18068 lines
494 KiB
JSON
18068 lines
494 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.7947721653126104,
|
|
"eval_steps": 3000,
|
|
"global_step": 9000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.692046070098877,
|
|
"epoch": 0.0004415400918403391,
|
|
"grad_norm": 15.5625,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.7987,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 9390.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.69192419052124,
|
|
"epoch": 0.0008830801836806782,
|
|
"grad_norm": 14.4375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7211,
|
|
"mean_token_accuracy": 0.0002551274374127388,
|
|
"num_tokens": 18671.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.69034719467163,
|
|
"epoch": 0.0013246202755210173,
|
|
"grad_norm": 10.1875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.4504,
|
|
"mean_token_accuracy": 0.04107050695456564,
|
|
"num_tokens": 27614.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.65851650238037,
|
|
"epoch": 0.0017661603673613563,
|
|
"grad_norm": 6.09375,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.1437,
|
|
"mean_token_accuracy": 0.05260300412774086,
|
|
"num_tokens": 37850.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.480317497253418,
|
|
"epoch": 0.0022077004592016957,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 9.7713,
|
|
"mean_token_accuracy": 0.06779314689338208,
|
|
"num_tokens": 47166.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.35213108062744,
|
|
"epoch": 0.0026492405510420347,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 9.6925,
|
|
"mean_token_accuracy": 0.0573563989251852,
|
|
"num_tokens": 55500.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.413340187072754,
|
|
"epoch": 0.0030907806428823736,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 9.676,
|
|
"mean_token_accuracy": 0.05297967046499252,
|
|
"num_tokens": 63851.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.392519474029541,
|
|
"epoch": 0.0035323207347227126,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 9.5804,
|
|
"mean_token_accuracy": 0.06258798092603683,
|
|
"num_tokens": 73697.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.351652717590332,
|
|
"epoch": 0.003973860826563052,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.5487,
|
|
"mean_token_accuracy": 0.06010213047266007,
|
|
"num_tokens": 83000.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.341690158843994,
|
|
"epoch": 0.004415400918403391,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.5288,
|
|
"mean_token_accuracy": 0.06254246681928635,
|
|
"num_tokens": 92982.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.24167251586914,
|
|
"epoch": 0.00485694101024373,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.4211,
|
|
"mean_token_accuracy": 0.06874397993087769,
|
|
"num_tokens": 101455.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.19759111404419,
|
|
"epoch": 0.005298481102084069,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.3764,
|
|
"mean_token_accuracy": 0.07629412487149238,
|
|
"num_tokens": 110782.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.167214965820312,
|
|
"epoch": 0.005740021193924408,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.2641,
|
|
"mean_token_accuracy": 0.07399890869855881,
|
|
"num_tokens": 119241.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.210993480682372,
|
|
"epoch": 0.006181561285764747,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.2782,
|
|
"mean_token_accuracy": 0.07282476425170899,
|
|
"num_tokens": 127903.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.159809684753418,
|
|
"epoch": 0.006623101377605086,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.2258,
|
|
"mean_token_accuracy": 0.07543315626680851,
|
|
"num_tokens": 137370.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.111583232879639,
|
|
"epoch": 0.007064641469445425,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.0774,
|
|
"mean_token_accuracy": 0.08292015641927719,
|
|
"num_tokens": 146582.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.07847490310669,
|
|
"epoch": 0.007506181561285765,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.0108,
|
|
"mean_token_accuracy": 0.07970988750457764,
|
|
"num_tokens": 154933.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.015530204772949,
|
|
"epoch": 0.007947721653126103,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 8.9747,
|
|
"mean_token_accuracy": 0.07985232844948768,
|
|
"num_tokens": 165157.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.035838222503662,
|
|
"epoch": 0.008389261744966443,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.8768,
|
|
"mean_token_accuracy": 0.07754012271761894,
|
|
"num_tokens": 174958.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 9.947721004486084,
|
|
"epoch": 0.008830801836806783,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.7872,
|
|
"mean_token_accuracy": 0.0828177772462368,
|
|
"num_tokens": 184256.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 9.94132833480835,
|
|
"epoch": 0.009272341928647121,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.6971,
|
|
"mean_token_accuracy": 0.07942965477705002,
|
|
"num_tokens": 192894.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 9.842441368103028,
|
|
"epoch": 0.00971388202048746,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.6172,
|
|
"mean_token_accuracy": 0.08055685237050056,
|
|
"num_tokens": 202675.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 9.828944206237793,
|
|
"epoch": 0.010155422112327799,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.5621,
|
|
"mean_token_accuracy": 0.07997862100601197,
|
|
"num_tokens": 212261.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.671414470672607,
|
|
"epoch": 0.010596962204168139,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.5494,
|
|
"mean_token_accuracy": 0.07975570932030678,
|
|
"num_tokens": 222329.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.579044532775878,
|
|
"epoch": 0.011038502296008477,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.392,
|
|
"mean_token_accuracy": 0.07828540578484536,
|
|
"num_tokens": 231247.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.464293384552002,
|
|
"epoch": 0.011480042387848817,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.2789,
|
|
"mean_token_accuracy": 0.08522977083921432,
|
|
"num_tokens": 239978.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.329948711395264,
|
|
"epoch": 0.011921582479689156,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.243,
|
|
"mean_token_accuracy": 0.08045366927981376,
|
|
"num_tokens": 249735.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.195873355865478,
|
|
"epoch": 0.012363122571529495,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.1804,
|
|
"mean_token_accuracy": 0.07878185361623764,
|
|
"num_tokens": 259369.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.076773929595948,
|
|
"epoch": 0.012804662663369834,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.165,
|
|
"mean_token_accuracy": 0.07605967372655868,
|
|
"num_tokens": 268645.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.913009357452392,
|
|
"epoch": 0.013246202755210172,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.992,
|
|
"mean_token_accuracy": 0.08179110959172249,
|
|
"num_tokens": 276667.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.75396728515625,
|
|
"epoch": 0.013687742847050512,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.9969,
|
|
"mean_token_accuracy": 0.08649424239993095,
|
|
"num_tokens": 286017.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.627446365356445,
|
|
"epoch": 0.01412928293889085,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.9781,
|
|
"mean_token_accuracy": 0.08121571242809296,
|
|
"num_tokens": 295631.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.693611431121827,
|
|
"epoch": 0.01457082303073119,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.9589,
|
|
"mean_token_accuracy": 0.08223926201462746,
|
|
"num_tokens": 304704.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.534437942504884,
|
|
"epoch": 0.01501236312257153,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.9731,
|
|
"mean_token_accuracy": 0.08499160557985305,
|
|
"num_tokens": 314195.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.449780178070068,
|
|
"epoch": 0.015453903214411868,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.9605,
|
|
"mean_token_accuracy": 0.08167596161365509,
|
|
"num_tokens": 323379.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.427653789520264,
|
|
"epoch": 0.015895443306252206,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.864,
|
|
"mean_token_accuracy": 0.08790193870663643,
|
|
"num_tokens": 332322.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.308454895019532,
|
|
"epoch": 0.016336983398092548,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.8241,
|
|
"mean_token_accuracy": 0.0907207302749157,
|
|
"num_tokens": 341735.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.393166542053223,
|
|
"epoch": 0.016778523489932886,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.9195,
|
|
"mean_token_accuracy": 0.08468585535883903,
|
|
"num_tokens": 351209.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.27011661529541,
|
|
"epoch": 0.017220063581773224,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.8614,
|
|
"mean_token_accuracy": 0.08361415192484856,
|
|
"num_tokens": 360467.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.242918300628663,
|
|
"epoch": 0.017661603673613566,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.8241,
|
|
"mean_token_accuracy": 0.0869070716202259,
|
|
"num_tokens": 370361.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.279992771148681,
|
|
"epoch": 0.018103143765453904,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.8877,
|
|
"mean_token_accuracy": 0.07924672663211822,
|
|
"num_tokens": 380366.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.198458003997803,
|
|
"epoch": 0.018544683857294242,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.7928,
|
|
"mean_token_accuracy": 0.08724351823329926,
|
|
"num_tokens": 390690.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.174153900146484,
|
|
"epoch": 0.01898622394913458,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.8526,
|
|
"mean_token_accuracy": 0.0823112078011036,
|
|
"num_tokens": 400722.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.113383865356445,
|
|
"epoch": 0.01942776404097492,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.733,
|
|
"mean_token_accuracy": 0.08983569592237473,
|
|
"num_tokens": 410223.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.137540912628173,
|
|
"epoch": 0.01986930413281526,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.7948,
|
|
"mean_token_accuracy": 0.0847058854997158,
|
|
"num_tokens": 420214.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.165675449371339,
|
|
"epoch": 0.020310844224655598,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.7491,
|
|
"mean_token_accuracy": 0.08784600198268891,
|
|
"num_tokens": 429407.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.056314134597779,
|
|
"epoch": 0.02075238431649594,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.7019,
|
|
"mean_token_accuracy": 0.08565770387649536,
|
|
"num_tokens": 438403.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.126753520965575,
|
|
"epoch": 0.021193924408336277,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.7374,
|
|
"mean_token_accuracy": 0.09219109117984772,
|
|
"num_tokens": 447466.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.062481260299682,
|
|
"epoch": 0.021635464500176615,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.8271,
|
|
"mean_token_accuracy": 0.0802032507956028,
|
|
"num_tokens": 457141.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.097463226318359,
|
|
"epoch": 0.022077004592016954,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.698,
|
|
"mean_token_accuracy": 0.0921065405011177,
|
|
"num_tokens": 465708.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.170325756072998,
|
|
"epoch": 0.022518544683857295,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.7169,
|
|
"mean_token_accuracy": 0.0848769947886467,
|
|
"num_tokens": 475369.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.963189935684204,
|
|
"epoch": 0.022960084775697633,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.6855,
|
|
"mean_token_accuracy": 0.08922288343310356,
|
|
"num_tokens": 484249.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.03909511566162,
|
|
"epoch": 0.02340162486753797,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.7881,
|
|
"mean_token_accuracy": 0.08452328145503998,
|
|
"num_tokens": 493303.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.062015914916993,
|
|
"epoch": 0.023843164959378313,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.758,
|
|
"mean_token_accuracy": 0.09125194177031518,
|
|
"num_tokens": 501503.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.085032892227172,
|
|
"epoch": 0.02428470505121865,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.6942,
|
|
"mean_token_accuracy": 0.09186801388859749,
|
|
"num_tokens": 509661.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.047321224212647,
|
|
"epoch": 0.02472624514305899,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.6684,
|
|
"mean_token_accuracy": 0.09005074873566628,
|
|
"num_tokens": 519464.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.028418731689452,
|
|
"epoch": 0.025167785234899327,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.6342,
|
|
"mean_token_accuracy": 0.09150514975190163,
|
|
"num_tokens": 527968.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.062326526641845,
|
|
"epoch": 0.02560932532673967,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.6649,
|
|
"mean_token_accuracy": 0.09316564500331878,
|
|
"num_tokens": 537234.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.969491100311279,
|
|
"epoch": 0.026050865418580007,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.6521,
|
|
"mean_token_accuracy": 0.09308369681239129,
|
|
"num_tokens": 546398.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.048774671554565,
|
|
"epoch": 0.026492405510420345,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.6327,
|
|
"mean_token_accuracy": 0.09298400059342385,
|
|
"num_tokens": 555362.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.990510559082031,
|
|
"epoch": 0.026933945602260687,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.6861,
|
|
"mean_token_accuracy": 0.08575507774949073,
|
|
"num_tokens": 564575.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.113833093643189,
|
|
"epoch": 0.027375485694101025,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.7137,
|
|
"mean_token_accuracy": 0.08935339227318764,
|
|
"num_tokens": 573915.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.953329849243164,
|
|
"epoch": 0.027817025785941363,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.6052,
|
|
"mean_token_accuracy": 0.08935642167925835,
|
|
"num_tokens": 583216.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.974963426589966,
|
|
"epoch": 0.0282585658777817,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.6365,
|
|
"mean_token_accuracy": 0.09493646398186684,
|
|
"num_tokens": 591955.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.945090007781983,
|
|
"epoch": 0.028700105969622042,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.6372,
|
|
"mean_token_accuracy": 0.09564759358763694,
|
|
"num_tokens": 600999.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.945532560348511,
|
|
"epoch": 0.02914164606146238,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.5347,
|
|
"mean_token_accuracy": 0.09901952669024468,
|
|
"num_tokens": 609478.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.826081418991089,
|
|
"epoch": 0.02958318615330272,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.6044,
|
|
"mean_token_accuracy": 0.09094477742910385,
|
|
"num_tokens": 618348.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.00728144645691,
|
|
"epoch": 0.03002472624514306,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.651,
|
|
"mean_token_accuracy": 0.08828822076320648,
|
|
"num_tokens": 628548.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.951943874359131,
|
|
"epoch": 0.0304662663369834,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.5861,
|
|
"mean_token_accuracy": 0.09196597188711167,
|
|
"num_tokens": 637489.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.842890119552612,
|
|
"epoch": 0.030907806428823736,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.5698,
|
|
"mean_token_accuracy": 0.08872186839580536,
|
|
"num_tokens": 646715.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.839594936370849,
|
|
"epoch": 0.031349346520664075,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.5673,
|
|
"mean_token_accuracy": 0.09486312419176102,
|
|
"num_tokens": 656858.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.985370254516601,
|
|
"epoch": 0.03179088661250441,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.5492,
|
|
"mean_token_accuracy": 0.09201375618577004,
|
|
"num_tokens": 665968.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.856255674362183,
|
|
"epoch": 0.03223242670434476,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.5346,
|
|
"mean_token_accuracy": 0.0938662439584732,
|
|
"num_tokens": 674295.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.819755506515503,
|
|
"epoch": 0.032673966796185096,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.4683,
|
|
"mean_token_accuracy": 0.0921003058552742,
|
|
"num_tokens": 683559.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.767789649963379,
|
|
"epoch": 0.033115506888025434,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.4958,
|
|
"mean_token_accuracy": 0.09682972505688667,
|
|
"num_tokens": 692402.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.937490701675415,
|
|
"epoch": 0.03355704697986577,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.61,
|
|
"mean_token_accuracy": 0.08481517881155014,
|
|
"num_tokens": 702052.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.88536114692688,
|
|
"epoch": 0.03399858707170611,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.5255,
|
|
"mean_token_accuracy": 0.09476071372628211,
|
|
"num_tokens": 711926.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.827258634567261,
|
|
"epoch": 0.03444012716354645,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.4746,
|
|
"mean_token_accuracy": 0.09309235811233521,
|
|
"num_tokens": 720948.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.764995431900024,
|
|
"epoch": 0.034881667255386786,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.5254,
|
|
"mean_token_accuracy": 0.09631742537021637,
|
|
"num_tokens": 729611.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.932223796844482,
|
|
"epoch": 0.03532320734722713,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.4985,
|
|
"mean_token_accuracy": 0.08739121779799461,
|
|
"num_tokens": 738433.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.759926271438599,
|
|
"epoch": 0.03576474743906747,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.5344,
|
|
"mean_token_accuracy": 0.09274654388427735,
|
|
"num_tokens": 747310.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.756983041763306,
|
|
"epoch": 0.03620628753090781,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.5047,
|
|
"mean_token_accuracy": 0.09618922770023346,
|
|
"num_tokens": 756362.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.847079801559448,
|
|
"epoch": 0.036647827622748146,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.4946,
|
|
"mean_token_accuracy": 0.09153542071580886,
|
|
"num_tokens": 764978.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.769409275054931,
|
|
"epoch": 0.037089367714588484,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.4616,
|
|
"mean_token_accuracy": 0.09671959578990937,
|
|
"num_tokens": 774058.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.735736560821533,
|
|
"epoch": 0.03753090780642882,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.4465,
|
|
"mean_token_accuracy": 0.09103933200240136,
|
|
"num_tokens": 783332.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.767506504058838,
|
|
"epoch": 0.03797244789826916,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.5161,
|
|
"mean_token_accuracy": 0.09249499961733817,
|
|
"num_tokens": 792481.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.697516012191772,
|
|
"epoch": 0.038413987990109505,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.4117,
|
|
"mean_token_accuracy": 0.09788367450237274,
|
|
"num_tokens": 801396.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.726156330108642,
|
|
"epoch": 0.03885552808194984,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.4781,
|
|
"mean_token_accuracy": 0.09258785918354988,
|
|
"num_tokens": 809903.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.754117822647094,
|
|
"epoch": 0.03929706817379018,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.4228,
|
|
"mean_token_accuracy": 0.10010684058070182,
|
|
"num_tokens": 819144.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.638237190246582,
|
|
"epoch": 0.03973860826563052,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.4501,
|
|
"mean_token_accuracy": 0.09609700441360473,
|
|
"num_tokens": 828881.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.699933958053589,
|
|
"epoch": 0.04018014835747086,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.3763,
|
|
"mean_token_accuracy": 0.09211291894316673,
|
|
"num_tokens": 837588.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.64010763168335,
|
|
"epoch": 0.040621688449311195,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.3807,
|
|
"mean_token_accuracy": 0.09671871289610863,
|
|
"num_tokens": 847002.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.623350667953491,
|
|
"epoch": 0.041063228541151534,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.3849,
|
|
"mean_token_accuracy": 0.0986923448741436,
|
|
"num_tokens": 855791.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.721793460845947,
|
|
"epoch": 0.04150476863299188,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.4131,
|
|
"mean_token_accuracy": 0.09923509359359742,
|
|
"num_tokens": 865392.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.608292579650879,
|
|
"epoch": 0.04194630872483222,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.478,
|
|
"mean_token_accuracy": 0.09382415115833283,
|
|
"num_tokens": 874807.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.754652500152588,
|
|
"epoch": 0.042387848816672555,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.4339,
|
|
"mean_token_accuracy": 0.09926938116550446,
|
|
"num_tokens": 883928.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.652652740478516,
|
|
"epoch": 0.04282938890851289,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.3376,
|
|
"mean_token_accuracy": 0.09957752376794815,
|
|
"num_tokens": 893047.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.5953545570373535,
|
|
"epoch": 0.04327092900035323,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.3515,
|
|
"mean_token_accuracy": 0.10079265013337135,
|
|
"num_tokens": 901645.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.616002416610717,
|
|
"epoch": 0.04371246909219357,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.3691,
|
|
"mean_token_accuracy": 0.09735967218875885,
|
|
"num_tokens": 911169.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.688420724868775,
|
|
"epoch": 0.04415400918403391,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.3811,
|
|
"mean_token_accuracy": 0.0928712822496891,
|
|
"num_tokens": 921382.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.501060581207275,
|
|
"epoch": 0.04459554927587425,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.3012,
|
|
"mean_token_accuracy": 0.09976874813437461,
|
|
"num_tokens": 930409.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.606061887741089,
|
|
"epoch": 0.04503708936771459,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.283,
|
|
"mean_token_accuracy": 0.10316867306828499,
|
|
"num_tokens": 939049.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.589950037002564,
|
|
"epoch": 0.04547862945955493,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.2954,
|
|
"mean_token_accuracy": 0.10237202495336532,
|
|
"num_tokens": 947575.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.631234502792358,
|
|
"epoch": 0.045920169551395267,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.4624,
|
|
"mean_token_accuracy": 0.09285921081900597,
|
|
"num_tokens": 957848.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.598208427429199,
|
|
"epoch": 0.046361709643235605,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.2919,
|
|
"mean_token_accuracy": 0.10156237781047821,
|
|
"num_tokens": 966521.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.606314086914063,
|
|
"epoch": 0.04680324973507594,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.3541,
|
|
"mean_token_accuracy": 0.10115546062588691,
|
|
"num_tokens": 975827.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.526746702194214,
|
|
"epoch": 0.04724478982691628,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.2985,
|
|
"mean_token_accuracy": 0.10082201957702637,
|
|
"num_tokens": 985292.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.502959203720093,
|
|
"epoch": 0.047686329918756626,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.2896,
|
|
"mean_token_accuracy": 0.10343632996082305,
|
|
"num_tokens": 994791.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.516558980941772,
|
|
"epoch": 0.048127870010596964,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.2553,
|
|
"mean_token_accuracy": 0.10770378857851029,
|
|
"num_tokens": 1003700.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.503448867797852,
|
|
"epoch": 0.0485694101024373,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.2947,
|
|
"mean_token_accuracy": 0.10270922258496284,
|
|
"num_tokens": 1012682.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.590410900115967,
|
|
"epoch": 0.04901095019427764,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.3023,
|
|
"mean_token_accuracy": 0.10066464468836785,
|
|
"num_tokens": 1021018.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.514344882965088,
|
|
"epoch": 0.04945249028611798,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.1687,
|
|
"mean_token_accuracy": 0.10436531826853752,
|
|
"num_tokens": 1029744.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.328309202194214,
|
|
"epoch": 0.049894030377958316,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.2636,
|
|
"mean_token_accuracy": 0.11038385182619095,
|
|
"num_tokens": 1038805.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.525923824310302,
|
|
"epoch": 0.050335570469798654,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.3197,
|
|
"mean_token_accuracy": 0.10082013010978699,
|
|
"num_tokens": 1047656.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.603262233734131,
|
|
"epoch": 0.050777110561639,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.3119,
|
|
"mean_token_accuracy": 0.10330245941877365,
|
|
"num_tokens": 1056598.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.506361103057861,
|
|
"epoch": 0.05121865065347934,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.3105,
|
|
"mean_token_accuracy": 0.10376007333397866,
|
|
"num_tokens": 1065226.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.43021969795227,
|
|
"epoch": 0.051660190745319676,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.2312,
|
|
"mean_token_accuracy": 0.10194071978330613,
|
|
"num_tokens": 1074661.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.51248574256897,
|
|
"epoch": 0.052101730837160014,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.3225,
|
|
"mean_token_accuracy": 0.10019931197166443,
|
|
"num_tokens": 1083921.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.486316394805908,
|
|
"epoch": 0.05254327092900035,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.2137,
|
|
"mean_token_accuracy": 0.10983922332525253,
|
|
"num_tokens": 1093399.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.439640522003174,
|
|
"epoch": 0.05298481102084069,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.2835,
|
|
"mean_token_accuracy": 0.10640830993652343,
|
|
"num_tokens": 1104065.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.37196102142334,
|
|
"epoch": 0.05342635111268103,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.1855,
|
|
"mean_token_accuracy": 0.10447794273495674,
|
|
"num_tokens": 1112995.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.374333763122559,
|
|
"epoch": 0.05386789120452137,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.219,
|
|
"mean_token_accuracy": 0.10373939201235771,
|
|
"num_tokens": 1121637.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.4547041893005375,
|
|
"epoch": 0.05430943129636171,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.163,
|
|
"mean_token_accuracy": 0.10560059025883675,
|
|
"num_tokens": 1131166.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.4077800750732425,
|
|
"epoch": 0.05475097138820205,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.1546,
|
|
"mean_token_accuracy": 0.11212797611951827,
|
|
"num_tokens": 1140888.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.458501863479614,
|
|
"epoch": 0.05519251148004239,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.3313,
|
|
"mean_token_accuracy": 0.10084073692560196,
|
|
"num_tokens": 1150278.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.399151372909546,
|
|
"epoch": 0.055634051571882726,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.2699,
|
|
"mean_token_accuracy": 0.10444999486207962,
|
|
"num_tokens": 1159348.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.549579715728759,
|
|
"epoch": 0.056075591663723064,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.2841,
|
|
"mean_token_accuracy": 0.1042952410876751,
|
|
"num_tokens": 1168883.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.408907222747803,
|
|
"epoch": 0.0565171317555634,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.1845,
|
|
"mean_token_accuracy": 0.10902434810996056,
|
|
"num_tokens": 1178572.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.410972738265992,
|
|
"epoch": 0.05695867184740375,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.2662,
|
|
"mean_token_accuracy": 0.10295297279953956,
|
|
"num_tokens": 1188909.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.352515697479248,
|
|
"epoch": 0.057400211939244085,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.1696,
|
|
"mean_token_accuracy": 0.10579917058348656,
|
|
"num_tokens": 1197705.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.353521823883057,
|
|
"epoch": 0.05784175203108442,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.0136,
|
|
"mean_token_accuracy": 0.11067867055535316,
|
|
"num_tokens": 1206351.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.337934875488282,
|
|
"epoch": 0.05828329212292476,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.1286,
|
|
"mean_token_accuracy": 0.1017768256366253,
|
|
"num_tokens": 1214984.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.323618602752686,
|
|
"epoch": 0.0587248322147651,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.22,
|
|
"mean_token_accuracy": 0.0986666016280651,
|
|
"num_tokens": 1224485.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.373797750473022,
|
|
"epoch": 0.05916637230660544,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.2399,
|
|
"mean_token_accuracy": 0.10024571865797043,
|
|
"num_tokens": 1233560.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.387822151184082,
|
|
"epoch": 0.05960791239844578,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.1624,
|
|
"mean_token_accuracy": 0.10045728534460067,
|
|
"num_tokens": 1242628.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.265125274658203,
|
|
"epoch": 0.06004945249028612,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.0658,
|
|
"mean_token_accuracy": 0.1067326933145523,
|
|
"num_tokens": 1251004.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.378535032272339,
|
|
"epoch": 0.06049099258212646,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.2571,
|
|
"mean_token_accuracy": 0.10440935268998146,
|
|
"num_tokens": 1260344.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.322955751419068,
|
|
"epoch": 0.0609325326739668,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.1572,
|
|
"mean_token_accuracy": 0.10920507833361626,
|
|
"num_tokens": 1269988.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.2962963581085205,
|
|
"epoch": 0.061374072765807135,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.1193,
|
|
"mean_token_accuracy": 0.11102982461452485,
|
|
"num_tokens": 1280912.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.252480220794678,
|
|
"epoch": 0.06181561285764747,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.134,
|
|
"mean_token_accuracy": 0.10760174319148064,
|
|
"num_tokens": 1289684.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.354262113571167,
|
|
"epoch": 0.06225715294948781,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.1721,
|
|
"mean_token_accuracy": 0.10398160740733146,
|
|
"num_tokens": 1298853.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.227016019821167,
|
|
"epoch": 0.06269869304132815,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.1271,
|
|
"mean_token_accuracy": 0.1127957746386528,
|
|
"num_tokens": 1309112.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.324345111846924,
|
|
"epoch": 0.0631402331331685,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.1092,
|
|
"mean_token_accuracy": 0.1057639792561531,
|
|
"num_tokens": 1319064.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.188746166229248,
|
|
"epoch": 0.06358177322500883,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.0766,
|
|
"mean_token_accuracy": 0.11342449262738227,
|
|
"num_tokens": 1327889.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.324895286560059,
|
|
"epoch": 0.06402331331684917,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.1054,
|
|
"mean_token_accuracy": 0.10539671033620834,
|
|
"num_tokens": 1337241.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.222482204437256,
|
|
"epoch": 0.06446485340868952,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.1636,
|
|
"mean_token_accuracy": 0.10495321676135064,
|
|
"num_tokens": 1346527.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.305452728271485,
|
|
"epoch": 0.06490639350052985,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.1429,
|
|
"mean_token_accuracy": 0.10441825911402702,
|
|
"num_tokens": 1355677.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.290005493164062,
|
|
"epoch": 0.06534793359237019,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.1298,
|
|
"mean_token_accuracy": 0.10936881825327874,
|
|
"num_tokens": 1364874.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.279782056808472,
|
|
"epoch": 0.06578947368421052,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.0692,
|
|
"mean_token_accuracy": 0.11476822644472122,
|
|
"num_tokens": 1373717.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.331944179534912,
|
|
"epoch": 0.06623101377605087,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.0294,
|
|
"mean_token_accuracy": 0.11214973554015159,
|
|
"num_tokens": 1382767.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.091894626617432,
|
|
"epoch": 0.0666725538678912,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.0713,
|
|
"mean_token_accuracy": 0.11100590229034424,
|
|
"num_tokens": 1391190.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.175401639938355,
|
|
"epoch": 0.06711409395973154,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.0763,
|
|
"mean_token_accuracy": 0.10921204090118408,
|
|
"num_tokens": 1400722.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.318567132949829,
|
|
"epoch": 0.06755563405157189,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.0907,
|
|
"mean_token_accuracy": 0.10661459416151046,
|
|
"num_tokens": 1409328.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.106989192962646,
|
|
"epoch": 0.06799717414341222,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.967,
|
|
"mean_token_accuracy": 0.10996146872639656,
|
|
"num_tokens": 1418504.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.248307847976685,
|
|
"epoch": 0.06843871423525257,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.1104,
|
|
"mean_token_accuracy": 0.10902469977736473,
|
|
"num_tokens": 1427690.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.239201641082763,
|
|
"epoch": 0.0688802543270929,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.091,
|
|
"mean_token_accuracy": 0.11118610724806785,
|
|
"num_tokens": 1436798.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.1204283237457275,
|
|
"epoch": 0.06932179441893324,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.0933,
|
|
"mean_token_accuracy": 0.10568799898028373,
|
|
"num_tokens": 1446357.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.168965148925781,
|
|
"epoch": 0.06976333451077357,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.0073,
|
|
"mean_token_accuracy": 0.11038993671536446,
|
|
"num_tokens": 1455998.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.229979085922241,
|
|
"epoch": 0.07020487460261392,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.0599,
|
|
"mean_token_accuracy": 0.10410151407122611,
|
|
"num_tokens": 1465237.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.097687721252441,
|
|
"epoch": 0.07064641469445426,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.024,
|
|
"mean_token_accuracy": 0.11839348077774048,
|
|
"num_tokens": 1474363.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.138771963119507,
|
|
"epoch": 0.0710879547862946,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.0872,
|
|
"mean_token_accuracy": 0.1139365516602993,
|
|
"num_tokens": 1483379.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.267211008071899,
|
|
"epoch": 0.07152949487813494,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.0619,
|
|
"mean_token_accuracy": 0.10780827179551125,
|
|
"num_tokens": 1492507.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.073677682876587,
|
|
"epoch": 0.07197103496997527,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.9431,
|
|
"mean_token_accuracy": 0.11598889455199242,
|
|
"num_tokens": 1500888.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.079563140869141,
|
|
"epoch": 0.07241257506181561,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.9983,
|
|
"mean_token_accuracy": 0.11227924451231956,
|
|
"num_tokens": 1510310.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.121931362152099,
|
|
"epoch": 0.07285411515365595,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.9855,
|
|
"mean_token_accuracy": 0.11764683723449706,
|
|
"num_tokens": 1519427.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.14368166923523,
|
|
"epoch": 0.07329565524549629,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.0087,
|
|
"mean_token_accuracy": 0.10792600363492966,
|
|
"num_tokens": 1529456.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.080411815643311,
|
|
"epoch": 0.07373719533733664,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.9375,
|
|
"mean_token_accuracy": 0.11380904093384743,
|
|
"num_tokens": 1537695.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.071755599975586,
|
|
"epoch": 0.07417873542917697,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.0784,
|
|
"mean_token_accuracy": 0.11253369823098183,
|
|
"num_tokens": 1547511.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.204211902618408,
|
|
"epoch": 0.07462027552101731,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.0709,
|
|
"mean_token_accuracy": 0.11463971808552742,
|
|
"num_tokens": 1557035.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.083140897750854,
|
|
"epoch": 0.07506181561285764,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.0065,
|
|
"mean_token_accuracy": 0.11546228975057601,
|
|
"num_tokens": 1566773.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.061517763137817,
|
|
"epoch": 0.07550335570469799,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.0081,
|
|
"mean_token_accuracy": 0.10918990075588227,
|
|
"num_tokens": 1576873.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.128572607040406,
|
|
"epoch": 0.07594489579653832,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.0375,
|
|
"mean_token_accuracy": 0.10865660831332206,
|
|
"num_tokens": 1586170.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.218125915527343,
|
|
"epoch": 0.07638643588837866,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.0778,
|
|
"mean_token_accuracy": 0.11018856391310691,
|
|
"num_tokens": 1596054.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.02945466041565,
|
|
"epoch": 0.07682797598021901,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.9583,
|
|
"mean_token_accuracy": 0.11728574708104134,
|
|
"num_tokens": 1604544.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.105824756622314,
|
|
"epoch": 0.07726951607205934,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.9789,
|
|
"mean_token_accuracy": 0.1162014789879322,
|
|
"num_tokens": 1614580.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.058492374420166,
|
|
"epoch": 0.07771105616389969,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.0641,
|
|
"mean_token_accuracy": 0.11256316900253296,
|
|
"num_tokens": 1624701.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.0211296558380125,
|
|
"epoch": 0.07815259625574002,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.9931,
|
|
"mean_token_accuracy": 0.11021944805979729,
|
|
"num_tokens": 1634085.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.09322075843811,
|
|
"epoch": 0.07859413634758036,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.9645,
|
|
"mean_token_accuracy": 0.1174542985856533,
|
|
"num_tokens": 1643190.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.966829776763916,
|
|
"epoch": 0.0790356764394207,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.006,
|
|
"mean_token_accuracy": 0.11372746750712395,
|
|
"num_tokens": 1652705.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.127198505401611,
|
|
"epoch": 0.07947721653126104,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.977,
|
|
"mean_token_accuracy": 0.10978531762957573,
|
|
"num_tokens": 1662210.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.1131603717803955,
|
|
"epoch": 0.07991875662310138,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.0268,
|
|
"mean_token_accuracy": 0.10922672674059868,
|
|
"num_tokens": 1671893.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.049384355545044,
|
|
"epoch": 0.08036029671494171,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.9779,
|
|
"mean_token_accuracy": 0.11501859724521638,
|
|
"num_tokens": 1681217.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.015186929702759,
|
|
"epoch": 0.08080183680678206,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.988,
|
|
"mean_token_accuracy": 0.1133071318268776,
|
|
"num_tokens": 1690447.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.087394189834595,
|
|
"epoch": 0.08124337689862239,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.0741,
|
|
"mean_token_accuracy": 0.10595951378345489,
|
|
"num_tokens": 1700355.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.045471048355102,
|
|
"epoch": 0.08168491699046274,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.9851,
|
|
"mean_token_accuracy": 0.10544866621494293,
|
|
"num_tokens": 1709449.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.048018169403076,
|
|
"epoch": 0.08212645708230307,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.0167,
|
|
"mean_token_accuracy": 0.105999456346035,
|
|
"num_tokens": 1718838.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.981620121002197,
|
|
"epoch": 0.08256799717414341,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.9721,
|
|
"mean_token_accuracy": 0.11307689547538757,
|
|
"num_tokens": 1728594.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.088650274276733,
|
|
"epoch": 0.08300953726598376,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.0148,
|
|
"mean_token_accuracy": 0.11065684705972671,
|
|
"num_tokens": 1738814.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.006063842773438,
|
|
"epoch": 0.08345107735782409,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.9401,
|
|
"mean_token_accuracy": 0.11795193180441857,
|
|
"num_tokens": 1747644.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.048807621002197,
|
|
"epoch": 0.08389261744966443,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.9822,
|
|
"mean_token_accuracy": 0.11285707354545593,
|
|
"num_tokens": 1757489.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.994456195831299,
|
|
"epoch": 0.08433415754150476,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.8881,
|
|
"mean_token_accuracy": 0.12073725908994674,
|
|
"num_tokens": 1767546.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.929489183425903,
|
|
"epoch": 0.08477569763334511,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.9528,
|
|
"mean_token_accuracy": 0.10833125934004784,
|
|
"num_tokens": 1776035.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.031561088562012,
|
|
"epoch": 0.08521723772518544,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.0163,
|
|
"mean_token_accuracy": 0.10963534265756607,
|
|
"num_tokens": 1786161.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.13347601890564,
|
|
"epoch": 0.08565877781702579,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.0758,
|
|
"mean_token_accuracy": 0.10902466773986816,
|
|
"num_tokens": 1796093.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.994558525085449,
|
|
"epoch": 0.08610031790886613,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.9267,
|
|
"mean_token_accuracy": 0.10800953432917595,
|
|
"num_tokens": 1805574.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.005662727355957,
|
|
"epoch": 0.08654185800070646,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.9528,
|
|
"mean_token_accuracy": 0.11506856232881546,
|
|
"num_tokens": 1815175.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.939174652099609,
|
|
"epoch": 0.08698339809254681,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.8892,
|
|
"mean_token_accuracy": 0.11544275358319282,
|
|
"num_tokens": 1824683.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.9920509338378904,
|
|
"epoch": 0.08742493818438714,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.8652,
|
|
"mean_token_accuracy": 0.1142121821641922,
|
|
"num_tokens": 1833174.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.92423644065857,
|
|
"epoch": 0.08786647827622748,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.9598,
|
|
"mean_token_accuracy": 0.11292968466877937,
|
|
"num_tokens": 1842409.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.785798788070679,
|
|
"epoch": 0.08830801836806781,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.8616,
|
|
"mean_token_accuracy": 0.11990160048007965,
|
|
"num_tokens": 1851441.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.146481227874756,
|
|
"epoch": 0.08874955845990816,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499999998589561,
|
|
"loss": 6.9982,
|
|
"mean_token_accuracy": 0.11039657667279243,
|
|
"num_tokens": 1861188.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.901903963088989,
|
|
"epoch": 0.0891910985517485,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999999928596523,
|
|
"loss": 6.9301,
|
|
"mean_token_accuracy": 0.11363181099295616,
|
|
"num_tokens": 1870284.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.84821515083313,
|
|
"epoch": 0.08963263864358884,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999999827221219,
|
|
"loss": 6.8983,
|
|
"mean_token_accuracy": 0.12304212301969528,
|
|
"num_tokens": 1879744.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.960662460327148,
|
|
"epoch": 0.09007417873542918,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999999681769696,
|
|
"loss": 6.8983,
|
|
"mean_token_accuracy": 0.11716285720467567,
|
|
"num_tokens": 1889241.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.971296596527099,
|
|
"epoch": 0.09051571882726951,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499999949224196,
|
|
"loss": 6.9084,
|
|
"mean_token_accuracy": 0.1200313277542591,
|
|
"num_tokens": 1898247.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.955649042129517,
|
|
"epoch": 0.09095725891910986,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999999258638013,
|
|
"loss": 6.8611,
|
|
"mean_token_accuracy": 0.11644072383642197,
|
|
"num_tokens": 1907559.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.793795824050903,
|
|
"epoch": 0.09139879901095019,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999998980957861,
|
|
"loss": 6.8669,
|
|
"mean_token_accuracy": 0.12169807255268097,
|
|
"num_tokens": 1917072.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.9457625389099125,
|
|
"epoch": 0.09184033910279053,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999998659201508,
|
|
"loss": 6.8238,
|
|
"mean_token_accuracy": 0.1175873689353466,
|
|
"num_tokens": 1926597.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.854114770889282,
|
|
"epoch": 0.09228187919463088,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999998293368961,
|
|
"loss": 6.8766,
|
|
"mean_token_accuracy": 0.11491318792104721,
|
|
"num_tokens": 1935978.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.869282388687134,
|
|
"epoch": 0.09272341928647121,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999997883460227,
|
|
"loss": 6.8304,
|
|
"mean_token_accuracy": 0.11738137528300285,
|
|
"num_tokens": 1944424.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.931444597244263,
|
|
"epoch": 0.09316495937831155,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999997429475314,
|
|
"loss": 6.7926,
|
|
"mean_token_accuracy": 0.1264521062374115,
|
|
"num_tokens": 1953844.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.838017129898072,
|
|
"epoch": 0.09360649947015189,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999996931414232,
|
|
"loss": 6.8929,
|
|
"mean_token_accuracy": 0.12035574093461036,
|
|
"num_tokens": 1963974.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.908746671676636,
|
|
"epoch": 0.09404803956199223,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999996389276988,
|
|
"loss": 6.8573,
|
|
"mean_token_accuracy": 0.12281356453895569,
|
|
"num_tokens": 1973466.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.815357208251953,
|
|
"epoch": 0.09448957965383256,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999995803063596,
|
|
"loss": 6.8649,
|
|
"mean_token_accuracy": 0.11969125345349312,
|
|
"num_tokens": 1983478.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.947906064987182,
|
|
"epoch": 0.0949311197456729,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999995172774065,
|
|
"loss": 6.9373,
|
|
"mean_token_accuracy": 0.11548090726137161,
|
|
"num_tokens": 1992775.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.954066181182862,
|
|
"epoch": 0.09537265983751325,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999994498408408,
|
|
"loss": 6.9065,
|
|
"mean_token_accuracy": 0.11163463667035103,
|
|
"num_tokens": 2002526.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.880347061157226,
|
|
"epoch": 0.09581419992935358,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999993779966639,
|
|
"loss": 6.9226,
|
|
"mean_token_accuracy": 0.11343899965286255,
|
|
"num_tokens": 2012476.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.772713136672974,
|
|
"epoch": 0.09625574002119393,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999993017448771,
|
|
"loss": 6.7619,
|
|
"mean_token_accuracy": 0.1315491996705532,
|
|
"num_tokens": 2021252.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.972479009628296,
|
|
"epoch": 0.09669728011303426,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999992210854821,
|
|
"loss": 6.9025,
|
|
"mean_token_accuracy": 0.1197818472981453,
|
|
"num_tokens": 2031438.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.9433167457580565,
|
|
"epoch": 0.0971388202048746,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999991360184801,
|
|
"loss": 6.9497,
|
|
"mean_token_accuracy": 0.11331594586372376,
|
|
"num_tokens": 2041319.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.875679302215576,
|
|
"epoch": 0.09758036029671494,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999990465438731,
|
|
"loss": 6.9417,
|
|
"mean_token_accuracy": 0.11621764153242112,
|
|
"num_tokens": 2052060.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.868831157684326,
|
|
"epoch": 0.09802190038855528,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999989526616628,
|
|
"loss": 6.8207,
|
|
"mean_token_accuracy": 0.12271343320608138,
|
|
"num_tokens": 2061331.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.84274697303772,
|
|
"epoch": 0.09846344048039563,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999988543718509,
|
|
"loss": 6.8327,
|
|
"mean_token_accuracy": 0.1182619109749794,
|
|
"num_tokens": 2070006.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.921954727172851,
|
|
"epoch": 0.09890498057223596,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999987516744394,
|
|
"loss": 6.7824,
|
|
"mean_token_accuracy": 0.12447450086474418,
|
|
"num_tokens": 2079089.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.797588872909546,
|
|
"epoch": 0.0993465206640763,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999986445694303,
|
|
"loss": 6.778,
|
|
"mean_token_accuracy": 0.118412546813488,
|
|
"num_tokens": 2087237.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.792767906188965,
|
|
"epoch": 0.09978806075591663,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999985330568258,
|
|
"loss": 6.7448,
|
|
"mean_token_accuracy": 0.12214136868715286,
|
|
"num_tokens": 2096598.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.833769607543945,
|
|
"epoch": 0.10022960084775698,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999984171366278,
|
|
"loss": 6.8458,
|
|
"mean_token_accuracy": 0.11508344933390617,
|
|
"num_tokens": 2106106.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.860817527770996,
|
|
"epoch": 0.10067114093959731,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499998296808839,
|
|
"loss": 6.8066,
|
|
"mean_token_accuracy": 0.11775731146335602,
|
|
"num_tokens": 2115478.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.8433990478515625,
|
|
"epoch": 0.10111268103143765,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004999981720734615,
|
|
"loss": 6.8429,
|
|
"mean_token_accuracy": 0.11517784297466278,
|
|
"num_tokens": 2124439.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.893320178985595,
|
|
"epoch": 0.101554221123278,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999980429304977,
|
|
"loss": 6.861,
|
|
"mean_token_accuracy": 0.11661542877554894,
|
|
"num_tokens": 2133718.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.720952081680298,
|
|
"epoch": 0.10199576121511833,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999979093799502,
|
|
"loss": 6.7669,
|
|
"mean_token_accuracy": 0.1219759725034237,
|
|
"num_tokens": 2142978.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.826765871047973,
|
|
"epoch": 0.10243730130695868,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999977714218217,
|
|
"loss": 6.8287,
|
|
"mean_token_accuracy": 0.11483320519328118,
|
|
"num_tokens": 2152250.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.841332817077637,
|
|
"epoch": 0.102878841398799,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999976290561147,
|
|
"loss": 6.8186,
|
|
"mean_token_accuracy": 0.11421233564615249,
|
|
"num_tokens": 2161620.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.8951427936553955,
|
|
"epoch": 0.10332038149063935,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999974822828322,
|
|
"loss": 6.8321,
|
|
"mean_token_accuracy": 0.11468955874443054,
|
|
"num_tokens": 2170856.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.783407306671142,
|
|
"epoch": 0.10376192158247968,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499997331101977,
|
|
"loss": 6.8226,
|
|
"mean_token_accuracy": 0.1140426091849804,
|
|
"num_tokens": 2180926.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.841979598999023,
|
|
"epoch": 0.10420346167432003,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499997175513552,
|
|
"loss": 6.7918,
|
|
"mean_token_accuracy": 0.11650402471423149,
|
|
"num_tokens": 2190248.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.812575197219848,
|
|
"epoch": 0.10464500176616037,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999970155175603,
|
|
"loss": 6.8152,
|
|
"mean_token_accuracy": 0.12006641253829002,
|
|
"num_tokens": 2199833.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.79837212562561,
|
|
"epoch": 0.1050865418580007,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499996851114005,
|
|
"loss": 6.7952,
|
|
"mean_token_accuracy": 0.12233175113797187,
|
|
"num_tokens": 2208240.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.796438360214234,
|
|
"epoch": 0.10552808194984105,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999966823028894,
|
|
"loss": 6.8365,
|
|
"mean_token_accuracy": 0.11369045302271844,
|
|
"num_tokens": 2218758.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.935247182846069,
|
|
"epoch": 0.10596962204168138,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999965090842168,
|
|
"loss": 6.8302,
|
|
"mean_token_accuracy": 0.12288962900638581,
|
|
"num_tokens": 2228443.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.712041759490967,
|
|
"epoch": 0.10641116213352173,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999963314579905,
|
|
"loss": 6.6787,
|
|
"mean_token_accuracy": 0.13284276723861693,
|
|
"num_tokens": 2236787.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.800426197052002,
|
|
"epoch": 0.10685270222536206,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999961494242139,
|
|
"loss": 6.8593,
|
|
"mean_token_accuracy": 0.11500039100646972,
|
|
"num_tokens": 2247089.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.786765146255493,
|
|
"epoch": 0.1072942423172024,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999959629828908,
|
|
"loss": 6.7664,
|
|
"mean_token_accuracy": 0.11581304892897606,
|
|
"num_tokens": 2256045.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.886348628997803,
|
|
"epoch": 0.10773578240904275,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999957721340248,
|
|
"loss": 6.8384,
|
|
"mean_token_accuracy": 0.12041957154870034,
|
|
"num_tokens": 2265835.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.722246551513672,
|
|
"epoch": 0.10817732250088308,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999955768776195,
|
|
"loss": 6.7786,
|
|
"mean_token_accuracy": 0.12380016893148423,
|
|
"num_tokens": 2275318.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.808089828491211,
|
|
"epoch": 0.10861886259272342,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999953772136788,
|
|
"loss": 6.7658,
|
|
"mean_token_accuracy": 0.12278728261590004,
|
|
"num_tokens": 2284821.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.8324737548828125,
|
|
"epoch": 0.10906040268456375,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999951731422068,
|
|
"loss": 6.7482,
|
|
"mean_token_accuracy": 0.11858468577265739,
|
|
"num_tokens": 2294013.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.786966562271118,
|
|
"epoch": 0.1095019427764041,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999949646632072,
|
|
"loss": 6.73,
|
|
"mean_token_accuracy": 0.12245445623993874,
|
|
"num_tokens": 2302727.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.705034589767456,
|
|
"epoch": 0.10994348286824443,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999947517766842,
|
|
"loss": 6.7649,
|
|
"mean_token_accuracy": 0.12241661176085472,
|
|
"num_tokens": 2312032.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.982846593856811,
|
|
"epoch": 0.11038502296008477,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499994534482642,
|
|
"loss": 6.8443,
|
|
"mean_token_accuracy": 0.11787378117442131,
|
|
"num_tokens": 2321839.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.719681882858277,
|
|
"epoch": 0.11082656305192512,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999943127810847,
|
|
"loss": 6.8137,
|
|
"mean_token_accuracy": 0.11633599549531937,
|
|
"num_tokens": 2331255.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.744579744338989,
|
|
"epoch": 0.11126810314376545,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999940866720169,
|
|
"loss": 6.6363,
|
|
"mean_token_accuracy": 0.13151753917336464,
|
|
"num_tokens": 2340038.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.680500268936157,
|
|
"epoch": 0.1117096432356058,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999938561554429,
|
|
"loss": 6.7486,
|
|
"mean_token_accuracy": 0.1244722306728363,
|
|
"num_tokens": 2348901.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.772228145599366,
|
|
"epoch": 0.11215118332744613,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999936212313672,
|
|
"loss": 6.827,
|
|
"mean_token_accuracy": 0.11700050979852676,
|
|
"num_tokens": 2358842.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.788944578170776,
|
|
"epoch": 0.11259272341928647,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999933818997943,
|
|
"loss": 6.7218,
|
|
"mean_token_accuracy": 0.1224422350525856,
|
|
"num_tokens": 2368650.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.765577077865601,
|
|
"epoch": 0.1130342635111268,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999931381607292,
|
|
"loss": 6.7811,
|
|
"mean_token_accuracy": 0.12511691078543663,
|
|
"num_tokens": 2377916.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.782421112060547,
|
|
"epoch": 0.11347580360296715,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999928900141764,
|
|
"loss": 6.7279,
|
|
"mean_token_accuracy": 0.12245306149125099,
|
|
"num_tokens": 2387507.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.7623984813690186,
|
|
"epoch": 0.1139173436948075,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499992637460141,
|
|
"loss": 6.7762,
|
|
"mean_token_accuracy": 0.1228838860988617,
|
|
"num_tokens": 2396148.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.7144958019256595,
|
|
"epoch": 0.11435888378664782,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999923804986275,
|
|
"loss": 6.6356,
|
|
"mean_token_accuracy": 0.12269090339541436,
|
|
"num_tokens": 2404891.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.786207437515259,
|
|
"epoch": 0.11480042387848817,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999921191296415,
|
|
"loss": 6.6766,
|
|
"mean_token_accuracy": 0.12154053971171379,
|
|
"num_tokens": 2414406.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.703838205337524,
|
|
"epoch": 0.1152419639703285,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999918533531877,
|
|
"loss": 6.7829,
|
|
"mean_token_accuracy": 0.12308658063411712,
|
|
"num_tokens": 2424363.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.811527252197266,
|
|
"epoch": 0.11568350406216885,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999915831692714,
|
|
"loss": 6.7213,
|
|
"mean_token_accuracy": 0.12458684146404267,
|
|
"num_tokens": 2433753.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.642784214019775,
|
|
"epoch": 0.11612504415400918,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999913085778981,
|
|
"loss": 6.7353,
|
|
"mean_token_accuracy": 0.1179688699543476,
|
|
"num_tokens": 2443275.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.845086908340454,
|
|
"epoch": 0.11656658424584952,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999910295790729,
|
|
"loss": 6.7522,
|
|
"mean_token_accuracy": 0.116317979991436,
|
|
"num_tokens": 2452510.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.789072132110595,
|
|
"epoch": 0.11700812433768987,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999907461728014,
|
|
"loss": 6.8496,
|
|
"mean_token_accuracy": 0.1186776876449585,
|
|
"num_tokens": 2462742.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.73516001701355,
|
|
"epoch": 0.1174496644295302,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999904583590893,
|
|
"loss": 6.7087,
|
|
"mean_token_accuracy": 0.11719698682427407,
|
|
"num_tokens": 2471409.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.80999174118042,
|
|
"epoch": 0.11789120452137054,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999901661379418,
|
|
"loss": 6.66,
|
|
"mean_token_accuracy": 0.12834221944212915,
|
|
"num_tokens": 2481011.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.656212949752808,
|
|
"epoch": 0.11833274461321087,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999898695093652,
|
|
"loss": 6.7655,
|
|
"mean_token_accuracy": 0.1210456795990467,
|
|
"num_tokens": 2490664.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.774575805664062,
|
|
"epoch": 0.11877428470505122,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999895684733648,
|
|
"loss": 6.6871,
|
|
"mean_token_accuracy": 0.12933790683746338,
|
|
"num_tokens": 2499799.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.75890417098999,
|
|
"epoch": 0.11921582479689156,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004999892630299467,
|
|
"loss": 6.6744,
|
|
"mean_token_accuracy": 0.12494029551744461,
|
|
"num_tokens": 2508780.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.714679288864136,
|
|
"epoch": 0.1196573648887319,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999889531791171,
|
|
"loss": 6.6833,
|
|
"mean_token_accuracy": 0.12272755652666092,
|
|
"num_tokens": 2517741.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.662789583206177,
|
|
"epoch": 0.12009890498057224,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999886389208817,
|
|
"loss": 6.7716,
|
|
"mean_token_accuracy": 0.12046518027782441,
|
|
"num_tokens": 2528742.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.69284987449646,
|
|
"epoch": 0.12054044507241257,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999883202552468,
|
|
"loss": 6.7043,
|
|
"mean_token_accuracy": 0.12755436450242996,
|
|
"num_tokens": 2538609.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.828431463241577,
|
|
"epoch": 0.12098198516425292,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999879971822189,
|
|
"loss": 6.684,
|
|
"mean_token_accuracy": 0.11924384832382202,
|
|
"num_tokens": 2547772.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.571238899230957,
|
|
"epoch": 0.12142352525609325,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999876697018038,
|
|
"loss": 6.6582,
|
|
"mean_token_accuracy": 0.12748303934931754,
|
|
"num_tokens": 2556114.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.8254400253295895,
|
|
"epoch": 0.1218650653479336,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999873378140085,
|
|
"loss": 6.7179,
|
|
"mean_token_accuracy": 0.1250918261706829,
|
|
"num_tokens": 2566814.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.614608812332153,
|
|
"epoch": 0.12230660543977394,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999870015188389,
|
|
"loss": 6.6667,
|
|
"mean_token_accuracy": 0.12528225034475327,
|
|
"num_tokens": 2576030.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.711950302124023,
|
|
"epoch": 0.12274814553161427,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999866608163021,
|
|
"loss": 6.689,
|
|
"mean_token_accuracy": 0.12896783277392387,
|
|
"num_tokens": 2585756.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.719356441497803,
|
|
"epoch": 0.12318968562345461,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999863157064045,
|
|
"loss": 6.7433,
|
|
"mean_token_accuracy": 0.12513794749975204,
|
|
"num_tokens": 2595676.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.758820867538452,
|
|
"epoch": 0.12363122571529495,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999859661891529,
|
|
"loss": 6.7445,
|
|
"mean_token_accuracy": 0.12377320975065231,
|
|
"num_tokens": 2606197.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.740264415740967,
|
|
"epoch": 0.12407276580713529,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999856122645543,
|
|
"loss": 6.6646,
|
|
"mean_token_accuracy": 0.12415967881679535,
|
|
"num_tokens": 2615311.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.632203722000122,
|
|
"epoch": 0.12451430589897562,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999852539326154,
|
|
"loss": 6.5799,
|
|
"mean_token_accuracy": 0.1287233628332615,
|
|
"num_tokens": 2624074.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.623841571807861,
|
|
"epoch": 0.12495584599081597,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999848911933434,
|
|
"loss": 6.7141,
|
|
"mean_token_accuracy": 0.13292624652385712,
|
|
"num_tokens": 2633877.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.68168888092041,
|
|
"epoch": 0.1253973860826563,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999845240467453,
|
|
"loss": 6.6526,
|
|
"mean_token_accuracy": 0.12299527004361152,
|
|
"num_tokens": 2643330.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.702590560913086,
|
|
"epoch": 0.12583892617449666,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999841524928282,
|
|
"loss": 6.6348,
|
|
"mean_token_accuracy": 0.12881363406777382,
|
|
"num_tokens": 2652070.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.6873023986816404,
|
|
"epoch": 0.126280466266337,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999837765315997,
|
|
"loss": 6.6718,
|
|
"mean_token_accuracy": 0.12390449419617652,
|
|
"num_tokens": 2660546.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.522921085357666,
|
|
"epoch": 0.12672200635817732,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999833961630669,
|
|
"loss": 6.5631,
|
|
"mean_token_accuracy": 0.13146114349365234,
|
|
"num_tokens": 2669938.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.8073399543762205,
|
|
"epoch": 0.12716354645001765,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999830113872374,
|
|
"loss": 6.6919,
|
|
"mean_token_accuracy": 0.12384787425398827,
|
|
"num_tokens": 2679814.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.547947025299072,
|
|
"epoch": 0.127605086541858,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999826222041186,
|
|
"loss": 6.6066,
|
|
"mean_token_accuracy": 0.1329873576760292,
|
|
"num_tokens": 2688733.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.649660348892212,
|
|
"epoch": 0.12804662663369834,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999822286137182,
|
|
"loss": 6.5858,
|
|
"mean_token_accuracy": 0.1287431985139847,
|
|
"num_tokens": 2697744.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.6083179950714115,
|
|
"epoch": 0.12848816672553867,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999818306160439,
|
|
"loss": 6.5587,
|
|
"mean_token_accuracy": 0.13241407200694083,
|
|
"num_tokens": 2707037.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.707999324798584,
|
|
"epoch": 0.12892970681737903,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999814282111034,
|
|
"loss": 6.7159,
|
|
"mean_token_accuracy": 0.12165460363030434,
|
|
"num_tokens": 2717345.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.706764125823975,
|
|
"epoch": 0.12937124690921936,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999810213989047,
|
|
"loss": 6.6771,
|
|
"mean_token_accuracy": 0.11996371075510978,
|
|
"num_tokens": 2726892.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.606377267837525,
|
|
"epoch": 0.1298127870010597,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999806101794558,
|
|
"loss": 6.6282,
|
|
"mean_token_accuracy": 0.12699908390641212,
|
|
"num_tokens": 2736479.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.772217559814453,
|
|
"epoch": 0.13025432709290002,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999801945527648,
|
|
"loss": 6.6764,
|
|
"mean_token_accuracy": 0.12172863110899926,
|
|
"num_tokens": 2745998.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.60609245300293,
|
|
"epoch": 0.13069586718474038,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999797745188395,
|
|
"loss": 6.6578,
|
|
"mean_token_accuracy": 0.12872695848345755,
|
|
"num_tokens": 2754346.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.701602792739868,
|
|
"epoch": 0.13113740727658071,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999793500776886,
|
|
"loss": 6.6094,
|
|
"mean_token_accuracy": 0.13089651241898537,
|
|
"num_tokens": 2763391.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.633615016937256,
|
|
"epoch": 0.13157894736842105,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999789212293201,
|
|
"loss": 6.669,
|
|
"mean_token_accuracy": 0.12867793068289757,
|
|
"num_tokens": 2772764.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.7330268859863285,
|
|
"epoch": 0.1320204874602614,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999784879737423,
|
|
"loss": 6.7564,
|
|
"mean_token_accuracy": 0.1226215623319149,
|
|
"num_tokens": 2782312.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.67516393661499,
|
|
"epoch": 0.13246202755210174,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999780503109642,
|
|
"loss": 6.6484,
|
|
"mean_token_accuracy": 0.12383122742176056,
|
|
"num_tokens": 2791159.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.610153341293335,
|
|
"epoch": 0.13290356764394207,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999776082409939,
|
|
"loss": 6.4972,
|
|
"mean_token_accuracy": 0.13475448414683341,
|
|
"num_tokens": 2799319.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.595534706115723,
|
|
"epoch": 0.1333451077357824,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999771617638401,
|
|
"loss": 6.6108,
|
|
"mean_token_accuracy": 0.1235594168305397,
|
|
"num_tokens": 2807401.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.707736253738403,
|
|
"epoch": 0.13378664782762276,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999767108795118,
|
|
"loss": 6.661,
|
|
"mean_token_accuracy": 0.1273370273411274,
|
|
"num_tokens": 2817734.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.612422895431519,
|
|
"epoch": 0.1342281879194631,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999762555880176,
|
|
"loss": 6.6679,
|
|
"mean_token_accuracy": 0.12645771428942681,
|
|
"num_tokens": 2828235.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.702644395828247,
|
|
"epoch": 0.13466972801130342,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999757958893666,
|
|
"loss": 6.6872,
|
|
"mean_token_accuracy": 0.12617624551057816,
|
|
"num_tokens": 2837453.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.566971969604492,
|
|
"epoch": 0.13511126810314378,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999753317835677,
|
|
"loss": 6.6608,
|
|
"mean_token_accuracy": 0.12031328305602074,
|
|
"num_tokens": 2847055.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.747590446472168,
|
|
"epoch": 0.1355528081949841,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999748632706299,
|
|
"loss": 6.6333,
|
|
"mean_token_accuracy": 0.12874888330698014,
|
|
"num_tokens": 2857101.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.58017520904541,
|
|
"epoch": 0.13599434828682444,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999743903505626,
|
|
"loss": 6.5493,
|
|
"mean_token_accuracy": 0.12921440675854684,
|
|
"num_tokens": 2866685.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.686506080627441,
|
|
"epoch": 0.13643588837866477,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999739130233749,
|
|
"loss": 6.6483,
|
|
"mean_token_accuracy": 0.12603347525000572,
|
|
"num_tokens": 2876022.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.676938915252686,
|
|
"epoch": 0.13687742847050513,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999734312890761,
|
|
"loss": 6.5654,
|
|
"mean_token_accuracy": 0.1277615949511528,
|
|
"num_tokens": 2885560.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.552069282531738,
|
|
"epoch": 0.13731896856234546,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999729451476757,
|
|
"loss": 6.6064,
|
|
"mean_token_accuracy": 0.1283570185303688,
|
|
"num_tokens": 2894686.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.67106065750122,
|
|
"epoch": 0.1377605086541858,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999724545991835,
|
|
"loss": 6.6135,
|
|
"mean_token_accuracy": 0.13272278234362603,
|
|
"num_tokens": 2904390.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.641124057769775,
|
|
"epoch": 0.13820204874602615,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999719596436086,
|
|
"loss": 6.6751,
|
|
"mean_token_accuracy": 0.12594080567359925,
|
|
"num_tokens": 2913311.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.69909701347351,
|
|
"epoch": 0.13864358883786648,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999714602809611,
|
|
"loss": 6.5549,
|
|
"mean_token_accuracy": 0.13006579801440238,
|
|
"num_tokens": 2923196.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.554364538192749,
|
|
"epoch": 0.1390851289297068,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999709565112506,
|
|
"loss": 6.6195,
|
|
"mean_token_accuracy": 0.12607380226254464,
|
|
"num_tokens": 2932813.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.618018245697021,
|
|
"epoch": 0.13952666902154715,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499970448334487,
|
|
"loss": 6.5517,
|
|
"mean_token_accuracy": 0.1182281494140625,
|
|
"num_tokens": 2942694.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.567258405685425,
|
|
"epoch": 0.1399682091133875,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999699357506803,
|
|
"loss": 6.4833,
|
|
"mean_token_accuracy": 0.13758974224328996,
|
|
"num_tokens": 2950932.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.665033578872681,
|
|
"epoch": 0.14040974920522784,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999694187598406,
|
|
"loss": 6.5959,
|
|
"mean_token_accuracy": 0.13096074685454367,
|
|
"num_tokens": 2960102.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.5607537746429445,
|
|
"epoch": 0.14085128929706817,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004999688973619777,
|
|
"loss": 6.5666,
|
|
"mean_token_accuracy": 0.12616149932146073,
|
|
"num_tokens": 2969968.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.565665245056152,
|
|
"epoch": 0.14129282938890853,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999683715571022,
|
|
"loss": 6.5376,
|
|
"mean_token_accuracy": 0.13295454159379005,
|
|
"num_tokens": 2978880.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.6195861339569095,
|
|
"epoch": 0.14173436948074886,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999678413452242,
|
|
"loss": 6.5692,
|
|
"mean_token_accuracy": 0.1263133704662323,
|
|
"num_tokens": 2988369.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.635553073883057,
|
|
"epoch": 0.1421759095725892,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999673067263542,
|
|
"loss": 6.6144,
|
|
"mean_token_accuracy": 0.12454515546560288,
|
|
"num_tokens": 2997070.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.616920137405396,
|
|
"epoch": 0.14261744966442952,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999667677005026,
|
|
"loss": 6.5553,
|
|
"mean_token_accuracy": 0.13325243517756463,
|
|
"num_tokens": 3006547.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.574477910995483,
|
|
"epoch": 0.14305898975626988,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999662242676799,
|
|
"loss": 6.5792,
|
|
"mean_token_accuracy": 0.12996308133006096,
|
|
"num_tokens": 3015821.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.618298435211182,
|
|
"epoch": 0.1435005298481102,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999656764278968,
|
|
"loss": 6.5491,
|
|
"mean_token_accuracy": 0.13459995537996292,
|
|
"num_tokens": 3024750.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.57071361541748,
|
|
"epoch": 0.14394206993995054,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999651241811642,
|
|
"loss": 6.5191,
|
|
"mean_token_accuracy": 0.13164762035012245,
|
|
"num_tokens": 3033345.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.575192975997925,
|
|
"epoch": 0.1443836100317909,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999645675274925,
|
|
"loss": 6.4902,
|
|
"mean_token_accuracy": 0.13214875981211663,
|
|
"num_tokens": 3042060.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.564555883407593,
|
|
"epoch": 0.14482515012363123,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999640064668931,
|
|
"loss": 6.6404,
|
|
"mean_token_accuracy": 0.12763455510139465,
|
|
"num_tokens": 3052490.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.715090990066528,
|
|
"epoch": 0.14526669021547156,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999634409993766,
|
|
"loss": 6.6155,
|
|
"mean_token_accuracy": 0.12552304938435555,
|
|
"num_tokens": 3061934.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.513729286193848,
|
|
"epoch": 0.1457082303073119,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999628711249544,
|
|
"loss": 6.5198,
|
|
"mean_token_accuracy": 0.13856697753071784,
|
|
"num_tokens": 3070890.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.682709264755249,
|
|
"epoch": 0.14614977039915225,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999622968436373,
|
|
"loss": 6.5315,
|
|
"mean_token_accuracy": 0.128802065551281,
|
|
"num_tokens": 3079933.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.47434253692627,
|
|
"epoch": 0.14659131049099258,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999617181554369,
|
|
"loss": 6.6016,
|
|
"mean_token_accuracy": 0.13180896043777465,
|
|
"num_tokens": 3089910.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.710703754425049,
|
|
"epoch": 0.1470328505828329,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999611350603643,
|
|
"loss": 6.5781,
|
|
"mean_token_accuracy": 0.13360659033060074,
|
|
"num_tokens": 3098676.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.531248569488525,
|
|
"epoch": 0.14747439067467327,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499960547558431,
|
|
"loss": 6.69,
|
|
"mean_token_accuracy": 0.12630268037319184,
|
|
"num_tokens": 3109055.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.600419187545777,
|
|
"epoch": 0.1479159307665136,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999599556496486,
|
|
"loss": 6.5276,
|
|
"mean_token_accuracy": 0.13437643125653267,
|
|
"num_tokens": 3117517.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.542807102203369,
|
|
"epoch": 0.14835747085835393,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999593593340286,
|
|
"loss": 6.5288,
|
|
"mean_token_accuracy": 0.13295082822442056,
|
|
"num_tokens": 3126606.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.650139379501343,
|
|
"epoch": 0.14879901095019427,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999587586115826,
|
|
"loss": 6.551,
|
|
"mean_token_accuracy": 0.13533952906727792,
|
|
"num_tokens": 3135444.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.524611854553223,
|
|
"epoch": 0.14924055104203462,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999581534823226,
|
|
"loss": 6.4885,
|
|
"mean_token_accuracy": 0.13537175804376603,
|
|
"num_tokens": 3144967.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.606992101669311,
|
|
"epoch": 0.14968209113387496,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999575439462601,
|
|
"loss": 6.5042,
|
|
"mean_token_accuracy": 0.1286872260272503,
|
|
"num_tokens": 3153898.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.504314661026001,
|
|
"epoch": 0.1501236312257153,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999569300034075,
|
|
"loss": 6.5644,
|
|
"mean_token_accuracy": 0.12845081239938735,
|
|
"num_tokens": 3162341.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.507896661758423,
|
|
"epoch": 0.15056517131755565,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999563116537764,
|
|
"loss": 6.3613,
|
|
"mean_token_accuracy": 0.14074554145336152,
|
|
"num_tokens": 3171420.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.5167927742004395,
|
|
"epoch": 0.15100671140939598,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999556888973792,
|
|
"loss": 6.4165,
|
|
"mean_token_accuracy": 0.12971381321549416,
|
|
"num_tokens": 3180221.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.600985956192017,
|
|
"epoch": 0.1514482515012363,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999550617342279,
|
|
"loss": 6.5615,
|
|
"mean_token_accuracy": 0.12731998935341834,
|
|
"num_tokens": 3189156.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.536636877059936,
|
|
"epoch": 0.15188979159307664,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499954430164335,
|
|
"loss": 6.4905,
|
|
"mean_token_accuracy": 0.1309817299246788,
|
|
"num_tokens": 3199870.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.541285371780395,
|
|
"epoch": 0.152331331684917,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999537941877127,
|
|
"loss": 6.4727,
|
|
"mean_token_accuracy": 0.13528374806046486,
|
|
"num_tokens": 3208815.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.487531661987305,
|
|
"epoch": 0.15277287177675733,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999531538043735,
|
|
"loss": 6.5498,
|
|
"mean_token_accuracy": 0.12755031064152716,
|
|
"num_tokens": 3218692.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.591389942169189,
|
|
"epoch": 0.15321441186859766,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999525090143298,
|
|
"loss": 6.5177,
|
|
"mean_token_accuracy": 0.13854537010192872,
|
|
"num_tokens": 3227604.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.57657470703125,
|
|
"epoch": 0.15365595196043802,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999518598175946,
|
|
"loss": 6.5291,
|
|
"mean_token_accuracy": 0.13887950852513314,
|
|
"num_tokens": 3237912.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.481386184692383,
|
|
"epoch": 0.15409749205227835,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999512062141805,
|
|
"loss": 6.3914,
|
|
"mean_token_accuracy": 0.1368810623884201,
|
|
"num_tokens": 3246003.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.51813645362854,
|
|
"epoch": 0.15453903214411868,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999505482040999,
|
|
"loss": 6.5332,
|
|
"mean_token_accuracy": 0.13183941319584846,
|
|
"num_tokens": 3256363.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.553296089172363,
|
|
"epoch": 0.154980572235959,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999498857873662,
|
|
"loss": 6.5312,
|
|
"mean_token_accuracy": 0.1321260340511799,
|
|
"num_tokens": 3265822.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.417472457885742,
|
|
"epoch": 0.15542211232779937,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999492189639921,
|
|
"loss": 6.424,
|
|
"mean_token_accuracy": 0.13568418473005295,
|
|
"num_tokens": 3274614.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.586168956756592,
|
|
"epoch": 0.1558636524196397,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999485477339907,
|
|
"loss": 6.5175,
|
|
"mean_token_accuracy": 0.12809595912694932,
|
|
"num_tokens": 3283800.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.485697317123413,
|
|
"epoch": 0.15630519251148003,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999478720973753,
|
|
"loss": 6.4297,
|
|
"mean_token_accuracy": 0.13804005309939385,
|
|
"num_tokens": 3293221.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.522076082229614,
|
|
"epoch": 0.1567467326033204,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499947192054159,
|
|
"loss": 6.5876,
|
|
"mean_token_accuracy": 0.12661009952425956,
|
|
"num_tokens": 3302852.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.621862745285034,
|
|
"epoch": 0.15718827269516072,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499946507604355,
|
|
"loss": 6.4486,
|
|
"mean_token_accuracy": 0.1398267850279808,
|
|
"num_tokens": 3311752.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.4172522068023685,
|
|
"epoch": 0.15762981278700106,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499945818747977,
|
|
"loss": 6.5267,
|
|
"mean_token_accuracy": 0.13450878411531447,
|
|
"num_tokens": 3321339.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.623373413085938,
|
|
"epoch": 0.1580713528788414,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999451254850383,
|
|
"loss": 6.5377,
|
|
"mean_token_accuracy": 0.13095242530107498,
|
|
"num_tokens": 3330269.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.57389874458313,
|
|
"epoch": 0.15851289297068175,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999444278155525,
|
|
"loss": 6.4619,
|
|
"mean_token_accuracy": 0.13360615670681,
|
|
"num_tokens": 3340770.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.484994888305664,
|
|
"epoch": 0.15895443306252208,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999437257395333,
|
|
"loss": 6.5612,
|
|
"mean_token_accuracy": 0.1361308626830578,
|
|
"num_tokens": 3349976.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.629813623428345,
|
|
"epoch": 0.1593959731543624,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999430192569944,
|
|
"loss": 6.5942,
|
|
"mean_token_accuracy": 0.126756651699543,
|
|
"num_tokens": 3359764.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.493142127990723,
|
|
"epoch": 0.15983751324620277,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999423083679498,
|
|
"loss": 6.4589,
|
|
"mean_token_accuracy": 0.1307877480983734,
|
|
"num_tokens": 3369939.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.5387725830078125,
|
|
"epoch": 0.1602790533380431,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999415930724133,
|
|
"loss": 6.6238,
|
|
"mean_token_accuracy": 0.12685370370745658,
|
|
"num_tokens": 3381326.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.630081462860107,
|
|
"epoch": 0.16072059342988343,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999408733703988,
|
|
"loss": 6.5692,
|
|
"mean_token_accuracy": 0.12697295919060708,
|
|
"num_tokens": 3391016.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.515750217437744,
|
|
"epoch": 0.16116213352172376,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999401492619207,
|
|
"loss": 6.3301,
|
|
"mean_token_accuracy": 0.1411547876894474,
|
|
"num_tokens": 3400294.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.519891738891602,
|
|
"epoch": 0.16160367361356412,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999394207469928,
|
|
"loss": 6.5452,
|
|
"mean_token_accuracy": 0.12329790964722634,
|
|
"num_tokens": 3409685.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.627039623260498,
|
|
"epoch": 0.16204521370540445,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999386878256297,
|
|
"loss": 6.4467,
|
|
"mean_token_accuracy": 0.12930482253432274,
|
|
"num_tokens": 3418946.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.345337200164795,
|
|
"epoch": 0.16248675379724478,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999379504978457,
|
|
"loss": 6.4523,
|
|
"mean_token_accuracy": 0.1312091715633869,
|
|
"num_tokens": 3428245.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.535007095336914,
|
|
"epoch": 0.16292829388908514,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499937208763655,
|
|
"loss": 6.4627,
|
|
"mean_token_accuracy": 0.13302566036581992,
|
|
"num_tokens": 3437580.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.5879792213439945,
|
|
"epoch": 0.16336983398092547,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999364626230724,
|
|
"loss": 6.4411,
|
|
"mean_token_accuracy": 0.1374020665884018,
|
|
"num_tokens": 3446393.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.394599485397339,
|
|
"epoch": 0.1638113740727658,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999357120761124,
|
|
"loss": 6.5361,
|
|
"mean_token_accuracy": 0.13167317807674409,
|
|
"num_tokens": 3455956.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.6326652526855465,
|
|
"epoch": 0.16425291416460613,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999349571227898,
|
|
"loss": 6.5281,
|
|
"mean_token_accuracy": 0.13483646959066392,
|
|
"num_tokens": 3465722.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.507793617248535,
|
|
"epoch": 0.1646944542564465,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999341977631193,
|
|
"loss": 6.5072,
|
|
"mean_token_accuracy": 0.12958121970295905,
|
|
"num_tokens": 3475467.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.5095072269439695,
|
|
"epoch": 0.16513599434828682,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999334339971157,
|
|
"loss": 6.3989,
|
|
"mean_token_accuracy": 0.13358662649989128,
|
|
"num_tokens": 3484931.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.522356176376343,
|
|
"epoch": 0.16557753444012716,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999326658247942,
|
|
"loss": 6.5123,
|
|
"mean_token_accuracy": 0.13453342840075494,
|
|
"num_tokens": 3494001.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.49297513961792,
|
|
"epoch": 0.16601907453196751,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999318932461696,
|
|
"loss": 6.4281,
|
|
"mean_token_accuracy": 0.1413221076130867,
|
|
"num_tokens": 3503021.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.447078704833984,
|
|
"epoch": 0.16646061462380785,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004999311162612571,
|
|
"loss": 6.4761,
|
|
"mean_token_accuracy": 0.13532513231039048,
|
|
"num_tokens": 3513005.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.60153341293335,
|
|
"epoch": 0.16690215471564818,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499930334870072,
|
|
"loss": 6.5511,
|
|
"mean_token_accuracy": 0.13551064282655717,
|
|
"num_tokens": 3523219.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.511942768096924,
|
|
"epoch": 0.1673436948074885,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999295490726296,
|
|
"loss": 6.5013,
|
|
"mean_token_accuracy": 0.130006618052721,
|
|
"num_tokens": 3532917.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.566938781738282,
|
|
"epoch": 0.16778523489932887,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999287588689453,
|
|
"loss": 6.496,
|
|
"mean_token_accuracy": 0.1396396428346634,
|
|
"num_tokens": 3542845.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.521204996109009,
|
|
"epoch": 0.1682267749911692,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999279642590344,
|
|
"loss": 6.5214,
|
|
"mean_token_accuracy": 0.13577667698264123,
|
|
"num_tokens": 3552126.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.5692566394805905,
|
|
"epoch": 0.16866831508300953,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999271652429127,
|
|
"loss": 6.5265,
|
|
"mean_token_accuracy": 0.127306517213583,
|
|
"num_tokens": 3561254.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.499909734725952,
|
|
"epoch": 0.1691098551748499,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999263618205958,
|
|
"loss": 6.3733,
|
|
"mean_token_accuracy": 0.14404519647359848,
|
|
"num_tokens": 3569781.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.53024697303772,
|
|
"epoch": 0.16955139526669022,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999255539920993,
|
|
"loss": 6.4874,
|
|
"mean_token_accuracy": 0.13062172681093215,
|
|
"num_tokens": 3579664.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.532351350784301,
|
|
"epoch": 0.16999293535853055,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999247417574391,
|
|
"loss": 6.526,
|
|
"mean_token_accuracy": 0.13393994346261023,
|
|
"num_tokens": 3588671.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.538648414611816,
|
|
"epoch": 0.17043447545037088,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999239251166312,
|
|
"loss": 6.4128,
|
|
"mean_token_accuracy": 0.14050136953592302,
|
|
"num_tokens": 3597656.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.45431957244873,
|
|
"epoch": 0.17087601554221124,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999231040696914,
|
|
"loss": 6.4342,
|
|
"mean_token_accuracy": 0.14062088206410409,
|
|
"num_tokens": 3608017.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.46071605682373,
|
|
"epoch": 0.17131755563405157,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999222786166361,
|
|
"loss": 6.5009,
|
|
"mean_token_accuracy": 0.13390257805585862,
|
|
"num_tokens": 3618189.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.564482021331787,
|
|
"epoch": 0.1717590957258919,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999214487574812,
|
|
"loss": 6.463,
|
|
"mean_token_accuracy": 0.13240221589803697,
|
|
"num_tokens": 3627211.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.480297803878784,
|
|
"epoch": 0.17220063581773226,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999206144922431,
|
|
"loss": 6.4038,
|
|
"mean_token_accuracy": 0.13147775381803511,
|
|
"num_tokens": 3636781.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.488903188705445,
|
|
"epoch": 0.1726421759095726,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499919775820938,
|
|
"loss": 6.4913,
|
|
"mean_token_accuracy": 0.14189594313502313,
|
|
"num_tokens": 3644891.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.561635589599609,
|
|
"epoch": 0.17308371600141292,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999189327435825,
|
|
"loss": 6.5195,
|
|
"mean_token_accuracy": 0.13184107840061188,
|
|
"num_tokens": 3655477.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.517252016067505,
|
|
"epoch": 0.17352525609325326,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999180852601929,
|
|
"loss": 6.5422,
|
|
"mean_token_accuracy": 0.13338224366307258,
|
|
"num_tokens": 3664542.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.498584127426147,
|
|
"epoch": 0.17396679618509361,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000499917233370786,
|
|
"loss": 6.4452,
|
|
"mean_token_accuracy": 0.12930241152644156,
|
|
"num_tokens": 3673806.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.516369295120239,
|
|
"epoch": 0.17440833627693395,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999163770753784,
|
|
"loss": 6.4487,
|
|
"mean_token_accuracy": 0.13249206990003587,
|
|
"num_tokens": 3683238.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.473311996459961,
|
|
"epoch": 0.17484987636877428,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004999155163739869,
|
|
"loss": 6.4228,
|
|
"mean_token_accuracy": 0.13501294553279877,
|
|
"num_tokens": 3692161.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.512854528427124,
|
|
"epoch": 0.17529141646061464,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999146512666284,
|
|
"loss": 6.4675,
|
|
"mean_token_accuracy": 0.13027839213609696,
|
|
"num_tokens": 3701431.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.468549728393555,
|
|
"epoch": 0.17573295655245497,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999137817533197,
|
|
"loss": 6.419,
|
|
"mean_token_accuracy": 0.14170578867197037,
|
|
"num_tokens": 3710963.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.4296314239501955,
|
|
"epoch": 0.1761744966442953,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999129078340779,
|
|
"loss": 6.4214,
|
|
"mean_token_accuracy": 0.13799419105052949,
|
|
"num_tokens": 3720177.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.4377001285552975,
|
|
"epoch": 0.17661603673613563,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999120295089202,
|
|
"loss": 6.3718,
|
|
"mean_token_accuracy": 0.14307373464107515,
|
|
"num_tokens": 3728123.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.573485851287842,
|
|
"epoch": 0.177057576827976,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999111467778639,
|
|
"loss": 6.509,
|
|
"mean_token_accuracy": 0.13284810408949851,
|
|
"num_tokens": 3736869.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.46274700164795,
|
|
"epoch": 0.17749911691981632,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000499910259640926,
|
|
"loss": 6.3788,
|
|
"mean_token_accuracy": 0.13863728046417237,
|
|
"num_tokens": 3745830.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.421447610855102,
|
|
"epoch": 0.17794065701165665,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499909368098124,
|
|
"loss": 6.4166,
|
|
"mean_token_accuracy": 0.13812872543931007,
|
|
"num_tokens": 3755019.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.508076333999634,
|
|
"epoch": 0.178382197103497,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999084721494754,
|
|
"loss": 6.3968,
|
|
"mean_token_accuracy": 0.1333928920328617,
|
|
"num_tokens": 3764814.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.345089483261108,
|
|
"epoch": 0.17882373719533734,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999075717949978,
|
|
"loss": 6.3581,
|
|
"mean_token_accuracy": 0.14092704504728318,
|
|
"num_tokens": 3774258.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.421577262878418,
|
|
"epoch": 0.17926527728717767,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999066670347089,
|
|
"loss": 6.3978,
|
|
"mean_token_accuracy": 0.13964474871754645,
|
|
"num_tokens": 3783961.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.40748291015625,
|
|
"epoch": 0.179706817379018,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999057578686261,
|
|
"loss": 6.363,
|
|
"mean_token_accuracy": 0.13734552562236785,
|
|
"num_tokens": 3792417.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.495989513397217,
|
|
"epoch": 0.18014835747085836,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999048442967675,
|
|
"loss": 6.3557,
|
|
"mean_token_accuracy": 0.13433733358979225,
|
|
"num_tokens": 3801479.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.37765908241272,
|
|
"epoch": 0.1805898975626987,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999039263191508,
|
|
"loss": 6.4254,
|
|
"mean_token_accuracy": 0.13214251399040222,
|
|
"num_tokens": 3810799.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.491030645370484,
|
|
"epoch": 0.18103143765453902,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999030039357943,
|
|
"loss": 6.462,
|
|
"mean_token_accuracy": 0.13567366376519202,
|
|
"num_tokens": 3820966.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.463741731643677,
|
|
"epoch": 0.18147297774637938,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999020771467158,
|
|
"loss": 6.4423,
|
|
"mean_token_accuracy": 0.1354211077094078,
|
|
"num_tokens": 3829247.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.572631978988648,
|
|
"epoch": 0.1819145178382197,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999011459519335,
|
|
"loss": 6.3891,
|
|
"mean_token_accuracy": 0.1375864826142788,
|
|
"num_tokens": 3838114.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.325645637512207,
|
|
"epoch": 0.18235605793006004,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999002103514655,
|
|
"loss": 6.4586,
|
|
"mean_token_accuracy": 0.13582065477967262,
|
|
"num_tokens": 3848075.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.570796966552734,
|
|
"epoch": 0.18279759802190038,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998992703453304,
|
|
"loss": 6.4987,
|
|
"mean_token_accuracy": 0.13409382104873657,
|
|
"num_tokens": 3857934.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.490766811370849,
|
|
"epoch": 0.18323913811374073,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998983259335466,
|
|
"loss": 6.3433,
|
|
"mean_token_accuracy": 0.14234771504998206,
|
|
"num_tokens": 3866707.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.456926107406616,
|
|
"epoch": 0.18368067820558107,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998973771161324,
|
|
"loss": 6.4192,
|
|
"mean_token_accuracy": 0.13825157508254052,
|
|
"num_tokens": 3875233.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.485457134246826,
|
|
"epoch": 0.1841222182974214,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998964238931065,
|
|
"loss": 6.4138,
|
|
"mean_token_accuracy": 0.13973441645503043,
|
|
"num_tokens": 3885173.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.477391719818115,
|
|
"epoch": 0.18456375838926176,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998954662644876,
|
|
"loss": 6.3774,
|
|
"mean_token_accuracy": 0.13736600577831268,
|
|
"num_tokens": 3894198.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.421681976318359,
|
|
"epoch": 0.1850052984811021,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998945042302943,
|
|
"loss": 6.373,
|
|
"mean_token_accuracy": 0.13609152138233185,
|
|
"num_tokens": 3904076.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.480407571792602,
|
|
"epoch": 0.18544683857294242,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998935377905457,
|
|
"loss": 6.4802,
|
|
"mean_token_accuracy": 0.1311386428773403,
|
|
"num_tokens": 3913204.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.535258817672729,
|
|
"epoch": 0.18588837866478275,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998925669452605,
|
|
"loss": 6.4323,
|
|
"mean_token_accuracy": 0.13564323037862777,
|
|
"num_tokens": 3922148.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.398992824554443,
|
|
"epoch": 0.1863299187566231,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998915916944579,
|
|
"loss": 6.4129,
|
|
"mean_token_accuracy": 0.13676537424325944,
|
|
"num_tokens": 3931333.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.4503209590911865,
|
|
"epoch": 0.18677145884846344,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998906120381568,
|
|
"loss": 6.374,
|
|
"mean_token_accuracy": 0.14027760475873946,
|
|
"num_tokens": 3941061.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.508623027801514,
|
|
"epoch": 0.18721299894030377,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998896279763766,
|
|
"loss": 6.4722,
|
|
"mean_token_accuracy": 0.13354425132274628,
|
|
"num_tokens": 3950075.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.476150178909302,
|
|
"epoch": 0.18765453903214413,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998886395091365,
|
|
"loss": 6.3316,
|
|
"mean_token_accuracy": 0.13695699274539946,
|
|
"num_tokens": 3958885.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.3462131977081295,
|
|
"epoch": 0.18809607912398446,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998876466364559,
|
|
"loss": 6.4256,
|
|
"mean_token_accuracy": 0.13821618929505347,
|
|
"num_tokens": 3968218.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.443255281448364,
|
|
"epoch": 0.1885376192158248,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998866493583541,
|
|
"loss": 6.3606,
|
|
"mean_token_accuracy": 0.1383839502930641,
|
|
"num_tokens": 3977435.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.356647872924805,
|
|
"epoch": 0.18897915930766512,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998856476748509,
|
|
"loss": 6.3498,
|
|
"mean_token_accuracy": 0.1412102162837982,
|
|
"num_tokens": 3986608.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.431683588027954,
|
|
"epoch": 0.18942069939950548,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998846415859656,
|
|
"loss": 6.3585,
|
|
"mean_token_accuracy": 0.14042109996080399,
|
|
"num_tokens": 3996087.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.444839954376221,
|
|
"epoch": 0.1898622394913458,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998836310917182,
|
|
"loss": 6.4002,
|
|
"mean_token_accuracy": 0.13422135785222053,
|
|
"num_tokens": 4006257.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.52928204536438,
|
|
"epoch": 0.19030377958318614,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998826161921282,
|
|
"loss": 6.4156,
|
|
"mean_token_accuracy": 0.1421043999493122,
|
|
"num_tokens": 4015904.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.383703994750976,
|
|
"epoch": 0.1907453196750265,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998815968872157,
|
|
"loss": 6.4115,
|
|
"mean_token_accuracy": 0.13542449548840524,
|
|
"num_tokens": 4025417.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.363600587844848,
|
|
"epoch": 0.19118685976686683,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998805731770007,
|
|
"loss": 6.2801,
|
|
"mean_token_accuracy": 0.15531659871339798,
|
|
"num_tokens": 4035181.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.47420859336853,
|
|
"epoch": 0.19162839985870717,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499879545061503,
|
|
"loss": 6.4466,
|
|
"mean_token_accuracy": 0.13034741580486298,
|
|
"num_tokens": 4045112.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.513006162643433,
|
|
"epoch": 0.1920699399505475,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998785125407432,
|
|
"loss": 6.5509,
|
|
"mean_token_accuracy": 0.12224270775914192,
|
|
"num_tokens": 4054566.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.533349084854126,
|
|
"epoch": 0.19251148004238786,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499877475614741,
|
|
"loss": 6.3601,
|
|
"mean_token_accuracy": 0.1362767845392227,
|
|
"num_tokens": 4063960.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.30982141494751,
|
|
"epoch": 0.1929530201342282,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998764342835169,
|
|
"loss": 6.3077,
|
|
"mean_token_accuracy": 0.14436172991991042,
|
|
"num_tokens": 4072620.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.325711584091186,
|
|
"epoch": 0.19339456022606852,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998753885470915,
|
|
"loss": 6.2856,
|
|
"mean_token_accuracy": 0.1410072512924671,
|
|
"num_tokens": 4081590.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.443258333206177,
|
|
"epoch": 0.19383610031790888,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998743384054851,
|
|
"loss": 6.4024,
|
|
"mean_token_accuracy": 0.14100263118743897,
|
|
"num_tokens": 4090758.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.343490505218506,
|
|
"epoch": 0.1942776404097492,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998732838587183,
|
|
"loss": 6.2339,
|
|
"mean_token_accuracy": 0.14560552909970284,
|
|
"num_tokens": 4099281.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.428974056243897,
|
|
"epoch": 0.19471918050158954,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998722249068118,
|
|
"loss": 6.3508,
|
|
"mean_token_accuracy": 0.13685052916407586,
|
|
"num_tokens": 4108953.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.399385118484497,
|
|
"epoch": 0.19516072059342987,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998711615497863,
|
|
"loss": 6.453,
|
|
"mean_token_accuracy": 0.13157615587115287,
|
|
"num_tokens": 4118799.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.466229009628296,
|
|
"epoch": 0.19560226068527023,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998700937876626,
|
|
"loss": 6.4178,
|
|
"mean_token_accuracy": 0.13792671710252763,
|
|
"num_tokens": 4127862.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.433918428421021,
|
|
"epoch": 0.19604380077711056,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998690216204615,
|
|
"loss": 6.4809,
|
|
"mean_token_accuracy": 0.12709898576140405,
|
|
"num_tokens": 4139029.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.472035026550293,
|
|
"epoch": 0.1964853408689509,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998679450482043,
|
|
"loss": 6.3062,
|
|
"mean_token_accuracy": 0.14617246389389038,
|
|
"num_tokens": 4148257.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.365042209625244,
|
|
"epoch": 0.19692688096079125,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499866864070912,
|
|
"loss": 6.2528,
|
|
"mean_token_accuracy": 0.13704810217022895,
|
|
"num_tokens": 4157626.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.411515808105468,
|
|
"epoch": 0.19736842105263158,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998657786886056,
|
|
"loss": 6.4857,
|
|
"mean_token_accuracy": 0.13319113329052926,
|
|
"num_tokens": 4166804.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.512064790725708,
|
|
"epoch": 0.1978099611444719,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998646889013066,
|
|
"loss": 6.3594,
|
|
"mean_token_accuracy": 0.1408704087138176,
|
|
"num_tokens": 4175701.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.454934692382812,
|
|
"epoch": 0.19825150123631224,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998635947090362,
|
|
"loss": 6.4385,
|
|
"mean_token_accuracy": 0.13829853162169456,
|
|
"num_tokens": 4184711.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.43667516708374,
|
|
"epoch": 0.1986930413281526,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004998624961118158,
|
|
"loss": 6.4075,
|
|
"mean_token_accuracy": 0.1378791533410549,
|
|
"num_tokens": 4193931.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.431211376190186,
|
|
"epoch": 0.19913458141999293,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499861393109667,
|
|
"loss": 6.2785,
|
|
"mean_token_accuracy": 0.1496691472828388,
|
|
"num_tokens": 4203000.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.271931219100952,
|
|
"epoch": 0.19957612151183327,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998602857026114,
|
|
"loss": 6.3027,
|
|
"mean_token_accuracy": 0.14634378403425216,
|
|
"num_tokens": 4211977.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.447495746612549,
|
|
"epoch": 0.20001766160367362,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998591738906708,
|
|
"loss": 6.3856,
|
|
"mean_token_accuracy": 0.14466411918401717,
|
|
"num_tokens": 4220375.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.450564670562744,
|
|
"epoch": 0.20045920169551396,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998580576738668,
|
|
"loss": 6.3736,
|
|
"mean_token_accuracy": 0.13617569133639335,
|
|
"num_tokens": 4230506.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.417342710494995,
|
|
"epoch": 0.2009007417873543,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998569370522213,
|
|
"loss": 6.3418,
|
|
"mean_token_accuracy": 0.1376570299267769,
|
|
"num_tokens": 4240235.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.406169795989991,
|
|
"epoch": 0.20134228187919462,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998558120257563,
|
|
"loss": 6.3963,
|
|
"mean_token_accuracy": 0.1375265248119831,
|
|
"num_tokens": 4249775.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.394922590255737,
|
|
"epoch": 0.20178382197103498,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998546825944938,
|
|
"loss": 6.3459,
|
|
"mean_token_accuracy": 0.13671498522162437,
|
|
"num_tokens": 4258523.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.455841398239135,
|
|
"epoch": 0.2022253620628753,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000499853548758456,
|
|
"loss": 6.348,
|
|
"mean_token_accuracy": 0.13951429352164268,
|
|
"num_tokens": 4267683.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.456370782852173,
|
|
"epoch": 0.20266690215471564,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000499852410517665,
|
|
"loss": 6.4251,
|
|
"mean_token_accuracy": 0.13333277478814126,
|
|
"num_tokens": 4276903.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.424126148223877,
|
|
"epoch": 0.203108442246556,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004998512678721431,
|
|
"loss": 6.3582,
|
|
"mean_token_accuracy": 0.13599715530872344,
|
|
"num_tokens": 4287257.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.428092765808105,
|
|
"epoch": 0.20354998233839633,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499850120821913,
|
|
"loss": 6.3942,
|
|
"mean_token_accuracy": 0.1357932858169079,
|
|
"num_tokens": 4297345.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.505991411209107,
|
|
"epoch": 0.20399152243023666,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998489693669967,
|
|
"loss": 6.3373,
|
|
"mean_token_accuracy": 0.1377499908208847,
|
|
"num_tokens": 4306533.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.375578260421753,
|
|
"epoch": 0.204433062522077,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499847813507417,
|
|
"loss": 6.404,
|
|
"mean_token_accuracy": 0.1373721919953823,
|
|
"num_tokens": 4316338.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.3910376071929935,
|
|
"epoch": 0.20487460261391735,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998466532431966,
|
|
"loss": 6.3591,
|
|
"mean_token_accuracy": 0.13833511546254157,
|
|
"num_tokens": 4326585.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.526772165298462,
|
|
"epoch": 0.20531614270575768,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998454885743581,
|
|
"loss": 6.4797,
|
|
"mean_token_accuracy": 0.13367427811026572,
|
|
"num_tokens": 4336490.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.390794658660889,
|
|
"epoch": 0.205757682797598,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998443195009242,
|
|
"loss": 6.3557,
|
|
"mean_token_accuracy": 0.13690442964434624,
|
|
"num_tokens": 4346264.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.416228103637695,
|
|
"epoch": 0.20619922288943837,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998431460229182,
|
|
"loss": 6.3522,
|
|
"mean_token_accuracy": 0.14161566868424416,
|
|
"num_tokens": 4355102.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.50619740486145,
|
|
"epoch": 0.2066407629812787,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004998419681403627,
|
|
"loss": 6.5122,
|
|
"mean_token_accuracy": 0.13018345609307289,
|
|
"num_tokens": 4365569.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.376383638381958,
|
|
"epoch": 0.20708230307311903,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998407858532809,
|
|
"loss": 6.3474,
|
|
"mean_token_accuracy": 0.14445040747523308,
|
|
"num_tokens": 4375437.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.404212570190429,
|
|
"epoch": 0.20752384316495937,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499839599161696,
|
|
"loss": 6.342,
|
|
"mean_token_accuracy": 0.14488178491592407,
|
|
"num_tokens": 4384420.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.3863624095916744,
|
|
"epoch": 0.20796538325679972,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998384080656314,
|
|
"loss": 6.3048,
|
|
"mean_token_accuracy": 0.14010295867919922,
|
|
"num_tokens": 4393730.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.41755633354187,
|
|
"epoch": 0.20840692334864006,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00049983721256511,
|
|
"loss": 6.2839,
|
|
"mean_token_accuracy": 0.14398279786109924,
|
|
"num_tokens": 4402731.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.356699991226196,
|
|
"epoch": 0.2088484634404804,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998360126601556,
|
|
"loss": 6.3451,
|
|
"mean_token_accuracy": 0.13590056598186492,
|
|
"num_tokens": 4411606.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.3600341320037845,
|
|
"epoch": 0.20929000353232075,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998348083507916,
|
|
"loss": 6.4137,
|
|
"mean_token_accuracy": 0.14537313282489778,
|
|
"num_tokens": 4421685.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.469741773605347,
|
|
"epoch": 0.20973154362416108,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998335996370416,
|
|
"loss": 6.3762,
|
|
"mean_token_accuracy": 0.14291262701153756,
|
|
"num_tokens": 4431765.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.3404137134552006,
|
|
"epoch": 0.2101730837160014,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998323865189291,
|
|
"loss": 6.3491,
|
|
"mean_token_accuracy": 0.13587618842720986,
|
|
"num_tokens": 4441191.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.441226148605347,
|
|
"epoch": 0.21061462380784174,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998311689964781,
|
|
"loss": 6.4262,
|
|
"mean_token_accuracy": 0.13476165607571602,
|
|
"num_tokens": 4450156.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.482025623321533,
|
|
"epoch": 0.2110561638996821,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998299470697125,
|
|
"loss": 6.4254,
|
|
"mean_token_accuracy": 0.13929163217544555,
|
|
"num_tokens": 4459466.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.4643927097320555,
|
|
"epoch": 0.21149770399152243,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998287207386559,
|
|
"loss": 6.4186,
|
|
"mean_token_accuracy": 0.13592114597558974,
|
|
"num_tokens": 4468539.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.458880662918091,
|
|
"epoch": 0.21193924408336276,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998274900033326,
|
|
"loss": 6.3128,
|
|
"mean_token_accuracy": 0.1451781891286373,
|
|
"num_tokens": 4477579.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.237515068054199,
|
|
"epoch": 0.21238078417520312,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998262548637667,
|
|
"loss": 6.2987,
|
|
"mean_token_accuracy": 0.15145175904035568,
|
|
"num_tokens": 4486800.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.3636726379394535,
|
|
"epoch": 0.21282232426704345,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004998250153199822,
|
|
"loss": 6.2466,
|
|
"mean_token_accuracy": 0.14414403662085534,
|
|
"num_tokens": 4495985.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.3901232242584225,
|
|
"epoch": 0.21326386435888378,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998237713720036,
|
|
"loss": 6.4023,
|
|
"mean_token_accuracy": 0.13772075325250627,
|
|
"num_tokens": 4504944.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.378066778182983,
|
|
"epoch": 0.2137054044507241,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998225230198552,
|
|
"loss": 6.2988,
|
|
"mean_token_accuracy": 0.14631899818778038,
|
|
"num_tokens": 4515402.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.370953845977783,
|
|
"epoch": 0.21414694454256447,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998212702635614,
|
|
"loss": 6.3772,
|
|
"mean_token_accuracy": 0.13616864681243895,
|
|
"num_tokens": 4525009.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.461081838607788,
|
|
"epoch": 0.2145884846344048,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004998200131031469,
|
|
"loss": 6.4151,
|
|
"mean_token_accuracy": 0.1347133368253708,
|
|
"num_tokens": 4534460.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.410534858703613,
|
|
"epoch": 0.21503002472624513,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998187515386361,
|
|
"loss": 6.2343,
|
|
"mean_token_accuracy": 0.15018296167254447,
|
|
"num_tokens": 4543748.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.339591979980469,
|
|
"epoch": 0.2154715648180855,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998174855700538,
|
|
"loss": 6.3688,
|
|
"mean_token_accuracy": 0.1432553306221962,
|
|
"num_tokens": 4552722.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.41485447883606,
|
|
"epoch": 0.21591310490992582,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004998162151974248,
|
|
"loss": 6.2185,
|
|
"mean_token_accuracy": 0.14427638724446296,
|
|
"num_tokens": 4561607.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.3874904155731205,
|
|
"epoch": 0.21635464500176615,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499814940420774,
|
|
"loss": 6.4909,
|
|
"mean_token_accuracy": 0.12949233055114745,
|
|
"num_tokens": 4572524.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.417895221710205,
|
|
"epoch": 0.21679618509360649,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998136612401266,
|
|
"loss": 6.3014,
|
|
"mean_token_accuracy": 0.14473507031798363,
|
|
"num_tokens": 4581601.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.422118234634399,
|
|
"epoch": 0.21723772518544684,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998123776555071,
|
|
"loss": 6.3707,
|
|
"mean_token_accuracy": 0.13594872877001762,
|
|
"num_tokens": 4591795.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.37589282989502,
|
|
"epoch": 0.21767926527728718,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998110896669412,
|
|
"loss": 6.3263,
|
|
"mean_token_accuracy": 0.14324304163455964,
|
|
"num_tokens": 4600745.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.44620714187622,
|
|
"epoch": 0.2181208053691275,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998097972744539,
|
|
"loss": 6.3737,
|
|
"mean_token_accuracy": 0.13417462706565858,
|
|
"num_tokens": 4610490.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.308990859985352,
|
|
"epoch": 0.21856234546096787,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998085004780705,
|
|
"loss": 6.3033,
|
|
"mean_token_accuracy": 0.14380738139152527,
|
|
"num_tokens": 4619511.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.418844270706177,
|
|
"epoch": 0.2190038855528082,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998071992778164,
|
|
"loss": 6.3332,
|
|
"mean_token_accuracy": 0.1404774770140648,
|
|
"num_tokens": 4628186.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.4331684589385985,
|
|
"epoch": 0.21944542564464853,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499805893673717,
|
|
"loss": 6.3698,
|
|
"mean_token_accuracy": 0.13764599412679673,
|
|
"num_tokens": 4637431.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.297756719589233,
|
|
"epoch": 0.21988696573648886,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998045836657982,
|
|
"loss": 6.2293,
|
|
"mean_token_accuracy": 0.14262612611055375,
|
|
"num_tokens": 4646627.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.3736780166625975,
|
|
"epoch": 0.22032850582832922,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004998032692540853,
|
|
"loss": 6.3126,
|
|
"mean_token_accuracy": 0.14131407141685487,
|
|
"num_tokens": 4656095.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.4055116176605225,
|
|
"epoch": 0.22077004592016955,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998019504386044,
|
|
"loss": 6.3932,
|
|
"mean_token_accuracy": 0.1364021860063076,
|
|
"num_tokens": 4665807.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.426360702514648,
|
|
"epoch": 0.22121158601200988,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004998006272193809,
|
|
"loss": 6.3543,
|
|
"mean_token_accuracy": 0.13680973649024963,
|
|
"num_tokens": 4674459.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.394381141662597,
|
|
"epoch": 0.22165312610385024,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997992995964412,
|
|
"loss": 6.4516,
|
|
"mean_token_accuracy": 0.13281818181276323,
|
|
"num_tokens": 4684063.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.355847644805908,
|
|
"epoch": 0.22209466619569057,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004997979675698109,
|
|
"loss": 6.3149,
|
|
"mean_token_accuracy": 0.1413261540234089,
|
|
"num_tokens": 4692807.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.509682703018188,
|
|
"epoch": 0.2225362062875309,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997966311395164,
|
|
"loss": 6.2561,
|
|
"mean_token_accuracy": 0.14682135581970215,
|
|
"num_tokens": 4701100.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.257225751876831,
|
|
"epoch": 0.22297774637937123,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997952903055836,
|
|
"loss": 6.313,
|
|
"mean_token_accuracy": 0.13383381441235542,
|
|
"num_tokens": 4710697.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.414626836776733,
|
|
"epoch": 0.2234192864712116,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499793945068039,
|
|
"loss": 6.2857,
|
|
"mean_token_accuracy": 0.14284081608057023,
|
|
"num_tokens": 4718745.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.376047897338867,
|
|
"epoch": 0.22386082656305192,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997925954269088,
|
|
"loss": 6.2546,
|
|
"mean_token_accuracy": 0.1423765517771244,
|
|
"num_tokens": 4728056.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.395099210739136,
|
|
"epoch": 0.22430236665489225,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997912413822196,
|
|
"loss": 6.4015,
|
|
"mean_token_accuracy": 0.13739172071218492,
|
|
"num_tokens": 4737605.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.362033176422119,
|
|
"epoch": 0.2247439067467326,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997898829339979,
|
|
"loss": 6.2078,
|
|
"mean_token_accuracy": 0.1501716986298561,
|
|
"num_tokens": 4746168.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.374505853652954,
|
|
"epoch": 0.22518544683857294,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00049978852008227,
|
|
"loss": 6.303,
|
|
"mean_token_accuracy": 0.14293254241347314,
|
|
"num_tokens": 4755072.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.365287399291992,
|
|
"epoch": 0.22562698693041328,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499787152827063,
|
|
"loss": 6.3115,
|
|
"mean_token_accuracy": 0.14703276976943017,
|
|
"num_tokens": 4764580.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.290199661254883,
|
|
"epoch": 0.2260685270222536,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997857811684035,
|
|
"loss": 6.311,
|
|
"mean_token_accuracy": 0.14540447145700455,
|
|
"num_tokens": 4774135.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.446982669830322,
|
|
"epoch": 0.22651006711409397,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997844051063183,
|
|
"loss": 6.4022,
|
|
"mean_token_accuracy": 0.13750494867563248,
|
|
"num_tokens": 4784733.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.385699224472046,
|
|
"epoch": 0.2269516072059343,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997830246408346,
|
|
"loss": 6.3325,
|
|
"mean_token_accuracy": 0.14618165343999862,
|
|
"num_tokens": 4795327.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.268747615814209,
|
|
"epoch": 0.22739314729777463,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997816397719791,
|
|
"loss": 6.2983,
|
|
"mean_token_accuracy": 0.14008190780878066,
|
|
"num_tokens": 4804314.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.464039659500122,
|
|
"epoch": 0.227834687389615,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997802504997792,
|
|
"loss": 6.3878,
|
|
"mean_token_accuracy": 0.135692573338747,
|
|
"num_tokens": 4813637.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.395627689361572,
|
|
"epoch": 0.22827622748145532,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997788568242621,
|
|
"loss": 6.279,
|
|
"mean_token_accuracy": 0.14184108525514602,
|
|
"num_tokens": 4823094.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.306736660003662,
|
|
"epoch": 0.22871776757329565,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499777458745455,
|
|
"loss": 6.206,
|
|
"mean_token_accuracy": 0.14509037733078003,
|
|
"num_tokens": 4833199.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.366773796081543,
|
|
"epoch": 0.22915930766513598,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997760562633853,
|
|
"loss": 6.3026,
|
|
"mean_token_accuracy": 0.13990220725536345,
|
|
"num_tokens": 4842970.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.40316481590271,
|
|
"epoch": 0.22960084775697634,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997746493780804,
|
|
"loss": 6.3996,
|
|
"mean_token_accuracy": 0.13560035228729247,
|
|
"num_tokens": 4852043.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.3404639720916744,
|
|
"epoch": 0.23004238784881667,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000499773238089568,
|
|
"loss": 6.2733,
|
|
"mean_token_accuracy": 0.1323003001511097,
|
|
"num_tokens": 4862232.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.368188381195068,
|
|
"epoch": 0.230483927940657,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997718223978758,
|
|
"loss": 6.2331,
|
|
"mean_token_accuracy": 0.141592987626791,
|
|
"num_tokens": 4871186.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.359707069396973,
|
|
"epoch": 0.23092546803249736,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997704023030315,
|
|
"loss": 6.3149,
|
|
"mean_token_accuracy": 0.1497406058013439,
|
|
"num_tokens": 4879974.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.361460208892822,
|
|
"epoch": 0.2313670081243377,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997689778050627,
|
|
"loss": 6.3786,
|
|
"mean_token_accuracy": 0.13907945528626442,
|
|
"num_tokens": 4890300.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.382821655273437,
|
|
"epoch": 0.23180854821617802,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997675489039975,
|
|
"loss": 6.3479,
|
|
"mean_token_accuracy": 0.1409486159682274,
|
|
"num_tokens": 4900428.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.362385368347168,
|
|
"epoch": 0.23225008830801835,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997661155998638,
|
|
"loss": 6.3464,
|
|
"mean_token_accuracy": 0.14176245480775834,
|
|
"num_tokens": 4910092.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.404236078262329,
|
|
"epoch": 0.2326916283998587,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997646778926898,
|
|
"loss": 6.3387,
|
|
"mean_token_accuracy": 0.1374544769525528,
|
|
"num_tokens": 4919593.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.340755891799927,
|
|
"epoch": 0.23313316849169904,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997632357825035,
|
|
"loss": 6.3179,
|
|
"mean_token_accuracy": 0.13816252574324608,
|
|
"num_tokens": 4929098.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.456451320648194,
|
|
"epoch": 0.23357470858353938,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997617892693333,
|
|
"loss": 6.35,
|
|
"mean_token_accuracy": 0.14228551536798478,
|
|
"num_tokens": 4938265.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.420327758789062,
|
|
"epoch": 0.23401624867537973,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997603383532075,
|
|
"loss": 6.3003,
|
|
"mean_token_accuracy": 0.14199153259396552,
|
|
"num_tokens": 4946694.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.29103798866272,
|
|
"epoch": 0.23445778876722007,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004997588830341545,
|
|
"loss": 6.3152,
|
|
"mean_token_accuracy": 0.14269881397485734,
|
|
"num_tokens": 4955296.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.337425231933594,
|
|
"epoch": 0.2348993288590604,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997574233122028,
|
|
"loss": 6.3015,
|
|
"mean_token_accuracy": 0.147652330994606,
|
|
"num_tokens": 4964409.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.348830032348633,
|
|
"epoch": 0.23534086895090076,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997559591873809,
|
|
"loss": 6.2893,
|
|
"mean_token_accuracy": 0.14996645748615264,
|
|
"num_tokens": 4973449.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.3320433616638185,
|
|
"epoch": 0.2357824090427411,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997544906597178,
|
|
"loss": 6.2838,
|
|
"mean_token_accuracy": 0.14481322914361955,
|
|
"num_tokens": 4983057.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.325637483596802,
|
|
"epoch": 0.23622394913458142,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004997530177292418,
|
|
"loss": 6.3494,
|
|
"mean_token_accuracy": 0.13466070592403412,
|
|
"num_tokens": 4991950.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.43730731010437,
|
|
"epoch": 0.23666548922642175,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997515403959823,
|
|
"loss": 6.2955,
|
|
"mean_token_accuracy": 0.14283260256052016,
|
|
"num_tokens": 5001042.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.396935892105103,
|
|
"epoch": 0.2371070293182621,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004997500586599677,
|
|
"loss": 6.2485,
|
|
"mean_token_accuracy": 0.14456894770264625,
|
|
"num_tokens": 5009827.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.2672782897949215,
|
|
"epoch": 0.23754856941010244,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997485725212274,
|
|
"loss": 6.2885,
|
|
"mean_token_accuracy": 0.14449408054351806,
|
|
"num_tokens": 5018708.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.272865295410156,
|
|
"epoch": 0.23799010950194277,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997470819797903,
|
|
"loss": 6.1679,
|
|
"mean_token_accuracy": 0.1527360998094082,
|
|
"num_tokens": 5027522.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.284482479095459,
|
|
"epoch": 0.23843164959378313,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997455870356857,
|
|
"loss": 6.2987,
|
|
"mean_token_accuracy": 0.1458326295018196,
|
|
"num_tokens": 5035755.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.35535831451416,
|
|
"epoch": 0.23887318968562346,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997440876889429,
|
|
"loss": 6.2588,
|
|
"mean_token_accuracy": 0.14414956122636796,
|
|
"num_tokens": 5045289.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.262376403808593,
|
|
"epoch": 0.2393147297774638,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997425839395913,
|
|
"loss": 6.2788,
|
|
"mean_token_accuracy": 0.14706139862537385,
|
|
"num_tokens": 5053774.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.403537845611572,
|
|
"epoch": 0.23975626986930412,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997410757876602,
|
|
"loss": 6.3583,
|
|
"mean_token_accuracy": 0.1355147533118725,
|
|
"num_tokens": 5062911.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.373221158981323,
|
|
"epoch": 0.24019780996114448,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997395632331793,
|
|
"loss": 6.223,
|
|
"mean_token_accuracy": 0.1466083750128746,
|
|
"num_tokens": 5072107.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.251181316375733,
|
|
"epoch": 0.2406393500529848,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004997380462761781,
|
|
"loss": 6.181,
|
|
"mean_token_accuracy": 0.1502533346414566,
|
|
"num_tokens": 5080588.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.353159761428833,
|
|
"epoch": 0.24108089014482514,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997365249166864,
|
|
"loss": 6.3864,
|
|
"mean_token_accuracy": 0.14094797894358635,
|
|
"num_tokens": 5090262.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.381338834762573,
|
|
"epoch": 0.2415224302366655,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997349991547342,
|
|
"loss": 6.2962,
|
|
"mean_token_accuracy": 0.14725386276841163,
|
|
"num_tokens": 5099285.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.368382978439331,
|
|
"epoch": 0.24196397032850583,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997334689903509,
|
|
"loss": 6.3307,
|
|
"mean_token_accuracy": 0.14288511276245117,
|
|
"num_tokens": 5109115.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.4272418975830075,
|
|
"epoch": 0.24240551042034617,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004997319344235668,
|
|
"loss": 6.3721,
|
|
"mean_token_accuracy": 0.1368812806904316,
|
|
"num_tokens": 5117977.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.413669633865356,
|
|
"epoch": 0.2428470505121865,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000499730395454412,
|
|
"loss": 6.3185,
|
|
"mean_token_accuracy": 0.14243241772055626,
|
|
"num_tokens": 5127457.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.2972547054290775,
|
|
"epoch": 0.24328859060402686,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997288520829166,
|
|
"loss": 6.3606,
|
|
"mean_token_accuracy": 0.13738505616784097,
|
|
"num_tokens": 5137310.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.390837097167969,
|
|
"epoch": 0.2437301306958672,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997273043091107,
|
|
"loss": 6.2857,
|
|
"mean_token_accuracy": 0.1405642569065094,
|
|
"num_tokens": 5146963.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.359052276611328,
|
|
"epoch": 0.24417167078770752,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004997257521330248,
|
|
"loss": 6.2501,
|
|
"mean_token_accuracy": 0.14132534712553024,
|
|
"num_tokens": 5155521.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.37628755569458,
|
|
"epoch": 0.24461321087954788,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004997241955546892,
|
|
"loss": 6.2586,
|
|
"mean_token_accuracy": 0.13957886546850204,
|
|
"num_tokens": 5165182.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.32409896850586,
|
|
"epoch": 0.2450547509713882,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997226345741343,
|
|
"loss": 6.2833,
|
|
"mean_token_accuracy": 0.13664216697216033,
|
|
"num_tokens": 5175511.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.361440944671631,
|
|
"epoch": 0.24549629106322854,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000499721069191391,
|
|
"loss": 6.2283,
|
|
"mean_token_accuracy": 0.14851997345685958,
|
|
"num_tokens": 5184772.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.256292247772217,
|
|
"epoch": 0.24593783115506887,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997194994064896,
|
|
"loss": 6.3103,
|
|
"mean_token_accuracy": 0.14024864211678506,
|
|
"num_tokens": 5195136.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.3915492534637455,
|
|
"epoch": 0.24637937124690923,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499717925219461,
|
|
"loss": 6.249,
|
|
"mean_token_accuracy": 0.14889259859919549,
|
|
"num_tokens": 5203163.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.315735578536987,
|
|
"epoch": 0.24682091133874956,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997163466303362,
|
|
"loss": 6.3376,
|
|
"mean_token_accuracy": 0.13842562362551689,
|
|
"num_tokens": 5213233.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.385308742523193,
|
|
"epoch": 0.2472624514305899,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499714763639146,
|
|
"loss": 6.2659,
|
|
"mean_token_accuracy": 0.1395539350807667,
|
|
"num_tokens": 5222940.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.331099176406861,
|
|
"epoch": 0.24770399152243025,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004997131762459211,
|
|
"loss": 6.2917,
|
|
"mean_token_accuracy": 0.13852713331580163,
|
|
"num_tokens": 5232263.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.337193584442138,
|
|
"epoch": 0.24814553161427058,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004997115844506932,
|
|
"loss": 6.2739,
|
|
"mean_token_accuracy": 0.13856021910905839,
|
|
"num_tokens": 5241536.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.376536083221436,
|
|
"epoch": 0.2485870717061109,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004997099882534929,
|
|
"loss": 6.2841,
|
|
"mean_token_accuracy": 0.13798881992697715,
|
|
"num_tokens": 5250702.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.387785339355469,
|
|
"epoch": 0.24902861179795124,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997083876543519,
|
|
"loss": 6.2968,
|
|
"mean_token_accuracy": 0.1387106366455555,
|
|
"num_tokens": 5259811.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.46270055770874,
|
|
"epoch": 0.2494701518897916,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997067826533014,
|
|
"loss": 6.3787,
|
|
"mean_token_accuracy": 0.13431487306952478,
|
|
"num_tokens": 5270518.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.343976306915283,
|
|
"epoch": 0.24991169198163193,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004997051732503726,
|
|
"loss": 6.2692,
|
|
"mean_token_accuracy": 0.14104484394192696,
|
|
"num_tokens": 5279538.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.288498306274414,
|
|
"epoch": 0.25035323207347226,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004997035594455975,
|
|
"loss": 6.2935,
|
|
"mean_token_accuracy": 0.13851248025894164,
|
|
"num_tokens": 5289633.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.403953742980957,
|
|
"epoch": 0.2507947721653126,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004997019412390074,
|
|
"loss": 6.3908,
|
|
"mean_token_accuracy": 0.14274223148822784,
|
|
"num_tokens": 5299148.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.318170356750488,
|
|
"epoch": 0.2512363122571529,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499700318630634,
|
|
"loss": 6.2601,
|
|
"mean_token_accuracy": 0.14186998903751374,
|
|
"num_tokens": 5309090.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.378513526916504,
|
|
"epoch": 0.2516778523489933,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004996986916205092,
|
|
"loss": 6.3497,
|
|
"mean_token_accuracy": 0.13793296962976456,
|
|
"num_tokens": 5318798.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.330926847457886,
|
|
"epoch": 0.25211939244083365,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996970602086648,
|
|
"loss": 6.2201,
|
|
"mean_token_accuracy": 0.14618514329195023,
|
|
"num_tokens": 5327915.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.227778148651123,
|
|
"epoch": 0.252560932532674,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004996954243951327,
|
|
"loss": 6.2396,
|
|
"mean_token_accuracy": 0.15025153011083603,
|
|
"num_tokens": 5336970.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.362396907806397,
|
|
"epoch": 0.2530024726245143,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004996937841799451,
|
|
"loss": 6.2156,
|
|
"mean_token_accuracy": 0.14974839985370636,
|
|
"num_tokens": 5345167.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.2248279571533205,
|
|
"epoch": 0.25344401271635464,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004996921395631342,
|
|
"loss": 6.1855,
|
|
"mean_token_accuracy": 0.14353529885411262,
|
|
"num_tokens": 5353399.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.3493123054504395,
|
|
"epoch": 0.25388555280819497,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000499690490544732,
|
|
"loss": 6.2894,
|
|
"mean_token_accuracy": 0.14165428131818772,
|
|
"num_tokens": 5363224.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.406820631027221,
|
|
"epoch": 0.2543270929000353,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996888371247707,
|
|
"loss": 6.3181,
|
|
"mean_token_accuracy": 0.14098790735006334,
|
|
"num_tokens": 5372274.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.34662184715271,
|
|
"epoch": 0.2547686329918757,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499687179303283,
|
|
"loss": 6.2874,
|
|
"mean_token_accuracy": 0.14797318130731582,
|
|
"num_tokens": 5380240.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.25228362083435,
|
|
"epoch": 0.255210173083716,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996855170803012,
|
|
"loss": 6.1607,
|
|
"mean_token_accuracy": 0.15010163933038712,
|
|
"num_tokens": 5389390.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.337203788757324,
|
|
"epoch": 0.25565171317555635,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004996838504558581,
|
|
"loss": 6.3114,
|
|
"mean_token_accuracy": 0.14117275848984717,
|
|
"num_tokens": 5399425.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.378282165527343,
|
|
"epoch": 0.2560932532673967,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000499682179429986,
|
|
"loss": 6.3199,
|
|
"mean_token_accuracy": 0.14286198765039443,
|
|
"num_tokens": 5408717.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.319883155822754,
|
|
"epoch": 0.256534793359237,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996805040027178,
|
|
"loss": 6.2533,
|
|
"mean_token_accuracy": 0.13577283322811126,
|
|
"num_tokens": 5418475.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.353005409240723,
|
|
"epoch": 0.25697633345107734,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996788241740863,
|
|
"loss": 6.3058,
|
|
"mean_token_accuracy": 0.14230425655841827,
|
|
"num_tokens": 5428403.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.345854663848877,
|
|
"epoch": 0.2574178735429177,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996771399441243,
|
|
"loss": 6.3449,
|
|
"mean_token_accuracy": 0.13902240470051766,
|
|
"num_tokens": 5437347.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.451116418838501,
|
|
"epoch": 0.25785941363475806,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996754513128652,
|
|
"loss": 6.2456,
|
|
"mean_token_accuracy": 0.14855796918272973,
|
|
"num_tokens": 5446804.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.2477256774902346,
|
|
"epoch": 0.2583009537265984,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004996737582803416,
|
|
"loss": 6.2091,
|
|
"mean_token_accuracy": 0.1402647577226162,
|
|
"num_tokens": 5455888.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.36528582572937,
|
|
"epoch": 0.2587424938184387,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004996720608465868,
|
|
"loss": 6.1781,
|
|
"mean_token_accuracy": 0.14944826811552048,
|
|
"num_tokens": 5463977.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.307216548919678,
|
|
"epoch": 0.25918403391027905,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004996703590116342,
|
|
"loss": 6.3079,
|
|
"mean_token_accuracy": 0.14276890456676483,
|
|
"num_tokens": 5473780.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.31512484550476,
|
|
"epoch": 0.2596255740021194,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004996686527755171,
|
|
"loss": 6.1977,
|
|
"mean_token_accuracy": 0.1501262977719307,
|
|
"num_tokens": 5482151.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.3214874267578125,
|
|
"epoch": 0.2600671140939597,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004996669421382687,
|
|
"loss": 6.2257,
|
|
"mean_token_accuracy": 0.1505381152033806,
|
|
"num_tokens": 5491103.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.25068473815918,
|
|
"epoch": 0.26050865418580005,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004996652270999228,
|
|
"loss": 6.2349,
|
|
"mean_token_accuracy": 0.15028091371059418,
|
|
"num_tokens": 5500367.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.329337501525879,
|
|
"epoch": 0.26095019427764043,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004996635076605128,
|
|
"loss": 6.2539,
|
|
"mean_token_accuracy": 0.15224550366401673,
|
|
"num_tokens": 5509631.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.459008836746216,
|
|
"epoch": 0.26139173436948077,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004996617838200725,
|
|
"loss": 6.289,
|
|
"mean_token_accuracy": 0.1362527571618557,
|
|
"num_tokens": 5518635.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.2465019702911375,
|
|
"epoch": 0.2618332744613211,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004996600555786357,
|
|
"loss": 6.2431,
|
|
"mean_token_accuracy": 0.14100067913532258,
|
|
"num_tokens": 5527696.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.315958070755005,
|
|
"epoch": 0.26227481455316143,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004996583229362362,
|
|
"loss": 6.2046,
|
|
"mean_token_accuracy": 0.14614154621958733,
|
|
"num_tokens": 5536632.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.385778141021729,
|
|
"epoch": 0.26271635464500176,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004996565858929078,
|
|
"loss": 6.2772,
|
|
"mean_token_accuracy": 0.14362908750772477,
|
|
"num_tokens": 5545825.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.284611654281616,
|
|
"epoch": 0.2631578947368421,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996548444486847,
|
|
"loss": 6.166,
|
|
"mean_token_accuracy": 0.14970893263816834,
|
|
"num_tokens": 5555158.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.209372615814209,
|
|
"epoch": 0.2635994348286824,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004996530986036008,
|
|
"loss": 6.0922,
|
|
"mean_token_accuracy": 0.15141627043485642,
|
|
"num_tokens": 5564218.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.198943185806274,
|
|
"epoch": 0.2640409749205228,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004996513483576907,
|
|
"loss": 6.2522,
|
|
"mean_token_accuracy": 0.14398482963442802,
|
|
"num_tokens": 5572760.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.441630268096924,
|
|
"epoch": 0.26448251501236314,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004996495937109884,
|
|
"loss": 6.3173,
|
|
"mean_token_accuracy": 0.14210836142301558,
|
|
"num_tokens": 5581660.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.330695295333863,
|
|
"epoch": 0.26492405510420347,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004996478346635283,
|
|
"loss": 6.2178,
|
|
"mean_token_accuracy": 0.14186472147703172,
|
|
"num_tokens": 5590664.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.26492405510420347,
|
|
"eval_entropy": 6.125705798268993,
|
|
"eval_loss": 6.292537212371826,
|
|
"eval_mean_token_accuracy": 0.14802020881356648,
|
|
"eval_num_tokens": 5590664.0,
|
|
"eval_runtime": 26.6031,
|
|
"eval_samples_per_second": 1327.479,
|
|
"eval_steps_per_second": 165.958,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 6.237614250183105,
|
|
"epoch": 0.2653655951960438,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004996460712153448,
|
|
"loss": 6.1001,
|
|
"mean_token_accuracy": 0.15663176029920578,
|
|
"num_tokens": 5598727.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 6.179663801193238,
|
|
"epoch": 0.26580713528788413,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004996443033664726,
|
|
"loss": 6.2871,
|
|
"mean_token_accuracy": 0.14380988031625747,
|
|
"num_tokens": 5608549.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 6.340897512435913,
|
|
"epoch": 0.26624867537972446,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004996425311169463,
|
|
"loss": 6.2245,
|
|
"mean_token_accuracy": 0.15150296986103057,
|
|
"num_tokens": 5617628.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 6.377718782424926,
|
|
"epoch": 0.2666902154715648,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004996407544668005,
|
|
"loss": 6.2818,
|
|
"mean_token_accuracy": 0.13613456413149833,
|
|
"num_tokens": 5627182.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 6.350316286087036,
|
|
"epoch": 0.2671317555634052,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004996389734160701,
|
|
"loss": 6.3055,
|
|
"mean_token_accuracy": 0.13961158990859984,
|
|
"num_tokens": 5636413.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 6.370533466339111,
|
|
"epoch": 0.2675732956552455,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00049963718796479,
|
|
"loss": 6.2542,
|
|
"mean_token_accuracy": 0.14205907806754112,
|
|
"num_tokens": 5646025.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 6.296344900131226,
|
|
"epoch": 0.26801483574708584,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996353981129952,
|
|
"loss": 6.2607,
|
|
"mean_token_accuracy": 0.1442931205034256,
|
|
"num_tokens": 5656577.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 6.4285656929016115,
|
|
"epoch": 0.2684563758389262,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996336038607206,
|
|
"loss": 6.2455,
|
|
"mean_token_accuracy": 0.14679916203022003,
|
|
"num_tokens": 5665163.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 6.330079984664917,
|
|
"epoch": 0.2688979159307665,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004996318052080015,
|
|
"loss": 6.2566,
|
|
"mean_token_accuracy": 0.14481926709413528,
|
|
"num_tokens": 5675196.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 6.34555835723877,
|
|
"epoch": 0.26933945602260684,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004996300021548731,
|
|
"loss": 6.197,
|
|
"mean_token_accuracy": 0.1455060735344887,
|
|
"num_tokens": 5684361.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 6.260120964050293,
|
|
"epoch": 0.26978099611444717,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996281947013707,
|
|
"loss": 6.1798,
|
|
"mean_token_accuracy": 0.15278830826282502,
|
|
"num_tokens": 5694187.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 6.297383594512939,
|
|
"epoch": 0.27022253620628756,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004996263828475298,
|
|
"loss": 6.2398,
|
|
"mean_token_accuracy": 0.14067175090312958,
|
|
"num_tokens": 5702858.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 6.256354093551636,
|
|
"epoch": 0.2706640762981279,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996245665933857,
|
|
"loss": 6.1588,
|
|
"mean_token_accuracy": 0.15283851474523544,
|
|
"num_tokens": 5712727.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.318592643737793,
|
|
"epoch": 0.2711056163899682,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004996227459389741,
|
|
"loss": 6.2727,
|
|
"mean_token_accuracy": 0.14474223479628562,
|
|
"num_tokens": 5722904.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 6.408034229278565,
|
|
"epoch": 0.27154715648180855,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004996209208843307,
|
|
"loss": 6.3752,
|
|
"mean_token_accuracy": 0.14424618259072303,
|
|
"num_tokens": 5732228.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 6.349897289276123,
|
|
"epoch": 0.2719886965736489,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996190914294912,
|
|
"loss": 6.2983,
|
|
"mean_token_accuracy": 0.14683646857738494,
|
|
"num_tokens": 5743548.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 6.293585872650146,
|
|
"epoch": 0.2724302366654892,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004996172575744914,
|
|
"loss": 6.3202,
|
|
"mean_token_accuracy": 0.13539790511131286,
|
|
"num_tokens": 5754112.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 6.393399858474732,
|
|
"epoch": 0.27287177675732954,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996154193193673,
|
|
"loss": 6.1409,
|
|
"mean_token_accuracy": 0.15001579597592354,
|
|
"num_tokens": 5763377.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 6.1732752323150635,
|
|
"epoch": 0.27331331684916993,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004996135766641549,
|
|
"loss": 6.108,
|
|
"mean_token_accuracy": 0.14798013716936112,
|
|
"num_tokens": 5772000.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 6.311184072494507,
|
|
"epoch": 0.27375485694101026,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996117296088903,
|
|
"loss": 6.2394,
|
|
"mean_token_accuracy": 0.1420420527458191,
|
|
"num_tokens": 5782192.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 6.404490375518799,
|
|
"epoch": 0.2741963970328506,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004996098781536095,
|
|
"loss": 6.2906,
|
|
"mean_token_accuracy": 0.1430370345711708,
|
|
"num_tokens": 5791163.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 6.3008567810058596,
|
|
"epoch": 0.2746379371246909,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996080222983492,
|
|
"loss": 6.2862,
|
|
"mean_token_accuracy": 0.13813944384455681,
|
|
"num_tokens": 5801815.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 6.412563610076904,
|
|
"epoch": 0.27507947721653125,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996061620431453,
|
|
"loss": 6.3053,
|
|
"mean_token_accuracy": 0.1372584030032158,
|
|
"num_tokens": 5811545.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 6.312923192977905,
|
|
"epoch": 0.2755210173083716,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996042973880344,
|
|
"loss": 6.3151,
|
|
"mean_token_accuracy": 0.1433285042643547,
|
|
"num_tokens": 5820285.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 6.318920564651489,
|
|
"epoch": 0.2759625574002119,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996024283330532,
|
|
"loss": 6.1485,
|
|
"mean_token_accuracy": 0.14611285403370858,
|
|
"num_tokens": 5829284.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 6.29420223236084,
|
|
"epoch": 0.2764040974920523,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499600554878238,
|
|
"loss": 6.3298,
|
|
"mean_token_accuracy": 0.13846347481012344,
|
|
"num_tokens": 5838973.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 6.27738995552063,
|
|
"epoch": 0.27684563758389263,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004995986770236258,
|
|
"loss": 6.1795,
|
|
"mean_token_accuracy": 0.14896027445793153,
|
|
"num_tokens": 5847434.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 6.298033714294434,
|
|
"epoch": 0.27728717767573297,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995967947692533,
|
|
"loss": 6.1943,
|
|
"mean_token_accuracy": 0.14507781639695166,
|
|
"num_tokens": 5856464.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 6.335427713394165,
|
|
"epoch": 0.2777287177675733,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004995949081151571,
|
|
"loss": 6.2722,
|
|
"mean_token_accuracy": 0.14494210481643677,
|
|
"num_tokens": 5865892.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 6.315033102035523,
|
|
"epoch": 0.2781702578594136,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995930170613746,
|
|
"loss": 6.237,
|
|
"mean_token_accuracy": 0.14656798988580705,
|
|
"num_tokens": 5874606.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 6.306213092803955,
|
|
"epoch": 0.27861179795125396,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995911216079425,
|
|
"loss": 6.2319,
|
|
"mean_token_accuracy": 0.14783644378185273,
|
|
"num_tokens": 5883853.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 6.385525226593018,
|
|
"epoch": 0.2790533380430943,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004995892217548981,
|
|
"loss": 6.2583,
|
|
"mean_token_accuracy": 0.14387187659740447,
|
|
"num_tokens": 5892841.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 6.3458394527435305,
|
|
"epoch": 0.2794948781349347,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004995873175022786,
|
|
"loss": 6.2353,
|
|
"mean_token_accuracy": 0.1464378446340561,
|
|
"num_tokens": 5901966.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 6.269200468063355,
|
|
"epoch": 0.279936418226775,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995854088501213,
|
|
"loss": 6.1382,
|
|
"mean_token_accuracy": 0.1440639741718769,
|
|
"num_tokens": 5910003.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 6.240004587173462,
|
|
"epoch": 0.28037795831861534,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004995834957984634,
|
|
"loss": 6.291,
|
|
"mean_token_accuracy": 0.1417745180428028,
|
|
"num_tokens": 5920307.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 6.307330751419068,
|
|
"epoch": 0.28081949841045567,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004995815783473428,
|
|
"loss": 6.1405,
|
|
"mean_token_accuracy": 0.14922185912728309,
|
|
"num_tokens": 5929875.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 6.276836585998535,
|
|
"epoch": 0.281261038502296,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004995796564967967,
|
|
"loss": 6.1274,
|
|
"mean_token_accuracy": 0.14101065844297409,
|
|
"num_tokens": 5938570.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 6.234568166732788,
|
|
"epoch": 0.28170257859413633,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004995777302468628,
|
|
"loss": 6.2715,
|
|
"mean_token_accuracy": 0.1487502433359623,
|
|
"num_tokens": 5947693.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 6.2986798763275145,
|
|
"epoch": 0.28214411868597666,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004995757995975789,
|
|
"loss": 6.3549,
|
|
"mean_token_accuracy": 0.14176566973328592,
|
|
"num_tokens": 5957377.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 6.414698123931885,
|
|
"epoch": 0.28258565877781705,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004995738645489828,
|
|
"loss": 6.2702,
|
|
"mean_token_accuracy": 0.14696883633732796,
|
|
"num_tokens": 5966443.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 6.282436943054199,
|
|
"epoch": 0.2830271988696574,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004995719251011124,
|
|
"loss": 6.1681,
|
|
"mean_token_accuracy": 0.14562456011772157,
|
|
"num_tokens": 5975027.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 6.329652166366577,
|
|
"epoch": 0.2834687389614977,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004995699812540058,
|
|
"loss": 6.2486,
|
|
"mean_token_accuracy": 0.148249339312315,
|
|
"num_tokens": 5983722.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 6.231355476379394,
|
|
"epoch": 0.28391027905333804,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499568033007701,
|
|
"loss": 6.2674,
|
|
"mean_token_accuracy": 0.1401293992996216,
|
|
"num_tokens": 5993358.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 6.362948560714722,
|
|
"epoch": 0.2843518191451784,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004995660803622361,
|
|
"loss": 6.2067,
|
|
"mean_token_accuracy": 0.15058139562606812,
|
|
"num_tokens": 6002743.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 6.4410686016082765,
|
|
"epoch": 0.2847933592370187,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004995641233176494,
|
|
"loss": 6.3638,
|
|
"mean_token_accuracy": 0.13944116085767747,
|
|
"num_tokens": 6013727.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 6.373442220687866,
|
|
"epoch": 0.28523489932885904,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004995621618739792,
|
|
"loss": 6.2881,
|
|
"mean_token_accuracy": 0.1439940005540848,
|
|
"num_tokens": 6023397.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 6.350295162200927,
|
|
"epoch": 0.2856764394206994,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499560196031264,
|
|
"loss": 6.1873,
|
|
"mean_token_accuracy": 0.14995670616626738,
|
|
"num_tokens": 6032453.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 6.175947523117065,
|
|
"epoch": 0.28611797951253976,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004995582257895423,
|
|
"loss": 6.1641,
|
|
"mean_token_accuracy": 0.13984985798597335,
|
|
"num_tokens": 6042441.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 6.310670042037964,
|
|
"epoch": 0.2865595196043801,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004995562511488528,
|
|
"loss": 6.1649,
|
|
"mean_token_accuracy": 0.1534782238304615,
|
|
"num_tokens": 6050881.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 6.252470016479492,
|
|
"epoch": 0.2870010596962204,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004995542721092337,
|
|
"loss": 6.2226,
|
|
"mean_token_accuracy": 0.1445020094513893,
|
|
"num_tokens": 6060804.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 6.373200368881226,
|
|
"epoch": 0.28744259978806075,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004995522886707244,
|
|
"loss": 6.3284,
|
|
"mean_token_accuracy": 0.14050979763269425,
|
|
"num_tokens": 6070774.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 6.413953495025635,
|
|
"epoch": 0.2878841398799011,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995503008333634,
|
|
"loss": 6.2875,
|
|
"mean_token_accuracy": 0.1406187132000923,
|
|
"num_tokens": 6080158.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 6.315617513656616,
|
|
"epoch": 0.2883256799717414,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004995483085971897,
|
|
"loss": 6.1952,
|
|
"mean_token_accuracy": 0.1474509745836258,
|
|
"num_tokens": 6089183.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 6.305659580230713,
|
|
"epoch": 0.2887672200635818,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004995463119622424,
|
|
"loss": 6.294,
|
|
"mean_token_accuracy": 0.14213767349720002,
|
|
"num_tokens": 6098536.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 6.171843099594116,
|
|
"epoch": 0.28920876015542213,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995443109285604,
|
|
"loss": 6.051,
|
|
"mean_token_accuracy": 0.16226806342601777,
|
|
"num_tokens": 6107745.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 6.261803674697876,
|
|
"epoch": 0.28965030024726246,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995423054961832,
|
|
"loss": 6.247,
|
|
"mean_token_accuracy": 0.152182936668396,
|
|
"num_tokens": 6117512.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 6.266145706176758,
|
|
"epoch": 0.2900918403391028,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00049954029566515,
|
|
"loss": 6.2528,
|
|
"mean_token_accuracy": 0.15064032524824142,
|
|
"num_tokens": 6126030.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 6.380165672302246,
|
|
"epoch": 0.2905333804309431,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004995382814355,
|
|
"loss": 6.2915,
|
|
"mean_token_accuracy": 0.1421806663274765,
|
|
"num_tokens": 6134888.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 6.435223770141602,
|
|
"epoch": 0.29097492052278345,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004995362628072728,
|
|
"loss": 6.2507,
|
|
"mean_token_accuracy": 0.15030645132064818,
|
|
"num_tokens": 6144274.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 6.207036447525025,
|
|
"epoch": 0.2914164606146238,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004995342397805078,
|
|
"loss": 6.2525,
|
|
"mean_token_accuracy": 0.14731749445199965,
|
|
"num_tokens": 6153406.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 6.286630725860595,
|
|
"epoch": 0.29185800070646417,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004995322123552448,
|
|
"loss": 6.1763,
|
|
"mean_token_accuracy": 0.14860426858067513,
|
|
"num_tokens": 6162743.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 6.315083646774292,
|
|
"epoch": 0.2922995407983045,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004995301805315235,
|
|
"loss": 6.1518,
|
|
"mean_token_accuracy": 0.14915710389614106,
|
|
"num_tokens": 6171997.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 6.227348041534424,
|
|
"epoch": 0.29274108089014483,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004995281443093837,
|
|
"loss": 6.1821,
|
|
"mean_token_accuracy": 0.14849540442228318,
|
|
"num_tokens": 6181275.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 6.332483291625977,
|
|
"epoch": 0.29318262098198516,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004995261036888652,
|
|
"loss": 6.2705,
|
|
"mean_token_accuracy": 0.14153582453727723,
|
|
"num_tokens": 6191640.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 6.383525228500366,
|
|
"epoch": 0.2936241610738255,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004995240586700081,
|
|
"loss": 6.2574,
|
|
"mean_token_accuracy": 0.14164062663912774,
|
|
"num_tokens": 6201508.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 6.233497428894043,
|
|
"epoch": 0.2940657011656658,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004995220092528522,
|
|
"loss": 6.139,
|
|
"mean_token_accuracy": 0.15600898191332818,
|
|
"num_tokens": 6209902.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 6.386223220825196,
|
|
"epoch": 0.29450724125750616,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000499519955437438,
|
|
"loss": 6.2886,
|
|
"mean_token_accuracy": 0.13724534064531327,
|
|
"num_tokens": 6219760.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 6.308050680160522,
|
|
"epoch": 0.29494878134934654,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004995178972238054,
|
|
"loss": 6.2712,
|
|
"mean_token_accuracy": 0.140892493724823,
|
|
"num_tokens": 6228721.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 6.249277830123901,
|
|
"epoch": 0.2953903214411869,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000499515834611995,
|
|
"loss": 6.0912,
|
|
"mean_token_accuracy": 0.15884328559041022,
|
|
"num_tokens": 6237070.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 6.2829673290252686,
|
|
"epoch": 0.2958318615330272,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004995137676020472,
|
|
"loss": 6.2342,
|
|
"mean_token_accuracy": 0.14056732952594758,
|
|
"num_tokens": 6245659.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 6.2845625400543215,
|
|
"epoch": 0.29627340162486754,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004995116961940023,
|
|
"loss": 6.211,
|
|
"mean_token_accuracy": 0.15007902830839157,
|
|
"num_tokens": 6255175.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 6.2821348190307615,
|
|
"epoch": 0.29671494171670787,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995096203879009,
|
|
"loss": 6.2275,
|
|
"mean_token_accuracy": 0.13889190107583999,
|
|
"num_tokens": 6264962.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 6.295028495788574,
|
|
"epoch": 0.2971564818085482,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004995075401837837,
|
|
"loss": 6.1385,
|
|
"mean_token_accuracy": 0.15292445346713066,
|
|
"num_tokens": 6273411.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 6.216491222381592,
|
|
"epoch": 0.29759802190038853,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004995054555816915,
|
|
"loss": 6.1184,
|
|
"mean_token_accuracy": 0.15340590327978135,
|
|
"num_tokens": 6282618.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 6.16982479095459,
|
|
"epoch": 0.2980395619922289,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995033665816651,
|
|
"loss": 6.107,
|
|
"mean_token_accuracy": 0.15143536180257797,
|
|
"num_tokens": 6292008.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 6.202243089675903,
|
|
"epoch": 0.29848110208406925,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004995012731837454,
|
|
"loss": 6.085,
|
|
"mean_token_accuracy": 0.1523757502436638,
|
|
"num_tokens": 6301079.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 6.280016565322876,
|
|
"epoch": 0.2989226421759096,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004994991753879736,
|
|
"loss": 6.2433,
|
|
"mean_token_accuracy": 0.14038580283522606,
|
|
"num_tokens": 6310543.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 6.310758495330811,
|
|
"epoch": 0.2993641822677499,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004994970731943904,
|
|
"loss": 6.201,
|
|
"mean_token_accuracy": 0.14722133427858353,
|
|
"num_tokens": 6320037.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 6.285776853561401,
|
|
"epoch": 0.29980572235959024,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004994949666030374,
|
|
"loss": 6.2149,
|
|
"mean_token_accuracy": 0.14747923761606216,
|
|
"num_tokens": 6328948.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 6.212871885299682,
|
|
"epoch": 0.3002472624514306,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004994928556139557,
|
|
"loss": 6.093,
|
|
"mean_token_accuracy": 0.15421175062656403,
|
|
"num_tokens": 6337449.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 6.196883726119995,
|
|
"epoch": 0.3006888025432709,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004994907402271865,
|
|
"loss": 6.1322,
|
|
"mean_token_accuracy": 0.15156666040420533,
|
|
"num_tokens": 6346130.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 6.221924304962158,
|
|
"epoch": 0.3011303426351113,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004994886204427715,
|
|
"loss": 6.1765,
|
|
"mean_token_accuracy": 0.15341567099094391,
|
|
"num_tokens": 6354973.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 6.323950290679932,
|
|
"epoch": 0.3015718827269516,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004994864962607519,
|
|
"loss": 6.2308,
|
|
"mean_token_accuracy": 0.1454234704375267,
|
|
"num_tokens": 6364107.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 6.2969788074493405,
|
|
"epoch": 0.30201342281879195,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004994843676811697,
|
|
"loss": 6.199,
|
|
"mean_token_accuracy": 0.1469217300415039,
|
|
"num_tokens": 6372859.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 6.2598062515258786,
|
|
"epoch": 0.3024549629106323,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004994822347040664,
|
|
"loss": 6.0796,
|
|
"mean_token_accuracy": 0.15675319582223893,
|
|
"num_tokens": 6381818.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 6.2870680809021,
|
|
"epoch": 0.3028965030024726,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004994800973294837,
|
|
"loss": 6.2419,
|
|
"mean_token_accuracy": 0.1480972073972225,
|
|
"num_tokens": 6391460.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 6.335415649414062,
|
|
"epoch": 0.30333804309431295,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004994779555574636,
|
|
"loss": 6.2516,
|
|
"mean_token_accuracy": 0.14857821315526962,
|
|
"num_tokens": 6401461.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 6.295047855377197,
|
|
"epoch": 0.3037795831861533,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000499475809388048,
|
|
"loss": 6.1387,
|
|
"mean_token_accuracy": 0.14693403244018555,
|
|
"num_tokens": 6410435.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 6.2984706401824955,
|
|
"epoch": 0.30422112327799367,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000499473658821279,
|
|
"loss": 6.352,
|
|
"mean_token_accuracy": 0.13787579387426377,
|
|
"num_tokens": 6420710.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 6.374636268615722,
|
|
"epoch": 0.304662663369834,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004994715038571986,
|
|
"loss": 6.1802,
|
|
"mean_token_accuracy": 0.14614371061325074,
|
|
"num_tokens": 6429882.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 6.22500171661377,
|
|
"epoch": 0.30510420346167433,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004994693444958493,
|
|
"loss": 6.1599,
|
|
"mean_token_accuracy": 0.1555553011596203,
|
|
"num_tokens": 6439183.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 6.33427243232727,
|
|
"epoch": 0.30554574355351466,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.000499467180737273,
|
|
"loss": 6.3324,
|
|
"mean_token_accuracy": 0.14285074174404144,
|
|
"num_tokens": 6448460.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 6.340069055557251,
|
|
"epoch": 0.305987283645355,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004994650125815124,
|
|
"loss": 6.2093,
|
|
"mean_token_accuracy": 0.14827462136745453,
|
|
"num_tokens": 6457687.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 6.230474996566772,
|
|
"epoch": 0.3064288237371953,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004994628400286097,
|
|
"loss": 6.1509,
|
|
"mean_token_accuracy": 0.14839715510606766,
|
|
"num_tokens": 6467057.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 6.220822429656982,
|
|
"epoch": 0.30687036382903565,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004994606630786078,
|
|
"loss": 6.2087,
|
|
"mean_token_accuracy": 0.1455997943878174,
|
|
"num_tokens": 6477484.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 6.366261005401611,
|
|
"epoch": 0.30731190392087604,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004994584817315492,
|
|
"loss": 6.2814,
|
|
"mean_token_accuracy": 0.14490586519241333,
|
|
"num_tokens": 6488381.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 6.3309496402740475,
|
|
"epoch": 0.30775344401271637,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004994562959874765,
|
|
"loss": 6.1799,
|
|
"mean_token_accuracy": 0.14776056110858918,
|
|
"num_tokens": 6498279.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 6.247140789031983,
|
|
"epoch": 0.3081949841045567,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004994541058464326,
|
|
"loss": 6.1835,
|
|
"mean_token_accuracy": 0.14511879906058311,
|
|
"num_tokens": 6508008.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 6.368619108200074,
|
|
"epoch": 0.30863652419639703,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004994519113084605,
|
|
"loss": 6.2442,
|
|
"mean_token_accuracy": 0.14024475663900376,
|
|
"num_tokens": 6517263.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 6.38942060470581,
|
|
"epoch": 0.30907806428823736,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004994497123736029,
|
|
"loss": 6.3158,
|
|
"mean_token_accuracy": 0.13759939074516297,
|
|
"num_tokens": 6527682.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 6.29895167350769,
|
|
"epoch": 0.3095196043800777,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004994475090419034,
|
|
"loss": 6.1809,
|
|
"mean_token_accuracy": 0.14446886107325554,
|
|
"num_tokens": 6537143.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 6.31071515083313,
|
|
"epoch": 0.309961144471918,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004994453013134047,
|
|
"loss": 6.1863,
|
|
"mean_token_accuracy": 0.1450910188257694,
|
|
"num_tokens": 6546561.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 6.23366641998291,
|
|
"epoch": 0.3104026845637584,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004994430891881502,
|
|
"loss": 6.1911,
|
|
"mean_token_accuracy": 0.14489428102970123,
|
|
"num_tokens": 6555806.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 6.293187618255615,
|
|
"epoch": 0.31084422465559874,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004994408726661832,
|
|
"loss": 6.2141,
|
|
"mean_token_accuracy": 0.1494822882115841,
|
|
"num_tokens": 6564836.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 6.278930139541626,
|
|
"epoch": 0.3112857647474391,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994386517475472,
|
|
"loss": 6.2068,
|
|
"mean_token_accuracy": 0.1408160336315632,
|
|
"num_tokens": 6574997.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 6.318894767761231,
|
|
"epoch": 0.3117273048392794,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004994364264322856,
|
|
"loss": 6.2252,
|
|
"mean_token_accuracy": 0.14185250252485276,
|
|
"num_tokens": 6584589.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 6.292446851730347,
|
|
"epoch": 0.31216884493111974,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004994341967204421,
|
|
"loss": 6.1669,
|
|
"mean_token_accuracy": 0.15242523699998856,
|
|
"num_tokens": 6592898.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 6.3396844387054445,
|
|
"epoch": 0.31261038502296007,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004994319626120603,
|
|
"loss": 6.1949,
|
|
"mean_token_accuracy": 0.15440042167901993,
|
|
"num_tokens": 6602454.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 6.231834363937378,
|
|
"epoch": 0.3130519251148004,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004994297241071841,
|
|
"loss": 6.1852,
|
|
"mean_token_accuracy": 0.1523444212973118,
|
|
"num_tokens": 6612454.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 6.299538946151733,
|
|
"epoch": 0.3134934652066408,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000499427481205857,
|
|
"loss": 6.1802,
|
|
"mean_token_accuracy": 0.1479717329144478,
|
|
"num_tokens": 6621286.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 6.264144992828369,
|
|
"epoch": 0.3139350052984811,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004994252339081234,
|
|
"loss": 6.1195,
|
|
"mean_token_accuracy": 0.14949584379792213,
|
|
"num_tokens": 6629684.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 6.2147904396057125,
|
|
"epoch": 0.31437654539032145,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000499422982214027,
|
|
"loss": 6.2063,
|
|
"mean_token_accuracy": 0.15209176391363144,
|
|
"num_tokens": 6638836.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 6.2978600025177,
|
|
"epoch": 0.3148180854821618,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004994207261236121,
|
|
"loss": 6.1618,
|
|
"mean_token_accuracy": 0.14471966549754142,
|
|
"num_tokens": 6647337.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 6.1957439422607425,
|
|
"epoch": 0.3152596255740021,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004994184656369227,
|
|
"loss": 6.1509,
|
|
"mean_token_accuracy": 0.14381661489605904,
|
|
"num_tokens": 6657246.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 6.334473371505737,
|
|
"epoch": 0.31570116566584244,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994162007540033,
|
|
"loss": 6.2969,
|
|
"mean_token_accuracy": 0.13743397295475007,
|
|
"num_tokens": 6667981.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 6.342165803909301,
|
|
"epoch": 0.3161427057576828,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004994139314748981,
|
|
"loss": 6.14,
|
|
"mean_token_accuracy": 0.15782761424779893,
|
|
"num_tokens": 6677462.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 6.14517126083374,
|
|
"epoch": 0.31658424584952316,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994116577996517,
|
|
"loss": 6.1806,
|
|
"mean_token_accuracy": 0.14892098158597947,
|
|
"num_tokens": 6687225.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 6.278700685501098,
|
|
"epoch": 0.3170257859413635,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004994093797283084,
|
|
"loss": 6.2461,
|
|
"mean_token_accuracy": 0.14409312158823012,
|
|
"num_tokens": 6696345.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 6.365807723999024,
|
|
"epoch": 0.3174673260332038,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004994070972609132,
|
|
"loss": 6.2278,
|
|
"mean_token_accuracy": 0.1436710849404335,
|
|
"num_tokens": 6706207.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 6.277693223953247,
|
|
"epoch": 0.31790886612504415,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004994048103975103,
|
|
"loss": 6.141,
|
|
"mean_token_accuracy": 0.14587350636720658,
|
|
"num_tokens": 6714430.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 6.256088304519653,
|
|
"epoch": 0.3183504062168845,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499402519138145,
|
|
"loss": 6.165,
|
|
"mean_token_accuracy": 0.15041644424200057,
|
|
"num_tokens": 6724139.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 6.239550638198852,
|
|
"epoch": 0.3187919463087248,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994002234828619,
|
|
"loss": 6.2016,
|
|
"mean_token_accuracy": 0.1462198480963707,
|
|
"num_tokens": 6733525.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 6.281878137588501,
|
|
"epoch": 0.31923348640056515,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000499397923431706,
|
|
"loss": 6.3159,
|
|
"mean_token_accuracy": 0.1457715466618538,
|
|
"num_tokens": 6743738.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 6.400450372695923,
|
|
"epoch": 0.31967502649240553,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004993956189847226,
|
|
"loss": 6.1568,
|
|
"mean_token_accuracy": 0.15204840898513794,
|
|
"num_tokens": 6752900.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 6.209289264678955,
|
|
"epoch": 0.32011656658424587,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004993933101419565,
|
|
"loss": 6.1341,
|
|
"mean_token_accuracy": 0.15580240935087203,
|
|
"num_tokens": 6761776.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 6.293803882598877,
|
|
"epoch": 0.3205581066760862,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004993909969034531,
|
|
"loss": 6.2924,
|
|
"mean_token_accuracy": 0.1407908871769905,
|
|
"num_tokens": 6771543.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 6.315399408340454,
|
|
"epoch": 0.3209996467679265,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004993886792692576,
|
|
"loss": 6.1578,
|
|
"mean_token_accuracy": 0.14261920005083084,
|
|
"num_tokens": 6780010.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 6.289389181137085,
|
|
"epoch": 0.32144118685976686,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004993863572394156,
|
|
"loss": 6.241,
|
|
"mean_token_accuracy": 0.14563653171062468,
|
|
"num_tokens": 6788830.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 6.26135663986206,
|
|
"epoch": 0.3218827269516072,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004993840308139724,
|
|
"loss": 6.2059,
|
|
"mean_token_accuracy": 0.14630922228097915,
|
|
"num_tokens": 6799121.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 6.330420780181885,
|
|
"epoch": 0.3223242670434475,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004993816999929738,
|
|
"loss": 6.1656,
|
|
"mean_token_accuracy": 0.1479571595788002,
|
|
"num_tokens": 6808519.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 6.250893688201904,
|
|
"epoch": 0.3227658071352879,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004993793647764651,
|
|
"loss": 6.1855,
|
|
"mean_token_accuracy": 0.15019199550151824,
|
|
"num_tokens": 6817583.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 6.281541872024536,
|
|
"epoch": 0.32320734722712824,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004993770251644923,
|
|
"loss": 6.1776,
|
|
"mean_token_accuracy": 0.14661791399121285,
|
|
"num_tokens": 6827732.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 6.200496053695678,
|
|
"epoch": 0.32364888731896857,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004993746811571013,
|
|
"loss": 6.1516,
|
|
"mean_token_accuracy": 0.1507879838347435,
|
|
"num_tokens": 6836903.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 6.15623197555542,
|
|
"epoch": 0.3240904274108089,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004993723327543379,
|
|
"loss": 6.1458,
|
|
"mean_token_accuracy": 0.15642194598913192,
|
|
"num_tokens": 6845684.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 6.226500606536865,
|
|
"epoch": 0.32453196750264923,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000499369979956248,
|
|
"loss": 6.1508,
|
|
"mean_token_accuracy": 0.1459520123898983,
|
|
"num_tokens": 6854650.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 6.29415922164917,
|
|
"epoch": 0.32497350759448956,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004993676227628779,
|
|
"loss": 6.148,
|
|
"mean_token_accuracy": 0.14504464268684386,
|
|
"num_tokens": 6864340.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 6.306327772140503,
|
|
"epoch": 0.3254150476863299,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004993652611742736,
|
|
"loss": 6.1858,
|
|
"mean_token_accuracy": 0.15019768550992013,
|
|
"num_tokens": 6873244.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 6.112890195846558,
|
|
"epoch": 0.3258565877781703,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993628951904815,
|
|
"loss": 6.0704,
|
|
"mean_token_accuracy": 0.1555016480386257,
|
|
"num_tokens": 6882392.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 6.28070034980774,
|
|
"epoch": 0.3262981278700106,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004993605248115479,
|
|
"loss": 6.2963,
|
|
"mean_token_accuracy": 0.14003317803144455,
|
|
"num_tokens": 6891515.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 6.373077821731568,
|
|
"epoch": 0.32673966796185094,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004993581500375191,
|
|
"loss": 6.173,
|
|
"mean_token_accuracy": 0.14526692926883697,
|
|
"num_tokens": 6900104.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 6.296589422225952,
|
|
"epoch": 0.3271812080536913,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004993557708684417,
|
|
"loss": 6.2939,
|
|
"mean_token_accuracy": 0.13876401036977767,
|
|
"num_tokens": 6910443.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 6.245956897735596,
|
|
"epoch": 0.3276227481455316,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004993533873043625,
|
|
"loss": 6.1438,
|
|
"mean_token_accuracy": 0.1444818288087845,
|
|
"num_tokens": 6919882.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 6.338452863693237,
|
|
"epoch": 0.32806428823737194,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000499350999345328,
|
|
"loss": 6.2593,
|
|
"mean_token_accuracy": 0.13912570625543594,
|
|
"num_tokens": 6929757.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 6.288271760940551,
|
|
"epoch": 0.32850582832921227,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000499348606991385,
|
|
"loss": 6.2531,
|
|
"mean_token_accuracy": 0.13713812530040742,
|
|
"num_tokens": 6938578.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 6.316042470932007,
|
|
"epoch": 0.32894736842105265,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004993462102425805,
|
|
"loss": 6.1391,
|
|
"mean_token_accuracy": 0.14824429005384446,
|
|
"num_tokens": 6947920.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 6.1937977313995365,
|
|
"epoch": 0.329388908512893,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004993438090989612,
|
|
"loss": 6.0803,
|
|
"mean_token_accuracy": 0.1511243000626564,
|
|
"num_tokens": 6957291.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 6.253715133666992,
|
|
"epoch": 0.3298304486047333,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004993414035605743,
|
|
"loss": 6.1485,
|
|
"mean_token_accuracy": 0.15854721516370773,
|
|
"num_tokens": 6966504.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 6.280976629257202,
|
|
"epoch": 0.33027198869657365,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004993389936274669,
|
|
"loss": 6.1878,
|
|
"mean_token_accuracy": 0.1520113728940487,
|
|
"num_tokens": 6976234.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 6.250279951095581,
|
|
"epoch": 0.330713528788414,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004993365792996862,
|
|
"loss": 6.2406,
|
|
"mean_token_accuracy": 0.14429223239421846,
|
|
"num_tokens": 6986372.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 6.307081604003907,
|
|
"epoch": 0.3311550688802543,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004993341605772795,
|
|
"loss": 6.1238,
|
|
"mean_token_accuracy": 0.15334457531571388,
|
|
"num_tokens": 6995553.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 6.191009140014648,
|
|
"epoch": 0.33159660897209464,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004993317374602941,
|
|
"loss": 6.0382,
|
|
"mean_token_accuracy": 0.15769377201795579,
|
|
"num_tokens": 7005675.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 6.14142336845398,
|
|
"epoch": 0.33203814906393503,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004993293099487777,
|
|
"loss": 6.1723,
|
|
"mean_token_accuracy": 0.1418219581246376,
|
|
"num_tokens": 7014953.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 6.301387357711792,
|
|
"epoch": 0.33247968915577536,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004993268780427776,
|
|
"loss": 6.197,
|
|
"mean_token_accuracy": 0.15199018269777298,
|
|
"num_tokens": 7025075.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 6.2432451248168945,
|
|
"epoch": 0.3329212292476157,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004993244417423416,
|
|
"loss": 6.1866,
|
|
"mean_token_accuracy": 0.14759992957115173,
|
|
"num_tokens": 7034286.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 6.276465892791748,
|
|
"epoch": 0.333362769339456,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004993220010475174,
|
|
"loss": 6.2286,
|
|
"mean_token_accuracy": 0.1462813802063465,
|
|
"num_tokens": 7043957.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 6.321380186080932,
|
|
"epoch": 0.33380430943129635,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993195559583526,
|
|
"loss": 6.1348,
|
|
"mean_token_accuracy": 0.1504329338669777,
|
|
"num_tokens": 7053170.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 6.1749907493591305,
|
|
"epoch": 0.3342458495231367,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004993171064748954,
|
|
"loss": 6.1522,
|
|
"mean_token_accuracy": 0.14876105189323424,
|
|
"num_tokens": 7062469.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 6.1947144031524655,
|
|
"epoch": 0.334687389614977,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004993146525971937,
|
|
"loss": 6.1273,
|
|
"mean_token_accuracy": 0.1507238492369652,
|
|
"num_tokens": 7071463.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 6.411292028427124,
|
|
"epoch": 0.3351289297068174,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004993121943252955,
|
|
"loss": 6.2072,
|
|
"mean_token_accuracy": 0.14429879561066628,
|
|
"num_tokens": 7081574.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 6.190117692947387,
|
|
"epoch": 0.33557046979865773,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004993097316592489,
|
|
"loss": 6.1422,
|
|
"mean_token_accuracy": 0.1508495032787323,
|
|
"num_tokens": 7090835.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 6.117297267913818,
|
|
"epoch": 0.33601200989049806,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004993072645991023,
|
|
"loss": 6.0815,
|
|
"mean_token_accuracy": 0.1401878349483013,
|
|
"num_tokens": 7100521.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 6.263327598571777,
|
|
"epoch": 0.3364535499823384,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000499304793144904,
|
|
"loss": 6.153,
|
|
"mean_token_accuracy": 0.15199762284755708,
|
|
"num_tokens": 7109011.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 6.273023176193237,
|
|
"epoch": 0.3368950900741787,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004993023172967022,
|
|
"loss": 6.1882,
|
|
"mean_token_accuracy": 0.13951589912176132,
|
|
"num_tokens": 7119128.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 6.324663877487183,
|
|
"epoch": 0.33733663016601906,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004992998370545458,
|
|
"loss": 6.254,
|
|
"mean_token_accuracy": 0.1373855710029602,
|
|
"num_tokens": 7128313.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 6.305013370513916,
|
|
"epoch": 0.3377781702578594,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004992973524184831,
|
|
"loss": 6.2009,
|
|
"mean_token_accuracy": 0.14602725803852082,
|
|
"num_tokens": 7137567.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 6.249309396743774,
|
|
"epoch": 0.3382197103496998,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004992948633885627,
|
|
"loss": 6.1709,
|
|
"mean_token_accuracy": 0.15077222734689713,
|
|
"num_tokens": 7147254.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 6.1801636695861815,
|
|
"epoch": 0.3386612504415401,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004992923699648335,
|
|
"loss": 6.115,
|
|
"mean_token_accuracy": 0.14965742975473403,
|
|
"num_tokens": 7156215.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 6.356573963165284,
|
|
"epoch": 0.33910279053338044,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004992898721473445,
|
|
"loss": 6.1772,
|
|
"mean_token_accuracy": 0.14581147357821464,
|
|
"num_tokens": 7165653.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 6.171209383010864,
|
|
"epoch": 0.33954433062522077,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004992873699361444,
|
|
"loss": 6.0745,
|
|
"mean_token_accuracy": 0.14739914536476134,
|
|
"num_tokens": 7174797.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 6.224230861663818,
|
|
"epoch": 0.3399858707170611,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004992848633312822,
|
|
"loss": 6.1114,
|
|
"mean_token_accuracy": 0.15535301566123963,
|
|
"num_tokens": 7184040.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 6.294191217422485,
|
|
"epoch": 0.34042741080890143,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004992823523328071,
|
|
"loss": 6.0608,
|
|
"mean_token_accuracy": 0.15379656255245208,
|
|
"num_tokens": 7193533.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 6.183957767486572,
|
|
"epoch": 0.34086895090074176,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004992798369407684,
|
|
"loss": 6.1687,
|
|
"mean_token_accuracy": 0.1520672157406807,
|
|
"num_tokens": 7203355.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 6.271494150161743,
|
|
"epoch": 0.34131049099258215,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004992773171552152,
|
|
"loss": 6.1249,
|
|
"mean_token_accuracy": 0.1494740977883339,
|
|
"num_tokens": 7212569.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 6.210461950302124,
|
|
"epoch": 0.3417520310844225,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004992747929761968,
|
|
"loss": 6.1419,
|
|
"mean_token_accuracy": 0.15112009570002555,
|
|
"num_tokens": 7221886.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 6.223880386352539,
|
|
"epoch": 0.3421935711762628,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004992722644037628,
|
|
"loss": 6.2028,
|
|
"mean_token_accuracy": 0.14669590443372726,
|
|
"num_tokens": 7232065.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 6.258075428009033,
|
|
"epoch": 0.34263511126810314,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004992697314379628,
|
|
"loss": 6.1439,
|
|
"mean_token_accuracy": 0.14625586122274398,
|
|
"num_tokens": 7242287.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 6.217844772338867,
|
|
"epoch": 0.3430766513599435,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004992671940788462,
|
|
"loss": 6.1326,
|
|
"mean_token_accuracy": 0.14522299468517302,
|
|
"num_tokens": 7250638.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 6.199563884735108,
|
|
"epoch": 0.3435181914517838,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004992646523264628,
|
|
"loss": 6.1238,
|
|
"mean_token_accuracy": 0.15116736590862273,
|
|
"num_tokens": 7259526.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 6.25900559425354,
|
|
"epoch": 0.34395973154362414,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004992621061808625,
|
|
"loss": 6.1216,
|
|
"mean_token_accuracy": 0.1581985518336296,
|
|
"num_tokens": 7269260.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 6.257178878784179,
|
|
"epoch": 0.3444012716354645,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.000499259555642095,
|
|
"loss": 6.1278,
|
|
"mean_token_accuracy": 0.1471450299024582,
|
|
"num_tokens": 7279061.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 6.255412244796753,
|
|
"epoch": 0.34484281172730485,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004992570007102104,
|
|
"loss": 6.1315,
|
|
"mean_token_accuracy": 0.1531999722123146,
|
|
"num_tokens": 7289721.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 6.344775438308716,
|
|
"epoch": 0.3452843518191452,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004992544413852587,
|
|
"loss": 6.2762,
|
|
"mean_token_accuracy": 0.14250053465366364,
|
|
"num_tokens": 7299836.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 6.264148616790772,
|
|
"epoch": 0.3457258919109855,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00049925187766729,
|
|
"loss": 6.2837,
|
|
"mean_token_accuracy": 0.14403201416134834,
|
|
"num_tokens": 7309306.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 6.2656416416168215,
|
|
"epoch": 0.34616743200282585,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004992493095563545,
|
|
"loss": 6.1734,
|
|
"mean_token_accuracy": 0.1555798202753067,
|
|
"num_tokens": 7318486.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 6.212107849121094,
|
|
"epoch": 0.3466089720946662,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004992467370525026,
|
|
"loss": 6.1484,
|
|
"mean_token_accuracy": 0.14943969249725342,
|
|
"num_tokens": 7327764.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 6.288184976577758,
|
|
"epoch": 0.3470505121865065,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004992441601557848,
|
|
"loss": 6.2374,
|
|
"mean_token_accuracy": 0.1469939887523651,
|
|
"num_tokens": 7337118.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 6.226384830474854,
|
|
"epoch": 0.3474920522783469,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004992415788662514,
|
|
"loss": 6.1395,
|
|
"mean_token_accuracy": 0.15226749777793885,
|
|
"num_tokens": 7345973.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 6.269987630844116,
|
|
"epoch": 0.34793359237018723,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004992389931839529,
|
|
"loss": 6.1567,
|
|
"mean_token_accuracy": 0.14694736152887344,
|
|
"num_tokens": 7355776.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 6.228302812576294,
|
|
"epoch": 0.34837513246202756,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004992364031089401,
|
|
"loss": 6.1744,
|
|
"mean_token_accuracy": 0.15075116157531737,
|
|
"num_tokens": 7364820.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 6.300107622146607,
|
|
"epoch": 0.3488166725538679,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004992338086412636,
|
|
"loss": 6.1812,
|
|
"mean_token_accuracy": 0.14802317172288895,
|
|
"num_tokens": 7373881.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 6.2126740455627445,
|
|
"epoch": 0.3492582126457082,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004992312097809744,
|
|
"loss": 6.1403,
|
|
"mean_token_accuracy": 0.15314085334539412,
|
|
"num_tokens": 7383095.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 6.218991088867187,
|
|
"epoch": 0.34969975273754855,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004992286065281234,
|
|
"loss": 6.1802,
|
|
"mean_token_accuracy": 0.1452938474714756,
|
|
"num_tokens": 7392702.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 6.283171558380127,
|
|
"epoch": 0.3501412928293889,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004992259988827614,
|
|
"loss": 6.3207,
|
|
"mean_token_accuracy": 0.14126615449786187,
|
|
"num_tokens": 7402560.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 6.350764322280884,
|
|
"epoch": 0.35058283292122927,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004992233868449397,
|
|
"loss": 6.103,
|
|
"mean_token_accuracy": 0.15924863666296005,
|
|
"num_tokens": 7412375.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 6.316436672210694,
|
|
"epoch": 0.3510243730130696,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004992207704147093,
|
|
"loss": 6.1616,
|
|
"mean_token_accuracy": 0.14135508239269257,
|
|
"num_tokens": 7420734.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 6.153539371490479,
|
|
"epoch": 0.35146591310490993,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004992181495921216,
|
|
"loss": 6.1609,
|
|
"mean_token_accuracy": 0.15113684087991713,
|
|
"num_tokens": 7430156.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 6.280019330978393,
|
|
"epoch": 0.35190745319675026,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004992155243772277,
|
|
"loss": 6.139,
|
|
"mean_token_accuracy": 0.15385181754827498,
|
|
"num_tokens": 7439189.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 6.287850189208984,
|
|
"epoch": 0.3523489932885906,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004992128947700795,
|
|
"loss": 6.1788,
|
|
"mean_token_accuracy": 0.14511018246412277,
|
|
"num_tokens": 7448768.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 6.22083477973938,
|
|
"epoch": 0.3527905333804309,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000499210260770728,
|
|
"loss": 6.1243,
|
|
"mean_token_accuracy": 0.15062997192144395,
|
|
"num_tokens": 7458468.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 6.228656339645386,
|
|
"epoch": 0.35323207347227126,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.000499207622379225,
|
|
"loss": 6.2126,
|
|
"mean_token_accuracy": 0.1429911307990551,
|
|
"num_tokens": 7467351.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 6.292384910583496,
|
|
"epoch": 0.35367361356411164,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004992049795956222,
|
|
"loss": 6.1705,
|
|
"mean_token_accuracy": 0.14206876754760742,
|
|
"num_tokens": 7477116.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 6.26902494430542,
|
|
"epoch": 0.354115153655952,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004992023324199715,
|
|
"loss": 6.1079,
|
|
"mean_token_accuracy": 0.1501702331006527,
|
|
"num_tokens": 7485216.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 6.2245752811431885,
|
|
"epoch": 0.3545566937477923,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004991996808523245,
|
|
"loss": 6.2427,
|
|
"mean_token_accuracy": 0.14149800166487694,
|
|
"num_tokens": 7495084.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 6.3255280494689945,
|
|
"epoch": 0.35499823383963264,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004991970248927332,
|
|
"loss": 6.2509,
|
|
"mean_token_accuracy": 0.14352200627326966,
|
|
"num_tokens": 7503219.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 6.284476709365845,
|
|
"epoch": 0.35543977393147297,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004991943645412498,
|
|
"loss": 6.0345,
|
|
"mean_token_accuracy": 0.1627778947353363,
|
|
"num_tokens": 7511961.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 6.1485429286956785,
|
|
"epoch": 0.3558813140233133,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004991916997979263,
|
|
"loss": 6.1654,
|
|
"mean_token_accuracy": 0.14940103366971016,
|
|
"num_tokens": 7521927.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 6.13094744682312,
|
|
"epoch": 0.35632285411515363,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004991890306628149,
|
|
"loss": 6.0939,
|
|
"mean_token_accuracy": 0.15506702959537505,
|
|
"num_tokens": 7531093.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 6.243637800216675,
|
|
"epoch": 0.356764394206994,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004991863571359678,
|
|
"loss": 6.0711,
|
|
"mean_token_accuracy": 0.15308146178722382,
|
|
"num_tokens": 7539813.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 6.321143770217896,
|
|
"epoch": 0.35720593429883435,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004991836792174376,
|
|
"loss": 6.2364,
|
|
"mean_token_accuracy": 0.1433838851749897,
|
|
"num_tokens": 7548954.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 6.192954874038696,
|
|
"epoch": 0.3576474743906747,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004991809969072765,
|
|
"loss": 6.11,
|
|
"mean_token_accuracy": 0.14762938171625137,
|
|
"num_tokens": 7558275.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 6.174587869644165,
|
|
"epoch": 0.358089014482515,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004991783102055371,
|
|
"loss": 6.1449,
|
|
"mean_token_accuracy": 0.15545178204774857,
|
|
"num_tokens": 7567870.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 6.297899484634399,
|
|
"epoch": 0.35853055457435534,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004991756191122723,
|
|
"loss": 6.0934,
|
|
"mean_token_accuracy": 0.1541736677289009,
|
|
"num_tokens": 7577485.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 6.299658966064453,
|
|
"epoch": 0.3589720946661957,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004991729236275346,
|
|
"loss": 6.138,
|
|
"mean_token_accuracy": 0.14600877314805985,
|
|
"num_tokens": 7587398.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 6.189863204956055,
|
|
"epoch": 0.359413634758036,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004991702237513768,
|
|
"loss": 6.1578,
|
|
"mean_token_accuracy": 0.14482004195451736,
|
|
"num_tokens": 7596310.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 6.276207828521729,
|
|
"epoch": 0.3598551748498764,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004991675194838517,
|
|
"loss": 6.1762,
|
|
"mean_token_accuracy": 0.14214570224285125,
|
|
"num_tokens": 7606971.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 6.229099607467651,
|
|
"epoch": 0.3602967149417167,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004991648108250125,
|
|
"loss": 6.1613,
|
|
"mean_token_accuracy": 0.1436733439564705,
|
|
"num_tokens": 7616636.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 6.272100257873535,
|
|
"epoch": 0.36073825503355705,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.000499162097774912,
|
|
"loss": 6.1936,
|
|
"mean_token_accuracy": 0.14892185628414153,
|
|
"num_tokens": 7625128.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 6.300772094726563,
|
|
"epoch": 0.3611797951253974,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004991593803336037,
|
|
"loss": 6.1048,
|
|
"mean_token_accuracy": 0.15312197506427766,
|
|
"num_tokens": 7634224.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 6.205416059494018,
|
|
"epoch": 0.3616213352172377,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004991566585011405,
|
|
"loss": 6.0989,
|
|
"mean_token_accuracy": 0.15441585183143616,
|
|
"num_tokens": 7643392.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 6.1346405982971195,
|
|
"epoch": 0.36206287530907805,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004991539322775758,
|
|
"loss": 6.1058,
|
|
"mean_token_accuracy": 0.15174489617347717,
|
|
"num_tokens": 7652491.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 6.368760204315185,
|
|
"epoch": 0.3625044154009184,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004991512016629632,
|
|
"loss": 6.3038,
|
|
"mean_token_accuracy": 0.13078175261616706,
|
|
"num_tokens": 7663192.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 6.315375518798828,
|
|
"epoch": 0.36294595549275877,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004991484666573558,
|
|
"loss": 6.1522,
|
|
"mean_token_accuracy": 0.14904795587062836,
|
|
"num_tokens": 7672801.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 6.252296113967896,
|
|
"epoch": 0.3633874955845991,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004991457272608077,
|
|
"loss": 6.1542,
|
|
"mean_token_accuracy": 0.14702531695365906,
|
|
"num_tokens": 7683013.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 6.297828722000122,
|
|
"epoch": 0.3638290356764394,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004991429834733721,
|
|
"loss": 6.1931,
|
|
"mean_token_accuracy": 0.14496390148997307,
|
|
"num_tokens": 7692760.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 6.298480558395386,
|
|
"epoch": 0.36427057576827976,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000499140235295103,
|
|
"loss": 6.1446,
|
|
"mean_token_accuracy": 0.14857310950756072,
|
|
"num_tokens": 7702005.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 6.211084604263306,
|
|
"epoch": 0.3647121158601201,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004991374827260542,
|
|
"loss": 6.1843,
|
|
"mean_token_accuracy": 0.1434581458568573,
|
|
"num_tokens": 7711604.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 6.183524751663208,
|
|
"epoch": 0.3651536559519604,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004991347257662795,
|
|
"loss": 6.071,
|
|
"mean_token_accuracy": 0.14973973408341407,
|
|
"num_tokens": 7720434.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 6.288224840164185,
|
|
"epoch": 0.36559519604380075,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000499131964415833,
|
|
"loss": 6.1418,
|
|
"mean_token_accuracy": 0.15498689860105513,
|
|
"num_tokens": 7730733.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 6.203797483444214,
|
|
"epoch": 0.36603673613564114,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004991291986747689,
|
|
"loss": 6.2046,
|
|
"mean_token_accuracy": 0.14789941981434823,
|
|
"num_tokens": 7740394.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 6.29754409790039,
|
|
"epoch": 0.36647827622748147,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004991264285431412,
|
|
"loss": 6.1513,
|
|
"mean_token_accuracy": 0.1500290587544441,
|
|
"num_tokens": 7748919.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 6.3295409202575685,
|
|
"epoch": 0.3669198163193218,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004991236540210041,
|
|
"loss": 6.1714,
|
|
"mean_token_accuracy": 0.1469644583761692,
|
|
"num_tokens": 7758591.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 6.285003566741944,
|
|
"epoch": 0.36736135641116213,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004991208751084122,
|
|
"loss": 6.2316,
|
|
"mean_token_accuracy": 0.13881740272045134,
|
|
"num_tokens": 7768269.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 6.3394371509552006,
|
|
"epoch": 0.36780289650300246,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004991180918054199,
|
|
"loss": 6.2465,
|
|
"mean_token_accuracy": 0.13873956948518754,
|
|
"num_tokens": 7776980.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 6.301831388473511,
|
|
"epoch": 0.3682444365948428,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004991153041120815,
|
|
"loss": 6.153,
|
|
"mean_token_accuracy": 0.14983465075492858,
|
|
"num_tokens": 7786664.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 6.168996095657349,
|
|
"epoch": 0.3686859766866831,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004991125120284519,
|
|
"loss": 6.0133,
|
|
"mean_token_accuracy": 0.15708141028881073,
|
|
"num_tokens": 7794981.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 6.173023843765259,
|
|
"epoch": 0.3691275167785235,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004991097155545856,
|
|
"loss": 6.0913,
|
|
"mean_token_accuracy": 0.14929922968149184,
|
|
"num_tokens": 7804850.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 6.1990776538848875,
|
|
"epoch": 0.36956905687036384,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004991069146905374,
|
|
"loss": 6.1201,
|
|
"mean_token_accuracy": 0.1546562761068344,
|
|
"num_tokens": 7814117.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 6.218803024291992,
|
|
"epoch": 0.3700105969622042,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004991041094363621,
|
|
"loss": 6.1467,
|
|
"mean_token_accuracy": 0.1517006754875183,
|
|
"num_tokens": 7823384.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 6.262414836883545,
|
|
"epoch": 0.3704521370540445,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004991012997921149,
|
|
"loss": 6.1422,
|
|
"mean_token_accuracy": 0.15224702507257462,
|
|
"num_tokens": 7834072.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 6.276657199859619,
|
|
"epoch": 0.37089367714588484,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004990984857578506,
|
|
"loss": 6.1365,
|
|
"mean_token_accuracy": 0.14929545894265175,
|
|
"num_tokens": 7843334.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 6.120020055770874,
|
|
"epoch": 0.37133521723772517,
|
|
"grad_norm": 4.125,
|
|
"learning_rate": 0.0004990956673336245,
|
|
"loss": 6.0645,
|
|
"mean_token_accuracy": 0.15058329552412034,
|
|
"num_tokens": 7853187.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 6.233019495010376,
|
|
"epoch": 0.3717767573295655,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004990928445194917,
|
|
"loss": 6.1478,
|
|
"mean_token_accuracy": 0.15026503801345825,
|
|
"num_tokens": 7862262.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 6.240013313293457,
|
|
"epoch": 0.3722182974214059,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004990900173155074,
|
|
"loss": 6.0835,
|
|
"mean_token_accuracy": 0.1559366464614868,
|
|
"num_tokens": 7870725.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 6.1844745635986325,
|
|
"epoch": 0.3726598375132462,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004990871857217273,
|
|
"loss": 6.0175,
|
|
"mean_token_accuracy": 0.156622314453125,
|
|
"num_tokens": 7879492.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 6.186220645904541,
|
|
"epoch": 0.37310137760508655,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004990843497382066,
|
|
"loss": 6.1199,
|
|
"mean_token_accuracy": 0.15137410163879395,
|
|
"num_tokens": 7888710.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 6.2027770519256595,
|
|
"epoch": 0.3735429176969269,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004990815093650009,
|
|
"loss": 6.1373,
|
|
"mean_token_accuracy": 0.15678878873586655,
|
|
"num_tokens": 7898313.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 6.225341176986694,
|
|
"epoch": 0.3739844577887672,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004990786646021659,
|
|
"loss": 6.1545,
|
|
"mean_token_accuracy": 0.15106336325407027,
|
|
"num_tokens": 7906726.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 6.251669549942017,
|
|
"epoch": 0.37442599788060754,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004990758154497573,
|
|
"loss": 6.0697,
|
|
"mean_token_accuracy": 0.1596512719988823,
|
|
"num_tokens": 7915554.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 6.321279048919678,
|
|
"epoch": 0.3748675379724479,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004990729619078309,
|
|
"loss": 6.1919,
|
|
"mean_token_accuracy": 0.1491725593805313,
|
|
"num_tokens": 7924732.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 6.317298793792725,
|
|
"epoch": 0.37530907806428826,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004990701039764427,
|
|
"loss": 6.1122,
|
|
"mean_token_accuracy": 0.15492920577526093,
|
|
"num_tokens": 7933808.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 6.2203545570373535,
|
|
"epoch": 0.3757506181561286,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004990672416556485,
|
|
"loss": 6.0878,
|
|
"mean_token_accuracy": 0.15237104147672653,
|
|
"num_tokens": 7942558.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 6.167264366149903,
|
|
"epoch": 0.3761921582479689,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004990643749455045,
|
|
"loss": 6.1847,
|
|
"mean_token_accuracy": 0.14426907226443292,
|
|
"num_tokens": 7951951.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 6.262331008911133,
|
|
"epoch": 0.37663369833980925,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004990615038460667,
|
|
"loss": 6.0762,
|
|
"mean_token_accuracy": 0.15311131328344346,
|
|
"num_tokens": 7960543.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 6.225819635391235,
|
|
"epoch": 0.3770752384316496,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004990586283573916,
|
|
"loss": 6.0691,
|
|
"mean_token_accuracy": 0.14869122356176376,
|
|
"num_tokens": 7970273.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 6.235108423233032,
|
|
"epoch": 0.3775167785234899,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004990557484795355,
|
|
"loss": 6.1568,
|
|
"mean_token_accuracy": 0.14895667880773544,
|
|
"num_tokens": 7978888.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 6.253112888336181,
|
|
"epoch": 0.37795831861533025,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004990528642125545,
|
|
"loss": 6.1542,
|
|
"mean_token_accuracy": 0.14458952248096466,
|
|
"num_tokens": 7988843.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 6.303048610687256,
|
|
"epoch": 0.37839985870717063,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004990499755565055,
|
|
"loss": 6.1415,
|
|
"mean_token_accuracy": 0.15063393414020537,
|
|
"num_tokens": 7998403.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 6.212564897537232,
|
|
"epoch": 0.37884139879901096,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004990470825114448,
|
|
"loss": 6.1823,
|
|
"mean_token_accuracy": 0.14829795211553573,
|
|
"num_tokens": 8007493.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 6.183409309387207,
|
|
"epoch": 0.3792829388908513,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004990441850774292,
|
|
"loss": 6.1306,
|
|
"mean_token_accuracy": 0.15667677968740462,
|
|
"num_tokens": 8016399.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 6.299896287918091,
|
|
"epoch": 0.3797244789826916,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004990412832545155,
|
|
"loss": 6.1374,
|
|
"mean_token_accuracy": 0.14585245102643968,
|
|
"num_tokens": 8025891.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 6.230182123184204,
|
|
"epoch": 0.38016601907453196,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004990383770427603,
|
|
"loss": 6.067,
|
|
"mean_token_accuracy": 0.1459854580461979,
|
|
"num_tokens": 8034733.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 6.226004886627197,
|
|
"epoch": 0.3806075591663723,
|
|
"grad_norm": 4.03125,
|
|
"learning_rate": 0.0004990354664422209,
|
|
"loss": 6.1477,
|
|
"mean_token_accuracy": 0.1523943141102791,
|
|
"num_tokens": 8044443.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 6.189437389373779,
|
|
"epoch": 0.3810490992582126,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004990325514529541,
|
|
"loss": 6.116,
|
|
"mean_token_accuracy": 0.15985741317272187,
|
|
"num_tokens": 8053920.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 6.259650993347168,
|
|
"epoch": 0.381490639350053,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004990296320750169,
|
|
"loss": 6.1096,
|
|
"mean_token_accuracy": 0.1530056282877922,
|
|
"num_tokens": 8063455.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 6.243551778793335,
|
|
"epoch": 0.38193217944189334,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004990267083084667,
|
|
"loss": 6.1845,
|
|
"mean_token_accuracy": 0.14791684821248055,
|
|
"num_tokens": 8073353.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 6.274292850494385,
|
|
"epoch": 0.38237371953373367,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004990237801533607,
|
|
"loss": 6.2066,
|
|
"mean_token_accuracy": 0.15257567763328553,
|
|
"num_tokens": 8082164.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 6.287510538101197,
|
|
"epoch": 0.382815259625574,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004990208476097562,
|
|
"loss": 6.1886,
|
|
"mean_token_accuracy": 0.1459839954972267,
|
|
"num_tokens": 8090790.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 6.418135309219361,
|
|
"epoch": 0.38325679971741433,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004990179106777109,
|
|
"loss": 6.2336,
|
|
"mean_token_accuracy": 0.14242262542247772,
|
|
"num_tokens": 8100412.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 6.273163890838623,
|
|
"epoch": 0.38369833980925466,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004990149693572819,
|
|
"loss": 6.2018,
|
|
"mean_token_accuracy": 0.14505023881793022,
|
|
"num_tokens": 8110002.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 6.2056801319122314,
|
|
"epoch": 0.384139879901095,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004990120236485271,
|
|
"loss": 6.099,
|
|
"mean_token_accuracy": 0.15307314246892928,
|
|
"num_tokens": 8118898.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 6.196920156478882,
|
|
"epoch": 0.3845814199929354,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004990090735515043,
|
|
"loss": 6.1459,
|
|
"mean_token_accuracy": 0.1457451120018959,
|
|
"num_tokens": 8128207.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 6.205824518203736,
|
|
"epoch": 0.3850229600847757,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000499006119066271,
|
|
"loss": 6.1487,
|
|
"mean_token_accuracy": 0.1461340069770813,
|
|
"num_tokens": 8137317.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 6.264606618881226,
|
|
"epoch": 0.38546450017661604,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004990031601928854,
|
|
"loss": 6.1663,
|
|
"mean_token_accuracy": 0.1496730253100395,
|
|
"num_tokens": 8146519.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 6.180057716369629,
|
|
"epoch": 0.3859060402684564,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004990001969314051,
|
|
"loss": 6.2049,
|
|
"mean_token_accuracy": 0.1440427668392658,
|
|
"num_tokens": 8155916.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 6.339586400985718,
|
|
"epoch": 0.3863475803602967,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004989972292818884,
|
|
"loss": 6.2029,
|
|
"mean_token_accuracy": 0.14926931411027908,
|
|
"num_tokens": 8165251.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 6.304240703582764,
|
|
"epoch": 0.38678912045213704,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004989942572443934,
|
|
"loss": 6.1867,
|
|
"mean_token_accuracy": 0.1430036559700966,
|
|
"num_tokens": 8174761.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 6.2764472484588625,
|
|
"epoch": 0.38723066054397737,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004989912808189784,
|
|
"loss": 6.1522,
|
|
"mean_token_accuracy": 0.15029871091246605,
|
|
"num_tokens": 8182980.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 6.334861803054809,
|
|
"epoch": 0.38767220063581775,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004989883000057013,
|
|
"loss": 6.1787,
|
|
"mean_token_accuracy": 0.14282853454351424,
|
|
"num_tokens": 8193306.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 6.217415761947632,
|
|
"epoch": 0.3881137407276581,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000498985314804621,
|
|
"loss": 6.068,
|
|
"mean_token_accuracy": 0.15467920452356337,
|
|
"num_tokens": 8203446.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 6.20694055557251,
|
|
"epoch": 0.3885552808194984,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004989823252157958,
|
|
"loss": 6.1278,
|
|
"mean_token_accuracy": 0.147111739218235,
|
|
"num_tokens": 8212414.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 6.193415260314941,
|
|
"epoch": 0.38899682091133875,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004989793312392841,
|
|
"loss": 6.0397,
|
|
"mean_token_accuracy": 0.15125779658555985,
|
|
"num_tokens": 8221509.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 6.265850067138672,
|
|
"epoch": 0.3894383610031791,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004989763328751448,
|
|
"loss": 6.1512,
|
|
"mean_token_accuracy": 0.15394337922334672,
|
|
"num_tokens": 8230017.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 6.226738405227661,
|
|
"epoch": 0.3898799010950194,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004989733301234365,
|
|
"loss": 6.1199,
|
|
"mean_token_accuracy": 0.15255994945764542,
|
|
"num_tokens": 8238853.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 6.279262447357178,
|
|
"epoch": 0.39032144118685974,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000498970322984218,
|
|
"loss": 6.1839,
|
|
"mean_token_accuracy": 0.14515341222286224,
|
|
"num_tokens": 8248112.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 6.294642305374145,
|
|
"epoch": 0.39076298127870013,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004989673114575483,
|
|
"loss": 6.1343,
|
|
"mean_token_accuracy": 0.14913589581847192,
|
|
"num_tokens": 8257166.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 6.163078498840332,
|
|
"epoch": 0.39120452137054046,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004989642955434863,
|
|
"loss": 6.1596,
|
|
"mean_token_accuracy": 0.14764805734157563,
|
|
"num_tokens": 8266229.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 6.260275363922119,
|
|
"epoch": 0.3916460614623808,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004989612752420912,
|
|
"loss": 6.1085,
|
|
"mean_token_accuracy": 0.14915528297424316,
|
|
"num_tokens": 8275102.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 6.19262204170227,
|
|
"epoch": 0.3920876015542211,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000498958250553422,
|
|
"loss": 6.0353,
|
|
"mean_token_accuracy": 0.15324682742357254,
|
|
"num_tokens": 8283847.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 6.227700424194336,
|
|
"epoch": 0.39252914164606145,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004989552214775381,
|
|
"loss": 6.1766,
|
|
"mean_token_accuracy": 0.144762846827507,
|
|
"num_tokens": 8292622.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 6.3205742835998535,
|
|
"epoch": 0.3929706817379018,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004989521880144988,
|
|
"loss": 6.0763,
|
|
"mean_token_accuracy": 0.1604698970913887,
|
|
"num_tokens": 8301026.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 6.306861019134521,
|
|
"epoch": 0.3934122218297421,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004989491501643635,
|
|
"loss": 6.3392,
|
|
"mean_token_accuracy": 0.13891248479485513,
|
|
"num_tokens": 8310977.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 6.242893123626709,
|
|
"epoch": 0.3938537619215825,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004989461079271916,
|
|
"loss": 6.1061,
|
|
"mean_token_accuracy": 0.153610959649086,
|
|
"num_tokens": 8319391.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 6.266516590118409,
|
|
"epoch": 0.39429530201342283,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004989430613030429,
|
|
"loss": 6.0661,
|
|
"mean_token_accuracy": 0.15280731469392778,
|
|
"num_tokens": 8328639.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 6.233418989181518,
|
|
"epoch": 0.39473684210526316,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000498940010291977,
|
|
"loss": 6.1681,
|
|
"mean_token_accuracy": 0.1455265462398529,
|
|
"num_tokens": 8338190.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 6.24021577835083,
|
|
"epoch": 0.3951783821971035,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.0004989369548940536,
|
|
"loss": 6.1149,
|
|
"mean_token_accuracy": 0.14980215281248094,
|
|
"num_tokens": 8346874.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 6.238305997848511,
|
|
"epoch": 0.3956199222889438,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004989338951093327,
|
|
"loss": 6.0917,
|
|
"mean_token_accuracy": 0.15748346149921416,
|
|
"num_tokens": 8356446.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 6.260767602920533,
|
|
"epoch": 0.39606146238078416,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004989308309378741,
|
|
"loss": 6.1065,
|
|
"mean_token_accuracy": 0.15552318841218948,
|
|
"num_tokens": 8365694.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 6.261749219894409,
|
|
"epoch": 0.3965030024726245,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004989277623797379,
|
|
"loss": 6.1529,
|
|
"mean_token_accuracy": 0.14739976376295089,
|
|
"num_tokens": 8374282.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 6.177736425399781,
|
|
"epoch": 0.3969445425644649,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004989246894349841,
|
|
"loss": 6.1265,
|
|
"mean_token_accuracy": 0.15178793370723725,
|
|
"num_tokens": 8383315.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 6.239930438995361,
|
|
"epoch": 0.3973860826563052,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004989216121036732,
|
|
"loss": 6.0836,
|
|
"mean_token_accuracy": 0.15232260078191756,
|
|
"num_tokens": 8392263.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 6.2768608093261715,
|
|
"epoch": 0.39782762274814554,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004989185303858651,
|
|
"loss": 6.1353,
|
|
"mean_token_accuracy": 0.1466260112822056,
|
|
"num_tokens": 8400734.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 6.238184452056885,
|
|
"epoch": 0.39826916283998587,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004989154442816203,
|
|
"loss": 6.1551,
|
|
"mean_token_accuracy": 0.14806681126356125,
|
|
"num_tokens": 8410635.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 6.2955420970916744,
|
|
"epoch": 0.3987107029318262,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004989123537909994,
|
|
"loss": 6.1333,
|
|
"mean_token_accuracy": 0.15284045189619064,
|
|
"num_tokens": 8420111.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 6.221891450881958,
|
|
"epoch": 0.39915224302366653,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004989092589140629,
|
|
"loss": 6.0963,
|
|
"mean_token_accuracy": 0.1426243230700493,
|
|
"num_tokens": 8429459.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 6.260979318618775,
|
|
"epoch": 0.39959378311550686,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004989061596508712,
|
|
"loss": 6.102,
|
|
"mean_token_accuracy": 0.15004376024007798,
|
|
"num_tokens": 8438083.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 6.165115070343018,
|
|
"epoch": 0.40003532320734725,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004989030560014853,
|
|
"loss": 6.1361,
|
|
"mean_token_accuracy": 0.15093458965420722,
|
|
"num_tokens": 8447713.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 6.242450094223022,
|
|
"epoch": 0.4004768632991876,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004988999479659657,
|
|
"loss": 6.1097,
|
|
"mean_token_accuracy": 0.15013383626937865,
|
|
"num_tokens": 8457394.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 6.2484495639801025,
|
|
"epoch": 0.4009184033910279,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004988968355443737,
|
|
"loss": 6.067,
|
|
"mean_token_accuracy": 0.1564113289117813,
|
|
"num_tokens": 8467333.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 6.130180597305298,
|
|
"epoch": 0.40135994348286824,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004988937187367699,
|
|
"loss": 6.1609,
|
|
"mean_token_accuracy": 0.14751122146844864,
|
|
"num_tokens": 8477530.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 6.293128538131714,
|
|
"epoch": 0.4018014835747086,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004988905975432154,
|
|
"loss": 6.2429,
|
|
"mean_token_accuracy": 0.14654314517974854,
|
|
"num_tokens": 8486861.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 6.31817512512207,
|
|
"epoch": 0.4022430236665489,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004988874719637715,
|
|
"loss": 6.0701,
|
|
"mean_token_accuracy": 0.15331597551703452,
|
|
"num_tokens": 8496541.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 6.139620399475097,
|
|
"epoch": 0.40268456375838924,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004988843419984994,
|
|
"loss": 6.1423,
|
|
"mean_token_accuracy": 0.147700135409832,
|
|
"num_tokens": 8505667.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 6.309397125244141,
|
|
"epoch": 0.4031261038502296,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004988812076474604,
|
|
"loss": 6.1109,
|
|
"mean_token_accuracy": 0.15095604285597802,
|
|
"num_tokens": 8515133.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 6.331642770767212,
|
|
"epoch": 0.40356764394206995,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004988780689107158,
|
|
"loss": 6.099,
|
|
"mean_token_accuracy": 0.1547642931342125,
|
|
"num_tokens": 8524797.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 6.155235958099365,
|
|
"epoch": 0.4040091840339103,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004988749257883271,
|
|
"loss": 6.1163,
|
|
"mean_token_accuracy": 0.1479724317789078,
|
|
"num_tokens": 8534667.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 6.191133165359497,
|
|
"epoch": 0.4044507241257506,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000498871778280356,
|
|
"loss": 6.1141,
|
|
"mean_token_accuracy": 0.15516297817230223,
|
|
"num_tokens": 8543874.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 6.1999842643737795,
|
|
"epoch": 0.40489226421759095,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004988686263868641,
|
|
"loss": 6.1129,
|
|
"mean_token_accuracy": 0.14598144590854645,
|
|
"num_tokens": 8553620.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 6.319142484664917,
|
|
"epoch": 0.4053338043094313,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004988654701079131,
|
|
"loss": 6.1853,
|
|
"mean_token_accuracy": 0.14762324318289757,
|
|
"num_tokens": 8563857.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 6.312997579574585,
|
|
"epoch": 0.4057753444012716,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004988623094435649,
|
|
"loss": 6.1642,
|
|
"mean_token_accuracy": 0.13997963890433313,
|
|
"num_tokens": 8572677.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 6.116331768035889,
|
|
"epoch": 0.406216884493112,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004988591443938813,
|
|
"loss": 6.1003,
|
|
"mean_token_accuracy": 0.15262969210743904,
|
|
"num_tokens": 8581907.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 6.220039224624633,
|
|
"epoch": 0.4066584245849523,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004988559749589244,
|
|
"loss": 6.1454,
|
|
"mean_token_accuracy": 0.14895498976111413,
|
|
"num_tokens": 8591701.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 6.287181425094604,
|
|
"epoch": 0.40709996467679266,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004988528011387563,
|
|
"loss": 6.167,
|
|
"mean_token_accuracy": 0.15494169369339944,
|
|
"num_tokens": 8601054.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 6.205023622512817,
|
|
"epoch": 0.407541504768633,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004988496229334392,
|
|
"loss": 6.0806,
|
|
"mean_token_accuracy": 0.15186309069395065,
|
|
"num_tokens": 8610346.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 6.23344054222107,
|
|
"epoch": 0.4079830448604733,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004988464403430352,
|
|
"loss": 6.0837,
|
|
"mean_token_accuracy": 0.15217070728540422,
|
|
"num_tokens": 8620823.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 6.270275688171386,
|
|
"epoch": 0.40842458495231365,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004988432533676067,
|
|
"loss": 6.2275,
|
|
"mean_token_accuracy": 0.14184264317154885,
|
|
"num_tokens": 8630184.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 6.302144241333008,
|
|
"epoch": 0.408866125044154,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004988400620072163,
|
|
"loss": 6.2212,
|
|
"mean_token_accuracy": 0.1352216251194477,
|
|
"num_tokens": 8640064.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 6.338855314254761,
|
|
"epoch": 0.40930766513599437,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004988368662619263,
|
|
"loss": 6.1382,
|
|
"mean_token_accuracy": 0.14780254140496255,
|
|
"num_tokens": 8650503.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 6.308487844467163,
|
|
"epoch": 0.4097492052278347,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004988336661317994,
|
|
"loss": 6.1487,
|
|
"mean_token_accuracy": 0.1496379256248474,
|
|
"num_tokens": 8659125.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 6.24177737236023,
|
|
"epoch": 0.41019074531967503,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004988304616168984,
|
|
"loss": 6.1595,
|
|
"mean_token_accuracy": 0.15009454786777496,
|
|
"num_tokens": 8668193.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 6.259683895111084,
|
|
"epoch": 0.41063228541151536,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004988272527172858,
|
|
"loss": 6.1284,
|
|
"mean_token_accuracy": 0.14531345665454865,
|
|
"num_tokens": 8677515.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 6.2487578868865965,
|
|
"epoch": 0.4110738255033557,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004988240394330246,
|
|
"loss": 6.1509,
|
|
"mean_token_accuracy": 0.14197378158569335,
|
|
"num_tokens": 8687549.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 6.216428947448731,
|
|
"epoch": 0.411515365595196,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004988208217641778,
|
|
"loss": 6.1462,
|
|
"mean_token_accuracy": 0.15048618465662003,
|
|
"num_tokens": 8697371.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 6.271879529953003,
|
|
"epoch": 0.41195690568703636,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004988175997108086,
|
|
"loss": 6.1572,
|
|
"mean_token_accuracy": 0.14906407445669173,
|
|
"num_tokens": 8707193.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 6.241507244110108,
|
|
"epoch": 0.41239844577887674,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004988143732729797,
|
|
"loss": 6.1306,
|
|
"mean_token_accuracy": 0.1517687276005745,
|
|
"num_tokens": 8716052.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 6.193820285797119,
|
|
"epoch": 0.4128399858707171,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004988111424507546,
|
|
"loss": 6.1083,
|
|
"mean_token_accuracy": 0.15722774118185043,
|
|
"num_tokens": 8726140.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 6.198861217498779,
|
|
"epoch": 0.4132815259625574,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004988079072441964,
|
|
"loss": 6.0886,
|
|
"mean_token_accuracy": 0.16114656776189804,
|
|
"num_tokens": 8735299.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 6.275176668167115,
|
|
"epoch": 0.41372306605439774,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004988046676533687,
|
|
"loss": 6.1618,
|
|
"mean_token_accuracy": 0.14906339049339296,
|
|
"num_tokens": 8744686.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 6.259121036529541,
|
|
"epoch": 0.41416460614623807,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004988014236783347,
|
|
"loss": 6.1494,
|
|
"mean_token_accuracy": 0.15465974658727646,
|
|
"num_tokens": 8754942.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 6.326023912429809,
|
|
"epoch": 0.4146061462380784,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004987981753191582,
|
|
"loss": 6.1409,
|
|
"mean_token_accuracy": 0.14824373871088029,
|
|
"num_tokens": 8764054.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 6.13715353012085,
|
|
"epoch": 0.41504768632991873,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004987949225759027,
|
|
"loss": 6.0228,
|
|
"mean_token_accuracy": 0.15374697595834733,
|
|
"num_tokens": 8773050.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 6.222603893280029,
|
|
"epoch": 0.4154892264217591,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004987916654486321,
|
|
"loss": 6.1314,
|
|
"mean_token_accuracy": 0.14893667995929719,
|
|
"num_tokens": 8782476.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 6.285632705688476,
|
|
"epoch": 0.41593076651359945,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004987884039374099,
|
|
"loss": 6.209,
|
|
"mean_token_accuracy": 0.14228173792362214,
|
|
"num_tokens": 8791147.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 6.412950849533081,
|
|
"epoch": 0.4163723066054398,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004987851380423001,
|
|
"loss": 6.2029,
|
|
"mean_token_accuracy": 0.14925967529416084,
|
|
"num_tokens": 8801151.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 6.243388557434082,
|
|
"epoch": 0.4168138466972801,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004987818677633668,
|
|
"loss": 6.1428,
|
|
"mean_token_accuracy": 0.14483709558844565,
|
|
"num_tokens": 8809587.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 6.118964433670044,
|
|
"epoch": 0.41725538678912044,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.000498778593100674,
|
|
"loss": 6.0157,
|
|
"mean_token_accuracy": 0.15019246488809584,
|
|
"num_tokens": 8818168.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 6.184421253204346,
|
|
"epoch": 0.4176969268809608,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004987753140542857,
|
|
"loss": 6.0773,
|
|
"mean_token_accuracy": 0.15195630490779877,
|
|
"num_tokens": 8827477.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 6.219823694229126,
|
|
"epoch": 0.4181384669728011,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004987720306242664,
|
|
"loss": 6.075,
|
|
"mean_token_accuracy": 0.15527386367321014,
|
|
"num_tokens": 8837067.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 6.181506729125976,
|
|
"epoch": 0.4185800070646415,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004987687428106803,
|
|
"loss": 6.1618,
|
|
"mean_token_accuracy": 0.15378424376249314,
|
|
"num_tokens": 8845790.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 6.227482891082763,
|
|
"epoch": 0.4190215471564818,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004987654506135917,
|
|
"loss": 6.1095,
|
|
"mean_token_accuracy": 0.15375100672245026,
|
|
"num_tokens": 8855242.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 6.376747179031372,
|
|
"epoch": 0.41946308724832215,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004987621540330652,
|
|
"loss": 6.1442,
|
|
"mean_token_accuracy": 0.1527914009988308,
|
|
"num_tokens": 8864459.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 6.280859184265137,
|
|
"epoch": 0.4199046273401625,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004987588530691653,
|
|
"loss": 6.2056,
|
|
"mean_token_accuracy": 0.147312493622303,
|
|
"num_tokens": 8875028.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 6.171601629257202,
|
|
"epoch": 0.4203461674320028,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004987555477219569,
|
|
"loss": 6.0686,
|
|
"mean_token_accuracy": 0.1505084216594696,
|
|
"num_tokens": 8883857.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 6.242595100402832,
|
|
"epoch": 0.42078770752384315,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004987522379915045,
|
|
"loss": 6.0426,
|
|
"mean_token_accuracy": 0.15613523721694947,
|
|
"num_tokens": 8893499.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 6.229691648483277,
|
|
"epoch": 0.4212292476156835,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000498748923877873,
|
|
"loss": 6.0557,
|
|
"mean_token_accuracy": 0.15882878750562668,
|
|
"num_tokens": 8903368.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 6.212651014328003,
|
|
"epoch": 0.42167078770752386,
|
|
"grad_norm": 5.5,
|
|
"learning_rate": 0.0004987456053811273,
|
|
"loss": 6.1755,
|
|
"mean_token_accuracy": 0.14916257932782173,
|
|
"num_tokens": 8912701.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 6.215025615692139,
|
|
"epoch": 0.4221123277993642,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004987422825013325,
|
|
"loss": 6.1222,
|
|
"mean_token_accuracy": 0.14846726655960082,
|
|
"num_tokens": 8921962.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 6.263440942764282,
|
|
"epoch": 0.4225538678912045,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004987389552385536,
|
|
"loss": 6.1159,
|
|
"mean_token_accuracy": 0.14788118600845337,
|
|
"num_tokens": 8931923.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 6.222282361984253,
|
|
"epoch": 0.42299540798304486,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004987356235928558,
|
|
"loss": 6.1408,
|
|
"mean_token_accuracy": 0.1438957691192627,
|
|
"num_tokens": 8940403.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 6.247937631607056,
|
|
"epoch": 0.4234369480748852,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004987322875643044,
|
|
"loss": 6.0725,
|
|
"mean_token_accuracy": 0.1556072860956192,
|
|
"num_tokens": 8949377.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 6.289243221282959,
|
|
"epoch": 0.4238784881667255,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004987289471529647,
|
|
"loss": 6.2231,
|
|
"mean_token_accuracy": 0.14357297345995904,
|
|
"num_tokens": 8958719.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 6.263422870635987,
|
|
"epoch": 0.42432002825856585,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004987256023589022,
|
|
"loss": 6.18,
|
|
"mean_token_accuracy": 0.1407242827117443,
|
|
"num_tokens": 8968226.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 6.298874139785767,
|
|
"epoch": 0.42476156835040624,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004987222531821824,
|
|
"loss": 6.1177,
|
|
"mean_token_accuracy": 0.15129526555538178,
|
|
"num_tokens": 8976670.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 6.174004793167114,
|
|
"epoch": 0.42520310844224657,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004987188996228709,
|
|
"loss": 6.0665,
|
|
"mean_token_accuracy": 0.1531901016831398,
|
|
"num_tokens": 8986185.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 6.158194541931152,
|
|
"epoch": 0.4256446485340869,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004987155416810334,
|
|
"loss": 6.0544,
|
|
"mean_token_accuracy": 0.15613151341676712,
|
|
"num_tokens": 8995124.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 6.2976361274719235,
|
|
"epoch": 0.42608618862592723,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004987121793567356,
|
|
"loss": 6.1548,
|
|
"mean_token_accuracy": 0.14807211086153985,
|
|
"num_tokens": 9004380.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 6.3067573547363285,
|
|
"epoch": 0.42652772871776756,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004987088126500436,
|
|
"loss": 6.0737,
|
|
"mean_token_accuracy": 0.15086135640740395,
|
|
"num_tokens": 9013791.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 6.224890661239624,
|
|
"epoch": 0.4269692688096079,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000498705441561023,
|
|
"loss": 6.0936,
|
|
"mean_token_accuracy": 0.15923204869031907,
|
|
"num_tokens": 9023076.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 6.32174015045166,
|
|
"epoch": 0.4274108089014482,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004987020660897401,
|
|
"loss": 6.212,
|
|
"mean_token_accuracy": 0.14178509786725044,
|
|
"num_tokens": 9032720.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 6.264952182769775,
|
|
"epoch": 0.4278523489932886,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.000498698686236261,
|
|
"loss": 6.1792,
|
|
"mean_token_accuracy": 0.14186724573373793,
|
|
"num_tokens": 9042652.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 6.329478549957275,
|
|
"epoch": 0.42829388908512894,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004986953020006519,
|
|
"loss": 6.2139,
|
|
"mean_token_accuracy": 0.1418928436934948,
|
|
"num_tokens": 9052172.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 6.253849077224731,
|
|
"epoch": 0.4287354291769693,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004986919133829788,
|
|
"loss": 6.0903,
|
|
"mean_token_accuracy": 0.15230478197336197,
|
|
"num_tokens": 9061798.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 6.191249799728394,
|
|
"epoch": 0.4291769692688096,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004986885203833086,
|
|
"loss": 6.0329,
|
|
"mean_token_accuracy": 0.15033992528915405,
|
|
"num_tokens": 9070429.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 6.241788244247436,
|
|
"epoch": 0.42961850936064994,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004986851230017075,
|
|
"loss": 6.15,
|
|
"mean_token_accuracy": 0.1566887989640236,
|
|
"num_tokens": 9080200.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 6.225221776962281,
|
|
"epoch": 0.43006004945249027,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004986817212382419,
|
|
"loss": 6.1323,
|
|
"mean_token_accuracy": 0.15193428695201874,
|
|
"num_tokens": 9089555.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 6.228102540969848,
|
|
"epoch": 0.4305015895443306,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004986783150929786,
|
|
"loss": 6.1154,
|
|
"mean_token_accuracy": 0.1448261022567749,
|
|
"num_tokens": 9099091.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 6.290770101547241,
|
|
"epoch": 0.430943129636171,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004986749045659845,
|
|
"loss": 6.1914,
|
|
"mean_token_accuracy": 0.14237287789583206,
|
|
"num_tokens": 9109008.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 6.272695302963257,
|
|
"epoch": 0.4313846697280113,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004986714896573261,
|
|
"loss": 6.0514,
|
|
"mean_token_accuracy": 0.15114877596497536,
|
|
"num_tokens": 9117882.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 6.255866146087646,
|
|
"epoch": 0.43182620981985165,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004986680703670704,
|
|
"loss": 6.2037,
|
|
"mean_token_accuracy": 0.14644545465707778,
|
|
"num_tokens": 9126860.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 6.22585277557373,
|
|
"epoch": 0.432267749911692,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004986646466952845,
|
|
"loss": 6.0799,
|
|
"mean_token_accuracy": 0.1504547193646431,
|
|
"num_tokens": 9135819.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 6.196601390838623,
|
|
"epoch": 0.4327092900035323,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004986612186420353,
|
|
"loss": 6.0686,
|
|
"mean_token_accuracy": 0.15574911236763,
|
|
"num_tokens": 9145302.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 6.1801060199737545,
|
|
"epoch": 0.43315083009537264,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004986577862073901,
|
|
"loss": 6.1494,
|
|
"mean_token_accuracy": 0.1479417622089386,
|
|
"num_tokens": 9154667.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 6.350726795196533,
|
|
"epoch": 0.43359237018721297,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004986543493914159,
|
|
"loss": 6.1896,
|
|
"mean_token_accuracy": 0.14393721222877504,
|
|
"num_tokens": 9164562.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 6.298789834976196,
|
|
"epoch": 0.43403391027905336,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004986509081941805,
|
|
"loss": 6.2075,
|
|
"mean_token_accuracy": 0.14493397623300552,
|
|
"num_tokens": 9174872.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 6.208137512207031,
|
|
"epoch": 0.4344754503708937,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004986474626157507,
|
|
"loss": 5.9565,
|
|
"mean_token_accuracy": 0.16489630788564683,
|
|
"num_tokens": 9184322.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 6.1365772724151615,
|
|
"epoch": 0.434916990462734,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004986440126561945,
|
|
"loss": 6.0811,
|
|
"mean_token_accuracy": 0.15020886659622193,
|
|
"num_tokens": 9194450.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 6.255832719802856,
|
|
"epoch": 0.43535853055457435,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004986405583155792,
|
|
"loss": 6.1312,
|
|
"mean_token_accuracy": 0.14965093955397607,
|
|
"num_tokens": 9203658.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 6.263164854049682,
|
|
"epoch": 0.4358000706464147,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004986370995939725,
|
|
"loss": 6.1128,
|
|
"mean_token_accuracy": 0.15106411650776863,
|
|
"num_tokens": 9213609.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 6.167392778396606,
|
|
"epoch": 0.436241610738255,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004986336364914423,
|
|
"loss": 6.1306,
|
|
"mean_token_accuracy": 0.14291212037205697,
|
|
"num_tokens": 9222704.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 6.223126554489136,
|
|
"epoch": 0.43668315083009535,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004986301690080564,
|
|
"loss": 6.1143,
|
|
"mean_token_accuracy": 0.14555411264300347,
|
|
"num_tokens": 9231599.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 6.2706419944763185,
|
|
"epoch": 0.43712469092193573,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004986266971438826,
|
|
"loss": 6.181,
|
|
"mean_token_accuracy": 0.14692962616682054,
|
|
"num_tokens": 9241886.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 6.284374094009399,
|
|
"epoch": 0.43756623101377606,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.000498623220898989,
|
|
"loss": 6.1704,
|
|
"mean_token_accuracy": 0.1431273728609085,
|
|
"num_tokens": 9251085.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 6.301024627685547,
|
|
"epoch": 0.4380077711056164,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004986197402734436,
|
|
"loss": 6.1277,
|
|
"mean_token_accuracy": 0.14820317775011063,
|
|
"num_tokens": 9259601.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 6.234680032730102,
|
|
"epoch": 0.4384493111974567,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004986162552673148,
|
|
"loss": 6.1537,
|
|
"mean_token_accuracy": 0.14889020547270776,
|
|
"num_tokens": 9268935.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 6.237508726119995,
|
|
"epoch": 0.43889085128929706,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004986127658806706,
|
|
"loss": 6.1582,
|
|
"mean_token_accuracy": 0.14848763048648833,
|
|
"num_tokens": 9277647.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 6.322979831695557,
|
|
"epoch": 0.4393323913811374,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004986092721135796,
|
|
"loss": 6.1039,
|
|
"mean_token_accuracy": 0.14526121839880943,
|
|
"num_tokens": 9286610.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 6.267163896560669,
|
|
"epoch": 0.4397739314729777,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004986057739661101,
|
|
"loss": 6.1928,
|
|
"mean_token_accuracy": 0.14434696733951569,
|
|
"num_tokens": 9295946.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 6.189084196090699,
|
|
"epoch": 0.4402154715648181,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004986022714383307,
|
|
"loss": 6.0794,
|
|
"mean_token_accuracy": 0.14832867309451103,
|
|
"num_tokens": 9304903.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 6.181007719039917,
|
|
"epoch": 0.44065701165665844,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004985987645303099,
|
|
"loss": 5.9935,
|
|
"mean_token_accuracy": 0.15543172061443328,
|
|
"num_tokens": 9313606.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 6.209528255462646,
|
|
"epoch": 0.44109855174849877,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004985952532421164,
|
|
"loss": 6.1194,
|
|
"mean_token_accuracy": 0.14723614528775214,
|
|
"num_tokens": 9322815.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 6.267077779769897,
|
|
"epoch": 0.4415400918403391,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004985917375738193,
|
|
"loss": 6.0501,
|
|
"mean_token_accuracy": 0.15317185521125792,
|
|
"num_tokens": 9332630.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 6.1830284118652346,
|
|
"epoch": 0.44198163193217943,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004985882175254871,
|
|
"loss": 6.0728,
|
|
"mean_token_accuracy": 0.1479358345270157,
|
|
"num_tokens": 9342216.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 6.253107023239136,
|
|
"epoch": 0.44242317202401976,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004985846930971887,
|
|
"loss": 6.1306,
|
|
"mean_token_accuracy": 0.14670003801584244,
|
|
"num_tokens": 9352295.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 6.196054363250733,
|
|
"epoch": 0.4428647121158601,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.0004985811642889937,
|
|
"loss": 6.1163,
|
|
"mean_token_accuracy": 0.15125398561358452,
|
|
"num_tokens": 9361462.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 6.217277193069458,
|
|
"epoch": 0.4433062522077005,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004985776311009705,
|
|
"loss": 6.0557,
|
|
"mean_token_accuracy": 0.1495061472058296,
|
|
"num_tokens": 9370379.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 6.280245161056518,
|
|
"epoch": 0.4437477922995408,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004985740935331888,
|
|
"loss": 6.104,
|
|
"mean_token_accuracy": 0.1499072551727295,
|
|
"num_tokens": 9379255.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 6.239386558532715,
|
|
"epoch": 0.44418933239138114,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004985705515857177,
|
|
"loss": 6.0894,
|
|
"mean_token_accuracy": 0.14710333198308945,
|
|
"num_tokens": 9389313.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 6.1093944072723385,
|
|
"epoch": 0.4446308724832215,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004985670052586268,
|
|
"loss": 5.8779,
|
|
"mean_token_accuracy": 0.164057657122612,
|
|
"num_tokens": 9397778.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 6.189831209182739,
|
|
"epoch": 0.4450724125750618,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004985634545519853,
|
|
"loss": 6.1612,
|
|
"mean_token_accuracy": 0.14539453983306885,
|
|
"num_tokens": 9407831.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 6.185821962356568,
|
|
"epoch": 0.44551395266690214,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004985598994658629,
|
|
"loss": 6.0563,
|
|
"mean_token_accuracy": 0.15882879197597505,
|
|
"num_tokens": 9418458.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 6.106141138076782,
|
|
"epoch": 0.44595549275874247,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004985563400003291,
|
|
"loss": 5.9568,
|
|
"mean_token_accuracy": 0.1698301136493683,
|
|
"num_tokens": 9426911.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 6.171579790115357,
|
|
"epoch": 0.44639703285058285,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004985527761554539,
|
|
"loss": 6.1417,
|
|
"mean_token_accuracy": 0.15014532953500748,
|
|
"num_tokens": 9435896.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 6.312262725830078,
|
|
"epoch": 0.4468385729424232,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.000498549207931307,
|
|
"loss": 6.1632,
|
|
"mean_token_accuracy": 0.1472449332475662,
|
|
"num_tokens": 9445272.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 6.271624374389648,
|
|
"epoch": 0.4472801130342635,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004985456353279581,
|
|
"loss": 6.1043,
|
|
"mean_token_accuracy": 0.14438070952892304,
|
|
"num_tokens": 9455377.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 6.281310558319092,
|
|
"epoch": 0.44772165312610385,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004985420583454774,
|
|
"loss": 6.1346,
|
|
"mean_token_accuracy": 0.14844611436128616,
|
|
"num_tokens": 9464918.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 6.201527786254883,
|
|
"epoch": 0.4481631932179442,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004985384769839349,
|
|
"loss": 6.1456,
|
|
"mean_token_accuracy": 0.14419942125678062,
|
|
"num_tokens": 9473322.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 6.247434282302857,
|
|
"epoch": 0.4486047333097845,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004985348912434008,
|
|
"loss": 6.0519,
|
|
"mean_token_accuracy": 0.15433547049760818,
|
|
"num_tokens": 9482255.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 6.251237630844116,
|
|
"epoch": 0.44904627340162484,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004985313011239452,
|
|
"loss": 6.0841,
|
|
"mean_token_accuracy": 0.15366279035806657,
|
|
"num_tokens": 9491709.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 6.1778288841247555,
|
|
"epoch": 0.4494878134934652,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004985277066256388,
|
|
"loss": 6.0674,
|
|
"mean_token_accuracy": 0.15499321296811103,
|
|
"num_tokens": 9500594.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 6.247628450393677,
|
|
"epoch": 0.44992935358530556,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004985241077485515,
|
|
"loss": 6.0831,
|
|
"mean_token_accuracy": 0.15359071865677834,
|
|
"num_tokens": 9509088.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 6.241946458816528,
|
|
"epoch": 0.4503708936771459,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004985205044927541,
|
|
"loss": 6.0756,
|
|
"mean_token_accuracy": 0.15193637013435363,
|
|
"num_tokens": 9517776.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 6.238159942626953,
|
|
"epoch": 0.4508124337689862,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004985168968583173,
|
|
"loss": 6.1324,
|
|
"mean_token_accuracy": 0.1565396472811699,
|
|
"num_tokens": 9527080.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 6.247459888458252,
|
|
"epoch": 0.45125397386082655,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004985132848453114,
|
|
"loss": 5.984,
|
|
"mean_token_accuracy": 0.16275231391191483,
|
|
"num_tokens": 9536358.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 6.1648458480834964,
|
|
"epoch": 0.4516955139526669,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004985096684538075,
|
|
"loss": 6.0744,
|
|
"mean_token_accuracy": 0.15135849714279176,
|
|
"num_tokens": 9545528.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 6.193127775192261,
|
|
"epoch": 0.4521370540445072,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004985060476838763,
|
|
"loss": 6.1043,
|
|
"mean_token_accuracy": 0.15256332159042357,
|
|
"num_tokens": 9554433.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 6.167931699752808,
|
|
"epoch": 0.4525785941363476,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004985024225355887,
|
|
"loss": 6.0743,
|
|
"mean_token_accuracy": 0.1511543370783329,
|
|
"num_tokens": 9563932.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 6.279501581192017,
|
|
"epoch": 0.45302013422818793,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004984987930090158,
|
|
"loss": 6.0467,
|
|
"mean_token_accuracy": 0.15174941271543502,
|
|
"num_tokens": 9572829.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 6.188870096206665,
|
|
"epoch": 0.45346167432002826,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004984951591042285,
|
|
"loss": 6.0999,
|
|
"mean_token_accuracy": 0.1528202399611473,
|
|
"num_tokens": 9583597.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 6.229509115219116,
|
|
"epoch": 0.4539032144118686,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004984915208212983,
|
|
"loss": 6.173,
|
|
"mean_token_accuracy": 0.14248777478933333,
|
|
"num_tokens": 9593114.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 6.253240156173706,
|
|
"epoch": 0.4543447545037089,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004984878781602964,
|
|
"loss": 6.0652,
|
|
"mean_token_accuracy": 0.14318513125181198,
|
|
"num_tokens": 9601454.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 6.231389141082763,
|
|
"epoch": 0.45478629459554926,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004984842311212939,
|
|
"loss": 6.1212,
|
|
"mean_token_accuracy": 0.1526548221707344,
|
|
"num_tokens": 9611994.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 6.281379318237304,
|
|
"epoch": 0.4552278346873896,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004984805797043625,
|
|
"loss": 6.0759,
|
|
"mean_token_accuracy": 0.15249461084604263,
|
|
"num_tokens": 9621318.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 6.2479390621185305,
|
|
"epoch": 0.45566937477923,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004984769239095736,
|
|
"loss": 6.0896,
|
|
"mean_token_accuracy": 0.1520428791642189,
|
|
"num_tokens": 9630270.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 6.206319427490234,
|
|
"epoch": 0.4561109148710703,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004984732637369989,
|
|
"loss": 6.1025,
|
|
"mean_token_accuracy": 0.14820861220359802,
|
|
"num_tokens": 9640391.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 6.210742044448852,
|
|
"epoch": 0.45655245496291064,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004984695991867099,
|
|
"loss": 6.1233,
|
|
"mean_token_accuracy": 0.14745756462216378,
|
|
"num_tokens": 9648827.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 6.217724370956421,
|
|
"epoch": 0.45699399505475097,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004984659302587788,
|
|
"loss": 6.0595,
|
|
"mean_token_accuracy": 0.14851401671767234,
|
|
"num_tokens": 9657940.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 6.192732238769532,
|
|
"epoch": 0.4574355351465913,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.000498462256953277,
|
|
"loss": 6.1821,
|
|
"mean_token_accuracy": 0.1421465255320072,
|
|
"num_tokens": 9668296.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 6.304067993164063,
|
|
"epoch": 0.45787707523843163,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004984585792702767,
|
|
"loss": 6.1234,
|
|
"mean_token_accuracy": 0.1482522204518318,
|
|
"num_tokens": 9677914.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 6.297015857696533,
|
|
"epoch": 0.45831861533027196,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004984548972098501,
|
|
"loss": 6.2678,
|
|
"mean_token_accuracy": 0.14042736887931823,
|
|
"num_tokens": 9687339.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 6.20817379951477,
|
|
"epoch": 0.45876015542211235,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.000498451210772069,
|
|
"loss": 6.033,
|
|
"mean_token_accuracy": 0.15873085483908653,
|
|
"num_tokens": 9696889.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 6.204896116256714,
|
|
"epoch": 0.4592016955139527,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004984475199570058,
|
|
"loss": 6.0156,
|
|
"mean_token_accuracy": 0.15423081889748574,
|
|
"num_tokens": 9705498.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 6.214762735366821,
|
|
"epoch": 0.459643235605793,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 0.0004984438247647329,
|
|
"loss": 6.0735,
|
|
"mean_token_accuracy": 0.1508117400109768,
|
|
"num_tokens": 9713936.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 6.2286858558654785,
|
|
"epoch": 0.46008477569763334,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004984401251953223,
|
|
"loss": 6.1494,
|
|
"mean_token_accuracy": 0.14881213307380675,
|
|
"num_tokens": 9723924.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 6.294112968444824,
|
|
"epoch": 0.4605263157894737,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004984364212488469,
|
|
"loss": 6.1745,
|
|
"mean_token_accuracy": 0.14484737291932107,
|
|
"num_tokens": 9733427.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 6.196189069747925,
|
|
"epoch": 0.460967855881314,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004984327129253789,
|
|
"loss": 5.979,
|
|
"mean_token_accuracy": 0.15575796514749526,
|
|
"num_tokens": 9742054.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 6.181635046005249,
|
|
"epoch": 0.46140939597315433,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004984290002249914,
|
|
"loss": 6.1526,
|
|
"mean_token_accuracy": 0.14558340460062028,
|
|
"num_tokens": 9752447.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 6.295547008514404,
|
|
"epoch": 0.4618509360649947,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004984252831477567,
|
|
"loss": 5.9775,
|
|
"mean_token_accuracy": 0.15951746702194214,
|
|
"num_tokens": 9760878.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 6.106395292282104,
|
|
"epoch": 0.46229247615683505,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004984215616937477,
|
|
"loss": 6.0652,
|
|
"mean_token_accuracy": 0.15369922667741776,
|
|
"num_tokens": 9770200.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 6.263768005371094,
|
|
"epoch": 0.4627340162486754,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004984178358630374,
|
|
"loss": 6.1482,
|
|
"mean_token_accuracy": 0.15308323130011559,
|
|
"num_tokens": 9780303.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 6.2224345207214355,
|
|
"epoch": 0.4631755563405157,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004984141056556989,
|
|
"loss": 6.0545,
|
|
"mean_token_accuracy": 0.1574157178401947,
|
|
"num_tokens": 9790248.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 6.233914422988891,
|
|
"epoch": 0.46361709643235605,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004984103710718051,
|
|
"loss": 6.1571,
|
|
"mean_token_accuracy": 0.14006953686475754,
|
|
"num_tokens": 9799345.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 6.21716718673706,
|
|
"epoch": 0.4640586365241964,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000498406632111429,
|
|
"loss": 6.0248,
|
|
"mean_token_accuracy": 0.15384083166718482,
|
|
"num_tokens": 9808561.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 6.176944255828857,
|
|
"epoch": 0.4645001766160367,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004984028887746443,
|
|
"loss": 6.075,
|
|
"mean_token_accuracy": 0.15321042835712434,
|
|
"num_tokens": 9818324.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 6.11839337348938,
|
|
"epoch": 0.4649417167078771,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004983991410615239,
|
|
"loss": 6.0642,
|
|
"mean_token_accuracy": 0.15897032916545867,
|
|
"num_tokens": 9827935.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 6.192565965652466,
|
|
"epoch": 0.4653832567997174,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004983953889721414,
|
|
"loss": 6.0708,
|
|
"mean_token_accuracy": 0.14985240399837493,
|
|
"num_tokens": 9837118.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 6.283035516738892,
|
|
"epoch": 0.46582479689155776,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004983916325065703,
|
|
"loss": 6.1452,
|
|
"mean_token_accuracy": 0.14742159396409987,
|
|
"num_tokens": 9846197.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 6.218610715866089,
|
|
"epoch": 0.4662663369833981,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004983878716648842,
|
|
"loss": 6.207,
|
|
"mean_token_accuracy": 0.138255525380373,
|
|
"num_tokens": 9856120.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 6.236172008514404,
|
|
"epoch": 0.4667078770752384,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004983841064471567,
|
|
"loss": 6.1443,
|
|
"mean_token_accuracy": 0.15334289371967316,
|
|
"num_tokens": 9865599.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 6.220607471466065,
|
|
"epoch": 0.46714941716707875,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004983803368534617,
|
|
"loss": 6.0731,
|
|
"mean_token_accuracy": 0.14917169362306595,
|
|
"num_tokens": 9876471.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 6.272904968261718,
|
|
"epoch": 0.4675909572589191,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004983765628838728,
|
|
"loss": 6.1206,
|
|
"mean_token_accuracy": 0.14877381771802903,
|
|
"num_tokens": 9887680.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 6.372138261795044,
|
|
"epoch": 0.46803249735075947,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004983727845384641,
|
|
"loss": 6.1891,
|
|
"mean_token_accuracy": 0.14280365407466888,
|
|
"num_tokens": 9897366.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 6.224646997451782,
|
|
"epoch": 0.4684740374425998,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004983690018173096,
|
|
"loss": 6.1643,
|
|
"mean_token_accuracy": 0.14118458405137063,
|
|
"num_tokens": 9907437.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 6.168851518630982,
|
|
"epoch": 0.46891557753444013,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004983652147204834,
|
|
"loss": 5.9414,
|
|
"mean_token_accuracy": 0.15954260528087616,
|
|
"num_tokens": 9915766.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 6.174386072158813,
|
|
"epoch": 0.46935711762628046,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004983614232480598,
|
|
"loss": 6.1676,
|
|
"mean_token_accuracy": 0.14472133666276932,
|
|
"num_tokens": 9925389.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 6.242318105697632,
|
|
"epoch": 0.4697986577181208,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004983576274001127,
|
|
"loss": 6.2095,
|
|
"mean_token_accuracy": 0.14636736437678338,
|
|
"num_tokens": 9935798.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 6.27483172416687,
|
|
"epoch": 0.4702401978099611,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000498353827176717,
|
|
"loss": 6.0797,
|
|
"mean_token_accuracy": 0.15635642111301423,
|
|
"num_tokens": 9945579.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 6.2160468101501465,
|
|
"epoch": 0.4706817379018015,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004983500225779466,
|
|
"loss": 6.0771,
|
|
"mean_token_accuracy": 0.15257431268692018,
|
|
"num_tokens": 9955248.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 6.233940362930298,
|
|
"epoch": 0.47112327799364184,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004983462136038764,
|
|
"loss": 6.0821,
|
|
"mean_token_accuracy": 0.1569819375872612,
|
|
"num_tokens": 9965078.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 6.246978759765625,
|
|
"epoch": 0.4715648180854822,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004983424002545809,
|
|
"loss": 6.0492,
|
|
"mean_token_accuracy": 0.15982300341129302,
|
|
"num_tokens": 9973932.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 6.262096881866455,
|
|
"epoch": 0.4720063581773225,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004983385825301348,
|
|
"loss": 6.1096,
|
|
"mean_token_accuracy": 0.14472333192825318,
|
|
"num_tokens": 9983315.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 6.222039794921875,
|
|
"epoch": 0.47244789826916284,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004983347604306129,
|
|
"loss": 6.0561,
|
|
"mean_token_accuracy": 0.15030533075332642,
|
|
"num_tokens": 9992987.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 6.092016220092773,
|
|
"epoch": 0.47288943836100317,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004983309339560899,
|
|
"loss": 6.126,
|
|
"mean_token_accuracy": 0.14506357684731483,
|
|
"num_tokens": 10002268.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 6.288043355941772,
|
|
"epoch": 0.4733309784528435,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004983271031066412,
|
|
"loss": 6.1245,
|
|
"mean_token_accuracy": 0.14628779739141465,
|
|
"num_tokens": 10011772.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 6.274447917938232,
|
|
"epoch": 0.4737725185446839,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004983232678823414,
|
|
"loss": 6.1144,
|
|
"mean_token_accuracy": 0.1535882532596588,
|
|
"num_tokens": 10021069.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 6.13931097984314,
|
|
"epoch": 0.4742140586365242,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004983194282832657,
|
|
"loss": 6.0469,
|
|
"mean_token_accuracy": 0.15460294410586356,
|
|
"num_tokens": 10029706.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 6.123434686660767,
|
|
"epoch": 0.47465559872836455,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004983155843094895,
|
|
"loss": 6.0094,
|
|
"mean_token_accuracy": 0.1568350613117218,
|
|
"num_tokens": 10039633.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 6.263561010360718,
|
|
"epoch": 0.4750971388202049,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004983117359610881,
|
|
"loss": 6.0676,
|
|
"mean_token_accuracy": 0.15199101269245147,
|
|
"num_tokens": 10048675.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 6.28706202507019,
|
|
"epoch": 0.4755386789120452,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004983078832381367,
|
|
"loss": 6.0521,
|
|
"mean_token_accuracy": 0.15566769391298294,
|
|
"num_tokens": 10057447.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 6.180134248733521,
|
|
"epoch": 0.47598021900388554,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004983040261407109,
|
|
"loss": 6.1343,
|
|
"mean_token_accuracy": 0.1476961798965931,
|
|
"num_tokens": 10067020.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 6.287719488143921,
|
|
"epoch": 0.47642175909572587,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004983001646688863,
|
|
"loss": 6.1531,
|
|
"mean_token_accuracy": 0.14605475217103958,
|
|
"num_tokens": 10076466.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 6.220081901550293,
|
|
"epoch": 0.47686329918756626,
|
|
"grad_norm": 4.5625,
|
|
"learning_rate": 0.0004982962988227383,
|
|
"loss": 6.0358,
|
|
"mean_token_accuracy": 0.151186566054821,
|
|
"num_tokens": 10085384.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 6.175395393371582,
|
|
"epoch": 0.4773048392794066,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000498292428602343,
|
|
"loss": 6.1598,
|
|
"mean_token_accuracy": 0.1484358288347721,
|
|
"num_tokens": 10094015.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 6.251093626022339,
|
|
"epoch": 0.4777463793712469,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004982885540077758,
|
|
"loss": 6.0493,
|
|
"mean_token_accuracy": 0.15062117725610732,
|
|
"num_tokens": 10103107.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 6.205082178115845,
|
|
"epoch": 0.47818791946308725,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004982846750391129,
|
|
"loss": 5.9784,
|
|
"mean_token_accuracy": 0.15971413403749465,
|
|
"num_tokens": 10112408.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 6.162239980697632,
|
|
"epoch": 0.4786294595549276,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004982807916964303,
|
|
"loss": 6.0535,
|
|
"mean_token_accuracy": 0.1549421191215515,
|
|
"num_tokens": 10121605.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 6.155058526992798,
|
|
"epoch": 0.4790709996467679,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000498276903979804,
|
|
"loss": 6.034,
|
|
"mean_token_accuracy": 0.15531475991010665,
|
|
"num_tokens": 10130484.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 6.175060844421386,
|
|
"epoch": 0.47951253973860825,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00049827301188931,
|
|
"loss": 6.0245,
|
|
"mean_token_accuracy": 0.15743746012449264,
|
|
"num_tokens": 10140002.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 6.31604700088501,
|
|
"epoch": 0.47995407983044863,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004982691154250247,
|
|
"loss": 6.1765,
|
|
"mean_token_accuracy": 0.14907011836767198,
|
|
"num_tokens": 10150287.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 6.230531549453735,
|
|
"epoch": 0.48039561992228896,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004982652145870245,
|
|
"loss": 6.0174,
|
|
"mean_token_accuracy": 0.15797854363918304,
|
|
"num_tokens": 10160615.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 6.179948806762695,
|
|
"epoch": 0.4808371600141293,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004982613093753856,
|
|
"loss": 6.0705,
|
|
"mean_token_accuracy": 0.14943629652261733,
|
|
"num_tokens": 10170271.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 6.231583595275879,
|
|
"epoch": 0.4812787001059696,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004982573997901847,
|
|
"loss": 6.056,
|
|
"mean_token_accuracy": 0.15738898664712905,
|
|
"num_tokens": 10179663.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 6.289588546752929,
|
|
"epoch": 0.48172024019780996,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004982534858314982,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.14590489864349365,
|
|
"num_tokens": 10188608.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 6.254216098785401,
|
|
"epoch": 0.4821617802896503,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004982495674994031,
|
|
"loss": 6.0859,
|
|
"mean_token_accuracy": 0.1491940975189209,
|
|
"num_tokens": 10198462.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 6.120104646682739,
|
|
"epoch": 0.4826033203814906,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004982456447939758,
|
|
"loss": 6.0338,
|
|
"mean_token_accuracy": 0.15759821385145187,
|
|
"num_tokens": 10208362.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 6.200664806365967,
|
|
"epoch": 0.483044860473331,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004982417177152933,
|
|
"loss": 6.0675,
|
|
"mean_token_accuracy": 0.1542600154876709,
|
|
"num_tokens": 10217915.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 6.256381845474243,
|
|
"epoch": 0.48348640056517134,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004982377862634325,
|
|
"loss": 6.1251,
|
|
"mean_token_accuracy": 0.14791901409626007,
|
|
"num_tokens": 10226913.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 6.213307809829712,
|
|
"epoch": 0.48392794065701167,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004982338504384705,
|
|
"loss": 6.0808,
|
|
"mean_token_accuracy": 0.14749183356761933,
|
|
"num_tokens": 10236516.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 6.281264781951904,
|
|
"epoch": 0.484369480748852,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004982299102404843,
|
|
"loss": 6.0938,
|
|
"mean_token_accuracy": 0.15255813151597977,
|
|
"num_tokens": 10245492.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 6.161162233352661,
|
|
"epoch": 0.48481102084069233,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000498225965669551,
|
|
"loss": 5.9864,
|
|
"mean_token_accuracy": 0.1673749029636383,
|
|
"num_tokens": 10254094.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 6.163426876068115,
|
|
"epoch": 0.48525256093253266,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004982220167257482,
|
|
"loss": 6.025,
|
|
"mean_token_accuracy": 0.15340587124228477,
|
|
"num_tokens": 10263645.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 6.130688619613648,
|
|
"epoch": 0.485694101024373,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004982180634091529,
|
|
"loss": 5.9811,
|
|
"mean_token_accuracy": 0.1652866408228874,
|
|
"num_tokens": 10273416.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 6.197805738449096,
|
|
"epoch": 0.4861356411162134,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004982141057198427,
|
|
"loss": 6.088,
|
|
"mean_token_accuracy": 0.15661069452762605,
|
|
"num_tokens": 10283194.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 6.230135869979859,
|
|
"epoch": 0.4865771812080537,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004982101436578952,
|
|
"loss": 6.0745,
|
|
"mean_token_accuracy": 0.15319612324237825,
|
|
"num_tokens": 10292188.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 6.199646711349487,
|
|
"epoch": 0.48701872129989404,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004982061772233878,
|
|
"loss": 6.0012,
|
|
"mean_token_accuracy": 0.16849624663591384,
|
|
"num_tokens": 10301539.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 6.155360364913941,
|
|
"epoch": 0.4874602613917344,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004982022064163984,
|
|
"loss": 6.0182,
|
|
"mean_token_accuracy": 0.1558818131685257,
|
|
"num_tokens": 10310379.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 6.2828093528747555,
|
|
"epoch": 0.4879018014835747,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004981982312370047,
|
|
"loss": 6.1951,
|
|
"mean_token_accuracy": 0.14344881922006608,
|
|
"num_tokens": 10320622.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 6.2398645877838135,
|
|
"epoch": 0.48834334157541504,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004981942516852847,
|
|
"loss": 6.0523,
|
|
"mean_token_accuracy": 0.1519939720630646,
|
|
"num_tokens": 10330525.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 6.178468704223633,
|
|
"epoch": 0.48878488166725537,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004981902677613161,
|
|
"loss": 6.0634,
|
|
"mean_token_accuracy": 0.1571633905172348,
|
|
"num_tokens": 10340288.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 6.321018171310425,
|
|
"epoch": 0.48922642175909575,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004981862794651771,
|
|
"loss": 6.1756,
|
|
"mean_token_accuracy": 0.14611549079418182,
|
|
"num_tokens": 10349836.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 6.298594951629639,
|
|
"epoch": 0.4896679618509361,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004981822867969459,
|
|
"loss": 6.0876,
|
|
"mean_token_accuracy": 0.15010807365179063,
|
|
"num_tokens": 10359481.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 6.17570424079895,
|
|
"epoch": 0.4901095019427764,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004981782897567006,
|
|
"loss": 6.0731,
|
|
"mean_token_accuracy": 0.15269545316696168,
|
|
"num_tokens": 10369837.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 6.232746553421021,
|
|
"epoch": 0.49055104203461675,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004981742883445195,
|
|
"loss": 6.0222,
|
|
"mean_token_accuracy": 0.15387771874666215,
|
|
"num_tokens": 10379276.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 6.2836329460144045,
|
|
"epoch": 0.4909925821264571,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000498170282560481,
|
|
"loss": 6.1657,
|
|
"mean_token_accuracy": 0.14680661410093307,
|
|
"num_tokens": 10388878.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 6.268063640594482,
|
|
"epoch": 0.4914341222182974,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004981662724046637,
|
|
"loss": 6.1498,
|
|
"mean_token_accuracy": 0.14900615811347961,
|
|
"num_tokens": 10399148.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 6.17643632888794,
|
|
"epoch": 0.49187566231013774,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000498162257877146,
|
|
"loss": 6.0708,
|
|
"mean_token_accuracy": 0.15419022738933563,
|
|
"num_tokens": 10409002.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 6.202827405929566,
|
|
"epoch": 0.4923172024019781,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004981582389780065,
|
|
"loss": 6.1264,
|
|
"mean_token_accuracy": 0.14688992947340013,
|
|
"num_tokens": 10418083.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 6.325224685668945,
|
|
"epoch": 0.49275874249381846,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004981542157073241,
|
|
"loss": 6.1325,
|
|
"mean_token_accuracy": 0.1459851548075676,
|
|
"num_tokens": 10428134.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 6.244769668579101,
|
|
"epoch": 0.4932002825856588,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004981501880651775,
|
|
"loss": 6.1025,
|
|
"mean_token_accuracy": 0.14910912066698073,
|
|
"num_tokens": 10437436.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 6.241864013671875,
|
|
"epoch": 0.4936418226774991,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004981461560516457,
|
|
"loss": 6.0608,
|
|
"mean_token_accuracy": 0.1482058048248291,
|
|
"num_tokens": 10446176.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 6.2926859855651855,
|
|
"epoch": 0.49408336276933945,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004981421196668075,
|
|
"loss": 6.2225,
|
|
"mean_token_accuracy": 0.1453863188624382,
|
|
"num_tokens": 10455953.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 6.237603664398193,
|
|
"epoch": 0.4945249028611798,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004981380789107422,
|
|
"loss": 6.0531,
|
|
"mean_token_accuracy": 0.152923521399498,
|
|
"num_tokens": 10465129.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 6.152634859085083,
|
|
"epoch": 0.4949664429530201,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004981340337835287,
|
|
"loss": 6.0626,
|
|
"mean_token_accuracy": 0.15646580308675767,
|
|
"num_tokens": 10474376.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 6.27559905052185,
|
|
"epoch": 0.4954079830448605,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004981299842852464,
|
|
"loss": 6.127,
|
|
"mean_token_accuracy": 0.15202730447053908,
|
|
"num_tokens": 10484849.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 6.164656114578247,
|
|
"epoch": 0.49584952313670083,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004981259304159747,
|
|
"loss": 5.9974,
|
|
"mean_token_accuracy": 0.16477532535791398,
|
|
"num_tokens": 10493950.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 6.120241928100586,
|
|
"epoch": 0.49629106322854116,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004981218721757929,
|
|
"loss": 5.9823,
|
|
"mean_token_accuracy": 0.16299533545970918,
|
|
"num_tokens": 10502890.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 6.169768047332764,
|
|
"epoch": 0.4967326033203815,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004981178095647805,
|
|
"loss": 5.9726,
|
|
"mean_token_accuracy": 0.15252360329031944,
|
|
"num_tokens": 10511702.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 6.239253520965576,
|
|
"epoch": 0.4971741434122218,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004981137425830171,
|
|
"loss": 6.0442,
|
|
"mean_token_accuracy": 0.1530621826648712,
|
|
"num_tokens": 10520212.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 6.224827003479004,
|
|
"epoch": 0.49761568350406216,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004981096712305825,
|
|
"loss": 6.0788,
|
|
"mean_token_accuracy": 0.15880460888147355,
|
|
"num_tokens": 10529652.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 6.2657328128814695,
|
|
"epoch": 0.4980572235959025,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004981055955075561,
|
|
"loss": 6.1398,
|
|
"mean_token_accuracy": 0.14761028215289115,
|
|
"num_tokens": 10537980.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 6.235979509353638,
|
|
"epoch": 0.4984987636877429,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004981015154140181,
|
|
"loss": 6.01,
|
|
"mean_token_accuracy": 0.1574429005384445,
|
|
"num_tokens": 10546854.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 6.17179799079895,
|
|
"epoch": 0.4989403037795832,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004980974309500483,
|
|
"loss": 6.0232,
|
|
"mean_token_accuracy": 0.15442994236946106,
|
|
"num_tokens": 10555691.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 6.178042984008789,
|
|
"epoch": 0.49938184387142354,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004980933421157267,
|
|
"loss": 6.1029,
|
|
"mean_token_accuracy": 0.1499166801571846,
|
|
"num_tokens": 10564750.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 6.26821002960205,
|
|
"epoch": 0.49982338396326387,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004980892489111334,
|
|
"loss": 6.1341,
|
|
"mean_token_accuracy": 0.15029960572719575,
|
|
"num_tokens": 10573515.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 6.175892972946167,
|
|
"epoch": 0.5002649240551043,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004980851513363486,
|
|
"loss": 6.0086,
|
|
"mean_token_accuracy": 0.15723771452903748,
|
|
"num_tokens": 10582730.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 6.070863533020019,
|
|
"epoch": 0.5007064641469445,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004980810493914526,
|
|
"loss": 5.9176,
|
|
"mean_token_accuracy": 0.17001818120479584,
|
|
"num_tokens": 10591267.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 6.2038191795349125,
|
|
"epoch": 0.5011480042387849,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004980769430765256,
|
|
"loss": 6.0305,
|
|
"mean_token_accuracy": 0.1541754946112633,
|
|
"num_tokens": 10599776.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 6.175134658813477,
|
|
"epoch": 0.5015895443306252,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004980728323916484,
|
|
"loss": 6.0343,
|
|
"mean_token_accuracy": 0.14554973393678666,
|
|
"num_tokens": 10609670.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 6.148836851119995,
|
|
"epoch": 0.5020310844224656,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004980687173369009,
|
|
"loss": 5.9921,
|
|
"mean_token_accuracy": 0.1531945288181305,
|
|
"num_tokens": 10619032.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 6.200354480743409,
|
|
"epoch": 0.5024726245143059,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004980645979123644,
|
|
"loss": 6.0675,
|
|
"mean_token_accuracy": 0.15187735557556153,
|
|
"num_tokens": 10628851.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 6.234457206726074,
|
|
"epoch": 0.5029141646061462,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004980604741181192,
|
|
"loss": 6.0212,
|
|
"mean_token_accuracy": 0.15740241408348082,
|
|
"num_tokens": 10638335.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 6.225916147232056,
|
|
"epoch": 0.5033557046979866,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004980563459542461,
|
|
"loss": 6.1203,
|
|
"mean_token_accuracy": 0.1536049425601959,
|
|
"num_tokens": 10648450.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 6.271219968795776,
|
|
"epoch": 0.5037972447898269,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004980522134208261,
|
|
"loss": 6.1492,
|
|
"mean_token_accuracy": 0.146041289716959,
|
|
"num_tokens": 10658700.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 6.291195201873779,
|
|
"epoch": 0.5042387848816673,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004980480765179401,
|
|
"loss": 6.1487,
|
|
"mean_token_accuracy": 0.14889888167381288,
|
|
"num_tokens": 10667952.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 6.102896404266358,
|
|
"epoch": 0.5046803249735076,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004980439352456692,
|
|
"loss": 5.9948,
|
|
"mean_token_accuracy": 0.1518148198723793,
|
|
"num_tokens": 10677228.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 6.179556941986084,
|
|
"epoch": 0.505121865065348,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004980397896040944,
|
|
"loss": 6.0536,
|
|
"mean_token_accuracy": 0.1556122913956642,
|
|
"num_tokens": 10686183.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 6.3303307056427,
|
|
"epoch": 0.5055634051571882,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004980356395932969,
|
|
"loss": 6.0907,
|
|
"mean_token_accuracy": 0.1538555309176445,
|
|
"num_tokens": 10695293.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 6.229521656036377,
|
|
"epoch": 0.5060049452490286,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004980314852133581,
|
|
"loss": 6.0481,
|
|
"mean_token_accuracy": 0.15595095455646515,
|
|
"num_tokens": 10704853.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 6.178576850891114,
|
|
"epoch": 0.506446485340869,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004980273264643594,
|
|
"loss": 6.0573,
|
|
"mean_token_accuracy": 0.14866793304681777,
|
|
"num_tokens": 10714307.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 6.105400037765503,
|
|
"epoch": 0.5068880254327093,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004980231633463822,
|
|
"loss": 5.9431,
|
|
"mean_token_accuracy": 0.15429134145379067,
|
|
"num_tokens": 10723513.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 6.182111120223999,
|
|
"epoch": 0.5073295655245497,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004980189958595081,
|
|
"loss": 6.1135,
|
|
"mean_token_accuracy": 0.14779711961746217,
|
|
"num_tokens": 10732809.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 6.219801568984986,
|
|
"epoch": 0.5077711056163899,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004980148240038186,
|
|
"loss": 6.1188,
|
|
"mean_token_accuracy": 0.1531921371817589,
|
|
"num_tokens": 10742960.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 6.291525602340698,
|
|
"epoch": 0.5082126457082303,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004980106477793957,
|
|
"loss": 6.163,
|
|
"mean_token_accuracy": 0.1517067790031433,
|
|
"num_tokens": 10752835.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 6.241646194458008,
|
|
"epoch": 0.5086541858000706,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004980064671863209,
|
|
"loss": 6.0603,
|
|
"mean_token_accuracy": 0.15527053624391557,
|
|
"num_tokens": 10762139.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 6.215019416809082,
|
|
"epoch": 0.509095725891911,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004980022822246763,
|
|
"loss": 6.1307,
|
|
"mean_token_accuracy": 0.1484266459941864,
|
|
"num_tokens": 10771961.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 6.309531927108765,
|
|
"epoch": 0.5095372659837514,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004979980928945439,
|
|
"loss": 6.1903,
|
|
"mean_token_accuracy": 0.1406489558517933,
|
|
"num_tokens": 10780163.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 6.264658117294312,
|
|
"epoch": 0.5099788060755917,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004979938991960056,
|
|
"loss": 6.1436,
|
|
"mean_token_accuracy": 0.14712898582220077,
|
|
"num_tokens": 10788339.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 6.287960481643677,
|
|
"epoch": 0.510420346167432,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004979897011291436,
|
|
"loss": 6.1436,
|
|
"mean_token_accuracy": 0.1394449144601822,
|
|
"num_tokens": 10797315.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 6.310721778869629,
|
|
"epoch": 0.5108618862592723,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004979854986940402,
|
|
"loss": 6.0521,
|
|
"mean_token_accuracy": 0.1499259203672409,
|
|
"num_tokens": 10806864.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 6.211594343185425,
|
|
"epoch": 0.5113034263511127,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004979812918907777,
|
|
"loss": 6.0803,
|
|
"mean_token_accuracy": 0.149106565117836,
|
|
"num_tokens": 10816417.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 6.235892724990845,
|
|
"epoch": 0.511744966442953,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004979770807194385,
|
|
"loss": 6.1297,
|
|
"mean_token_accuracy": 0.1502230428159237,
|
|
"num_tokens": 10825692.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 6.17337121963501,
|
|
"epoch": 0.5121865065347934,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004979728651801051,
|
|
"loss": 6.1258,
|
|
"mean_token_accuracy": 0.15180813670158386,
|
|
"num_tokens": 10834652.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 6.238249397277832,
|
|
"epoch": 0.5126280466266337,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004979686452728602,
|
|
"loss": 6.1223,
|
|
"mean_token_accuracy": 0.1498955324292183,
|
|
"num_tokens": 10844491.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 6.253004026412964,
|
|
"epoch": 0.513069586718474,
|
|
"grad_norm": 3.390625,
|
|
"learning_rate": 0.0004979644209977863,
|
|
"loss": 6.0567,
|
|
"mean_token_accuracy": 0.15736870020627974,
|
|
"num_tokens": 10853948.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 6.219189548492432,
|
|
"epoch": 0.5135111268103144,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004979601923549661,
|
|
"loss": 6.0507,
|
|
"mean_token_accuracy": 0.15809340327978133,
|
|
"num_tokens": 10861745.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 6.255096530914306,
|
|
"epoch": 0.5139526669021547,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004979559593444826,
|
|
"loss": 6.1591,
|
|
"mean_token_accuracy": 0.15061620324850084,
|
|
"num_tokens": 10871239.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 6.206992340087891,
|
|
"epoch": 0.5143942069939951,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004979517219664187,
|
|
"loss": 6.0095,
|
|
"mean_token_accuracy": 0.15605255961418152,
|
|
"num_tokens": 10880883.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 6.200674915313721,
|
|
"epoch": 0.5148357470858353,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004979474802208572,
|
|
"loss": 6.0706,
|
|
"mean_token_accuracy": 0.1538535013794899,
|
|
"num_tokens": 10890002.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 6.1436597347259525,
|
|
"epoch": 0.5152772871776757,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004979432341078816,
|
|
"loss": 5.9781,
|
|
"mean_token_accuracy": 0.15378640592098236,
|
|
"num_tokens": 10898299.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 6.246534204483032,
|
|
"epoch": 0.5157188272695161,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004979389836275746,
|
|
"loss": 6.1891,
|
|
"mean_token_accuracy": 0.14030280113220214,
|
|
"num_tokens": 10907918.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 6.283355760574341,
|
|
"epoch": 0.5161603673613564,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004979347287800198,
|
|
"loss": 6.0666,
|
|
"mean_token_accuracy": 0.15159436464309692,
|
|
"num_tokens": 10917318.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 6.239576005935669,
|
|
"epoch": 0.5166019074531968,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004979304695653005,
|
|
"loss": 6.0368,
|
|
"mean_token_accuracy": 0.14758304730057717,
|
|
"num_tokens": 10926338.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 6.180262565612793,
|
|
"epoch": 0.5170434475450371,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004979262059835001,
|
|
"loss": 6.0567,
|
|
"mean_token_accuracy": 0.1544695608317852,
|
|
"num_tokens": 10935244.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 6.227532386779785,
|
|
"epoch": 0.5174849876368774,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004979219380347021,
|
|
"loss": 6.0895,
|
|
"mean_token_accuracy": 0.15278323590755463,
|
|
"num_tokens": 10943764.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 6.217388772964478,
|
|
"epoch": 0.5179265277287177,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004979176657189901,
|
|
"loss": 6.0614,
|
|
"mean_token_accuracy": 0.15153294652700425,
|
|
"num_tokens": 10952580.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 6.184233570098877,
|
|
"epoch": 0.5183680678205581,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004979133890364477,
|
|
"loss": 6.0912,
|
|
"mean_token_accuracy": 0.15725700706243514,
|
|
"num_tokens": 10961745.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 6.132976865768432,
|
|
"epoch": 0.5188096079123985,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000497909107987159,
|
|
"loss": 6.0044,
|
|
"mean_token_accuracy": 0.14987772107124328,
|
|
"num_tokens": 10971018.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 6.245497131347657,
|
|
"epoch": 0.5192511480042388,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004979048225712074,
|
|
"loss": 6.0635,
|
|
"mean_token_accuracy": 0.1502876304090023,
|
|
"num_tokens": 10980070.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 6.2374574661254885,
|
|
"epoch": 0.5196926880960792,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004979005327886772,
|
|
"loss": 6.0151,
|
|
"mean_token_accuracy": 0.15238675773143767,
|
|
"num_tokens": 10989090.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 6.192137956619263,
|
|
"epoch": 0.5201342281879194,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004978962386396525,
|
|
"loss": 6.0671,
|
|
"mean_token_accuracy": 0.15695874094963075,
|
|
"num_tokens": 10998652.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 6.124173307418824,
|
|
"epoch": 0.5205757682797598,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004978919401242171,
|
|
"loss": 5.9867,
|
|
"mean_token_accuracy": 0.15875377953052522,
|
|
"num_tokens": 11006323.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 6.016487741470337,
|
|
"epoch": 0.5210173083716001,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004978876372424553,
|
|
"loss": 5.9289,
|
|
"mean_token_accuracy": 0.16370188891887666,
|
|
"num_tokens": 11015054.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 6.187124967575073,
|
|
"epoch": 0.5214588484634405,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004978833299944515,
|
|
"loss": 6.0942,
|
|
"mean_token_accuracy": 0.14643116071820259,
|
|
"num_tokens": 11025787.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 6.38083028793335,
|
|
"epoch": 0.5219003885552809,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004978790183802901,
|
|
"loss": 6.2004,
|
|
"mean_token_accuracy": 0.1463787078857422,
|
|
"num_tokens": 11036091.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 6.241087150573731,
|
|
"epoch": 0.5223419286471211,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004978747024000554,
|
|
"loss": 6.1841,
|
|
"mean_token_accuracy": 0.13922761231660843,
|
|
"num_tokens": 11046442.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 6.289608478546143,
|
|
"epoch": 0.5227834687389615,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004978703820538321,
|
|
"loss": 6.1859,
|
|
"mean_token_accuracy": 0.14226099327206612,
|
|
"num_tokens": 11056907.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 6.275417995452881,
|
|
"epoch": 0.5232250088308018,
|
|
"grad_norm": 3.640625,
|
|
"learning_rate": 0.0004978660573417048,
|
|
"loss": 6.0243,
|
|
"mean_token_accuracy": 0.15696371644735335,
|
|
"num_tokens": 11065298.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 6.223781394958496,
|
|
"epoch": 0.5236665489226422,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.000497861728263758,
|
|
"loss": 6.0378,
|
|
"mean_token_accuracy": 0.15642370134592057,
|
|
"num_tokens": 11074509.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 6.137613821029663,
|
|
"epoch": 0.5241080890144825,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004978573948200769,
|
|
"loss": 6.0634,
|
|
"mean_token_accuracy": 0.15504582077264786,
|
|
"num_tokens": 11082433.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 6.159803628921509,
|
|
"epoch": 0.5245496291063229,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004978530570107461,
|
|
"loss": 6.0445,
|
|
"mean_token_accuracy": 0.15370505750179292,
|
|
"num_tokens": 11090838.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 6.244238471984863,
|
|
"epoch": 0.5249911691981632,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004978487148358506,
|
|
"loss": 6.0384,
|
|
"mean_token_accuracy": 0.1582946076989174,
|
|
"num_tokens": 11100048.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 6.176552677154541,
|
|
"epoch": 0.5254327092900035,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004978443682954756,
|
|
"loss": 6.0653,
|
|
"mean_token_accuracy": 0.1521560877561569,
|
|
"num_tokens": 11109871.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 6.178084754943848,
|
|
"epoch": 0.5258742493818439,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004978400173897061,
|
|
"loss": 6.0575,
|
|
"mean_token_accuracy": 0.14851836115121841,
|
|
"num_tokens": 11119450.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 6.225746393203735,
|
|
"epoch": 0.5263157894736842,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004978356621186275,
|
|
"loss": 5.9822,
|
|
"mean_token_accuracy": 0.16357790529727936,
|
|
"num_tokens": 11128321.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 6.185709714889526,
|
|
"epoch": 0.5267573295655246,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004978313024823249,
|
|
"loss": 6.0541,
|
|
"mean_token_accuracy": 0.15418425425887108,
|
|
"num_tokens": 11138657.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 6.152607488632202,
|
|
"epoch": 0.5271988696573648,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004978269384808839,
|
|
"loss": 6.049,
|
|
"mean_token_accuracy": 0.15706575363874437,
|
|
"num_tokens": 11147704.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 6.214599370956421,
|
|
"epoch": 0.5276404097492052,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004978225701143898,
|
|
"loss": 6.1374,
|
|
"mean_token_accuracy": 0.14667211771011351,
|
|
"num_tokens": 11156979.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 6.2628809928894045,
|
|
"epoch": 0.5280819498410456,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004978181973829284,
|
|
"loss": 6.0121,
|
|
"mean_token_accuracy": 0.15455354899168014,
|
|
"num_tokens": 11165539.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 6.253372669219971,
|
|
"epoch": 0.5285234899328859,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004978138202865851,
|
|
"loss": 6.1024,
|
|
"mean_token_accuracy": 0.14563342407345772,
|
|
"num_tokens": 11175911.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 6.145098304748535,
|
|
"epoch": 0.5289650300247263,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004978094388254459,
|
|
"loss": 6.1126,
|
|
"mean_token_accuracy": 0.15134625881910324,
|
|
"num_tokens": 11185365.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 6.199877214431763,
|
|
"epoch": 0.5294065701165666,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004978050529995965,
|
|
"loss": 6.0203,
|
|
"mean_token_accuracy": 0.15819834619760514,
|
|
"num_tokens": 11195318.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 6.259531831741333,
|
|
"epoch": 0.5298481102084069,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004978006628091228,
|
|
"loss": 6.124,
|
|
"mean_token_accuracy": 0.15193520560860635,
|
|
"num_tokens": 11205246.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5298481102084069,
|
|
"eval_entropy": 6.072632251968471,
|
|
"eval_loss": 6.105443477630615,
|
|
"eval_mean_token_accuracy": 0.15762448798056106,
|
|
"eval_num_tokens": 11205246.0,
|
|
"eval_runtime": 26.2122,
|
|
"eval_samples_per_second": 1347.271,
|
|
"eval_steps_per_second": 168.433,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 6.221136379241943,
|
|
"epoch": 0.5302896503002472,
|
|
"grad_norm": 3.34375,
|
|
"learning_rate": 0.0004977962682541108,
|
|
"loss": 6.0844,
|
|
"mean_token_accuracy": 0.14883435368537903,
|
|
"num_tokens": 11215183.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 6.219206190109253,
|
|
"epoch": 0.5307311903920876,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004977918693346467,
|
|
"loss": 6.0399,
|
|
"mean_token_accuracy": 0.15056363940238954,
|
|
"num_tokens": 11224127.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 6.2305787086486815,
|
|
"epoch": 0.531172730483928,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004977874660508165,
|
|
"loss": 6.0903,
|
|
"mean_token_accuracy": 0.15893068611621858,
|
|
"num_tokens": 11233014.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 6.2588090896606445,
|
|
"epoch": 0.5316142705757683,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004977830584027065,
|
|
"loss": 6.083,
|
|
"mean_token_accuracy": 0.15423338562250138,
|
|
"num_tokens": 11242251.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 6.2501606941223145,
|
|
"epoch": 0.5320558106676087,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004977786463904033,
|
|
"loss": 6.1309,
|
|
"mean_token_accuracy": 0.15289058089256286,
|
|
"num_tokens": 11251947.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 6.194758558273316,
|
|
"epoch": 0.5324973507594489,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004977742300139929,
|
|
"loss": 6.136,
|
|
"mean_token_accuracy": 0.15161363184452056,
|
|
"num_tokens": 11261125.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 6.236899757385254,
|
|
"epoch": 0.5329388908512893,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004977698092735621,
|
|
"loss": 6.0582,
|
|
"mean_token_accuracy": 0.15455631986260415,
|
|
"num_tokens": 11270334.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 6.179041385650635,
|
|
"epoch": 0.5333804309431296,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004977653841691975,
|
|
"loss": 6.0322,
|
|
"mean_token_accuracy": 0.15208539068698884,
|
|
"num_tokens": 11280497.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 6.218136930465699,
|
|
"epoch": 0.53382197103497,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004977609547009857,
|
|
"loss": 5.9771,
|
|
"mean_token_accuracy": 0.15844970792531968,
|
|
"num_tokens": 11288636.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 6.245617341995239,
|
|
"epoch": 0.5342635111268104,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004977565208690134,
|
|
"loss": 6.1018,
|
|
"mean_token_accuracy": 0.1520757868885994,
|
|
"num_tokens": 11297519.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 6.245824909210205,
|
|
"epoch": 0.5347050512186506,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004977520826733677,
|
|
"loss": 6.066,
|
|
"mean_token_accuracy": 0.15709497183561325,
|
|
"num_tokens": 11306280.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 6.236036396026611,
|
|
"epoch": 0.535146591310491,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004977476401141353,
|
|
"loss": 6.0554,
|
|
"mean_token_accuracy": 0.1493854656815529,
|
|
"num_tokens": 11315366.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 6.173353767395019,
|
|
"epoch": 0.5355881314023313,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004977431931914032,
|
|
"loss": 6.0739,
|
|
"mean_token_accuracy": 0.14963485300540924,
|
|
"num_tokens": 11324664.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 6.2184101104736325,
|
|
"epoch": 0.5360296714941717,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004977387419052586,
|
|
"loss": 6.0594,
|
|
"mean_token_accuracy": 0.14554163068532944,
|
|
"num_tokens": 11334118.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 6.306727123260498,
|
|
"epoch": 0.536471211586012,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.000497734286255789,
|
|
"loss": 6.1534,
|
|
"mean_token_accuracy": 0.14518513083457946,
|
|
"num_tokens": 11342684.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 6.220088005065918,
|
|
"epoch": 0.5369127516778524,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004977298262430813,
|
|
"loss": 6.0866,
|
|
"mean_token_accuracy": 0.15716351717710494,
|
|
"num_tokens": 11351298.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 6.250485229492187,
|
|
"epoch": 0.5373542917696927,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004977253618672229,
|
|
"loss": 6.0406,
|
|
"mean_token_accuracy": 0.15668216794729234,
|
|
"num_tokens": 11360264.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 6.207029247283936,
|
|
"epoch": 0.537795831861533,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004977208931283013,
|
|
"loss": 6.0102,
|
|
"mean_token_accuracy": 0.15628669857978822,
|
|
"num_tokens": 11369815.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 6.236184930801391,
|
|
"epoch": 0.5382373719533734,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004977164200264042,
|
|
"loss": 6.0925,
|
|
"mean_token_accuracy": 0.14922692477703095,
|
|
"num_tokens": 11379131.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 6.219870615005493,
|
|
"epoch": 0.5386789120452137,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004977119425616191,
|
|
"loss": 5.985,
|
|
"mean_token_accuracy": 0.1577737271785736,
|
|
"num_tokens": 11387692.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 6.217037391662598,
|
|
"epoch": 0.5391204521370541,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004977074607340336,
|
|
"loss": 6.0477,
|
|
"mean_token_accuracy": 0.1549394980072975,
|
|
"num_tokens": 11396278.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 6.16995267868042,
|
|
"epoch": 0.5395619922288943,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004977029745437357,
|
|
"loss": 5.9917,
|
|
"mean_token_accuracy": 0.1600234627723694,
|
|
"num_tokens": 11404790.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 6.192595767974853,
|
|
"epoch": 0.5400035323207347,
|
|
"grad_norm": 3.265625,
|
|
"learning_rate": 0.000497698483990813,
|
|
"loss": 6.0543,
|
|
"mean_token_accuracy": 0.14963596761226655,
|
|
"num_tokens": 11414614.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 6.211039113998413,
|
|
"epoch": 0.5404450724125751,
|
|
"grad_norm": 6.09375,
|
|
"learning_rate": 0.0004976939890753539,
|
|
"loss": 6.1049,
|
|
"mean_token_accuracy": 0.14544194787740708,
|
|
"num_tokens": 11423696.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 6.149191761016846,
|
|
"epoch": 0.5408866125044154,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.000497689489797446,
|
|
"loss": 6.0452,
|
|
"mean_token_accuracy": 0.15861246436834336,
|
|
"num_tokens": 11432669.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 6.166212034225464,
|
|
"epoch": 0.5413281525962558,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004976849861571778,
|
|
"loss": 6.0826,
|
|
"mean_token_accuracy": 0.1487231358885765,
|
|
"num_tokens": 11442132.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 6.241407299041748,
|
|
"epoch": 0.541769692688096,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004976804781546373,
|
|
"loss": 6.0527,
|
|
"mean_token_accuracy": 0.14581861943006516,
|
|
"num_tokens": 11451821.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 6.252784061431885,
|
|
"epoch": 0.5422112327799364,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004976759657899129,
|
|
"loss": 6.0389,
|
|
"mean_token_accuracy": 0.15604016929864883,
|
|
"num_tokens": 11460242.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 6.11449785232544,
|
|
"epoch": 0.5426527728717767,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000497671449063093,
|
|
"loss": 6.0737,
|
|
"mean_token_accuracy": 0.15422818958759307,
|
|
"num_tokens": 11469588.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 6.202958011627198,
|
|
"epoch": 0.5430943129636171,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.000497666927974266,
|
|
"loss": 6.1415,
|
|
"mean_token_accuracy": 0.1440917208790779,
|
|
"num_tokens": 11480401.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 6.303856229782104,
|
|
"epoch": 0.5435358530554575,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004976624025235205,
|
|
"loss": 6.0483,
|
|
"mean_token_accuracy": 0.15544205233454705,
|
|
"num_tokens": 11489117.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 6.240538835525513,
|
|
"epoch": 0.5439773931472978,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004976578727109453,
|
|
"loss": 5.9981,
|
|
"mean_token_accuracy": 0.15545659959316255,
|
|
"num_tokens": 11497612.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 6.185356140136719,
|
|
"epoch": 0.5444189332391381,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004976533385366289,
|
|
"loss": 6.0946,
|
|
"mean_token_accuracy": 0.1490752339363098,
|
|
"num_tokens": 11507024.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 6.148120260238647,
|
|
"epoch": 0.5448604733309784,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004976488000006602,
|
|
"loss": 6.0407,
|
|
"mean_token_accuracy": 0.15611946433782578,
|
|
"num_tokens": 11516873.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 6.2696808815002445,
|
|
"epoch": 0.5453020134228188,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004976442571031282,
|
|
"loss": 6.1051,
|
|
"mean_token_accuracy": 0.158052060008049,
|
|
"num_tokens": 11526128.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 6.232856321334839,
|
|
"epoch": 0.5457435535146591,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004976397098441218,
|
|
"loss": 6.12,
|
|
"mean_token_accuracy": 0.15662789046764375,
|
|
"num_tokens": 11535030.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 6.125250816345215,
|
|
"epoch": 0.5461850936064995,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004976351582237301,
|
|
"loss": 5.991,
|
|
"mean_token_accuracy": 0.15584895610809327,
|
|
"num_tokens": 11543113.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 6.217065048217774,
|
|
"epoch": 0.5466266336983399,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004976306022420423,
|
|
"loss": 6.0469,
|
|
"mean_token_accuracy": 0.15273384153842925,
|
|
"num_tokens": 11552744.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 6.246813106536865,
|
|
"epoch": 0.5470681737901801,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004976260418991476,
|
|
"loss": 6.0742,
|
|
"mean_token_accuracy": 0.15100209563970565,
|
|
"num_tokens": 11561274.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 6.235352563858032,
|
|
"epoch": 0.5475097138820205,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004976214771951354,
|
|
"loss": 6.0979,
|
|
"mean_token_accuracy": 0.15295421630144118,
|
|
"num_tokens": 11570485.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 6.219387817382812,
|
|
"epoch": 0.5479512539738608,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004976169081300949,
|
|
"loss": 6.0886,
|
|
"mean_token_accuracy": 0.14947510063648223,
|
|
"num_tokens": 11579380.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 6.178956794738769,
|
|
"epoch": 0.5483927940657012,
|
|
"grad_norm": 3.8125,
|
|
"learning_rate": 0.0004976123347041159,
|
|
"loss": 6.0597,
|
|
"mean_token_accuracy": 0.15444108843803406,
|
|
"num_tokens": 11588686.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 6.140177059173584,
|
|
"epoch": 0.5488343341575415,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004976077569172879,
|
|
"loss": 5.9833,
|
|
"mean_token_accuracy": 0.15883075296878815,
|
|
"num_tokens": 11598547.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 6.1776646137237545,
|
|
"epoch": 0.5492758742493818,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004976031747697006,
|
|
"loss": 6.0861,
|
|
"mean_token_accuracy": 0.15330686420202255,
|
|
"num_tokens": 11608407.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 6.18137674331665,
|
|
"epoch": 0.5497174143412222,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004975985882614435,
|
|
"loss": 6.0452,
|
|
"mean_token_accuracy": 0.1502505511045456,
|
|
"num_tokens": 11618641.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 6.249125671386719,
|
|
"epoch": 0.5501589544330625,
|
|
"grad_norm": 3.625,
|
|
"learning_rate": 0.0004975939973926068,
|
|
"loss": 6.0977,
|
|
"mean_token_accuracy": 0.14472403898835182,
|
|
"num_tokens": 11627082.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 6.176290273666382,
|
|
"epoch": 0.5506004945249029,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004975894021632803,
|
|
"loss": 6.0098,
|
|
"mean_token_accuracy": 0.1578657031059265,
|
|
"num_tokens": 11636045.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 6.196209478378296,
|
|
"epoch": 0.5510420346167432,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.000497584802573554,
|
|
"loss": 6.0775,
|
|
"mean_token_accuracy": 0.15153235495090484,
|
|
"num_tokens": 11646516.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 6.184172677993774,
|
|
"epoch": 0.5514835747085836,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.000497580198623518,
|
|
"loss": 6.0178,
|
|
"mean_token_accuracy": 0.159309720993042,
|
|
"num_tokens": 11655512.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 6.219246768951416,
|
|
"epoch": 0.5519251148004238,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.0004975755903132623,
|
|
"loss": 6.1042,
|
|
"mean_token_accuracy": 0.1587233141064644,
|
|
"num_tokens": 11665641.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 6.249983072280884,
|
|
"epoch": 0.5523666548922642,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004975709776428776,
|
|
"loss": 6.0623,
|
|
"mean_token_accuracy": 0.14356809556484224,
|
|
"num_tokens": 11674585.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 6.228289794921875,
|
|
"epoch": 0.5528081949841046,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.000497566360612454,
|
|
"loss": 5.9479,
|
|
"mean_token_accuracy": 0.1648830331861973,
|
|
"num_tokens": 11683498.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 6.145007753372193,
|
|
"epoch": 0.5532497350759449,
|
|
"grad_norm": 4.0,
|
|
"learning_rate": 0.000497561739222082,
|
|
"loss": 6.0016,
|
|
"mean_token_accuracy": 0.16011423319578172,
|
|
"num_tokens": 11692663.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 6.150508165359497,
|
|
"epoch": 0.5536912751677853,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004975571134718521,
|
|
"loss": 6.1505,
|
|
"mean_token_accuracy": 0.14764927104115486,
|
|
"num_tokens": 11701906.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 6.235524654388428,
|
|
"epoch": 0.5541328152596255,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004975524833618548,
|
|
"loss": 6.0321,
|
|
"mean_token_accuracy": 0.1586230754852295,
|
|
"num_tokens": 11710932.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 6.186596059799195,
|
|
"epoch": 0.5545743553514659,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.000497547848892181,
|
|
"loss": 6.0478,
|
|
"mean_token_accuracy": 0.15520632714033128,
|
|
"num_tokens": 11719953.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 6.210802841186523,
|
|
"epoch": 0.5550158954433062,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004975432100629215,
|
|
"loss": 5.9519,
|
|
"mean_token_accuracy": 0.15992908477783202,
|
|
"num_tokens": 11728706.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 6.220610618591309,
|
|
"epoch": 0.5554574355351466,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.000497538566874167,
|
|
"loss": 6.1439,
|
|
"mean_token_accuracy": 0.14255456030368804,
|
|
"num_tokens": 11738537.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 6.201089715957641,
|
|
"epoch": 0.555898975626987,
|
|
"grad_norm": 3.53125,
|
|
"learning_rate": 0.0004975339193260084,
|
|
"loss": 5.9668,
|
|
"mean_token_accuracy": 0.1601237177848816,
|
|
"num_tokens": 11747503.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 6.213198041915893,
|
|
"epoch": 0.5563405157188273,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004975292674185371,
|
|
"loss": 6.0626,
|
|
"mean_token_accuracy": 0.15619527399539948,
|
|
"num_tokens": 11756501.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 6.191322374343872,
|
|
"epoch": 0.5567820558106676,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004975246111518439,
|
|
"loss": 6.0361,
|
|
"mean_token_accuracy": 0.14940138384699822,
|
|
"num_tokens": 11765483.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 6.269068384170533,
|
|
"epoch": 0.5572235959025079,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004975199505260202,
|
|
"loss": 6.1656,
|
|
"mean_token_accuracy": 0.13972411677241325,
|
|
"num_tokens": 11774941.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 6.2427021026611325,
|
|
"epoch": 0.5576651359943483,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004975152855411571,
|
|
"loss": 6.1377,
|
|
"mean_token_accuracy": 0.14668529033660888,
|
|
"num_tokens": 11785080.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 6.262989568710327,
|
|
"epoch": 0.5581066760861886,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004975106161973462,
|
|
"loss": 6.0218,
|
|
"mean_token_accuracy": 0.15202814787626268,
|
|
"num_tokens": 11793933.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 6.200152206420898,
|
|
"epoch": 0.558548216178029,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.000497505942494679,
|
|
"loss": 6.0765,
|
|
"mean_token_accuracy": 0.15423234254121782,
|
|
"num_tokens": 11803592.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 6.144359588623047,
|
|
"epoch": 0.5589897562698694,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004975012644332467,
|
|
"loss": 5.9658,
|
|
"mean_token_accuracy": 0.16332813650369643,
|
|
"num_tokens": 11812397.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 6.213898658752441,
|
|
"epoch": 0.5594312963617096,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004974965820131413,
|
|
"loss": 6.0918,
|
|
"mean_token_accuracy": 0.15081132724881172,
|
|
"num_tokens": 11821734.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 6.154282140731811,
|
|
"epoch": 0.55987283645355,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 0.0004974918952344544,
|
|
"loss": 5.995,
|
|
"mean_token_accuracy": 0.15411488115787506,
|
|
"num_tokens": 11832107.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 6.172497034072876,
|
|
"epoch": 0.5603143765453903,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004974872040972777,
|
|
"loss": 6.003,
|
|
"mean_token_accuracy": 0.15274750143289567,
|
|
"num_tokens": 11841983.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 6.1340217113494875,
|
|
"epoch": 0.5607559166372307,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004974825086017033,
|
|
"loss": 5.9912,
|
|
"mean_token_accuracy": 0.1592399835586548,
|
|
"num_tokens": 11851836.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 6.246949529647827,
|
|
"epoch": 0.561197456729071,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.000497477808747823,
|
|
"loss": 6.0429,
|
|
"mean_token_accuracy": 0.15607572942972184,
|
|
"num_tokens": 11861109.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 6.239613485336304,
|
|
"epoch": 0.5616389968209113,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004974731045357292,
|
|
"loss": 6.1315,
|
|
"mean_token_accuracy": 0.14992361664772033,
|
|
"num_tokens": 11871015.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 6.148267030715942,
|
|
"epoch": 0.5620805369127517,
|
|
"grad_norm": 3.78125,
|
|
"learning_rate": 0.0004974683959655136,
|
|
"loss": 6.0401,
|
|
"mean_token_accuracy": 0.15593761950731277,
|
|
"num_tokens": 11881306.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 6.214121961593628,
|
|
"epoch": 0.562522077004592,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004974636830372686,
|
|
"loss": 5.9581,
|
|
"mean_token_accuracy": 0.16205299645662308,
|
|
"num_tokens": 11890251.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 6.193024778366089,
|
|
"epoch": 0.5629636170964324,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004974589657510866,
|
|
"loss": 6.0825,
|
|
"mean_token_accuracy": 0.14803064465522767,
|
|
"num_tokens": 11899662.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 6.168805980682373,
|
|
"epoch": 0.5634051571882727,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004974542441070601,
|
|
"loss": 6.0345,
|
|
"mean_token_accuracy": 0.15523566752672197,
|
|
"num_tokens": 11908699.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 6.189884614944458,
|
|
"epoch": 0.563846697280113,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004974495181052814,
|
|
"loss": 6.0269,
|
|
"mean_token_accuracy": 0.15429562777280809,
|
|
"num_tokens": 11916637.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 6.201843118667602,
|
|
"epoch": 0.5642882373719533,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004974447877458433,
|
|
"loss": 6.0881,
|
|
"mean_token_accuracy": 0.15210264176130295,
|
|
"num_tokens": 11926063.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 6.176416444778442,
|
|
"epoch": 0.5647297774637937,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004974400530288381,
|
|
"loss": 5.9706,
|
|
"mean_token_accuracy": 0.15895548462867737,
|
|
"num_tokens": 11934861.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 6.286151695251465,
|
|
"epoch": 0.5651713175556341,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004974353139543589,
|
|
"loss": 6.0918,
|
|
"mean_token_accuracy": 0.14939165115356445,
|
|
"num_tokens": 11944403.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 6.264640760421753,
|
|
"epoch": 0.5656128576474744,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004974305705224983,
|
|
"loss": 6.1495,
|
|
"mean_token_accuracy": 0.1527331218123436,
|
|
"num_tokens": 11953306.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 6.199301099777221,
|
|
"epoch": 0.5660543977393148,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004974258227333493,
|
|
"loss": 6.0376,
|
|
"mean_token_accuracy": 0.155905519425869,
|
|
"num_tokens": 11962727.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 6.2386260509490965,
|
|
"epoch": 0.566495937831155,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004974210705870052,
|
|
"loss": 6.191,
|
|
"mean_token_accuracy": 0.14767182171344756,
|
|
"num_tokens": 11972375.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 6.132161664962768,
|
|
"epoch": 0.5669374779229954,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004974163140835586,
|
|
"loss": 5.9688,
|
|
"mean_token_accuracy": 0.15154811069369317,
|
|
"num_tokens": 11981989.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 6.206036567687988,
|
|
"epoch": 0.5673790180148357,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004974115532231029,
|
|
"loss": 6.0272,
|
|
"mean_token_accuracy": 0.1478888511657715,
|
|
"num_tokens": 11990865.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 6.1785540103912355,
|
|
"epoch": 0.5678205581066761,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004974067880057315,
|
|
"loss": 6.0118,
|
|
"mean_token_accuracy": 0.16050802171230316,
|
|
"num_tokens": 12000697.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 6.123645830154419,
|
|
"epoch": 0.5682620981985165,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004974020184315375,
|
|
"loss": 6.0857,
|
|
"mean_token_accuracy": 0.15496583580970763,
|
|
"num_tokens": 12010560.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 6.261683130264283,
|
|
"epoch": 0.5687036382903567,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004973972445006144,
|
|
"loss": 6.123,
|
|
"mean_token_accuracy": 0.15426487401127814,
|
|
"num_tokens": 12020760.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 6.10278959274292,
|
|
"epoch": 0.5691451783821971,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004973924662130559,
|
|
"loss": 5.9569,
|
|
"mean_token_accuracy": 0.1542418286204338,
|
|
"num_tokens": 12030467.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 6.166108751296997,
|
|
"epoch": 0.5695867184740374,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004973876835689554,
|
|
"loss": 6.069,
|
|
"mean_token_accuracy": 0.156872521340847,
|
|
"num_tokens": 12039897.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 6.27096848487854,
|
|
"epoch": 0.5700282585658778,
|
|
"grad_norm": 4.875,
|
|
"learning_rate": 0.0004973828965684066,
|
|
"loss": 6.0884,
|
|
"mean_token_accuracy": 0.1475502520799637,
|
|
"num_tokens": 12048997.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 6.220898103713989,
|
|
"epoch": 0.5704697986577181,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004973781052115035,
|
|
"loss": 5.9901,
|
|
"mean_token_accuracy": 0.16035318821668626,
|
|
"num_tokens": 12057493.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 6.075660610198975,
|
|
"epoch": 0.5709113387495585,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004973733094983396,
|
|
"loss": 6.0659,
|
|
"mean_token_accuracy": 0.15576789081096648,
|
|
"num_tokens": 12066329.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 6.112877702713012,
|
|
"epoch": 0.5713528788413988,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004973685094290092,
|
|
"loss": 6.0907,
|
|
"mean_token_accuracy": 0.15044785290956497,
|
|
"num_tokens": 12076022.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 6.243810939788818,
|
|
"epoch": 0.5717944189332391,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.000497363705003606,
|
|
"loss": 6.0335,
|
|
"mean_token_accuracy": 0.14949652031064034,
|
|
"num_tokens": 12085750.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 6.25089545249939,
|
|
"epoch": 0.5722359590250795,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004973588962222244,
|
|
"loss": 6.0547,
|
|
"mean_token_accuracy": 0.1555928558111191,
|
|
"num_tokens": 12094935.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 6.165074634552002,
|
|
"epoch": 0.5726774991169198,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004973540830849585,
|
|
"loss": 5.9943,
|
|
"mean_token_accuracy": 0.15322138816118241,
|
|
"num_tokens": 12104970.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 6.203184366226196,
|
|
"epoch": 0.5731190392087602,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004973492655919025,
|
|
"loss": 6.1188,
|
|
"mean_token_accuracy": 0.14760904386639595,
|
|
"num_tokens": 12116195.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 6.294361782073975,
|
|
"epoch": 0.5735605793006004,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004973444437431508,
|
|
"loss": 6.0475,
|
|
"mean_token_accuracy": 0.15356907099485398,
|
|
"num_tokens": 12125485.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 6.193444156646729,
|
|
"epoch": 0.5740021193924408,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004973396175387981,
|
|
"loss": 6.056,
|
|
"mean_token_accuracy": 0.15648747980594635,
|
|
"num_tokens": 12135474.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 6.191966485977173,
|
|
"epoch": 0.5744436594842812,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004973347869789385,
|
|
"loss": 6.0901,
|
|
"mean_token_accuracy": 0.1518266037106514,
|
|
"num_tokens": 12144945.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 6.252193546295166,
|
|
"epoch": 0.5748851995761215,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004973299520636671,
|
|
"loss": 6.0382,
|
|
"mean_token_accuracy": 0.15668775588274003,
|
|
"num_tokens": 12154893.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 6.2492657661437985,
|
|
"epoch": 0.5753267396679619,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004973251127930782,
|
|
"loss": 6.1126,
|
|
"mean_token_accuracy": 0.1518278144299984,
|
|
"num_tokens": 12164047.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 6.247848701477051,
|
|
"epoch": 0.5757682797598022,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004973202691672669,
|
|
"loss": 6.1037,
|
|
"mean_token_accuracy": 0.15016882196068765,
|
|
"num_tokens": 12172965.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 6.226498222351074,
|
|
"epoch": 0.5762098198516425,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004973154211863279,
|
|
"loss": 6.122,
|
|
"mean_token_accuracy": 0.14945205301046371,
|
|
"num_tokens": 12183534.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 6.1939177989959715,
|
|
"epoch": 0.5766513599434828,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004973105688503563,
|
|
"loss": 6.0807,
|
|
"mean_token_accuracy": 0.15398238748311996,
|
|
"num_tokens": 12194370.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 6.242078161239624,
|
|
"epoch": 0.5770929000353232,
|
|
"grad_norm": 4.65625,
|
|
"learning_rate": 0.000497305712159447,
|
|
"loss": 6.0691,
|
|
"mean_token_accuracy": 0.15035768449306489,
|
|
"num_tokens": 12203765.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 6.2378651142120365,
|
|
"epoch": 0.5775344401271636,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004973008511136954,
|
|
"loss": 6.0373,
|
|
"mean_token_accuracy": 0.15557296574115753,
|
|
"num_tokens": 12212889.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 6.177788972854614,
|
|
"epoch": 0.5779759802190039,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004972959857131963,
|
|
"loss": 6.1085,
|
|
"mean_token_accuracy": 0.14831465035676955,
|
|
"num_tokens": 12222055.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 6.297669792175293,
|
|
"epoch": 0.5784175203108443,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004972911159580454,
|
|
"loss": 6.102,
|
|
"mean_token_accuracy": 0.14912044182419776,
|
|
"num_tokens": 12232092.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 6.292926406860351,
|
|
"epoch": 0.5788590604026845,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.000497286241848338,
|
|
"loss": 6.1226,
|
|
"mean_token_accuracy": 0.14944964945316314,
|
|
"num_tokens": 12241411.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 6.200898456573486,
|
|
"epoch": 0.5793006004945249,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004972813633841696,
|
|
"loss": 5.9886,
|
|
"mean_token_accuracy": 0.1560185208916664,
|
|
"num_tokens": 12249735.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 6.168171453475952,
|
|
"epoch": 0.5797421405863652,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004972764805656355,
|
|
"loss": 6.0127,
|
|
"mean_token_accuracy": 0.1622329831123352,
|
|
"num_tokens": 12259132.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 6.175434255599976,
|
|
"epoch": 0.5801836806782056,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004972715933928318,
|
|
"loss": 6.0896,
|
|
"mean_token_accuracy": 0.16034998446702958,
|
|
"num_tokens": 12269401.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 6.23064079284668,
|
|
"epoch": 0.580625220770046,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004972667018658539,
|
|
"loss": 6.109,
|
|
"mean_token_accuracy": 0.14848504364490508,
|
|
"num_tokens": 12279163.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 6.145978307723999,
|
|
"epoch": 0.5810667608618862,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 0.0004972618059847976,
|
|
"loss": 6.0028,
|
|
"mean_token_accuracy": 0.15803629159927368,
|
|
"num_tokens": 12287942.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 6.1623132705688475,
|
|
"epoch": 0.5815083009537266,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004972569057497591,
|
|
"loss": 5.9963,
|
|
"mean_token_accuracy": 0.15548112392425537,
|
|
"num_tokens": 12296717.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 6.260863351821899,
|
|
"epoch": 0.5819498410455669,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004972520011608341,
|
|
"loss": 5.9805,
|
|
"mean_token_accuracy": 0.16117053180933,
|
|
"num_tokens": 12305983.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 6.097669696807861,
|
|
"epoch": 0.5823913811374073,
|
|
"grad_norm": 6.4375,
|
|
"learning_rate": 0.0004972470922181189,
|
|
"loss": 6.0512,
|
|
"mean_token_accuracy": 0.1469077378511429,
|
|
"num_tokens": 12315338.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 6.187917041778564,
|
|
"epoch": 0.5828329212292476,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004972421789217094,
|
|
"loss": 6.1392,
|
|
"mean_token_accuracy": 0.14520934969186783,
|
|
"num_tokens": 12324828.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 6.350688695907593,
|
|
"epoch": 0.583274461321088,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004972372612717022,
|
|
"loss": 6.0047,
|
|
"mean_token_accuracy": 0.16197529584169387,
|
|
"num_tokens": 12332844.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 6.276282072067261,
|
|
"epoch": 0.5837160014129283,
|
|
"grad_norm": 6.65625,
|
|
"learning_rate": 0.0004972323392681934,
|
|
"loss": 6.031,
|
|
"mean_token_accuracy": 0.15629135370254515,
|
|
"num_tokens": 12342062.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 6.184615802764893,
|
|
"epoch": 0.5841575415047686,
|
|
"grad_norm": 3.125,
|
|
"learning_rate": 0.0004972274129112794,
|
|
"loss": 6.1162,
|
|
"mean_token_accuracy": 0.14776388108730315,
|
|
"num_tokens": 12352071.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 6.271507930755615,
|
|
"epoch": 0.584599081596609,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004972224822010567,
|
|
"loss": 6.1749,
|
|
"mean_token_accuracy": 0.1432945176959038,
|
|
"num_tokens": 12362025.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 6.242451143264771,
|
|
"epoch": 0.5850406216884493,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004972175471376222,
|
|
"loss": 6.1652,
|
|
"mean_token_accuracy": 0.1467423915863037,
|
|
"num_tokens": 12371547.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 6.290982723236084,
|
|
"epoch": 0.5854821617802897,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004972126077210722,
|
|
"loss": 6.0833,
|
|
"mean_token_accuracy": 0.14927616715431213,
|
|
"num_tokens": 12381385.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 6.2902881622314455,
|
|
"epoch": 0.5859237018721299,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004972076639515035,
|
|
"loss": 6.1217,
|
|
"mean_token_accuracy": 0.1538809731602669,
|
|
"num_tokens": 12391302.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 6.085922527313232,
|
|
"epoch": 0.5863652419639703,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004972027158290131,
|
|
"loss": 6.0164,
|
|
"mean_token_accuracy": 0.15934976935386658,
|
|
"num_tokens": 12400388.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 6.170651435852051,
|
|
"epoch": 0.5868067820558107,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.000497197763353698,
|
|
"loss": 6.0939,
|
|
"mean_token_accuracy": 0.14469650983810425,
|
|
"num_tokens": 12409695.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 6.278474140167236,
|
|
"epoch": 0.587248322147651,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000497192806525655,
|
|
"loss": 5.9556,
|
|
"mean_token_accuracy": 0.16218124628067015,
|
|
"num_tokens": 12418728.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 6.220705509185791,
|
|
"epoch": 0.5876898622394914,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004971878453449811,
|
|
"loss": 6.1291,
|
|
"mean_token_accuracy": 0.14868279695510864,
|
|
"num_tokens": 12428072.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 6.202286434173584,
|
|
"epoch": 0.5881314023313317,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.000497182879811774,
|
|
"loss": 6.0501,
|
|
"mean_token_accuracy": 0.15819858834147454,
|
|
"num_tokens": 12436624.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 6.177549600601196,
|
|
"epoch": 0.588572942423172,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004971779099261304,
|
|
"loss": 6.0603,
|
|
"mean_token_accuracy": 0.14843887835741043,
|
|
"num_tokens": 12446370.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 6.236004447937011,
|
|
"epoch": 0.5890144825150123,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.000497172935688148,
|
|
"loss": 6.1136,
|
|
"mean_token_accuracy": 0.15249148458242417,
|
|
"num_tokens": 12456705.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 6.248232030868531,
|
|
"epoch": 0.5894560226068527,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004971679570979242,
|
|
"loss": 6.1159,
|
|
"mean_token_accuracy": 0.1509490966796875,
|
|
"num_tokens": 12466150.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 6.2066127300262455,
|
|
"epoch": 0.5898975626986931,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004971629741555565,
|
|
"loss": 5.9648,
|
|
"mean_token_accuracy": 0.15754401981830596,
|
|
"num_tokens": 12475051.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 6.199983835220337,
|
|
"epoch": 0.5903391027905334,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004971579868611423,
|
|
"loss": 6.0543,
|
|
"mean_token_accuracy": 0.15531396567821504,
|
|
"num_tokens": 12485427.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 6.144886445999146,
|
|
"epoch": 0.5907806428823738,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004971529952147797,
|
|
"loss": 5.9991,
|
|
"mean_token_accuracy": 0.1566150113940239,
|
|
"num_tokens": 12494489.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 6.212142562866211,
|
|
"epoch": 0.591222182974214,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000497147999216566,
|
|
"loss": 6.0259,
|
|
"mean_token_accuracy": 0.15383399724960328,
|
|
"num_tokens": 12503656.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 6.257586860656739,
|
|
"epoch": 0.5916637230660544,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004971429988665996,
|
|
"loss": 6.0541,
|
|
"mean_token_accuracy": 0.14916461184620858,
|
|
"num_tokens": 12512940.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 6.21803913116455,
|
|
"epoch": 0.5921052631578947,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.000497137994164978,
|
|
"loss": 6.0141,
|
|
"mean_token_accuracy": 0.15520734190940857,
|
|
"num_tokens": 12523186.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 6.175590991973877,
|
|
"epoch": 0.5925468032497351,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004971329851117996,
|
|
"loss": 6.0537,
|
|
"mean_token_accuracy": 0.15011201053857803,
|
|
"num_tokens": 12533018.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 6.257619857788086,
|
|
"epoch": 0.5929883433415755,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004971279717071622,
|
|
"loss": 6.115,
|
|
"mean_token_accuracy": 0.15560168474912645,
|
|
"num_tokens": 12542889.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 6.295772314071655,
|
|
"epoch": 0.5934298834334157,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004971229539511643,
|
|
"loss": 6.1275,
|
|
"mean_token_accuracy": 0.14035015031695366,
|
|
"num_tokens": 12553625.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 6.150123023986817,
|
|
"epoch": 0.5938714235252561,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000497117931843904,
|
|
"loss": 6.0409,
|
|
"mean_token_accuracy": 0.15282395333051682,
|
|
"num_tokens": 12563012.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 6.2669105052948,
|
|
"epoch": 0.5943129636170964,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004971129053854797,
|
|
"loss": 6.1758,
|
|
"mean_token_accuracy": 0.14357056468725204,
|
|
"num_tokens": 12572892.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 6.2501020431518555,
|
|
"epoch": 0.5947545037089368,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00049710787457599,
|
|
"loss": 6.0011,
|
|
"mean_token_accuracy": 0.16138584166765213,
|
|
"num_tokens": 12581550.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 6.204801893234253,
|
|
"epoch": 0.5951960438007771,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004971028394155332,
|
|
"loss": 6.0926,
|
|
"mean_token_accuracy": 0.15026257038116456,
|
|
"num_tokens": 12590599.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 6.2605963230133055,
|
|
"epoch": 0.5956375838926175,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.0004970977999042082,
|
|
"loss": 6.0422,
|
|
"mean_token_accuracy": 0.15356017649173737,
|
|
"num_tokens": 12599497.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 6.165054607391357,
|
|
"epoch": 0.5960791239844578,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004970927560421137,
|
|
"loss": 6.0937,
|
|
"mean_token_accuracy": 0.1541163817048073,
|
|
"num_tokens": 12608273.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 6.140692090988159,
|
|
"epoch": 0.5965206640762981,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004970877078293483,
|
|
"loss": 5.9893,
|
|
"mean_token_accuracy": 0.1589522145688534,
|
|
"num_tokens": 12617287.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 6.239122676849365,
|
|
"epoch": 0.5969622041681385,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004970826552660111,
|
|
"loss": 6.0656,
|
|
"mean_token_accuracy": 0.15358479097485542,
|
|
"num_tokens": 12626874.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 6.191449689865112,
|
|
"epoch": 0.5974037442599788,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004970775983522009,
|
|
"loss": 6.0956,
|
|
"mean_token_accuracy": 0.15042449682950973,
|
|
"num_tokens": 12635218.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 6.20980019569397,
|
|
"epoch": 0.5978452843518192,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004970725370880168,
|
|
"loss": 6.0466,
|
|
"mean_token_accuracy": 0.15192867666482926,
|
|
"num_tokens": 12644395.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 6.27781343460083,
|
|
"epoch": 0.5982868244436594,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004970674714735581,
|
|
"loss": 6.0915,
|
|
"mean_token_accuracy": 0.1551320508122444,
|
|
"num_tokens": 12654540.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 6.217710781097412,
|
|
"epoch": 0.5987283645354998,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004970624015089239,
|
|
"loss": 5.9557,
|
|
"mean_token_accuracy": 0.16181351020932197,
|
|
"num_tokens": 12663546.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 6.087097930908203,
|
|
"epoch": 0.5991699046273402,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004970573271942135,
|
|
"loss": 6.0446,
|
|
"mean_token_accuracy": 0.1569458231329918,
|
|
"num_tokens": 12672353.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 6.069739484786988,
|
|
"epoch": 0.5996114447191805,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004970522485295265,
|
|
"loss": 5.9354,
|
|
"mean_token_accuracy": 0.16273632645606995,
|
|
"num_tokens": 12680833.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 6.170738983154297,
|
|
"epoch": 0.6000529848110209,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004970471655149621,
|
|
"loss": 5.9042,
|
|
"mean_token_accuracy": 0.16110148131847382,
|
|
"num_tokens": 12690033.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 6.103061532974243,
|
|
"epoch": 0.6004945249028611,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.00049704207815062,
|
|
"loss": 5.99,
|
|
"mean_token_accuracy": 0.1616707846522331,
|
|
"num_tokens": 12700127.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 6.221381616592407,
|
|
"epoch": 0.6009360649947015,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004970369864366,
|
|
"loss": 6.0294,
|
|
"mean_token_accuracy": 0.1497489720582962,
|
|
"num_tokens": 12709803.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 6.2039313316345215,
|
|
"epoch": 0.6013776050865418,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004970318903730017,
|
|
"loss": 6.0089,
|
|
"mean_token_accuracy": 0.15192246660590172,
|
|
"num_tokens": 12718876.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 6.282535219192505,
|
|
"epoch": 0.6018191451783822,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004970267899599249,
|
|
"loss": 6.1185,
|
|
"mean_token_accuracy": 0.1507984146475792,
|
|
"num_tokens": 12728745.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 6.2520589351654055,
|
|
"epoch": 0.6022606852702226,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004970216851974695,
|
|
"loss": 6.1066,
|
|
"mean_token_accuracy": 0.14358121454715728,
|
|
"num_tokens": 12738764.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 6.153601789474488,
|
|
"epoch": 0.6027022253620629,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004970165760857356,
|
|
"loss": 6.0483,
|
|
"mean_token_accuracy": 0.1471211776137352,
|
|
"num_tokens": 12747888.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 6.2664146900177,
|
|
"epoch": 0.6031437654539032,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004970114626248232,
|
|
"loss": 6.0709,
|
|
"mean_token_accuracy": 0.15116212218999864,
|
|
"num_tokens": 12757763.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 6.225366640090942,
|
|
"epoch": 0.6035853055457435,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004970063448148326,
|
|
"loss": 6.108,
|
|
"mean_token_accuracy": 0.14670519903302193,
|
|
"num_tokens": 12767924.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 6.247302484512329,
|
|
"epoch": 0.6040268456375839,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004970012226558639,
|
|
"loss": 6.1148,
|
|
"mean_token_accuracy": 0.14938763603568078,
|
|
"num_tokens": 12777140.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 6.2420226573944095,
|
|
"epoch": 0.6044683857294242,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004969960961480176,
|
|
"loss": 6.0861,
|
|
"mean_token_accuracy": 0.1501963809132576,
|
|
"num_tokens": 12786731.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 6.213519048690796,
|
|
"epoch": 0.6049099258212646,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004969909652913939,
|
|
"loss": 6.0218,
|
|
"mean_token_accuracy": 0.15606847256422043,
|
|
"num_tokens": 12796839.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 6.237181377410889,
|
|
"epoch": 0.605351465913105,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004969858300860935,
|
|
"loss": 6.0995,
|
|
"mean_token_accuracy": 0.14979733973741532,
|
|
"num_tokens": 12805944.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 6.167507648468018,
|
|
"epoch": 0.6057930060049452,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004969806905322169,
|
|
"loss": 6.0561,
|
|
"mean_token_accuracy": 0.15602336823940277,
|
|
"num_tokens": 12814692.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 6.131442928314209,
|
|
"epoch": 0.6062345460967856,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004969755466298649,
|
|
"loss": 6.0132,
|
|
"mean_token_accuracy": 0.15122820138931276,
|
|
"num_tokens": 12824506.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 6.236468505859375,
|
|
"epoch": 0.6066760861886259,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004969703983791382,
|
|
"loss": 6.0776,
|
|
"mean_token_accuracy": 0.1508278429508209,
|
|
"num_tokens": 12835157.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 6.225825595855713,
|
|
"epoch": 0.6071176262804663,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004969652457801376,
|
|
"loss": 5.9857,
|
|
"mean_token_accuracy": 0.15083080306649208,
|
|
"num_tokens": 12844281.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 6.2883728504180905,
|
|
"epoch": 0.6075591663723066,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004969600888329641,
|
|
"loss": 6.0412,
|
|
"mean_token_accuracy": 0.1524555817246437,
|
|
"num_tokens": 12854486.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 6.211116743087769,
|
|
"epoch": 0.608000706464147,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004969549275377186,
|
|
"loss": 6.0277,
|
|
"mean_token_accuracy": 0.14935416579246522,
|
|
"num_tokens": 12863574.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 6.210080862045288,
|
|
"epoch": 0.6084422465559873,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004969497618945024,
|
|
"loss": 5.9959,
|
|
"mean_token_accuracy": 0.1540638104081154,
|
|
"num_tokens": 12872450.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 6.191243648529053,
|
|
"epoch": 0.6088837866478276,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 0.0004969445919034165,
|
|
"loss": 5.9611,
|
|
"mean_token_accuracy": 0.1621923491358757,
|
|
"num_tokens": 12881299.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 6.115060424804687,
|
|
"epoch": 0.609325326739668,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004969394175645623,
|
|
"loss": 5.9291,
|
|
"mean_token_accuracy": 0.15979383438825606,
|
|
"num_tokens": 12889943.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 6.155762672424316,
|
|
"epoch": 0.6097668668315083,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004969342388780411,
|
|
"loss": 6.0358,
|
|
"mean_token_accuracy": 0.1543547108769417,
|
|
"num_tokens": 12899497.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 6.21222677230835,
|
|
"epoch": 0.6102084069233487,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004969290558439546,
|
|
"loss": 6.0083,
|
|
"mean_token_accuracy": 0.15624455213546753,
|
|
"num_tokens": 12908677.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 6.203832674026489,
|
|
"epoch": 0.6106499470151889,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004969238684624038,
|
|
"loss": 6.1268,
|
|
"mean_token_accuracy": 0.14566057920455933,
|
|
"num_tokens": 12918468.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 6.166177558898926,
|
|
"epoch": 0.6110914871070293,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004969186767334908,
|
|
"loss": 6.0247,
|
|
"mean_token_accuracy": 0.15501216650009156,
|
|
"num_tokens": 12928527.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 6.192750883102417,
|
|
"epoch": 0.6115330271988697,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004969134806573172,
|
|
"loss": 5.9829,
|
|
"mean_token_accuracy": 0.1576339840888977,
|
|
"num_tokens": 12937021.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 6.096978569030762,
|
|
"epoch": 0.61197456729071,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004969082802339846,
|
|
"loss": 5.9439,
|
|
"mean_token_accuracy": 0.1602706491947174,
|
|
"num_tokens": 12945570.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 6.146313714981079,
|
|
"epoch": 0.6124161073825504,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000496903075463595,
|
|
"loss": 6.0759,
|
|
"mean_token_accuracy": 0.15233781188726425,
|
|
"num_tokens": 12954594.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 6.1925209045410154,
|
|
"epoch": 0.6128576474743906,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004968978663462504,
|
|
"loss": 6.0444,
|
|
"mean_token_accuracy": 0.16344080865383148,
|
|
"num_tokens": 12963328.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 6.184589910507202,
|
|
"epoch": 0.613299187566231,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004968926528820529,
|
|
"loss": 6.0414,
|
|
"mean_token_accuracy": 0.15409351587295533,
|
|
"num_tokens": 12972806.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 6.214977741241455,
|
|
"epoch": 0.6137407276580713,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004968874350711044,
|
|
"loss": 6.0413,
|
|
"mean_token_accuracy": 0.15354430079460143,
|
|
"num_tokens": 12981940.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 6.146689558029175,
|
|
"epoch": 0.6141822677499117,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004968822129135072,
|
|
"loss": 6.0022,
|
|
"mean_token_accuracy": 0.15630166381597518,
|
|
"num_tokens": 12990501.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 6.2418646812438965,
|
|
"epoch": 0.6146238078417521,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004968769864093637,
|
|
"loss": 6.0442,
|
|
"mean_token_accuracy": 0.15087320953607558,
|
|
"num_tokens": 12999734.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 6.264814567565918,
|
|
"epoch": 0.6150653479335924,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004968717555587762,
|
|
"loss": 6.1179,
|
|
"mean_token_accuracy": 0.1479475438594818,
|
|
"num_tokens": 13009323.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 6.256582355499267,
|
|
"epoch": 0.6155068880254327,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004968665203618472,
|
|
"loss": 6.118,
|
|
"mean_token_accuracy": 0.15157626569271088,
|
|
"num_tokens": 13018136.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 6.167997980117798,
|
|
"epoch": 0.615948428117273,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004968612808186793,
|
|
"loss": 6.0711,
|
|
"mean_token_accuracy": 0.1537791147828102,
|
|
"num_tokens": 13026494.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 6.140088653564453,
|
|
"epoch": 0.6163899682091134,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004968560369293751,
|
|
"loss": 6.0657,
|
|
"mean_token_accuracy": 0.15240042209625243,
|
|
"num_tokens": 13036548.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 6.258679151535034,
|
|
"epoch": 0.6168315083009537,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004968507886940372,
|
|
"loss": 6.0944,
|
|
"mean_token_accuracy": 0.1527463138103485,
|
|
"num_tokens": 13045653.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 6.304360866546631,
|
|
"epoch": 0.6172730483927941,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004968455361127686,
|
|
"loss": 6.1532,
|
|
"mean_token_accuracy": 0.15307221710681915,
|
|
"num_tokens": 13056204.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 6.2066652297973635,
|
|
"epoch": 0.6177145884846345,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004968402791856721,
|
|
"loss": 6.1142,
|
|
"mean_token_accuracy": 0.1567689709365368,
|
|
"num_tokens": 13067215.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 6.22037148475647,
|
|
"epoch": 0.6181561285764747,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004968350179128507,
|
|
"loss": 6.0603,
|
|
"mean_token_accuracy": 0.15270569920539856,
|
|
"num_tokens": 13076824.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 6.193442726135254,
|
|
"epoch": 0.6185976686683151,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004968297522944075,
|
|
"loss": 6.0174,
|
|
"mean_token_accuracy": 0.15545051395893097,
|
|
"num_tokens": 13086205.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 6.099516534805298,
|
|
"epoch": 0.6190392087601554,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004968244823304455,
|
|
"loss": 5.9611,
|
|
"mean_token_accuracy": 0.15705401301383973,
|
|
"num_tokens": 13096381.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 6.205773544311524,
|
|
"epoch": 0.6194807488519958,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004968192080210683,
|
|
"loss": 6.0129,
|
|
"mean_token_accuracy": 0.16113550513982772,
|
|
"num_tokens": 13106533.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 6.12206654548645,
|
|
"epoch": 0.619922288943836,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004968139293663787,
|
|
"loss": 6.0266,
|
|
"mean_token_accuracy": 0.1595764510333538,
|
|
"num_tokens": 13116605.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 6.093244457244873,
|
|
"epoch": 0.6203638290356764,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004968086463664806,
|
|
"loss": 5.9842,
|
|
"mean_token_accuracy": 0.1645537257194519,
|
|
"num_tokens": 13125316.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 6.265250492095947,
|
|
"epoch": 0.6208053691275168,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.000496803359021477,
|
|
"loss": 6.1575,
|
|
"mean_token_accuracy": 0.1529717206954956,
|
|
"num_tokens": 13135595.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 6.212677383422852,
|
|
"epoch": 0.6212469092193571,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004967980673314719,
|
|
"loss": 6.0798,
|
|
"mean_token_accuracy": 0.14972247779369355,
|
|
"num_tokens": 13144395.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 6.135273265838623,
|
|
"epoch": 0.6216884493111975,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004967927712965688,
|
|
"loss": 6.0286,
|
|
"mean_token_accuracy": 0.15182404965162277,
|
|
"num_tokens": 13153906.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 6.1989999294281,
|
|
"epoch": 0.6221299894030378,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004967874709168714,
|
|
"loss": 5.9929,
|
|
"mean_token_accuracy": 0.15975963473320007,
|
|
"num_tokens": 13163840.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 6.160951852798462,
|
|
"epoch": 0.6225715294948782,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004967821661924837,
|
|
"loss": 5.9912,
|
|
"mean_token_accuracy": 0.15861564129590988,
|
|
"num_tokens": 13173224.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 6.2140748500823975,
|
|
"epoch": 0.6230130695867184,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004967768571235094,
|
|
"loss": 6.0213,
|
|
"mean_token_accuracy": 0.15119415298104286,
|
|
"num_tokens": 13182664.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 6.139879417419434,
|
|
"epoch": 0.6234546096785588,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004967715437100526,
|
|
"loss": 5.9334,
|
|
"mean_token_accuracy": 0.15559878945350647,
|
|
"num_tokens": 13191076.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 6.238690948486328,
|
|
"epoch": 0.6238961497703992,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004967662259522174,
|
|
"loss": 6.1416,
|
|
"mean_token_accuracy": 0.14745589941740037,
|
|
"num_tokens": 13201075.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 6.198676013946534,
|
|
"epoch": 0.6243376898622395,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000496760903850108,
|
|
"loss": 6.0701,
|
|
"mean_token_accuracy": 0.15464459657669066,
|
|
"num_tokens": 13210602.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 6.221945667266846,
|
|
"epoch": 0.6247792299540799,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004967555774038286,
|
|
"loss": 6.037,
|
|
"mean_token_accuracy": 0.1527566909790039,
|
|
"num_tokens": 13219601.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 6.167340087890625,
|
|
"epoch": 0.6252207700459201,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004967502466134836,
|
|
"loss": 6.1025,
|
|
"mean_token_accuracy": 0.14824306815862656,
|
|
"num_tokens": 13230675.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 6.246257257461548,
|
|
"epoch": 0.6256623101377605,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004967449114791773,
|
|
"loss": 6.0849,
|
|
"mean_token_accuracy": 0.15261531695723535,
|
|
"num_tokens": 13240349.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 6.272697830200196,
|
|
"epoch": 0.6261038502296008,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004967395720010143,
|
|
"loss": 6.1202,
|
|
"mean_token_accuracy": 0.14724196419119834,
|
|
"num_tokens": 13249867.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 6.2154772758483885,
|
|
"epoch": 0.6265453903214412,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004967342281790992,
|
|
"loss": 6.0531,
|
|
"mean_token_accuracy": 0.15856875777244567,
|
|
"num_tokens": 13259143.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 6.159865665435791,
|
|
"epoch": 0.6269869304132816,
|
|
"grad_norm": 6.71875,
|
|
"learning_rate": 0.0004967288800135368,
|
|
"loss": 5.9901,
|
|
"mean_token_accuracy": 0.1546819418668747,
|
|
"num_tokens": 13268673.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 6.220469045639038,
|
|
"epoch": 0.6274284705051218,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004967235275044315,
|
|
"loss": 6.0192,
|
|
"mean_token_accuracy": 0.15441524162888526,
|
|
"num_tokens": 13278035.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 6.266829919815064,
|
|
"epoch": 0.6278700105969622,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004967181706518886,
|
|
"loss": 6.1135,
|
|
"mean_token_accuracy": 0.1488713502883911,
|
|
"num_tokens": 13286950.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 6.115516662597656,
|
|
"epoch": 0.6283115506888025,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004967128094560128,
|
|
"loss": 5.9907,
|
|
"mean_token_accuracy": 0.1635320097208023,
|
|
"num_tokens": 13296425.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 6.243912315368652,
|
|
"epoch": 0.6287530907806429,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004967074439169092,
|
|
"loss": 6.1113,
|
|
"mean_token_accuracy": 0.14275412932038306,
|
|
"num_tokens": 13306094.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 6.2228553771972654,
|
|
"epoch": 0.6291946308724832,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004967020740346827,
|
|
"loss": 6.05,
|
|
"mean_token_accuracy": 0.1568419575691223,
|
|
"num_tokens": 13315181.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 6.162428712844848,
|
|
"epoch": 0.6296361709643236,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004966966998094387,
|
|
"loss": 5.9656,
|
|
"mean_token_accuracy": 0.15805367827415467,
|
|
"num_tokens": 13324108.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 6.156050443649292,
|
|
"epoch": 0.630077711056164,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004966913212412825,
|
|
"loss": 6.0323,
|
|
"mean_token_accuracy": 0.15374385565519333,
|
|
"num_tokens": 13333101.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 6.179844665527344,
|
|
"epoch": 0.6305192511480042,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004966859383303194,
|
|
"loss": 5.9586,
|
|
"mean_token_accuracy": 0.16109023243188858,
|
|
"num_tokens": 13341804.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 6.1235325813293455,
|
|
"epoch": 0.6309607912398446,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004966805510766549,
|
|
"loss": 6.0073,
|
|
"mean_token_accuracy": 0.1541972875595093,
|
|
"num_tokens": 13350911.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 6.2234206199646,
|
|
"epoch": 0.6314023313316849,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004966751594803944,
|
|
"loss": 6.0057,
|
|
"mean_token_accuracy": 0.15637123882770537,
|
|
"num_tokens": 13360657.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 6.098598146438599,
|
|
"epoch": 0.6318438714235253,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004966697635416437,
|
|
"loss": 5.9476,
|
|
"mean_token_accuracy": 0.16033453047275542,
|
|
"num_tokens": 13370462.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 6.207261085510254,
|
|
"epoch": 0.6322854115153655,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004966643632605082,
|
|
"loss": 6.0723,
|
|
"mean_token_accuracy": 0.15057104974985122,
|
|
"num_tokens": 13379446.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 6.190232229232788,
|
|
"epoch": 0.6327269516072059,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000496658958637094,
|
|
"loss": 6.0594,
|
|
"mean_token_accuracy": 0.1560957133769989,
|
|
"num_tokens": 13389238.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 6.161271476745606,
|
|
"epoch": 0.6331684916990463,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000496653549671507,
|
|
"loss": 6.0535,
|
|
"mean_token_accuracy": 0.158417047560215,
|
|
"num_tokens": 13398613.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 6.223568677902222,
|
|
"epoch": 0.6336100317908866,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004966481363638529,
|
|
"loss": 6.0537,
|
|
"mean_token_accuracy": 0.15781836062669755,
|
|
"num_tokens": 13407600.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 6.083367395401001,
|
|
"epoch": 0.634051571882727,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004966427187142378,
|
|
"loss": 5.9372,
|
|
"mean_token_accuracy": 0.16657115668058395,
|
|
"num_tokens": 13415974.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 6.179879426956177,
|
|
"epoch": 0.6344931119745673,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004966372967227681,
|
|
"loss": 5.9663,
|
|
"mean_token_accuracy": 0.16088535636663437,
|
|
"num_tokens": 13425628.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 6.104554843902588,
|
|
"epoch": 0.6349346520664076,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004966318703895496,
|
|
"loss": 5.9651,
|
|
"mean_token_accuracy": 0.15989047139883042,
|
|
"num_tokens": 13435573.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 6.174526977539062,
|
|
"epoch": 0.6353761921582479,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004966264397146888,
|
|
"loss": 5.9525,
|
|
"mean_token_accuracy": 0.15323926508426666,
|
|
"num_tokens": 13443969.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 6.237339973449707,
|
|
"epoch": 0.6358177322500883,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004966210046982921,
|
|
"loss": 6.0317,
|
|
"mean_token_accuracy": 0.15322933718562126,
|
|
"num_tokens": 13452823.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 6.173512315750122,
|
|
"epoch": 0.6362592723419287,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004966155653404661,
|
|
"loss": 6.0345,
|
|
"mean_token_accuracy": 0.1533308818936348,
|
|
"num_tokens": 13461090.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 6.238847970962524,
|
|
"epoch": 0.636700812433769,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004966101216413172,
|
|
"loss": 6.0399,
|
|
"mean_token_accuracy": 0.14800184667110444,
|
|
"num_tokens": 13471425.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 6.24900188446045,
|
|
"epoch": 0.6371423525256094,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004966046736009519,
|
|
"loss": 6.102,
|
|
"mean_token_accuracy": 0.15328046232461928,
|
|
"num_tokens": 13479755.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 6.145252418518067,
|
|
"epoch": 0.6375838926174496,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004965992212194772,
|
|
"loss": 5.9879,
|
|
"mean_token_accuracy": 0.16141076385974884,
|
|
"num_tokens": 13488854.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 6.176625680923462,
|
|
"epoch": 0.63802543270929,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004965937644969998,
|
|
"loss": 6.0312,
|
|
"mean_token_accuracy": 0.1527988314628601,
|
|
"num_tokens": 13497987.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 6.167853355407715,
|
|
"epoch": 0.6384669728011303,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004965883034336266,
|
|
"loss": 6.0724,
|
|
"mean_token_accuracy": 0.15332372784614562,
|
|
"num_tokens": 13506960.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 6.188836574554443,
|
|
"epoch": 0.6389085128929707,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004965828380294645,
|
|
"loss": 6.0088,
|
|
"mean_token_accuracy": 0.1588570401072502,
|
|
"num_tokens": 13515907.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 6.19733247756958,
|
|
"epoch": 0.6393500529848111,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004965773682846207,
|
|
"loss": 6.1018,
|
|
"mean_token_accuracy": 0.15815342366695403,
|
|
"num_tokens": 13524876.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 6.239398574829101,
|
|
"epoch": 0.6397915930766513,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004965718941992021,
|
|
"loss": 5.9933,
|
|
"mean_token_accuracy": 0.15970173925161363,
|
|
"num_tokens": 13532891.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 6.235479259490967,
|
|
"epoch": 0.6402331331684917,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004965664157733162,
|
|
"loss": 6.0929,
|
|
"mean_token_accuracy": 0.15196404308080674,
|
|
"num_tokens": 13542409.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 6.110021781921387,
|
|
"epoch": 0.640674673260332,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004965609330070703,
|
|
"loss": 6.0384,
|
|
"mean_token_accuracy": 0.15410862118005753,
|
|
"num_tokens": 13551947.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 6.18615756034851,
|
|
"epoch": 0.6411162133521724,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004965554459005717,
|
|
"loss": 6.0771,
|
|
"mean_token_accuracy": 0.15247684121131896,
|
|
"num_tokens": 13560812.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 6.2198789596557615,
|
|
"epoch": 0.6415577534440127,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004965499544539278,
|
|
"loss": 6.0743,
|
|
"mean_token_accuracy": 0.15167128220200538,
|
|
"num_tokens": 13570197.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 6.101568555831909,
|
|
"epoch": 0.641999293535853,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004965444586672463,
|
|
"loss": 5.9756,
|
|
"mean_token_accuracy": 0.15539582222700118,
|
|
"num_tokens": 13579614.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 6.202238512039185,
|
|
"epoch": 0.6424408336276934,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.000496538958540635,
|
|
"loss": 6.0465,
|
|
"mean_token_accuracy": 0.15560982376337051,
|
|
"num_tokens": 13589511.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 6.208220481872559,
|
|
"epoch": 0.6428823737195337,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.0004965334540742015,
|
|
"loss": 6.0106,
|
|
"mean_token_accuracy": 0.1608133688569069,
|
|
"num_tokens": 13597718.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 6.158794736862182,
|
|
"epoch": 0.6433239138113741,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004965279452680535,
|
|
"loss": 6.0865,
|
|
"mean_token_accuracy": 0.15283747911453247,
|
|
"num_tokens": 13607599.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 6.276890754699707,
|
|
"epoch": 0.6437654539032144,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004965224321222991,
|
|
"loss": 6.1314,
|
|
"mean_token_accuracy": 0.1545204684138298,
|
|
"num_tokens": 13616513.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 6.200278282165527,
|
|
"epoch": 0.6442069939950548,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004965169146370462,
|
|
"loss": 5.9904,
|
|
"mean_token_accuracy": 0.15849745124578477,
|
|
"num_tokens": 13625505.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 6.182850933074951,
|
|
"epoch": 0.644648534086895,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004965113928124031,
|
|
"loss": 6.0756,
|
|
"mean_token_accuracy": 0.15372237116098403,
|
|
"num_tokens": 13635340.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 6.109626913070679,
|
|
"epoch": 0.6450900741787354,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004965058666484775,
|
|
"loss": 6.0078,
|
|
"mean_token_accuracy": 0.15201882123947144,
|
|
"num_tokens": 13644886.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 6.15017876625061,
|
|
"epoch": 0.6455316142705758,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004965003361453782,
|
|
"loss": 6.0276,
|
|
"mean_token_accuracy": 0.15886009931564332,
|
|
"num_tokens": 13654093.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 6.20392689704895,
|
|
"epoch": 0.6459731543624161,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004964948013032132,
|
|
"loss": 6.0804,
|
|
"mean_token_accuracy": 0.1466074138879776,
|
|
"num_tokens": 13663095.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 6.269616031646729,
|
|
"epoch": 0.6464146944542565,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.000496489262122091,
|
|
"loss": 6.143,
|
|
"mean_token_accuracy": 0.148014035820961,
|
|
"num_tokens": 13673624.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 6.282114791870117,
|
|
"epoch": 0.6468562345460968,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004964837186021201,
|
|
"loss": 6.0103,
|
|
"mean_token_accuracy": 0.1536534234881401,
|
|
"num_tokens": 13683145.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 6.128833675384522,
|
|
"epoch": 0.6472977746379371,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004964781707434093,
|
|
"loss": 5.994,
|
|
"mean_token_accuracy": 0.15334709733724594,
|
|
"num_tokens": 13691963.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 6.1130454540252686,
|
|
"epoch": 0.6477393147297774,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004964726185460669,
|
|
"loss": 5.9203,
|
|
"mean_token_accuracy": 0.15729135423898696,
|
|
"num_tokens": 13700926.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 6.237424993515015,
|
|
"epoch": 0.6481808548216178,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004964670620102019,
|
|
"loss": 6.1112,
|
|
"mean_token_accuracy": 0.14292953461408614,
|
|
"num_tokens": 13709824.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 6.164659690856934,
|
|
"epoch": 0.6486223949134582,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004964615011359231,
|
|
"loss": 6.0311,
|
|
"mean_token_accuracy": 0.15380015969276428,
|
|
"num_tokens": 13718789.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 6.159794521331787,
|
|
"epoch": 0.6490639350052985,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004964559359233395,
|
|
"loss": 6.0327,
|
|
"mean_token_accuracy": 0.15380071178078653,
|
|
"num_tokens": 13728180.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 6.16060094833374,
|
|
"epoch": 0.6495054750971389,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004964503663725601,
|
|
"loss": 6.1386,
|
|
"mean_token_accuracy": 0.14987644106149672,
|
|
"num_tokens": 13737819.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 6.268680000305176,
|
|
"epoch": 0.6499470151889791,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004964447924836938,
|
|
"loss": 6.0988,
|
|
"mean_token_accuracy": 0.15023177042603492,
|
|
"num_tokens": 13747519.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 6.2985249042510985,
|
|
"epoch": 0.6503885552808195,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004964392142568501,
|
|
"loss": 6.094,
|
|
"mean_token_accuracy": 0.14414478316903115,
|
|
"num_tokens": 13757821.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 6.04947338104248,
|
|
"epoch": 0.6508300953726598,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004964336316921381,
|
|
"loss": 5.9195,
|
|
"mean_token_accuracy": 0.15920277088880538,
|
|
"num_tokens": 13766560.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 6.1585005760192875,
|
|
"epoch": 0.6512716354645002,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004964280447896672,
|
|
"loss": 5.962,
|
|
"mean_token_accuracy": 0.1555796004831791,
|
|
"num_tokens": 13775560.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 6.175464487075805,
|
|
"epoch": 0.6517131755563406,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004964224535495468,
|
|
"loss": 6.0342,
|
|
"mean_token_accuracy": 0.1482674792408943,
|
|
"num_tokens": 13784391.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 6.127026128768921,
|
|
"epoch": 0.6521547156481808,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004964168579718864,
|
|
"loss": 6.0231,
|
|
"mean_token_accuracy": 0.15469812899827956,
|
|
"num_tokens": 13794008.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 6.201027870178223,
|
|
"epoch": 0.6525962557400212,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004964112580567959,
|
|
"loss": 6.0601,
|
|
"mean_token_accuracy": 0.14791031777858735,
|
|
"num_tokens": 13804321.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 6.25521821975708,
|
|
"epoch": 0.6530377958318615,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004964056538043845,
|
|
"loss": 6.0741,
|
|
"mean_token_accuracy": 0.15069704353809357,
|
|
"num_tokens": 13813492.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 6.206275129318238,
|
|
"epoch": 0.6534793359237019,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004964000452147624,
|
|
"loss": 6.0423,
|
|
"mean_token_accuracy": 0.15457727909088134,
|
|
"num_tokens": 13822471.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 6.151892614364624,
|
|
"epoch": 0.6539208760155422,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004963944322880394,
|
|
"loss": 6.1031,
|
|
"mean_token_accuracy": 0.14857663363218307,
|
|
"num_tokens": 13832789.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 6.192709827423096,
|
|
"epoch": 0.6543624161073825,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.0004963888150243253,
|
|
"loss": 6.0634,
|
|
"mean_token_accuracy": 0.1518451228737831,
|
|
"num_tokens": 13842230.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 6.236910200119018,
|
|
"epoch": 0.6548039561992229,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004963831934237302,
|
|
"loss": 5.9893,
|
|
"mean_token_accuracy": 0.1569280132651329,
|
|
"num_tokens": 13851542.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 6.200952482223511,
|
|
"epoch": 0.6552454962910632,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004963775674863643,
|
|
"loss": 6.0211,
|
|
"mean_token_accuracy": 0.15067466497421264,
|
|
"num_tokens": 13860753.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 6.125022459030151,
|
|
"epoch": 0.6556870363829036,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004963719372123378,
|
|
"loss": 6.0103,
|
|
"mean_token_accuracy": 0.1566421151161194,
|
|
"num_tokens": 13870133.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 6.160869884490967,
|
|
"epoch": 0.6561285764747439,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004963663026017609,
|
|
"loss": 6.0807,
|
|
"mean_token_accuracy": 0.15429066121578217,
|
|
"num_tokens": 13879086.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 6.210341215133667,
|
|
"epoch": 0.6565701165665843,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004963606636547441,
|
|
"loss": 6.0369,
|
|
"mean_token_accuracy": 0.15373207926750182,
|
|
"num_tokens": 13888706.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 6.169106435775757,
|
|
"epoch": 0.6570116566584245,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004963550203713976,
|
|
"loss": 6.0729,
|
|
"mean_token_accuracy": 0.15174360275268556,
|
|
"num_tokens": 13897455.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 6.200068998336792,
|
|
"epoch": 0.6574531967502649,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004963493727518323,
|
|
"loss": 6.0686,
|
|
"mean_token_accuracy": 0.15949563831090927,
|
|
"num_tokens": 13907697.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 6.150499439239502,
|
|
"epoch": 0.6578947368421053,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004963437207961585,
|
|
"loss": 6.0823,
|
|
"mean_token_accuracy": 0.15188951194286346,
|
|
"num_tokens": 13917124.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 6.219438552856445,
|
|
"epoch": 0.6583362769339456,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004963380645044874,
|
|
"loss": 6.0081,
|
|
"mean_token_accuracy": 0.1529169574379921,
|
|
"num_tokens": 13926434.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 6.155338430404663,
|
|
"epoch": 0.658777817025786,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004963324038769292,
|
|
"loss": 5.9663,
|
|
"mean_token_accuracy": 0.15937378257513046,
|
|
"num_tokens": 13934883.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 6.193954133987427,
|
|
"epoch": 0.6592193571176262,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004963267389135953,
|
|
"loss": 6.0847,
|
|
"mean_token_accuracy": 0.1530764505267143,
|
|
"num_tokens": 13944514.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 6.201335525512695,
|
|
"epoch": 0.6596608972094666,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004963210696145964,
|
|
"loss": 5.9884,
|
|
"mean_token_accuracy": 0.1515755258500576,
|
|
"num_tokens": 13953434.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 6.180365705490113,
|
|
"epoch": 0.6601024373013069,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004963153959800436,
|
|
"loss": 6.0165,
|
|
"mean_token_accuracy": 0.1623746007680893,
|
|
"num_tokens": 13962493.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 6.1569962978363035,
|
|
"epoch": 0.6605439773931473,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.000496309718010048,
|
|
"loss": 6.0601,
|
|
"mean_token_accuracy": 0.15363184958696366,
|
|
"num_tokens": 13971193.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 6.146395444869995,
|
|
"epoch": 0.6609855174849877,
|
|
"grad_norm": 6.0625,
|
|
"learning_rate": 0.0004963040357047209,
|
|
"loss": 6.0695,
|
|
"mean_token_accuracy": 0.15360373705625535,
|
|
"num_tokens": 13981829.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 6.251808404922485,
|
|
"epoch": 0.661427057576828,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004962983490641737,
|
|
"loss": 6.0077,
|
|
"mean_token_accuracy": 0.15239822417497634,
|
|
"num_tokens": 13990262.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 6.214360237121582,
|
|
"epoch": 0.6618685976686683,
|
|
"grad_norm": 3.40625,
|
|
"learning_rate": 0.0004962926580885177,
|
|
"loss": 6.052,
|
|
"mean_token_accuracy": 0.15461465418338777,
|
|
"num_tokens": 14000100.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 6.171396398544312,
|
|
"epoch": 0.6623101377605086,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004962869627778642,
|
|
"loss": 6.0768,
|
|
"mean_token_accuracy": 0.1547115571796894,
|
|
"num_tokens": 14009330.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 6.157674789428711,
|
|
"epoch": 0.662751677852349,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004962812631323252,
|
|
"loss": 6.0428,
|
|
"mean_token_accuracy": 0.15067947879433632,
|
|
"num_tokens": 14018109.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 6.194535255432129,
|
|
"epoch": 0.6631932179441893,
|
|
"grad_norm": 4.15625,
|
|
"learning_rate": 0.000496275559152012,
|
|
"loss": 5.9776,
|
|
"mean_token_accuracy": 0.15149088948965073,
|
|
"num_tokens": 14027318.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 6.23044638633728,
|
|
"epoch": 0.6636347580360297,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004962698508370365,
|
|
"loss": 6.0642,
|
|
"mean_token_accuracy": 0.15488168299198152,
|
|
"num_tokens": 14037061.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 6.167206764221191,
|
|
"epoch": 0.6640762981278701,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004962641381875103,
|
|
"loss": 6.046,
|
|
"mean_token_accuracy": 0.14700114279985427,
|
|
"num_tokens": 14046008.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 6.190823316574097,
|
|
"epoch": 0.6645178382197103,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004962584212035456,
|
|
"loss": 6.0347,
|
|
"mean_token_accuracy": 0.14479782730340957,
|
|
"num_tokens": 14054535.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 6.246673536300659,
|
|
"epoch": 0.6649593783115507,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004962526998852543,
|
|
"loss": 6.0309,
|
|
"mean_token_accuracy": 0.15494185984134673,
|
|
"num_tokens": 14063680.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 6.224277019500732,
|
|
"epoch": 0.665400918403391,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004962469742327483,
|
|
"loss": 6.0658,
|
|
"mean_token_accuracy": 0.15635597407817842,
|
|
"num_tokens": 14072206.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 6.1906343460083,
|
|
"epoch": 0.6658424584952314,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.00049624124424614,
|
|
"loss": 6.0704,
|
|
"mean_token_accuracy": 0.15779808908700943,
|
|
"num_tokens": 14081943.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 6.227981519699097,
|
|
"epoch": 0.6662839985870717,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004962355099255415,
|
|
"loss": 6.0206,
|
|
"mean_token_accuracy": 0.15675265938043595,
|
|
"num_tokens": 14091695.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 6.104007530212402,
|
|
"epoch": 0.666725538678912,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004962297712710653,
|
|
"loss": 5.9565,
|
|
"mean_token_accuracy": 0.16455004662275313,
|
|
"num_tokens": 14100811.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 6.2424914836883545,
|
|
"epoch": 0.6671670787707524,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004962240282828236,
|
|
"loss": 6.1233,
|
|
"mean_token_accuracy": 0.14141942113637923,
|
|
"num_tokens": 14109818.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 6.216471481323242,
|
|
"epoch": 0.6676086188625927,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000496218280960929,
|
|
"loss": 6.0572,
|
|
"mean_token_accuracy": 0.15262652635574342,
|
|
"num_tokens": 14119811.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 6.239268493652344,
|
|
"epoch": 0.6680501589544331,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004962125293054941,
|
|
"loss": 6.025,
|
|
"mean_token_accuracy": 0.15912486165761947,
|
|
"num_tokens": 14128963.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 6.2218653678894045,
|
|
"epoch": 0.6684916990462734,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004962067733166317,
|
|
"loss": 6.0639,
|
|
"mean_token_accuracy": 0.14333775714039804,
|
|
"num_tokens": 14138532.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 6.133137989044189,
|
|
"epoch": 0.6689332391381138,
|
|
"grad_norm": 10.875,
|
|
"learning_rate": 0.0004962010129944542,
|
|
"loss": 6.022,
|
|
"mean_token_accuracy": 0.15838389694690705,
|
|
"num_tokens": 14148107.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 6.217996215820312,
|
|
"epoch": 0.669374779229954,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004961952483390747,
|
|
"loss": 6.0777,
|
|
"mean_token_accuracy": 0.14390667974948884,
|
|
"num_tokens": 14158823.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 6.213542175292969,
|
|
"epoch": 0.6698163193217944,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004961894793506062,
|
|
"loss": 6.0274,
|
|
"mean_token_accuracy": 0.15735121071338654,
|
|
"num_tokens": 14168147.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 6.191353988647461,
|
|
"epoch": 0.6702578594136348,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004961837060291615,
|
|
"loss": 6.0631,
|
|
"mean_token_accuracy": 0.15633561462163925,
|
|
"num_tokens": 14177123.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 6.1563966274261475,
|
|
"epoch": 0.6706993995054751,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004961779283748538,
|
|
"loss": 6.0379,
|
|
"mean_token_accuracy": 0.152371346950531,
|
|
"num_tokens": 14186614.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 6.20333046913147,
|
|
"epoch": 0.6711409395973155,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.0004961721463877963,
|
|
"loss": 6.0552,
|
|
"mean_token_accuracy": 0.1476649187505245,
|
|
"num_tokens": 14195310.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 6.227256631851196,
|
|
"epoch": 0.6715824796891557,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.0004961663600681023,
|
|
"loss": 6.024,
|
|
"mean_token_accuracy": 0.15250837355852126,
|
|
"num_tokens": 14204321.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 6.143589925765991,
|
|
"epoch": 0.6720240197809961,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.000496160569415885,
|
|
"loss": 6.0496,
|
|
"mean_token_accuracy": 0.1539103403687477,
|
|
"num_tokens": 14213615.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 6.21385612487793,
|
|
"epoch": 0.6724655598728364,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004961547744312579,
|
|
"loss": 5.9204,
|
|
"mean_token_accuracy": 0.16402706652879714,
|
|
"num_tokens": 14222715.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 6.237391233444214,
|
|
"epoch": 0.6729070999646768,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004961489751143346,
|
|
"loss": 6.058,
|
|
"mean_token_accuracy": 0.1577908456325531,
|
|
"num_tokens": 14232117.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 6.157371234893799,
|
|
"epoch": 0.6733486400565172,
|
|
"grad_norm": 3.59375,
|
|
"learning_rate": 0.0004961431714652287,
|
|
"loss": 5.9363,
|
|
"mean_token_accuracy": 0.16300475001335143,
|
|
"num_tokens": 14240606.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 6.200923204421997,
|
|
"epoch": 0.6737901801483575,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004961373634840538,
|
|
"loss": 6.0607,
|
|
"mean_token_accuracy": 0.14696891009807586,
|
|
"num_tokens": 14249844.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 6.180020952224732,
|
|
"epoch": 0.6742317202401978,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004961315511709237,
|
|
"loss": 6.0499,
|
|
"mean_token_accuracy": 0.158081291615963,
|
|
"num_tokens": 14259231.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 6.236937952041626,
|
|
"epoch": 0.6746732603320381,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004961257345259524,
|
|
"loss": 6.0816,
|
|
"mean_token_accuracy": 0.1563194699585438,
|
|
"num_tokens": 14268508.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 6.155371046066284,
|
|
"epoch": 0.6751148004238785,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004961199135492535,
|
|
"loss": 5.9805,
|
|
"mean_token_accuracy": 0.16023090481758118,
|
|
"num_tokens": 14278057.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 6.118306589126587,
|
|
"epoch": 0.6755563405157188,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004961140882409414,
|
|
"loss": 6.0529,
|
|
"mean_token_accuracy": 0.15492414236068724,
|
|
"num_tokens": 14287225.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 6.240869092941284,
|
|
"epoch": 0.6759978806075592,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.00049610825860113,
|
|
"loss": 6.0236,
|
|
"mean_token_accuracy": 0.15528398603200913,
|
|
"num_tokens": 14296529.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 6.245958948135376,
|
|
"epoch": 0.6764394206993996,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004961024246299336,
|
|
"loss": 5.9777,
|
|
"mean_token_accuracy": 0.15906981527805328,
|
|
"num_tokens": 14305675.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 6.131229877471924,
|
|
"epoch": 0.6768809607912398,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004960965863274665,
|
|
"loss": 5.9681,
|
|
"mean_token_accuracy": 0.14951292872428895,
|
|
"num_tokens": 14313632.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 6.071325588226318,
|
|
"epoch": 0.6773225008830802,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000496090743693843,
|
|
"loss": 6.0515,
|
|
"mean_token_accuracy": 0.1581055074930191,
|
|
"num_tokens": 14323353.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 6.252487707138061,
|
|
"epoch": 0.6777640409749205,
|
|
"grad_norm": 4.59375,
|
|
"learning_rate": 0.0004960848967291775,
|
|
"loss": 6.0338,
|
|
"mean_token_accuracy": 0.15270647183060646,
|
|
"num_tokens": 14331953.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 6.303414726257325,
|
|
"epoch": 0.6782055810667609,
|
|
"grad_norm": 3.328125,
|
|
"learning_rate": 0.0004960790454335846,
|
|
"loss": 6.0904,
|
|
"mean_token_accuracy": 0.1472955822944641,
|
|
"num_tokens": 14342456.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 6.174389600753784,
|
|
"epoch": 0.6786471211586012,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000496073189807179,
|
|
"loss": 5.8712,
|
|
"mean_token_accuracy": 0.16455910801887513,
|
|
"num_tokens": 14351013.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 6.159072923660278,
|
|
"epoch": 0.6790886612504415,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 0.0004960673298500753,
|
|
"loss": 6.1372,
|
|
"mean_token_accuracy": 0.1494605213403702,
|
|
"num_tokens": 14360887.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 6.243593358993531,
|
|
"epoch": 0.6795302013422819,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004960614655623883,
|
|
"loss": 6.0558,
|
|
"mean_token_accuracy": 0.1525572694838047,
|
|
"num_tokens": 14370510.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 6.219086408615112,
|
|
"epoch": 0.6799717414341222,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000496055596944233,
|
|
"loss": 6.0523,
|
|
"mean_token_accuracy": 0.15971649289131165,
|
|
"num_tokens": 14379315.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 6.224992895126343,
|
|
"epoch": 0.6804132815259626,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004960497239957243,
|
|
"loss": 6.0278,
|
|
"mean_token_accuracy": 0.15483266711235047,
|
|
"num_tokens": 14388537.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 6.255096578598023,
|
|
"epoch": 0.6808548216178029,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004960438467169772,
|
|
"loss": 6.0771,
|
|
"mean_token_accuracy": 0.15052061378955842,
|
|
"num_tokens": 14398347.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 6.2659049987792965,
|
|
"epoch": 0.6812963617096433,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004960379651081068,
|
|
"loss": 5.9995,
|
|
"mean_token_accuracy": 0.1563209906220436,
|
|
"num_tokens": 14407304.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 6.172527694702149,
|
|
"epoch": 0.6817379018014835,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004960320791692283,
|
|
"loss": 6.012,
|
|
"mean_token_accuracy": 0.1538145899772644,
|
|
"num_tokens": 14416641.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 6.225734663009644,
|
|
"epoch": 0.6821794418933239,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004960261889004572,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.15217306613922119,
|
|
"num_tokens": 14426095.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 6.2689765930175785,
|
|
"epoch": 0.6826209819851643,
|
|
"grad_norm": 3.78125,
|
|
"learning_rate": 0.0004960202943019088,
|
|
"loss": 6.019,
|
|
"mean_token_accuracy": 0.15503756403923036,
|
|
"num_tokens": 14434563.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 6.118977451324463,
|
|
"epoch": 0.6830625220770046,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004960143953736984,
|
|
"loss": 5.9469,
|
|
"mean_token_accuracy": 0.162799833714962,
|
|
"num_tokens": 14444319.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 6.1699401378631595,
|
|
"epoch": 0.683504062168845,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004960084921159419,
|
|
"loss": 6.0117,
|
|
"mean_token_accuracy": 0.15735335201025008,
|
|
"num_tokens": 14453381.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 6.077239513397217,
|
|
"epoch": 0.6839456022606852,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 0.0004960025845287546,
|
|
"loss": 6.0127,
|
|
"mean_token_accuracy": 0.1571413978934288,
|
|
"num_tokens": 14462660.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 6.122715616226197,
|
|
"epoch": 0.6843871423525256,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004959966726122523,
|
|
"loss": 5.9396,
|
|
"mean_token_accuracy": 0.1614696577191353,
|
|
"num_tokens": 14471820.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 6.262823152542114,
|
|
"epoch": 0.6848286824443659,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.000495990756366551,
|
|
"loss": 6.0931,
|
|
"mean_token_accuracy": 0.15349064767360687,
|
|
"num_tokens": 14481663.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 6.2986386775970455,
|
|
"epoch": 0.6852702225362063,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004959848357917664,
|
|
"loss": 6.1068,
|
|
"mean_token_accuracy": 0.14945002198219298,
|
|
"num_tokens": 14491515.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 6.162067222595215,
|
|
"epoch": 0.6857117626280467,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004959789108880145,
|
|
"loss": 5.9387,
|
|
"mean_token_accuracy": 0.15316417962312698,
|
|
"num_tokens": 14500852.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 6.145100688934326,
|
|
"epoch": 0.686153302719887,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004959729816554115,
|
|
"loss": 5.9974,
|
|
"mean_token_accuracy": 0.1625947669148445,
|
|
"num_tokens": 14509771.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 6.165549850463867,
|
|
"epoch": 0.6865948428117273,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004959670480940734,
|
|
"loss": 5.9828,
|
|
"mean_token_accuracy": 0.16008143573999406,
|
|
"num_tokens": 14519377.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 6.182248115539551,
|
|
"epoch": 0.6870363829035676,
|
|
"grad_norm": 3.765625,
|
|
"learning_rate": 0.0004959611102041165,
|
|
"loss": 6.0214,
|
|
"mean_token_accuracy": 0.1562317878007889,
|
|
"num_tokens": 14528998.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 6.187045478820801,
|
|
"epoch": 0.687477922995408,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004959551679856571,
|
|
"loss": 6.0704,
|
|
"mean_token_accuracy": 0.1578943520784378,
|
|
"num_tokens": 14538153.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 6.205445671081543,
|
|
"epoch": 0.6879194630872483,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004959492214388117,
|
|
"loss": 5.9983,
|
|
"mean_token_accuracy": 0.15714774578809737,
|
|
"num_tokens": 14547631.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 6.212453413009643,
|
|
"epoch": 0.6883610031790887,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 0.0004959432705636968,
|
|
"loss": 5.938,
|
|
"mean_token_accuracy": 0.15711806267499923,
|
|
"num_tokens": 14557685.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 6.187683820724487,
|
|
"epoch": 0.688802543270929,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004959373153604287,
|
|
"loss": 6.0801,
|
|
"mean_token_accuracy": 0.15477632135152816,
|
|
"num_tokens": 14567360.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 6.106691360473633,
|
|
"epoch": 0.6892440833627693,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004959313558291243,
|
|
"loss": 5.9908,
|
|
"mean_token_accuracy": 0.15953385531902314,
|
|
"num_tokens": 14576916.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 6.156253290176392,
|
|
"epoch": 0.6896856234546097,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004959253919699004,
|
|
"loss": 5.9252,
|
|
"mean_token_accuracy": 0.16435384154319763,
|
|
"num_tokens": 14586716.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 6.230778503417969,
|
|
"epoch": 0.69012716354645,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004959194237828735,
|
|
"loss": 5.9814,
|
|
"mean_token_accuracy": 0.15456454455852509,
|
|
"num_tokens": 14595690.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 6.188361740112304,
|
|
"epoch": 0.6905687036382904,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004959134512681609,
|
|
"loss": 6.0332,
|
|
"mean_token_accuracy": 0.15250634253025055,
|
|
"num_tokens": 14605481.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 6.181294059753418,
|
|
"epoch": 0.6910102437301306,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004959074744258794,
|
|
"loss": 6.0903,
|
|
"mean_token_accuracy": 0.15014140903949738,
|
|
"num_tokens": 14615242.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 6.230496025085449,
|
|
"epoch": 0.691451783821971,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004959014932561461,
|
|
"loss": 5.9381,
|
|
"mean_token_accuracy": 0.15997153967618943,
|
|
"num_tokens": 14624343.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 6.120389366149903,
|
|
"epoch": 0.6918933239138114,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004958955077590782,
|
|
"loss": 5.9101,
|
|
"mean_token_accuracy": 0.16377195715904236,
|
|
"num_tokens": 14633014.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 6.106595802307129,
|
|
"epoch": 0.6923348640056517,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004958895179347929,
|
|
"loss": 6.0347,
|
|
"mean_token_accuracy": 0.15466284155845642,
|
|
"num_tokens": 14642796.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 6.2087477684021,
|
|
"epoch": 0.6927764040974921,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004958835237834075,
|
|
"loss": 6.0596,
|
|
"mean_token_accuracy": 0.147278793156147,
|
|
"num_tokens": 14652388.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 6.244549369812011,
|
|
"epoch": 0.6932179441893324,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004958775253050396,
|
|
"loss": 6.009,
|
|
"mean_token_accuracy": 0.15765104815363884,
|
|
"num_tokens": 14661219.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 6.1913094997406,
|
|
"epoch": 0.6936594842811727,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004958715224998066,
|
|
"loss": 6.0441,
|
|
"mean_token_accuracy": 0.15406350493431092,
|
|
"num_tokens": 14670878.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 6.172409582138061,
|
|
"epoch": 0.694101024373013,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004958655153678261,
|
|
"loss": 6.0716,
|
|
"mean_token_accuracy": 0.15391165465116502,
|
|
"num_tokens": 14680893.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 6.219511985778809,
|
|
"epoch": 0.6945425644648534,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004958595039092156,
|
|
"loss": 5.9792,
|
|
"mean_token_accuracy": 0.15655152648687362,
|
|
"num_tokens": 14689249.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 6.182665777206421,
|
|
"epoch": 0.6949841045566938,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004958534881240932,
|
|
"loss": 5.9882,
|
|
"mean_token_accuracy": 0.1581635668873787,
|
|
"num_tokens": 14698724.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 6.14864559173584,
|
|
"epoch": 0.6954256446485341,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004958474680125766,
|
|
"loss": 5.9603,
|
|
"mean_token_accuracy": 0.1531504362821579,
|
|
"num_tokens": 14707756.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 6.187934350967407,
|
|
"epoch": 0.6958671847403745,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004958414435747837,
|
|
"loss": 5.9853,
|
|
"mean_token_accuracy": 0.15955897867679597,
|
|
"num_tokens": 14717416.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 6.1442454814910885,
|
|
"epoch": 0.6963087248322147,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004958354148108324,
|
|
"loss": 6.0472,
|
|
"mean_token_accuracy": 0.15862099528312684,
|
|
"num_tokens": 14727321.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 6.0992106914520265,
|
|
"epoch": 0.6967502649240551,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.000495829381720841,
|
|
"loss": 5.9261,
|
|
"mean_token_accuracy": 0.1667322650551796,
|
|
"num_tokens": 14736298.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 6.207462453842163,
|
|
"epoch": 0.6971918050158954,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004958233443049275,
|
|
"loss": 5.9832,
|
|
"mean_token_accuracy": 0.14948185682296752,
|
|
"num_tokens": 14745893.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 6.241129732131958,
|
|
"epoch": 0.6976333451077358,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004958173025632103,
|
|
"loss": 6.0299,
|
|
"mean_token_accuracy": 0.14750152826309204,
|
|
"num_tokens": 14755277.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 6.215299606323242,
|
|
"epoch": 0.6980748851995762,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004958112564958079,
|
|
"loss": 6.1356,
|
|
"mean_token_accuracy": 0.14761845543980598,
|
|
"num_tokens": 14764369.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 6.110063552856445,
|
|
"epoch": 0.6985164252914164,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004958052061028385,
|
|
"loss": 5.9721,
|
|
"mean_token_accuracy": 0.16243066340684892,
|
|
"num_tokens": 14772970.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 6.167850589752197,
|
|
"epoch": 0.6989579653832568,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004957991513844205,
|
|
"loss": 6.0378,
|
|
"mean_token_accuracy": 0.15475951582193376,
|
|
"num_tokens": 14782862.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 6.272579956054687,
|
|
"epoch": 0.6993995054750971,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004957930923406729,
|
|
"loss": 6.0498,
|
|
"mean_token_accuracy": 0.1560375764966011,
|
|
"num_tokens": 14792042.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 6.2410767555236815,
|
|
"epoch": 0.6998410455669375,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004957870289717142,
|
|
"loss": 6.0025,
|
|
"mean_token_accuracy": 0.15189553946256637,
|
|
"num_tokens": 14801032.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 6.1055858612060545,
|
|
"epoch": 0.7002825856587778,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004957809612776631,
|
|
"loss": 5.9942,
|
|
"mean_token_accuracy": 0.15394028574228286,
|
|
"num_tokens": 14810594.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 6.133386659622192,
|
|
"epoch": 0.7007241257506182,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004957748892586384,
|
|
"loss": 6.0889,
|
|
"mean_token_accuracy": 0.15561799257993697,
|
|
"num_tokens": 14820570.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 6.063908386230469,
|
|
"epoch": 0.7011656658424585,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004957688129147594,
|
|
"loss": 5.8994,
|
|
"mean_token_accuracy": 0.16970330625772476,
|
|
"num_tokens": 14830078.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 6.132439613342285,
|
|
"epoch": 0.7016072059342988,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004957627322461448,
|
|
"loss": 5.9721,
|
|
"mean_token_accuracy": 0.15395658761262893,
|
|
"num_tokens": 14839974.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 6.20572566986084,
|
|
"epoch": 0.7020487460261392,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004957566472529139,
|
|
"loss": 6.0807,
|
|
"mean_token_accuracy": 0.1480936288833618,
|
|
"num_tokens": 14849551.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 6.222087621688843,
|
|
"epoch": 0.7024902861179795,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004957505579351858,
|
|
"loss": 6.007,
|
|
"mean_token_accuracy": 0.1552036628127098,
|
|
"num_tokens": 14859011.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 6.159627532958984,
|
|
"epoch": 0.7029318262098199,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004957444642930798,
|
|
"loss": 5.9619,
|
|
"mean_token_accuracy": 0.15881793648004533,
|
|
"num_tokens": 14867948.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 6.186864185333252,
|
|
"epoch": 0.7033733663016601,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004957383663267152,
|
|
"loss": 6.0275,
|
|
"mean_token_accuracy": 0.15494029894471167,
|
|
"num_tokens": 14877233.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 6.2205883979797365,
|
|
"epoch": 0.7038149063935005,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004957322640362118,
|
|
"loss": 6.0418,
|
|
"mean_token_accuracy": 0.1551240026950836,
|
|
"num_tokens": 14887439.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 6.327660989761353,
|
|
"epoch": 0.7042564464853409,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004957261574216887,
|
|
"loss": 6.1012,
|
|
"mean_token_accuracy": 0.15123100578784943,
|
|
"num_tokens": 14897064.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 6.2104428768157955,
|
|
"epoch": 0.7046979865771812,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004957200464832656,
|
|
"loss": 6.0699,
|
|
"mean_token_accuracy": 0.14506227374076844,
|
|
"num_tokens": 14907054.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 6.188334894180298,
|
|
"epoch": 0.7051395266690216,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004957139312210626,
|
|
"loss": 6.0287,
|
|
"mean_token_accuracy": 0.15283627659082413,
|
|
"num_tokens": 14916969.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 6.236026954650879,
|
|
"epoch": 0.7055810667608619,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.000495707811635199,
|
|
"loss": 6.0549,
|
|
"mean_token_accuracy": 0.1538621038198471,
|
|
"num_tokens": 14926404.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 6.2148487091064455,
|
|
"epoch": 0.7060226068527022,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004957016877257949,
|
|
"loss": 6.0189,
|
|
"mean_token_accuracy": 0.15292533934116365,
|
|
"num_tokens": 14935693.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 6.207205963134766,
|
|
"epoch": 0.7064641469445425,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004956955594929704,
|
|
"loss": 5.9647,
|
|
"mean_token_accuracy": 0.1577726759016514,
|
|
"num_tokens": 14945147.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 6.177611207962036,
|
|
"epoch": 0.7069056870363829,
|
|
"grad_norm": 3.734375,
|
|
"learning_rate": 0.0004956894269368454,
|
|
"loss": 6.0077,
|
|
"mean_token_accuracy": 0.15413163900375365,
|
|
"num_tokens": 14954022.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 6.099345397949219,
|
|
"epoch": 0.7073472271282233,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004956832900575399,
|
|
"loss": 6.0193,
|
|
"mean_token_accuracy": 0.15245394557714462,
|
|
"num_tokens": 14962977.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 6.157639408111573,
|
|
"epoch": 0.7077887672200636,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004956771488551742,
|
|
"loss": 6.0603,
|
|
"mean_token_accuracy": 0.15071365088224412,
|
|
"num_tokens": 14973420.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 6.239572954177857,
|
|
"epoch": 0.708230307311904,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004956710033298689,
|
|
"loss": 6.0173,
|
|
"mean_token_accuracy": 0.15658407807350158,
|
|
"num_tokens": 14981762.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 6.302951097488403,
|
|
"epoch": 0.7086718474037442,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.000495664853481744,
|
|
"loss": 6.0903,
|
|
"mean_token_accuracy": 0.14736679941415787,
|
|
"num_tokens": 14991449.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 6.2615893363952635,
|
|
"epoch": 0.7091133874955846,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004956586993109201,
|
|
"loss": 6.0125,
|
|
"mean_token_accuracy": 0.15616520941257478,
|
|
"num_tokens": 15000802.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 6.105866622924805,
|
|
"epoch": 0.7095549275874249,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004956525408175179,
|
|
"loss": 6.0313,
|
|
"mean_token_accuracy": 0.1552100345492363,
|
|
"num_tokens": 15010580.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 6.132424592971802,
|
|
"epoch": 0.7099964676792653,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004956463780016578,
|
|
"loss": 6.0584,
|
|
"mean_token_accuracy": 0.14935311377048494,
|
|
"num_tokens": 15020059.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 6.241670608520508,
|
|
"epoch": 0.7104380077711057,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004956402108634607,
|
|
"loss": 6.0088,
|
|
"mean_token_accuracy": 0.1565178796648979,
|
|
"num_tokens": 15030268.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 6.200330638885498,
|
|
"epoch": 0.7108795478629459,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004956340394030473,
|
|
"loss": 5.9875,
|
|
"mean_token_accuracy": 0.15514944046735762,
|
|
"num_tokens": 15038865.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 6.282695722579956,
|
|
"epoch": 0.7113210879547863,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004956278636205386,
|
|
"loss": 6.1354,
|
|
"mean_token_accuracy": 0.1421603739261627,
|
|
"num_tokens": 15048427.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 6.177859306335449,
|
|
"epoch": 0.7117626280466266,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004956216835160556,
|
|
"loss": 5.9996,
|
|
"mean_token_accuracy": 0.15979120433330535,
|
|
"num_tokens": 15057366.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 6.217433261871338,
|
|
"epoch": 0.712204168138467,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004956154990897191,
|
|
"loss": 6.0384,
|
|
"mean_token_accuracy": 0.15537583380937575,
|
|
"num_tokens": 15067098.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 6.192469930648803,
|
|
"epoch": 0.7126457082303073,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004956093103416505,
|
|
"loss": 6.0311,
|
|
"mean_token_accuracy": 0.15546699613332748,
|
|
"num_tokens": 15075734.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 6.2102759838104244,
|
|
"epoch": 0.7130872483221476,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004956031172719711,
|
|
"loss": 6.073,
|
|
"mean_token_accuracy": 0.1536272294819355,
|
|
"num_tokens": 15084625.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 6.101073455810547,
|
|
"epoch": 0.713528788413988,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004955969198808021,
|
|
"loss": 5.8924,
|
|
"mean_token_accuracy": 0.1668921247124672,
|
|
"num_tokens": 15093256.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 6.102929306030274,
|
|
"epoch": 0.7139703285058283,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004955907181682648,
|
|
"loss": 5.9618,
|
|
"mean_token_accuracy": 0.16315532177686692,
|
|
"num_tokens": 15103175.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 6.144030427932739,
|
|
"epoch": 0.7144118685976687,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004955845121344809,
|
|
"loss": 6.0469,
|
|
"mean_token_accuracy": 0.1541796073317528,
|
|
"num_tokens": 15112789.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 6.204605007171631,
|
|
"epoch": 0.714853408689509,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004955783017795717,
|
|
"loss": 6.0605,
|
|
"mean_token_accuracy": 0.15732798725366592,
|
|
"num_tokens": 15121869.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 6.189707899093628,
|
|
"epoch": 0.7152949487813494,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.000495572087103659,
|
|
"loss": 5.9738,
|
|
"mean_token_accuracy": 0.15560177564620972,
|
|
"num_tokens": 15131441.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 6.137331628799439,
|
|
"epoch": 0.7157364888731896,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004955658681068647,
|
|
"loss": 6.0193,
|
|
"mean_token_accuracy": 0.15403990298509598,
|
|
"num_tokens": 15140641.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 6.19461874961853,
|
|
"epoch": 0.71617802896503,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004955596447893105,
|
|
"loss": 6.0101,
|
|
"mean_token_accuracy": 0.15569014549255372,
|
|
"num_tokens": 15150073.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 6.098717784881591,
|
|
"epoch": 0.7166195690568704,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004955534171511181,
|
|
"loss": 5.7712,
|
|
"mean_token_accuracy": 0.17266993075609208,
|
|
"num_tokens": 15159879.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 6.118933868408203,
|
|
"epoch": 0.7170611091487107,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00049554718519241,
|
|
"loss": 5.9694,
|
|
"mean_token_accuracy": 0.1589986950159073,
|
|
"num_tokens": 15168316.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 6.1255974769592285,
|
|
"epoch": 0.7175026492405511,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004955409489133078,
|
|
"loss": 6.0004,
|
|
"mean_token_accuracy": 0.15388742089271545,
|
|
"num_tokens": 15176700.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 6.20945520401001,
|
|
"epoch": 0.7179441893323913,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004955347083139338,
|
|
"loss": 6.0261,
|
|
"mean_token_accuracy": 0.1599735736846924,
|
|
"num_tokens": 15185997.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 6.116842317581177,
|
|
"epoch": 0.7183857294242317,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 0.0004955284633944104,
|
|
"loss": 6.0101,
|
|
"mean_token_accuracy": 0.15412014573812485,
|
|
"num_tokens": 15195341.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 6.185818815231324,
|
|
"epoch": 0.718827269516072,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004955222141548597,
|
|
"loss": 6.0459,
|
|
"mean_token_accuracy": 0.15609263628721237,
|
|
"num_tokens": 15205501.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 6.136814928054809,
|
|
"epoch": 0.7192688096079124,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004955159605954043,
|
|
"loss": 5.9916,
|
|
"mean_token_accuracy": 0.15846392139792442,
|
|
"num_tokens": 15214778.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 6.288878870010376,
|
|
"epoch": 0.7197103496997528,
|
|
"grad_norm": 5.03125,
|
|
"learning_rate": 0.0004955097027161666,
|
|
"loss": 6.0159,
|
|
"mean_token_accuracy": 0.1611801378428936,
|
|
"num_tokens": 15224201.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 6.287253952026367,
|
|
"epoch": 0.7201518897915931,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004955034405172693,
|
|
"loss": 5.9812,
|
|
"mean_token_accuracy": 0.16084180772304535,
|
|
"num_tokens": 15233472.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 6.245111751556396,
|
|
"epoch": 0.7205934298834334,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.000495497173998835,
|
|
"loss": 6.0336,
|
|
"mean_token_accuracy": 0.15393038243055343,
|
|
"num_tokens": 15242323.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 6.148213624954224,
|
|
"epoch": 0.7210349699752737,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004954909031609864,
|
|
"loss": 6.0538,
|
|
"mean_token_accuracy": 0.15215684324502946,
|
|
"num_tokens": 15252952.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 6.181010341644287,
|
|
"epoch": 0.7214765100671141,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004954846280038465,
|
|
"loss": 6.0217,
|
|
"mean_token_accuracy": 0.15112778842449187,
|
|
"num_tokens": 15261815.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 6.211622905731201,
|
|
"epoch": 0.7219180501589544,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004954783485275381,
|
|
"loss": 6.0724,
|
|
"mean_token_accuracy": 0.1537321016192436,
|
|
"num_tokens": 15271026.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 6.138492250442505,
|
|
"epoch": 0.7223595902507948,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.0004954720647321843,
|
|
"loss": 5.9284,
|
|
"mean_token_accuracy": 0.16433208882808686,
|
|
"num_tokens": 15279795.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 6.1683433055877686,
|
|
"epoch": 0.7228011303426352,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004954657766179081,
|
|
"loss": 6.0374,
|
|
"mean_token_accuracy": 0.151440542191267,
|
|
"num_tokens": 15289113.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 6.117907285690308,
|
|
"epoch": 0.7232426704344754,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004954594841848327,
|
|
"loss": 5.9016,
|
|
"mean_token_accuracy": 0.16442391872406006,
|
|
"num_tokens": 15298271.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 6.252900695800781,
|
|
"epoch": 0.7236842105263158,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004954531874330814,
|
|
"loss": 5.9948,
|
|
"mean_token_accuracy": 0.1522049143910408,
|
|
"num_tokens": 15307677.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 6.165901708602905,
|
|
"epoch": 0.7241257506181561,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004954468863627774,
|
|
"loss": 5.9982,
|
|
"mean_token_accuracy": 0.15651184022426606,
|
|
"num_tokens": 15316637.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 6.1402503490448,
|
|
"epoch": 0.7245672907099965,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004954405809740445,
|
|
"loss": 5.9851,
|
|
"mean_token_accuracy": 0.15237015783786773,
|
|
"num_tokens": 15325221.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 6.182305383682251,
|
|
"epoch": 0.7250088308018368,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004954342712670058,
|
|
"loss": 6.0363,
|
|
"mean_token_accuracy": 0.15432765632867812,
|
|
"num_tokens": 15335877.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 6.196657276153564,
|
|
"epoch": 0.7254503708936771,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004954279572417852,
|
|
"loss": 6.0317,
|
|
"mean_token_accuracy": 0.15272038280963898,
|
|
"num_tokens": 15345096.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 6.151156330108643,
|
|
"epoch": 0.7258919109855175,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004954216388985063,
|
|
"loss": 5.8724,
|
|
"mean_token_accuracy": 0.16933880299329757,
|
|
"num_tokens": 15353785.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 6.138664054870605,
|
|
"epoch": 0.7263334510773578,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004954153162372928,
|
|
"loss": 5.9699,
|
|
"mean_token_accuracy": 0.15810664743185043,
|
|
"num_tokens": 15362761.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 6.1775671482086185,
|
|
"epoch": 0.7267749911691982,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004954089892582686,
|
|
"loss": 5.9502,
|
|
"mean_token_accuracy": 0.15694193840026854,
|
|
"num_tokens": 15371951.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 6.154006862640381,
|
|
"epoch": 0.7272165312610385,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004954026579615577,
|
|
"loss": 6.035,
|
|
"mean_token_accuracy": 0.15585743859410287,
|
|
"num_tokens": 15380277.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 6.1166462898254395,
|
|
"epoch": 0.7276580713528789,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004953963223472841,
|
|
"loss": 6.0501,
|
|
"mean_token_accuracy": 0.152119879424572,
|
|
"num_tokens": 15390951.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 6.230410432815551,
|
|
"epoch": 0.7280996114447191,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004953899824155718,
|
|
"loss": 5.9975,
|
|
"mean_token_accuracy": 0.1529814049601555,
|
|
"num_tokens": 15399394.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 6.199048280715942,
|
|
"epoch": 0.7285411515365595,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004953836381665452,
|
|
"loss": 5.9384,
|
|
"mean_token_accuracy": 0.16169310212135315,
|
|
"num_tokens": 15408644.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 6.229496145248413,
|
|
"epoch": 0.7289826916283999,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004953772896003284,
|
|
"loss": 6.0229,
|
|
"mean_token_accuracy": 0.15219994485378266,
|
|
"num_tokens": 15417398.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 6.18380217552185,
|
|
"epoch": 0.7294242317202402,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004953709367170458,
|
|
"loss": 6.0979,
|
|
"mean_token_accuracy": 0.14707581102848052,
|
|
"num_tokens": 15426532.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 6.205737209320068,
|
|
"epoch": 0.7298657718120806,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.000495364579516822,
|
|
"loss": 6.087,
|
|
"mean_token_accuracy": 0.15145862251520156,
|
|
"num_tokens": 15436371.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 6.250464200973511,
|
|
"epoch": 0.7303073119039208,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004953582179997813,
|
|
"loss": 6.1247,
|
|
"mean_token_accuracy": 0.14918783605098723,
|
|
"num_tokens": 15446600.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 6.218456268310547,
|
|
"epoch": 0.7307488519957612,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004953518521660484,
|
|
"loss": 5.9647,
|
|
"mean_token_accuracy": 0.1545114502310753,
|
|
"num_tokens": 15455547.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 6.165512323379517,
|
|
"epoch": 0.7311903920876015,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004953454820157481,
|
|
"loss": 6.0138,
|
|
"mean_token_accuracy": 0.153198678791523,
|
|
"num_tokens": 15464543.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 6.280844497680664,
|
|
"epoch": 0.7316319321794419,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004953391075490051,
|
|
"loss": 6.1253,
|
|
"mean_token_accuracy": 0.14796603918075563,
|
|
"num_tokens": 15473626.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 6.2266065120697025,
|
|
"epoch": 0.7320734722712823,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004953327287659444,
|
|
"loss": 6.0639,
|
|
"mean_token_accuracy": 0.15035302489995955,
|
|
"num_tokens": 15484164.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 6.316344976425171,
|
|
"epoch": 0.7325150123631226,
|
|
"grad_norm": 3.546875,
|
|
"learning_rate": 0.0004953263456666907,
|
|
"loss": 6.0694,
|
|
"mean_token_accuracy": 0.14661551713943483,
|
|
"num_tokens": 15493718.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 6.210640335083008,
|
|
"epoch": 0.7329565524549629,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004953199582513693,
|
|
"loss": 5.9896,
|
|
"mean_token_accuracy": 0.15981052368879317,
|
|
"num_tokens": 15503339.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 6.206534719467163,
|
|
"epoch": 0.7333980925468032,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004953135665201052,
|
|
"loss": 5.9813,
|
|
"mean_token_accuracy": 0.1627606123685837,
|
|
"num_tokens": 15513314.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 6.265380430221557,
|
|
"epoch": 0.7338396326386436,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004953071704730237,
|
|
"loss": 6.0648,
|
|
"mean_token_accuracy": 0.15312278568744658,
|
|
"num_tokens": 15522943.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 6.231940984725952,
|
|
"epoch": 0.7342811727304839,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004953007701102499,
|
|
"loss": 6.0337,
|
|
"mean_token_accuracy": 0.15085222870111464,
|
|
"num_tokens": 15531975.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 6.169845247268677,
|
|
"epoch": 0.7347227128223243,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004952943654319094,
|
|
"loss": 5.9786,
|
|
"mean_token_accuracy": 0.15557436197996138,
|
|
"num_tokens": 15541139.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 6.169338655471802,
|
|
"epoch": 0.7351642529141647,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004952879564381276,
|
|
"loss": 6.0413,
|
|
"mean_token_accuracy": 0.15694883614778518,
|
|
"num_tokens": 15550604.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 6.152047348022461,
|
|
"epoch": 0.7356057930060049,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004952815431290298,
|
|
"loss": 5.9537,
|
|
"mean_token_accuracy": 0.1595415860414505,
|
|
"num_tokens": 15558995.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 6.275175952911377,
|
|
"epoch": 0.7360473330978453,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.000495275125504742,
|
|
"loss": 6.0278,
|
|
"mean_token_accuracy": 0.15613498240709306,
|
|
"num_tokens": 15568229.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 6.14049506187439,
|
|
"epoch": 0.7364888731896856,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004952687035653899,
|
|
"loss": 5.9771,
|
|
"mean_token_accuracy": 0.15214631259441375,
|
|
"num_tokens": 15577042.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 6.137394666671753,
|
|
"epoch": 0.736930413281526,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004952622773110989,
|
|
"loss": 5.9003,
|
|
"mean_token_accuracy": 0.16799579858779906,
|
|
"num_tokens": 15585825.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 6.182384014129639,
|
|
"epoch": 0.7373719533733663,
|
|
"grad_norm": 3.71875,
|
|
"learning_rate": 0.0004952558467419953,
|
|
"loss": 5.9035,
|
|
"mean_token_accuracy": 0.16247234046459197,
|
|
"num_tokens": 15595486.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 6.171746444702149,
|
|
"epoch": 0.7378134934652066,
|
|
"grad_norm": 6.0,
|
|
"learning_rate": 0.000495249411858205,
|
|
"loss": 5.9618,
|
|
"mean_token_accuracy": 0.14454634860157967,
|
|
"num_tokens": 15605312.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 6.100625085830688,
|
|
"epoch": 0.738255033557047,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004952429726598538,
|
|
"loss": 5.9682,
|
|
"mean_token_accuracy": 0.1587691068649292,
|
|
"num_tokens": 15615185.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 6.209043741226196,
|
|
"epoch": 0.7386965736488873,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004952365291470682,
|
|
"loss": 6.0665,
|
|
"mean_token_accuracy": 0.15307985991239548,
|
|
"num_tokens": 15625259.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 6.267195034027099,
|
|
"epoch": 0.7391381137407277,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004952300813199742,
|
|
"loss": 6.0527,
|
|
"mean_token_accuracy": 0.15336710289120675,
|
|
"num_tokens": 15635040.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 6.244267320632934,
|
|
"epoch": 0.739579653832568,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004952236291786981,
|
|
"loss": 6.0663,
|
|
"mean_token_accuracy": 0.15102097690105437,
|
|
"num_tokens": 15644996.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 6.1261107444763185,
|
|
"epoch": 0.7400211939244083,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004952171727233665,
|
|
"loss": 5.9584,
|
|
"mean_token_accuracy": 0.15442091524600982,
|
|
"num_tokens": 15654598.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 6.2025392055511475,
|
|
"epoch": 0.7404627340162486,
|
|
"grad_norm": 3.09375,
|
|
"learning_rate": 0.0004952107119541055,
|
|
"loss": 5.9911,
|
|
"mean_token_accuracy": 0.1527467727661133,
|
|
"num_tokens": 15664213.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 6.142297172546387,
|
|
"epoch": 0.740904274108089,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004952042468710421,
|
|
"loss": 6.0431,
|
|
"mean_token_accuracy": 0.15506284832954406,
|
|
"num_tokens": 15673595.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 6.190773963928223,
|
|
"epoch": 0.7413458141999294,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004951977774743027,
|
|
"loss": 6.1065,
|
|
"mean_token_accuracy": 0.14471191465854644,
|
|
"num_tokens": 15682753.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 6.180733728408813,
|
|
"epoch": 0.7417873542917697,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004951913037640139,
|
|
"loss": 5.9113,
|
|
"mean_token_accuracy": 0.16720414012670518,
|
|
"num_tokens": 15691508.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 6.121179008483887,
|
|
"epoch": 0.7422288943836101,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004951848257403029,
|
|
"loss": 5.9028,
|
|
"mean_token_accuracy": 0.15747786164283753,
|
|
"num_tokens": 15701110.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 6.08272123336792,
|
|
"epoch": 0.7426704344754503,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004951783434032963,
|
|
"loss": 5.8728,
|
|
"mean_token_accuracy": 0.164331416785717,
|
|
"num_tokens": 15710565.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 6.2023955345153805,
|
|
"epoch": 0.7431119745672907,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004951718567531211,
|
|
"loss": 6.0323,
|
|
"mean_token_accuracy": 0.15471521392464638,
|
|
"num_tokens": 15718364.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 6.212370777130127,
|
|
"epoch": 0.743553514659131,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004951653657899045,
|
|
"loss": 6.1132,
|
|
"mean_token_accuracy": 0.14646557569503785,
|
|
"num_tokens": 15729127.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 6.194227457046509,
|
|
"epoch": 0.7439950547509714,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004951588705137737,
|
|
"loss": 6.0708,
|
|
"mean_token_accuracy": 0.1511780470609665,
|
|
"num_tokens": 15738491.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 6.251719379425049,
|
|
"epoch": 0.7444365948428118,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004951523709248557,
|
|
"loss": 5.9506,
|
|
"mean_token_accuracy": 0.1640294149518013,
|
|
"num_tokens": 15748346.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 6.168902730941772,
|
|
"epoch": 0.744878134934652,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.000495145867023278,
|
|
"loss": 5.9772,
|
|
"mean_token_accuracy": 0.16299238950014114,
|
|
"num_tokens": 15757242.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 6.272220706939697,
|
|
"epoch": 0.7453196750264924,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.000495139358809168,
|
|
"loss": 6.0206,
|
|
"mean_token_accuracy": 0.15597838014364243,
|
|
"num_tokens": 15767236.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 6.231273603439331,
|
|
"epoch": 0.7457612151183327,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004951328462826532,
|
|
"loss": 6.0656,
|
|
"mean_token_accuracy": 0.14785979986190795,
|
|
"num_tokens": 15776977.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 6.1693408489227295,
|
|
"epoch": 0.7462027552101731,
|
|
"grad_norm": 2.828125,
|
|
"learning_rate": 0.0004951263294438611,
|
|
"loss": 5.9554,
|
|
"mean_token_accuracy": 0.15859422236680984,
|
|
"num_tokens": 15787333.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 6.130995225906372,
|
|
"epoch": 0.7466442953020134,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004951198082929194,
|
|
"loss": 5.8685,
|
|
"mean_token_accuracy": 0.16755239814519882,
|
|
"num_tokens": 15794773.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 6.08733286857605,
|
|
"epoch": 0.7470858353938538,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.0004951132828299558,
|
|
"loss": 5.9636,
|
|
"mean_token_accuracy": 0.16573742181062698,
|
|
"num_tokens": 15803803.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 6.172519779205322,
|
|
"epoch": 0.7475273754856941,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004951067530550982,
|
|
"loss": 6.0095,
|
|
"mean_token_accuracy": 0.15405793190002443,
|
|
"num_tokens": 15814021.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 6.209099340438843,
|
|
"epoch": 0.7479689155775344,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004951002189684745,
|
|
"loss": 5.9937,
|
|
"mean_token_accuracy": 0.15232694447040557,
|
|
"num_tokens": 15822974.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 6.133933877944946,
|
|
"epoch": 0.7484104556693748,
|
|
"grad_norm": 5.0,
|
|
"learning_rate": 0.0004950936805702127,
|
|
"loss": 5.8909,
|
|
"mean_token_accuracy": 0.16856021732091903,
|
|
"num_tokens": 15832202.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 6.188068151473999,
|
|
"epoch": 0.7488519957612151,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004950871378604409,
|
|
"loss": 6.007,
|
|
"mean_token_accuracy": 0.16055386513471603,
|
|
"num_tokens": 15841223.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 6.148092460632324,
|
|
"epoch": 0.7492935358530555,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.0004950805908392872,
|
|
"loss": 5.9876,
|
|
"mean_token_accuracy": 0.15736652314662933,
|
|
"num_tokens": 15850260.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 6.113380336761475,
|
|
"epoch": 0.7497350759448957,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.0004950740395068799,
|
|
"loss": 6.0402,
|
|
"mean_token_accuracy": 0.15413001626729966,
|
|
"num_tokens": 15859780.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 6.19255747795105,
|
|
"epoch": 0.7501766160367361,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004950674838633473,
|
|
"loss": 5.9852,
|
|
"mean_token_accuracy": 0.15405904054641723,
|
|
"num_tokens": 15868331.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 6.168982124328613,
|
|
"epoch": 0.7506181561285765,
|
|
"grad_norm": 2.953125,
|
|
"learning_rate": 0.0004950609239088178,
|
|
"loss": 6.0518,
|
|
"mean_token_accuracy": 0.1502481520175934,
|
|
"num_tokens": 15877359.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 6.1584141731262205,
|
|
"epoch": 0.7510596962204168,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.0004950543596434201,
|
|
"loss": 5.9389,
|
|
"mean_token_accuracy": 0.1636333480477333,
|
|
"num_tokens": 15886976.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 6.078968238830567,
|
|
"epoch": 0.7515012363122572,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004950477910672825,
|
|
"loss": 6.0163,
|
|
"mean_token_accuracy": 0.15548164248466492,
|
|
"num_tokens": 15896139.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 6.216708183288574,
|
|
"epoch": 0.7519427764040975,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.000495041218180534,
|
|
"loss": 5.9989,
|
|
"mean_token_accuracy": 0.16013481318950654,
|
|
"num_tokens": 15904672.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 6.133269357681274,
|
|
"epoch": 0.7523843164959378,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.000495034640983303,
|
|
"loss": 5.8667,
|
|
"mean_token_accuracy": 0.16843710839748383,
|
|
"num_tokens": 15912716.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 6.134620475769043,
|
|
"epoch": 0.7528258565877781,
|
|
"grad_norm": 5.5,
|
|
"learning_rate": 0.0004950280594757186,
|
|
"loss": 5.9746,
|
|
"mean_token_accuracy": 0.15392025411128998,
|
|
"num_tokens": 15921974.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 6.210237741470337,
|
|
"epoch": 0.7532673966796185,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004950214736579097,
|
|
"loss": 5.9908,
|
|
"mean_token_accuracy": 0.15580060631036757,
|
|
"num_tokens": 15930859.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 6.125013971328736,
|
|
"epoch": 0.7537089367714589,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004950148835300051,
|
|
"loss": 5.9076,
|
|
"mean_token_accuracy": 0.16171641200780867,
|
|
"num_tokens": 15940052.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 6.11407995223999,
|
|
"epoch": 0.7541504768632992,
|
|
"grad_norm": 2.546875,
|
|
"learning_rate": 0.0004950082890921341,
|
|
"loss": 5.9867,
|
|
"mean_token_accuracy": 0.1578494466841221,
|
|
"num_tokens": 15948422.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 6.157030868530273,
|
|
"epoch": 0.7545920169551396,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004950016903444261,
|
|
"loss": 6.0618,
|
|
"mean_token_accuracy": 0.15601774156093598,
|
|
"num_tokens": 15957433.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 6.269704675674438,
|
|
"epoch": 0.7550335570469798,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004949950872870099,
|
|
"loss": 5.988,
|
|
"mean_token_accuracy": 0.1615738093852997,
|
|
"num_tokens": 15966542.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 6.254258298873902,
|
|
"epoch": 0.7554750971388202,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.000494988479920015,
|
|
"loss": 6.1397,
|
|
"mean_token_accuracy": 0.1473035305738449,
|
|
"num_tokens": 15977067.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 6.227912759780883,
|
|
"epoch": 0.7559166372306605,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.000494981868243571,
|
|
"loss": 6.0394,
|
|
"mean_token_accuracy": 0.15444127321243287,
|
|
"num_tokens": 15986502.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 6.279629898071289,
|
|
"epoch": 0.7563581773225009,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004949752522578073,
|
|
"loss": 6.0964,
|
|
"mean_token_accuracy": 0.1465997241437435,
|
|
"num_tokens": 15996788.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 6.169799137115478,
|
|
"epoch": 0.7567997174143413,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004949686319628535,
|
|
"loss": 5.9954,
|
|
"mean_token_accuracy": 0.1538490191102028,
|
|
"num_tokens": 16007212.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 6.133602476119995,
|
|
"epoch": 0.7572412575061815,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004949620073588394,
|
|
"loss": 6.0182,
|
|
"mean_token_accuracy": 0.15578313320875167,
|
|
"num_tokens": 16017000.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 6.281605195999146,
|
|
"epoch": 0.7576827975980219,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004949553784458945,
|
|
"loss": 6.1126,
|
|
"mean_token_accuracy": 0.14807434976100922,
|
|
"num_tokens": 16026647.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 6.1851507186889645,
|
|
"epoch": 0.7581243376898622,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004949487452241489,
|
|
"loss": 5.844,
|
|
"mean_token_accuracy": 0.1705327793955803,
|
|
"num_tokens": 16034773.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 6.19845027923584,
|
|
"epoch": 0.7585658777817026,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004949421076937325,
|
|
"loss": 5.9807,
|
|
"mean_token_accuracy": 0.15956246256828308,
|
|
"num_tokens": 16043787.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 6.062042713165283,
|
|
"epoch": 0.7590074178735429,
|
|
"grad_norm": 11.8125,
|
|
"learning_rate": 0.0004949354658547753,
|
|
"loss": 5.9444,
|
|
"mean_token_accuracy": 0.1681981384754181,
|
|
"num_tokens": 16053130.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 6.098703050613404,
|
|
"epoch": 0.7594489579653833,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004949288197074074,
|
|
"loss": 6.1009,
|
|
"mean_token_accuracy": 0.15323710292577744,
|
|
"num_tokens": 16062529.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 6.109501838684082,
|
|
"epoch": 0.7598904980572236,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004949221692517589,
|
|
"loss": 5.96,
|
|
"mean_token_accuracy": 0.14846655800938607,
|
|
"num_tokens": 16071932.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 6.240110111236572,
|
|
"epoch": 0.7603320381490639,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004949155144879602,
|
|
"loss": 5.9511,
|
|
"mean_token_accuracy": 0.15825047194957734,
|
|
"num_tokens": 16081077.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 6.118295192718506,
|
|
"epoch": 0.7607735782409043,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004949088554161417,
|
|
"loss": 5.8764,
|
|
"mean_token_accuracy": 0.1641096889972687,
|
|
"num_tokens": 16089725.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 6.051836967468262,
|
|
"epoch": 0.7612151183327446,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004949021920364339,
|
|
"loss": 6.045,
|
|
"mean_token_accuracy": 0.1546042039990425,
|
|
"num_tokens": 16099362.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 6.206489562988281,
|
|
"epoch": 0.761656658424585,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004948955243489671,
|
|
"loss": 6.0685,
|
|
"mean_token_accuracy": 0.15602654963731766,
|
|
"num_tokens": 16108746.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 6.284847402572632,
|
|
"epoch": 0.7620981985164252,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004948888523538721,
|
|
"loss": 6.1846,
|
|
"mean_token_accuracy": 0.14481205195188523,
|
|
"num_tokens": 16118902.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 6.125094079971314,
|
|
"epoch": 0.7625397386082656,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004948821760512795,
|
|
"loss": 5.9464,
|
|
"mean_token_accuracy": 0.15824127048254014,
|
|
"num_tokens": 16127781.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 6.186475229263306,
|
|
"epoch": 0.762981278700106,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004948754954413201,
|
|
"loss": 5.9137,
|
|
"mean_token_accuracy": 0.16810621470212936,
|
|
"num_tokens": 16136004.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 6.171486759185791,
|
|
"epoch": 0.7634228187919463,
|
|
"grad_norm": 3.109375,
|
|
"learning_rate": 0.0004948688105241248,
|
|
"loss": 5.9864,
|
|
"mean_token_accuracy": 0.16084740161895753,
|
|
"num_tokens": 16145023.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 6.142913198471069,
|
|
"epoch": 0.7638643588837867,
|
|
"grad_norm": 6.25,
|
|
"learning_rate": 0.0004948621212998246,
|
|
"loss": 6.0319,
|
|
"mean_token_accuracy": 0.15112509354948997,
|
|
"num_tokens": 16154242.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 6.192302179336548,
|
|
"epoch": 0.764305898975627,
|
|
"grad_norm": 2.9375,
|
|
"learning_rate": 0.0004948554277685505,
|
|
"loss": 6.013,
|
|
"mean_token_accuracy": 0.1505245789885521,
|
|
"num_tokens": 16163252.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 6.232281637191773,
|
|
"epoch": 0.7647474390674673,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 0.0004948487299304335,
|
|
"loss": 5.9173,
|
|
"mean_token_accuracy": 0.16507309079170226,
|
|
"num_tokens": 16171363.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 6.186713075637817,
|
|
"epoch": 0.7651889791593076,
|
|
"grad_norm": 6.53125,
|
|
"learning_rate": 0.000494842027785605,
|
|
"loss": 6.1024,
|
|
"mean_token_accuracy": 0.15555563420057297,
|
|
"num_tokens": 16181234.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 6.204009485244751,
|
|
"epoch": 0.765630519251148,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004948353213341961,
|
|
"loss": 6.0111,
|
|
"mean_token_accuracy": 0.15684083476662636,
|
|
"num_tokens": 16189420.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 6.2717845916748045,
|
|
"epoch": 0.7660720593429884,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.0004948286105763385,
|
|
"loss": 6.1761,
|
|
"mean_token_accuracy": 0.14456427991390228,
|
|
"num_tokens": 16199202.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 6.234415864944458,
|
|
"epoch": 0.7665135994348287,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004948218955121632,
|
|
"loss": 5.9953,
|
|
"mean_token_accuracy": 0.1586536779999733,
|
|
"num_tokens": 16208481.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 6.1947956562042235,
|
|
"epoch": 0.766955139526669,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.0004948151761418021,
|
|
"loss": 6.0516,
|
|
"mean_token_accuracy": 0.15920995250344278,
|
|
"num_tokens": 16217282.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 6.214151334762573,
|
|
"epoch": 0.7673966796185093,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004948084524653868,
|
|
"loss": 5.9577,
|
|
"mean_token_accuracy": 0.16501378268003464,
|
|
"num_tokens": 16226567.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 6.199850082397461,
|
|
"epoch": 0.7678382197103497,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004948017244830489,
|
|
"loss": 6.1424,
|
|
"mean_token_accuracy": 0.14520249366760254,
|
|
"num_tokens": 16236255.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 6.20784821510315,
|
|
"epoch": 0.76827975980219,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004947949921949201,
|
|
"loss": 5.9037,
|
|
"mean_token_accuracy": 0.17059655785560607,
|
|
"num_tokens": 16244838.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 6.057857513427734,
|
|
"epoch": 0.7687212998940304,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004947882556011325,
|
|
"loss": 5.8378,
|
|
"mean_token_accuracy": 0.16639560759067534,
|
|
"num_tokens": 16254101.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.99750018119812,
|
|
"epoch": 0.7691628399858708,
|
|
"grad_norm": 2.90625,
|
|
"learning_rate": 0.000494781514701818,
|
|
"loss": 5.9132,
|
|
"mean_token_accuracy": 0.16554349213838576,
|
|
"num_tokens": 16263496.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 6.181209897994995,
|
|
"epoch": 0.769604380077711,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004947747694971085,
|
|
"loss": 6.0067,
|
|
"mean_token_accuracy": 0.15718649476766586,
|
|
"num_tokens": 16271884.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 6.164455318450928,
|
|
"epoch": 0.7700459201695514,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004947680199871363,
|
|
"loss": 5.9177,
|
|
"mean_token_accuracy": 0.166747522354126,
|
|
"num_tokens": 16281197.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 6.127913951873779,
|
|
"epoch": 0.7704874602613917,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 0.0004947612661720336,
|
|
"loss": 6.0124,
|
|
"mean_token_accuracy": 0.1616952523589134,
|
|
"num_tokens": 16289908.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 6.152335500717163,
|
|
"epoch": 0.7709290003532321,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004947545080519327,
|
|
"loss": 5.9877,
|
|
"mean_token_accuracy": 0.15621994733810424,
|
|
"num_tokens": 16299237.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 6.287478113174439,
|
|
"epoch": 0.7713705404450724,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.000494747745626966,
|
|
"loss": 6.0191,
|
|
"mean_token_accuracy": 0.15918604731559755,
|
|
"num_tokens": 16308175.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 6.178919315338135,
|
|
"epoch": 0.7718120805369127,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 0.0004947409788972659,
|
|
"loss": 5.9601,
|
|
"mean_token_accuracy": 0.1646192342042923,
|
|
"num_tokens": 16317121.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 6.140972852706909,
|
|
"epoch": 0.7722536206287531,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004947342078629649,
|
|
"loss": 5.9384,
|
|
"mean_token_accuracy": 0.16014498323202134,
|
|
"num_tokens": 16325764.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 6.144241285324097,
|
|
"epoch": 0.7726951607205934,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004947274325241959,
|
|
"loss": 5.936,
|
|
"mean_token_accuracy": 0.1571967288851738,
|
|
"num_tokens": 16333823.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 6.1269455909729,
|
|
"epoch": 0.7731367008124338,
|
|
"grad_norm": 3.53125,
|
|
"learning_rate": 0.0004947206528810913,
|
|
"loss": 5.9381,
|
|
"mean_token_accuracy": 0.16401293277740478,
|
|
"num_tokens": 16341918.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 6.091715383529663,
|
|
"epoch": 0.7735782409042741,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004947138689337843,
|
|
"loss": 6.0016,
|
|
"mean_token_accuracy": 0.15863162279129028,
|
|
"num_tokens": 16351904.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 6.1892224788665775,
|
|
"epoch": 0.7740197809961145,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004947070806824074,
|
|
"loss": 6.0067,
|
|
"mean_token_accuracy": 0.15773371160030364,
|
|
"num_tokens": 16360921.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 6.224908304214478,
|
|
"epoch": 0.7744613210879547,
|
|
"grad_norm": 4.21875,
|
|
"learning_rate": 0.0004947002881270937,
|
|
"loss": 6.0339,
|
|
"mean_token_accuracy": 0.1500479370355606,
|
|
"num_tokens": 16370929.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 6.191905832290649,
|
|
"epoch": 0.7749028611797951,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004946934912679764,
|
|
"loss": 6.0201,
|
|
"mean_token_accuracy": 0.1589919537305832,
|
|
"num_tokens": 16380099.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 6.212633848190308,
|
|
"epoch": 0.7753444012716355,
|
|
"grad_norm": 3.640625,
|
|
"learning_rate": 0.0004946866901051885,
|
|
"loss": 6.0483,
|
|
"mean_token_accuracy": 0.15650965869426728,
|
|
"num_tokens": 16389109.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 6.190409326553345,
|
|
"epoch": 0.7757859413634758,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004946798846388634,
|
|
"loss": 6.0967,
|
|
"mean_token_accuracy": 0.15047696828842164,
|
|
"num_tokens": 16398601.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 6.147092676162719,
|
|
"epoch": 0.7762274814553162,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004946730748691342,
|
|
"loss": 5.9525,
|
|
"mean_token_accuracy": 0.1679944798350334,
|
|
"num_tokens": 16406950.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 6.214142847061157,
|
|
"epoch": 0.7766690215471564,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004946662607961344,
|
|
"loss": 5.9534,
|
|
"mean_token_accuracy": 0.16123656928539276,
|
|
"num_tokens": 16414680.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 6.197415208816528,
|
|
"epoch": 0.7771105616389968,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.0004946594424199976,
|
|
"loss": 6.0265,
|
|
"mean_token_accuracy": 0.1588950887322426,
|
|
"num_tokens": 16424060.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 6.12212233543396,
|
|
"epoch": 0.7775521017308371,
|
|
"grad_norm": 18.5,
|
|
"learning_rate": 0.0004946526197408571,
|
|
"loss": 6.0326,
|
|
"mean_token_accuracy": 0.15300369560718535,
|
|
"num_tokens": 16433691.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 6.134805727005005,
|
|
"epoch": 0.7779936418226775,
|
|
"grad_norm": 4.4375,
|
|
"learning_rate": 0.0004946457927588467,
|
|
"loss": 6.0504,
|
|
"mean_token_accuracy": 0.15356888324022294,
|
|
"num_tokens": 16443234.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 6.117645978927612,
|
|
"epoch": 0.7784351819145179,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.0004946389614741002,
|
|
"loss": 5.9759,
|
|
"mean_token_accuracy": 0.15613539069890975,
|
|
"num_tokens": 16452084.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 6.16737117767334,
|
|
"epoch": 0.7788767220063582,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 0.0004946321258867513,
|
|
"loss": 5.9643,
|
|
"mean_token_accuracy": 0.16132914572954177,
|
|
"num_tokens": 16460135.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 6.213026332855224,
|
|
"epoch": 0.7793182620981985,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.000494625285996934,
|
|
"loss": 6.093,
|
|
"mean_token_accuracy": 0.1526857390999794,
|
|
"num_tokens": 16469919.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 6.259012365341187,
|
|
"epoch": 0.7797598021900388,
|
|
"grad_norm": 2.96875,
|
|
"learning_rate": 0.0004946184418047823,
|
|
"loss": 5.9994,
|
|
"mean_token_accuracy": 0.15334686413407325,
|
|
"num_tokens": 16478473.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 6.229764699935913,
|
|
"epoch": 0.7802013422818792,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004946115933104301,
|
|
"loss": 6.0208,
|
|
"mean_token_accuracy": 0.15497473552823066,
|
|
"num_tokens": 16486878.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 6.231283283233642,
|
|
"epoch": 0.7806428823737195,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004946047405140119,
|
|
"loss": 6.0594,
|
|
"mean_token_accuracy": 0.15498514473438263,
|
|
"num_tokens": 16496798.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 6.258311176300049,
|
|
"epoch": 0.7810844224655599,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004945978834156616,
|
|
"loss": 5.9831,
|
|
"mean_token_accuracy": 0.1629524976015091,
|
|
"num_tokens": 16506508.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 6.072232294082641,
|
|
"epoch": 0.7815259625574003,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004945910220155136,
|
|
"loss": 5.9576,
|
|
"mean_token_accuracy": 0.1621218889951706,
|
|
"num_tokens": 16514979.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 6.17908296585083,
|
|
"epoch": 0.7819675026492405,
|
|
"grad_norm": 4.1875,
|
|
"learning_rate": 0.0004945841563137025,
|
|
"loss": 6.0063,
|
|
"mean_token_accuracy": 0.154913267493248,
|
|
"num_tokens": 16524654.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 6.257924222946167,
|
|
"epoch": 0.7824090427410809,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004945772863103626,
|
|
"loss": 6.0897,
|
|
"mean_token_accuracy": 0.15017425939440726,
|
|
"num_tokens": 16534486.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 6.261570596694947,
|
|
"epoch": 0.7828505828329212,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004945704120056286,
|
|
"loss": 6.0177,
|
|
"mean_token_accuracy": 0.16266490668058395,
|
|
"num_tokens": 16543718.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 6.117233991622925,
|
|
"epoch": 0.7832921229247616,
|
|
"grad_norm": 3.484375,
|
|
"learning_rate": 0.000494563533399635,
|
|
"loss": 5.9634,
|
|
"mean_token_accuracy": 0.15218463391065598,
|
|
"num_tokens": 16553159.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 6.2105433464050295,
|
|
"epoch": 0.7837336630166019,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004945566504925167,
|
|
"loss": 6.0539,
|
|
"mean_token_accuracy": 0.15422216653823853,
|
|
"num_tokens": 16562398.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 6.276419067382813,
|
|
"epoch": 0.7841752031084422,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004945497632844084,
|
|
"loss": 5.9933,
|
|
"mean_token_accuracy": 0.16456555128097533,
|
|
"num_tokens": 16571530.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 6.170430421829224,
|
|
"epoch": 0.7846167432002826,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004945428717754453,
|
|
"loss": 5.9927,
|
|
"mean_token_accuracy": 0.15764102190732956,
|
|
"num_tokens": 16581074.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 6.134314918518067,
|
|
"epoch": 0.7850582832921229,
|
|
"grad_norm": 4.78125,
|
|
"learning_rate": 0.000494535975965762,
|
|
"loss": 5.8683,
|
|
"mean_token_accuracy": 0.17008696496486664,
|
|
"num_tokens": 16589574.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 6.10400881767273,
|
|
"epoch": 0.7854998233839633,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004945290758554939,
|
|
"loss": 5.9269,
|
|
"mean_token_accuracy": 0.16250946074724198,
|
|
"num_tokens": 16599623.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 6.16852765083313,
|
|
"epoch": 0.7859413634758036,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.000494522171444776,
|
|
"loss": 6.0309,
|
|
"mean_token_accuracy": 0.14622992724180223,
|
|
"num_tokens": 16608559.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 6.219989156723022,
|
|
"epoch": 0.786382903567644,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004945152627337437,
|
|
"loss": 5.9316,
|
|
"mean_token_accuracy": 0.16550691723823546,
|
|
"num_tokens": 16617148.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 6.124237823486328,
|
|
"epoch": 0.7868244436594842,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004945083497225321,
|
|
"loss": 5.9672,
|
|
"mean_token_accuracy": 0.1638670802116394,
|
|
"num_tokens": 16626405.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 6.194284296035766,
|
|
"epoch": 0.7872659837513246,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004945014324112769,
|
|
"loss": 5.9909,
|
|
"mean_token_accuracy": 0.1605047181248665,
|
|
"num_tokens": 16635116.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 6.155191087722779,
|
|
"epoch": 0.787707523843165,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004944945108001134,
|
|
"loss": 5.9647,
|
|
"mean_token_accuracy": 0.15713569819927214,
|
|
"num_tokens": 16644381.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 6.194045686721802,
|
|
"epoch": 0.7881490639350053,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.0004944875848891773,
|
|
"loss": 6.0273,
|
|
"mean_token_accuracy": 0.15611210465431213,
|
|
"num_tokens": 16654275.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 6.248635768890381,
|
|
"epoch": 0.7885906040268457,
|
|
"grad_norm": 3.03125,
|
|
"learning_rate": 0.0004944806546786042,
|
|
"loss": 6.0775,
|
|
"mean_token_accuracy": 0.15530216097831726,
|
|
"num_tokens": 16663484.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 6.167916774749756,
|
|
"epoch": 0.7890321441186859,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 0.00049447372016853,
|
|
"loss": 6.015,
|
|
"mean_token_accuracy": 0.1575445979833603,
|
|
"num_tokens": 16672490.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 6.142238140106201,
|
|
"epoch": 0.7894736842105263,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004944667813590904,
|
|
"loss": 5.997,
|
|
"mean_token_accuracy": 0.15616441369056702,
|
|
"num_tokens": 16681242.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 6.176788473129273,
|
|
"epoch": 0.7899152243023666,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004944598382504214,
|
|
"loss": 5.9263,
|
|
"mean_token_accuracy": 0.16061309725046158,
|
|
"num_tokens": 16690359.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 6.186691522598267,
|
|
"epoch": 0.790356764394207,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004944528908426589,
|
|
"loss": 6.0147,
|
|
"mean_token_accuracy": 0.16011423915624617,
|
|
"num_tokens": 16700774.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 6.230863285064697,
|
|
"epoch": 0.7907983044860474,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004944459391359391,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.1576569065451622,
|
|
"num_tokens": 16710513.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 6.200728082656861,
|
|
"epoch": 0.7912398445778877,
|
|
"grad_norm": 2.6875,
|
|
"learning_rate": 0.0004944389831303982,
|
|
"loss": 5.9829,
|
|
"mean_token_accuracy": 0.16038448214530945,
|
|
"num_tokens": 16720785.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 6.229797983169556,
|
|
"epoch": 0.791681384669728,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004944320228261723,
|
|
"loss": 5.9785,
|
|
"mean_token_accuracy": 0.15734335631132126,
|
|
"num_tokens": 16729083.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 6.1684887409210205,
|
|
"epoch": 0.7921229247615683,
|
|
"grad_norm": 3.375,
|
|
"learning_rate": 0.000494425058223398,
|
|
"loss": 6.0018,
|
|
"mean_token_accuracy": 0.15480220317840576,
|
|
"num_tokens": 16738313.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 6.16772427558899,
|
|
"epoch": 0.7925644648534087,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004944180893222117,
|
|
"loss": 5.9379,
|
|
"mean_token_accuracy": 0.16542160883545876,
|
|
"num_tokens": 16747191.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 6.121258020401001,
|
|
"epoch": 0.793006004945249,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004944111161227496,
|
|
"loss": 5.9712,
|
|
"mean_token_accuracy": 0.16323955059051515,
|
|
"num_tokens": 16755921.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 6.232733106613159,
|
|
"epoch": 0.7934475450370894,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004944041386251486,
|
|
"loss": 6.1172,
|
|
"mean_token_accuracy": 0.15585152059793472,
|
|
"num_tokens": 16765394.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 6.168314599990845,
|
|
"epoch": 0.7938890851289298,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004943971568295454,
|
|
"loss": 6.0134,
|
|
"mean_token_accuracy": 0.1611020252108574,
|
|
"num_tokens": 16774824.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 6.227082300186157,
|
|
"epoch": 0.79433062522077,
|
|
"grad_norm": 10.0625,
|
|
"learning_rate": 0.0004943901707360765,
|
|
"loss": 6.1348,
|
|
"mean_token_accuracy": 0.14640742987394334,
|
|
"num_tokens": 16783945.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 6.219871282577515,
|
|
"epoch": 0.7947721653126104,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.000494383180344879,
|
|
"loss": 5.9064,
|
|
"mean_token_accuracy": 0.1599573463201523,
|
|
"num_tokens": 16792618.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.7947721653126104,
|
|
"eval_entropy": 5.99483757380856,
|
|
"eval_loss": 6.030915260314941,
|
|
"eval_mean_token_accuracy": 0.16231492948844936,
|
|
"eval_num_tokens": 16792618.0,
|
|
"eval_runtime": 26.2471,
|
|
"eval_samples_per_second": 1345.48,
|
|
"eval_steps_per_second": 168.209,
|
|
"step": 9000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 113230,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 2.4825257975808e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|