406416893,
|
|
"num_tokens": 10423447.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.752364015579223,
|
|
"epoch": 5.293386374937842,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00029068654928823666,
|
|
"loss": 5.0825,
|
|
"mean_token_accuracy": 0.2092158928513527,
|
|
"num_tokens": 10433785.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.746443462371826,
|
|
"epoch": 5.298359025360517,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00029029694664134284,
|
|
"loss": 5.1875,
|
|
"mean_token_accuracy": 0.19743933975696565,
|
|
"num_tokens": 10444748.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.897410583496094,
|
|
"epoch": 5.303331675783192,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002899072979107597,
|
|
"loss": 5.2716,
|
|
"mean_token_accuracy": 0.19101898074150087,
|
|
"num_tokens": 10455778.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.833417558670044,
|
|
"epoch": 5.308304326205867,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002895176042703461,
|
|
"loss": 5.2479,
|
|
"mean_token_accuracy": 0.2028838574886322,
|
|
"num_tokens": 10465915.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.718726444244385,
|
|
"epoch": 5.3132769766285435,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00028912786689409554,
|
|
"loss": 5.0428,
|
|
"mean_token_accuracy": 0.22175320237874985,
|
|
"num_tokens": 10475838.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.571369600296021,
|
|
"epoch": 5.318249627051218,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002887380869561338,
|
|
"loss": 4.9314,
|
|
"mean_token_accuracy": 0.22238486558198928,
|
|
"num_tokens": 10485719.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.827309846878052,
|
|
"epoch": 5.323222277473894,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002883482656307145,
|
|
"loss": 5.1176,
|
|
"mean_token_accuracy": 0.21037093549966812,
|
|
"num_tokens": 10494695.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.862833690643311,
|
|
"epoch": 5.328194927896569,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002879584040922162,
|
|
"loss": 5.2619,
|
|
"mean_token_accuracy": 0.19844678789377213,
|
|
"num_tokens": 10505356.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.763680648803711,
|
|
"epoch": 5.3331675783192445,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002875685035151386,
|
|
"loss": 5.0272,
|
|
"mean_token_accuracy": 0.2136157363653183,
|
|
"num_tokens": 10515118.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.786312389373779,
|
|
"epoch": 5.33814022874192,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00028717856507409886,
|
|
"loss": 5.1638,
|
|
"mean_token_accuracy": 0.207216876745224,
|
|
"num_tokens": 10525713.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.806897449493408,
|
|
"epoch": 5.343112879164595,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002867885899438281,
|
|
"loss": 5.0936,
|
|
"mean_token_accuracy": 0.2107505679130554,
|
|
"num_tokens": 10534363.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.6719193935394285,
|
|
"epoch": 5.34808552958727,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002863985792991683,
|
|
"loss": 5.0069,
|
|
"mean_token_accuracy": 0.21127400696277618,
|
|
"num_tokens": 10544302.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.797803497314453,
|
|
"epoch": 5.3530581800099455,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002860085343150683,
|
|
"loss": 5.159,
|
|
"mean_token_accuracy": 0.20736413449048996,
|
|
"num_tokens": 10553742.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.878936004638672,
|
|
"epoch": 5.358030830432621,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00028561845616658033,
|
|
"loss": 5.2753,
|
|
"mean_token_accuracy": 0.19682454615831374,
|
|
"num_tokens": 10564061.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.8236597061157225,
|
|
"epoch": 5.363003480855296,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00028522834602885656,
|
|
"loss": 5.2327,
|
|
"mean_token_accuracy": 0.20059376657009126,
|
|
"num_tokens": 10573439.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.833716583251953,
|
|
"epoch": 5.367976131277971,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002848382050771455,
|
|
"loss": 5.1925,
|
|
"mean_token_accuracy": 0.20389105528593063,
|
|
"num_tokens": 10583694.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.880038118362426,
|
|
"epoch": 5.3729487817006465,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002844480344867886,
|
|
"loss": 5.2779,
|
|
"mean_token_accuracy": 0.20232824832201005,
|
|
"num_tokens": 10593432.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.542480897903443,
|
|
"epoch": 5.377921432123322,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002840578354332165,
|
|
"loss": 4.9243,
|
|
"mean_token_accuracy": 0.23442455381155014,
|
|
"num_tokens": 10603050.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.738883972167969,
|
|
"epoch": 5.382894082545997,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002836676090919456,
|
|
"loss": 5.1683,
|
|
"mean_token_accuracy": 0.20876742899417877,
|
|
"num_tokens": 10613842.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.841043329238891,
|
|
"epoch": 5.387866732968672,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002832773566385746,
|
|
"loss": 5.155,
|
|
"mean_token_accuracy": 0.2053508698940277,
|
|
"num_tokens": 10624220.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.714201736450195,
|
|
"epoch": 5.3928393833913475,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00028288707924878056,
|
|
"loss": 4.9923,
|
|
"mean_token_accuracy": 0.2240742638707161,
|
|
"num_tokens": 10633797.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.720912027359009,
|
|
"epoch": 5.397812033814023,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002824967780983162,
|
|
"loss": 5.0961,
|
|
"mean_token_accuracy": 0.21383296698331833,
|
|
"num_tokens": 10642718.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.84358696937561,
|
|
"epoch": 5.402784684236698,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00028210645436300524,
|
|
"loss": 5.2476,
|
|
"mean_token_accuracy": 0.1947984963655472,
|
|
"num_tokens": 10653733.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.819284963607788,
|
|
"epoch": 5.407757334659373,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00028171610921873995,
|
|
"loss": 5.1858,
|
|
"mean_token_accuracy": 0.19785005152225493,
|
|
"num_tokens": 10663238.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.855039167404175,
|
|
"epoch": 5.4127299850820485,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002813257438414766,
|
|
"loss": 5.2359,
|
|
"mean_token_accuracy": 0.19450863152742387,
|
|
"num_tokens": 10674037.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.845829439163208,
|
|
"epoch": 5.417702635504724,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000280935359407233,
|
|
"loss": 5.2341,
|
|
"mean_token_accuracy": 0.19420353025197984,
|
|
"num_tokens": 10684394.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.811713981628418,
|
|
"epoch": 5.422675285927399,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0002805449570920838,
|
|
"loss": 5.2316,
|
|
"mean_token_accuracy": 0.19578944593667985,
|
|
"num_tokens": 10693396.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.780010318756103,
|
|
"epoch": 5.427647936350074,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00028015453807215786,
|
|
"loss": 5.1811,
|
|
"mean_token_accuracy": 0.20606605112552642,
|
|
"num_tokens": 10703643.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.815720653533935,
|
|
"epoch": 5.4326205867727495,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00027976410352363416,
|
|
"loss": 5.121,
|
|
"mean_token_accuracy": 0.20814442932605742,
|
|
"num_tokens": 10712883.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.763059663772583,
|
|
"epoch": 5.437593237195425,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00027937365462273864,
|
|
"loss": 5.0873,
|
|
"mean_token_accuracy": 0.20349799692630768,
|
|
"num_tokens": 10721926.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.753995704650879,
|
|
"epoch": 5.4425658876181,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00027898319254574043,
|
|
"loss": 5.1408,
|
|
"mean_token_accuracy": 0.208660788834095,
|
|
"num_tokens": 10731772.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.884405136108398,
|
|
"epoch": 5.447538538040776,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002785927184689483,
|
|
"loss": 5.3018,
|
|
"mean_token_accuracy": 0.1970638081431389,
|
|
"num_tokens": 10742815.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.7974348068237305,
|
|
"epoch": 5.452511188463451,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0002782022335687073,
|
|
"loss": 5.1477,
|
|
"mean_token_accuracy": 0.21347075700759888,
|
|
"num_tokens": 10753958.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.871429872512818,
|
|
"epoch": 5.457483838886127,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00027781173902139485,
|
|
"loss": 5.2506,
|
|
"mean_token_accuracy": 0.19803023785352708,
|
|
"num_tokens": 10763808.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.796165847778321,
|
|
"epoch": 5.462456489308802,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002774212360034176,
|
|
"loss": 5.225,
|
|
"mean_token_accuracy": 0.20104679465293884,
|
|
"num_tokens": 10773688.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.800871515274048,
|
|
"epoch": 5.467429139731477,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002770307256912078,
|
|
"loss": 5.2087,
|
|
"mean_token_accuracy": 0.20078072398900987,
|
|
"num_tokens": 10783902.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.64855318069458,
|
|
"epoch": 5.472401790154152,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00027664020926121944,
|
|
"loss": 4.9266,
|
|
"mean_token_accuracy": 0.23253031075000763,
|
|
"num_tokens": 10794138.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.7639227390289305,
|
|
"epoch": 5.477374440576828,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002762496878899251,
|
|
"loss": 5.2,
|
|
"mean_token_accuracy": 0.2054206296801567,
|
|
"num_tokens": 10804599.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.844069862365723,
|
|
"epoch": 5.482347090999503,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00027585916275381226,
|
|
"loss": 5.1404,
|
|
"mean_token_accuracy": 0.21245988011360167,
|
|
"num_tokens": 10813632.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.781446886062622,
|
|
"epoch": 5.487319741422178,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002754686350293797,
|
|
"loss": 5.2585,
|
|
"mean_token_accuracy": 0.19756506383419037,
|
|
"num_tokens": 10824287.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.805607557296753,
|
|
"epoch": 5.492292391844853,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002750781058931339,
|
|
"loss": 5.2893,
|
|
"mean_token_accuracy": 0.1971137285232544,
|
|
"num_tokens": 10834079.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.867652177810669,
|
|
"epoch": 5.497265042267529,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002746875765215857,
|
|
"loss": 5.2558,
|
|
"mean_token_accuracy": 0.198168283700943,
|
|
"num_tokens": 10843029.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.833099603652954,
|
|
"epoch": 5.502237692690204,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00027429704809124665,
|
|
"loss": 5.18,
|
|
"mean_token_accuracy": 0.20636758655309678,
|
|
"num_tokens": 10852749.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.685366916656494,
|
|
"epoch": 5.507210343112879,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002739065217786255,
|
|
"loss": 5.082,
|
|
"mean_token_accuracy": 0.21097600013017653,
|
|
"num_tokens": 10862911.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.807827091217041,
|
|
"epoch": 5.512182993535554,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002735159987602246,
|
|
"loss": 5.131,
|
|
"mean_token_accuracy": 0.20998883694410325,
|
|
"num_tokens": 10872389.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.766295719146728,
|
|
"epoch": 5.51715564395823,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002731254802125362,
|
|
"loss": 5.112,
|
|
"mean_token_accuracy": 0.21131891906261444,
|
|
"num_tokens": 10881280.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.7538489818573,
|
|
"epoch": 5.522128294380905,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00027273496731203945,
|
|
"loss": 5.2106,
|
|
"mean_token_accuracy": 0.211619234085083,
|
|
"num_tokens": 10891154.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.812362241744995,
|
|
"epoch": 5.52710094480358,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000272344461235196,
|
|
"loss": 5.1164,
|
|
"mean_token_accuracy": 0.21190424263477325,
|
|
"num_tokens": 10900029.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.596913290023804,
|
|
"epoch": 5.532073595226255,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00027195396315844733,
|
|
"loss": 4.963,
|
|
"mean_token_accuracy": 0.23529947251081468,
|
|
"num_tokens": 10909616.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.657571840286255,
|
|
"epoch": 5.537046245648931,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0002715634742582107,
|
|
"loss": 4.9376,
|
|
"mean_token_accuracy": 0.23488021194934844,
|
|
"num_tokens": 10920754.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.812657642364502,
|
|
"epoch": 5.542018896071606,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00027117299571087576,
|
|
"loss": 5.1358,
|
|
"mean_token_accuracy": 0.20197756886482238,
|
|
"num_tokens": 10929918.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.824498891830444,
|
|
"epoch": 5.546991546494281,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002707825286928008,
|
|
"loss": 5.1779,
|
|
"mean_token_accuracy": 0.2056986317038536,
|
|
"num_tokens": 10938932.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.723819208145142,
|
|
"epoch": 5.551964196916956,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002703920743803097,
|
|
"loss": 5.0909,
|
|
"mean_token_accuracy": 0.20400631427764893,
|
|
"num_tokens": 10948896.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.8341131687164305,
|
|
"epoch": 5.556936847339632,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00027000163394968763,
|
|
"loss": 5.247,
|
|
"mean_token_accuracy": 0.20106089860200882,
|
|
"num_tokens": 10958245.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.8438796043396,
|
|
"epoch": 5.561909497762308,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00026961120857717843,
|
|
"loss": 5.1687,
|
|
"mean_token_accuracy": 0.21319232434034346,
|
|
"num_tokens": 10967917.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.772462511062622,
|
|
"epoch": 5.566882148184982,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00026922079943898016,
|
|
"loss": 5.1621,
|
|
"mean_token_accuracy": 0.2072613477706909,
|
|
"num_tokens": 10977062.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.800261163711548,
|
|
"epoch": 5.571854798607658,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002688304077112421,
|
|
"loss": 5.2695,
|
|
"mean_token_accuracy": 0.2001063957810402,
|
|
"num_tokens": 10987009.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.755256652832031,
|
|
"epoch": 5.576827449030333,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0002684400345700613,
|
|
"loss": 5.0302,
|
|
"mean_token_accuracy": 0.21703779846429824,
|
|
"num_tokens": 10996077.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.794111633300782,
|
|
"epoch": 5.581800099453009,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002680496811914786,
|
|
"loss": 5.1401,
|
|
"mean_token_accuracy": 0.2054967999458313,
|
|
"num_tokens": 11005240.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.772623538970947,
|
|
"epoch": 5.586772749875684,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00026765934875147513,
|
|
"loss": 5.2571,
|
|
"mean_token_accuracy": 0.19418160021305084,
|
|
"num_tokens": 11014373.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.59212441444397,
|
|
"epoch": 5.591745400298359,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002672690384259693,
|
|
"loss": 4.952,
|
|
"mean_token_accuracy": 0.2377627283334732,
|
|
"num_tokens": 11024676.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.756594562530518,
|
|
"epoch": 5.596718050721035,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00026687875139081287,
|
|
"loss": 5.1373,
|
|
"mean_token_accuracy": 0.21161254197359086,
|
|
"num_tokens": 11033722.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.754390621185303,
|
|
"epoch": 5.60169070114371,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00026648848882178703,
|
|
"loss": 5.1731,
|
|
"mean_token_accuracy": 0.20825813561677933,
|
|
"num_tokens": 11043405.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.763212251663208,
|
|
"epoch": 5.606663351566385,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0002660982518945998,
|
|
"loss": 5.1663,
|
|
"mean_token_accuracy": 0.2054306834936142,
|
|
"num_tokens": 11053577.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.740426731109619,
|
|
"epoch": 5.61163600198906,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00026570804178488146,
|
|
"loss": 5.1383,
|
|
"mean_token_accuracy": 0.20873744189739227,
|
|
"num_tokens": 11062890.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.637407922744751,
|
|
"epoch": 5.616608652411736,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002653178596681819,
|
|
"loss": 5.0282,
|
|
"mean_token_accuracy": 0.22634379863739013,
|
|
"num_tokens": 11073445.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.761264038085938,
|
|
"epoch": 5.621581302834411,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002649277067199665,
|
|
"loss": 5.1899,
|
|
"mean_token_accuracy": 0.1986963853240013,
|
|
"num_tokens": 11083159.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.812113809585571,
|
|
"epoch": 5.626553953257086,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002645375841156127,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.19776999801397324,
|
|
"num_tokens": 11093417.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.825606107711792,
|
|
"epoch": 5.631526603679761,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002641474930304067,
|
|
"loss": 5.1892,
|
|
"mean_token_accuracy": 0.20738001465797423,
|
|
"num_tokens": 11102775.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.833545255661011,
|
|
"epoch": 5.636499254102437,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0002637574346395396,
|
|
"loss": 5.2315,
|
|
"mean_token_accuracy": 0.1961537167429924,
|
|
"num_tokens": 11111952.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.73120150566101,
|
|
"epoch": 5.641471904525112,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000263367410118104,
|
|
"loss": 5.0271,
|
|
"mean_token_accuracy": 0.21554083824157716,
|
|
"num_tokens": 11120391.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.856266927719116,
|
|
"epoch": 5.646444554947787,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002629774206410906,
|
|
"loss": 5.21,
|
|
"mean_token_accuracy": 0.20242860168218613,
|
|
"num_tokens": 11129905.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.787564468383789,
|
|
"epoch": 5.651417205370462,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002625874673833844,
|
|
"loss": 5.2029,
|
|
"mean_token_accuracy": 0.2062305435538292,
|
|
"num_tokens": 11139068.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.733178329467774,
|
|
"epoch": 5.656389855793138,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002621975515197613,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.21682682633399963,
|
|
"num_tokens": 11147718.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.863492155075074,
|
|
"epoch": 5.661362506215813,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00026180767422488466,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.1959388703107834,
|
|
"num_tokens": 11157621.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.84276328086853,
|
|
"epoch": 5.666335156638488,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00026141783667330156,
|
|
"loss": 5.1798,
|
|
"mean_token_accuracy": 0.20235221534967424,
|
|
"num_tokens": 11168061.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.84671835899353,
|
|
"epoch": 5.671307807061163,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0002610280400394393,
|
|
"loss": 5.2682,
|
|
"mean_token_accuracy": 0.19645842611789704,
|
|
"num_tokens": 11177240.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.814459896087646,
|
|
"epoch": 5.676280457483839,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00026063828549760195,
|
|
"loss": 5.2939,
|
|
"mean_token_accuracy": 0.19714879393577575,
|
|
"num_tokens": 11187280.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.732856893539429,
|
|
"epoch": 5.681253107906514,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002602485742219667,
|
|
"loss": 5.1296,
|
|
"mean_token_accuracy": 0.20931842625141145,
|
|
"num_tokens": 11197207.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.82003436088562,
|
|
"epoch": 5.686225758329189,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00025985890738658077,
|
|
"loss": 5.2338,
|
|
"mean_token_accuracy": 0.19720476865768433,
|
|
"num_tokens": 11206373.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.819964838027954,
|
|
"epoch": 5.691198408751864,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000259469286165357,
|
|
"loss": 5.1949,
|
|
"mean_token_accuracy": 0.19844458848237992,
|
|
"num_tokens": 11216799.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.84061861038208,
|
|
"epoch": 5.6961710591745405,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00025907971173207107,
|
|
"loss": 5.2288,
|
|
"mean_token_accuracy": 0.1930568739771843,
|
|
"num_tokens": 11226968.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.80801362991333,
|
|
"epoch": 5.701143709597215,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002586901852603576,
|
|
"loss": 5.2458,
|
|
"mean_token_accuracy": 0.20063577890396117,
|
|
"num_tokens": 11235741.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.820827007293701,
|
|
"epoch": 5.706116360019891,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002583007079237069,
|
|
"loss": 5.2109,
|
|
"mean_token_accuracy": 0.2058287665247917,
|
|
"num_tokens": 11245804.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.783116149902344,
|
|
"epoch": 5.711089010442566,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00025791128089546107,
|
|
"loss": 5.2418,
|
|
"mean_token_accuracy": 0.20162438601255417,
|
|
"num_tokens": 11256304.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.836018323898315,
|
|
"epoch": 5.7160616608652415,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00025752190534881065,
|
|
"loss": 5.2504,
|
|
"mean_token_accuracy": 0.19357924908399582,
|
|
"num_tokens": 11265800.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.887954187393189,
|
|
"epoch": 5.721034311287917,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00025713258245679127,
|
|
"loss": 5.2398,
|
|
"mean_token_accuracy": 0.20000062584877015,
|
|
"num_tokens": 11275983.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.850507497787476,
|
|
"epoch": 5.726006961710592,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00025674331339227966,
|
|
"loss": 5.1397,
|
|
"mean_token_accuracy": 0.21778065115213394,
|
|
"num_tokens": 11286375.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.846100282669068,
|
|
"epoch": 5.730979612133267,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00025635409932799074,
|
|
"loss": 5.2489,
|
|
"mean_token_accuracy": 0.19928124248981477,
|
|
"num_tokens": 11297359.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.8332275390625,
|
|
"epoch": 5.7359522625559425,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0002559649414364735,
|
|
"loss": 5.298,
|
|
"mean_token_accuracy": 0.19506183117628098,
|
|
"num_tokens": 11307235.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.890503692626953,
|
|
"epoch": 5.740924912978618,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0002555758408901076,
|
|
"loss": 5.2245,
|
|
"mean_token_accuracy": 0.19191835522651673,
|
|
"num_tokens": 11316618.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.91607518196106,
|
|
"epoch": 5.745897563401293,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00025518679886110023,
|
|
"loss": 5.3125,
|
|
"mean_token_accuracy": 0.19089377373456956,
|
|
"num_tokens": 11327178.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.60752272605896,
|
|
"epoch": 5.750870213823968,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002547978165214822,
|
|
"loss": 4.9921,
|
|
"mean_token_accuracy": 0.22764871269464493,
|
|
"num_tokens": 11337788.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.780555629730225,
|
|
"epoch": 5.7558428642466435,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00025440889504310416,
|
|
"loss": 5.1243,
|
|
"mean_token_accuracy": 0.21347679644823075,
|
|
"num_tokens": 11346958.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.82982325553894,
|
|
"epoch": 5.760815514669319,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00025402003559763393,
|
|
"loss": 5.1922,
|
|
"mean_token_accuracy": 0.2046399936079979,
|
|
"num_tokens": 11355817.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.8392956256866455,
|
|
"epoch": 5.765788165091994,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00025363123935655214,
|
|
"loss": 5.2542,
|
|
"mean_token_accuracy": 0.1999742269515991,
|
|
"num_tokens": 11366557.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.773776006698609,
|
|
"epoch": 5.770760815514669,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002532425074911491,
|
|
"loss": 5.2552,
|
|
"mean_token_accuracy": 0.1934459239244461,
|
|
"num_tokens": 11376931.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.815201759338379,
|
|
"epoch": 5.7757334659373445,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002528538411725212,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.1923217460513115,
|
|
"num_tokens": 11387430.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.824406147003174,
|
|
"epoch": 5.78070611636002,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0002524652415715672,
|
|
"loss": 5.1168,
|
|
"mean_token_accuracy": 0.21086911857128143,
|
|
"num_tokens": 11396957.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.8451169490814205,
|
|
"epoch": 5.785678766782695,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002520767098589852,
|
|
"loss": 5.1236,
|
|
"mean_token_accuracy": 0.2057564526796341,
|
|
"num_tokens": 11405313.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.837593698501587,
|
|
"epoch": 5.79065141720537,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002516882472052683,
|
|
"loss": 5.2632,
|
|
"mean_token_accuracy": 0.19831399619579315,
|
|
"num_tokens": 11414437.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.877068042755127,
|
|
"epoch": 5.7956240676280455,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002512998547807022,
|
|
"loss": 5.3449,
|
|
"mean_token_accuracy": 0.1958352655172348,
|
|
"num_tokens": 11425498.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.926218032836914,
|
|
"epoch": 5.800596718050721,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00025091153375536026,
|
|
"loss": 5.2813,
|
|
"mean_token_accuracy": 0.19600177109241484,
|
|
"num_tokens": 11435333.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.625732517242431,
|
|
"epoch": 5.805569368473396,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00025052328529910135,
|
|
"loss": 4.994,
|
|
"mean_token_accuracy": 0.22631680816411973,
|
|
"num_tokens": 11445366.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.736702728271484,
|
|
"epoch": 5.810542018896071,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002501351105815655,
|
|
"loss": 5.1034,
|
|
"mean_token_accuracy": 0.21663547605276107,
|
|
"num_tokens": 11455229.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.811320066452026,
|
|
"epoch": 5.8155146693187465,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00024974701077217057,
|
|
"loss": 5.2021,
|
|
"mean_token_accuracy": 0.19964847564697266,
|
|
"num_tokens": 11464789.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.804903745651245,
|
|
"epoch": 5.820487319741423,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00024935898704010875,
|
|
"loss": 5.1711,
|
|
"mean_token_accuracy": 0.2063405379652977,
|
|
"num_tokens": 11473694.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.840327024459839,
|
|
"epoch": 5.825459970164097,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00024897104055434304,
|
|
"loss": 5.2254,
|
|
"mean_token_accuracy": 0.20190955251455306,
|
|
"num_tokens": 11482701.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.842611598968506,
|
|
"epoch": 5.830432620586773,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00024858317248360387,
|
|
"loss": 5.3088,
|
|
"mean_token_accuracy": 0.19049390703439711,
|
|
"num_tokens": 11493917.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.7712431907653805,
|
|
"epoch": 5.835405271009448,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002481953839963851,
|
|
"loss": 5.0779,
|
|
"mean_token_accuracy": 0.21529926657676696,
|
|
"num_tokens": 11504001.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.844436931610107,
|
|
"epoch": 5.840377921432124,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002478076762609413,
|
|
"loss": 5.2614,
|
|
"mean_token_accuracy": 0.1986458495259285,
|
|
"num_tokens": 11513010.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.8052370071411135,
|
|
"epoch": 5.845350571854799,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002474200504452834,
|
|
"loss": 5.1777,
|
|
"mean_token_accuracy": 0.21024476289749144,
|
|
"num_tokens": 11522190.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.836629629135132,
|
|
"epoch": 5.850323222277474,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00024703250771717576,
|
|
"loss": 5.2283,
|
|
"mean_token_accuracy": 0.2063994824886322,
|
|
"num_tokens": 11531180.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.853888463973999,
|
|
"epoch": 5.855295872700149,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00024664504924413224,
|
|
"loss": 5.2265,
|
|
"mean_token_accuracy": 0.19980136901140214,
|
|
"num_tokens": 11540829.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.863179731369018,
|
|
"epoch": 5.860268523122825,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002462576761934129,
|
|
"loss": 5.1981,
|
|
"mean_token_accuracy": 0.1941586419939995,
|
|
"num_tokens": 11549118.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.747703504562378,
|
|
"epoch": 5.8652411735455,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002458703897320208,
|
|
"loss": 5.1589,
|
|
"mean_token_accuracy": 0.2122413694858551,
|
|
"num_tokens": 11557942.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.761559581756591,
|
|
"epoch": 5.870213823968175,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00024548319102669745,
|
|
"loss": 5.1446,
|
|
"mean_token_accuracy": 0.20361201614141464,
|
|
"num_tokens": 11567273.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.849589395523071,
|
|
"epoch": 5.87518647439085,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00024509608124392065,
|
|
"loss": 5.2136,
|
|
"mean_token_accuracy": 0.19927402585744858,
|
|
"num_tokens": 11577383.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.825436210632324,
|
|
"epoch": 5.880159124813526,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002447090615499,
|
|
"loss": 5.2214,
|
|
"mean_token_accuracy": 0.2048507437109947,
|
|
"num_tokens": 11586899.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.840100574493408,
|
|
"epoch": 5.885131775236201,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00024432213311057383,
|
|
"loss": 5.2273,
|
|
"mean_token_accuracy": 0.20084301233291627,
|
|
"num_tokens": 11596884.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.758055830001831,
|
|
"epoch": 5.890104425658876,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00024393529709160544,
|
|
"loss": 5.1397,
|
|
"mean_token_accuracy": 0.21229133903980255,
|
|
"num_tokens": 11606603.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.743732118606568,
|
|
"epoch": 5.895077076081551,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00024354855465837967,
|
|
"loss": 5.1847,
|
|
"mean_token_accuracy": 0.20828092843294144,
|
|
"num_tokens": 11616202.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.742969512939453,
|
|
"epoch": 5.900049726504227,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00024316190697599955,
|
|
"loss": 5.0745,
|
|
"mean_token_accuracy": 0.21665455847978593,
|
|
"num_tokens": 11625054.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.767182445526123,
|
|
"epoch": 5.905022376926902,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00024277535520928257,
|
|
"loss": 5.1813,
|
|
"mean_token_accuracy": 0.2045110881328583,
|
|
"num_tokens": 11634636.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.843095064163208,
|
|
"epoch": 5.909995027349577,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00024238890052275742,
|
|
"loss": 5.2494,
|
|
"mean_token_accuracy": 0.19773934185504913,
|
|
"num_tokens": 11643949.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.843686246871949,
|
|
"epoch": 5.914967677772252,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00024200254408066014,
|
|
"loss": 5.1942,
|
|
"mean_token_accuracy": 0.20062797218561174,
|
|
"num_tokens": 11653964.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.79449577331543,
|
|
"epoch": 5.919940328194928,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002416162870469308,
|
|
"loss": 5.2193,
|
|
"mean_token_accuracy": 0.21146778762340546,
|
|
"num_tokens": 11662774.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.795069646835327,
|
|
"epoch": 5.924912978617603,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002412301305852102,
|
|
"loss": 5.2371,
|
|
"mean_token_accuracy": 0.19431576877832413,
|
|
"num_tokens": 11672504.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.848728227615356,
|
|
"epoch": 5.929885629040278,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00024084407585883588,
|
|
"loss": 5.2507,
|
|
"mean_token_accuracy": 0.20391916781663894,
|
|
"num_tokens": 11682225.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.8219305038452145,
|
|
"epoch": 5.934858279462953,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0002404581240308391,
|
|
"loss": 5.2306,
|
|
"mean_token_accuracy": 0.2018824338912964,
|
|
"num_tokens": 11691886.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.743938302993774,
|
|
"epoch": 5.939830929885629,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000240072276263941,
|
|
"loss": 5.1315,
|
|
"mean_token_accuracy": 0.2074597582221031,
|
|
"num_tokens": 11701366.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.7273674488067625,
|
|
"epoch": 5.944803580308305,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00023968653372054933,
|
|
"loss": 5.035,
|
|
"mean_token_accuracy": 0.21511294096708297,
|
|
"num_tokens": 11710309.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.850169038772583,
|
|
"epoch": 5.949776230730979,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00023930089756275474,
|
|
"loss": 5.2403,
|
|
"mean_token_accuracy": 0.19843266755342484,
|
|
"num_tokens": 11719123.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.736039686203003,
|
|
"epoch": 5.954748881153655,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002389153689523275,
|
|
"loss": 5.1694,
|
|
"mean_token_accuracy": 0.20977117717266083,
|
|
"num_tokens": 11728931.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.788062858581543,
|
|
"epoch": 5.9597215315763306,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00023852994905071385,
|
|
"loss": 5.1691,
|
|
"mean_token_accuracy": 0.20750078856945037,
|
|
"num_tokens": 11738666.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.753121757507325,
|
|
"epoch": 5.964694181999006,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00023814463901903238,
|
|
"loss": 5.1812,
|
|
"mean_token_accuracy": 0.20551323443651198,
|
|
"num_tokens": 11748530.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 5.964694181999006,
|
|
"eval_entropy": 5.742761397691367,
|
|
"eval_loss": 6.453769683837891,
|
|
"eval_mean_token_accuracy": 0.1502815871950119,
|
|
"eval_num_tokens": 11748530.0,
|
|
"eval_runtime": 2.5075,
|
|
"eval_samples_per_second": 1381.848,
|
|
"eval_steps_per_second": 173.08,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.796556806564331,
|
|
"epoch": 5.969666832421681,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00023775944001807077,
|
|
"loss": 5.1977,
|
|
"mean_token_accuracy": 0.20604104101657866,
|
|
"num_tokens": 11759611.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.833880996704101,
|
|
"epoch": 5.974639482844356,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00023737435320828244,
|
|
"loss": 5.1336,
|
|
"mean_token_accuracy": 0.21630909740924836,
|
|
"num_tokens": 11769427.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.732567167282104,
|
|
"epoch": 5.979612133267032,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00023698937974978257,
|
|
"loss": 5.0295,
|
|
"mean_token_accuracy": 0.21594223827123643,
|
|
"num_tokens": 11778992.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.680847406387329,
|
|
"epoch": 5.984584783689707,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00023660452080234473,
|
|
"loss": 5.0801,
|
|
"mean_token_accuracy": 0.21707364320755004,
|
|
"num_tokens": 11789844.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.783070611953735,
|
|
"epoch": 5.989557434112382,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00023621977752539785,
|
|
"loss": 5.1988,
|
|
"mean_token_accuracy": 0.20363202095031738,
|
|
"num_tokens": 11800336.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.803541660308838,
|
|
"epoch": 5.994530084535057,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002358351510780223,
|
|
"loss": 5.2327,
|
|
"mean_token_accuracy": 0.20104734152555465,
|
|
"num_tokens": 11810081.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.7934980392456055,
|
|
"epoch": 5.999502734957733,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00023545064261894623,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.20133887380361556,
|
|
"num_tokens": 11820046.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.7752771907382545,
|
|
"epoch": 6.00397812033814,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00023506625330654263,
|
|
"loss": 4.9122,
|
|
"mean_token_accuracy": 0.22935774094528621,
|
|
"num_tokens": 11828769.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.792873382568359,
|
|
"epoch": 6.008950770760816,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00023468198429882548,
|
|
"loss": 4.8795,
|
|
"mean_token_accuracy": 0.22578822672367097,
|
|
"num_tokens": 11838217.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.811983346939087,
|
|
"epoch": 6.013923421183491,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002342978367534462,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.21342911720275878,
|
|
"num_tokens": 11847268.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.801833772659302,
|
|
"epoch": 6.018896071606166,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002339138118276905,
|
|
"loss": 5.0099,
|
|
"mean_token_accuracy": 0.2178531289100647,
|
|
"num_tokens": 11857781.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.745023488998413,
|
|
"epoch": 6.023868722028841,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00023352991067847456,
|
|
"loss": 4.8449,
|
|
"mean_token_accuracy": 0.23143234401941298,
|
|
"num_tokens": 11867810.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.702177238464356,
|
|
"epoch": 6.028841372451517,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00023314613446234162,
|
|
"loss": 4.8894,
|
|
"mean_token_accuracy": 0.23054394721984864,
|
|
"num_tokens": 11877698.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.7310549259185795,
|
|
"epoch": 6.033814022874192,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00023276248433545867,
|
|
"loss": 5.0066,
|
|
"mean_token_accuracy": 0.21637514978647232,
|
|
"num_tokens": 11888696.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.849057245254516,
|
|
"epoch": 6.038786673296867,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00023237896145361276,
|
|
"loss": 5.0454,
|
|
"mean_token_accuracy": 0.2173118606209755,
|
|
"num_tokens": 11898865.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.744859600067139,
|
|
"epoch": 6.043759323719542,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00023199556697220758,
|
|
"loss": 4.8748,
|
|
"mean_token_accuracy": 0.2328149065375328,
|
|
"num_tokens": 11909506.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.79648003578186,
|
|
"epoch": 6.048731974142218,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00023161230204626015,
|
|
"loss": 4.9186,
|
|
"mean_token_accuracy": 0.22345959395170212,
|
|
"num_tokens": 11918663.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.859292078018188,
|
|
"epoch": 6.053704624564893,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00023122916783039694,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.21385511755943298,
|
|
"num_tokens": 11928683.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.739581727981568,
|
|
"epoch": 6.058677274987568,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0002308461654788509,
|
|
"loss": 4.8752,
|
|
"mean_token_accuracy": 0.2280689686536789,
|
|
"num_tokens": 11937251.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.776302671432495,
|
|
"epoch": 6.063649925410243,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00023046329614545758,
|
|
"loss": 4.8906,
|
|
"mean_token_accuracy": 0.2284036695957184,
|
|
"num_tokens": 11946061.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.759119606018066,
|
|
"epoch": 6.068622575832919,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00023008056098365183,
|
|
"loss": 4.8884,
|
|
"mean_token_accuracy": 0.222708997130394,
|
|
"num_tokens": 11956512.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.778053426742554,
|
|
"epoch": 6.073595226255594,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00022969796114646424,
|
|
"loss": 5.0119,
|
|
"mean_token_accuracy": 0.21489977687597275,
|
|
"num_tokens": 11966052.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.750843667984009,
|
|
"epoch": 6.078567876678269,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00022931549778651783,
|
|
"loss": 4.9305,
|
|
"mean_token_accuracy": 0.22040867805480957,
|
|
"num_tokens": 11974742.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.759443044662476,
|
|
"epoch": 6.083540527100944,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00022893317205602444,
|
|
"loss": 4.8996,
|
|
"mean_token_accuracy": 0.23115915954113006,
|
|
"num_tokens": 11985009.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.748704433441162,
|
|
"epoch": 6.08851317752362,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00022855098510678125,
|
|
"loss": 5.0078,
|
|
"mean_token_accuracy": 0.22152238935232163,
|
|
"num_tokens": 11994685.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.806336498260498,
|
|
"epoch": 6.093485827946296,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00022816893809016737,
|
|
"loss": 4.9857,
|
|
"mean_token_accuracy": 0.2155529022216797,
|
|
"num_tokens": 12004225.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.714574670791626,
|
|
"epoch": 6.098458478368971,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00022778703215714014,
|
|
"loss": 4.9458,
|
|
"mean_token_accuracy": 0.2224680095911026,
|
|
"num_tokens": 12013422.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.677380800247192,
|
|
"epoch": 6.103431128791646,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00022740526845823223,
|
|
"loss": 4.7995,
|
|
"mean_token_accuracy": 0.2417245849967003,
|
|
"num_tokens": 12023739.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.867645978927612,
|
|
"epoch": 6.1084037792143215,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002270236481435477,
|
|
"loss": 5.028,
|
|
"mean_token_accuracy": 0.215295447409153,
|
|
"num_tokens": 12034189.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.858246469497681,
|
|
"epoch": 6.113376429636997,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00022664217236275847,
|
|
"loss": 5.0583,
|
|
"mean_token_accuracy": 0.21213481426239014,
|
|
"num_tokens": 12043134.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.720355749130249,
|
|
"epoch": 6.118349080059672,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00022626084226510124,
|
|
"loss": 4.8989,
|
|
"mean_token_accuracy": 0.22778327614068986,
|
|
"num_tokens": 12052843.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.791149711608886,
|
|
"epoch": 6.123321730482347,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00022587965899937364,
|
|
"loss": 4.9881,
|
|
"mean_token_accuracy": 0.21906272172927857,
|
|
"num_tokens": 12063260.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.782792806625366,
|
|
"epoch": 6.1282943809050225,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0002254986237139312,
|
|
"loss": 4.9824,
|
|
"mean_token_accuracy": 0.22162739634513856,
|
|
"num_tokens": 12072534.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.815975332260132,
|
|
"epoch": 6.133267031327698,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00022511773755668342,
|
|
"loss": 5.1003,
|
|
"mean_token_accuracy": 0.20080506950616836,
|
|
"num_tokens": 12081796.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.614479827880859,
|
|
"epoch": 6.138239681750373,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002247370016750907,
|
|
"loss": 4.8382,
|
|
"mean_token_accuracy": 0.2368844524025917,
|
|
"num_tokens": 12092885.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.773766708374024,
|
|
"epoch": 6.143212332173048,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002243564172161605,
|
|
"loss": 4.9789,
|
|
"mean_token_accuracy": 0.21473100334405898,
|
|
"num_tokens": 12102432.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.676724815368653,
|
|
"epoch": 6.1481849825957235,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00022397598532644441,
|
|
"loss": 4.8342,
|
|
"mean_token_accuracy": 0.2362564131617546,
|
|
"num_tokens": 12112245.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.769500589370727,
|
|
"epoch": 6.153157633018399,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00022359570715203408,
|
|
"loss": 4.9165,
|
|
"mean_token_accuracy": 0.22345261871814728,
|
|
"num_tokens": 12121850.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.662306690216065,
|
|
"epoch": 6.158130283441074,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00022321558383855828,
|
|
"loss": 4.8019,
|
|
"mean_token_accuracy": 0.2415502905845642,
|
|
"num_tokens": 12132538.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.556177186965942,
|
|
"epoch": 6.163102933863749,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002228356165311791,
|
|
"loss": 4.7663,
|
|
"mean_token_accuracy": 0.24139104187488555,
|
|
"num_tokens": 12142041.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.810911750793457,
|
|
"epoch": 6.1680755842864246,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00022245580637458883,
|
|
"loss": 5.0888,
|
|
"mean_token_accuracy": 0.2141086757183075,
|
|
"num_tokens": 12151075.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.864644861221313,
|
|
"epoch": 6.1730482347091,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00022207615451300616,
|
|
"loss": 4.9783,
|
|
"mean_token_accuracy": 0.22147137373685838,
|
|
"num_tokens": 12160657.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.840275716781616,
|
|
"epoch": 6.178020885131775,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00022169666209017304,
|
|
"loss": 5.1368,
|
|
"mean_token_accuracy": 0.2057352364063263,
|
|
"num_tokens": 12171692.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.664615869522095,
|
|
"epoch": 6.18299353555445,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002213173302493509,
|
|
"loss": 4.8854,
|
|
"mean_token_accuracy": 0.22374286651611328,
|
|
"num_tokens": 12181429.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.728168678283692,
|
|
"epoch": 6.1879661859771256,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00022093816013331763,
|
|
"loss": 4.9233,
|
|
"mean_token_accuracy": 0.22622972428798677,
|
|
"num_tokens": 12191992.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.6482665061950685,
|
|
"epoch": 6.192938836399801,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00022055915288436362,
|
|
"loss": 4.8894,
|
|
"mean_token_accuracy": 0.23052081167697908,
|
|
"num_tokens": 12200804.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.857772159576416,
|
|
"epoch": 6.197911486822476,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00022018030964428897,
|
|
"loss": 5.0311,
|
|
"mean_token_accuracy": 0.21213303208351136,
|
|
"num_tokens": 12211774.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.78406286239624,
|
|
"epoch": 6.202884137245151,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00021980163155439943,
|
|
"loss": 4.9527,
|
|
"mean_token_accuracy": 0.2292575106024742,
|
|
"num_tokens": 12220270.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.819236946105957,
|
|
"epoch": 6.207856787667827,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00021942311975550323,
|
|
"loss": 5.0224,
|
|
"mean_token_accuracy": 0.21314507126808166,
|
|
"num_tokens": 12230662.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.789381742477417,
|
|
"epoch": 6.212829438090502,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00021904477538790774,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.21047717481851577,
|
|
"num_tokens": 12240383.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.773439025878906,
|
|
"epoch": 6.217802088513178,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00021866659959141578,
|
|
"loss": 5.0561,
|
|
"mean_token_accuracy": 0.21399274617433547,
|
|
"num_tokens": 12250247.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.670014953613281,
|
|
"epoch": 6.222774738935853,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0002182885935053225,
|
|
"loss": 4.9108,
|
|
"mean_token_accuracy": 0.23310362100601195,
|
|
"num_tokens": 12261245.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.807941532135009,
|
|
"epoch": 6.2277473893585285,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00021791075826841166,
|
|
"loss": 5.0697,
|
|
"mean_token_accuracy": 0.2051616132259369,
|
|
"num_tokens": 12271596.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.870597171783447,
|
|
"epoch": 6.232720039781204,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002175330950189523,
|
|
"loss": 5.1125,
|
|
"mean_token_accuracy": 0.2126794010400772,
|
|
"num_tokens": 12283124.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.741745185852051,
|
|
"epoch": 6.237692690203879,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002171556048946955,
|
|
"loss": 4.9392,
|
|
"mean_token_accuracy": 0.22262582033872605,
|
|
"num_tokens": 12293399.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.599240112304687,
|
|
"epoch": 6.242665340626554,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00021677828903287063,
|
|
"loss": 4.8601,
|
|
"mean_token_accuracy": 0.23807165026664734,
|
|
"num_tokens": 12303396.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.809062480926514,
|
|
"epoch": 6.2476379910492295,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00021640114857018205,
|
|
"loss": 4.9693,
|
|
"mean_token_accuracy": 0.2247156798839569,
|
|
"num_tokens": 12312483.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.719710016250611,
|
|
"epoch": 6.252610641471905,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00021602418464280586,
|
|
"loss": 4.8742,
|
|
"mean_token_accuracy": 0.23284967094659806,
|
|
"num_tokens": 12322420.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.880938386917114,
|
|
"epoch": 6.25758329189458,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00021564739838638615,
|
|
"loss": 5.1713,
|
|
"mean_token_accuracy": 0.19878542721271514,
|
|
"num_tokens": 12331740.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.82938551902771,
|
|
"epoch": 6.262555942317255,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00021527079093603202,
|
|
"loss": 5.056,
|
|
"mean_token_accuracy": 0.21008970886468886,
|
|
"num_tokens": 12341803.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.754930639266968,
|
|
"epoch": 6.2675285927399305,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00021489436342631352,
|
|
"loss": 4.9589,
|
|
"mean_token_accuracy": 0.21870766282081605,
|
|
"num_tokens": 12350824.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.804752445220947,
|
|
"epoch": 6.272501243162606,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00021451811699125883,
|
|
"loss": 5.0062,
|
|
"mean_token_accuracy": 0.21438478529453278,
|
|
"num_tokens": 12360116.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.773992109298706,
|
|
"epoch": 6.277473893585281,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00021414205276435073,
|
|
"loss": 4.9726,
|
|
"mean_token_accuracy": 0.2161247357726097,
|
|
"num_tokens": 12370486.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.75182466506958,
|
|
"epoch": 6.282446544007956,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002137661718785229,
|
|
"loss": 4.8931,
|
|
"mean_token_accuracy": 0.22871206253767012,
|
|
"num_tokens": 12380178.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.798911046981812,
|
|
"epoch": 6.2874191944306315,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00021339047546615675,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.2126149997115135,
|
|
"num_tokens": 12389844.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.810003566741943,
|
|
"epoch": 6.292391844853307,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00021301496465907794,
|
|
"loss": 5.0401,
|
|
"mean_token_accuracy": 0.2176359102129936,
|
|
"num_tokens": 12400880.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.782121658325195,
|
|
"epoch": 6.297364495275982,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00021263964058855294,
|
|
"loss": 5.0081,
|
|
"mean_token_accuracy": 0.21485229581594467,
|
|
"num_tokens": 12410833.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.816357088088989,
|
|
"epoch": 6.302337145698657,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00021226450438528572,
|
|
"loss": 4.9186,
|
|
"mean_token_accuracy": 0.22658170908689498,
|
|
"num_tokens": 12419993.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.80844349861145,
|
|
"epoch": 6.3073097961213325,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00021188955717941428,
|
|
"loss": 5.0703,
|
|
"mean_token_accuracy": 0.2115544855594635,
|
|
"num_tokens": 12431395.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.6798076152801515,
|
|
"epoch": 6.312282446544008,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0002115148001005071,
|
|
"loss": 4.8723,
|
|
"mean_token_accuracy": 0.22438751459121703,
|
|
"num_tokens": 12440961.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.795302200317383,
|
|
"epoch": 6.317255096966683,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00021114023427756012,
|
|
"loss": 5.0303,
|
|
"mean_token_accuracy": 0.21625926941633225,
|
|
"num_tokens": 12450333.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.837156295776367,
|
|
"epoch": 6.322227747389358,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00021076586083899296,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.2180263563990593,
|
|
"num_tokens": 12459373.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.7313549518585205,
|
|
"epoch": 6.3272003978120335,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0002103916809126456,
|
|
"loss": 4.9449,
|
|
"mean_token_accuracy": 0.2215929299592972,
|
|
"num_tokens": 12469366.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.821239042282104,
|
|
"epoch": 6.332173048234709,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00021001769562577517,
|
|
"loss": 4.972,
|
|
"mean_token_accuracy": 0.2225111946463585,
|
|
"num_tokens": 12478650.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.495806884765625,
|
|
"epoch": 6.337145698657384,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002096439061050523,
|
|
"loss": 4.6793,
|
|
"mean_token_accuracy": 0.24887047559022904,
|
|
"num_tokens": 12490607.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.7309869766235355,
|
|
"epoch": 6.34211834908006,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000209270313476558,
|
|
"loss": 5.0416,
|
|
"mean_token_accuracy": 0.2140985533595085,
|
|
"num_tokens": 12502893.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.608294486999512,
|
|
"epoch": 6.347090999502735,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00020889691886578004,
|
|
"loss": 4.8011,
|
|
"mean_token_accuracy": 0.24145514219999314,
|
|
"num_tokens": 12513470.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.806584262847901,
|
|
"epoch": 6.352063649925411,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00020852372339760973,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.21656888127326965,
|
|
"num_tokens": 12522982.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.6548114776611325,
|
|
"epoch": 6.357036300348086,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002081507281963383,
|
|
"loss": 4.9275,
|
|
"mean_token_accuracy": 0.22323464304208757,
|
|
"num_tokens": 12533247.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.67568073272705,
|
|
"epoch": 6.362008950770761,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00020777793438565368,
|
|
"loss": 5.0753,
|
|
"mean_token_accuracy": 0.21024061888456344,
|
|
"num_tokens": 12543488.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.820740985870361,
|
|
"epoch": 6.366981601193436,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00020740534308863717,
|
|
"loss": 5.1218,
|
|
"mean_token_accuracy": 0.21026428788900375,
|
|
"num_tokens": 12553782.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.878458261489868,
|
|
"epoch": 6.371954251616112,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00020703295542775992,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.20697135031223296,
|
|
"num_tokens": 12562913.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.718147945404053,
|
|
"epoch": 6.376926902038787,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00020666077252487968,
|
|
"loss": 4.8648,
|
|
"mean_token_accuracy": 0.23167754262685775,
|
|
"num_tokens": 12571979.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.5168791055679325,
|
|
"epoch": 6.381899552461462,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0002062887955012372,
|
|
"loss": 4.7274,
|
|
"mean_token_accuracy": 0.24945868104696273,
|
|
"num_tokens": 12581445.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.80403995513916,
|
|
"epoch": 6.386872202884137,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00020591702547745306,
|
|
"loss": 5.0983,
|
|
"mean_token_accuracy": 0.2078007698059082,
|
|
"num_tokens": 12592437.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.759623670578003,
|
|
"epoch": 6.391844853306813,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00020554546357352433,
|
|
"loss": 4.9673,
|
|
"mean_token_accuracy": 0.22608183026313783,
|
|
"num_tokens": 12602946.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.846452951431274,
|
|
"epoch": 6.396817503729488,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000205174110908821,
|
|
"loss": 5.0454,
|
|
"mean_token_accuracy": 0.21518912613391877,
|
|
"num_tokens": 12612620.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.779588794708252,
|
|
"epoch": 6.401790154152163,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0002048029686020827,
|
|
"loss": 4.9665,
|
|
"mean_token_accuracy": 0.21493392586708068,
|
|
"num_tokens": 12621588.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.732927846908569,
|
|
"epoch": 6.406762804574838,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002044320377714154,
|
|
"loss": 4.9043,
|
|
"mean_token_accuracy": 0.22827706187963487,
|
|
"num_tokens": 12630802.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.73603253364563,
|
|
"epoch": 6.411735454997514,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00020406131953428785,
|
|
"loss": 4.9075,
|
|
"mean_token_accuracy": 0.22817528247833252,
|
|
"num_tokens": 12640358.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.81327714920044,
|
|
"epoch": 6.416708105420189,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002036908150075285,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.20818021446466445,
|
|
"num_tokens": 12650598.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.743423509597778,
|
|
"epoch": 6.421680755842864,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002033205253073218,
|
|
"loss": 4.9431,
|
|
"mean_token_accuracy": 0.22703344374895096,
|
|
"num_tokens": 12661213.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.792520141601562,
|
|
"epoch": 6.426653406265539,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00020295045154920528,
|
|
"loss": 5.0119,
|
|
"mean_token_accuracy": 0.22134610414505004,
|
|
"num_tokens": 12670374.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.751080846786499,
|
|
"epoch": 6.431626056688215,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00020258059484806564,
|
|
"loss": 4.9893,
|
|
"mean_token_accuracy": 0.2197373017668724,
|
|
"num_tokens": 12679725.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.729063415527344,
|
|
"epoch": 6.43659870711089,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00020221095631813574,
|
|
"loss": 4.942,
|
|
"mean_token_accuracy": 0.2194691151380539,
|
|
"num_tokens": 12688391.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.773144006729126,
|
|
"epoch": 6.441571357533565,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002018415370729913,
|
|
"loss": 5.0336,
|
|
"mean_token_accuracy": 0.21337719559669494,
|
|
"num_tokens": 12698030.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.781252813339234,
|
|
"epoch": 6.44654400795624,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00020147233822554722,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.21637423038482667,
|
|
"num_tokens": 12708577.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.82703046798706,
|
|
"epoch": 6.451516658378916,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00020110336088805463,
|
|
"loss": 5.0524,
|
|
"mean_token_accuracy": 0.21116605699062346,
|
|
"num_tokens": 12718573.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.776969003677368,
|
|
"epoch": 6.456489308801591,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00020073460617209732,
|
|
"loss": 4.8912,
|
|
"mean_token_accuracy": 0.22597435414791106,
|
|
"num_tokens": 12728246.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.725563955307007,
|
|
"epoch": 6.461461959224266,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00020036607518858824,
|
|
"loss": 4.9875,
|
|
"mean_token_accuracy": 0.2232201561331749,
|
|
"num_tokens": 12737807.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.825282144546509,
|
|
"epoch": 6.466434609646942,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00019999776904776646,
|
|
"loss": 5.1097,
|
|
"mean_token_accuracy": 0.20644655972719192,
|
|
"num_tokens": 12747463.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.829600477218628,
|
|
"epoch": 6.471407260069617,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0001996296888591937,
|
|
"loss": 5.0046,
|
|
"mean_token_accuracy": 0.2159730836749077,
|
|
"num_tokens": 12757449.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.733340120315551,
|
|
"epoch": 6.476379910492293,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00019926183573175084,
|
|
"loss": 4.9425,
|
|
"mean_token_accuracy": 0.22915790528059005,
|
|
"num_tokens": 12767698.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.75927767753601,
|
|
"epoch": 6.481352560914968,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0001988942107736348,
|
|
"loss": 4.9705,
|
|
"mean_token_accuracy": 0.22058000415563583,
|
|
"num_tokens": 12776252.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.702142906188965,
|
|
"epoch": 6.486325211337643,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00019852681509235516,
|
|
"loss": 4.899,
|
|
"mean_token_accuracy": 0.2277068093419075,
|
|
"num_tokens": 12785001.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.779895782470703,
|
|
"epoch": 6.4912978617603185,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00019815964979473088,
|
|
"loss": 5.0447,
|
|
"mean_token_accuracy": 0.22021796107292174,
|
|
"num_tokens": 12794587.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.790762090682984,
|
|
"epoch": 6.496270512182994,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00019779271598688642,
|
|
"loss": 5.005,
|
|
"mean_token_accuracy": 0.2155056670308113,
|
|
"num_tokens": 12803439.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.756672763824463,
|
|
"epoch": 6.501243162605669,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00019742601477424937,
|
|
"loss": 5.0471,
|
|
"mean_token_accuracy": 0.20916286557912828,
|
|
"num_tokens": 12813039.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.7403816223144535,
|
|
"epoch": 6.506215813028344,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0001970595472615463,
|
|
"loss": 4.9652,
|
|
"mean_token_accuracy": 0.22509440034627914,
|
|
"num_tokens": 12823105.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.693891000747681,
|
|
"epoch": 6.5111884634510195,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00019669331455279989,
|
|
"loss": 4.96,
|
|
"mean_token_accuracy": 0.22909341901540756,
|
|
"num_tokens": 12833576.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.810893440246582,
|
|
"epoch": 6.516161113873695,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00019632731775132522,
|
|
"loss": 5.0963,
|
|
"mean_token_accuracy": 0.20751657634973525,
|
|
"num_tokens": 12843570.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.823085784912109,
|
|
"epoch": 6.52113376429637,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00019596155795972698,
|
|
"loss": 5.0854,
|
|
"mean_token_accuracy": 0.2188723236322403,
|
|
"num_tokens": 12852751.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.768367004394531,
|
|
"epoch": 6.526106414719045,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0001955960362798957,
|
|
"loss": 5.0058,
|
|
"mean_token_accuracy": 0.21617185175418854,
|
|
"num_tokens": 12863114.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.723651456832886,
|
|
"epoch": 6.5310790651417205,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0001952307538130045,
|
|
"loss": 4.8774,
|
|
"mean_token_accuracy": 0.2232176125049591,
|
|
"num_tokens": 12871731.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.74789023399353,
|
|
"epoch": 6.536051715564396,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0001948657116595059,
|
|
"loss": 4.9829,
|
|
"mean_token_accuracy": 0.2204902470111847,
|
|
"num_tokens": 12880261.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.738331460952759,
|
|
"epoch": 6.541024365987071,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00019450091091912847,
|
|
"loss": 4.9137,
|
|
"mean_token_accuracy": 0.22297689765691758,
|
|
"num_tokens": 12889528.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.572204613685608,
|
|
"epoch": 6.545997016409746,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0001941363526908736,
|
|
"loss": 4.8557,
|
|
"mean_token_accuracy": 0.23778597563505172,
|
|
"num_tokens": 12899734.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.771384239196777,
|
|
"epoch": 6.5509696668324215,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00019377203807301185,
|
|
"loss": 4.9593,
|
|
"mean_token_accuracy": 0.21610347777605057,
|
|
"num_tokens": 12909960.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.720004653930664,
|
|
"epoch": 6.555942317255097,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00019340796816308,
|
|
"loss": 4.9863,
|
|
"mean_token_accuracy": 0.22182489037513733,
|
|
"num_tokens": 12919411.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.784110403060913,
|
|
"epoch": 6.560914967677772,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00019304414405787768,
|
|
"loss": 5.0714,
|
|
"mean_token_accuracy": 0.21646376103162765,
|
|
"num_tokens": 12929470.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.75920295715332,
|
|
"epoch": 6.565887618100447,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001926805668534639,
|
|
"loss": 5.024,
|
|
"mean_token_accuracy": 0.21484150737524033,
|
|
"num_tokens": 12940292.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.800962114334107,
|
|
"epoch": 6.5708602685231225,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00019231723764515397,
|
|
"loss": 5.0334,
|
|
"mean_token_accuracy": 0.20758202970027922,
|
|
"num_tokens": 12950218.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.79684591293335,
|
|
"epoch": 6.575832918945798,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00019195415752751595,
|
|
"loss": 5.0857,
|
|
"mean_token_accuracy": 0.2092265322804451,
|
|
"num_tokens": 12961082.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.8012584209442135,
|
|
"epoch": 6.580805569368473,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00019159132759436764,
|
|
"loss": 5.0898,
|
|
"mean_token_accuracy": 0.20406343191862106,
|
|
"num_tokens": 12970913.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.809730863571167,
|
|
"epoch": 6.585778219791148,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00019122874893877294,
|
|
"loss": 5.0609,
|
|
"mean_token_accuracy": 0.2149926021695137,
|
|
"num_tokens": 12981201.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.815408992767334,
|
|
"epoch": 6.590750870213824,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00019086642265303894,
|
|
"loss": 5.0706,
|
|
"mean_token_accuracy": 0.20948077291250228,
|
|
"num_tokens": 12991283.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.728418397903442,
|
|
"epoch": 6.595723520636499,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0001905043498287124,
|
|
"loss": 4.861,
|
|
"mean_token_accuracy": 0.23777890354394912,
|
|
"num_tokens": 13001201.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.618921279907227,
|
|
"epoch": 6.600696171059175,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0001901425315565764,
|
|
"loss": 4.8116,
|
|
"mean_token_accuracy": 0.24385300129652024,
|
|
"num_tokens": 13011119.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.781985139846801,
|
|
"epoch": 6.60566882148185,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00018978096892664726,
|
|
"loss": 4.9966,
|
|
"mean_token_accuracy": 0.2202678292989731,
|
|
"num_tokens": 13021459.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.651460456848144,
|
|
"epoch": 6.6106414719045254,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000189419663028171,
|
|
"loss": 4.9158,
|
|
"mean_token_accuracy": 0.22164898067712785,
|
|
"num_tokens": 13032021.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.771470737457276,
|
|
"epoch": 6.615614122327201,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00018905861494962034,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.21703945994377136,
|
|
"num_tokens": 13041418.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.8028820037841795,
|
|
"epoch": 6.620586772749876,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00018869782577869132,
|
|
"loss": 5.0091,
|
|
"mean_token_accuracy": 0.21160737723112105,
|
|
"num_tokens": 13051535.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.811369752883911,
|
|
"epoch": 6.625559423172551,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00018833729660229997,
|
|
"loss": 4.9559,
|
|
"mean_token_accuracy": 0.22168831825256347,
|
|
"num_tokens": 13060854.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.784315013885498,
|
|
"epoch": 6.6305320735952264,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00018797702850657889,
|
|
"loss": 5.0166,
|
|
"mean_token_accuracy": 0.21800300776958464,
|
|
"num_tokens": 13069429.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.699229097366333,
|
|
"epoch": 6.635504724017902,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0001876170225768744,
|
|
"loss": 4.9967,
|
|
"mean_token_accuracy": 0.22020397186279297,
|
|
"num_tokens": 13078990.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.6513982772827145,
|
|
"epoch": 6.640477374440577,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0001872572798977429,
|
|
"loss": 4.8697,
|
|
"mean_token_accuracy": 0.23717480897903442,
|
|
"num_tokens": 13089702.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.801228427886963,
|
|
"epoch": 6.645450024863252,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0001868978015529476,
|
|
"loss": 4.974,
|
|
"mean_token_accuracy": 0.21462280452251434,
|
|
"num_tokens": 13099890.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.806415748596192,
|
|
"epoch": 6.6504226752859275,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00018653858862545565,
|
|
"loss": 5.1113,
|
|
"mean_token_accuracy": 0.20807499587535858,
|
|
"num_tokens": 13108767.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.55604043006897,
|
|
"epoch": 6.655395325708603,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00018617964219743428,
|
|
"loss": 4.7084,
|
|
"mean_token_accuracy": 0.25089298337697985,
|
|
"num_tokens": 13118548.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.741314029693603,
|
|
"epoch": 6.660367976131278,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00018582096335024813,
|
|
"loss": 5.0222,
|
|
"mean_token_accuracy": 0.21791223734617232,
|
|
"num_tokens": 13129451.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.779950952529907,
|
|
"epoch": 6.665340626553953,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0001854625531644557,
|
|
"loss": 5.0348,
|
|
"mean_token_accuracy": 0.2131907433271408,
|
|
"num_tokens": 13138679.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.832522392272949,
|
|
"epoch": 6.6703132769766285,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00018510441271980588,
|
|
"loss": 5.1174,
|
|
"mean_token_accuracy": 0.20344968885183334,
|
|
"num_tokens": 13148980.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.7129346370697025,
|
|
"epoch": 6.675285927399304,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00018474654309523508,
|
|
"loss": 4.9246,
|
|
"mean_token_accuracy": 0.23507798016071318,
|
|
"num_tokens": 13158743.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.676855897903442,
|
|
"epoch": 6.680258577821979,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00018438894536886396,
|
|
"loss": 4.9145,
|
|
"mean_token_accuracy": 0.23291720896959306,
|
|
"num_tokens": 13168371.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.807549238204956,
|
|
"epoch": 6.685231228244654,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00018403162061799395,
|
|
"loss": 5.0102,
|
|
"mean_token_accuracy": 0.21349057257175447,
|
|
"num_tokens": 13177399.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.785579681396484,
|
|
"epoch": 6.6902038786673295,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00018367456991910403,
|
|
"loss": 4.9066,
|
|
"mean_token_accuracy": 0.2275314137339592,
|
|
"num_tokens": 13186689.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.706558132171631,
|
|
"epoch": 6.695176529090005,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00018331779434784773,
|
|
"loss": 4.8994,
|
|
"mean_token_accuracy": 0.22435745745897293,
|
|
"num_tokens": 13198859.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.792715787887573,
|
|
"epoch": 6.70014917951268,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00018296129497904955,
|
|
"loss": 4.9554,
|
|
"mean_token_accuracy": 0.2237139090895653,
|
|
"num_tokens": 13207237.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.783191537857055,
|
|
"epoch": 6.705121829935355,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0001826050728867021,
|
|
"loss": 5.0042,
|
|
"mean_token_accuracy": 0.22007857710123063,
|
|
"num_tokens": 13216163.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.867406415939331,
|
|
"epoch": 6.7100944803580305,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00018224912914396253,
|
|
"loss": 5.1109,
|
|
"mean_token_accuracy": 0.2093421548604965,
|
|
"num_tokens": 13225714.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.7421365737915036,
|
|
"epoch": 6.715067130780707,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00018189346482314945,
|
|
"loss": 5.0,
|
|
"mean_token_accuracy": 0.21880636364221573,
|
|
"num_tokens": 13234226.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.807155275344849,
|
|
"epoch": 6.720039781203381,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00018153808099573976,
|
|
"loss": 5.0639,
|
|
"mean_token_accuracy": 0.213060362637043,
|
|
"num_tokens": 13244286.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.7276444911956785,
|
|
"epoch": 6.725012431626057,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00018118297873236517,
|
|
"loss": 5.0022,
|
|
"mean_token_accuracy": 0.21884128153324128,
|
|
"num_tokens": 13254283.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.7597252368927006,
|
|
"epoch": 6.729985082048732,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00018082815910280925,
|
|
"loss": 4.941,
|
|
"mean_token_accuracy": 0.21653785556554794,
|
|
"num_tokens": 13263886.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.813850736618042,
|
|
"epoch": 6.734957732471408,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00018047362317600424,
|
|
"loss": 5.0312,
|
|
"mean_token_accuracy": 0.22039688229560853,
|
|
"num_tokens": 13273406.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.6672931671142575,
|
|
"epoch": 6.739930382894083,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00018011937202002748,
|
|
"loss": 4.8715,
|
|
"mean_token_accuracy": 0.24096726030111312,
|
|
"num_tokens": 13282980.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.723915719985962,
|
|
"epoch": 6.744903033316758,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00017976540670209856,
|
|
"loss": 4.9386,
|
|
"mean_token_accuracy": 0.21949985027313232,
|
|
"num_tokens": 13292791.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.578207635879517,
|
|
"epoch": 6.749875683739433,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00017941172828857572,
|
|
"loss": 4.8373,
|
|
"mean_token_accuracy": 0.2434277355670929,
|
|
"num_tokens": 13302440.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.735390901565552,
|
|
"epoch": 6.754848334162109,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00017905833784495325,
|
|
"loss": 4.9827,
|
|
"mean_token_accuracy": 0.21593716740608215,
|
|
"num_tokens": 13312465.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.834824419021606,
|
|
"epoch": 6.759820984584784,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00017870523643585769,
|
|
"loss": 4.9961,
|
|
"mean_token_accuracy": 0.2189650282263756,
|
|
"num_tokens": 13321991.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.687113857269287,
|
|
"epoch": 6.764793635007459,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00017835242512504463,
|
|
"loss": 4.8954,
|
|
"mean_token_accuracy": 0.22275741249322892,
|
|
"num_tokens": 13331671.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.758288621902466,
|
|
"epoch": 6.769766285430134,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00017799990497539608,
|
|
"loss": 5.0548,
|
|
"mean_token_accuracy": 0.21617412567138672,
|
|
"num_tokens": 13341196.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.794560241699219,
|
|
"epoch": 6.77473893585281,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0001776476770489167,
|
|
"loss": 5.0409,
|
|
"mean_token_accuracy": 0.20546902865171432,
|
|
"num_tokens": 13350993.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.782895135879516,
|
|
"epoch": 6.779711586275485,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00017729574240673069,
|
|
"loss": 4.9882,
|
|
"mean_token_accuracy": 0.21895190924406052,
|
|
"num_tokens": 13360385.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.72673544883728,
|
|
"epoch": 6.78468423669816,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00017694410210907906,
|
|
"loss": 4.9844,
|
|
"mean_token_accuracy": 0.21963416785001755,
|
|
"num_tokens": 13370057.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.61151156425476,
|
|
"epoch": 6.789656887120835,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0001765927572153156,
|
|
"loss": 4.8203,
|
|
"mean_token_accuracy": 0.24337499886751174,
|
|
"num_tokens": 13380379.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.845886945724487,
|
|
"epoch": 6.794629537543511,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0001762417087839046,
|
|
"loss": 5.0657,
|
|
"mean_token_accuracy": 0.21057667285203935,
|
|
"num_tokens": 13389795.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.781686210632325,
|
|
"epoch": 6.799602187966186,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00017589095787241688,
|
|
"loss": 4.9786,
|
|
"mean_token_accuracy": 0.2225270763039589,
|
|
"num_tokens": 13400630.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.761485242843628,
|
|
"epoch": 6.804574838388861,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001755405055375272,
|
|
"loss": 4.9758,
|
|
"mean_token_accuracy": 0.21645060926675797,
|
|
"num_tokens": 13411044.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.772102546691895,
|
|
"epoch": 6.809547488811536,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00017519035283501084,
|
|
"loss": 4.9906,
|
|
"mean_token_accuracy": 0.21144272536039352,
|
|
"num_tokens": 13420092.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.732190895080566,
|
|
"epoch": 6.814520139234212,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00017484050081974004,
|
|
"loss": 5.0103,
|
|
"mean_token_accuracy": 0.22232451289892197,
|
|
"num_tokens": 13430058.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.79632158279419,
|
|
"epoch": 6.819492789656887,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0001744909505456817,
|
|
"loss": 4.9913,
|
|
"mean_token_accuracy": 0.22410221695899962,
|
|
"num_tokens": 13439061.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.780145454406738,
|
|
"epoch": 6.824465440079562,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00017414170306589318,
|
|
"loss": 5.0747,
|
|
"mean_token_accuracy": 0.2153870940208435,
|
|
"num_tokens": 13449341.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.796961784362793,
|
|
"epoch": 6.829438090502237,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0001737927594325201,
|
|
"loss": 5.0232,
|
|
"mean_token_accuracy": 0.2167483910918236,
|
|
"num_tokens": 13457896.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.741919946670532,
|
|
"epoch": 6.834410740924913,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00017344412069679257,
|
|
"loss": 4.9856,
|
|
"mean_token_accuracy": 0.2215201735496521,
|
|
"num_tokens": 13468404.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.760574245452881,
|
|
"epoch": 6.839383391347588,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0001730957879090218,
|
|
"loss": 5.046,
|
|
"mean_token_accuracy": 0.21442678570747375,
|
|
"num_tokens": 13477530.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.769275569915772,
|
|
"epoch": 6.844356041770263,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00017274776211859778,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.21066582351922988,
|
|
"num_tokens": 13487250.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.781524610519409,
|
|
"epoch": 6.849328692192939,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00017240004437398554,
|
|
"loss": 5.0455,
|
|
"mean_token_accuracy": 0.21457413733005523,
|
|
"num_tokens": 13497342.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.8544394969940186,
|
|
"epoch": 6.854301342615614,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0001720526357227218,
|
|
"loss": 5.0935,
|
|
"mean_token_accuracy": 0.21465780436992646,
|
|
"num_tokens": 13507644.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.770434093475342,
|
|
"epoch": 6.85927399303829,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00017170553721141253,
|
|
"loss": 5.0123,
|
|
"mean_token_accuracy": 0.21567609161138535,
|
|
"num_tokens": 13516713.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.765035820007324,
|
|
"epoch": 6.864246643460965,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0001713587498857289,
|
|
"loss": 4.9584,
|
|
"mean_token_accuracy": 0.21715863645076752,
|
|
"num_tokens": 13525603.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.784005784988404,
|
|
"epoch": 6.86921929388364,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00017101227479040498,
|
|
"loss": 4.9782,
|
|
"mean_token_accuracy": 0.2150896519422531,
|
|
"num_tokens": 13534809.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.744484710693359,
|
|
"epoch": 6.8741919443063155,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00017066611296923424,
|
|
"loss": 4.9762,
|
|
"mean_token_accuracy": 0.21785249710083007,
|
|
"num_tokens": 13544482.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.753024625778198,
|
|
"epoch": 6.879164594728991,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00017032026546506595,
|
|
"loss": 5.0055,
|
|
"mean_token_accuracy": 0.2139527752995491,
|
|
"num_tokens": 13553583.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.798416996002198,
|
|
"epoch": 6.884137245151666,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00016997473331980295,
|
|
"loss": 5.1125,
|
|
"mean_token_accuracy": 0.20553038418293,
|
|
"num_tokens": 13562387.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.849046468734741,
|
|
"epoch": 6.889109895574341,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0001696295175743977,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.20877499580383302,
|
|
"num_tokens": 13572654.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.821051836013794,
|
|
"epoch": 6.8940825459970165,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00016928461926884954,
|
|
"loss": 4.9463,
|
|
"mean_token_accuracy": 0.23027115166187287,
|
|
"num_tokens": 13582066.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.767705631256104,
|
|
"epoch": 6.899055196419692,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00016894003944220167,
|
|
"loss": 4.963,
|
|
"mean_token_accuracy": 0.22448194026947021,
|
|
"num_tokens": 13591702.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.782188606262207,
|
|
"epoch": 6.904027846842367,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0001685957791325375,
|
|
"loss": 4.9869,
|
|
"mean_token_accuracy": 0.2222226768732071,
|
|
"num_tokens": 13601822.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.604835271835327,
|
|
"epoch": 6.909000497265042,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0001682518393769782,
|
|
"loss": 4.818,
|
|
"mean_token_accuracy": 0.23212510347366333,
|
|
"num_tokens": 13611389.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.697763872146607,
|
|
"epoch": 6.9139731476877175,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00016790822121167913,
|
|
"loss": 4.9831,
|
|
"mean_token_accuracy": 0.22281939536333084,
|
|
"num_tokens": 13621590.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.717285776138306,
|
|
"epoch": 6.918945798110393,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00016756492567182674,
|
|
"loss": 4.9163,
|
|
"mean_token_accuracy": 0.22621488124132155,
|
|
"num_tokens": 13630319.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.69885401725769,
|
|
"epoch": 6.923918448533068,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00016722195379163568,
|
|
"loss": 4.8877,
|
|
"mean_token_accuracy": 0.22674857825040817,
|
|
"num_tokens": 13639807.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.691522789001465,
|
|
"epoch": 6.928891098955743,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00016687930660434528,
|
|
"loss": 4.9245,
|
|
"mean_token_accuracy": 0.227017742395401,
|
|
"num_tokens": 13649522.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.708332824707031,
|
|
"epoch": 6.9338637493784185,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00016653698514221694,
|
|
"loss": 4.9334,
|
|
"mean_token_accuracy": 0.2281072109937668,
|
|
"num_tokens": 13658855.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.644028806686402,
|
|
"epoch": 6.938836399801094,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0001661949904365308,
|
|
"loss": 4.7977,
|
|
"mean_token_accuracy": 0.23988936394453048,
|
|
"num_tokens": 13669196.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.721158742904663,
|
|
"epoch": 6.943809050223769,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0001658533235175824,
|
|
"loss": 4.8908,
|
|
"mean_token_accuracy": 0.22259773761034013,
|
|
"num_tokens": 13680222.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.76847095489502,
|
|
"epoch": 6.948781700646444,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00016551198541468,
|
|
"loss": 4.9949,
|
|
"mean_token_accuracy": 0.22554108500480652,
|
|
"num_tokens": 13689392.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.65790023803711,
|
|
"epoch": 6.9537543510691195,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00016517097715614115,
|
|
"loss": 4.8909,
|
|
"mean_token_accuracy": 0.2300471618771553,
|
|
"num_tokens": 13698104.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.784369230270386,
|
|
"epoch": 6.958727001491795,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00016483029976928958,
|
|
"loss": 5.0099,
|
|
"mean_token_accuracy": 0.22124136090278626,
|
|
"num_tokens": 13707386.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"epoch": 6.958727001491795,
|
|
"eval_entropy": 5.743314448589554,
|
|
"eval_loss": 6.439155101776123,
|
|
"eval_mean_token_accuracy": 0.15161392424032435,
|
|
"eval_num_tokens": 13707386.0,
|
|
"eval_runtime": 2.6904,
|
|
"eval_samples_per_second": 1287.901,
|
|
"eval_steps_per_second": 161.313,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.736767053604126,
|
|
"epoch": 6.96369965191447,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0001644899542804526,
|
|
"loss": 4.9447,
|
|
"mean_token_accuracy": 0.2195888414978981,
|
|
"num_tokens": 13716643.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.573602247238159,
|
|
"epoch": 6.968672302337145,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00016414994171495728,
|
|
"loss": 4.8477,
|
|
"mean_token_accuracy": 0.23888232707977294,
|
|
"num_tokens": 13727125.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.7323160648345945,
|
|
"epoch": 6.973644952759821,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00016381026309712787,
|
|
"loss": 5.0381,
|
|
"mean_token_accuracy": 0.22130025029182435,
|
|
"num_tokens": 13737267.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.7645604610443115,
|
|
"epoch": 6.978617603182496,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00016347091945028273,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.2197049841284752,
|
|
"num_tokens": 13748051.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.772989511489868,
|
|
"epoch": 6.983590253605172,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001631319117967307,
|
|
"loss": 5.0259,
|
|
"mean_token_accuracy": 0.21849102526903152,
|
|
"num_tokens": 13758958.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.67297248840332,
|
|
"epoch": 6.988562904027847,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00016279324115776886,
|
|
"loss": 4.8553,
|
|
"mean_token_accuracy": 0.24190341383218766,
|
|
"num_tokens": 13768566.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.73263692855835,
|
|
"epoch": 6.993535554450522,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0001624549085536785,
|
|
"loss": 5.0444,
|
|
"mean_token_accuracy": 0.21318924725055693,
|
|
"num_tokens": 13777777.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.695686626434326,
|
|
"epoch": 6.998508204873198,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00016211691500372304,
|
|
"loss": 5.0155,
|
|
"mean_token_accuracy": 0.22316440045833588,
|
|
"num_tokens": 13788178.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.562890847524007,
|
|
"epoch": 7.0029835902536055,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00016177926152614414,
|
|
"loss": 4.6681,
|
|
"mean_token_accuracy": 0.2511300990978877,
|
|
"num_tokens": 13797143.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.58250675201416,
|
|
"epoch": 7.007956240676281,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00016144194913815887,
|
|
"loss": 4.5976,
|
|
"mean_token_accuracy": 0.26270999312400817,
|
|
"num_tokens": 13806835.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.788944339752197,
|
|
"epoch": 7.012928891098956,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0001611049788559572,
|
|
"loss": 4.8407,
|
|
"mean_token_accuracy": 0.22632508277893065,
|
|
"num_tokens": 13816313.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.763921070098877,
|
|
"epoch": 7.017901541521631,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00016076835169469796,
|
|
"loss": 4.8608,
|
|
"mean_token_accuracy": 0.22954008877277374,
|
|
"num_tokens": 13825692.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.7839577198028564,
|
|
"epoch": 7.0228741919443065,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00016043206866850652,
|
|
"loss": 4.8536,
|
|
"mean_token_accuracy": 0.22364830672740937,
|
|
"num_tokens": 13835398.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.712060976028442,
|
|
"epoch": 7.027846842366982,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0001600961307904717,
|
|
"loss": 4.7871,
|
|
"mean_token_accuracy": 0.24017711579799653,
|
|
"num_tokens": 13844548.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.75835952758789,
|
|
"epoch": 7.032819492789657,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00015976053907264208,
|
|
"loss": 4.8201,
|
|
"mean_token_accuracy": 0.23103471845388412,
|
|
"num_tokens": 13853844.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.714350986480713,
|
|
"epoch": 7.037792143212332,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00015942529452602378,
|
|
"loss": 4.786,
|
|
"mean_token_accuracy": 0.2397241175174713,
|
|
"num_tokens": 13862477.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.6459540843963625,
|
|
"epoch": 7.0427647936350075,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00015909039816057674,
|
|
"loss": 4.6926,
|
|
"mean_token_accuracy": 0.2462707743048668,
|
|
"num_tokens": 13874248.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.575007724761963,
|
|
"epoch": 7.047737444057683,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00015875585098521218,
|
|
"loss": 4.6113,
|
|
"mean_token_accuracy": 0.2657154381275177,
|
|
"num_tokens": 13883952.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.590839433670044,
|
|
"epoch": 7.052710094480358,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00015842165400778942,
|
|
"loss": 4.7012,
|
|
"mean_token_accuracy": 0.2492325335741043,
|
|
"num_tokens": 13893782.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.5845797777175905,
|
|
"epoch": 7.057682744903033,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0001580878082351123,
|
|
"loss": 4.6425,
|
|
"mean_token_accuracy": 0.25861815363168716,
|
|
"num_tokens": 13903366.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.755000591278076,
|
|
"epoch": 7.0626553953257085,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00015775431467292733,
|
|
"loss": 4.8343,
|
|
"mean_token_accuracy": 0.22791135907173157,
|
|
"num_tokens": 13912345.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.7484540939331055,
|
|
"epoch": 7.067628045748384,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00015742117432591935,
|
|
"loss": 4.8332,
|
|
"mean_token_accuracy": 0.23078036606311797,
|
|
"num_tokens": 13922670.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.635217905044556,
|
|
"epoch": 7.072600696171059,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00015708838819770922,
|
|
"loss": 4.7109,
|
|
"mean_token_accuracy": 0.24813043922185898,
|
|
"num_tokens": 13932367.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.678648185729981,
|
|
"epoch": 7.077573346593734,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000156755957290851,
|
|
"loss": 4.7532,
|
|
"mean_token_accuracy": 0.24740718305110931,
|
|
"num_tokens": 13942996.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.76995587348938,
|
|
"epoch": 7.0825459970164095,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00015642388260682816,
|
|
"loss": 4.8394,
|
|
"mean_token_accuracy": 0.23116111606359482,
|
|
"num_tokens": 13952296.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.758057975769043,
|
|
"epoch": 7.087518647439085,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00015609216514605136,
|
|
"loss": 4.8868,
|
|
"mean_token_accuracy": 0.2332200825214386,
|
|
"num_tokens": 13962169.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.757958650588989,
|
|
"epoch": 7.09249129786176,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00015576080590785503,
|
|
"loss": 4.8875,
|
|
"mean_token_accuracy": 0.22637977302074433,
|
|
"num_tokens": 13971184.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.75021710395813,
|
|
"epoch": 7.097463948284435,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00015542980589049413,
|
|
"loss": 4.9095,
|
|
"mean_token_accuracy": 0.23775167018175125,
|
|
"num_tokens": 13980379.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.675694465637207,
|
|
"epoch": 7.1024365987071105,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00015509916609114188,
|
|
"loss": 4.7675,
|
|
"mean_token_accuracy": 0.23427939116954805,
|
|
"num_tokens": 13989405.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.817636156082154,
|
|
"epoch": 7.107409249129786,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00015476888750588585,
|
|
"loss": 4.8867,
|
|
"mean_token_accuracy": 0.22982141226530076,
|
|
"num_tokens": 13998208.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.83677110671997,
|
|
"epoch": 7.112381899552461,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00015443897112972572,
|
|
"loss": 4.9518,
|
|
"mean_token_accuracy": 0.22148246467113494,
|
|
"num_tokens": 14007041.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.721876382827759,
|
|
"epoch": 7.117354549975137,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00015410941795657008,
|
|
"loss": 4.7641,
|
|
"mean_token_accuracy": 0.23933228254318237,
|
|
"num_tokens": 14017637.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.793567848205567,
|
|
"epoch": 7.122327200397812,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00015378022897923277,
|
|
"loss": 4.9274,
|
|
"mean_token_accuracy": 0.21742166429758072,
|
|
"num_tokens": 14027532.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.781089019775391,
|
|
"epoch": 7.127299850820488,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00015345140518943103,
|
|
"loss": 4.9252,
|
|
"mean_token_accuracy": 0.2219378963112831,
|
|
"num_tokens": 14037442.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.786999177932739,
|
|
"epoch": 7.132272501243163,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0001531229475777818,
|
|
"loss": 4.8744,
|
|
"mean_token_accuracy": 0.22463020384311677,
|
|
"num_tokens": 14048898.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.7417370796203615,
|
|
"epoch": 7.137245151665838,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0001527948571337986,
|
|
"loss": 4.8682,
|
|
"mean_token_accuracy": 0.22933888733386992,
|
|
"num_tokens": 14058594.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.547769451141358,
|
|
"epoch": 7.142217802088513,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0001524671348458892,
|
|
"loss": 4.6221,
|
|
"mean_token_accuracy": 0.25705876499414443,
|
|
"num_tokens": 14068254.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.763268089294433,
|
|
"epoch": 7.147190452511189,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00015213978170135187,
|
|
"loss": 4.8141,
|
|
"mean_token_accuracy": 0.23088497519493104,
|
|
"num_tokens": 14077158.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.781985092163086,
|
|
"epoch": 7.152163102933864,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00015181279868637312,
|
|
"loss": 4.8481,
|
|
"mean_token_accuracy": 0.23137861490249634,
|
|
"num_tokens": 14086737.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.839643239974976,
|
|
"epoch": 7.157135753356539,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00015148618678602433,
|
|
"loss": 4.9915,
|
|
"mean_token_accuracy": 0.22171418368816376,
|
|
"num_tokens": 14096606.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.71131739616394,
|
|
"epoch": 7.162108403779214,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00015115994698425872,
|
|
"loss": 4.8581,
|
|
"mean_token_accuracy": 0.23021993786096573,
|
|
"num_tokens": 14107125.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.7270674228668215,
|
|
"epoch": 7.16708105420189,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001508340802639087,
|
|
"loss": 4.9381,
|
|
"mean_token_accuracy": 0.22516272515058516,
|
|
"num_tokens": 14117665.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.6259815216064455,
|
|
"epoch": 7.172053704624565,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00015050858760668246,
|
|
"loss": 4.7306,
|
|
"mean_token_accuracy": 0.24744520783424379,
|
|
"num_tokens": 14128730.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.735867977142334,
|
|
"epoch": 7.17702635504724,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00015018346999316173,
|
|
"loss": 4.9027,
|
|
"mean_token_accuracy": 0.22811349034309386,
|
|
"num_tokens": 14139670.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.779388046264648,
|
|
"epoch": 7.181999005469915,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000149858728402798,
|
|
"loss": 4.8474,
|
|
"mean_token_accuracy": 0.23344215154647827,
|
|
"num_tokens": 14149308.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.729670572280884,
|
|
"epoch": 7.186971655892591,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00014953436381390998,
|
|
"loss": 4.7887,
|
|
"mean_token_accuracy": 0.24011003375053405,
|
|
"num_tokens": 14160280.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.774718141555786,
|
|
"epoch": 7.191944306315266,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00014921037720368085,
|
|
"loss": 4.964,
|
|
"mean_token_accuracy": 0.21771349906921386,
|
|
"num_tokens": 14170313.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.685129308700562,
|
|
"epoch": 7.196916956737941,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00014888676954815484,
|
|
"loss": 4.8315,
|
|
"mean_token_accuracy": 0.236543644964695,
|
|
"num_tokens": 14180418.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.745480537414551,
|
|
"epoch": 7.201889607160616,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0001485635418222347,
|
|
"loss": 4.8753,
|
|
"mean_token_accuracy": 0.22744094729423522,
|
|
"num_tokens": 14190503.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.8134355545043945,
|
|
"epoch": 7.206862257583292,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00014824069499967863,
|
|
"loss": 4.8371,
|
|
"mean_token_accuracy": 0.2292497768998146,
|
|
"num_tokens": 14200193.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.596547031402588,
|
|
"epoch": 7.211834908005967,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001479182300530971,
|
|
"loss": 4.6668,
|
|
"mean_token_accuracy": 0.25474432557821275,
|
|
"num_tokens": 14209601.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.71230182647705,
|
|
"epoch": 7.216807558428642,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00014759614795395044,
|
|
"loss": 4.7506,
|
|
"mean_token_accuracy": 0.24621475785970687,
|
|
"num_tokens": 14218966.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.723094177246094,
|
|
"epoch": 7.221780208851317,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00014727444967254527,
|
|
"loss": 4.8082,
|
|
"mean_token_accuracy": 0.2325216680765152,
|
|
"num_tokens": 14228805.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.694224548339844,
|
|
"epoch": 7.226752859273993,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0001469531361780322,
|
|
"loss": 4.8282,
|
|
"mean_token_accuracy": 0.2334984540939331,
|
|
"num_tokens": 14237719.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.678453207015991,
|
|
"epoch": 7.231725509696668,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00014663220843840266,
|
|
"loss": 4.7325,
|
|
"mean_token_accuracy": 0.24301085323095323,
|
|
"num_tokens": 14247496.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.545563125610352,
|
|
"epoch": 7.236698160119343,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001463116674204855,
|
|
"loss": 4.6559,
|
|
"mean_token_accuracy": 0.25789573043584824,
|
|
"num_tokens": 14257715.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.7328877449035645,
|
|
"epoch": 7.241670810542018,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00014599151408994503,
|
|
"loss": 4.886,
|
|
"mean_token_accuracy": 0.23336173146963118,
|
|
"num_tokens": 14267546.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.700300312042236,
|
|
"epoch": 7.246643460964695,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00014567174941127752,
|
|
"loss": 4.7459,
|
|
"mean_token_accuracy": 0.24415047019720076,
|
|
"num_tokens": 14276808.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.797729349136352,
|
|
"epoch": 7.25161611138737,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00014535237434780814,
|
|
"loss": 4.8938,
|
|
"mean_token_accuracy": 0.2287557139992714,
|
|
"num_tokens": 14286467.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.864686059951782,
|
|
"epoch": 7.256588761810045,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0001450333898616885,
|
|
"loss": 4.9681,
|
|
"mean_token_accuracy": 0.2161648079752922,
|
|
"num_tokens": 14296308.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.641185235977173,
|
|
"epoch": 7.26156141223272,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00014471479691389343,
|
|
"loss": 4.7289,
|
|
"mean_token_accuracy": 0.24300810396671296,
|
|
"num_tokens": 14307267.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.735360622406006,
|
|
"epoch": 7.266534062655396,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00014439659646421843,
|
|
"loss": 4.8954,
|
|
"mean_token_accuracy": 0.22469708174467087,
|
|
"num_tokens": 14317053.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.67605357170105,
|
|
"epoch": 7.271506713078071,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001440787894712764,
|
|
"loss": 4.8361,
|
|
"mean_token_accuracy": 0.22977325469255447,
|
|
"num_tokens": 14327123.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.737891054153442,
|
|
"epoch": 7.276479363500746,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0001437613768924948,
|
|
"loss": 4.8574,
|
|
"mean_token_accuracy": 0.2257971942424774,
|
|
"num_tokens": 14337552.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.56473708152771,
|
|
"epoch": 7.281452013923421,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00014344435968411317,
|
|
"loss": 4.6753,
|
|
"mean_token_accuracy": 0.2563610404729843,
|
|
"num_tokens": 14347692.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.801803636550903,
|
|
"epoch": 7.286424664346097,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0001431277388011796,
|
|
"loss": 4.8643,
|
|
"mean_token_accuracy": 0.22746853679418563,
|
|
"num_tokens": 14357306.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.799275827407837,
|
|
"epoch": 7.291397314768772,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00014281151519754853,
|
|
"loss": 4.8615,
|
|
"mean_token_accuracy": 0.22342442572116852,
|
|
"num_tokens": 14367914.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.840006017684937,
|
|
"epoch": 7.296369965191447,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0001424956898258774,
|
|
"loss": 5.0035,
|
|
"mean_token_accuracy": 0.2156432241201401,
|
|
"num_tokens": 14377852.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.781799173355102,
|
|
"epoch": 7.301342615614122,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00014218026363762383,
|
|
"loss": 4.878,
|
|
"mean_token_accuracy": 0.23277349025011063,
|
|
"num_tokens": 14388087.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.758423662185669,
|
|
"epoch": 7.306315266036798,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0001418652375830431,
|
|
"loss": 4.8242,
|
|
"mean_token_accuracy": 0.24161914139986038,
|
|
"num_tokens": 14399060.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.734177350997925,
|
|
"epoch": 7.311287916459473,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00014155061261118487,
|
|
"loss": 4.8313,
|
|
"mean_token_accuracy": 0.22710709124803544,
|
|
"num_tokens": 14408975.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.727807188034058,
|
|
"epoch": 7.316260566882148,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00014123638966989055,
|
|
"loss": 4.9081,
|
|
"mean_token_accuracy": 0.22185783982276916,
|
|
"num_tokens": 14418932.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.722775554656982,
|
|
"epoch": 7.321233217304823,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001409225697057904,
|
|
"loss": 4.8359,
|
|
"mean_token_accuracy": 0.2278663322329521,
|
|
"num_tokens": 14428441.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.687107181549072,
|
|
"epoch": 7.326205867727499,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0001406091536643006,
|
|
"loss": 4.7995,
|
|
"mean_token_accuracy": 0.23567714244127275,
|
|
"num_tokens": 14438849.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.732573938369751,
|
|
"epoch": 7.331178518150174,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0001402961424896206,
|
|
"loss": 4.9079,
|
|
"mean_token_accuracy": 0.22063389271497727,
|
|
"num_tokens": 14448927.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.7555759906768795,
|
|
"epoch": 7.336151168572849,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00013998353712473005,
|
|
"loss": 4.9184,
|
|
"mean_token_accuracy": 0.22731295078992844,
|
|
"num_tokens": 14458754.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.720234537124634,
|
|
"epoch": 7.341123818995524,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00013967133851138603,
|
|
"loss": 4.9149,
|
|
"mean_token_accuracy": 0.2233096331357956,
|
|
"num_tokens": 14469752.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.770171356201172,
|
|
"epoch": 7.3460964694182,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00013935954759012036,
|
|
"loss": 4.8797,
|
|
"mean_token_accuracy": 0.2236953392624855,
|
|
"num_tokens": 14479672.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.696949148178101,
|
|
"epoch": 7.351069119840875,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0001390481653002365,
|
|
"loss": 4.7626,
|
|
"mean_token_accuracy": 0.24227889329195024,
|
|
"num_tokens": 14490428.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.721937990188598,
|
|
"epoch": 7.35604177026355,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0001387371925798069,
|
|
"loss": 4.818,
|
|
"mean_token_accuracy": 0.22957019805908202,
|
|
"num_tokens": 14499736.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.732993507385254,
|
|
"epoch": 7.361014420686225,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00013842663036567026,
|
|
"loss": 4.8456,
|
|
"mean_token_accuracy": 0.23796065896749496,
|
|
"num_tokens": 14509420.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.695678949356079,
|
|
"epoch": 7.365987071108901,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00013811647959342834,
|
|
"loss": 4.8235,
|
|
"mean_token_accuracy": 0.2392924517393112,
|
|
"num_tokens": 14519994.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.674740552902222,
|
|
"epoch": 7.370959721531577,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00013780674119744375,
|
|
"loss": 4.7882,
|
|
"mean_token_accuracy": 0.2362645998597145,
|
|
"num_tokens": 14528283.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.716722726821899,
|
|
"epoch": 7.375932371954252,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0001374974161108364,
|
|
"loss": 4.8596,
|
|
"mean_token_accuracy": 0.22991252392530442,
|
|
"num_tokens": 14537612.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.743496370315552,
|
|
"epoch": 7.380905022376927,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0001371885052654812,
|
|
"loss": 4.8436,
|
|
"mean_token_accuracy": 0.23617133796215056,
|
|
"num_tokens": 14547820.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.742102241516113,
|
|
"epoch": 7.3858776727996025,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0001368800095920053,
|
|
"loss": 4.8137,
|
|
"mean_token_accuracy": 0.24058916866779329,
|
|
"num_tokens": 14557123.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.760421180725098,
|
|
"epoch": 7.390850323222278,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0001365719300197848,
|
|
"loss": 4.8357,
|
|
"mean_token_accuracy": 0.2317008674144745,
|
|
"num_tokens": 14565736.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.724656295776367,
|
|
"epoch": 7.395822973644953,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00013626426747694254,
|
|
"loss": 4.8116,
|
|
"mean_token_accuracy": 0.2294807568192482,
|
|
"num_tokens": 14575454.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.6577009677886965,
|
|
"epoch": 7.400795624067628,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00013595702289034473,
|
|
"loss": 4.7529,
|
|
"mean_token_accuracy": 0.23870905190706254,
|
|
"num_tokens": 14585041.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.717573881149292,
|
|
"epoch": 7.4057682744903035,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00013565019718559854,
|
|
"loss": 4.7784,
|
|
"mean_token_accuracy": 0.23283345252275467,
|
|
"num_tokens": 14594829.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.768716716766358,
|
|
"epoch": 7.410740924912979,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00013534379128704937,
|
|
"loss": 4.9197,
|
|
"mean_token_accuracy": 0.21996960937976837,
|
|
"num_tokens": 14605271.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.6876795291900635,
|
|
"epoch": 7.415713575335654,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00013503780611777766,
|
|
"loss": 4.7771,
|
|
"mean_token_accuracy": 0.23452734798192978,
|
|
"num_tokens": 14616002.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.866127300262451,
|
|
"epoch": 7.420686225758329,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0001347322425995966,
|
|
"loss": 4.9811,
|
|
"mean_token_accuracy": 0.22180100679397582,
|
|
"num_tokens": 14626042.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.763747978210449,
|
|
"epoch": 7.4256588761810045,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00013442710165304894,
|
|
"loss": 4.8822,
|
|
"mean_token_accuracy": 0.2291405826807022,
|
|
"num_tokens": 14636367.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.771715116500855,
|
|
"epoch": 7.43063152660368,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00013412238419740444,
|
|
"loss": 4.9259,
|
|
"mean_token_accuracy": 0.22057836800813674,
|
|
"num_tokens": 14646596.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.7516539096832275,
|
|
"epoch": 7.435604177026355,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00013381809115065716,
|
|
"loss": 4.871,
|
|
"mean_token_accuracy": 0.22592024952173234,
|
|
"num_tokens": 14656757.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.7765465259552,
|
|
"epoch": 7.44057682744903,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00013351422342952228,
|
|
"loss": 4.8835,
|
|
"mean_token_accuracy": 0.22321729212999344,
|
|
"num_tokens": 14666060.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.775210666656494,
|
|
"epoch": 7.4455494778717055,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00013321078194943392,
|
|
"loss": 4.8742,
|
|
"mean_token_accuracy": 0.23253957480192183,
|
|
"num_tokens": 14675677.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.699023723602295,
|
|
"epoch": 7.450522128294381,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0001329077676245421,
|
|
"loss": 4.77,
|
|
"mean_token_accuracy": 0.24140475392341615,
|
|
"num_tokens": 14684585.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.735626935958862,
|
|
"epoch": 7.455494778717056,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00013260518136770983,
|
|
"loss": 4.9396,
|
|
"mean_token_accuracy": 0.21906584352254868,
|
|
"num_tokens": 14694853.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.780051851272583,
|
|
"epoch": 7.460467429139731,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00013230302409051066,
|
|
"loss": 4.9428,
|
|
"mean_token_accuracy": 0.22741854935884476,
|
|
"num_tokens": 14704600.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.747225666046143,
|
|
"epoch": 7.4654400795624065,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00013200129670322563,
|
|
"loss": 4.8535,
|
|
"mean_token_accuracy": 0.23195099234580993,
|
|
"num_tokens": 14714476.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.7213667869567875,
|
|
"epoch": 7.470412729985082,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00013170000011484084,
|
|
"loss": 4.8477,
|
|
"mean_token_accuracy": 0.2290831059217453,
|
|
"num_tokens": 14723704.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.772958421707154,
|
|
"epoch": 7.475385380407757,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00013139913523304458,
|
|
"loss": 4.9391,
|
|
"mean_token_accuracy": 0.2210873156785965,
|
|
"num_tokens": 14734128.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.761407375335693,
|
|
"epoch": 7.480358030830432,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00013109870296422436,
|
|
"loss": 4.9264,
|
|
"mean_token_accuracy": 0.22870128005743026,
|
|
"num_tokens": 14743186.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.583943605422974,
|
|
"epoch": 7.4853306812531075,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00013079870421346465,
|
|
"loss": 4.6503,
|
|
"mean_token_accuracy": 0.2568370893597603,
|
|
"num_tokens": 14752315.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.740175390243531,
|
|
"epoch": 7.490303331675783,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00013049913988454385,
|
|
"loss": 4.8522,
|
|
"mean_token_accuracy": 0.22794617116451263,
|
|
"num_tokens": 14761006.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.719165325164795,
|
|
"epoch": 7.495275982098459,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00013020001087993142,
|
|
"loss": 4.8233,
|
|
"mean_token_accuracy": 0.23197283893823623,
|
|
"num_tokens": 14770685.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.69482307434082,
|
|
"epoch": 7.500248632521133,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00012990131810078565,
|
|
"loss": 4.8565,
|
|
"mean_token_accuracy": 0.22604914605617524,
|
|
"num_tokens": 14781316.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.712518358230591,
|
|
"epoch": 7.505221282943809,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00012960306244695041,
|
|
"loss": 4.8127,
|
|
"mean_token_accuracy": 0.23276252001523973,
|
|
"num_tokens": 14789877.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.596545124053955,
|
|
"epoch": 7.510193933366485,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00012930524481695278,
|
|
"loss": 4.7211,
|
|
"mean_token_accuracy": 0.24495594203472137,
|
|
"num_tokens": 14800901.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.700004529953003,
|
|
"epoch": 7.51516658378916,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00012900786610800047,
|
|
"loss": 4.8018,
|
|
"mean_token_accuracy": 0.23981088399887085,
|
|
"num_tokens": 14811055.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.700896978378296,
|
|
"epoch": 7.520139234211835,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00012871092721597832,
|
|
"loss": 4.8098,
|
|
"mean_token_accuracy": 0.22774598747491837,
|
|
"num_tokens": 14820305.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.625151991844177,
|
|
"epoch": 7.52511188463451,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00012841442903544666,
|
|
"loss": 4.7966,
|
|
"mean_token_accuracy": 0.24641194194555283,
|
|
"num_tokens": 14829746.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.723742055892944,
|
|
"epoch": 7.530084535057186,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00012811837245963817,
|
|
"loss": 4.8841,
|
|
"mean_token_accuracy": 0.22708194106817245,
|
|
"num_tokens": 14837880.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.7929483413696286,
|
|
"epoch": 7.535057185479861,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00012782275838045475,
|
|
"loss": 4.9398,
|
|
"mean_token_accuracy": 0.22057607471942903,
|
|
"num_tokens": 14848543.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.684967851638794,
|
|
"epoch": 7.540029835902536,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00012752758768846557,
|
|
"loss": 4.7693,
|
|
"mean_token_accuracy": 0.2359561324119568,
|
|
"num_tokens": 14858063.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.6443202018737795,
|
|
"epoch": 7.545002486325211,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00012723286127290387,
|
|
"loss": 4.8067,
|
|
"mean_token_accuracy": 0.23979560881853104,
|
|
"num_tokens": 14868166.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.760419273376465,
|
|
"epoch": 7.549975136747887,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00012693858002166465,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.2300698086619377,
|
|
"num_tokens": 14879315.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.81210241317749,
|
|
"epoch": 7.554947787170562,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00012664474482130145,
|
|
"loss": 4.9072,
|
|
"mean_token_accuracy": 0.22073249369859696,
|
|
"num_tokens": 14889433.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.625191116333008,
|
|
"epoch": 7.559920437593237,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00012635135655702446,
|
|
"loss": 4.729,
|
|
"mean_token_accuracy": 0.2553102493286133,
|
|
"num_tokens": 14900143.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.681385946273804,
|
|
"epoch": 7.564893088015912,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00012605841611269721,
|
|
"loss": 4.7663,
|
|
"mean_token_accuracy": 0.24420079588890076,
|
|
"num_tokens": 14910295.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.7512250423431395,
|
|
"epoch": 7.569865738438588,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001257659243708341,
|
|
"loss": 4.8302,
|
|
"mean_token_accuracy": 0.23952266275882722,
|
|
"num_tokens": 14919767.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.7695282936096195,
|
|
"epoch": 7.574838388861263,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0001254738822125978,
|
|
"loss": 4.9288,
|
|
"mean_token_accuracy": 0.22417934536933898,
|
|
"num_tokens": 14929925.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.764023399353027,
|
|
"epoch": 7.579811039283938,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00012518229051779666,
|
|
"loss": 4.8493,
|
|
"mean_token_accuracy": 0.2345461890101433,
|
|
"num_tokens": 14938765.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.735164594650269,
|
|
"epoch": 7.584783689706613,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0001248911501648817,
|
|
"loss": 4.8446,
|
|
"mean_token_accuracy": 0.23249727636575698,
|
|
"num_tokens": 14948926.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.727315998077392,
|
|
"epoch": 7.589756340129289,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00012460046203094458,
|
|
"loss": 4.8978,
|
|
"mean_token_accuracy": 0.22492721378803254,
|
|
"num_tokens": 14958841.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.736771821975708,
|
|
"epoch": 7.594728990551964,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001243102269917143,
|
|
"loss": 4.901,
|
|
"mean_token_accuracy": 0.22463118582963942,
|
|
"num_tokens": 14967973.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.76140513420105,
|
|
"epoch": 7.599701640974639,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00012402044592155497,
|
|
"loss": 4.8138,
|
|
"mean_token_accuracy": 0.23645501732826232,
|
|
"num_tokens": 14977877.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.760353374481201,
|
|
"epoch": 7.604674291397314,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00012373111969346323,
|
|
"loss": 4.8844,
|
|
"mean_token_accuracy": 0.22721491158008575,
|
|
"num_tokens": 14987943.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.79175124168396,
|
|
"epoch": 7.60964694181999,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00012344224917906516,
|
|
"loss": 4.9263,
|
|
"mean_token_accuracy": 0.2290188640356064,
|
|
"num_tokens": 14998685.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.734990739822388,
|
|
"epoch": 7.614619592242665,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0001231538352486142,
|
|
"loss": 4.8563,
|
|
"mean_token_accuracy": 0.2354977935552597,
|
|
"num_tokens": 15008258.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.740645170211792,
|
|
"epoch": 7.619592242665341,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00012286587877098808,
|
|
"loss": 4.8985,
|
|
"mean_token_accuracy": 0.22952869832515715,
|
|
"num_tokens": 15017738.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.775796747207641,
|
|
"epoch": 7.624564893088015,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00012257838061368657,
|
|
"loss": 4.9025,
|
|
"mean_token_accuracy": 0.22357654571533203,
|
|
"num_tokens": 15026834.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.658383893966675,
|
|
"epoch": 7.629537543510692,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00012229134164282884,
|
|
"loss": 4.712,
|
|
"mean_token_accuracy": 0.2462295725941658,
|
|
"num_tokens": 15036811.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.739960145950318,
|
|
"epoch": 7.634510193933367,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00012200476272315015,
|
|
"loss": 4.8733,
|
|
"mean_token_accuracy": 0.22637662887573243,
|
|
"num_tokens": 15047540.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.688639402389526,
|
|
"epoch": 7.639482844356042,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00012171864471800033,
|
|
"loss": 4.8078,
|
|
"mean_token_accuracy": 0.23129206150770187,
|
|
"num_tokens": 15056346.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.810892486572266,
|
|
"epoch": 7.644455494778717,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00012143298848934063,
|
|
"loss": 5.0029,
|
|
"mean_token_accuracy": 0.22019362896680833,
|
|
"num_tokens": 15067247.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.704875946044922,
|
|
"epoch": 7.649428145201393,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001211477948977408,
|
|
"loss": 4.8213,
|
|
"mean_token_accuracy": 0.2368731528520584,
|
|
"num_tokens": 15077468.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.7055457592010494,
|
|
"epoch": 7.654400795624068,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00012086306480237723,
|
|
"loss": 4.8596,
|
|
"mean_token_accuracy": 0.2299886792898178,
|
|
"num_tokens": 15086420.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.737376499176025,
|
|
"epoch": 7.659373446046743,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00012057879906102967,
|
|
"loss": 4.8681,
|
|
"mean_token_accuracy": 0.2301819160580635,
|
|
"num_tokens": 15096380.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.716031217575074,
|
|
"epoch": 7.664346096469418,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00012029499853007916,
|
|
"loss": 4.9103,
|
|
"mean_token_accuracy": 0.22743095606565475,
|
|
"num_tokens": 15107362.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.794512510299683,
|
|
"epoch": 7.669318746892094,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00012001166406450528,
|
|
"loss": 4.9074,
|
|
"mean_token_accuracy": 0.23198344856500625,
|
|
"num_tokens": 15117749.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.73840970993042,
|
|
"epoch": 7.674291397314769,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00011972879651788323,
|
|
"loss": 4.8666,
|
|
"mean_token_accuracy": 0.2256113499403,
|
|
"num_tokens": 15128049.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.719971466064453,
|
|
"epoch": 7.679264047737444,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00011944639674238197,
|
|
"loss": 4.9047,
|
|
"mean_token_accuracy": 0.22198701798915862,
|
|
"num_tokens": 15137998.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.7303173542022705,
|
|
"epoch": 7.684236698160119,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00011916446558876088,
|
|
"loss": 4.8149,
|
|
"mean_token_accuracy": 0.23651453405618666,
|
|
"num_tokens": 15147380.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.730715560913086,
|
|
"epoch": 7.689209348582795,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00011888300390636788,
|
|
"loss": 4.7782,
|
|
"mean_token_accuracy": 0.23462645560503007,
|
|
"num_tokens": 15155803.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.748771142959595,
|
|
"epoch": 7.69418199900547,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001186020125431364,
|
|
"loss": 4.9416,
|
|
"mean_token_accuracy": 0.21487671434879302,
|
|
"num_tokens": 15166547.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.699914836883545,
|
|
"epoch": 7.699154649428145,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00011832149234558286,
|
|
"loss": 4.8292,
|
|
"mean_token_accuracy": 0.23819921314716339,
|
|
"num_tokens": 15176949.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.65885214805603,
|
|
"epoch": 7.70412729985082,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00011804144415880445,
|
|
"loss": 4.7648,
|
|
"mean_token_accuracy": 0.2439616248011589,
|
|
"num_tokens": 15186574.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.746994733810425,
|
|
"epoch": 7.709099950273496,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00011776186882647643,
|
|
"loss": 4.8075,
|
|
"mean_token_accuracy": 0.23031618893146516,
|
|
"num_tokens": 15195626.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.71231632232666,
|
|
"epoch": 7.714072600696171,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00011748276719084924,
|
|
"loss": 4.8695,
|
|
"mean_token_accuracy": 0.23186291754245758,
|
|
"num_tokens": 15205098.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.709358644485474,
|
|
"epoch": 7.719045251118846,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0001172041400927466,
|
|
"loss": 4.8315,
|
|
"mean_token_accuracy": 0.2276723176240921,
|
|
"num_tokens": 15214780.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.592115020751953,
|
|
"epoch": 7.724017901541521,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0001169259883715623,
|
|
"loss": 4.7378,
|
|
"mean_token_accuracy": 0.2533108726143837,
|
|
"num_tokens": 15224119.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.738422632217407,
|
|
"epoch": 7.728990551964197,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0001166483128652583,
|
|
"loss": 4.8972,
|
|
"mean_token_accuracy": 0.22825340181589127,
|
|
"num_tokens": 15234795.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.8033778190612795,
|
|
"epoch": 7.733963202386872,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0001163711144103617,
|
|
"loss": 4.8876,
|
|
"mean_token_accuracy": 0.22193024009466172,
|
|
"num_tokens": 15244016.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.763039541244507,
|
|
"epoch": 7.738935852809547,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00011609439384196255,
|
|
"loss": 4.9174,
|
|
"mean_token_accuracy": 0.22202619165182114,
|
|
"num_tokens": 15253395.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.701743936538696,
|
|
"epoch": 7.743908503232223,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0001158181519937113,
|
|
"loss": 4.8656,
|
|
"mean_token_accuracy": 0.23275785595178605,
|
|
"num_tokens": 15263184.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.714768266677856,
|
|
"epoch": 7.748881153654898,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00011554238969781585,
|
|
"loss": 4.7941,
|
|
"mean_token_accuracy": 0.23873485624790192,
|
|
"num_tokens": 15273039.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.706122875213623,
|
|
"epoch": 7.753853804077574,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00011526710778503977,
|
|
"loss": 4.8426,
|
|
"mean_token_accuracy": 0.22970400303602218,
|
|
"num_tokens": 15281800.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.709101009368896,
|
|
"epoch": 7.758826454500249,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00011499230708469932,
|
|
"loss": 4.8501,
|
|
"mean_token_accuracy": 0.23359037041664124,
|
|
"num_tokens": 15291249.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.774801349639892,
|
|
"epoch": 7.763799104922924,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00011471798842466092,
|
|
"loss": 4.8881,
|
|
"mean_token_accuracy": 0.22213079631328583,
|
|
"num_tokens": 15301231.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.786993551254272,
|
|
"epoch": 7.7687717553455995,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00011444415263133905,
|
|
"loss": 4.9141,
|
|
"mean_token_accuracy": 0.22779910862445832,
|
|
"num_tokens": 15310947.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.602001953125,
|
|
"epoch": 7.773744405768275,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00011417080052969314,
|
|
"loss": 4.7,
|
|
"mean_token_accuracy": 0.24259751290082932,
|
|
"num_tokens": 15320376.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.529264736175537,
|
|
"epoch": 7.77871705619095,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00011389793294322582,
|
|
"loss": 4.5948,
|
|
"mean_token_accuracy": 0.2676339238882065,
|
|
"num_tokens": 15330268.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.659280395507812,
|
|
"epoch": 7.783689706613625,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00011362555069397988,
|
|
"loss": 4.8118,
|
|
"mean_token_accuracy": 0.2360175833106041,
|
|
"num_tokens": 15340995.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.709759330749511,
|
|
"epoch": 7.7886623570363005,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00011335365460253592,
|
|
"loss": 4.8652,
|
|
"mean_token_accuracy": 0.23542919158935546,
|
|
"num_tokens": 15350799.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.6106101989746096,
|
|
"epoch": 7.793635007458976,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00011308224548801014,
|
|
"loss": 4.703,
|
|
"mean_token_accuracy": 0.2457523986697197,
|
|
"num_tokens": 15360472.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.781686067581177,
|
|
"epoch": 7.798607657881651,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00011281132416805143,
|
|
"loss": 4.9647,
|
|
"mean_token_accuracy": 0.22128178924322128,
|
|
"num_tokens": 15370156.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.823363399505615,
|
|
"epoch": 7.803580308304326,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0001125408914588394,
|
|
"loss": 5.0062,
|
|
"mean_token_accuracy": 0.20943832993507386,
|
|
"num_tokens": 15380804.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.724689579010009,
|
|
"epoch": 7.8085529587270015,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0001122709481750814,
|
|
"loss": 4.9395,
|
|
"mean_token_accuracy": 0.2201671853661537,
|
|
"num_tokens": 15390991.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.71544246673584,
|
|
"epoch": 7.813525609149677,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0001120014951300105,
|
|
"loss": 4.7979,
|
|
"mean_token_accuracy": 0.23806399703025818,
|
|
"num_tokens": 15400199.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.735186672210693,
|
|
"epoch": 7.818498259572352,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00011173253313538284,
|
|
"loss": 4.8529,
|
|
"mean_token_accuracy": 0.22901747971773148,
|
|
"num_tokens": 15410074.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.733304882049561,
|
|
"epoch": 7.823470909995027,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001114640630014753,
|
|
"loss": 4.9112,
|
|
"mean_token_accuracy": 0.22832432836294175,
|
|
"num_tokens": 15421504.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.758359432220459,
|
|
"epoch": 7.8284435604177025,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00011119608553708277,
|
|
"loss": 4.8858,
|
|
"mean_token_accuracy": 0.22857076227664946,
|
|
"num_tokens": 15430469.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.681147813796997,
|
|
"epoch": 7.833416210840378,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00011092860154951618,
|
|
"loss": 4.8434,
|
|
"mean_token_accuracy": 0.22744334489107132,
|
|
"num_tokens": 15439690.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.784353542327881,
|
|
"epoch": 7.838388861263053,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00011066161184459954,
|
|
"loss": 4.9573,
|
|
"mean_token_accuracy": 0.2239438623189926,
|
|
"num_tokens": 15448835.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.571324586868286,
|
|
"epoch": 7.843361511685728,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00011039511722666795,
|
|
"loss": 4.5731,
|
|
"mean_token_accuracy": 0.26918807774782183,
|
|
"num_tokens": 15459124.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.769884967803955,
|
|
"epoch": 7.8483341621084035,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0001101291184985651,
|
|
"loss": 4.8294,
|
|
"mean_token_accuracy": 0.23768951296806334,
|
|
"num_tokens": 15469127.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.807385206222534,
|
|
"epoch": 7.853306812531079,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00010986361646164044,
|
|
"loss": 4.941,
|
|
"mean_token_accuracy": 0.2189931735396385,
|
|
"num_tokens": 15479039.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.786775016784668,
|
|
"epoch": 7.858279462953754,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00010959861191574746,
|
|
"loss": 4.8788,
|
|
"mean_token_accuracy": 0.23105338960886002,
|
|
"num_tokens": 15488186.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.798132276535034,
|
|
"epoch": 7.863252113376429,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00010933410565924061,
|
|
"loss": 4.8851,
|
|
"mean_token_accuracy": 0.22555664032697678,
|
|
"num_tokens": 15497560.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.7623429775238035,
|
|
"epoch": 7.868224763799105,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00010907009848897327,
|
|
"loss": 4.8904,
|
|
"mean_token_accuracy": 0.23265421390533447,
|
|
"num_tokens": 15507287.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.699031352996826,
|
|
"epoch": 7.87319741422178,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00010880659120029537,
|
|
"loss": 4.8352,
|
|
"mean_token_accuracy": 0.2299875423312187,
|
|
"num_tokens": 15516642.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.719702243804932,
|
|
"epoch": 7.878170064644456,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00010854358458705079,
|
|
"loss": 4.8924,
|
|
"mean_token_accuracy": 0.23126405775547026,
|
|
"num_tokens": 15526426.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.74426908493042,
|
|
"epoch": 7.883142715067131,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00010828107944157509,
|
|
"loss": 4.9201,
|
|
"mean_token_accuracy": 0.22250311970710754,
|
|
"num_tokens": 15535813.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.800505924224853,
|
|
"epoch": 7.888115365489806,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00010801907655469319,
|
|
"loss": 4.9372,
|
|
"mean_token_accuracy": 0.222596874833107,
|
|
"num_tokens": 15545473.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.792913484573364,
|
|
"epoch": 7.893088015912482,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00010775757671571675,
|
|
"loss": 4.9518,
|
|
"mean_token_accuracy": 0.22582974433898925,
|
|
"num_tokens": 15556059.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.707201814651489,
|
|
"epoch": 7.898060666335157,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00010749658071244211,
|
|
"loss": 4.8973,
|
|
"mean_token_accuracy": 0.22763569355010987,
|
|
"num_tokens": 15567252.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.730313777923584,
|
|
"epoch": 7.903033316757832,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00010723608933114754,
|
|
"loss": 4.8521,
|
|
"mean_token_accuracy": 0.2394305571913719,
|
|
"num_tokens": 15577158.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.681194496154785,
|
|
"epoch": 7.908005967180507,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00010697610335659139,
|
|
"loss": 4.8348,
|
|
"mean_token_accuracy": 0.23265456706285476,
|
|
"num_tokens": 15586153.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.7512345790863035,
|
|
"epoch": 7.912978617603183,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00010671662357200904,
|
|
"loss": 4.8849,
|
|
"mean_token_accuracy": 0.22589997202157974,
|
|
"num_tokens": 15594732.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.702524185180664,
|
|
"epoch": 7.917951268025858,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00010645765075911129,
|
|
"loss": 4.7842,
|
|
"mean_token_accuracy": 0.2388109192252159,
|
|
"num_tokens": 15604099.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.820755290985107,
|
|
"epoch": 7.922923918448533,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00010619918569808136,
|
|
"loss": 5.0009,
|
|
"mean_token_accuracy": 0.2150003805756569,
|
|
"num_tokens": 15614281.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.788143253326416,
|
|
"epoch": 7.927896568871208,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00010594122916757288,
|
|
"loss": 4.9301,
|
|
"mean_token_accuracy": 0.22671889513731003,
|
|
"num_tokens": 15624180.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.60467221736908,
|
|
"epoch": 7.932869219293884,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00010568378194470754,
|
|
"loss": 4.6824,
|
|
"mean_token_accuracy": 0.24197003096342087,
|
|
"num_tokens": 15633346.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.719754409790039,
|
|
"epoch": 7.937841869716559,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00010542684480507278,
|
|
"loss": 4.8034,
|
|
"mean_token_accuracy": 0.23930834829807282,
|
|
"num_tokens": 15643220.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.783296918869018,
|
|
"epoch": 7.942814520139234,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00010517041852271906,
|
|
"loss": 4.9284,
|
|
"mean_token_accuracy": 0.22589810639619828,
|
|
"num_tokens": 15653032.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.736640691757202,
|
|
"epoch": 7.947787170561909,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00010491450387015813,
|
|
"loss": 4.8893,
|
|
"mean_token_accuracy": 0.22691872715950012,
|
|
"num_tokens": 15662501.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.778686666488648,
|
|
"epoch": 7.952759820984585,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00010465910161836015,
|
|
"loss": 4.9186,
|
|
"mean_token_accuracy": 0.21416932344436646,
|
|
"num_tokens": 15671387.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"epoch": 7.952759820984585,
|
|
"eval_entropy": 5.717417826850293,
|
|
"eval_loss": 6.439521312713623,
|
|
"eval_mean_token_accuracy": 0.15227618293347447,
|
|
"eval_num_tokens": 15671387.0,
|
|
"eval_runtime": 2.5217,
|
|
"eval_samples_per_second": 1374.068,
|
|
"eval_steps_per_second": 172.105,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.728969097137451,
|
|
"epoch": 7.95773247140726,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00010440421253675184,
|
|
"loss": 4.8,
|
|
"mean_token_accuracy": 0.23675978779792786,
|
|
"num_tokens": 15679939.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.725871229171753,
|
|
"epoch": 7.962705121829935,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00010414983739321382,
|
|
"loss": 4.8438,
|
|
"mean_token_accuracy": 0.23634465485811235,
|
|
"num_tokens": 15690670.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.659476947784424,
|
|
"epoch": 7.96767777225261,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00010389597695407843,
|
|
"loss": 4.7213,
|
|
"mean_token_accuracy": 0.2445290669798851,
|
|
"num_tokens": 15700133.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.752642488479614,
|
|
"epoch": 7.972650422675286,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00010364263198412746,
|
|
"loss": 4.8406,
|
|
"mean_token_accuracy": 0.2279329091310501,
|
|
"num_tokens": 15709312.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.7528280258178714,
|
|
"epoch": 7.977623073097961,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00010338980324658972,
|
|
"loss": 4.8883,
|
|
"mean_token_accuracy": 0.22498410642147065,
|
|
"num_tokens": 15719122.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.801654720306397,
|
|
"epoch": 7.982595723520636,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00010313749150313872,
|
|
"loss": 4.9551,
|
|
"mean_token_accuracy": 0.22624436169862747,
|
|
"num_tokens": 15729710.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.732708549499511,
|
|
"epoch": 7.987568373943311,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00010288569751389082,
|
|
"loss": 4.8489,
|
|
"mean_token_accuracy": 0.23078796714544297,
|
|
"num_tokens": 15738906.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.74055438041687,
|
|
"epoch": 7.992541024365988,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00010263442203740217,
|
|
"loss": 4.8977,
|
|
"mean_token_accuracy": 0.22656267136335373,
|
|
"num_tokens": 15747647.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.747650241851806,
|
|
"epoch": 7.997513674788662,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00010238366583066713,
|
|
"loss": 4.8557,
|
|
"mean_token_accuracy": 0.22895135283470153,
|
|
"num_tokens": 15756664.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.730882220798069,
|
|
"epoch": 8.00198906016907,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00010213342964911568,
|
|
"loss": 4.7959,
|
|
"mean_token_accuracy": 0.23680547542042202,
|
|
"num_tokens": 15764754.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.752747583389282,
|
|
"epoch": 8.006961710591746,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00010188371424661095,
|
|
"loss": 4.8509,
|
|
"mean_token_accuracy": 0.22739016711711885,
|
|
"num_tokens": 15773557.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.7806439876556395,
|
|
"epoch": 8.01193436101442,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00010163452037544745,
|
|
"loss": 4.8587,
|
|
"mean_token_accuracy": 0.2273325130343437,
|
|
"num_tokens": 15782842.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.796919155120849,
|
|
"epoch": 8.016907011437096,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0001013858487863483,
|
|
"loss": 4.7812,
|
|
"mean_token_accuracy": 0.2307664558291435,
|
|
"num_tokens": 15792334.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.802726793289184,
|
|
"epoch": 8.02187966185977,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0001011377002284633,
|
|
"loss": 4.8084,
|
|
"mean_token_accuracy": 0.23744147419929504,
|
|
"num_tokens": 15800520.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.778570938110351,
|
|
"epoch": 8.026852312282447,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00010089007544936666,
|
|
"loss": 4.8785,
|
|
"mean_token_accuracy": 0.22033599615097046,
|
|
"num_tokens": 15810399.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.556277322769165,
|
|
"epoch": 8.031824962705121,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00010064297519505435,
|
|
"loss": 4.4759,
|
|
"mean_token_accuracy": 0.2682065322995186,
|
|
"num_tokens": 15820215.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.835760402679443,
|
|
"epoch": 8.036797613127797,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00010039640020994241,
|
|
"loss": 4.8369,
|
|
"mean_token_accuracy": 0.2270744875073433,
|
|
"num_tokens": 15830187.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.568360424041748,
|
|
"epoch": 8.041770263550472,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00010015035123686443,
|
|
"loss": 4.6542,
|
|
"mean_token_accuracy": 0.2539273127913475,
|
|
"num_tokens": 15840423.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.756316041946411,
|
|
"epoch": 8.046742913973148,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 9.990482901706918e-05,
|
|
"loss": 4.8017,
|
|
"mean_token_accuracy": 0.2342333734035492,
|
|
"num_tokens": 15849700.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.741629219055175,
|
|
"epoch": 8.051715564395822,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 9.965983429021874e-05,
|
|
"loss": 4.8454,
|
|
"mean_token_accuracy": 0.22734299004077912,
|
|
"num_tokens": 15860149.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.600561141967773,
|
|
"epoch": 8.056688214818498,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 9.941536779438584e-05,
|
|
"loss": 4.6204,
|
|
"mean_token_accuracy": 0.2573744416236877,
|
|
"num_tokens": 15870073.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.7596128463745115,
|
|
"epoch": 8.061660865241173,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 9.917143026605201e-05,
|
|
"loss": 4.8215,
|
|
"mean_token_accuracy": 0.23437779843807222,
|
|
"num_tokens": 15881145.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.757026243209839,
|
|
"epoch": 8.066633515663849,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 9.892802244010522e-05,
|
|
"loss": 4.7875,
|
|
"mean_token_accuracy": 0.23902373015880585,
|
|
"num_tokens": 15892588.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.728650856018066,
|
|
"epoch": 8.071606166086523,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 9.86851450498375e-05,
|
|
"loss": 4.7424,
|
|
"mean_token_accuracy": 0.2447783023118973,
|
|
"num_tokens": 15902846.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.771076250076294,
|
|
"epoch": 8.0765788165092,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 9.844279882694309e-05,
|
|
"loss": 4.8272,
|
|
"mean_token_accuracy": 0.22988823652267457,
|
|
"num_tokens": 15912987.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.733744478225708,
|
|
"epoch": 8.081551466931876,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 9.820098450151582e-05,
|
|
"loss": 4.708,
|
|
"mean_token_accuracy": 0.24361601769924163,
|
|
"num_tokens": 15922808.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.740266799926758,
|
|
"epoch": 8.08652411735455,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 9.795970280204733e-05,
|
|
"loss": 4.7738,
|
|
"mean_token_accuracy": 0.2359317272901535,
|
|
"num_tokens": 15931807.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.759758710861206,
|
|
"epoch": 8.091496767777226,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 9.771895445542453e-05,
|
|
"loss": 4.7976,
|
|
"mean_token_accuracy": 0.23183262795209886,
|
|
"num_tokens": 15941755.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.713161277770996,
|
|
"epoch": 8.0964694181999,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 9.747874018692752e-05,
|
|
"loss": 4.785,
|
|
"mean_token_accuracy": 0.23868806958198546,
|
|
"num_tokens": 15950112.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.797889184951782,
|
|
"epoch": 8.101442068622577,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 9.723906072022759e-05,
|
|
"loss": 4.8108,
|
|
"mean_token_accuracy": 0.2302407890558243,
|
|
"num_tokens": 15959342.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.699204444885254,
|
|
"epoch": 8.106414719045251,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 9.69999167773847e-05,
|
|
"loss": 4.7049,
|
|
"mean_token_accuracy": 0.24687332212924956,
|
|
"num_tokens": 15968630.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.775094127655029,
|
|
"epoch": 8.111387369467927,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 9.676130907884564e-05,
|
|
"loss": 4.8802,
|
|
"mean_token_accuracy": 0.23582212626934052,
|
|
"num_tokens": 15978634.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.676481771469116,
|
|
"epoch": 8.116360019890601,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 9.652323834344166e-05,
|
|
"loss": 4.7341,
|
|
"mean_token_accuracy": 0.23957301378250123,
|
|
"num_tokens": 15989450.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.7566145896911625,
|
|
"epoch": 8.121332670313278,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 9.628570528838626e-05,
|
|
"loss": 4.7693,
|
|
"mean_token_accuracy": 0.23393630087375641,
|
|
"num_tokens": 15998575.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.720115375518799,
|
|
"epoch": 8.126305320735952,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 9.604871062927328e-05,
|
|
"loss": 4.7398,
|
|
"mean_token_accuracy": 0.24635081738233566,
|
|
"num_tokens": 16007756.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.716300582885742,
|
|
"epoch": 8.131277971158628,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 9.581225508007441e-05,
|
|
"loss": 4.7413,
|
|
"mean_token_accuracy": 0.23346025496721268,
|
|
"num_tokens": 16017274.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.71357159614563,
|
|
"epoch": 8.136250621581302,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 9.557633935313731e-05,
|
|
"loss": 4.8379,
|
|
"mean_token_accuracy": 0.236208912730217,
|
|
"num_tokens": 16027492.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.745103120803833,
|
|
"epoch": 8.141223272003979,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 9.534096415918354e-05,
|
|
"loss": 4.8058,
|
|
"mean_token_accuracy": 0.23754797875881195,
|
|
"num_tokens": 16036657.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.7416908740997314,
|
|
"epoch": 8.146195922426653,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 9.51061302073058e-05,
|
|
"loss": 4.8357,
|
|
"mean_token_accuracy": 0.23138444125652313,
|
|
"num_tokens": 16047003.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.669106817245483,
|
|
"epoch": 8.151168572849329,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 9.487183820496664e-05,
|
|
"loss": 4.6924,
|
|
"mean_token_accuracy": 0.24440116286277772,
|
|
"num_tokens": 16056613.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.559702396392822,
|
|
"epoch": 8.156141223272003,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 9.463808885799582e-05,
|
|
"loss": 4.6173,
|
|
"mean_token_accuracy": 0.2573344990611076,
|
|
"num_tokens": 16066121.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.575288534164429,
|
|
"epoch": 8.16111387369468,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 9.440488287058819e-05,
|
|
"loss": 4.5535,
|
|
"mean_token_accuracy": 0.25739071518182755,
|
|
"num_tokens": 16076644.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.762288665771484,
|
|
"epoch": 8.166086524117354,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 9.417222094530181e-05,
|
|
"loss": 4.8027,
|
|
"mean_token_accuracy": 0.2251436486840248,
|
|
"num_tokens": 16085384.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.758998966217041,
|
|
"epoch": 8.17105917454003,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 9.39401037830556e-05,
|
|
"loss": 4.8163,
|
|
"mean_token_accuracy": 0.22983629405498504,
|
|
"num_tokens": 16094669.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.7753016471862795,
|
|
"epoch": 8.176031824962704,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 9.370853208312732e-05,
|
|
"loss": 4.8006,
|
|
"mean_token_accuracy": 0.23429126143455506,
|
|
"num_tokens": 16104756.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.766112422943115,
|
|
"epoch": 8.18100447538538,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 9.347750654315165e-05,
|
|
"loss": 4.8424,
|
|
"mean_token_accuracy": 0.2342137351632118,
|
|
"num_tokens": 16114103.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.720001840591431,
|
|
"epoch": 8.185977125808055,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 9.324702785911762e-05,
|
|
"loss": 4.7413,
|
|
"mean_token_accuracy": 0.23616638630628586,
|
|
"num_tokens": 16123362.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.565114116668701,
|
|
"epoch": 8.190949776230731,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 9.301709672536701e-05,
|
|
"loss": 4.6215,
|
|
"mean_token_accuracy": 0.25148549377918245,
|
|
"num_tokens": 16132296.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.700975370407105,
|
|
"epoch": 8.195922426653405,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 9.278771383459189e-05,
|
|
"loss": 4.8091,
|
|
"mean_token_accuracy": 0.2355460062623024,
|
|
"num_tokens": 16141871.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.745033025741577,
|
|
"epoch": 8.200895077076082,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 9.255887987783287e-05,
|
|
"loss": 4.8486,
|
|
"mean_token_accuracy": 0.23444511890411376,
|
|
"num_tokens": 16151514.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.734634590148926,
|
|
"epoch": 8.205867727498758,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 9.233059554447674e-05,
|
|
"loss": 4.7713,
|
|
"mean_token_accuracy": 0.238850237429142,
|
|
"num_tokens": 16160993.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.70439658164978,
|
|
"epoch": 8.210840377921432,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 9.210286152225433e-05,
|
|
"loss": 4.725,
|
|
"mean_token_accuracy": 0.24955628514289857,
|
|
"num_tokens": 16170444.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.771754360198974,
|
|
"epoch": 8.215813028344108,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 9.187567849723889e-05,
|
|
"loss": 4.8701,
|
|
"mean_token_accuracy": 0.2201365515589714,
|
|
"num_tokens": 16180137.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.48816237449646,
|
|
"epoch": 8.220785678766783,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 9.164904715384363e-05,
|
|
"loss": 4.5188,
|
|
"mean_token_accuracy": 0.2725518062710762,
|
|
"num_tokens": 16189536.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.49136962890625,
|
|
"epoch": 8.225758329189459,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 9.142296817481963e-05,
|
|
"loss": 4.4935,
|
|
"mean_token_accuracy": 0.278119845688343,
|
|
"num_tokens": 16199762.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.721905851364136,
|
|
"epoch": 8.230730979612133,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 9.11974422412541e-05,
|
|
"loss": 4.7615,
|
|
"mean_token_accuracy": 0.24390091896057128,
|
|
"num_tokens": 16209284.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.696897172927857,
|
|
"epoch": 8.23570363003481,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 9.097247003256801e-05,
|
|
"loss": 4.6744,
|
|
"mean_token_accuracy": 0.24602424055337907,
|
|
"num_tokens": 16219150.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.705034494400024,
|
|
"epoch": 8.240676280457484,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 9.074805222651418e-05,
|
|
"loss": 4.6953,
|
|
"mean_token_accuracy": 0.24978252947330476,
|
|
"num_tokens": 16228624.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.780733680725097,
|
|
"epoch": 8.24564893088016,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 9.052418949917543e-05,
|
|
"loss": 4.8379,
|
|
"mean_token_accuracy": 0.22981504648923873,
|
|
"num_tokens": 16238274.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.726059198379517,
|
|
"epoch": 8.250621581302834,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 9.030088252496199e-05,
|
|
"loss": 4.8337,
|
|
"mean_token_accuracy": 0.23175521343946456,
|
|
"num_tokens": 16247303.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.6526741027832035,
|
|
"epoch": 8.25559423172551,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 9.007813197661016e-05,
|
|
"loss": 4.6207,
|
|
"mean_token_accuracy": 0.26014442592859266,
|
|
"num_tokens": 16257324.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.672706031799317,
|
|
"epoch": 8.260566882148185,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 8.985593852517979e-05,
|
|
"loss": 4.7285,
|
|
"mean_token_accuracy": 0.24472035318613053,
|
|
"num_tokens": 16267784.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.682960891723633,
|
|
"epoch": 8.26553953257086,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 8.963430284005235e-05,
|
|
"loss": 4.6936,
|
|
"mean_token_accuracy": 0.2424460083246231,
|
|
"num_tokens": 16277706.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.60527491569519,
|
|
"epoch": 8.270512182993535,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 8.941322558892918e-05,
|
|
"loss": 4.6688,
|
|
"mean_token_accuracy": 0.24925828129053115,
|
|
"num_tokens": 16288389.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.739186716079712,
|
|
"epoch": 8.275484833416211,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 8.919270743782903e-05,
|
|
"loss": 4.8452,
|
|
"mean_token_accuracy": 0.22890521436929703,
|
|
"num_tokens": 16298343.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.761815929412842,
|
|
"epoch": 8.280457483838886,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 8.897274905108653e-05,
|
|
"loss": 4.8138,
|
|
"mean_token_accuracy": 0.2300345256924629,
|
|
"num_tokens": 16307547.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.726864147186279,
|
|
"epoch": 8.285430134261562,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 8.87533510913499e-05,
|
|
"loss": 4.7999,
|
|
"mean_token_accuracy": 0.2323715940117836,
|
|
"num_tokens": 16317378.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.718853187561035,
|
|
"epoch": 8.290402784684236,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 8.853451421957887e-05,
|
|
"loss": 4.7118,
|
|
"mean_token_accuracy": 0.24629787355661392,
|
|
"num_tokens": 16327085.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.719252490997315,
|
|
"epoch": 8.295375435106912,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 8.831623909504304e-05,
|
|
"loss": 4.8182,
|
|
"mean_token_accuracy": 0.2361117571592331,
|
|
"num_tokens": 16337401.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.720012521743774,
|
|
"epoch": 8.300348085529587,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 8.809852637531951e-05,
|
|
"loss": 4.8034,
|
|
"mean_token_accuracy": 0.23400144875049592,
|
|
"num_tokens": 16347141.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.738323116302491,
|
|
"epoch": 8.305320735952263,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 8.788137671629121e-05,
|
|
"loss": 4.8069,
|
|
"mean_token_accuracy": 0.23786402344703675,
|
|
"num_tokens": 16356418.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.53735318183899,
|
|
"epoch": 8.310293386374937,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 8.766479077214466e-05,
|
|
"loss": 4.4636,
|
|
"mean_token_accuracy": 0.2721980720758438,
|
|
"num_tokens": 16365218.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.72739577293396,
|
|
"epoch": 8.315266036797613,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 8.744876919536832e-05,
|
|
"loss": 4.8548,
|
|
"mean_token_accuracy": 0.235097835958004,
|
|
"num_tokens": 16374764.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.70956449508667,
|
|
"epoch": 8.320238687220288,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 8.723331263675021e-05,
|
|
"loss": 4.7666,
|
|
"mean_token_accuracy": 0.23722241967916488,
|
|
"num_tokens": 16383797.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.72767391204834,
|
|
"epoch": 8.325211337642964,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 8.701842174537627e-05,
|
|
"loss": 4.7838,
|
|
"mean_token_accuracy": 0.23625009655952453,
|
|
"num_tokens": 16394349.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.745525789260864,
|
|
"epoch": 8.330183988065638,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 8.680409716862833e-05,
|
|
"loss": 4.7663,
|
|
"mean_token_accuracy": 0.23664241284132004,
|
|
"num_tokens": 16404890.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.667834663391114,
|
|
"epoch": 8.335156638488314,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 8.659033955218221e-05,
|
|
"loss": 4.6832,
|
|
"mean_token_accuracy": 0.24880923479795455,
|
|
"num_tokens": 16414943.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.67570858001709,
|
|
"epoch": 8.34012928891099,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 8.637714954000548e-05,
|
|
"loss": 4.6805,
|
|
"mean_token_accuracy": 0.24686645865440368,
|
|
"num_tokens": 16425578.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.595616674423217,
|
|
"epoch": 8.345101939333665,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 8.616452777435597e-05,
|
|
"loss": 4.6327,
|
|
"mean_token_accuracy": 0.2616020947694778,
|
|
"num_tokens": 16436376.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.7232677936553955,
|
|
"epoch": 8.35007458975634,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 8.595247489577939e-05,
|
|
"loss": 4.7507,
|
|
"mean_token_accuracy": 0.23954382836818694,
|
|
"num_tokens": 16445708.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.778854846954346,
|
|
"epoch": 8.355047240179015,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 8.574099154310782e-05,
|
|
"loss": 4.8903,
|
|
"mean_token_accuracy": 0.22840150743722915,
|
|
"num_tokens": 16456306.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.708134889602661,
|
|
"epoch": 8.360019890601691,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 8.553007835345755e-05,
|
|
"loss": 4.7612,
|
|
"mean_token_accuracy": 0.237241630256176,
|
|
"num_tokens": 16465579.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.791517210006714,
|
|
"epoch": 8.364992541024366,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 8.531973596222701e-05,
|
|
"loss": 4.8749,
|
|
"mean_token_accuracy": 0.22705305218696595,
|
|
"num_tokens": 16476050.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.786006307601928,
|
|
"epoch": 8.369965191447042,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 8.510996500309531e-05,
|
|
"loss": 4.8666,
|
|
"mean_token_accuracy": 0.2293496087193489,
|
|
"num_tokens": 16485745.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.75560359954834,
|
|
"epoch": 8.374937841869716,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 8.490076610801983e-05,
|
|
"loss": 4.7788,
|
|
"mean_token_accuracy": 0.2356301426887512,
|
|
"num_tokens": 16495121.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.725343799591064,
|
|
"epoch": 8.379910492292392,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 8.46921399072346e-05,
|
|
"loss": 4.8054,
|
|
"mean_token_accuracy": 0.24354963451623918,
|
|
"num_tokens": 16505782.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.755490732192993,
|
|
"epoch": 8.384883142715067,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 8.448408702924846e-05,
|
|
"loss": 4.8507,
|
|
"mean_token_accuracy": 0.2311719387769699,
|
|
"num_tokens": 16516068.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.586347913742065,
|
|
"epoch": 8.389855793137743,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 8.427660810084292e-05,
|
|
"loss": 4.6217,
|
|
"mean_token_accuracy": 0.26007543355226515,
|
|
"num_tokens": 16525809.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.736499452590943,
|
|
"epoch": 8.394828443560417,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 8.406970374707048e-05,
|
|
"loss": 4.7817,
|
|
"mean_token_accuracy": 0.23666399270296096,
|
|
"num_tokens": 16535823.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.701454210281372,
|
|
"epoch": 8.399801093983093,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 8.386337459125268e-05,
|
|
"loss": 4.8077,
|
|
"mean_token_accuracy": 0.23132889866828918,
|
|
"num_tokens": 16545889.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.593937540054322,
|
|
"epoch": 8.404773744405768,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 8.365762125497814e-05,
|
|
"loss": 4.6968,
|
|
"mean_token_accuracy": 0.24803219586610795,
|
|
"num_tokens": 16555945.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.708326148986816,
|
|
"epoch": 8.409746394828444,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 8.345244435810084e-05,
|
|
"loss": 4.7499,
|
|
"mean_token_accuracy": 0.23687490522861482,
|
|
"num_tokens": 16566417.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.584909868240357,
|
|
"epoch": 8.414719045251118,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 8.324784451873813e-05,
|
|
"loss": 4.5272,
|
|
"mean_token_accuracy": 0.26318762004375457,
|
|
"num_tokens": 16576524.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.696503734588623,
|
|
"epoch": 8.419691695673794,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 8.304382235326893e-05,
|
|
"loss": 4.7867,
|
|
"mean_token_accuracy": 0.2308330073952675,
|
|
"num_tokens": 16586512.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.722277736663818,
|
|
"epoch": 8.424664346096469,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 8.284037847633189e-05,
|
|
"loss": 4.8119,
|
|
"mean_token_accuracy": 0.23630050271749498,
|
|
"num_tokens": 16596866.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.731408023834229,
|
|
"epoch": 8.429636996519145,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 8.263751350082345e-05,
|
|
"loss": 4.7951,
|
|
"mean_token_accuracy": 0.23633018583059312,
|
|
"num_tokens": 16606506.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.731103563308716,
|
|
"epoch": 8.43460964694182,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 8.243522803789597e-05,
|
|
"loss": 4.7859,
|
|
"mean_token_accuracy": 0.23674667477607728,
|
|
"num_tokens": 16615836.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.752928352355957,
|
|
"epoch": 8.439582297364495,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 8.22335226969562e-05,
|
|
"loss": 4.8069,
|
|
"mean_token_accuracy": 0.23885927498340606,
|
|
"num_tokens": 16624601.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.605139112472534,
|
|
"epoch": 8.44455494778717,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 8.203239808566296e-05,
|
|
"loss": 4.6133,
|
|
"mean_token_accuracy": 0.25350956320762635,
|
|
"num_tokens": 16635389.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.780992841720581,
|
|
"epoch": 8.449527598209846,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 8.183185480992575e-05,
|
|
"loss": 4.9227,
|
|
"mean_token_accuracy": 0.2185651555657387,
|
|
"num_tokens": 16645944.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.78912935256958,
|
|
"epoch": 8.45450024863252,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 8.163189347390259e-05,
|
|
"loss": 4.9016,
|
|
"mean_token_accuracy": 0.21839455962181092,
|
|
"num_tokens": 16656416.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.726716804504394,
|
|
"epoch": 8.459472899055196,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 8.14325146799984e-05,
|
|
"loss": 4.7873,
|
|
"mean_token_accuracy": 0.23960964381694794,
|
|
"num_tokens": 16667932.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.729405689239502,
|
|
"epoch": 8.464445549477873,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 8.123371902886325e-05,
|
|
"loss": 4.9031,
|
|
"mean_token_accuracy": 0.22100209444761276,
|
|
"num_tokens": 16678769.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.6814604759216305,
|
|
"epoch": 8.469418199900547,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 8.103550711939018e-05,
|
|
"loss": 4.7482,
|
|
"mean_token_accuracy": 0.2370753213763237,
|
|
"num_tokens": 16688548.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.730917930603027,
|
|
"epoch": 8.474390850323223,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 8.08378795487139e-05,
|
|
"loss": 4.7866,
|
|
"mean_token_accuracy": 0.2388346165418625,
|
|
"num_tokens": 16698670.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.744521951675415,
|
|
"epoch": 8.479363500745897,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 8.064083691220852e-05,
|
|
"loss": 4.7593,
|
|
"mean_token_accuracy": 0.2434059277176857,
|
|
"num_tokens": 16708450.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.794715738296508,
|
|
"epoch": 8.484336151168574,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 8.044437980348619e-05,
|
|
"loss": 4.8437,
|
|
"mean_token_accuracy": 0.23510998636484146,
|
|
"num_tokens": 16718124.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.6059211730957035,
|
|
"epoch": 8.489308801591248,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 8.02485088143949e-05,
|
|
"loss": 4.6762,
|
|
"mean_token_accuracy": 0.24815888702869415,
|
|
"num_tokens": 16728919.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.7134621143341064,
|
|
"epoch": 8.494281452013924,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 8.005322453501692e-05,
|
|
"loss": 4.7574,
|
|
"mean_token_accuracy": 0.24111118763685227,
|
|
"num_tokens": 16738365.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.6753997802734375,
|
|
"epoch": 8.499254102436598,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 7.985852755366717e-05,
|
|
"loss": 4.6448,
|
|
"mean_token_accuracy": 0.2552033543586731,
|
|
"num_tokens": 16747158.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.696539878845215,
|
|
"epoch": 8.504226752859275,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 7.966441845689102e-05,
|
|
"loss": 4.7066,
|
|
"mean_token_accuracy": 0.24329676777124404,
|
|
"num_tokens": 16755636.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.783658695220947,
|
|
"epoch": 8.509199403281949,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 7.947089782946295e-05,
|
|
"loss": 4.9289,
|
|
"mean_token_accuracy": 0.2208818957209587,
|
|
"num_tokens": 16764932.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.772493600845337,
|
|
"epoch": 8.514172053704625,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 7.927796625438466e-05,
|
|
"loss": 4.748,
|
|
"mean_token_accuracy": 0.245768304169178,
|
|
"num_tokens": 16776889.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.640512084960937,
|
|
"epoch": 8.5191447041273,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 7.908562431288303e-05,
|
|
"loss": 4.7308,
|
|
"mean_token_accuracy": 0.2482721298933029,
|
|
"num_tokens": 16787855.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.7675714015960695,
|
|
"epoch": 8.524117354549976,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 7.889387258440884e-05,
|
|
"loss": 4.8053,
|
|
"mean_token_accuracy": 0.2350132793188095,
|
|
"num_tokens": 16796907.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.767992305755615,
|
|
"epoch": 8.52909000497265,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 7.870271164663463e-05,
|
|
"loss": 4.8009,
|
|
"mean_token_accuracy": 0.2359689623117447,
|
|
"num_tokens": 16806778.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.750254201889038,
|
|
"epoch": 8.534062655395326,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 7.851214207545322e-05,
|
|
"loss": 4.8695,
|
|
"mean_token_accuracy": 0.23341114521026612,
|
|
"num_tokens": 16816249.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.760043096542359,
|
|
"epoch": 8.539035305818,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 7.832216444497589e-05,
|
|
"loss": 4.8492,
|
|
"mean_token_accuracy": 0.23117787539958953,
|
|
"num_tokens": 16825726.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.739851284027099,
|
|
"epoch": 8.544007956240677,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 7.813277932753053e-05,
|
|
"loss": 4.8246,
|
|
"mean_token_accuracy": 0.23417348861694337,
|
|
"num_tokens": 16834833.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.737803363800049,
|
|
"epoch": 8.548980606663351,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 7.794398729366006e-05,
|
|
"loss": 4.7621,
|
|
"mean_token_accuracy": 0.23915400803089143,
|
|
"num_tokens": 16843414.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.813129043579101,
|
|
"epoch": 8.553953257086027,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 7.775578891212076e-05,
|
|
"loss": 4.8619,
|
|
"mean_token_accuracy": 0.22570784389972687,
|
|
"num_tokens": 16853602.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.717645215988159,
|
|
"epoch": 8.558925907508701,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 7.75681847498803e-05,
|
|
"loss": 4.7718,
|
|
"mean_token_accuracy": 0.2355202928185463,
|
|
"num_tokens": 16862845.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.7198278427124025,
|
|
"epoch": 8.563898557931378,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 7.73811753721164e-05,
|
|
"loss": 4.7442,
|
|
"mean_token_accuracy": 0.24223233610391617,
|
|
"num_tokens": 16872475.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.698551416397095,
|
|
"epoch": 8.568871208354052,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 7.719476134221474e-05,
|
|
"loss": 4.7423,
|
|
"mean_token_accuracy": 0.24738284200429916,
|
|
"num_tokens": 16882161.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.715541553497315,
|
|
"epoch": 8.573843858776728,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 7.70089432217676e-05,
|
|
"loss": 4.7114,
|
|
"mean_token_accuracy": 0.2534330889582634,
|
|
"num_tokens": 16891607.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.738381433486938,
|
|
"epoch": 8.578816509199402,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 7.682372157057196e-05,
|
|
"loss": 4.7707,
|
|
"mean_token_accuracy": 0.24262476414442063,
|
|
"num_tokens": 16900750.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.735481595993042,
|
|
"epoch": 8.583789159622079,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 7.663909694662783e-05,
|
|
"loss": 4.8048,
|
|
"mean_token_accuracy": 0.23080447018146516,
|
|
"num_tokens": 16910441.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.709149312973023,
|
|
"epoch": 8.588761810044755,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 7.64550699061367e-05,
|
|
"loss": 4.7638,
|
|
"mean_token_accuracy": 0.23974299132823945,
|
|
"num_tokens": 16919331.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.697609901428223,
|
|
"epoch": 8.593734460467429,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 7.627164100349967e-05,
|
|
"loss": 4.8075,
|
|
"mean_token_accuracy": 0.2323400691151619,
|
|
"num_tokens": 16930401.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.80483832359314,
|
|
"epoch": 8.598707110890105,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 7.608881079131604e-05,
|
|
"loss": 4.803,
|
|
"mean_token_accuracy": 0.2281631514430046,
|
|
"num_tokens": 16939552.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.67511100769043,
|
|
"epoch": 8.60367976131278,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 7.59065798203813e-05,
|
|
"loss": 4.7491,
|
|
"mean_token_accuracy": 0.2421405404806137,
|
|
"num_tokens": 16950022.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.644327116012573,
|
|
"epoch": 8.608652411735456,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 7.572494863968573e-05,
|
|
"loss": 4.6736,
|
|
"mean_token_accuracy": 0.25319394171237947,
|
|
"num_tokens": 16959583.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.6025361061096195,
|
|
"epoch": 8.61362506215813,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 7.55439177964128e-05,
|
|
"loss": 4.59,
|
|
"mean_token_accuracy": 0.2527657762169838,
|
|
"num_tokens": 16968541.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.570887565612793,
|
|
"epoch": 8.618597712580806,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 7.536348783593727e-05,
|
|
"loss": 4.612,
|
|
"mean_token_accuracy": 0.25698366165161135,
|
|
"num_tokens": 16978131.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.785293674468994,
|
|
"epoch": 8.62357036300348,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 7.518365930182368e-05,
|
|
"loss": 4.8499,
|
|
"mean_token_accuracy": 0.23294481933116912,
|
|
"num_tokens": 16989160.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.773700904846192,
|
|
"epoch": 8.628543013426157,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 7.500443273582478e-05,
|
|
"loss": 4.7841,
|
|
"mean_token_accuracy": 0.24077625721693038,
|
|
"num_tokens": 16998771.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.7599937915802,
|
|
"epoch": 8.633515663848831,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 7.482580867787974e-05,
|
|
"loss": 4.7649,
|
|
"mean_token_accuracy": 0.23643879294395448,
|
|
"num_tokens": 17007278.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.599241447448731,
|
|
"epoch": 8.638488314271507,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 7.464778766611266e-05,
|
|
"loss": 4.6137,
|
|
"mean_token_accuracy": 0.25089529901742935,
|
|
"num_tokens": 17018472.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.791153335571289,
|
|
"epoch": 8.643460964694182,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 7.447037023683095e-05,
|
|
"loss": 4.8314,
|
|
"mean_token_accuracy": 0.23184745013713837,
|
|
"num_tokens": 17028542.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.731298160552979,
|
|
"epoch": 8.648433615116858,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 7.429355692452355e-05,
|
|
"loss": 4.7715,
|
|
"mean_token_accuracy": 0.23871765434741973,
|
|
"num_tokens": 17037226.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.706887483596802,
|
|
"epoch": 8.653406265539532,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 7.411734826185953e-05,
|
|
"loss": 4.8473,
|
|
"mean_token_accuracy": 0.23052672743797303,
|
|
"num_tokens": 17046949.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.735724210739136,
|
|
"epoch": 8.658378915962208,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 7.394174477968632e-05,
|
|
"loss": 4.837,
|
|
"mean_token_accuracy": 0.24141440391540528,
|
|
"num_tokens": 17056753.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.732375907897949,
|
|
"epoch": 8.663351566384883,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 7.376674700702817e-05,
|
|
"loss": 4.7591,
|
|
"mean_token_accuracy": 0.24048995077610016,
|
|
"num_tokens": 17065859.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.809988260269165,
|
|
"epoch": 8.668324216807559,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 7.359235547108469e-05,
|
|
"loss": 4.837,
|
|
"mean_token_accuracy": 0.23623433709144592,
|
|
"num_tokens": 17075699.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.780055809020996,
|
|
"epoch": 8.673296867230233,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 7.341857069722897e-05,
|
|
"loss": 4.8205,
|
|
"mean_token_accuracy": 0.23592175990343095,
|
|
"num_tokens": 17085813.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.695162677764893,
|
|
"epoch": 8.67826951765291,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 7.324539320900632e-05,
|
|
"loss": 4.7195,
|
|
"mean_token_accuracy": 0.24415085166692735,
|
|
"num_tokens": 17095641.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.81505184173584,
|
|
"epoch": 8.683242168075584,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 7.307282352813237e-05,
|
|
"loss": 4.869,
|
|
"mean_token_accuracy": 0.2307497590780258,
|
|
"num_tokens": 17105776.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.789739656448364,
|
|
"epoch": 8.68821481849826,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 7.290086217449176e-05,
|
|
"loss": 4.8581,
|
|
"mean_token_accuracy": 0.22984296977519988,
|
|
"num_tokens": 17115157.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.7390885829925535,
|
|
"epoch": 8.693187468920934,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 7.272950966613659e-05,
|
|
"loss": 4.7789,
|
|
"mean_token_accuracy": 0.2344265967607498,
|
|
"num_tokens": 17124560.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.685404062271118,
|
|
"epoch": 8.69816011934361,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 7.255876651928453e-05,
|
|
"loss": 4.6988,
|
|
"mean_token_accuracy": 0.23923380821943283,
|
|
"num_tokens": 17134235.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.567207288742066,
|
|
"epoch": 8.703132769766285,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 7.238863324831762e-05,
|
|
"loss": 4.6399,
|
|
"mean_token_accuracy": 0.2596493050456047,
|
|
"num_tokens": 17143888.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.711487293243408,
|
|
"epoch": 8.70810542018896,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 7.221911036578053e-05,
|
|
"loss": 4.7298,
|
|
"mean_token_accuracy": 0.24962712228298187,
|
|
"num_tokens": 17152766.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.723424863815308,
|
|
"epoch": 8.713078070611637,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 7.205019838237916e-05,
|
|
"loss": 4.7915,
|
|
"mean_token_accuracy": 0.23386561274528503,
|
|
"num_tokens": 17162489.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.802021074295044,
|
|
"epoch": 8.718050721034311,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 7.188189780697885e-05,
|
|
"loss": 4.8551,
|
|
"mean_token_accuracy": 0.23297793865203859,
|
|
"num_tokens": 17172976.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.672204828262329,
|
|
"epoch": 8.723023371456987,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 7.171420914660308e-05,
|
|
"loss": 4.7395,
|
|
"mean_token_accuracy": 0.2359535351395607,
|
|
"num_tokens": 17182687.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.773297643661499,
|
|
"epoch": 8.727996021879662,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 7.154713290643195e-05,
|
|
"loss": 4.7375,
|
|
"mean_token_accuracy": 0.24126501977443696,
|
|
"num_tokens": 17192354.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.616232919692993,
|
|
"epoch": 8.732968672302338,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 7.13806695898006e-05,
|
|
"loss": 4.6063,
|
|
"mean_token_accuracy": 0.25759104192256926,
|
|
"num_tokens": 17202805.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.69417724609375,
|
|
"epoch": 8.737941322725012,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 7.121481969819739e-05,
|
|
"loss": 4.7178,
|
|
"mean_token_accuracy": 0.24495257288217545,
|
|
"num_tokens": 17212805.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.720059776306153,
|
|
"epoch": 8.742913973147688,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 7.104958373126306e-05,
|
|
"loss": 4.7652,
|
|
"mean_token_accuracy": 0.2376426115632057,
|
|
"num_tokens": 17222797.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.7517609119415285,
|
|
"epoch": 8.747886623570363,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 7.08849621867885e-05,
|
|
"loss": 4.8484,
|
|
"mean_token_accuracy": 0.23524854332208633,
|
|
"num_tokens": 17233120.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.728816509246826,
|
|
"epoch": 8.752859273993039,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 7.072095556071381e-05,
|
|
"loss": 4.7665,
|
|
"mean_token_accuracy": 0.24113591015338898,
|
|
"num_tokens": 17241234.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.76837124824524,
|
|
"epoch": 8.757831924415713,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 7.055756434712653e-05,
|
|
"loss": 4.8564,
|
|
"mean_token_accuracy": 0.23569905161857604,
|
|
"num_tokens": 17250502.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.8071832180023195,
|
|
"epoch": 8.76280457483839,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 7.039478903826012e-05,
|
|
"loss": 4.9451,
|
|
"mean_token_accuracy": 0.2215358778834343,
|
|
"num_tokens": 17260400.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.652414608001709,
|
|
"epoch": 8.767777225261064,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 7.023263012449269e-05,
|
|
"loss": 4.6945,
|
|
"mean_token_accuracy": 0.23970891833305358,
|
|
"num_tokens": 17269855.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.754698801040649,
|
|
"epoch": 8.77274987568374,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 7.007108809434527e-05,
|
|
"loss": 4.8066,
|
|
"mean_token_accuracy": 0.23254848569631575,
|
|
"num_tokens": 17280005.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.626655435562133,
|
|
"epoch": 8.777722526106414,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 6.99101634344805e-05,
|
|
"loss": 4.7229,
|
|
"mean_token_accuracy": 0.24268651753664017,
|
|
"num_tokens": 17289929.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.72801022529602,
|
|
"epoch": 8.78269517652909,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 6.974985662970119e-05,
|
|
"loss": 4.7458,
|
|
"mean_token_accuracy": 0.24850087314844133,
|
|
"num_tokens": 17299572.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.616584825515747,
|
|
"epoch": 8.787667826951765,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 6.959016816294872e-05,
|
|
"loss": 4.6655,
|
|
"mean_token_accuracy": 0.25240691006183624,
|
|
"num_tokens": 17308905.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.743388986587524,
|
|
"epoch": 8.79264047737444,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 6.943109851530168e-05,
|
|
"loss": 4.8239,
|
|
"mean_token_accuracy": 0.2391849622130394,
|
|
"num_tokens": 17320145.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.700746011734009,
|
|
"epoch": 8.797613127797115,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 6.927264816597448e-05,
|
|
"loss": 4.752,
|
|
"mean_token_accuracy": 0.2403920978307724,
|
|
"num_tokens": 17330189.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.759702968597412,
|
|
"epoch": 8.802585778219791,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 6.911481759231566e-05,
|
|
"loss": 4.8232,
|
|
"mean_token_accuracy": 0.23332372158765793,
|
|
"num_tokens": 17339154.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.754506683349609,
|
|
"epoch": 8.807558428642466,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 6.895760726980681e-05,
|
|
"loss": 4.8312,
|
|
"mean_token_accuracy": 0.2337367817759514,
|
|
"num_tokens": 17348611.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.784919357299804,
|
|
"epoch": 8.812531079065142,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 6.880101767206079e-05,
|
|
"loss": 4.8573,
|
|
"mean_token_accuracy": 0.22999710887670516,
|
|
"num_tokens": 17358572.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.5729225158691404,
|
|
"epoch": 8.817503729487816,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 6.864504927082051e-05,
|
|
"loss": 4.6176,
|
|
"mean_token_accuracy": 0.26416457146406175,
|
|
"num_tokens": 17368464.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.819681692123413,
|
|
"epoch": 8.822476379910492,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 6.848970253595759e-05,
|
|
"loss": 4.7967,
|
|
"mean_token_accuracy": 0.23615362942218782,
|
|
"num_tokens": 17377326.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.761116695404053,
|
|
"epoch": 8.827449030333167,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 6.833497793547059e-05,
|
|
"loss": 4.8281,
|
|
"mean_token_accuracy": 0.24145394265651704,
|
|
"num_tokens": 17387551.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.8095947265625,
|
|
"epoch": 8.832421680755843,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 6.818087593548391e-05,
|
|
"loss": 4.8694,
|
|
"mean_token_accuracy": 0.22755104005336763,
|
|
"num_tokens": 17398167.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.727512073516846,
|
|
"epoch": 8.837394331178519,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 6.802739700024643e-05,
|
|
"loss": 4.7793,
|
|
"mean_token_accuracy": 0.2342117667198181,
|
|
"num_tokens": 17408640.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.602620029449463,
|
|
"epoch": 8.842366981601193,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 6.787454159212974e-05,
|
|
"loss": 4.5982,
|
|
"mean_token_accuracy": 0.2601443871855736,
|
|
"num_tokens": 17418296.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.563220500946045,
|
|
"epoch": 8.84733963202387,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 6.772231017162725e-05,
|
|
"loss": 4.6232,
|
|
"mean_token_accuracy": 0.25553085207939147,
|
|
"num_tokens": 17428714.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.7483642578125,
|
|
"epoch": 8.852312282446544,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 6.75707031973523e-05,
|
|
"loss": 4.9451,
|
|
"mean_token_accuracy": 0.21916455179452896,
|
|
"num_tokens": 17439261.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.7334089279174805,
|
|
"epoch": 8.85728493286922,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 6.741972112603719e-05,
|
|
"loss": 4.834,
|
|
"mean_token_accuracy": 0.22904129028320314,
|
|
"num_tokens": 17449352.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.710401010513306,
|
|
"epoch": 8.862257583291894,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 6.726936441253155e-05,
|
|
"loss": 4.8014,
|
|
"mean_token_accuracy": 0.22783092856407167,
|
|
"num_tokens": 17460019.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.683493185043335,
|
|
"epoch": 8.86723023371457,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 6.711963350980106e-05,
|
|
"loss": 4.7602,
|
|
"mean_token_accuracy": 0.2439197227358818,
|
|
"num_tokens": 17470014.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.6806117534637455,
|
|
"epoch": 8.872202884137245,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 6.697052886892614e-05,
|
|
"loss": 4.7635,
|
|
"mean_token_accuracy": 0.24978929311037062,
|
|
"num_tokens": 17481126.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.7786461353302006,
|
|
"epoch": 8.877175534559921,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 6.682205093910044e-05,
|
|
"loss": 4.8549,
|
|
"mean_token_accuracy": 0.23568393141031266,
|
|
"num_tokens": 17492114.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.753329610824585,
|
|
"epoch": 8.882148184982595,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 6.667420016762963e-05,
|
|
"loss": 4.8617,
|
|
"mean_token_accuracy": 0.22668469250202178,
|
|
"num_tokens": 17501902.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.702280807495117,
|
|
"epoch": 8.887120835405272,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 6.652697699993e-05,
|
|
"loss": 4.7712,
|
|
"mean_token_accuracy": 0.23526289016008378,
|
|
"num_tokens": 17512321.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.79886794090271,
|
|
"epoch": 8.892093485827946,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 6.638038187952705e-05,
|
|
"loss": 4.8692,
|
|
"mean_token_accuracy": 0.22589537650346755,
|
|
"num_tokens": 17521681.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.670003461837768,
|
|
"epoch": 8.897066136250622,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 6.623441524805433e-05,
|
|
"loss": 4.6585,
|
|
"mean_token_accuracy": 0.26144315153360365,
|
|
"num_tokens": 17530378.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.802021551132202,
|
|
"epoch": 8.902038786673296,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 6.608907754525189e-05,
|
|
"loss": 4.8537,
|
|
"mean_token_accuracy": 0.23615972250699996,
|
|
"num_tokens": 17540310.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.722020769119263,
|
|
"epoch": 8.907011437095973,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 6.594436920896511e-05,
|
|
"loss": 4.8005,
|
|
"mean_token_accuracy": 0.2383416250348091,
|
|
"num_tokens": 17550413.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.722251224517822,
|
|
"epoch": 8.911984087518647,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 6.580029067514346e-05,
|
|
"loss": 4.8089,
|
|
"mean_token_accuracy": 0.23704744577407838,
|
|
"num_tokens": 17559627.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.665457677841187,
|
|
"epoch": 8.916956737941323,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 6.565684237783881e-05,
|
|
"loss": 4.7207,
|
|
"mean_token_accuracy": 0.24168052673339843,
|
|
"num_tokens": 17569562.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.730750894546508,
|
|
"epoch": 8.921929388363997,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 6.551402474920458e-05,
|
|
"loss": 4.8412,
|
|
"mean_token_accuracy": 0.2273334950208664,
|
|
"num_tokens": 17579763.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.673370122909546,
|
|
"epoch": 8.926902038786674,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 6.537183821949412e-05,
|
|
"loss": 4.726,
|
|
"mean_token_accuracy": 0.24571805596351623,
|
|
"num_tokens": 17589525.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.599218797683716,
|
|
"epoch": 8.931874689209348,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 6.52302832170596e-05,
|
|
"loss": 4.6427,
|
|
"mean_token_accuracy": 0.26002853363752365,
|
|
"num_tokens": 17599647.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.751396608352661,
|
|
"epoch": 8.936847339632024,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 6.508936016835063e-05,
|
|
"loss": 4.7619,
|
|
"mean_token_accuracy": 0.24406998604536057,
|
|
"num_tokens": 17608609.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.7600117206573485,
|
|
"epoch": 8.941819990054698,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 6.494906949791296e-05,
|
|
"loss": 4.8912,
|
|
"mean_token_accuracy": 0.22413513511419297,
|
|
"num_tokens": 17618529.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.800202894210815,
|
|
"epoch": 8.946792640477375,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 6.480941162838724e-05,
|
|
"loss": 4.887,
|
|
"mean_token_accuracy": 0.22558801621198654,
|
|
"num_tokens": 17627547.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 8.946792640477375,
|
|
"eval_entropy": 5.734747558145479,
|
|
"eval_loss": 6.436777591705322,
|
|
"eval_mean_token_accuracy": 0.15233354333118634,
|
|
"eval_num_tokens": 17627547.0,
|
|
"eval_runtime": 2.5117,
|
|
"eval_samples_per_second": 1379.553,
|
|
"eval_steps_per_second": 172.792,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.72571759223938,
|
|
"epoch": 8.951765290900049,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 6.46703869805078e-05,
|
|
"loss": 4.8102,
|
|
"mean_token_accuracy": 0.23303315043449402,
|
|
"num_tokens": 17638485.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.719112348556519,
|
|
"epoch": 8.956737941322725,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 6.453199597310119e-05,
|
|
"loss": 4.7412,
|
|
"mean_token_accuracy": 0.23915382623672485,
|
|
"num_tokens": 17648088.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.682679462432861,
|
|
"epoch": 8.961710591745401,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 6.439423902308521e-05,
|
|
"loss": 4.6778,
|
|
"mean_token_accuracy": 0.24932168871164323,
|
|
"num_tokens": 17656681.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.724529361724853,
|
|
"epoch": 8.966683242168076,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 6.425711654546736e-05,
|
|
"loss": 4.8376,
|
|
"mean_token_accuracy": 0.23624350279569625,
|
|
"num_tokens": 17665837.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.752431058883667,
|
|
"epoch": 8.971655892590752,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 6.41206289533438e-05,
|
|
"loss": 4.7748,
|
|
"mean_token_accuracy": 0.23769816309213637,
|
|
"num_tokens": 17674572.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.735546016693116,
|
|
"epoch": 8.976628543013426,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 6.398477665789803e-05,
|
|
"loss": 4.8717,
|
|
"mean_token_accuracy": 0.2242297723889351,
|
|
"num_tokens": 17684912.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.7972251892089846,
|
|
"epoch": 8.981601193436102,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 6.384956006839961e-05,
|
|
"loss": 4.8489,
|
|
"mean_token_accuracy": 0.2295003741979599,
|
|
"num_tokens": 17694706.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.695558977127075,
|
|
"epoch": 8.986573843858777,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 6.371497959220304e-05,
|
|
"loss": 4.7277,
|
|
"mean_token_accuracy": 0.24520538449287416,
|
|
"num_tokens": 17704798.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.729527139663697,
|
|
"epoch": 8.991546494281453,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 6.358103563474632e-05,
|
|
"loss": 4.7546,
|
|
"mean_token_accuracy": 0.23637684285640717,
|
|
"num_tokens": 17714650.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.714930391311645,
|
|
"epoch": 8.996519144704127,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 6.344772859955005e-05,
|
|
"loss": 4.8136,
|
|
"mean_token_accuracy": 0.2414506658911705,
|
|
"num_tokens": 17724636.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.51135958565606,
|
|
"epoch": 9.000994530084535,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 6.331505888821592e-05,
|
|
"loss": 4.537,
|
|
"mean_token_accuracy": 0.2674388504690594,
|
|
"num_tokens": 17732681.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.650811815261841,
|
|
"epoch": 9.005967180507211,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 6.318302690042557e-05,
|
|
"loss": 4.576,
|
|
"mean_token_accuracy": 0.2590370401740074,
|
|
"num_tokens": 17742979.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.841722536087036,
|
|
"epoch": 9.010939830929885,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 6.305163303393955e-05,
|
|
"loss": 4.9307,
|
|
"mean_token_accuracy": 0.22415484189987184,
|
|
"num_tokens": 17752686.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.553374910354615,
|
|
"epoch": 9.015912481352562,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 6.292087768459597e-05,
|
|
"loss": 4.5042,
|
|
"mean_token_accuracy": 0.2659313902258873,
|
|
"num_tokens": 17762750.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.709409952163696,
|
|
"epoch": 9.020885131775236,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 6.279076124630922e-05,
|
|
"loss": 4.6832,
|
|
"mean_token_accuracy": 0.24387344270944594,
|
|
"num_tokens": 17771324.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.763396883010865,
|
|
"epoch": 9.025857782197912,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 6.266128411106915e-05,
|
|
"loss": 4.7664,
|
|
"mean_token_accuracy": 0.24155892431735992,
|
|
"num_tokens": 17780654.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.716667318344117,
|
|
"epoch": 9.030830432620586,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 6.253244666893933e-05,
|
|
"loss": 4.7048,
|
|
"mean_token_accuracy": 0.24309048801660538,
|
|
"num_tokens": 17789420.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.713183116912842,
|
|
"epoch": 9.035803083043263,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 6.240424930805648e-05,
|
|
"loss": 4.7564,
|
|
"mean_token_accuracy": 0.23201724290847778,
|
|
"num_tokens": 17798630.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.755188941955566,
|
|
"epoch": 9.040775733465937,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 6.227669241462878e-05,
|
|
"loss": 4.776,
|
|
"mean_token_accuracy": 0.2360761672258377,
|
|
"num_tokens": 17808707.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.749425745010376,
|
|
"epoch": 9.045748383888613,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 6.214977637293502e-05,
|
|
"loss": 4.751,
|
|
"mean_token_accuracy": 0.23740091621875764,
|
|
"num_tokens": 17818644.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.726183032989502,
|
|
"epoch": 9.050721034311287,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 6.202350156532345e-05,
|
|
"loss": 4.7944,
|
|
"mean_token_accuracy": 0.23678018599748613,
|
|
"num_tokens": 17829464.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.738680648803711,
|
|
"epoch": 9.055693684733964,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 6.189786837221042e-05,
|
|
"loss": 4.7341,
|
|
"mean_token_accuracy": 0.23558668941259384,
|
|
"num_tokens": 17838055.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.719357919692993,
|
|
"epoch": 9.060666335156638,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 6.177287717207928e-05,
|
|
"loss": 4.7315,
|
|
"mean_token_accuracy": 0.24148688465356827,
|
|
"num_tokens": 17848515.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.708359098434448,
|
|
"epoch": 9.065638985579314,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 6.16485283414795e-05,
|
|
"loss": 4.7487,
|
|
"mean_token_accuracy": 0.24845849722623825,
|
|
"num_tokens": 17858181.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.737754011154175,
|
|
"epoch": 9.070611636001988,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 6.152482225502518e-05,
|
|
"loss": 4.7622,
|
|
"mean_token_accuracy": 0.24049349278211593,
|
|
"num_tokens": 17868314.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.722723531723022,
|
|
"epoch": 9.075584286424665,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 6.140175928539419e-05,
|
|
"loss": 4.8007,
|
|
"mean_token_accuracy": 0.23449794054031373,
|
|
"num_tokens": 17877444.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.737500476837158,
|
|
"epoch": 9.080556936847339,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 6.127933980332685e-05,
|
|
"loss": 4.8258,
|
|
"mean_token_accuracy": 0.23187499791383742,
|
|
"num_tokens": 17887311.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.741484117507935,
|
|
"epoch": 9.085529587270015,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 6.1157564177625e-05,
|
|
"loss": 4.8291,
|
|
"mean_token_accuracy": 0.23666648864746093,
|
|
"num_tokens": 17897354.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.692623662948608,
|
|
"epoch": 9.09050223769269,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 6.103643277515075e-05,
|
|
"loss": 4.6462,
|
|
"mean_token_accuracy": 0.2566697642207146,
|
|
"num_tokens": 17906054.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.699629592895508,
|
|
"epoch": 9.095474888115366,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 6.0915945960825393e-05,
|
|
"loss": 4.6722,
|
|
"mean_token_accuracy": 0.245567686855793,
|
|
"num_tokens": 17915851.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.787450838088989,
|
|
"epoch": 9.100447538538042,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 6.079610409762836e-05,
|
|
"loss": 4.7676,
|
|
"mean_token_accuracy": 0.23665722757577895,
|
|
"num_tokens": 17925489.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.797377634048462,
|
|
"epoch": 9.105420188960716,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 6.067690754659605e-05,
|
|
"loss": 4.8373,
|
|
"mean_token_accuracy": 0.23081181645393373,
|
|
"num_tokens": 17935488.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.782941770553589,
|
|
"epoch": 9.110392839383392,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 6.055835666682093e-05,
|
|
"loss": 4.8655,
|
|
"mean_token_accuracy": 0.22965573966503144,
|
|
"num_tokens": 17944626.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.749792194366455,
|
|
"epoch": 9.115365489806067,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 6.044045181545013e-05,
|
|
"loss": 4.7005,
|
|
"mean_token_accuracy": 0.24755238592624665,
|
|
"num_tokens": 17952809.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.711945343017578,
|
|
"epoch": 9.120338140228743,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 6.032319334768465e-05,
|
|
"loss": 4.7107,
|
|
"mean_token_accuracy": 0.24648090004920958,
|
|
"num_tokens": 17962858.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.753357315063477,
|
|
"epoch": 9.125310790651417,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 6.020658161677821e-05,
|
|
"loss": 4.7689,
|
|
"mean_token_accuracy": 0.23512907326221466,
|
|
"num_tokens": 17971714.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.772378921508789,
|
|
"epoch": 9.130283441074093,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 6.009061697403609e-05,
|
|
"loss": 4.8026,
|
|
"mean_token_accuracy": 0.2349621206521988,
|
|
"num_tokens": 17981512.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.732128477096557,
|
|
"epoch": 9.135256091496768,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.9975299768814204e-05,
|
|
"loss": 4.7523,
|
|
"mean_token_accuracy": 0.24128935635089874,
|
|
"num_tokens": 17991562.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.5978843688964846,
|
|
"epoch": 9.140228741919444,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 5.9860630348518004e-05,
|
|
"loss": 4.6218,
|
|
"mean_token_accuracy": 0.261157163977623,
|
|
"num_tokens": 18002100.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.666748762130737,
|
|
"epoch": 9.145201392342118,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 5.974660905860135e-05,
|
|
"loss": 4.6934,
|
|
"mean_token_accuracy": 0.2458907037973404,
|
|
"num_tokens": 18011870.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.653930807113648,
|
|
"epoch": 9.150174042764794,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 5.96332362425656e-05,
|
|
"loss": 4.6677,
|
|
"mean_token_accuracy": 0.2492228105664253,
|
|
"num_tokens": 18021683.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.695558214187622,
|
|
"epoch": 9.155146693187469,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 5.952051224195852e-05,
|
|
"loss": 4.7704,
|
|
"mean_token_accuracy": 0.2399110183119774,
|
|
"num_tokens": 18031430.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.755580949783325,
|
|
"epoch": 9.160119343610145,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 5.940843739637321e-05,
|
|
"loss": 4.7619,
|
|
"mean_token_accuracy": 0.2369675874710083,
|
|
"num_tokens": 18041072.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.806535911560059,
|
|
"epoch": 9.165091994032819,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 5.929701204344712e-05,
|
|
"loss": 4.8917,
|
|
"mean_token_accuracy": 0.22564924359321595,
|
|
"num_tokens": 18051847.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.761050415039063,
|
|
"epoch": 9.170064644455495,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 5.91862365188611e-05,
|
|
"loss": 4.8593,
|
|
"mean_token_accuracy": 0.22432335764169692,
|
|
"num_tokens": 18061901.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.738082075119019,
|
|
"epoch": 9.17503729487817,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 5.907611115633819e-05,
|
|
"loss": 4.7953,
|
|
"mean_token_accuracy": 0.2413667321205139,
|
|
"num_tokens": 18071492.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.818082284927368,
|
|
"epoch": 9.180009945300846,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.896663628764294e-05,
|
|
"loss": 4.7805,
|
|
"mean_token_accuracy": 0.2332383155822754,
|
|
"num_tokens": 18081309.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.731559133529663,
|
|
"epoch": 9.18498259572352,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.885781224258002e-05,
|
|
"loss": 4.7621,
|
|
"mean_token_accuracy": 0.23536192774772643,
|
|
"num_tokens": 18090970.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.719421672821045,
|
|
"epoch": 9.189955246146196,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 5.8749639348993537e-05,
|
|
"loss": 4.7689,
|
|
"mean_token_accuracy": 0.23682494163513185,
|
|
"num_tokens": 18100858.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.754687023162842,
|
|
"epoch": 9.19492789656887,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.864211793276597e-05,
|
|
"loss": 4.8021,
|
|
"mean_token_accuracy": 0.23808362632989882,
|
|
"num_tokens": 18110497.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.7815361499786375,
|
|
"epoch": 9.199900546991547,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 5.853524831781702e-05,
|
|
"loss": 4.805,
|
|
"mean_token_accuracy": 0.23150412738323212,
|
|
"num_tokens": 18119963.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.747420167922973,
|
|
"epoch": 9.204873197414221,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 5.8429030826102886e-05,
|
|
"loss": 4.8119,
|
|
"mean_token_accuracy": 0.2394228011369705,
|
|
"num_tokens": 18129403.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.754998588562012,
|
|
"epoch": 9.209845847836897,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.83234657776151e-05,
|
|
"loss": 4.7962,
|
|
"mean_token_accuracy": 0.24737656414508818,
|
|
"num_tokens": 18139917.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.69826831817627,
|
|
"epoch": 9.214818498259572,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.8218553490379686e-05,
|
|
"loss": 4.6875,
|
|
"mean_token_accuracy": 0.24801717102527618,
|
|
"num_tokens": 18148781.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.626548767089844,
|
|
"epoch": 9.219791148682248,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 5.8114294280456184e-05,
|
|
"loss": 4.5962,
|
|
"mean_token_accuracy": 0.25286598652601244,
|
|
"num_tokens": 18158856.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.707327842712402,
|
|
"epoch": 9.224763799104922,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.801068846193656e-05,
|
|
"loss": 4.7619,
|
|
"mean_token_accuracy": 0.23905758708715438,
|
|
"num_tokens": 18167859.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.690972423553466,
|
|
"epoch": 9.229736449527598,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 5.7907736346944444e-05,
|
|
"loss": 4.7537,
|
|
"mean_token_accuracy": 0.24430032074451447,
|
|
"num_tokens": 18178010.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.724025774002075,
|
|
"epoch": 9.234709099950274,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.780543824563411e-05,
|
|
"loss": 4.804,
|
|
"mean_token_accuracy": 0.23988984972238542,
|
|
"num_tokens": 18188017.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.681283092498779,
|
|
"epoch": 9.239681750372949,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 5.7703794466189524e-05,
|
|
"loss": 4.735,
|
|
"mean_token_accuracy": 0.23881873041391372,
|
|
"num_tokens": 18197502.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.751057577133179,
|
|
"epoch": 9.244654400795625,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 5.7602805314823495e-05,
|
|
"loss": 4.8076,
|
|
"mean_token_accuracy": 0.23928998559713363,
|
|
"num_tokens": 18207182.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.791915035247802,
|
|
"epoch": 9.2496270512183,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 5.7502471095776585e-05,
|
|
"loss": 4.8563,
|
|
"mean_token_accuracy": 0.23160286247730255,
|
|
"num_tokens": 18217490.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.623988008499145,
|
|
"epoch": 9.254599701640975,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 5.740279211131645e-05,
|
|
"loss": 4.6334,
|
|
"mean_token_accuracy": 0.2518390715122223,
|
|
"num_tokens": 18227620.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.700268840789795,
|
|
"epoch": 9.25957235206365,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 5.730376866173662e-05,
|
|
"loss": 4.6972,
|
|
"mean_token_accuracy": 0.24823591858148575,
|
|
"num_tokens": 18237413.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.659340953826904,
|
|
"epoch": 9.264545002486326,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 5.720540104535587e-05,
|
|
"loss": 4.6776,
|
|
"mean_token_accuracy": 0.24926891475915908,
|
|
"num_tokens": 18247688.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.683475208282471,
|
|
"epoch": 9.269517652909,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 5.710768955851721e-05,
|
|
"loss": 4.6839,
|
|
"mean_token_accuracy": 0.24730704724788666,
|
|
"num_tokens": 18257248.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.727902173995972,
|
|
"epoch": 9.274490303331676,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 5.701063449558688e-05,
|
|
"loss": 4.771,
|
|
"mean_token_accuracy": 0.2421570047736168,
|
|
"num_tokens": 18266426.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.749005317687988,
|
|
"epoch": 9.27946295375435,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.691423614895373e-05,
|
|
"loss": 4.7775,
|
|
"mean_token_accuracy": 0.2404157429933548,
|
|
"num_tokens": 18275345.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.476257038116455,
|
|
"epoch": 9.284435604177027,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 5.681849480902806e-05,
|
|
"loss": 4.5203,
|
|
"mean_token_accuracy": 0.275994174182415,
|
|
"num_tokens": 18286156.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.791285705566406,
|
|
"epoch": 9.289408254599701,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.672341076424086e-05,
|
|
"loss": 4.7632,
|
|
"mean_token_accuracy": 0.23866153955459596,
|
|
"num_tokens": 18295701.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.699013805389404,
|
|
"epoch": 9.294380905022377,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.662898430104306e-05,
|
|
"loss": 4.7489,
|
|
"mean_token_accuracy": 0.23606692552566527,
|
|
"num_tokens": 18305900.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.713144731521607,
|
|
"epoch": 9.299353555445052,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 5.653521570390442e-05,
|
|
"loss": 4.7556,
|
|
"mean_token_accuracy": 0.24441211223602294,
|
|
"num_tokens": 18316351.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.644883155822754,
|
|
"epoch": 9.304326205867728,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 5.64421052553129e-05,
|
|
"loss": 4.6932,
|
|
"mean_token_accuracy": 0.2509256511926651,
|
|
"num_tokens": 18326461.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.712883377075196,
|
|
"epoch": 9.309298856290402,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.6349653235773774e-05,
|
|
"loss": 4.7504,
|
|
"mean_token_accuracy": 0.24480343461036683,
|
|
"num_tokens": 18335792.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.763476228713989,
|
|
"epoch": 9.314271506713078,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 5.625785992380854e-05,
|
|
"loss": 4.8188,
|
|
"mean_token_accuracy": 0.23859134912490845,
|
|
"num_tokens": 18346613.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.6844226837158205,
|
|
"epoch": 9.319244157135753,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.6166725595954425e-05,
|
|
"loss": 4.7041,
|
|
"mean_token_accuracy": 0.24899565279483796,
|
|
"num_tokens": 18355435.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.6558574676513675,
|
|
"epoch": 9.324216807558429,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 5.6076250526763326e-05,
|
|
"loss": 4.6684,
|
|
"mean_token_accuracy": 0.2508609652519226,
|
|
"num_tokens": 18363518.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.802227783203125,
|
|
"epoch": 9.329189457981103,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.598643498880108e-05,
|
|
"loss": 4.792,
|
|
"mean_token_accuracy": 0.2391428455710411,
|
|
"num_tokens": 18374890.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.7377753257751465,
|
|
"epoch": 9.33416210840378,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.589727925264665e-05,
|
|
"loss": 4.7505,
|
|
"mean_token_accuracy": 0.234905906021595,
|
|
"num_tokens": 18384176.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.707299995422363,
|
|
"epoch": 9.339134758826454,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 5.5808783586891186e-05,
|
|
"loss": 4.7273,
|
|
"mean_token_accuracy": 0.24090053290128707,
|
|
"num_tokens": 18393440.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.705129241943359,
|
|
"epoch": 9.34410740924913,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 5.5720948258137345e-05,
|
|
"loss": 4.6754,
|
|
"mean_token_accuracy": 0.252980537712574,
|
|
"num_tokens": 18403058.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.714739036560059,
|
|
"epoch": 9.349080059671804,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.563377353099849e-05,
|
|
"loss": 4.7648,
|
|
"mean_token_accuracy": 0.23594101518392563,
|
|
"num_tokens": 18414189.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.674169874191284,
|
|
"epoch": 9.35405271009448,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 5.55472596680978e-05,
|
|
"loss": 4.7388,
|
|
"mean_token_accuracy": 0.24195618480443953,
|
|
"num_tokens": 18423438.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.673891162872314,
|
|
"epoch": 9.359025360517156,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 5.546140693006755e-05,
|
|
"loss": 4.7179,
|
|
"mean_token_accuracy": 0.24396341145038605,
|
|
"num_tokens": 18433060.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.726521587371826,
|
|
"epoch": 9.36399801093983,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.537621557554831e-05,
|
|
"loss": 4.7318,
|
|
"mean_token_accuracy": 0.23973069787025453,
|
|
"num_tokens": 18442687.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.756687784194947,
|
|
"epoch": 9.368970661362507,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 5.529168586118814e-05,
|
|
"loss": 4.7958,
|
|
"mean_token_accuracy": 0.23603698015213012,
|
|
"num_tokens": 18451990.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.739827632904053,
|
|
"epoch": 9.373943311785181,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 5.5207818041641894e-05,
|
|
"loss": 4.7741,
|
|
"mean_token_accuracy": 0.24237826764583587,
|
|
"num_tokens": 18462826.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.696814680099488,
|
|
"epoch": 9.378915962207858,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.5124612369570304e-05,
|
|
"loss": 4.7627,
|
|
"mean_token_accuracy": 0.23981632739305497,
|
|
"num_tokens": 18472466.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.816347980499268,
|
|
"epoch": 9.383888612630532,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 5.504206909563937e-05,
|
|
"loss": 4.9011,
|
|
"mean_token_accuracy": 0.21932261139154435,
|
|
"num_tokens": 18483008.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.816839218139648,
|
|
"epoch": 9.388861263053208,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 5.496018846851957e-05,
|
|
"loss": 4.8706,
|
|
"mean_token_accuracy": 0.2278875544667244,
|
|
"num_tokens": 18493321.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.7046679019927975,
|
|
"epoch": 9.393833913475882,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 5.4878970734885066e-05,
|
|
"loss": 4.6788,
|
|
"mean_token_accuracy": 0.2538030192255974,
|
|
"num_tokens": 18502438.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.807036256790161,
|
|
"epoch": 9.398806563898559,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 5.479841613941291e-05,
|
|
"loss": 4.8619,
|
|
"mean_token_accuracy": 0.22922588437795638,
|
|
"num_tokens": 18512839.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.726346492767334,
|
|
"epoch": 9.403779214321233,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.471852492478251e-05,
|
|
"loss": 4.7347,
|
|
"mean_token_accuracy": 0.24326378852128983,
|
|
"num_tokens": 18522431.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.564404058456421,
|
|
"epoch": 9.408751864743909,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 5.4639297331674625e-05,
|
|
"loss": 4.5814,
|
|
"mean_token_accuracy": 0.26434357464313507,
|
|
"num_tokens": 18532889.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.735915327072144,
|
|
"epoch": 9.413724515166583,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 5.4560733598770956e-05,
|
|
"loss": 4.7577,
|
|
"mean_token_accuracy": 0.23679649233818054,
|
|
"num_tokens": 18541937.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.32648012638092,
|
|
"epoch": 9.41869716558926,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 5.4482833962753094e-05,
|
|
"loss": 4.2978,
|
|
"mean_token_accuracy": 0.29413531720638275,
|
|
"num_tokens": 18552107.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.812619018554687,
|
|
"epoch": 9.423669816011934,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.440559865830207e-05,
|
|
"loss": 4.9013,
|
|
"mean_token_accuracy": 0.22709382623434066,
|
|
"num_tokens": 18562075.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.74341516494751,
|
|
"epoch": 9.42864246643461,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 5.432902791809747e-05,
|
|
"loss": 4.7272,
|
|
"mean_token_accuracy": 0.2331742063164711,
|
|
"num_tokens": 18572325.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.620044231414795,
|
|
"epoch": 9.433615116857284,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 5.425312197281686e-05,
|
|
"loss": 4.6277,
|
|
"mean_token_accuracy": 0.25849395990371704,
|
|
"num_tokens": 18582926.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.6365203857421875,
|
|
"epoch": 9.43858776727996,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 5.417788105113501e-05,
|
|
"loss": 4.6448,
|
|
"mean_token_accuracy": 0.2494202047586441,
|
|
"num_tokens": 18592869.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.637121629714966,
|
|
"epoch": 9.443560417702635,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 5.4103305379723265e-05,
|
|
"loss": 4.6592,
|
|
"mean_token_accuracy": 0.2512729212641716,
|
|
"num_tokens": 18602337.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.773551893234253,
|
|
"epoch": 9.448533068125311,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 5.4029395183248844e-05,
|
|
"loss": 4.8605,
|
|
"mean_token_accuracy": 0.22732495963573457,
|
|
"num_tokens": 18612393.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.723977136611938,
|
|
"epoch": 9.453505718547985,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.3956150684374093e-05,
|
|
"loss": 4.7472,
|
|
"mean_token_accuracy": 0.24001605063676834,
|
|
"num_tokens": 18621701.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.687651062011719,
|
|
"epoch": 9.458478368970662,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.388357210375588e-05,
|
|
"loss": 4.6984,
|
|
"mean_token_accuracy": 0.24289172887802124,
|
|
"num_tokens": 18631584.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.714912414550781,
|
|
"epoch": 9.463451019393336,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.381165966004503e-05,
|
|
"loss": 4.6791,
|
|
"mean_token_accuracy": 0.2528510704636574,
|
|
"num_tokens": 18640881.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.791462993621826,
|
|
"epoch": 9.468423669816012,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.3740413569885366e-05,
|
|
"loss": 4.8293,
|
|
"mean_token_accuracy": 0.232688707113266,
|
|
"num_tokens": 18649731.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.778021335601807,
|
|
"epoch": 9.473396320238686,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 5.366983404791347e-05,
|
|
"loss": 4.8546,
|
|
"mean_token_accuracy": 0.22816011905670167,
|
|
"num_tokens": 18661797.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.709976291656494,
|
|
"epoch": 9.478368970661363,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 5.359992130675761e-05,
|
|
"loss": 4.7541,
|
|
"mean_token_accuracy": 0.2410586178302765,
|
|
"num_tokens": 18671766.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.673158121109009,
|
|
"epoch": 9.483341621084037,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 5.3530675557037486e-05,
|
|
"loss": 4.5889,
|
|
"mean_token_accuracy": 0.2556030139327049,
|
|
"num_tokens": 18681757.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.716989898681641,
|
|
"epoch": 9.488314271506713,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 5.3462097007363274e-05,
|
|
"loss": 4.6747,
|
|
"mean_token_accuracy": 0.25308875888586047,
|
|
"num_tokens": 18691218.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.728265953063965,
|
|
"epoch": 9.49328692192939,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 5.3394185864335225e-05,
|
|
"loss": 4.7635,
|
|
"mean_token_accuracy": 0.2444571852684021,
|
|
"num_tokens": 18701006.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.740667772293091,
|
|
"epoch": 9.498259572352064,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.3326942332542907e-05,
|
|
"loss": 4.7708,
|
|
"mean_token_accuracy": 0.23659258633852004,
|
|
"num_tokens": 18710790.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.709140968322754,
|
|
"epoch": 9.50323222277474,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 5.326036661456468e-05,
|
|
"loss": 4.7527,
|
|
"mean_token_accuracy": 0.24022569507360458,
|
|
"num_tokens": 18719609.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.70463719367981,
|
|
"epoch": 9.508204873197414,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.319445891096703e-05,
|
|
"loss": 4.7471,
|
|
"mean_token_accuracy": 0.2444957822561264,
|
|
"num_tokens": 18728243.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.647353172302246,
|
|
"epoch": 9.51317752362009,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.312921942030392e-05,
|
|
"loss": 4.6185,
|
|
"mean_token_accuracy": 0.2620691955089569,
|
|
"num_tokens": 18737958.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.786059713363647,
|
|
"epoch": 9.518150174042765,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.306464833911631e-05,
|
|
"loss": 4.8975,
|
|
"mean_token_accuracy": 0.22348344177007676,
|
|
"num_tokens": 18747758.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.691358661651611,
|
|
"epoch": 9.52312282446544,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 5.300074586193152e-05,
|
|
"loss": 4.7246,
|
|
"mean_token_accuracy": 0.25060712844133376,
|
|
"num_tokens": 18759293.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.697151708602905,
|
|
"epoch": 9.528095474888115,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.293751218126261e-05,
|
|
"loss": 4.6919,
|
|
"mean_token_accuracy": 0.2547974795103073,
|
|
"num_tokens": 18769977.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.39106388092041,
|
|
"epoch": 9.533068125310791,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.287494748760776e-05,
|
|
"loss": 4.4259,
|
|
"mean_token_accuracy": 0.290972138941288,
|
|
"num_tokens": 18780294.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.729774761199951,
|
|
"epoch": 9.538040775733466,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.2813051969449886e-05,
|
|
"loss": 4.7188,
|
|
"mean_token_accuracy": 0.24602655172348023,
|
|
"num_tokens": 18789936.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.738465261459351,
|
|
"epoch": 9.543013426156142,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 5.2751825813255794e-05,
|
|
"loss": 4.7363,
|
|
"mean_token_accuracy": 0.24024363309144975,
|
|
"num_tokens": 18799446.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.598320960998535,
|
|
"epoch": 9.547986076578816,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 5.269126920347583e-05,
|
|
"loss": 4.6528,
|
|
"mean_token_accuracy": 0.24712977111339568,
|
|
"num_tokens": 18809648.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.690294361114502,
|
|
"epoch": 9.552958727001492,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 5.263138232254333e-05,
|
|
"loss": 4.6668,
|
|
"mean_token_accuracy": 0.24904582947492598,
|
|
"num_tokens": 18820334.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.810447645187378,
|
|
"epoch": 9.557931377424167,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 5.257216535087386e-05,
|
|
"loss": 4.7852,
|
|
"mean_token_accuracy": 0.23314252495765686,
|
|
"num_tokens": 18829715.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.766021299362182,
|
|
"epoch": 9.562904027846843,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 5.251361846686495e-05,
|
|
"loss": 4.7559,
|
|
"mean_token_accuracy": 0.24629541635513305,
|
|
"num_tokens": 18839602.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.732848405838013,
|
|
"epoch": 9.567876678269517,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.245574184689531e-05,
|
|
"loss": 4.808,
|
|
"mean_token_accuracy": 0.24225740134716034,
|
|
"num_tokens": 18849441.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.741774034500122,
|
|
"epoch": 9.572849328692193,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.239853566532444e-05,
|
|
"loss": 4.8023,
|
|
"mean_token_accuracy": 0.2328222393989563,
|
|
"num_tokens": 18859695.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.71055235862732,
|
|
"epoch": 9.577821979114868,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 5.234200009449215e-05,
|
|
"loss": 4.7078,
|
|
"mean_token_accuracy": 0.24663918167352678,
|
|
"num_tokens": 18868660.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.723022317886352,
|
|
"epoch": 9.582794629537544,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 5.228613530471782e-05,
|
|
"loss": 4.74,
|
|
"mean_token_accuracy": 0.2408188670873642,
|
|
"num_tokens": 18878101.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.784441566467285,
|
|
"epoch": 9.587767279960218,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.223094146430017e-05,
|
|
"loss": 4.8616,
|
|
"mean_token_accuracy": 0.23717232793569565,
|
|
"num_tokens": 18887202.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.715556240081787,
|
|
"epoch": 9.592739930382894,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 5.2176418739516534e-05,
|
|
"loss": 4.8185,
|
|
"mean_token_accuracy": 0.2351676881313324,
|
|
"num_tokens": 18897958.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.781640148162841,
|
|
"epoch": 9.597712580805569,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 5.212256729462242e-05,
|
|
"loss": 4.8658,
|
|
"mean_token_accuracy": 0.2282155141234398,
|
|
"num_tokens": 18907510.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.625884485244751,
|
|
"epoch": 9.602685231228245,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 5.2069387291851136e-05,
|
|
"loss": 4.6123,
|
|
"mean_token_accuracy": 0.25683604180812836,
|
|
"num_tokens": 18919219.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.6039269924163815,
|
|
"epoch": 9.607657881650919,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 5.2016878891413096e-05,
|
|
"loss": 4.6047,
|
|
"mean_token_accuracy": 0.25696097761392594,
|
|
"num_tokens": 18928993.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.6217371940612795,
|
|
"epoch": 9.612630532073595,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 5.196504225149547e-05,
|
|
"loss": 4.7359,
|
|
"mean_token_accuracy": 0.2392297625541687,
|
|
"num_tokens": 18939154.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.7443958759307865,
|
|
"epoch": 9.617603182496271,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.19138775282617e-05,
|
|
"loss": 4.7441,
|
|
"mean_token_accuracy": 0.23875711113214493,
|
|
"num_tokens": 18948265.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.694407939910889,
|
|
"epoch": 9.622575832918946,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 5.186338487585098e-05,
|
|
"loss": 4.7733,
|
|
"mean_token_accuracy": 0.2388232707977295,
|
|
"num_tokens": 18957390.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.738719177246094,
|
|
"epoch": 9.627548483341622,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 5.1813564446377855e-05,
|
|
"loss": 4.7284,
|
|
"mean_token_accuracy": 0.2472134307026863,
|
|
"num_tokens": 18966491.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.764021921157837,
|
|
"epoch": 9.632521133764296,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 5.176441638993165e-05,
|
|
"loss": 4.8607,
|
|
"mean_token_accuracy": 0.238643679022789,
|
|
"num_tokens": 18976450.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.734568071365357,
|
|
"epoch": 9.637493784186972,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 5.1715940854576196e-05,
|
|
"loss": 4.7216,
|
|
"mean_token_accuracy": 0.2468000277876854,
|
|
"num_tokens": 18985749.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.745421457290649,
|
|
"epoch": 9.642466434609647,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.1668137986349215e-05,
|
|
"loss": 4.8424,
|
|
"mean_token_accuracy": 0.23128079175949096,
|
|
"num_tokens": 18996288.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.733235597610474,
|
|
"epoch": 9.647439085032323,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 5.1621007929261955e-05,
|
|
"loss": 4.7494,
|
|
"mean_token_accuracy": 0.2407055452466011,
|
|
"num_tokens": 19006340.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.697161483764648,
|
|
"epoch": 9.652411735454997,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.157455082529877e-05,
|
|
"loss": 4.7019,
|
|
"mean_token_accuracy": 0.2401049703359604,
|
|
"num_tokens": 19015773.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.725761985778808,
|
|
"epoch": 9.657384385877673,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.1528766814416664e-05,
|
|
"loss": 4.7373,
|
|
"mean_token_accuracy": 0.24796616435050964,
|
|
"num_tokens": 19024547.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.792736673355103,
|
|
"epoch": 9.662357036300348,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.1483656034544846e-05,
|
|
"loss": 4.7862,
|
|
"mean_token_accuracy": 0.2322131350636482,
|
|
"num_tokens": 19034432.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.723001909255982,
|
|
"epoch": 9.667329686723024,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 5.14392186215844e-05,
|
|
"loss": 4.7277,
|
|
"mean_token_accuracy": 0.24562487453222276,
|
|
"num_tokens": 19044032.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.738001155853271,
|
|
"epoch": 9.672302337145698,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 5.1395454709407746e-05,
|
|
"loss": 4.7822,
|
|
"mean_token_accuracy": 0.23636454790830613,
|
|
"num_tokens": 19054706.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.685024261474609,
|
|
"epoch": 9.677274987568374,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 5.1352364429858414e-05,
|
|
"loss": 4.6361,
|
|
"mean_token_accuracy": 0.2511159896850586,
|
|
"num_tokens": 19063280.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.783568334579468,
|
|
"epoch": 9.682247637991049,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 5.1309947912750456e-05,
|
|
"loss": 4.8374,
|
|
"mean_token_accuracy": 0.22937464118003845,
|
|
"num_tokens": 19073006.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.716184663772583,
|
|
"epoch": 9.687220288413725,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.126820528586815e-05,
|
|
"loss": 4.785,
|
|
"mean_token_accuracy": 0.23094546645879746,
|
|
"num_tokens": 19082797.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.6660484790802,
|
|
"epoch": 9.6921929388364,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.1227136674965646e-05,
|
|
"loss": 4.7118,
|
|
"mean_token_accuracy": 0.24289920032024384,
|
|
"num_tokens": 19092126.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.7090565204620365,
|
|
"epoch": 9.697165589259075,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 5.11867422037665e-05,
|
|
"loss": 4.7916,
|
|
"mean_token_accuracy": 0.2384802907705307,
|
|
"num_tokens": 19102662.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.53021125793457,
|
|
"epoch": 9.70213823968175,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.114702199396343e-05,
|
|
"loss": 4.5334,
|
|
"mean_token_accuracy": 0.2656935349106789,
|
|
"num_tokens": 19112430.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.688211822509766,
|
|
"epoch": 9.707110890104426,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.1107976165217795e-05,
|
|
"loss": 4.7113,
|
|
"mean_token_accuracy": 0.24051076918840408,
|
|
"num_tokens": 19122540.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.718589544296265,
|
|
"epoch": 9.7120835405271,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 5.106960483515934e-05,
|
|
"loss": 4.7385,
|
|
"mean_token_accuracy": 0.24049608707427977,
|
|
"num_tokens": 19131636.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.755450201034546,
|
|
"epoch": 9.717056190949776,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.10319081193858e-05,
|
|
"loss": 4.8197,
|
|
"mean_token_accuracy": 0.22401837557554244,
|
|
"num_tokens": 19141865.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.781777811050415,
|
|
"epoch": 9.72202884137245,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.099488613146255e-05,
|
|
"loss": 4.8188,
|
|
"mean_token_accuracy": 0.23688066601753235,
|
|
"num_tokens": 19152075.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.589431524276733,
|
|
"epoch": 9.727001491795127,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 5.095853898292233e-05,
|
|
"loss": 4.5923,
|
|
"mean_token_accuracy": 0.2676633641123772,
|
|
"num_tokens": 19162503.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.720616865158081,
|
|
"epoch": 9.731974142217801,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 5.0922866783264784e-05,
|
|
"loss": 4.7299,
|
|
"mean_token_accuracy": 0.2392012283205986,
|
|
"num_tokens": 19172317.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.782110548019409,
|
|
"epoch": 9.736946792640477,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.088786963995624e-05,
|
|
"loss": 4.79,
|
|
"mean_token_accuracy": 0.23180126547813415,
|
|
"num_tokens": 19181388.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.78385181427002,
|
|
"epoch": 9.741919443063153,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 5.0853547658429324e-05,
|
|
"loss": 4.7949,
|
|
"mean_token_accuracy": 0.23702270686626434,
|
|
"num_tokens": 19191625.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.777885437011719,
|
|
"epoch": 9.746892093485828,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 5.081990094208271e-05,
|
|
"loss": 4.7566,
|
|
"mean_token_accuracy": 0.23412588089704514,
|
|
"num_tokens": 19200359.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.604658532142639,
|
|
"epoch": 9.751864743908504,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 5.0786929592280706e-05,
|
|
"loss": 4.6538,
|
|
"mean_token_accuracy": 0.25654194205999375,
|
|
"num_tokens": 19210514.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.786667919158935,
|
|
"epoch": 9.756837394331178,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 5.075463370835307e-05,
|
|
"loss": 4.87,
|
|
"mean_token_accuracy": 0.2262020006775856,
|
|
"num_tokens": 19222365.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.767758798599243,
|
|
"epoch": 9.761810044753854,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 5.072301338759455e-05,
|
|
"loss": 4.8248,
|
|
"mean_token_accuracy": 0.2309952363371849,
|
|
"num_tokens": 19231902.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.732509565353394,
|
|
"epoch": 9.766782695176529,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 5.069206872526479e-05,
|
|
"loss": 4.7551,
|
|
"mean_token_accuracy": 0.24324070513248444,
|
|
"num_tokens": 19241260.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.667922878265381,
|
|
"epoch": 9.771755345599205,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 5.06617998145879e-05,
|
|
"loss": 4.6213,
|
|
"mean_token_accuracy": 0.2523579731583595,
|
|
"num_tokens": 19250500.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.655468320846557,
|
|
"epoch": 9.77672799602188,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 5.063220674675219e-05,
|
|
"loss": 4.6454,
|
|
"mean_token_accuracy": 0.25480962842702864,
|
|
"num_tokens": 19260272.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.75284366607666,
|
|
"epoch": 9.781700646444556,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 5.060328961090996e-05,
|
|
"loss": 4.799,
|
|
"mean_token_accuracy": 0.22704235315322877,
|
|
"num_tokens": 19269807.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.789252042770386,
|
|
"epoch": 9.78667329686723,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 5.057504849417717e-05,
|
|
"loss": 4.7939,
|
|
"mean_token_accuracy": 0.23265314400196074,
|
|
"num_tokens": 19279758.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.730217695236206,
|
|
"epoch": 9.791645947289906,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 5.05474834816332e-05,
|
|
"loss": 4.7511,
|
|
"mean_token_accuracy": 0.2435338854789734,
|
|
"num_tokens": 19290936.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.6535076141357425,
|
|
"epoch": 9.79661859771258,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 5.052059465632063e-05,
|
|
"loss": 4.7036,
|
|
"mean_token_accuracy": 0.2513682901859283,
|
|
"num_tokens": 19299448.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.740879011154175,
|
|
"epoch": 9.801591248135257,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 5.049438209924489e-05,
|
|
"loss": 4.7983,
|
|
"mean_token_accuracy": 0.23316453099250795,
|
|
"num_tokens": 19309926.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.780432081222534,
|
|
"epoch": 9.80656389855793,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 5.0468845889374115e-05,
|
|
"loss": 4.8569,
|
|
"mean_token_accuracy": 0.22849688678979874,
|
|
"num_tokens": 19320495.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.496090412139893,
|
|
"epoch": 9.811536548980607,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 5.04439861036389e-05,
|
|
"loss": 4.4184,
|
|
"mean_token_accuracy": 0.28064538836479186,
|
|
"num_tokens": 19329699.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.74069447517395,
|
|
"epoch": 9.816509199403281,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.041980281693198e-05,
|
|
"loss": 4.6468,
|
|
"mean_token_accuracy": 0.25623865723609923,
|
|
"num_tokens": 19338760.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.692273139953613,
|
|
"epoch": 9.821481849825958,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.0396296102108134e-05,
|
|
"loss": 4.7034,
|
|
"mean_token_accuracy": 0.24262737333774567,
|
|
"num_tokens": 19349098.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.689055967330932,
|
|
"epoch": 9.826454500248632,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 5.037346602998383e-05,
|
|
"loss": 4.765,
|
|
"mean_token_accuracy": 0.23992313593626022,
|
|
"num_tokens": 19359541.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.680244779586792,
|
|
"epoch": 9.831427150671308,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 5.03513126693371e-05,
|
|
"loss": 4.6874,
|
|
"mean_token_accuracy": 0.2475058227777481,
|
|
"num_tokens": 19369376.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.709274673461914,
|
|
"epoch": 9.836399801093982,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.0329836086907294e-05,
|
|
"loss": 4.689,
|
|
"mean_token_accuracy": 0.25008203089237213,
|
|
"num_tokens": 19379147.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.7278220653533936,
|
|
"epoch": 9.841372451516659,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.030903634739498e-05,
|
|
"loss": 4.7787,
|
|
"mean_token_accuracy": 0.23454826921224595,
|
|
"num_tokens": 19388714.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.726080131530762,
|
|
"epoch": 9.846345101939333,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.028891351346154e-05,
|
|
"loss": 4.7101,
|
|
"mean_token_accuracy": 0.24489323496818544,
|
|
"num_tokens": 19397495.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.7386188983917235,
|
|
"epoch": 9.851317752362009,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.0269467645729184e-05,
|
|
"loss": 4.7431,
|
|
"mean_token_accuracy": 0.24095534384250641,
|
|
"num_tokens": 19407369.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.6156188488006595,
|
|
"epoch": 9.856290402784683,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.0250698802780684e-05,
|
|
"loss": 4.6351,
|
|
"mean_token_accuracy": 0.256623212993145,
|
|
"num_tokens": 19417169.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.7849548816680905,
|
|
"epoch": 9.86126305320736,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.0232607041159164e-05,
|
|
"loss": 4.7953,
|
|
"mean_token_accuracy": 0.2313209891319275,
|
|
"num_tokens": 19426463.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.7326913356781,
|
|
"epoch": 9.866235703630036,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.0215192415368e-05,
|
|
"loss": 4.707,
|
|
"mean_token_accuracy": 0.2373308554291725,
|
|
"num_tokens": 19436938.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.789185190200806,
|
|
"epoch": 9.87120835405271,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 5.0198454977870655e-05,
|
|
"loss": 4.7998,
|
|
"mean_token_accuracy": 0.23800361305475234,
|
|
"num_tokens": 19446930.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.7991796970367435,
|
|
"epoch": 9.876181004475386,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.018239477909039e-05,
|
|
"loss": 4.8727,
|
|
"mean_token_accuracy": 0.2244374930858612,
|
|
"num_tokens": 19456344.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.671865653991699,
|
|
"epoch": 9.88115365489806,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 5.01670118674103e-05,
|
|
"loss": 4.7159,
|
|
"mean_token_accuracy": 0.2477562665939331,
|
|
"num_tokens": 19466553.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.743785572052002,
|
|
"epoch": 9.886126305320737,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 5.015230628917305e-05,
|
|
"loss": 4.7965,
|
|
"mean_token_accuracy": 0.23163739442825318,
|
|
"num_tokens": 19476567.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.827611637115479,
|
|
"epoch": 9.891098955743411,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 5.013827808868079e-05,
|
|
"loss": 4.8605,
|
|
"mean_token_accuracy": 0.23354700952768326,
|
|
"num_tokens": 19485670.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.592171096801758,
|
|
"epoch": 9.896071606166087,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 5.012492730819495e-05,
|
|
"loss": 4.6164,
|
|
"mean_token_accuracy": 0.2518974423408508,
|
|
"num_tokens": 19496315.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.759787082672119,
|
|
"epoch": 9.901044256588762,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.0112253987936196e-05,
|
|
"loss": 4.7433,
|
|
"mean_token_accuracy": 0.24416202157735825,
|
|
"num_tokens": 19505932.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.750328874588012,
|
|
"epoch": 9.906016907011438,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 5.0100258166084246e-05,
|
|
"loss": 4.8265,
|
|
"mean_token_accuracy": 0.2326206937432289,
|
|
"num_tokens": 19516912.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.755430555343628,
|
|
"epoch": 9.910989557434112,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 5.008893987877781e-05,
|
|
"loss": 4.7908,
|
|
"mean_token_accuracy": 0.23306143879890442,
|
|
"num_tokens": 19526095.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.586808490753174,
|
|
"epoch": 9.915962207856788,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 5.0078299160114443e-05,
|
|
"loss": 4.6361,
|
|
"mean_token_accuracy": 0.2553794473409653,
|
|
"num_tokens": 19537147.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.7378284454345705,
|
|
"epoch": 9.920934858279463,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 5.0068336042150455e-05,
|
|
"loss": 4.7341,
|
|
"mean_token_accuracy": 0.23581708818674088,
|
|
"num_tokens": 19546014.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.781052684783935,
|
|
"epoch": 9.925907508702139,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 5.005905055490081e-05,
|
|
"loss": 4.8542,
|
|
"mean_token_accuracy": 0.2255322366952896,
|
|
"num_tokens": 19555451.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.741558170318603,
|
|
"epoch": 9.930880159124813,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 5.0050442726339e-05,
|
|
"loss": 4.7511,
|
|
"mean_token_accuracy": 0.24828654080629348,
|
|
"num_tokens": 19563773.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.384912061691284,
|
|
"epoch": 9.93585280954749,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 5.004251258239703e-05,
|
|
"loss": 4.4499,
|
|
"mean_token_accuracy": 0.28504408448934554,
|
|
"num_tokens": 19573821.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.604303216934204,
|
|
"epoch": 9.940825459970164,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 5.0035260146965355e-05,
|
|
"loss": 4.6242,
|
|
"mean_token_accuracy": 0.25908454656600954,
|
|
"num_tokens": 19584768.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"epoch": 9.940825459970164,
|
|
"eval_entropy": 5.72503297339936,
|
|
"eval_loss": 6.440331935882568,
|
|
"eval_mean_token_accuracy": 0.1521224493787448,
|
|
"eval_num_tokens": 19584768.0,
|
|
"eval_runtime": 2.5149,
|
|
"eval_samples_per_second": 1377.777,
|
|
"eval_steps_per_second": 172.57,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.577810859680175,
|
|
"epoch": 9.94579811039284,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 5.002868544189266e-05,
|
|
"loss": 4.5414,
|
|
"mean_token_accuracy": 0.26890093386173247,
|
|
"num_tokens": 19595054.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.760360527038574,
|
|
"epoch": 9.950770760815514,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 5.0022788486986e-05,
|
|
"loss": 4.7329,
|
|
"mean_token_accuracy": 0.24673573672771454,
|
|
"num_tokens": 19605261.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.70475401878357,
|
|
"epoch": 9.95574341123819,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.001756930001052e-05,
|
|
"loss": 4.7057,
|
|
"mean_token_accuracy": 0.24623171985149384,
|
|
"num_tokens": 19614612.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.8024373054504395,
|
|
"epoch": 9.960716061660865,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 5.001302789668965e-05,
|
|
"loss": 4.8556,
|
|
"mean_token_accuracy": 0.22325285375118256,
|
|
"num_tokens": 19624439.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.773643541336059,
|
|
"epoch": 9.96568871208354,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.00091642907048e-05,
|
|
"loss": 4.7896,
|
|
"mean_token_accuracy": 0.23147473633289337,
|
|
"num_tokens": 19634131.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.751474094390869,
|
|
"epoch": 9.970661362506215,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 5.0005978493695506e-05,
|
|
"loss": 4.7824,
|
|
"mean_token_accuracy": 0.23365445733070372,
|
|
"num_tokens": 19644039.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.723624610900879,
|
|
"epoch": 9.975634012928891,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.000347051525935e-05,
|
|
"loss": 4.8409,
|
|
"mean_token_accuracy": 0.228887677192688,
|
|
"num_tokens": 19653758.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.73131914138794,
|
|
"epoch": 9.980606663351566,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 5.000164036295185e-05,
|
|
"loss": 4.7667,
|
|
"mean_token_accuracy": 0.23599051386117936,
|
|
"num_tokens": 19662523.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.709031486511231,
|
|
"epoch": 9.985579313774242,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 5.000048804228656e-05,
|
|
"loss": 4.7896,
|
|
"mean_token_accuracy": 0.23855502158403397,
|
|
"num_tokens": 19672139.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.781178331375122,
|
|
"epoch": 9.990551964196918,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 5.000001355673494e-05,
|
|
"loss": 4.8351,
|
|
"mean_token_accuracy": 0.2325945481657982,
|
|
"num_tokens": 19682154.0,
|
|
"step": 10050
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 10050,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 1000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 3.2259820575744e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|