12057 lines
330 KiB
JSON
12057 lines
330 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.1705199492732417,
|
|
"eval_steps": 3000,
|
|
"global_step": 6000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.742545986175537,
|
|
"epoch": 0.0009755145839430299,
|
|
"grad_norm": 4.65625,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.8379,
|
|
"mean_token_accuracy": 0.00014434070908464491,
|
|
"num_tokens": 17120.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.742573165893555,
|
|
"epoch": 0.0019510291678860598,
|
|
"grad_norm": 4.96875,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.8311,
|
|
"mean_token_accuracy": 0.00011998222325928509,
|
|
"num_tokens": 34182.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.742534160614014,
|
|
"epoch": 0.0029265437518290896,
|
|
"grad_norm": 5.0,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.8027,
|
|
"mean_token_accuracy": 0.00012189020635560155,
|
|
"num_tokens": 51205.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.742509460449218,
|
|
"epoch": 0.0039020583357721197,
|
|
"grad_norm": 5.125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.7494,
|
|
"mean_token_accuracy": 0.0005705497809685766,
|
|
"num_tokens": 67722.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.742345905303955,
|
|
"epoch": 0.00487757291971515,
|
|
"grad_norm": 4.4375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.6494,
|
|
"mean_token_accuracy": 0.02957919198088348,
|
|
"num_tokens": 84230.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.741327095031739,
|
|
"epoch": 0.005853087503658179,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.5266,
|
|
"mean_token_accuracy": 0.061843523755669594,
|
|
"num_tokens": 100967.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.7347092628479,
|
|
"epoch": 0.00682860208760121,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.3637,
|
|
"mean_token_accuracy": 0.06739617437124253,
|
|
"num_tokens": 117450.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.70640697479248,
|
|
"epoch": 0.007804116671544239,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.2606,
|
|
"mean_token_accuracy": 0.06366759836673737,
|
|
"num_tokens": 135328.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.657337093353272,
|
|
"epoch": 0.00877963125548727,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.1636,
|
|
"mean_token_accuracy": 0.06608470231294632,
|
|
"num_tokens": 152571.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.620244789123536,
|
|
"epoch": 0.0097551458394303,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.0949,
|
|
"mean_token_accuracy": 0.0651657074689865,
|
|
"num_tokens": 170216.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.61258020401001,
|
|
"epoch": 0.010730660423373329,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 10.015,
|
|
"mean_token_accuracy": 0.07096394337713718,
|
|
"num_tokens": 186513.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.613809299468993,
|
|
"epoch": 0.011706175007316359,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 10.0117,
|
|
"mean_token_accuracy": 0.06269222758710384,
|
|
"num_tokens": 202600.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.618330478668213,
|
|
"epoch": 0.01268168959125939,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.9438,
|
|
"mean_token_accuracy": 0.07208959870040417,
|
|
"num_tokens": 220270.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.610760307312011,
|
|
"epoch": 0.01365720417520242,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.8933,
|
|
"mean_token_accuracy": 0.06949375495314598,
|
|
"num_tokens": 236810.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.593310832977295,
|
|
"epoch": 0.014632718759145449,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.8518,
|
|
"mean_token_accuracy": 0.07177168019115925,
|
|
"num_tokens": 252559.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.562477207183838,
|
|
"epoch": 0.015608233343088479,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.7687,
|
|
"mean_token_accuracy": 0.07241420224308967,
|
|
"num_tokens": 268507.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.535469722747802,
|
|
"epoch": 0.01658374792703151,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.7325,
|
|
"mean_token_accuracy": 0.0762402530759573,
|
|
"num_tokens": 284776.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.517255306243896,
|
|
"epoch": 0.01755926251097454,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.7206,
|
|
"mean_token_accuracy": 0.07280966117978097,
|
|
"num_tokens": 300937.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.505683422088623,
|
|
"epoch": 0.01853477709491757,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.654,
|
|
"mean_token_accuracy": 0.07415377609431743,
|
|
"num_tokens": 317464.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.483844089508057,
|
|
"epoch": 0.0195102916788606,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.5346,
|
|
"mean_token_accuracy": 0.0789559468626976,
|
|
"num_tokens": 334022.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.463724327087402,
|
|
"epoch": 0.02048580626280363,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.4998,
|
|
"mean_token_accuracy": 0.07889014333486558,
|
|
"num_tokens": 350545.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.37066593170166,
|
|
"epoch": 0.021461320846746658,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.4199,
|
|
"mean_token_accuracy": 0.08481870368123054,
|
|
"num_tokens": 368878.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.354177665710449,
|
|
"epoch": 0.022436835430689687,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.3886,
|
|
"mean_token_accuracy": 0.0817614309489727,
|
|
"num_tokens": 388381.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.36144495010376,
|
|
"epoch": 0.023412350014632717,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 9.3266,
|
|
"mean_token_accuracy": 0.07798456773161888,
|
|
"num_tokens": 403727.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.321478271484375,
|
|
"epoch": 0.02438786459857575,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 9.2543,
|
|
"mean_token_accuracy": 0.07955141216516495,
|
|
"num_tokens": 419046.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.201090621948243,
|
|
"epoch": 0.02536337918251878,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 9.1187,
|
|
"mean_token_accuracy": 0.08797711431980133,
|
|
"num_tokens": 435186.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.184612846374511,
|
|
"epoch": 0.02633889376646181,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 9.0877,
|
|
"mean_token_accuracy": 0.08292194977402687,
|
|
"num_tokens": 451552.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.037136459350586,
|
|
"epoch": 0.02731440835040484,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 9.0324,
|
|
"mean_token_accuracy": 0.08637636378407479,
|
|
"num_tokens": 468006.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.057977771759033,
|
|
"epoch": 0.02828992293434787,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.9508,
|
|
"mean_token_accuracy": 0.08355718627572059,
|
|
"num_tokens": 484381.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.876834678649903,
|
|
"epoch": 0.029265437518290898,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.93,
|
|
"mean_token_accuracy": 0.08421113938093186,
|
|
"num_tokens": 501309.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.873361778259277,
|
|
"epoch": 0.030240952102233928,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.8471,
|
|
"mean_token_accuracy": 0.07950809225440025,
|
|
"num_tokens": 518290.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.737128734588623,
|
|
"epoch": 0.031216466686176957,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.7745,
|
|
"mean_token_accuracy": 0.08451616615056992,
|
|
"num_tokens": 533700.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.578966617584229,
|
|
"epoch": 0.03219198127011999,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 8.6201,
|
|
"mean_token_accuracy": 0.08652802109718323,
|
|
"num_tokens": 548935.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.524422359466552,
|
|
"epoch": 0.03316749585406302,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 8.6444,
|
|
"mean_token_accuracy": 0.08372659981250763,
|
|
"num_tokens": 565869.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.335462665557861,
|
|
"epoch": 0.03414301043800605,
|
|
"grad_norm": 0.70703125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 8.6507,
|
|
"mean_token_accuracy": 0.08460443243384361,
|
|
"num_tokens": 583065.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 9.36280517578125,
|
|
"epoch": 0.03511852502194908,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 8.6329,
|
|
"mean_token_accuracy": 0.08482759669423104,
|
|
"num_tokens": 599875.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 9.173808383941651,
|
|
"epoch": 0.03609403960589211,
|
|
"grad_norm": 0.67578125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 8.5743,
|
|
"mean_token_accuracy": 0.08783280774950981,
|
|
"num_tokens": 616296.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 9.197137355804443,
|
|
"epoch": 0.03706955418983514,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 8.5285,
|
|
"mean_token_accuracy": 0.08100056424736976,
|
|
"num_tokens": 632548.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 9.10781021118164,
|
|
"epoch": 0.03804506877377817,
|
|
"grad_norm": 0.70703125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 8.5301,
|
|
"mean_token_accuracy": 0.08742500841617584,
|
|
"num_tokens": 650395.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 9.043368911743164,
|
|
"epoch": 0.0390205833577212,
|
|
"grad_norm": 0.68359375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 8.5218,
|
|
"mean_token_accuracy": 0.09499027654528618,
|
|
"num_tokens": 668453.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 9.030275917053222,
|
|
"epoch": 0.03999609794166423,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 8.4423,
|
|
"mean_token_accuracy": 0.08772219642996788,
|
|
"num_tokens": 683914.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.929483890533447,
|
|
"epoch": 0.04097161252560726,
|
|
"grad_norm": 0.66796875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 8.5108,
|
|
"mean_token_accuracy": 0.08664508312940597,
|
|
"num_tokens": 700480.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.955109214782714,
|
|
"epoch": 0.041947127109550286,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 8.4882,
|
|
"mean_token_accuracy": 0.08451240882277489,
|
|
"num_tokens": 716604.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.781434345245362,
|
|
"epoch": 0.042922641693493316,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 8.4715,
|
|
"mean_token_accuracy": 0.08864145204424859,
|
|
"num_tokens": 732697.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.88281774520874,
|
|
"epoch": 0.043898156277436345,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.000112,
|
|
"loss": 8.5344,
|
|
"mean_token_accuracy": 0.08214838653802872,
|
|
"num_tokens": 749072.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.81209487915039,
|
|
"epoch": 0.044873670861379375,
|
|
"grad_norm": 0.68359375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 8.4873,
|
|
"mean_token_accuracy": 0.08687537536025047,
|
|
"num_tokens": 767826.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.874574089050293,
|
|
"epoch": 0.045849185445322405,
|
|
"grad_norm": 2.734375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 8.4097,
|
|
"mean_token_accuracy": 0.09442409723997117,
|
|
"num_tokens": 786863.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.778143787384034,
|
|
"epoch": 0.046824700029265434,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 8.3929,
|
|
"mean_token_accuracy": 0.10005151331424714,
|
|
"num_tokens": 803925.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.731143760681153,
|
|
"epoch": 0.04780021461320847,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 8.4637,
|
|
"mean_token_accuracy": 0.09069854766130447,
|
|
"num_tokens": 822088.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.784804248809815,
|
|
"epoch": 0.0487757291971515,
|
|
"grad_norm": 0.671875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 8.4703,
|
|
"mean_token_accuracy": 0.08817133978009224,
|
|
"num_tokens": 837991.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.71630163192749,
|
|
"epoch": 0.04975124378109453,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 8.3759,
|
|
"mean_token_accuracy": 0.09599229618906975,
|
|
"num_tokens": 855593.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.778234958648682,
|
|
"epoch": 0.05072675836503756,
|
|
"grad_norm": 0.6953125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 8.3926,
|
|
"mean_token_accuracy": 0.08905554860830307,
|
|
"num_tokens": 873696.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.698340606689452,
|
|
"epoch": 0.05170227294898059,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.000132,
|
|
"loss": 8.3648,
|
|
"mean_token_accuracy": 0.09724866859614849,
|
|
"num_tokens": 890023.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.724142837524415,
|
|
"epoch": 0.05267778753292362,
|
|
"grad_norm": 0.69140625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 8.499,
|
|
"mean_token_accuracy": 0.08494378551840782,
|
|
"num_tokens": 906492.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.658268070220947,
|
|
"epoch": 0.05365330211686665,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 8.4326,
|
|
"mean_token_accuracy": 0.0881828211247921,
|
|
"num_tokens": 921837.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.749652004241943,
|
|
"epoch": 0.05462881670080968,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 8.3803,
|
|
"mean_token_accuracy": 0.10005034953355789,
|
|
"num_tokens": 938771.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.66503381729126,
|
|
"epoch": 0.05560433128475271,
|
|
"grad_norm": 0.65234375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 8.388,
|
|
"mean_token_accuracy": 0.08957169800996781,
|
|
"num_tokens": 954562.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.760249996185303,
|
|
"epoch": 0.05657984586869574,
|
|
"grad_norm": 0.67578125,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 8.3309,
|
|
"mean_token_accuracy": 0.09739773571491242,
|
|
"num_tokens": 973700.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.610127925872803,
|
|
"epoch": 0.05755536045263877,
|
|
"grad_norm": 0.6328125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 8.3841,
|
|
"mean_token_accuracy": 0.09089891463518143,
|
|
"num_tokens": 990688.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.602487468719483,
|
|
"epoch": 0.058530875036581796,
|
|
"grad_norm": 0.65234375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 8.4543,
|
|
"mean_token_accuracy": 0.08643004968762398,
|
|
"num_tokens": 1008144.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.684108543395997,
|
|
"epoch": 0.059506389620524826,
|
|
"grad_norm": 0.62109375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 8.4075,
|
|
"mean_token_accuracy": 0.08840584978461266,
|
|
"num_tokens": 1027379.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.618590164184571,
|
|
"epoch": 0.060481904204467855,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 8.3946,
|
|
"mean_token_accuracy": 0.09471525549888611,
|
|
"num_tokens": 1043999.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.71361255645752,
|
|
"epoch": 0.061457418788410885,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 8.3943,
|
|
"mean_token_accuracy": 0.08788567930459976,
|
|
"num_tokens": 1062237.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.668982696533202,
|
|
"epoch": 0.062432933372353915,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 8.3439,
|
|
"mean_token_accuracy": 0.09140986129641533,
|
|
"num_tokens": 1078092.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.612729835510255,
|
|
"epoch": 0.06340844795629695,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 8.3807,
|
|
"mean_token_accuracy": 0.09364238902926444,
|
|
"num_tokens": 1095124.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.613638973236084,
|
|
"epoch": 0.06438396254023998,
|
|
"grad_norm": 0.65625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 8.3699,
|
|
"mean_token_accuracy": 0.08994951322674752,
|
|
"num_tokens": 1112775.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.583961772918702,
|
|
"epoch": 0.06535947712418301,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 8.306,
|
|
"mean_token_accuracy": 0.09773509949445724,
|
|
"num_tokens": 1129726.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.63847484588623,
|
|
"epoch": 0.06633499170812604,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 8.3582,
|
|
"mean_token_accuracy": 0.09658835083246231,
|
|
"num_tokens": 1144034.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.646141052246094,
|
|
"epoch": 0.06731050629206907,
|
|
"grad_norm": 0.69921875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 8.3001,
|
|
"mean_token_accuracy": 0.09566695243120193,
|
|
"num_tokens": 1159633.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.552906799316407,
|
|
"epoch": 0.0682860208760121,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 8.2566,
|
|
"mean_token_accuracy": 0.09137818142771721,
|
|
"num_tokens": 1175350.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.47085542678833,
|
|
"epoch": 0.06926153545995513,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 8.2038,
|
|
"mean_token_accuracy": 0.09639394730329513,
|
|
"num_tokens": 1193121.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.64188289642334,
|
|
"epoch": 0.07023705004389816,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 8.352,
|
|
"mean_token_accuracy": 0.09170110374689103,
|
|
"num_tokens": 1209896.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.56321315765381,
|
|
"epoch": 0.07121256462784119,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 8.3321,
|
|
"mean_token_accuracy": 0.09032948762178421,
|
|
"num_tokens": 1227011.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.49931468963623,
|
|
"epoch": 0.07218807921178422,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 8.2586,
|
|
"mean_token_accuracy": 0.0936131976544857,
|
|
"num_tokens": 1241595.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 8.551326656341553,
|
|
"epoch": 0.07316359379572725,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 8.2809,
|
|
"mean_token_accuracy": 0.08881813138723374,
|
|
"num_tokens": 1256919.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.576890087127685,
|
|
"epoch": 0.07413910837967028,
|
|
"grad_norm": 0.69921875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 8.2696,
|
|
"mean_token_accuracy": 0.10841422453522682,
|
|
"num_tokens": 1274344.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 8.525260543823242,
|
|
"epoch": 0.0751146229636133,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 8.2441,
|
|
"mean_token_accuracy": 0.09685440510511398,
|
|
"num_tokens": 1290252.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.542247867584228,
|
|
"epoch": 0.07609013754755634,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 8.3092,
|
|
"mean_token_accuracy": 0.09308558702468872,
|
|
"num_tokens": 1306987.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 8.586502170562744,
|
|
"epoch": 0.07706565213149937,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 8.3282,
|
|
"mean_token_accuracy": 0.0875322088599205,
|
|
"num_tokens": 1323031.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 8.52306661605835,
|
|
"epoch": 0.0780411667154424,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 8.2677,
|
|
"mean_token_accuracy": 0.09020323976874352,
|
|
"num_tokens": 1339592.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.584537792205811,
|
|
"epoch": 0.07901668129938542,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.000202,
|
|
"loss": 8.2469,
|
|
"mean_token_accuracy": 0.0998822957277298,
|
|
"num_tokens": 1358131.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 8.492807197570801,
|
|
"epoch": 0.07999219588332845,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 8.1846,
|
|
"mean_token_accuracy": 0.10047675669193268,
|
|
"num_tokens": 1375705.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 8.449185466766357,
|
|
"epoch": 0.08096771046727148,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000207,
|
|
"loss": 8.2014,
|
|
"mean_token_accuracy": 0.09942332729697227,
|
|
"num_tokens": 1392736.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 8.513163948059082,
|
|
"epoch": 0.08194322505121451,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 8.2322,
|
|
"mean_token_accuracy": 0.08992344737052918,
|
|
"num_tokens": 1408536.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 8.381054210662843,
|
|
"epoch": 0.08291873963515754,
|
|
"grad_norm": 0.68359375,
|
|
"learning_rate": 0.000212,
|
|
"loss": 8.2024,
|
|
"mean_token_accuracy": 0.09349315315485,
|
|
"num_tokens": 1425423.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 8.559225177764892,
|
|
"epoch": 0.08389425421910057,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 8.2133,
|
|
"mean_token_accuracy": 0.09476829543709755,
|
|
"num_tokens": 1442420.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 8.574479293823241,
|
|
"epoch": 0.0848697688030436,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 8.1947,
|
|
"mean_token_accuracy": 0.09402725324034691,
|
|
"num_tokens": 1458835.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 8.469829273223876,
|
|
"epoch": 0.08584528338698663,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 8.2763,
|
|
"mean_token_accuracy": 0.09046141654253007,
|
|
"num_tokens": 1475563.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 8.52817611694336,
|
|
"epoch": 0.08682079797092966,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 8.2133,
|
|
"mean_token_accuracy": 0.10233243256807327,
|
|
"num_tokens": 1492687.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 8.53304328918457,
|
|
"epoch": 0.08779631255487269,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 8.2363,
|
|
"mean_token_accuracy": 0.09168101623654365,
|
|
"num_tokens": 1508394.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 8.450295543670654,
|
|
"epoch": 0.08877182713881572,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 8.2079,
|
|
"mean_token_accuracy": 0.10227799862623214,
|
|
"num_tokens": 1527112.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 8.415885162353515,
|
|
"epoch": 0.08974734172275875,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 8.2331,
|
|
"mean_token_accuracy": 0.09917902275919914,
|
|
"num_tokens": 1545401.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 8.569608402252197,
|
|
"epoch": 0.09072285630670178,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 8.1165,
|
|
"mean_token_accuracy": 0.09994321763515472,
|
|
"num_tokens": 1561621.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 8.473207664489745,
|
|
"epoch": 0.09169837089064481,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 8.2154,
|
|
"mean_token_accuracy": 0.0949926421046257,
|
|
"num_tokens": 1579225.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 8.467814540863037,
|
|
"epoch": 0.09267388547458784,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 8.1298,
|
|
"mean_token_accuracy": 0.09709430187940597,
|
|
"num_tokens": 1596125.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 8.408341693878175,
|
|
"epoch": 0.09364940005853087,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 8.239,
|
|
"mean_token_accuracy": 0.0889017254114151,
|
|
"num_tokens": 1613451.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 8.418604183197022,
|
|
"epoch": 0.09462491464247391,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.000242,
|
|
"loss": 8.1839,
|
|
"mean_token_accuracy": 0.09638622403144836,
|
|
"num_tokens": 1630929.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 8.463642883300782,
|
|
"epoch": 0.09560042922641694,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 8.1892,
|
|
"mean_token_accuracy": 0.09477911740541459,
|
|
"num_tokens": 1647379.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 8.404396533966064,
|
|
"epoch": 0.09657594381035997,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.972,
|
|
"mean_token_accuracy": 0.11155017167329788,
|
|
"num_tokens": 1664415.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 8.328124237060546,
|
|
"epoch": 0.097551458394303,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 8.0243,
|
|
"mean_token_accuracy": 0.10308937430381775,
|
|
"num_tokens": 1679556.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 8.29896330833435,
|
|
"epoch": 0.09852697297824603,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.9748,
|
|
"mean_token_accuracy": 0.11530740708112716,
|
|
"num_tokens": 1696727.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 8.333364772796632,
|
|
"epoch": 0.09950248756218906,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 8.0291,
|
|
"mean_token_accuracy": 0.10489359647035598,
|
|
"num_tokens": 1713918.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 8.449989509582519,
|
|
"epoch": 0.10047800214613209,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 8.1751,
|
|
"mean_token_accuracy": 0.09076813086867333,
|
|
"num_tokens": 1729581.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 8.419713687896728,
|
|
"epoch": 0.10145351673007512,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 8.0506,
|
|
"mean_token_accuracy": 0.09246140196919442,
|
|
"num_tokens": 1746367.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 8.433179187774659,
|
|
"epoch": 0.10242903131401815,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 8.1352,
|
|
"mean_token_accuracy": 0.09465765729546546,
|
|
"num_tokens": 1765009.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 8.420462512969971,
|
|
"epoch": 0.10340454589796118,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 8.1402,
|
|
"mean_token_accuracy": 0.09433027505874633,
|
|
"num_tokens": 1782113.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 8.339337825775146,
|
|
"epoch": 0.10438006048190421,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 8.0357,
|
|
"mean_token_accuracy": 0.10014683678746224,
|
|
"num_tokens": 1798301.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 8.32430820465088,
|
|
"epoch": 0.10535557506584724,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 8.0744,
|
|
"mean_token_accuracy": 0.09614607095718383,
|
|
"num_tokens": 1815059.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 8.255896091461182,
|
|
"epoch": 0.10633108964979027,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.9775,
|
|
"mean_token_accuracy": 0.10225188136100768,
|
|
"num_tokens": 1831699.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 8.343412113189697,
|
|
"epoch": 0.1073066042337333,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 8.0561,
|
|
"mean_token_accuracy": 0.09823954552412033,
|
|
"num_tokens": 1847993.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 8.432454490661621,
|
|
"epoch": 0.10828211881767633,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.9062,
|
|
"mean_token_accuracy": 0.11012097150087356,
|
|
"num_tokens": 1864753.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 8.282480907440185,
|
|
"epoch": 0.10925763340161936,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 8.06,
|
|
"mean_token_accuracy": 0.1011503592133522,
|
|
"num_tokens": 1882154.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 8.209473037719727,
|
|
"epoch": 0.11023314798556239,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.9362,
|
|
"mean_token_accuracy": 0.106295907497406,
|
|
"num_tokens": 1899683.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 8.26357274055481,
|
|
"epoch": 0.11120866256950541,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.9382,
|
|
"mean_token_accuracy": 0.10315194055438041,
|
|
"num_tokens": 1918489.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 8.3274995803833,
|
|
"epoch": 0.11218417715344844,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.9968,
|
|
"mean_token_accuracy": 0.09892351552844048,
|
|
"num_tokens": 1935609.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 8.20813455581665,
|
|
"epoch": 0.11315969173739147,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 8.0239,
|
|
"mean_token_accuracy": 0.09603053033351898,
|
|
"num_tokens": 1951311.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 8.337920379638671,
|
|
"epoch": 0.1141352063213345,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 8.0831,
|
|
"mean_token_accuracy": 0.0927000992000103,
|
|
"num_tokens": 1968908.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 8.290319728851319,
|
|
"epoch": 0.11511072090527753,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.9801,
|
|
"mean_token_accuracy": 0.09734337329864502,
|
|
"num_tokens": 1983807.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 8.349214029312133,
|
|
"epoch": 0.11608623548922056,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 8.0318,
|
|
"mean_token_accuracy": 0.09839608669281005,
|
|
"num_tokens": 2000219.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 8.2715407371521,
|
|
"epoch": 0.11706175007316359,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.9594,
|
|
"mean_token_accuracy": 0.1046835497021675,
|
|
"num_tokens": 2017360.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 8.223270702362061,
|
|
"epoch": 0.11803726465710662,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.9477,
|
|
"mean_token_accuracy": 0.10477901026606559,
|
|
"num_tokens": 2034953.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 8.252518939971925,
|
|
"epoch": 0.11901277924104965,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.921,
|
|
"mean_token_accuracy": 0.10113409459590912,
|
|
"num_tokens": 2051551.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 8.254705429077148,
|
|
"epoch": 0.11998829382499268,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.9086,
|
|
"mean_token_accuracy": 0.10554389208555222,
|
|
"num_tokens": 2067188.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 8.175243711471557,
|
|
"epoch": 0.12096380840893571,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.9407,
|
|
"mean_token_accuracy": 0.10011097714304924,
|
|
"num_tokens": 2082569.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 8.322654724121094,
|
|
"epoch": 0.12193932299287874,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 8.0026,
|
|
"mean_token_accuracy": 0.09715932160615921,
|
|
"num_tokens": 2099446.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 8.246174478530884,
|
|
"epoch": 0.12291483757682177,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.9585,
|
|
"mean_token_accuracy": 0.09914746657013893,
|
|
"num_tokens": 2116526.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 8.269398927688599,
|
|
"epoch": 0.1238903521607648,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.999,
|
|
"mean_token_accuracy": 0.09154902622103692,
|
|
"num_tokens": 2134624.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 8.124698829650878,
|
|
"epoch": 0.12486586674470783,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.8396,
|
|
"mean_token_accuracy": 0.10734372511506081,
|
|
"num_tokens": 2152872.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 8.231671237945557,
|
|
"epoch": 0.12584138132865086,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.9856,
|
|
"mean_token_accuracy": 0.09579248055815696,
|
|
"num_tokens": 2169480.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 8.27645206451416,
|
|
"epoch": 0.1268168959125939,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.8324,
|
|
"mean_token_accuracy": 0.10887673124670982,
|
|
"num_tokens": 2186054.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 8.135476446151733,
|
|
"epoch": 0.12779241049653692,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.9707,
|
|
"mean_token_accuracy": 0.095298021286726,
|
|
"num_tokens": 2202320.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 8.142270755767822,
|
|
"epoch": 0.12876792508047996,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.8372,
|
|
"mean_token_accuracy": 0.1047438345849514,
|
|
"num_tokens": 2218817.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 8.260239505767823,
|
|
"epoch": 0.12974343966442298,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.9913,
|
|
"mean_token_accuracy": 0.09537639319896699,
|
|
"num_tokens": 2234845.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 8.212341785430908,
|
|
"epoch": 0.13071895424836602,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.9264,
|
|
"mean_token_accuracy": 0.09926454424858093,
|
|
"num_tokens": 2251904.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 8.084620904922485,
|
|
"epoch": 0.13169446883230904,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.9275,
|
|
"mean_token_accuracy": 0.09966224431991577,
|
|
"num_tokens": 2268343.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 8.316670322418213,
|
|
"epoch": 0.13266998341625208,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.9125,
|
|
"mean_token_accuracy": 0.1013021558523178,
|
|
"num_tokens": 2284524.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 8.03240876197815,
|
|
"epoch": 0.1336454980001951,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.8445,
|
|
"mean_token_accuracy": 0.1054447665810585,
|
|
"num_tokens": 2302350.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 8.19091992378235,
|
|
"epoch": 0.13462101258413814,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.9228,
|
|
"mean_token_accuracy": 0.09539637044072151,
|
|
"num_tokens": 2319953.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 8.203334712982178,
|
|
"epoch": 0.13559652716808115,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.8172,
|
|
"mean_token_accuracy": 0.1024633839726448,
|
|
"num_tokens": 2336698.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 8.045712327957153,
|
|
"epoch": 0.1365720417520242,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.7726,
|
|
"mean_token_accuracy": 0.10965236350893974,
|
|
"num_tokens": 2353986.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 8.118633937835693,
|
|
"epoch": 0.1375475563359672,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.8241,
|
|
"mean_token_accuracy": 0.10513764396309852,
|
|
"num_tokens": 2370320.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 8.149739933013915,
|
|
"epoch": 0.13852307091991026,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.8644,
|
|
"mean_token_accuracy": 0.098866156488657,
|
|
"num_tokens": 2385453.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 8.12429337501526,
|
|
"epoch": 0.13949858550385327,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.8549,
|
|
"mean_token_accuracy": 0.09939151853322983,
|
|
"num_tokens": 2401545.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 8.115737628936767,
|
|
"epoch": 0.14047410008779632,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.8504,
|
|
"mean_token_accuracy": 0.10048539191484451,
|
|
"num_tokens": 2418414.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 8.118222570419311,
|
|
"epoch": 0.14144961467173933,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.9118,
|
|
"mean_token_accuracy": 0.10191983357071877,
|
|
"num_tokens": 2434973.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 8.17931604385376,
|
|
"epoch": 0.14242512925568238,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.8881,
|
|
"mean_token_accuracy": 0.09516675621271134,
|
|
"num_tokens": 2451053.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 8.09225902557373,
|
|
"epoch": 0.1434006438396254,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.8626,
|
|
"mean_token_accuracy": 0.09528173580765724,
|
|
"num_tokens": 2467280.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 8.088089656829833,
|
|
"epoch": 0.14437615842356843,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.7803,
|
|
"mean_token_accuracy": 0.1092884823679924,
|
|
"num_tokens": 2484588.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 8.081604194641113,
|
|
"epoch": 0.14535167300751145,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.7932,
|
|
"mean_token_accuracy": 0.10359530225396156,
|
|
"num_tokens": 2501200.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 8.028561162948609,
|
|
"epoch": 0.1463271875914545,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.7428,
|
|
"mean_token_accuracy": 0.11165913268923759,
|
|
"num_tokens": 2517199.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 8.071641397476196,
|
|
"epoch": 0.1473027021753975,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.8168,
|
|
"mean_token_accuracy": 0.09799458160996437,
|
|
"num_tokens": 2534824.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.968346309661865,
|
|
"epoch": 0.14827821675934055,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.6936,
|
|
"mean_token_accuracy": 0.10773247331380845,
|
|
"num_tokens": 2550842.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 8.000276184082031,
|
|
"epoch": 0.14925373134328357,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.6604,
|
|
"mean_token_accuracy": 0.10792932882905007,
|
|
"num_tokens": 2567878.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 8.091751098632812,
|
|
"epoch": 0.1502292459272266,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.7485,
|
|
"mean_token_accuracy": 0.10320784673094749,
|
|
"num_tokens": 2584148.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 8.008577871322633,
|
|
"epoch": 0.15120476051116966,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.7503,
|
|
"mean_token_accuracy": 0.10530681982636451,
|
|
"num_tokens": 2600067.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 8.026472663879394,
|
|
"epoch": 0.15218027509511267,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.7366,
|
|
"mean_token_accuracy": 0.09601326063275337,
|
|
"num_tokens": 2615746.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 8.045800304412841,
|
|
"epoch": 0.15315578967905571,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.7722,
|
|
"mean_token_accuracy": 0.10049763545393944,
|
|
"num_tokens": 2631641.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.96700086593628,
|
|
"epoch": 0.15413130426299873,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.7749,
|
|
"mean_token_accuracy": 0.10441548749804497,
|
|
"num_tokens": 2647015.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 8.038145112991334,
|
|
"epoch": 0.15510681884694177,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.687,
|
|
"mean_token_accuracy": 0.10431429743766785,
|
|
"num_tokens": 2664045.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.970753955841064,
|
|
"epoch": 0.1560823334308848,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.6672,
|
|
"mean_token_accuracy": 0.10528303459286689,
|
|
"num_tokens": 2680774.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 8.060584831237794,
|
|
"epoch": 0.15705784801482783,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.7653,
|
|
"mean_token_accuracy": 0.1024099849164486,
|
|
"num_tokens": 2697719.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.984896326065064,
|
|
"epoch": 0.15803336259877085,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.7287,
|
|
"mean_token_accuracy": 0.09548300430178643,
|
|
"num_tokens": 2714518.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.963473129272461,
|
|
"epoch": 0.1590088771827139,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.7758,
|
|
"mean_token_accuracy": 0.10250489190220832,
|
|
"num_tokens": 2729288.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 8.057403326034546,
|
|
"epoch": 0.1599843917666569,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.7589,
|
|
"mean_token_accuracy": 0.10371811836957931,
|
|
"num_tokens": 2746782.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.909966135025025,
|
|
"epoch": 0.16095990635059995,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.7918,
|
|
"mean_token_accuracy": 0.09433421418070793,
|
|
"num_tokens": 2763159.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.984905338287353,
|
|
"epoch": 0.16193542093454297,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.734,
|
|
"mean_token_accuracy": 0.10140182003378868,
|
|
"num_tokens": 2780338.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.930758285522461,
|
|
"epoch": 0.162910935518486,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.6397,
|
|
"mean_token_accuracy": 0.10677831694483757,
|
|
"num_tokens": 2796214.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 8.004572010040283,
|
|
"epoch": 0.16388645010242903,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.7556,
|
|
"mean_token_accuracy": 0.09714071974158286,
|
|
"num_tokens": 2812745.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.912738943099976,
|
|
"epoch": 0.16486196468637207,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.6233,
|
|
"mean_token_accuracy": 0.10320991724729538,
|
|
"num_tokens": 2828288.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.9848785400390625,
|
|
"epoch": 0.16583747927031509,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.7558,
|
|
"mean_token_accuracy": 0.0968838632106781,
|
|
"num_tokens": 2843618.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.911918306350708,
|
|
"epoch": 0.16681299385425813,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.5565,
|
|
"mean_token_accuracy": 0.11261726319789886,
|
|
"num_tokens": 2860659.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.907874202728271,
|
|
"epoch": 0.16778850843820114,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.665,
|
|
"mean_token_accuracy": 0.10077697262167931,
|
|
"num_tokens": 2877482.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.96095380783081,
|
|
"epoch": 0.1687640230221442,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.7396,
|
|
"mean_token_accuracy": 0.09533020779490471,
|
|
"num_tokens": 2895868.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.936106157302857,
|
|
"epoch": 0.1697395376060872,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.7286,
|
|
"mean_token_accuracy": 0.1010709173977375,
|
|
"num_tokens": 2913103.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.909117889404297,
|
|
"epoch": 0.17071505219003025,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.6449,
|
|
"mean_token_accuracy": 0.1050123207271099,
|
|
"num_tokens": 2928291.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.895384120941162,
|
|
"epoch": 0.17169056677397326,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.6968,
|
|
"mean_token_accuracy": 0.10348322838544846,
|
|
"num_tokens": 2945115.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.935518503189087,
|
|
"epoch": 0.1726660813579163,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.5932,
|
|
"mean_token_accuracy": 0.10359113737940788,
|
|
"num_tokens": 2962869.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.885776710510254,
|
|
"epoch": 0.17364159594185932,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.7148,
|
|
"mean_token_accuracy": 0.09867775589227676,
|
|
"num_tokens": 2979298.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.9616724967956545,
|
|
"epoch": 0.17461711052580237,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.6235,
|
|
"mean_token_accuracy": 0.10697314292192459,
|
|
"num_tokens": 2996146.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.861116552352906,
|
|
"epoch": 0.17559262510974538,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.6919,
|
|
"mean_token_accuracy": 0.10271590203046799,
|
|
"num_tokens": 3013075.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.901067304611206,
|
|
"epoch": 0.17656813969368843,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.6489,
|
|
"mean_token_accuracy": 0.10057242289185524,
|
|
"num_tokens": 3029494.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.8369715213775635,
|
|
"epoch": 0.17754365427763144,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.6549,
|
|
"mean_token_accuracy": 0.10227547287940979,
|
|
"num_tokens": 3046333.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.902799129486084,
|
|
"epoch": 0.17851916886157448,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.6405,
|
|
"mean_token_accuracy": 0.1027099683880806,
|
|
"num_tokens": 3062714.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.915635061264038,
|
|
"epoch": 0.1794946834455175,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.6243,
|
|
"mean_token_accuracy": 0.10555409193038941,
|
|
"num_tokens": 3080711.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.877739381790161,
|
|
"epoch": 0.18047019802946054,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.7127,
|
|
"mean_token_accuracy": 0.09761228263378144,
|
|
"num_tokens": 3096885.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.808351802825928,
|
|
"epoch": 0.18144571261340356,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.607,
|
|
"mean_token_accuracy": 0.1075299970805645,
|
|
"num_tokens": 3114536.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.82890100479126,
|
|
"epoch": 0.1824212271973466,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.5659,
|
|
"mean_token_accuracy": 0.10890542268753052,
|
|
"num_tokens": 3131921.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.862617540359497,
|
|
"epoch": 0.18339674178128962,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.7037,
|
|
"mean_token_accuracy": 0.09914149567484856,
|
|
"num_tokens": 3148064.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.748774862289428,
|
|
"epoch": 0.18437225636523266,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.527,
|
|
"mean_token_accuracy": 0.10934840366244317,
|
|
"num_tokens": 3165822.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.820528364181518,
|
|
"epoch": 0.18534777094917568,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.6245,
|
|
"mean_token_accuracy": 0.10755226612091065,
|
|
"num_tokens": 3183286.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.906544256210327,
|
|
"epoch": 0.18632328553311872,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.6609,
|
|
"mean_token_accuracy": 0.09516188427805901,
|
|
"num_tokens": 3198522.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.809338474273682,
|
|
"epoch": 0.18729880011706174,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.6494,
|
|
"mean_token_accuracy": 0.10158563554286956,
|
|
"num_tokens": 3218422.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.857818698883056,
|
|
"epoch": 0.18827431470100478,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.694,
|
|
"mean_token_accuracy": 0.09597188532352448,
|
|
"num_tokens": 3236407.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.813616561889648,
|
|
"epoch": 0.18924982928494782,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.6223,
|
|
"mean_token_accuracy": 0.10206324681639671,
|
|
"num_tokens": 3252740.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.8036384105682375,
|
|
"epoch": 0.19022534386889084,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.5892,
|
|
"mean_token_accuracy": 0.10098864287137985,
|
|
"num_tokens": 3269874.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.835381650924683,
|
|
"epoch": 0.19120085845283388,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.6163,
|
|
"mean_token_accuracy": 0.09953035637736321,
|
|
"num_tokens": 3286515.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.6930643081665036,
|
|
"epoch": 0.1921763730367769,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.4293,
|
|
"mean_token_accuracy": 0.11725058928132057,
|
|
"num_tokens": 3303700.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.785474395751953,
|
|
"epoch": 0.19315188762071994,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.5881,
|
|
"mean_token_accuracy": 0.10581063255667686,
|
|
"num_tokens": 3319768.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.838024091720581,
|
|
"epoch": 0.19412740220466296,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.4995,
|
|
"mean_token_accuracy": 0.10780946016311646,
|
|
"num_tokens": 3336555.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.650297355651856,
|
|
"epoch": 0.195102916788606,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.5032,
|
|
"mean_token_accuracy": 0.10967954769730567,
|
|
"num_tokens": 3353273.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.755049371719361,
|
|
"epoch": 0.19607843137254902,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004999999929644166,
|
|
"loss": 7.4093,
|
|
"mean_token_accuracy": 0.1141424149274826,
|
|
"num_tokens": 3369408.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.701835823059082,
|
|
"epoch": 0.19705394595649206,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004999999643823598,
|
|
"loss": 7.4702,
|
|
"mean_token_accuracy": 0.10950530394911766,
|
|
"num_tokens": 3385834.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.682157421112061,
|
|
"epoch": 0.19802946054043508,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999999138141084,
|
|
"loss": 7.5624,
|
|
"mean_token_accuracy": 0.10582574605941772,
|
|
"num_tokens": 3401407.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.864960336685181,
|
|
"epoch": 0.19900497512437812,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004999998412596673,
|
|
"loss": 7.5728,
|
|
"mean_token_accuracy": 0.0993146575987339,
|
|
"num_tokens": 3418256.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.658085298538208,
|
|
"epoch": 0.19998048970832114,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004999997467190435,
|
|
"loss": 7.5535,
|
|
"mean_token_accuracy": 0.10653921887278557,
|
|
"num_tokens": 3433932.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.765207004547119,
|
|
"epoch": 0.20095600429226418,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999996301922465,
|
|
"loss": 7.5996,
|
|
"mean_token_accuracy": 0.09861309975385665,
|
|
"num_tokens": 3451723.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.730470132827759,
|
|
"epoch": 0.2019315188762072,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999994916792876,
|
|
"loss": 7.5662,
|
|
"mean_token_accuracy": 0.1022422194480896,
|
|
"num_tokens": 3469170.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.746661567687989,
|
|
"epoch": 0.20290703346015024,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004999993311801802,
|
|
"loss": 7.5806,
|
|
"mean_token_accuracy": 0.10085131973028183,
|
|
"num_tokens": 3485282.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.7354357719421385,
|
|
"epoch": 0.20388254804409325,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.00049999914869494,
|
|
"loss": 7.5625,
|
|
"mean_token_accuracy": 0.09602305442094802,
|
|
"num_tokens": 3502206.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.754732227325439,
|
|
"epoch": 0.2048580626280363,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.000499998944223585,
|
|
"loss": 7.4983,
|
|
"mean_token_accuracy": 0.10457974448800086,
|
|
"num_tokens": 3520384.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.653174543380738,
|
|
"epoch": 0.2058335772119793,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.0004999987177661351,
|
|
"loss": 7.5054,
|
|
"mean_token_accuracy": 0.10512347519397736,
|
|
"num_tokens": 3536314.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.6191648006439205,
|
|
"epoch": 0.20680909179592236,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999984693226124,
|
|
"loss": 7.4757,
|
|
"mean_token_accuracy": 0.11180041655898094,
|
|
"num_tokens": 3551510.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.7276811599731445,
|
|
"epoch": 0.20778460637986537,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999981988930411,
|
|
"loss": 7.4781,
|
|
"mean_token_accuracy": 0.10681704133749008,
|
|
"num_tokens": 3568515.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.692039155960083,
|
|
"epoch": 0.20876012096380842,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004999979064774478,
|
|
"loss": 7.521,
|
|
"mean_token_accuracy": 0.1076972097158432,
|
|
"num_tokens": 3585183.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.666302013397217,
|
|
"epoch": 0.20973563554775143,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499997592075861,
|
|
"loss": 7.4576,
|
|
"mean_token_accuracy": 0.10820185318589211,
|
|
"num_tokens": 3601898.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.777315092086792,
|
|
"epoch": 0.21071115013169447,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999972556883113,
|
|
"loss": 7.5112,
|
|
"mean_token_accuracy": 0.10493268743157387,
|
|
"num_tokens": 3616699.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.650645208358765,
|
|
"epoch": 0.2116866647156375,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004999968973148318,
|
|
"loss": 7.5255,
|
|
"mean_token_accuracy": 0.10378064140677452,
|
|
"num_tokens": 3634030.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.74101037979126,
|
|
"epoch": 0.21266217929958053,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004999965169554573,
|
|
"loss": 7.5187,
|
|
"mean_token_accuracy": 0.10108392685651779,
|
|
"num_tokens": 3650495.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.681738424301147,
|
|
"epoch": 0.21363769388352355,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999961146102251,
|
|
"loss": 7.485,
|
|
"mean_token_accuracy": 0.10594045221805573,
|
|
"num_tokens": 3666926.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.639343309402466,
|
|
"epoch": 0.2146132084674666,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004999956902791746,
|
|
"loss": 7.4543,
|
|
"mean_token_accuracy": 0.11311954259872437,
|
|
"num_tokens": 3683061.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.593081951141357,
|
|
"epoch": 0.2155887230514096,
|
|
"grad_norm": 0.69921875,
|
|
"learning_rate": 0.0004999952439623469,
|
|
"loss": 7.5121,
|
|
"mean_token_accuracy": 0.10505839735269547,
|
|
"num_tokens": 3703013.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.679114913940429,
|
|
"epoch": 0.21656423763535265,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000499994775659786,
|
|
"loss": 7.3601,
|
|
"mean_token_accuracy": 0.11591144353151321,
|
|
"num_tokens": 3719885.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.631566095352173,
|
|
"epoch": 0.21753975221929567,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999942853715375,
|
|
"loss": 7.4971,
|
|
"mean_token_accuracy": 0.10333904549479485,
|
|
"num_tokens": 3735122.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.694211006164551,
|
|
"epoch": 0.2185152668032387,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.0004999937730976494,
|
|
"loss": 7.4806,
|
|
"mean_token_accuracy": 0.10258661657571792,
|
|
"num_tokens": 3751627.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.595678424835205,
|
|
"epoch": 0.21949078138718173,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004999932388381716,
|
|
"loss": 7.4929,
|
|
"mean_token_accuracy": 0.101930870115757,
|
|
"num_tokens": 3768165.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.726031064987183,
|
|
"epoch": 0.22046629597112477,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004999926825931564,
|
|
"loss": 7.5163,
|
|
"mean_token_accuracy": 0.10487755760550499,
|
|
"num_tokens": 3784245.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.5429949283599855,
|
|
"epoch": 0.2214418105550678,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004999921043626582,
|
|
"loss": 7.2742,
|
|
"mean_token_accuracy": 0.11879447922110557,
|
|
"num_tokens": 3802057.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.616366910934448,
|
|
"epoch": 0.22241732513901083,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004999915041467333,
|
|
"loss": 7.4538,
|
|
"mean_token_accuracy": 0.10403451472520828,
|
|
"num_tokens": 3817104.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.623820781707764,
|
|
"epoch": 0.22339283972295385,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004999908819454407,
|
|
"loss": 7.4557,
|
|
"mean_token_accuracy": 0.10573292225599289,
|
|
"num_tokens": 3833037.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.591778421401978,
|
|
"epoch": 0.2243683543068969,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004999902377588408,
|
|
"loss": 7.3454,
|
|
"mean_token_accuracy": 0.1075218863785267,
|
|
"num_tokens": 3849634.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.620333814620972,
|
|
"epoch": 0.2253438688908399,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000499989571586997,
|
|
"loss": 7.5125,
|
|
"mean_token_accuracy": 0.10198941007256508,
|
|
"num_tokens": 3865949.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.529477119445801,
|
|
"epoch": 0.22631938347478295,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004999888834299739,
|
|
"loss": 7.3796,
|
|
"mean_token_accuracy": 0.11067740991711617,
|
|
"num_tokens": 3884646.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.658005952835083,
|
|
"epoch": 0.227294898058726,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004999881732878391,
|
|
"loss": 7.4808,
|
|
"mean_token_accuracy": 0.10823895409703255,
|
|
"num_tokens": 3900740.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.605532455444336,
|
|
"epoch": 0.228270412642669,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004999874411606618,
|
|
"loss": 7.4248,
|
|
"mean_token_accuracy": 0.10825219377875328,
|
|
"num_tokens": 3918619.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.614225101470947,
|
|
"epoch": 0.22924592722661205,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004999866870485137,
|
|
"loss": 7.3986,
|
|
"mean_token_accuracy": 0.10738857686519623,
|
|
"num_tokens": 3938161.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.632542467117309,
|
|
"epoch": 0.23022144181055507,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999859109514684,
|
|
"loss": 7.4496,
|
|
"mean_token_accuracy": 0.10592144280672074,
|
|
"num_tokens": 3953582.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.637817001342773,
|
|
"epoch": 0.2311969563944981,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004999851128696017,
|
|
"loss": 7.4297,
|
|
"mean_token_accuracy": 0.09909034296870231,
|
|
"num_tokens": 3969747.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.631790590286255,
|
|
"epoch": 0.23217247097844113,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004999842928029917,
|
|
"loss": 7.4596,
|
|
"mean_token_accuracy": 0.10731764733791352,
|
|
"num_tokens": 3984646.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.594443273544312,
|
|
"epoch": 0.23314798556238417,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004999834507517184,
|
|
"loss": 7.4381,
|
|
"mean_token_accuracy": 0.10461552739143372,
|
|
"num_tokens": 4003108.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.619934177398681,
|
|
"epoch": 0.23412350014632718,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004999825867158642,
|
|
"loss": 7.5028,
|
|
"mean_token_accuracy": 0.10035586953163148,
|
|
"num_tokens": 4019944.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.667219352722168,
|
|
"epoch": 0.23509901473027023,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004999817006955134,
|
|
"loss": 7.3921,
|
|
"mean_token_accuracy": 0.10938728377223014,
|
|
"num_tokens": 4037617.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.553360652923584,
|
|
"epoch": 0.23607452931421324,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004999807926907527,
|
|
"loss": 7.3945,
|
|
"mean_token_accuracy": 0.10081385970115661,
|
|
"num_tokens": 4053483.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.64829454421997,
|
|
"epoch": 0.2370500438981563,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004999798627016707,
|
|
"loss": 7.4587,
|
|
"mean_token_accuracy": 0.10884808897972106,
|
|
"num_tokens": 4070165.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.619628667831421,
|
|
"epoch": 0.2380255584820993,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999789107283586,
|
|
"loss": 7.4342,
|
|
"mean_token_accuracy": 0.1030805915594101,
|
|
"num_tokens": 4086208.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.502168989181518,
|
|
"epoch": 0.23900107306604235,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.000499977936770909,
|
|
"loss": 7.4058,
|
|
"mean_token_accuracy": 0.10911756455898285,
|
|
"num_tokens": 4101790.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.568706035614014,
|
|
"epoch": 0.23997658764998536,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999769408294173,
|
|
"loss": 7.3363,
|
|
"mean_token_accuracy": 0.11626880168914795,
|
|
"num_tokens": 4117633.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.568750286102295,
|
|
"epoch": 0.2409521022339284,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004999759229039807,
|
|
"loss": 7.3873,
|
|
"mean_token_accuracy": 0.10927161276340484,
|
|
"num_tokens": 4132634.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.5792591094970705,
|
|
"epoch": 0.24192761681787142,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004999748829946988,
|
|
"loss": 7.442,
|
|
"mean_token_accuracy": 0.10532458499073982,
|
|
"num_tokens": 4150702.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.524825191497802,
|
|
"epoch": 0.24290313140181446,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004999738211016732,
|
|
"loss": 7.3054,
|
|
"mean_token_accuracy": 0.12065900191664695,
|
|
"num_tokens": 4168483.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.430249309539795,
|
|
"epoch": 0.24387864598575748,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004999727372250076,
|
|
"loss": 7.2814,
|
|
"mean_token_accuracy": 0.11273804232478142,
|
|
"num_tokens": 4186199.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.560726976394653,
|
|
"epoch": 0.24485416056970052,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999716313648079,
|
|
"loss": 7.4101,
|
|
"mean_token_accuracy": 0.10708601549267768,
|
|
"num_tokens": 4202303.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.622148323059082,
|
|
"epoch": 0.24582967515364354,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004999705035211822,
|
|
"loss": 7.4547,
|
|
"mean_token_accuracy": 0.10375886857509613,
|
|
"num_tokens": 4218541.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.5890209674835205,
|
|
"epoch": 0.24680518973758658,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004999693536942406,
|
|
"loss": 7.4123,
|
|
"mean_token_accuracy": 0.10459026619791985,
|
|
"num_tokens": 4234025.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.591500186920166,
|
|
"epoch": 0.2477807043215296,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999681818840957,
|
|
"loss": 7.4257,
|
|
"mean_token_accuracy": 0.11080710366368293,
|
|
"num_tokens": 4250798.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.561366319656372,
|
|
"epoch": 0.24875621890547264,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000499966988090862,
|
|
"loss": 7.4261,
|
|
"mean_token_accuracy": 0.10205279141664506,
|
|
"num_tokens": 4266453.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.638256502151489,
|
|
"epoch": 0.24973173348941566,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999657723146558,
|
|
"loss": 7.3818,
|
|
"mean_token_accuracy": 0.10573315620422363,
|
|
"num_tokens": 4281825.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.389687967300415,
|
|
"epoch": 0.2507072480733587,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004999645345555962,
|
|
"loss": 7.2205,
|
|
"mean_token_accuracy": 0.12211042940616608,
|
|
"num_tokens": 4298821.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.507760238647461,
|
|
"epoch": 0.2516827626573017,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999632748138041,
|
|
"loss": 7.267,
|
|
"mean_token_accuracy": 0.11187295690178871,
|
|
"num_tokens": 4314076.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.534629392623901,
|
|
"epoch": 0.25265827724124473,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004999619930894025,
|
|
"loss": 7.2723,
|
|
"mean_token_accuracy": 0.1124474972486496,
|
|
"num_tokens": 4330909.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.508888912200928,
|
|
"epoch": 0.2536337918251878,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004999606893825168,
|
|
"loss": 7.367,
|
|
"mean_token_accuracy": 0.10985746160149575,
|
|
"num_tokens": 4346927.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.526936769485474,
|
|
"epoch": 0.2546093064091308,
|
|
"grad_norm": 0.68359375,
|
|
"learning_rate": 0.0004999593636932742,
|
|
"loss": 7.4001,
|
|
"mean_token_accuracy": 0.10443056225776673,
|
|
"num_tokens": 4364956.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.524621152877808,
|
|
"epoch": 0.25558482099307384,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004999580160218044,
|
|
"loss": 7.3355,
|
|
"mean_token_accuracy": 0.10670254677534104,
|
|
"num_tokens": 4383014.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.467378330230713,
|
|
"epoch": 0.25656033557701685,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004999566463682391,
|
|
"loss": 7.4095,
|
|
"mean_token_accuracy": 0.10816679820418358,
|
|
"num_tokens": 4401050.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 7.533441591262817,
|
|
"epoch": 0.2575358501609599,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004999552547327119,
|
|
"loss": 7.3048,
|
|
"mean_token_accuracy": 0.10800013542175294,
|
|
"num_tokens": 4415453.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.4499256134033205,
|
|
"epoch": 0.25851136474490294,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999538411153591,
|
|
"loss": 7.2945,
|
|
"mean_token_accuracy": 0.11506965532898902,
|
|
"num_tokens": 4433107.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 7.55745005607605,
|
|
"epoch": 0.25948687932884595,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004999524055163187,
|
|
"loss": 7.373,
|
|
"mean_token_accuracy": 0.10276507884263993,
|
|
"num_tokens": 4449440.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.562828826904297,
|
|
"epoch": 0.26046239391278897,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.000499950947935731,
|
|
"loss": 7.3544,
|
|
"mean_token_accuracy": 0.10752240270376205,
|
|
"num_tokens": 4465327.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.5065587043762205,
|
|
"epoch": 0.26143790849673204,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004999494683737384,
|
|
"loss": 7.3836,
|
|
"mean_token_accuracy": 0.10438340827822686,
|
|
"num_tokens": 4481518.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.607649135589599,
|
|
"epoch": 0.26241342308067506,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004999479668304854,
|
|
"loss": 7.4024,
|
|
"mean_token_accuracy": 0.10401526093482971,
|
|
"num_tokens": 4497632.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.285141897201538,
|
|
"epoch": 0.2633889376646181,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004999464433061188,
|
|
"loss": 7.1554,
|
|
"mean_token_accuracy": 0.12241300269961357,
|
|
"num_tokens": 4513790.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.519728755950927,
|
|
"epoch": 0.26436445224856114,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004999448978007876,
|
|
"loss": 7.2984,
|
|
"mean_token_accuracy": 0.11036163046956063,
|
|
"num_tokens": 4530802.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.546466922760009,
|
|
"epoch": 0.26533996683250416,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999433303146426,
|
|
"loss": 7.3356,
|
|
"mean_token_accuracy": 0.1046901948750019,
|
|
"num_tokens": 4546208.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.4623072147369385,
|
|
"epoch": 0.2663154814164472,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.0004999417408478371,
|
|
"loss": 7.3911,
|
|
"mean_token_accuracy": 0.10712278932332993,
|
|
"num_tokens": 4563753.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.459856939315796,
|
|
"epoch": 0.2672909960003902,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999401294005264,
|
|
"loss": 7.273,
|
|
"mean_token_accuracy": 0.11257142499089241,
|
|
"num_tokens": 4580274.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 7.477842092514038,
|
|
"epoch": 0.26826651058433326,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000499938495972868,
|
|
"loss": 7.3515,
|
|
"mean_token_accuracy": 0.10793646723031998,
|
|
"num_tokens": 4596085.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.486316585540772,
|
|
"epoch": 0.2692420251682763,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004999368405650214,
|
|
"loss": 7.381,
|
|
"mean_token_accuracy": 0.10322927758097648,
|
|
"num_tokens": 4613258.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 7.384283590316772,
|
|
"epoch": 0.2702175397522193,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004999351631771485,
|
|
"loss": 7.2098,
|
|
"mean_token_accuracy": 0.11609927490353585,
|
|
"num_tokens": 4630128.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 7.547839498519897,
|
|
"epoch": 0.2711930543361623,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004999334638094131,
|
|
"loss": 7.2417,
|
|
"mean_token_accuracy": 0.11260311901569367,
|
|
"num_tokens": 4646181.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.463831806182862,
|
|
"epoch": 0.2721685689201054,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004999317424619812,
|
|
"loss": 7.299,
|
|
"mean_token_accuracy": 0.10586258545517921,
|
|
"num_tokens": 4661804.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 7.43352689743042,
|
|
"epoch": 0.2731440835040484,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004999299991350212,
|
|
"loss": 7.2196,
|
|
"mean_token_accuracy": 0.11394756436347961,
|
|
"num_tokens": 4678163.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.499938440322876,
|
|
"epoch": 0.2741195980879914,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999282338287034,
|
|
"loss": 7.2102,
|
|
"mean_token_accuracy": 0.11337384283542633,
|
|
"num_tokens": 4695469.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 7.501874732971191,
|
|
"epoch": 0.2750951126719344,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004999264465432001,
|
|
"loss": 7.3461,
|
|
"mean_token_accuracy": 0.11030107736587524,
|
|
"num_tokens": 4711599.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 7.478948163986206,
|
|
"epoch": 0.2760706272558775,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004999246372786862,
|
|
"loss": 7.3544,
|
|
"mean_token_accuracy": 0.10497529283165932,
|
|
"num_tokens": 4728381.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 7.4203221797943115,
|
|
"epoch": 0.2770461418398205,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.0004999228060353385,
|
|
"loss": 7.3363,
|
|
"mean_token_accuracy": 0.10868120938539505,
|
|
"num_tokens": 4745348.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.5548547267913815,
|
|
"epoch": 0.27802165642376353,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999209528133357,
|
|
"loss": 7.3448,
|
|
"mean_token_accuracy": 0.10266721099615098,
|
|
"num_tokens": 4763011.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.4765321731567385,
|
|
"epoch": 0.27899717100770655,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000499919077612859,
|
|
"loss": 7.2882,
|
|
"mean_token_accuracy": 0.10844862014055252,
|
|
"num_tokens": 4779462.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.293780994415283,
|
|
"epoch": 0.2799726855916496,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004999171804340917,
|
|
"loss": 7.2313,
|
|
"mean_token_accuracy": 0.11544499918818474,
|
|
"num_tokens": 4796844.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.474391031265259,
|
|
"epoch": 0.28094820017559263,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004999152612772191,
|
|
"loss": 7.2579,
|
|
"mean_token_accuracy": 0.11364135891199112,
|
|
"num_tokens": 4812851.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.348306369781494,
|
|
"epoch": 0.28192371475953565,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999133201424288,
|
|
"loss": 7.2109,
|
|
"mean_token_accuracy": 0.1137004129588604,
|
|
"num_tokens": 4830144.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 7.589390277862549,
|
|
"epoch": 0.28289922934347866,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004999113570299105,
|
|
"loss": 7.3162,
|
|
"mean_token_accuracy": 0.10344778746366501,
|
|
"num_tokens": 4846981.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 7.439992523193359,
|
|
"epoch": 0.28387474392742174,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.0004999093719398561,
|
|
"loss": 7.4507,
|
|
"mean_token_accuracy": 0.0993297427892685,
|
|
"num_tokens": 4864404.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 7.506286716461181,
|
|
"epoch": 0.28485025851136475,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999073648724592,
|
|
"loss": 7.3368,
|
|
"mean_token_accuracy": 0.10415377318859101,
|
|
"num_tokens": 4882004.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 7.455475807189941,
|
|
"epoch": 0.28582577309530777,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004999053358279164,
|
|
"loss": 7.2824,
|
|
"mean_token_accuracy": 0.10441663935780525,
|
|
"num_tokens": 4899444.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 7.507974910736084,
|
|
"epoch": 0.2868012876792508,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004999032848064256,
|
|
"loss": 7.2713,
|
|
"mean_token_accuracy": 0.105850101262331,
|
|
"num_tokens": 4917214.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 7.377426624298096,
|
|
"epoch": 0.28777680226319385,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999012118081875,
|
|
"loss": 7.3534,
|
|
"mean_token_accuracy": 0.1025879755616188,
|
|
"num_tokens": 4934534.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.548637533187867,
|
|
"epoch": 0.28875231684713687,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004998991168334045,
|
|
"loss": 7.2657,
|
|
"mean_token_accuracy": 0.10621999204158783,
|
|
"num_tokens": 4950740.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 7.444481134414673,
|
|
"epoch": 0.2897278314310799,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998969998822814,
|
|
"loss": 7.3529,
|
|
"mean_token_accuracy": 0.10245063826441765,
|
|
"num_tokens": 4966720.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 7.47595624923706,
|
|
"epoch": 0.2907033460150229,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004998948609550249,
|
|
"loss": 7.245,
|
|
"mean_token_accuracy": 0.10455562472343445,
|
|
"num_tokens": 4982195.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.48439302444458,
|
|
"epoch": 0.29167886059896597,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998927000518442,
|
|
"loss": 7.3514,
|
|
"mean_token_accuracy": 0.10247311592102051,
|
|
"num_tokens": 4997487.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 7.406205940246582,
|
|
"epoch": 0.292654375182909,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004998905171729505,
|
|
"loss": 7.2324,
|
|
"mean_token_accuracy": 0.10920758843421936,
|
|
"num_tokens": 5012913.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 7.351927471160889,
|
|
"epoch": 0.293629889766852,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004998883123185568,
|
|
"loss": 7.1937,
|
|
"mean_token_accuracy": 0.12020321637392044,
|
|
"num_tokens": 5031462.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 7.460276126861572,
|
|
"epoch": 0.294605404350795,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998860854888788,
|
|
"loss": 7.1911,
|
|
"mean_token_accuracy": 0.11498533636331558,
|
|
"num_tokens": 5047354.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 7.336567544937134,
|
|
"epoch": 0.2955809189347381,
|
|
"grad_norm": 0.69140625,
|
|
"learning_rate": 0.0004998838366841341,
|
|
"loss": 7.2655,
|
|
"mean_token_accuracy": 0.11058657392859458,
|
|
"num_tokens": 5065268.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 7.4529026508331295,
|
|
"epoch": 0.2965564335186811,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004998815659045423,
|
|
"loss": 7.2507,
|
|
"mean_token_accuracy": 0.11000868156552315,
|
|
"num_tokens": 5081066.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 7.428559732437134,
|
|
"epoch": 0.2975319481026241,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004998792731503254,
|
|
"loss": 7.284,
|
|
"mean_token_accuracy": 0.1131756454706192,
|
|
"num_tokens": 5099440.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 7.379742431640625,
|
|
"epoch": 0.29850746268656714,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004998769584217074,
|
|
"loss": 7.2445,
|
|
"mean_token_accuracy": 0.11773268282413482,
|
|
"num_tokens": 5116573.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 7.285349035263062,
|
|
"epoch": 0.2994829772705102,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004998746217189145,
|
|
"loss": 7.0154,
|
|
"mean_token_accuracy": 0.12612679973244667,
|
|
"num_tokens": 5132920.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 7.485317373275757,
|
|
"epoch": 0.3004584918544532,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.000499872263042175,
|
|
"loss": 7.2709,
|
|
"mean_token_accuracy": 0.10634980946779252,
|
|
"num_tokens": 5150681.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 7.2799914360046385,
|
|
"epoch": 0.30143400643839624,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998698823917196,
|
|
"loss": 7.0609,
|
|
"mean_token_accuracy": 0.12634149193763733,
|
|
"num_tokens": 5167473.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 7.412469148635864,
|
|
"epoch": 0.3024095210223393,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004998674797677805,
|
|
"loss": 7.329,
|
|
"mean_token_accuracy": 0.10400748774409294,
|
|
"num_tokens": 5183847.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 7.394794702529907,
|
|
"epoch": 0.3033850356062823,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998650551705929,
|
|
"loss": 7.2701,
|
|
"mean_token_accuracy": 0.1091896690428257,
|
|
"num_tokens": 5200019.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 7.368698263168335,
|
|
"epoch": 0.30436055019022534,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998626086003934,
|
|
"loss": 7.1482,
|
|
"mean_token_accuracy": 0.11328554674983024,
|
|
"num_tokens": 5217245.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 7.3528977394104,
|
|
"epoch": 0.30533606477416836,
|
|
"grad_norm": 0.66015625,
|
|
"learning_rate": 0.0004998601400574213,
|
|
"loss": 7.047,
|
|
"mean_token_accuracy": 0.11916083097457886,
|
|
"num_tokens": 5234822.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 7.351659297943115,
|
|
"epoch": 0.30631157935811143,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004998576495419177,
|
|
"loss": 7.1878,
|
|
"mean_token_accuracy": 0.10867269039154052,
|
|
"num_tokens": 5251282.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 7.320261383056641,
|
|
"epoch": 0.30728709394205445,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.000499855137054126,
|
|
"loss": 7.1493,
|
|
"mean_token_accuracy": 0.11374075636267662,
|
|
"num_tokens": 5269630.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 7.461973571777344,
|
|
"epoch": 0.30826260852599746,
|
|
"grad_norm": 0.703125,
|
|
"learning_rate": 0.0004998526025942917,
|
|
"loss": 7.231,
|
|
"mean_token_accuracy": 0.10755549967288972,
|
|
"num_tokens": 5287106.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 7.371440410614014,
|
|
"epoch": 0.3092381231099405,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004998500461626625,
|
|
"loss": 7.265,
|
|
"mean_token_accuracy": 0.10544228777289391,
|
|
"num_tokens": 5303387.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 7.4729814529418945,
|
|
"epoch": 0.31021363769388355,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.000499847467759488,
|
|
"loss": 7.2561,
|
|
"mean_token_accuracy": 0.10558799877762795,
|
|
"num_tokens": 5320482.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 7.344847202301025,
|
|
"epoch": 0.31118915227782656,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004998448673850205,
|
|
"loss": 7.2078,
|
|
"mean_token_accuracy": 0.1119214117527008,
|
|
"num_tokens": 5336420.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 7.33606595993042,
|
|
"epoch": 0.3121646668617696,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998422450395139,
|
|
"loss": 7.1265,
|
|
"mean_token_accuracy": 0.1145975984632969,
|
|
"num_tokens": 5353464.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 7.326481723785401,
|
|
"epoch": 0.3131401814457126,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004998396007232244,
|
|
"loss": 7.2097,
|
|
"mean_token_accuracy": 0.1147161565721035,
|
|
"num_tokens": 5372607.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 7.383757877349853,
|
|
"epoch": 0.31411569602965567,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004998369344364105,
|
|
"loss": 7.2393,
|
|
"mean_token_accuracy": 0.1151178702712059,
|
|
"num_tokens": 5390134.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 7.347494220733642,
|
|
"epoch": 0.3150912106135987,
|
|
"grad_norm": 0.69921875,
|
|
"learning_rate": 0.0004998342461793328,
|
|
"loss": 7.1527,
|
|
"mean_token_accuracy": 0.11332457587122917,
|
|
"num_tokens": 5407083.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 7.2023365020751955,
|
|
"epoch": 0.3160667251975417,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004998315359522538,
|
|
"loss": 7.0363,
|
|
"mean_token_accuracy": 0.12925028875470163,
|
|
"num_tokens": 5424617.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 7.328793096542358,
|
|
"epoch": 0.3170422397814847,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004998288037554383,
|
|
"loss": 7.1895,
|
|
"mean_token_accuracy": 0.11991029530763626,
|
|
"num_tokens": 5440913.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 7.3388244152069095,
|
|
"epoch": 0.3180177543654278,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004998260495891535,
|
|
"loss": 7.2081,
|
|
"mean_token_accuracy": 0.11506202220916747,
|
|
"num_tokens": 5457157.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 7.34562315940857,
|
|
"epoch": 0.3189932689493708,
|
|
"grad_norm": 0.64453125,
|
|
"learning_rate": 0.0004998232734536685,
|
|
"loss": 7.1309,
|
|
"mean_token_accuracy": 0.11558853089809418,
|
|
"num_tokens": 5474520.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 7.379280471801758,
|
|
"epoch": 0.3199687835333138,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998204753492544,
|
|
"loss": 7.1992,
|
|
"mean_token_accuracy": 0.11453557461500168,
|
|
"num_tokens": 5490599.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 7.365497016906739,
|
|
"epoch": 0.32094429811725683,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004998176552761848,
|
|
"loss": 7.2678,
|
|
"mean_token_accuracy": 0.10158305242657661,
|
|
"num_tokens": 5506714.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 7.373086643218994,
|
|
"epoch": 0.3219198127011999,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004998148132347352,
|
|
"loss": 7.221,
|
|
"mean_token_accuracy": 0.10766603276133538,
|
|
"num_tokens": 5522894.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 7.307815074920654,
|
|
"epoch": 0.3228953272851429,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004998119492251832,
|
|
"loss": 7.099,
|
|
"mean_token_accuracy": 0.11964272856712341,
|
|
"num_tokens": 5540054.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 7.383569002151489,
|
|
"epoch": 0.32387084186908593,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998090632478088,
|
|
"loss": 7.2552,
|
|
"mean_token_accuracy": 0.1003120444715023,
|
|
"num_tokens": 5556189.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 7.420545959472657,
|
|
"epoch": 0.32484635645302895,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.000499806155302894,
|
|
"loss": 7.2685,
|
|
"mean_token_accuracy": 0.10375322699546814,
|
|
"num_tokens": 5572562.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 7.390063381195068,
|
|
"epoch": 0.325821871036972,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.000499803225390723,
|
|
"loss": 7.2527,
|
|
"mean_token_accuracy": 0.10695536509156227,
|
|
"num_tokens": 5588992.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 7.4009096145629885,
|
|
"epoch": 0.32679738562091504,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004998002735115819,
|
|
"loss": 7.1757,
|
|
"mean_token_accuracy": 0.11011699885129929,
|
|
"num_tokens": 5604143.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 7.338191652297974,
|
|
"epoch": 0.32777290020485805,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004997972996657593,
|
|
"loss": 7.3027,
|
|
"mean_token_accuracy": 0.09990110099315644,
|
|
"num_tokens": 5620887.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 7.4250908374786375,
|
|
"epoch": 0.32874841478880107,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004997943038535459,
|
|
"loss": 7.2363,
|
|
"mean_token_accuracy": 0.11051089987158776,
|
|
"num_tokens": 5637156.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 7.357939052581787,
|
|
"epoch": 0.32972392937274414,
|
|
"grad_norm": 0.69921875,
|
|
"learning_rate": 0.0004997912860752341,
|
|
"loss": 7.1842,
|
|
"mean_token_accuracy": 0.10788781493902207,
|
|
"num_tokens": 5654024.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 7.352538108825684,
|
|
"epoch": 0.33069944395668716,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997882463311192,
|
|
"loss": 7.1334,
|
|
"mean_token_accuracy": 0.11298866793513299,
|
|
"num_tokens": 5671538.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 7.3202063083648685,
|
|
"epoch": 0.33167495854063017,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004997851846214979,
|
|
"loss": 7.1849,
|
|
"mean_token_accuracy": 0.11629349514842033,
|
|
"num_tokens": 5688788.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 7.302315759658813,
|
|
"epoch": 0.3326504731245732,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004997821009466695,
|
|
"loss": 7.1253,
|
|
"mean_token_accuracy": 0.11605177596211433,
|
|
"num_tokens": 5706066.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 7.300340795516968,
|
|
"epoch": 0.33362598770851626,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997789953069354,
|
|
"loss": 7.1025,
|
|
"mean_token_accuracy": 0.11065095141530037,
|
|
"num_tokens": 5722100.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 7.327347612380981,
|
|
"epoch": 0.3346015022924593,
|
|
"grad_norm": 0.6796875,
|
|
"learning_rate": 0.0004997758677025989,
|
|
"loss": 7.2352,
|
|
"mean_token_accuracy": 0.10814947485923768,
|
|
"num_tokens": 5739068.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 7.340763235092163,
|
|
"epoch": 0.3355770168764023,
|
|
"grad_norm": 0.69921875,
|
|
"learning_rate": 0.0004997727181339658,
|
|
"loss": 7.2012,
|
|
"mean_token_accuracy": 0.10828282088041305,
|
|
"num_tokens": 5756147.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 7.36230993270874,
|
|
"epoch": 0.3365525314603453,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004997695466013438,
|
|
"loss": 7.1668,
|
|
"mean_token_accuracy": 0.1097688615322113,
|
|
"num_tokens": 5772157.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 7.358744096755982,
|
|
"epoch": 0.3375280460442884,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004997663531050427,
|
|
"loss": 7.2051,
|
|
"mean_token_accuracy": 0.11012494564056396,
|
|
"num_tokens": 5788128.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 7.300439834594727,
|
|
"epoch": 0.3385035606282314,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004997631376453749,
|
|
"loss": 7.1783,
|
|
"mean_token_accuracy": 0.11115790754556656,
|
|
"num_tokens": 5804793.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 7.296383476257324,
|
|
"epoch": 0.3394790752121744,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004997599002226541,
|
|
"loss": 7.1114,
|
|
"mean_token_accuracy": 0.11314733251929283,
|
|
"num_tokens": 5822409.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 7.250304651260376,
|
|
"epoch": 0.3404545897961175,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499756640837197,
|
|
"loss": 7.1525,
|
|
"mean_token_accuracy": 0.1107781283557415,
|
|
"num_tokens": 5839023.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 7.371572017669678,
|
|
"epoch": 0.3414301043800605,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.000499753359489322,
|
|
"loss": 7.1678,
|
|
"mean_token_accuracy": 0.10706163644790649,
|
|
"num_tokens": 5855804.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 7.260924053192139,
|
|
"epoch": 0.3424056189640035,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004997500561793498,
|
|
"loss": 7.1683,
|
|
"mean_token_accuracy": 0.1108716905117035,
|
|
"num_tokens": 5872372.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 7.425952625274658,
|
|
"epoch": 0.3433811335479465,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004997467309076031,
|
|
"loss": 7.2114,
|
|
"mean_token_accuracy": 0.1058623306453228,
|
|
"num_tokens": 5888666.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 7.203307580947876,
|
|
"epoch": 0.3443566481318896,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004997433836744069,
|
|
"loss": 7.1538,
|
|
"mean_token_accuracy": 0.1110640175640583,
|
|
"num_tokens": 5905577.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 7.353317165374756,
|
|
"epoch": 0.3453321627158326,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004997400144800882,
|
|
"loss": 7.1263,
|
|
"mean_token_accuracy": 0.11214198097586632,
|
|
"num_tokens": 5922570.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 7.180663681030273,
|
|
"epoch": 0.34630767729977563,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997366233249762,
|
|
"loss": 7.0759,
|
|
"mean_token_accuracy": 0.1237415112555027,
|
|
"num_tokens": 5938995.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 7.281846189498902,
|
|
"epoch": 0.34728319188371864,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004997332102094024,
|
|
"loss": 7.095,
|
|
"mean_token_accuracy": 0.11867170929908752,
|
|
"num_tokens": 5954869.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 7.409283924102783,
|
|
"epoch": 0.3482587064676617,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004997297751337004,
|
|
"loss": 7.2056,
|
|
"mean_token_accuracy": 0.11266031563282013,
|
|
"num_tokens": 5972750.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 7.21663875579834,
|
|
"epoch": 0.34923422105160473,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.0004997263180982055,
|
|
"loss": 7.1203,
|
|
"mean_token_accuracy": 0.11525158882141114,
|
|
"num_tokens": 5989004.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 7.242398023605347,
|
|
"epoch": 0.35020973563554775,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004997228391032559,
|
|
"loss": 7.1336,
|
|
"mean_token_accuracy": 0.1106021262705326,
|
|
"num_tokens": 6004749.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 7.271965169906617,
|
|
"epoch": 0.35118525021949076,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004997193381491913,
|
|
"loss": 7.0186,
|
|
"mean_token_accuracy": 0.11608157455921173,
|
|
"num_tokens": 6022235.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 7.253506374359131,
|
|
"epoch": 0.35216076480343383,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000499715815236354,
|
|
"loss": 7.1938,
|
|
"mean_token_accuracy": 0.1065413273870945,
|
|
"num_tokens": 6039194.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 7.348612976074219,
|
|
"epoch": 0.35313627938737685,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.000499712270365088,
|
|
"loss": 7.0573,
|
|
"mean_token_accuracy": 0.11130550652742385,
|
|
"num_tokens": 6055376.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 7.285213661193848,
|
|
"epoch": 0.35411179397131987,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004997087035357398,
|
|
"loss": 7.1085,
|
|
"mean_token_accuracy": 0.11257182136178016,
|
|
"num_tokens": 6071105.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 7.185001993179322,
|
|
"epoch": 0.3550873085552629,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004997051147486582,
|
|
"loss": 7.0481,
|
|
"mean_token_accuracy": 0.11566854268312454,
|
|
"num_tokens": 6087964.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 7.231231546401977,
|
|
"epoch": 0.35606282313920595,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004997015040041935,
|
|
"loss": 7.1079,
|
|
"mean_token_accuracy": 0.10794939324259759,
|
|
"num_tokens": 6105245.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 7.218174982070923,
|
|
"epoch": 0.35703833772314897,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004996978713026986,
|
|
"loss": 7.0645,
|
|
"mean_token_accuracy": 0.11960886195302009,
|
|
"num_tokens": 6121736.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 7.306903123855591,
|
|
"epoch": 0.358013852307092,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004996942166445287,
|
|
"loss": 7.1124,
|
|
"mean_token_accuracy": 0.11296163201332092,
|
|
"num_tokens": 6137751.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 7.246757125854492,
|
|
"epoch": 0.358989366891035,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004996905400300407,
|
|
"loss": 7.1722,
|
|
"mean_token_accuracy": 0.11314689144492149,
|
|
"num_tokens": 6154655.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 7.333488273620605,
|
|
"epoch": 0.35996488147497807,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.000499686841459594,
|
|
"loss": 7.1761,
|
|
"mean_token_accuracy": 0.10916234776377678,
|
|
"num_tokens": 6172230.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 7.245674562454224,
|
|
"epoch": 0.3609403960589211,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004996831209335497,
|
|
"loss": 7.1167,
|
|
"mean_token_accuracy": 0.10682919770479202,
|
|
"num_tokens": 6188520.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 7.304710102081299,
|
|
"epoch": 0.3619159106428641,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.0004996793784522719,
|
|
"loss": 7.1444,
|
|
"mean_token_accuracy": 0.1107605941593647,
|
|
"num_tokens": 6205555.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 7.308576536178589,
|
|
"epoch": 0.3628914252268071,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004996756140161259,
|
|
"loss": 7.137,
|
|
"mean_token_accuracy": 0.11305367797613144,
|
|
"num_tokens": 6223548.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 7.237602376937867,
|
|
"epoch": 0.3638669398107502,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004996718276254797,
|
|
"loss": 7.1446,
|
|
"mean_token_accuracy": 0.10687385573983192,
|
|
"num_tokens": 6239266.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 7.311763906478882,
|
|
"epoch": 0.3648424543946932,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004996680192807032,
|
|
"loss": 7.1103,
|
|
"mean_token_accuracy": 0.11415550112724304,
|
|
"num_tokens": 6255020.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 7.2628981590271,
|
|
"epoch": 0.3658179689786362,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004996641889821686,
|
|
"loss": 7.0561,
|
|
"mean_token_accuracy": 0.10903556793928146,
|
|
"num_tokens": 6272774.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 7.241775321960449,
|
|
"epoch": 0.36679348356257924,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004996603367302502,
|
|
"loss": 7.0623,
|
|
"mean_token_accuracy": 0.11404155045747758,
|
|
"num_tokens": 6290478.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 7.243292140960693,
|
|
"epoch": 0.3677689981465223,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.0004996564625253244,
|
|
"loss": 7.1434,
|
|
"mean_token_accuracy": 0.11211170926690102,
|
|
"num_tokens": 6308003.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 7.27335000038147,
|
|
"epoch": 0.3687445127304653,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004996525663677697,
|
|
"loss": 7.1017,
|
|
"mean_token_accuracy": 0.10900750830769539,
|
|
"num_tokens": 6325748.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 7.2766975402832035,
|
|
"epoch": 0.36972002731440834,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.000499648648257967,
|
|
"loss": 7.0383,
|
|
"mean_token_accuracy": 0.12426020875573159,
|
|
"num_tokens": 6344031.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 7.189545965194702,
|
|
"epoch": 0.37069554189835136,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.000499644708196299,
|
|
"loss": 7.1028,
|
|
"mean_token_accuracy": 0.1133454717695713,
|
|
"num_tokens": 6359821.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 7.167187023162842,
|
|
"epoch": 0.3716710564822944,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004996407461831507,
|
|
"loss": 6.9456,
|
|
"mean_token_accuracy": 0.1260436162352562,
|
|
"num_tokens": 6376464.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 7.296348905563354,
|
|
"epoch": 0.37264657106623744,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004996367622189094,
|
|
"loss": 7.1198,
|
|
"mean_token_accuracy": 0.1087517760694027,
|
|
"num_tokens": 6392415.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 7.1976234912872314,
|
|
"epoch": 0.37362208565018046,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004996327563039643,
|
|
"loss": 7.1297,
|
|
"mean_token_accuracy": 0.10959314480423928,
|
|
"num_tokens": 6409151.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 7.263360643386841,
|
|
"epoch": 0.3745976002341235,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004996287284387068,
|
|
"loss": 7.0703,
|
|
"mean_token_accuracy": 0.11664813607931138,
|
|
"num_tokens": 6426997.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 7.25260739326477,
|
|
"epoch": 0.37557311481806654,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004996246786235306,
|
|
"loss": 7.0849,
|
|
"mean_token_accuracy": 0.11517348885536194,
|
|
"num_tokens": 6442871.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 7.1664557456970215,
|
|
"epoch": 0.37654862940200956,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004996206068588314,
|
|
"loss": 7.077,
|
|
"mean_token_accuracy": 0.11249651536345481,
|
|
"num_tokens": 6459677.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 7.309895324707031,
|
|
"epoch": 0.3775241439859526,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004996165131450071,
|
|
"loss": 7.2022,
|
|
"mean_token_accuracy": 0.10661727115511895,
|
|
"num_tokens": 6477239.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 7.2785297393798825,
|
|
"epoch": 0.37849965856989565,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004996123974824576,
|
|
"loss": 7.0671,
|
|
"mean_token_accuracy": 0.1197501078248024,
|
|
"num_tokens": 6493277.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 7.1475608348846436,
|
|
"epoch": 0.37947517315383866,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004996082598715852,
|
|
"loss": 7.0766,
|
|
"mean_token_accuracy": 0.11377091929316521,
|
|
"num_tokens": 6509204.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 7.211893129348755,
|
|
"epoch": 0.3804506877377817,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000499604100312794,
|
|
"loss": 6.9508,
|
|
"mean_token_accuracy": 0.12616619616746902,
|
|
"num_tokens": 6525486.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 7.141159534454346,
|
|
"epoch": 0.3814262023217247,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004995999188064908,
|
|
"loss": 7.1537,
|
|
"mean_token_accuracy": 0.10739106014370918,
|
|
"num_tokens": 6542227.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 7.345539331436157,
|
|
"epoch": 0.38240171690566777,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000499595715353084,
|
|
"loss": 7.2156,
|
|
"mean_token_accuracy": 0.1026027925312519,
|
|
"num_tokens": 6558951.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 7.271983861923218,
|
|
"epoch": 0.3833772314896108,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004995914899529844,
|
|
"loss": 7.1239,
|
|
"mean_token_accuracy": 0.11046183109283447,
|
|
"num_tokens": 6574696.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 7.303521347045899,
|
|
"epoch": 0.3843527460735538,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004995872426066048,
|
|
"loss": 7.1337,
|
|
"mean_token_accuracy": 0.1097158245742321,
|
|
"num_tokens": 6591628.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 7.247618675231934,
|
|
"epoch": 0.3853282606574968,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004995829733143602,
|
|
"loss": 7.0381,
|
|
"mean_token_accuracy": 0.11576716899871826,
|
|
"num_tokens": 6608107.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 7.224512672424316,
|
|
"epoch": 0.3863037752414399,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.000499578682076668,
|
|
"loss": 7.1625,
|
|
"mean_token_accuracy": 0.11688075736165046,
|
|
"num_tokens": 6626699.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 7.352358055114746,
|
|
"epoch": 0.3872792898253829,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004995743688939474,
|
|
"loss": 7.187,
|
|
"mean_token_accuracy": 0.09994767829775811,
|
|
"num_tokens": 6644540.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 7.222046613693237,
|
|
"epoch": 0.3882548044093259,
|
|
"grad_norm": 0.703125,
|
|
"learning_rate": 0.0004995700337666199,
|
|
"loss": 7.1305,
|
|
"mean_token_accuracy": 0.10689185112714768,
|
|
"num_tokens": 6660653.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 7.299875974655151,
|
|
"epoch": 0.38923031899326893,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.000499565676695109,
|
|
"loss": 7.1156,
|
|
"mean_token_accuracy": 0.10829658955335617,
|
|
"num_tokens": 6677553.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 7.261008453369141,
|
|
"epoch": 0.390205833577212,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004995612976798406,
|
|
"loss": 7.1023,
|
|
"mean_token_accuracy": 0.10821453481912613,
|
|
"num_tokens": 6695274.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 7.187166833877564,
|
|
"epoch": 0.391181348161155,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.0004995568967212425,
|
|
"loss": 7.0511,
|
|
"mean_token_accuracy": 0.11570428013801574,
|
|
"num_tokens": 6711166.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 7.146482372283936,
|
|
"epoch": 0.39215686274509803,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004995524738197448,
|
|
"loss": 7.0174,
|
|
"mean_token_accuracy": 0.11494055837392807,
|
|
"num_tokens": 6728827.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 7.1518950939178465,
|
|
"epoch": 0.39313237732904105,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004995480289757796,
|
|
"loss": 6.9904,
|
|
"mean_token_accuracy": 0.12252861484885216,
|
|
"num_tokens": 6745901.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 7.176534938812256,
|
|
"epoch": 0.3941078919129841,
|
|
"grad_norm": 0.6640625,
|
|
"learning_rate": 0.0004995435621897815,
|
|
"loss": 6.974,
|
|
"mean_token_accuracy": 0.12089047506451607,
|
|
"num_tokens": 6762176.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 7.1775041103363035,
|
|
"epoch": 0.39508340649692714,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004995390734621867,
|
|
"loss": 7.1308,
|
|
"mean_token_accuracy": 0.1080321915447712,
|
|
"num_tokens": 6779322.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 7.353971719741821,
|
|
"epoch": 0.39605892108087015,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004995345627934338,
|
|
"loss": 7.056,
|
|
"mean_token_accuracy": 0.11802642568945884,
|
|
"num_tokens": 6794293.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.9723522663116455,
|
|
"epoch": 0.39703443566481317,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004995300301839637,
|
|
"loss": 6.8772,
|
|
"mean_token_accuracy": 0.13384915441274642,
|
|
"num_tokens": 6812880.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 7.228035497665405,
|
|
"epoch": 0.39800995024875624,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004995254756342194,
|
|
"loss": 7.0977,
|
|
"mean_token_accuracy": 0.1094105526804924,
|
|
"num_tokens": 6829230.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 7.2402630805969235,
|
|
"epoch": 0.39898546483269925,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004995208991446458,
|
|
"loss": 7.0857,
|
|
"mean_token_accuracy": 0.11126495227217674,
|
|
"num_tokens": 6846787.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 7.175650978088379,
|
|
"epoch": 0.39996097941664227,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995163007156902,
|
|
"loss": 6.9601,
|
|
"mean_token_accuracy": 0.1128228485584259,
|
|
"num_tokens": 6862990.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 7.260164356231689,
|
|
"epoch": 0.4009364940005853,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004995116803478018,
|
|
"loss": 7.1035,
|
|
"mean_token_accuracy": 0.11000586748123169,
|
|
"num_tokens": 6879170.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 7.151089239120483,
|
|
"epoch": 0.40191200858452836,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004995070380414321,
|
|
"loss": 7.089,
|
|
"mean_token_accuracy": 0.10915887728333473,
|
|
"num_tokens": 6895635.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 7.192745923995972,
|
|
"epoch": 0.4028875231684714,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000499502373797035,
|
|
"loss": 6.9965,
|
|
"mean_token_accuracy": 0.11772431656718255,
|
|
"num_tokens": 6912836.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 7.169298124313355,
|
|
"epoch": 0.4038630377524144,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000499497687615066,
|
|
"loss": 7.0363,
|
|
"mean_token_accuracy": 0.12014092653989791,
|
|
"num_tokens": 6929507.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 7.242495536804199,
|
|
"epoch": 0.4048385523363574,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000499492979495983,
|
|
"loss": 7.0704,
|
|
"mean_token_accuracy": 0.10755309760570526,
|
|
"num_tokens": 6946527.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 7.223427963256836,
|
|
"epoch": 0.4058140669203005,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004994882494402462,
|
|
"loss": 7.0539,
|
|
"mean_token_accuracy": 0.11421060264110565,
|
|
"num_tokens": 6962582.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 7.19104118347168,
|
|
"epoch": 0.4067895815042435,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004994834974483178,
|
|
"loss": 7.0277,
|
|
"mean_token_accuracy": 0.11575962379574775,
|
|
"num_tokens": 6979389.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 7.1313694477081295,
|
|
"epoch": 0.4077650960881865,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004994787235206621,
|
|
"loss": 7.019,
|
|
"mean_token_accuracy": 0.11551673784852028,
|
|
"num_tokens": 6996637.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 7.241458940505981,
|
|
"epoch": 0.4087406106721295,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004994739276577456,
|
|
"loss": 7.1171,
|
|
"mean_token_accuracy": 0.10805290937423706,
|
|
"num_tokens": 7013013.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 7.170071363449097,
|
|
"epoch": 0.4097161252560726,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004994691098600369,
|
|
"loss": 7.0776,
|
|
"mean_token_accuracy": 0.11683185324072838,
|
|
"num_tokens": 7031476.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 7.2697829246521,
|
|
"epoch": 0.4106916398400156,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004994642701280068,
|
|
"loss": 6.9868,
|
|
"mean_token_accuracy": 0.11399012506008148,
|
|
"num_tokens": 7047424.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 7.187478828430176,
|
|
"epoch": 0.4116671544239586,
|
|
"grad_norm": 0.68359375,
|
|
"learning_rate": 0.0004994594084621282,
|
|
"loss": 7.0799,
|
|
"mean_token_accuracy": 0.11093296855688095,
|
|
"num_tokens": 7063793.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 7.3022997856140135,
|
|
"epoch": 0.41264266900790164,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004994545248628762,
|
|
"loss": 7.1182,
|
|
"mean_token_accuracy": 0.10961232632398606,
|
|
"num_tokens": 7079026.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 7.164968585968017,
|
|
"epoch": 0.4136181835918447,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000499449619330728,
|
|
"loss": 7.0457,
|
|
"mean_token_accuracy": 0.11346296891570092,
|
|
"num_tokens": 7097524.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 7.20493860244751,
|
|
"epoch": 0.41459369817578773,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.000499444691866163,
|
|
"loss": 7.1198,
|
|
"mean_token_accuracy": 0.10945150628685951,
|
|
"num_tokens": 7115514.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 7.2198486328125,
|
|
"epoch": 0.41556921275973074,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004994397424696625,
|
|
"loss": 7.0593,
|
|
"mean_token_accuracy": 0.11467726454138756,
|
|
"num_tokens": 7132589.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 7.19329047203064,
|
|
"epoch": 0.4165447273436738,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004994347711417105,
|
|
"loss": 7.0692,
|
|
"mean_token_accuracy": 0.10977566614747047,
|
|
"num_tokens": 7149416.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 7.157116937637329,
|
|
"epoch": 0.41752024192761683,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004994297778827924,
|
|
"loss": 7.0036,
|
|
"mean_token_accuracy": 0.11760117933154106,
|
|
"num_tokens": 7165763.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 7.109394168853759,
|
|
"epoch": 0.41849575651155985,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004994247626933964,
|
|
"loss": 6.9874,
|
|
"mean_token_accuracy": 0.12286769747734069,
|
|
"num_tokens": 7183131.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 7.155841255187989,
|
|
"epoch": 0.41947127109550286,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004994197255740124,
|
|
"loss": 7.0219,
|
|
"mean_token_accuracy": 0.11699268147349358,
|
|
"num_tokens": 7200467.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 7.1444660186767575,
|
|
"epoch": 0.42044678567944593,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004994146665251327,
|
|
"loss": 7.0043,
|
|
"mean_token_accuracy": 0.11433120444417,
|
|
"num_tokens": 7217311.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 7.217905759811401,
|
|
"epoch": 0.42142230026338895,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004994095855472516,
|
|
"loss": 7.0209,
|
|
"mean_token_accuracy": 0.1175784558057785,
|
|
"num_tokens": 7235244.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 7.1584502220153805,
|
|
"epoch": 0.42239781484733196,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.0004994044826408656,
|
|
"loss": 7.0469,
|
|
"mean_token_accuracy": 0.11080644354224205,
|
|
"num_tokens": 7252235.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 7.209628391265869,
|
|
"epoch": 0.423373329431275,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004993993578064733,
|
|
"loss": 7.0503,
|
|
"mean_token_accuracy": 0.11199532449245453,
|
|
"num_tokens": 7269367.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 7.252705907821655,
|
|
"epoch": 0.42434884401521805,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004993942110445756,
|
|
"loss": 7.0388,
|
|
"mean_token_accuracy": 0.11196756064891815,
|
|
"num_tokens": 7287198.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 7.162608671188354,
|
|
"epoch": 0.42532435859916107,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004993890423556753,
|
|
"loss": 6.9824,
|
|
"mean_token_accuracy": 0.11178981512784958,
|
|
"num_tokens": 7302356.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 7.153040552139283,
|
|
"epoch": 0.4262998731831041,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004993838517402775,
|
|
"loss": 6.9713,
|
|
"mean_token_accuracy": 0.12076517716050147,
|
|
"num_tokens": 7318530.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 7.195984268188477,
|
|
"epoch": 0.4272753877670471,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.0004993786391988894,
|
|
"loss": 6.9641,
|
|
"mean_token_accuracy": 0.11528254747390747,
|
|
"num_tokens": 7335195.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 7.076996326446533,
|
|
"epoch": 0.42825090235099017,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004993734047320206,
|
|
"loss": 6.975,
|
|
"mean_token_accuracy": 0.11309642419219017,
|
|
"num_tokens": 7352233.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 7.198031425476074,
|
|
"epoch": 0.4292264169349332,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004993681483401821,
|
|
"loss": 7.0177,
|
|
"mean_token_accuracy": 0.1178817830979824,
|
|
"num_tokens": 7368569.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 7.138528823852539,
|
|
"epoch": 0.4302019315188762,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004993628700238879,
|
|
"loss": 7.0605,
|
|
"mean_token_accuracy": 0.11159829273819924,
|
|
"num_tokens": 7384669.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 7.243989372253418,
|
|
"epoch": 0.4311774461028192,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004993575697836537,
|
|
"loss": 7.0764,
|
|
"mean_token_accuracy": 0.10855081602931023,
|
|
"num_tokens": 7401833.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 7.177517652511597,
|
|
"epoch": 0.4321529606867623,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004993522476199975,
|
|
"loss": 6.9746,
|
|
"mean_token_accuracy": 0.11231087371706963,
|
|
"num_tokens": 7418663.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 7.1457499980926515,
|
|
"epoch": 0.4331284752707053,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004993469035334392,
|
|
"loss": 6.9562,
|
|
"mean_token_accuracy": 0.12267854809761047,
|
|
"num_tokens": 7434701.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 7.158255243301392,
|
|
"epoch": 0.4341039898546483,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.000499341537524501,
|
|
"loss": 7.0339,
|
|
"mean_token_accuracy": 0.10957926958799362,
|
|
"num_tokens": 7450154.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 7.012423801422119,
|
|
"epoch": 0.43507950443859134,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004993361495937074,
|
|
"loss": 6.8259,
|
|
"mean_token_accuracy": 0.1353221409022808,
|
|
"num_tokens": 7468110.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 7.148668670654297,
|
|
"epoch": 0.4360550190225344,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004993307397415848,
|
|
"loss": 6.9687,
|
|
"mean_token_accuracy": 0.11352093443274498,
|
|
"num_tokens": 7482962.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 7.223632144927978,
|
|
"epoch": 0.4370305336064774,
|
|
"grad_norm": 0.703125,
|
|
"learning_rate": 0.0004993253079686619,
|
|
"loss": 7.0961,
|
|
"mean_token_accuracy": 0.1094274289906025,
|
|
"num_tokens": 7499116.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 7.205734777450561,
|
|
"epoch": 0.43800604819042044,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004993198542754692,
|
|
"loss": 7.0599,
|
|
"mean_token_accuracy": 0.11345275118947029,
|
|
"num_tokens": 7515765.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 7.174308013916016,
|
|
"epoch": 0.43898156277436345,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004993143786625401,
|
|
"loss": 7.0388,
|
|
"mean_token_accuracy": 0.11509429663419724,
|
|
"num_tokens": 7532074.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 7.064720487594604,
|
|
"epoch": 0.4399570773583065,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004993088811304092,
|
|
"loss": 6.8781,
|
|
"mean_token_accuracy": 0.12545035257935525,
|
|
"num_tokens": 7547704.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 7.157081985473633,
|
|
"epoch": 0.44093259194224954,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004993033616796139,
|
|
"loss": 6.9942,
|
|
"mean_token_accuracy": 0.11518247872591018,
|
|
"num_tokens": 7563317.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 7.077218532562256,
|
|
"epoch": 0.44190810652619256,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.0004992978203106936,
|
|
"loss": 6.9864,
|
|
"mean_token_accuracy": 0.1106504775583744,
|
|
"num_tokens": 7580770.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 7.1526469707489015,
|
|
"epoch": 0.4428836211101356,
|
|
"grad_norm": 0.70703125,
|
|
"learning_rate": 0.0004992922570241896,
|
|
"loss": 6.9601,
|
|
"mean_token_accuracy": 0.11600121185183525,
|
|
"num_tokens": 7598181.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 7.17113733291626,
|
|
"epoch": 0.44385913569407864,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004992866718206457,
|
|
"loss": 6.9712,
|
|
"mean_token_accuracy": 0.11577035710215569,
|
|
"num_tokens": 7613739.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 7.134070205688476,
|
|
"epoch": 0.44483465027802166,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004992810647006077,
|
|
"loss": 7.0444,
|
|
"mean_token_accuracy": 0.1104633316397667,
|
|
"num_tokens": 7629297.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 7.236656618118286,
|
|
"epoch": 0.4458101648619647,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004992754356646234,
|
|
"loss": 7.0396,
|
|
"mean_token_accuracy": 0.11165096834301949,
|
|
"num_tokens": 7645273.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 7.185686111450195,
|
|
"epoch": 0.4467856794459077,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.0004992697847132427,
|
|
"loss": 6.986,
|
|
"mean_token_accuracy": 0.11109313443303108,
|
|
"num_tokens": 7661296.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.987871694564819,
|
|
"epoch": 0.44776119402985076,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.000499264111847018,
|
|
"loss": 6.9891,
|
|
"mean_token_accuracy": 0.11404722481966019,
|
|
"num_tokens": 7678658.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 7.233692026138305,
|
|
"epoch": 0.4487367086137938,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004992584170665037,
|
|
"loss": 7.0149,
|
|
"mean_token_accuracy": 0.11008156463503838,
|
|
"num_tokens": 7693678.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 7.112862920761108,
|
|
"epoch": 0.4497122231977368,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000499252700372256,
|
|
"loss": 7.0179,
|
|
"mean_token_accuracy": 0.11447776332497597,
|
|
"num_tokens": 7709526.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 7.164843320846558,
|
|
"epoch": 0.4506877377816798,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004992469617648337,
|
|
"loss": 6.9164,
|
|
"mean_token_accuracy": 0.11364173144102097,
|
|
"num_tokens": 7725055.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.968656778335571,
|
|
"epoch": 0.4516632523656229,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004992412012447976,
|
|
"loss": 6.8243,
|
|
"mean_token_accuracy": 0.1330489881336689,
|
|
"num_tokens": 7742047.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 7.127957963943482,
|
|
"epoch": 0.4526387669495659,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004992354188127105,
|
|
"loss": 6.9932,
|
|
"mean_token_accuracy": 0.11281251534819603,
|
|
"num_tokens": 7758283.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 7.13198881149292,
|
|
"epoch": 0.4536142815335089,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004992296144691375,
|
|
"loss": 6.9322,
|
|
"mean_token_accuracy": 0.11692915037274361,
|
|
"num_tokens": 7774660.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 7.0494366645812985,
|
|
"epoch": 0.454589796117452,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004992237882146456,
|
|
"loss": 6.9336,
|
|
"mean_token_accuracy": 0.12027623504400253,
|
|
"num_tokens": 7792147.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 7.085804891586304,
|
|
"epoch": 0.455565310701395,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004992179400498044,
|
|
"loss": 6.884,
|
|
"mean_token_accuracy": 0.11990112587809562,
|
|
"num_tokens": 7809021.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 7.126865386962891,
|
|
"epoch": 0.456540825285338,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004992120699751852,
|
|
"loss": 6.9547,
|
|
"mean_token_accuracy": 0.11495627984404563,
|
|
"num_tokens": 7825074.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.991373491287232,
|
|
"epoch": 0.45751633986928103,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004992061779913616,
|
|
"loss": 6.882,
|
|
"mean_token_accuracy": 0.12588541582226753,
|
|
"num_tokens": 7843413.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 7.136522054672241,
|
|
"epoch": 0.4584918544532241,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004992002640989094,
|
|
"loss": 6.9829,
|
|
"mean_token_accuracy": 0.10877103731036186,
|
|
"num_tokens": 7859874.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 7.0421689510345455,
|
|
"epoch": 0.4594673690371671,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004991943282984065,
|
|
"loss": 6.9006,
|
|
"mean_token_accuracy": 0.12029767408967018,
|
|
"num_tokens": 7877302.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 7.098082065582275,
|
|
"epoch": 0.46044288362111013,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004991883705904328,
|
|
"loss": 7.0204,
|
|
"mean_token_accuracy": 0.11330386027693748,
|
|
"num_tokens": 7893207.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 7.0267304420471195,
|
|
"epoch": 0.46141839820505315,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004991823909755705,
|
|
"loss": 6.8693,
|
|
"mean_token_accuracy": 0.12727298960089684,
|
|
"num_tokens": 7910239.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 7.135089111328125,
|
|
"epoch": 0.4623939127889962,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004991763894544041,
|
|
"loss": 6.9956,
|
|
"mean_token_accuracy": 0.11252414360642433,
|
|
"num_tokens": 7928030.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 7.087430810928344,
|
|
"epoch": 0.46336942737293924,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004991703660275199,
|
|
"loss": 6.9537,
|
|
"mean_token_accuracy": 0.11425257176160812,
|
|
"num_tokens": 7943653.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 7.1508338928222654,
|
|
"epoch": 0.46434494195688225,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.0004991643206955064,
|
|
"loss": 7.0187,
|
|
"mean_token_accuracy": 0.1106310598552227,
|
|
"num_tokens": 7960564.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 7.126855993270874,
|
|
"epoch": 0.46532045654082527,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004991582534589544,
|
|
"loss": 6.9782,
|
|
"mean_token_accuracy": 0.11728396564722061,
|
|
"num_tokens": 7978045.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 7.158732795715332,
|
|
"epoch": 0.46629597112476834,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004991521643184567,
|
|
"loss": 7.0161,
|
|
"mean_token_accuracy": 0.11397831588983535,
|
|
"num_tokens": 7995074.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 7.136742782592774,
|
|
"epoch": 0.46727148570871135,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004991460532746087,
|
|
"loss": 7.0158,
|
|
"mean_token_accuracy": 0.10939189791679382,
|
|
"num_tokens": 8011800.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 7.1472780227661135,
|
|
"epoch": 0.46824700029265437,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000499139920328007,
|
|
"loss": 7.001,
|
|
"mean_token_accuracy": 0.11125169917941094,
|
|
"num_tokens": 8028090.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 7.1227765560150145,
|
|
"epoch": 0.4692225148765974,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004991337654792512,
|
|
"loss": 6.9313,
|
|
"mean_token_accuracy": 0.11610379964113235,
|
|
"num_tokens": 8044140.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 7.104448366165161,
|
|
"epoch": 0.47019802946054046,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004991275887289427,
|
|
"loss": 6.8733,
|
|
"mean_token_accuracy": 0.11896544992923737,
|
|
"num_tokens": 8060030.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 7.1025842189788815,
|
|
"epoch": 0.47117354404448347,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004991213900776849,
|
|
"loss": 6.9444,
|
|
"mean_token_accuracy": 0.11614150553941727,
|
|
"num_tokens": 8075445.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 7.138435411453247,
|
|
"epoch": 0.4721490586284265,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004991151695260838,
|
|
"loss": 6.9406,
|
|
"mean_token_accuracy": 0.1131170354783535,
|
|
"num_tokens": 8093250.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 7.017556381225586,
|
|
"epoch": 0.4731245732123695,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.000499108927074747,
|
|
"loss": 6.8782,
|
|
"mean_token_accuracy": 0.12963026240468026,
|
|
"num_tokens": 8109615.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 7.0512158393859865,
|
|
"epoch": 0.4741000877963126,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004991026627242846,
|
|
"loss": 6.9899,
|
|
"mean_token_accuracy": 0.11359846070408822,
|
|
"num_tokens": 8126591.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 7.101228904724121,
|
|
"epoch": 0.4750756023802556,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004990963764753088,
|
|
"loss": 6.9083,
|
|
"mean_token_accuracy": 0.11548377051949502,
|
|
"num_tokens": 8141360.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 7.109776735305786,
|
|
"epoch": 0.4760511169641986,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004990900683284337,
|
|
"loss": 7.002,
|
|
"mean_token_accuracy": 0.11828856319189071,
|
|
"num_tokens": 8159688.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 7.081469440460205,
|
|
"epoch": 0.4770266315481416,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004990837382842758,
|
|
"loss": 6.9589,
|
|
"mean_token_accuracy": 0.11527570113539695,
|
|
"num_tokens": 8176887.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.990096187591552,
|
|
"epoch": 0.4780021461320847,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004990773863434537,
|
|
"loss": 6.7791,
|
|
"mean_token_accuracy": 0.12774069532752036,
|
|
"num_tokens": 8193372.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 7.087004041671753,
|
|
"epoch": 0.4789776607160277,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004990710125065879,
|
|
"loss": 6.9977,
|
|
"mean_token_accuracy": 0.11214468628168106,
|
|
"num_tokens": 8209713.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 7.11400089263916,
|
|
"epoch": 0.4799531752999707,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004990646167743015,
|
|
"loss": 6.9882,
|
|
"mean_token_accuracy": 0.11344318985939025,
|
|
"num_tokens": 8226359.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 7.047367954254151,
|
|
"epoch": 0.48092868988391374,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004990581991472193,
|
|
"loss": 6.9662,
|
|
"mean_token_accuracy": 0.1149329237639904,
|
|
"num_tokens": 8243182.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 7.1153247356414795,
|
|
"epoch": 0.4819042044678568,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004990517596259684,
|
|
"loss": 6.9621,
|
|
"mean_token_accuracy": 0.11368496045470237,
|
|
"num_tokens": 8259185.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 7.141877031326294,
|
|
"epoch": 0.4828797190517998,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004990452982111781,
|
|
"loss": 7.0401,
|
|
"mean_token_accuracy": 0.11041902601718903,
|
|
"num_tokens": 8275941.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 7.108094882965088,
|
|
"epoch": 0.48385523363574284,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004990388149034797,
|
|
"loss": 6.9616,
|
|
"mean_token_accuracy": 0.11487062349915504,
|
|
"num_tokens": 8292535.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 7.117975378036499,
|
|
"epoch": 0.48483074821968586,
|
|
"grad_norm": 0.68359375,
|
|
"learning_rate": 0.0004990323097035069,
|
|
"loss": 6.9325,
|
|
"mean_token_accuracy": 0.12068861201405526,
|
|
"num_tokens": 8310562.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 7.053023147583008,
|
|
"epoch": 0.48580626280362893,
|
|
"grad_norm": 0.69921875,
|
|
"learning_rate": 0.0004990257826118952,
|
|
"loss": 6.952,
|
|
"mean_token_accuracy": 0.10922210142016411,
|
|
"num_tokens": 8327241.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 7.062554359436035,
|
|
"epoch": 0.48678177738757195,
|
|
"grad_norm": 0.6875,
|
|
"learning_rate": 0.0004990192336292824,
|
|
"loss": 6.8853,
|
|
"mean_token_accuracy": 0.12106603980064393,
|
|
"num_tokens": 8343516.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.936242532730103,
|
|
"epoch": 0.48775729197151496,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.0004990126627563087,
|
|
"loss": 6.7596,
|
|
"mean_token_accuracy": 0.1254474215209484,
|
|
"num_tokens": 8361809.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.997405242919922,
|
|
"epoch": 0.488732806555458,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004990060699936159,
|
|
"loss": 6.8241,
|
|
"mean_token_accuracy": 0.12973423004150392,
|
|
"num_tokens": 8378632.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 7.076214027404785,
|
|
"epoch": 0.48970832113940105,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004989994553418483,
|
|
"loss": 6.967,
|
|
"mean_token_accuracy": 0.10970980674028397,
|
|
"num_tokens": 8396201.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 7.017474126815796,
|
|
"epoch": 0.49068383572334406,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004989928188016522,
|
|
"loss": 6.857,
|
|
"mean_token_accuracy": 0.12434607595205308,
|
|
"num_tokens": 8412851.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.934906721115112,
|
|
"epoch": 0.4916593503072871,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004989861603736762,
|
|
"loss": 6.6964,
|
|
"mean_token_accuracy": 0.13276463598012925,
|
|
"num_tokens": 8430026.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 7.01360068321228,
|
|
"epoch": 0.49263486489123015,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004989794800585711,
|
|
"loss": 6.9332,
|
|
"mean_token_accuracy": 0.11373277679085732,
|
|
"num_tokens": 8446696.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 7.166025400161743,
|
|
"epoch": 0.49361037947517317,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004989727778569893,
|
|
"loss": 7.0107,
|
|
"mean_token_accuracy": 0.11518367677927017,
|
|
"num_tokens": 8464827.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 7.0952709197998045,
|
|
"epoch": 0.4945858940591162,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004989660537695859,
|
|
"loss": 6.9573,
|
|
"mean_token_accuracy": 0.11457037478685379,
|
|
"num_tokens": 8480185.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.976978826522827,
|
|
"epoch": 0.4955614086430592,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.000498959307797018,
|
|
"loss": 6.8495,
|
|
"mean_token_accuracy": 0.12594428285956383,
|
|
"num_tokens": 8497511.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 7.057211256027221,
|
|
"epoch": 0.49653692322700227,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004989525399399447,
|
|
"loss": 6.9164,
|
|
"mean_token_accuracy": 0.11622816175222397,
|
|
"num_tokens": 8514394.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 7.087595653533936,
|
|
"epoch": 0.4975124378109453,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004989457501990275,
|
|
"loss": 6.9275,
|
|
"mean_token_accuracy": 0.11328752487897872,
|
|
"num_tokens": 8531659.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 7.078902673721314,
|
|
"epoch": 0.4984879523948883,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004989389385749297,
|
|
"loss": 6.968,
|
|
"mean_token_accuracy": 0.11704642698168755,
|
|
"num_tokens": 8547986.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 7.091986656188965,
|
|
"epoch": 0.4994634669788313,
|
|
"grad_norm": 0.6953125,
|
|
"learning_rate": 0.0004989321050683169,
|
|
"loss": 6.9336,
|
|
"mean_token_accuracy": 0.11741236075758935,
|
|
"num_tokens": 8565021.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 7.019861841201783,
|
|
"epoch": 0.5004389815627743,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000498925249679857,
|
|
"loss": 6.92,
|
|
"mean_token_accuracy": 0.11312920749187469,
|
|
"num_tokens": 8582135.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 7.050804996490479,
|
|
"epoch": 0.5014144961467174,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004989183724102196,
|
|
"loss": 6.9426,
|
|
"mean_token_accuracy": 0.11648973152041435,
|
|
"num_tokens": 8599946.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 7.095156240463257,
|
|
"epoch": 0.5023900107306605,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.0004989114732600771,
|
|
"loss": 6.962,
|
|
"mean_token_accuracy": 0.11353963762521743,
|
|
"num_tokens": 8615831.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 7.0172281742095945,
|
|
"epoch": 0.5033655253146034,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004989045522301033,
|
|
"loss": 6.8659,
|
|
"mean_token_accuracy": 0.11678607761859894,
|
|
"num_tokens": 8631886.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 7.130041217803955,
|
|
"epoch": 0.5043410398985465,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004988976093209747,
|
|
"loss": 6.9024,
|
|
"mean_token_accuracy": 0.11544571220874786,
|
|
"num_tokens": 8647520.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 7.008956384658814,
|
|
"epoch": 0.5053165544824895,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004988906445333698,
|
|
"loss": 6.8257,
|
|
"mean_token_accuracy": 0.12740083709359168,
|
|
"num_tokens": 8663995.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 7.0500547885894775,
|
|
"epoch": 0.5062920690664325,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004988836578679691,
|
|
"loss": 6.8837,
|
|
"mean_token_accuracy": 0.11523761749267578,
|
|
"num_tokens": 8680201.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 7.057234573364258,
|
|
"epoch": 0.5072675836503756,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004988766493254552,
|
|
"loss": 6.8811,
|
|
"mean_token_accuracy": 0.12502829283475875,
|
|
"num_tokens": 8696978.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.975452184677124,
|
|
"epoch": 0.5082430982343186,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.000498869618906513,
|
|
"loss": 6.9349,
|
|
"mean_token_accuracy": 0.1191725805401802,
|
|
"num_tokens": 8713335.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 7.085032987594604,
|
|
"epoch": 0.5092186128182616,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004988625666118296,
|
|
"loss": 6.9079,
|
|
"mean_token_accuracy": 0.12075944617390633,
|
|
"num_tokens": 8730722.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 7.009021377563476,
|
|
"epoch": 0.5101941274022047,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.000498855492442094,
|
|
"loss": 6.8423,
|
|
"mean_token_accuracy": 0.11724851801991462,
|
|
"num_tokens": 8747430.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 7.055665969848633,
|
|
"epoch": 0.5111696419861477,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.0004988483963979975,
|
|
"loss": 6.9307,
|
|
"mean_token_accuracy": 0.1153571218252182,
|
|
"num_tokens": 8764817.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 7.095595455169677,
|
|
"epoch": 0.5121451565700907,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004988412784802336,
|
|
"loss": 6.952,
|
|
"mean_token_accuracy": 0.11426069363951682,
|
|
"num_tokens": 8780412.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 7.099550008773804,
|
|
"epoch": 0.5131206711540337,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004988341386894977,
|
|
"loss": 7.0133,
|
|
"mean_token_accuracy": 0.11473828405141831,
|
|
"num_tokens": 8795526.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 7.0228691577911375,
|
|
"epoch": 0.5140961857379768,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004988269770264876,
|
|
"loss": 6.8121,
|
|
"mean_token_accuracy": 0.12404470667243003,
|
|
"num_tokens": 8813568.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 7.096433353424072,
|
|
"epoch": 0.5150717003219198,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004988197934919029,
|
|
"loss": 6.975,
|
|
"mean_token_accuracy": 0.11357465535402297,
|
|
"num_tokens": 8831807.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 7.076529407501221,
|
|
"epoch": 0.5160472149058628,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004988125880864458,
|
|
"loss": 6.9645,
|
|
"mean_token_accuracy": 0.11619440764188767,
|
|
"num_tokens": 8848875.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.94493408203125,
|
|
"epoch": 0.5170227294898059,
|
|
"grad_norm": 0.67578125,
|
|
"learning_rate": 0.0004988053608108203,
|
|
"loss": 6.6698,
|
|
"mean_token_accuracy": 0.12810667157173156,
|
|
"num_tokens": 8866317.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 7.012036466598511,
|
|
"epoch": 0.517998244073749,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004987981116657325,
|
|
"loss": 6.8267,
|
|
"mean_token_accuracy": 0.11821717917919158,
|
|
"num_tokens": 8882543.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 7.038132619857788,
|
|
"epoch": 0.5189737586576919,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004987908406518909,
|
|
"loss": 6.8452,
|
|
"mean_token_accuracy": 0.11478555351495742,
|
|
"num_tokens": 8898640.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 7.044437074661255,
|
|
"epoch": 0.519949273241635,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.000498783547770006,
|
|
"loss": 6.9379,
|
|
"mean_token_accuracy": 0.11549510955810546,
|
|
"num_tokens": 8914649.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 7.070078182220459,
|
|
"epoch": 0.5209247878255779,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004987762330207903,
|
|
"loss": 6.9632,
|
|
"mean_token_accuracy": 0.11580834016203881,
|
|
"num_tokens": 8931585.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.993145561218261,
|
|
"epoch": 0.521900302409521,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004987688964049587,
|
|
"loss": 6.8512,
|
|
"mean_token_accuracy": 0.12186183482408523,
|
|
"num_tokens": 8948827.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.969137239456177,
|
|
"epoch": 0.5228758169934641,
|
|
"grad_norm": 0.69140625,
|
|
"learning_rate": 0.000498761537923228,
|
|
"loss": 6.8188,
|
|
"mean_token_accuracy": 0.12476989179849625,
|
|
"num_tokens": 8965680.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 7.103134489059448,
|
|
"epoch": 0.523851331577407,
|
|
"grad_norm": 0.69140625,
|
|
"learning_rate": 0.0004987541575763175,
|
|
"loss": 6.945,
|
|
"mean_token_accuracy": 0.10933230742812157,
|
|
"num_tokens": 8982813.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 7.053329753875732,
|
|
"epoch": 0.5248268461613501,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.000498746755364948,
|
|
"loss": 6.9238,
|
|
"mean_token_accuracy": 0.11738716661930085,
|
|
"num_tokens": 9000497.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 7.0302845478057865,
|
|
"epoch": 0.5258023607452932,
|
|
"grad_norm": 0.703125,
|
|
"learning_rate": 0.0004987393312898431,
|
|
"loss": 6.852,
|
|
"mean_token_accuracy": 0.11841250211000443,
|
|
"num_tokens": 9016195.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.972050142288208,
|
|
"epoch": 0.5267778753292361,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004987318853517282,
|
|
"loss": 6.8136,
|
|
"mean_token_accuracy": 0.1275354102253914,
|
|
"num_tokens": 9033295.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 7.0185223579406735,
|
|
"epoch": 0.5277533899131792,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004987244175513308,
|
|
"loss": 6.9096,
|
|
"mean_token_accuracy": 0.11717701405286789,
|
|
"num_tokens": 9050725.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 7.055005502700806,
|
|
"epoch": 0.5287289044971223,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004987169278893807,
|
|
"loss": 6.8533,
|
|
"mean_token_accuracy": 0.12087640091776848,
|
|
"num_tokens": 9067842.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 7.043317222595215,
|
|
"epoch": 0.5297044190810652,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004987094163666098,
|
|
"loss": 6.8802,
|
|
"mean_token_accuracy": 0.11303822621703148,
|
|
"num_tokens": 9084602.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.984019565582275,
|
|
"epoch": 0.5306799336650083,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.000498701882983752,
|
|
"loss": 6.8169,
|
|
"mean_token_accuracy": 0.12400035038590432,
|
|
"num_tokens": 9100530.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 7.082251310348511,
|
|
"epoch": 0.5316554482489513,
|
|
"grad_norm": 0.69921875,
|
|
"learning_rate": 0.0004986943277415435,
|
|
"loss": 6.9054,
|
|
"mean_token_accuracy": 0.12150466665625573,
|
|
"num_tokens": 9117304.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.934389734268189,
|
|
"epoch": 0.5326309628328944,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.0004986867506407225,
|
|
"loss": 6.8461,
|
|
"mean_token_accuracy": 0.13145331293344498,
|
|
"num_tokens": 9133974.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 7.023757410049439,
|
|
"epoch": 0.5336064774168374,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004986791516820295,
|
|
"loss": 6.82,
|
|
"mean_token_accuracy": 0.12260211110115052,
|
|
"num_tokens": 9150600.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.958559894561768,
|
|
"epoch": 0.5345819920007804,
|
|
"grad_norm": 0.6875,
|
|
"learning_rate": 0.000498671530866207,
|
|
"loss": 6.8195,
|
|
"mean_token_accuracy": 0.11772075891494752,
|
|
"num_tokens": 9167449.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.999980163574219,
|
|
"epoch": 0.5355575065847235,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004986638881939997,
|
|
"loss": 6.7508,
|
|
"mean_token_accuracy": 0.12078059241175651,
|
|
"num_tokens": 9184570.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 7.025358009338379,
|
|
"epoch": 0.5365330211686665,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004986562236661544,
|
|
"loss": 6.9478,
|
|
"mean_token_accuracy": 0.10966789573431016,
|
|
"num_tokens": 9200537.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 7.055627679824829,
|
|
"epoch": 0.5375085357526095,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.00049864853728342,
|
|
"loss": 6.8321,
|
|
"mean_token_accuracy": 0.12615425363183022,
|
|
"num_tokens": 9217252.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 7.011317777633667,
|
|
"epoch": 0.5384840503365526,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004986408290465476,
|
|
"loss": 6.8942,
|
|
"mean_token_accuracy": 0.11614497005939484,
|
|
"num_tokens": 9234108.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 7.009395360946655,
|
|
"epoch": 0.5394595649204955,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004986330989562906,
|
|
"loss": 6.79,
|
|
"mean_token_accuracy": 0.12128815576434135,
|
|
"num_tokens": 9251017.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.907582473754883,
|
|
"epoch": 0.5404350795044386,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004986253470134042,
|
|
"loss": 6.7643,
|
|
"mean_token_accuracy": 0.12897545844316483,
|
|
"num_tokens": 9267922.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.942857360839843,
|
|
"epoch": 0.5414105940883817,
|
|
"grad_norm": 0.70703125,
|
|
"learning_rate": 0.0004986175732186459,
|
|
"loss": 6.7594,
|
|
"mean_token_accuracy": 0.13300774469971657,
|
|
"num_tokens": 9284954.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 7.067489337921143,
|
|
"epoch": 0.5423861086723246,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004986097775727752,
|
|
"loss": 6.8754,
|
|
"mean_token_accuracy": 0.12139702215790749,
|
|
"num_tokens": 9303306.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.946069002151489,
|
|
"epoch": 0.5433616232562677,
|
|
"grad_norm": 0.68359375,
|
|
"learning_rate": 0.0004986019600765541,
|
|
"loss": 6.7636,
|
|
"mean_token_accuracy": 0.12780117020010948,
|
|
"num_tokens": 9319754.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.997291612625122,
|
|
"epoch": 0.5443371378402108,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004985941207307462,
|
|
"loss": 6.8388,
|
|
"mean_token_accuracy": 0.12043605893850326,
|
|
"num_tokens": 9335736.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.960863447189331,
|
|
"epoch": 0.5453126524241537,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004985862595361179,
|
|
"loss": 6.8276,
|
|
"mean_token_accuracy": 0.1238748125731945,
|
|
"num_tokens": 9350435.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 7.038047218322754,
|
|
"epoch": 0.5462881670080968,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004985783764934372,
|
|
"loss": 6.8846,
|
|
"mean_token_accuracy": 0.11675451174378396,
|
|
"num_tokens": 9367613.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.985388374328613,
|
|
"epoch": 0.5472636815920398,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004985704716034744,
|
|
"loss": 6.7739,
|
|
"mean_token_accuracy": 0.12371559590101242,
|
|
"num_tokens": 9385590.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 7.0262994289398195,
|
|
"epoch": 0.5482391961759828,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004985625448670019,
|
|
"loss": 6.9055,
|
|
"mean_token_accuracy": 0.10927185341715813,
|
|
"num_tokens": 9403286.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 7.065427780151367,
|
|
"epoch": 0.5492147107599259,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004985545962847943,
|
|
"loss": 6.8881,
|
|
"mean_token_accuracy": 0.11537767797708512,
|
|
"num_tokens": 9419880.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 7.033570194244385,
|
|
"epoch": 0.5501902253438689,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004985466258576283,
|
|
"loss": 6.8455,
|
|
"mean_token_accuracy": 0.11745240762829781,
|
|
"num_tokens": 9436579.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 7.046221017837524,
|
|
"epoch": 0.5511657399278119,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004985386335862829,
|
|
"loss": 6.93,
|
|
"mean_token_accuracy": 0.11016375422477723,
|
|
"num_tokens": 9452802.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 7.053445672988891,
|
|
"epoch": 0.552141254511755,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004985306194715387,
|
|
"loss": 6.938,
|
|
"mean_token_accuracy": 0.11385038048028946,
|
|
"num_tokens": 9468297.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 7.024582815170288,
|
|
"epoch": 0.553116769095698,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004985225835141792,
|
|
"loss": 6.9441,
|
|
"mean_token_accuracy": 0.11334621459245682,
|
|
"num_tokens": 9484954.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 7.109255123138428,
|
|
"epoch": 0.554092283679641,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004985145257149895,
|
|
"loss": 6.9819,
|
|
"mean_token_accuracy": 0.11194085255265236,
|
|
"num_tokens": 9502211.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 7.02985258102417,
|
|
"epoch": 0.555067798263584,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004985064460747569,
|
|
"loss": 6.8801,
|
|
"mean_token_accuracy": 0.11415814831852913,
|
|
"num_tokens": 9518103.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.930572509765625,
|
|
"epoch": 0.5560433128475271,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000498498344594271,
|
|
"loss": 6.8082,
|
|
"mean_token_accuracy": 0.1147056095302105,
|
|
"num_tokens": 9534155.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.953532028198242,
|
|
"epoch": 0.5570188274314701,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004984902212743234,
|
|
"loss": 6.8006,
|
|
"mean_token_accuracy": 0.12907804399728776,
|
|
"num_tokens": 9549972.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.932996416091919,
|
|
"epoch": 0.5579943420154131,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004984820761157079,
|
|
"loss": 6.7131,
|
|
"mean_token_accuracy": 0.1321914590895176,
|
|
"num_tokens": 9567306.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 7.030141401290893,
|
|
"epoch": 0.5589698565993562,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004984739091192205,
|
|
"loss": 6.9212,
|
|
"mean_token_accuracy": 0.1166323758661747,
|
|
"num_tokens": 9583488.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.894357776641845,
|
|
"epoch": 0.5599453711832992,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004984657202856592,
|
|
"loss": 6.698,
|
|
"mean_token_accuracy": 0.13180340230464935,
|
|
"num_tokens": 9600030.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.904035568237305,
|
|
"epoch": 0.5609208857672422,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000498457509615824,
|
|
"loss": 6.8267,
|
|
"mean_token_accuracy": 0.12177458480000496,
|
|
"num_tokens": 9615791.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 7.084134531021118,
|
|
"epoch": 0.5618964003511853,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004984492771105175,
|
|
"loss": 6.9083,
|
|
"mean_token_accuracy": 0.11326306611299515,
|
|
"num_tokens": 9630955.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.886215400695801,
|
|
"epoch": 0.5628719149351282,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004984410227705439,
|
|
"loss": 6.8119,
|
|
"mean_token_accuracy": 0.12833485156297683,
|
|
"num_tokens": 9647743.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.921821880340576,
|
|
"epoch": 0.5638474295190713,
|
|
"grad_norm": 0.68359375,
|
|
"learning_rate": 0.0004984327465967101,
|
|
"loss": 6.7455,
|
|
"mean_token_accuracy": 0.12699681594967843,
|
|
"num_tokens": 9665495.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.982145643234253,
|
|
"epoch": 0.5648229441030144,
|
|
"grad_norm": 0.69921875,
|
|
"learning_rate": 0.0004984244485898246,
|
|
"loss": 6.7774,
|
|
"mean_token_accuracy": 0.12316017523407936,
|
|
"num_tokens": 9683489.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.810558557510376,
|
|
"epoch": 0.5657984586869573,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004984161287506982,
|
|
"loss": 6.7105,
|
|
"mean_token_accuracy": 0.14188627004623414,
|
|
"num_tokens": 9700491.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 7.061842060089111,
|
|
"epoch": 0.5667739732709004,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.000498407787080144,
|
|
"loss": 6.8763,
|
|
"mean_token_accuracy": 0.11491131633520127,
|
|
"num_tokens": 9715694.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 7.022202444076538,
|
|
"epoch": 0.5677494878548435,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.000498399423578977,
|
|
"loss": 6.9327,
|
|
"mean_token_accuracy": 0.11375072970986366,
|
|
"num_tokens": 9731317.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 7.0759697437286375,
|
|
"epoch": 0.5687250024387864,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004983910382480146,
|
|
"loss": 6.9049,
|
|
"mean_token_accuracy": 0.1123342789709568,
|
|
"num_tokens": 9747928.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.998634338378906,
|
|
"epoch": 0.5697005170227295,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004983826310880762,
|
|
"loss": 6.841,
|
|
"mean_token_accuracy": 0.11529184207320213,
|
|
"num_tokens": 9765454.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 7.041535997390747,
|
|
"epoch": 0.5706760316066726,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004983742020999832,
|
|
"loss": 6.8941,
|
|
"mean_token_accuracy": 0.11383099108934402,
|
|
"num_tokens": 9782255.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.913339376449585,
|
|
"epoch": 0.5716515461906155,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.0004983657512845593,
|
|
"loss": 6.7069,
|
|
"mean_token_accuracy": 0.12910252287983895,
|
|
"num_tokens": 9798680.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.961237955093384,
|
|
"epoch": 0.5726270607745586,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004983572786426302,
|
|
"loss": 6.8695,
|
|
"mean_token_accuracy": 0.11734185367822647,
|
|
"num_tokens": 9813955.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.88823676109314,
|
|
"epoch": 0.5736025753585016,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004983487841750239,
|
|
"loss": 6.7594,
|
|
"mean_token_accuracy": 0.12689361944794655,
|
|
"num_tokens": 9830692.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 7.012313938140869,
|
|
"epoch": 0.5745780899424446,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004983402678825705,
|
|
"loss": 6.8604,
|
|
"mean_token_accuracy": 0.11689006462693215,
|
|
"num_tokens": 9848825.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 7.009697818756104,
|
|
"epoch": 0.5755536045263877,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004983317297661021,
|
|
"loss": 6.8636,
|
|
"mean_token_accuracy": 0.11862565949559212,
|
|
"num_tokens": 9865802.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.989213132858277,
|
|
"epoch": 0.5765291191103307,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.0004983231698264531,
|
|
"loss": 6.9113,
|
|
"mean_token_accuracy": 0.11293623223900795,
|
|
"num_tokens": 9883540.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 7.035774040222168,
|
|
"epoch": 0.5775046336942737,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004983145880644597,
|
|
"loss": 6.845,
|
|
"mean_token_accuracy": 0.11713336035609245,
|
|
"num_tokens": 9897724.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.980173540115357,
|
|
"epoch": 0.5784801482782168,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004983059844809608,
|
|
"loss": 6.7807,
|
|
"mean_token_accuracy": 0.12332117110490799,
|
|
"num_tokens": 9914710.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.9785926818847654,
|
|
"epoch": 0.5794556628621598,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004982973590767969,
|
|
"loss": 6.905,
|
|
"mean_token_accuracy": 0.1224606953561306,
|
|
"num_tokens": 9932362.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.90735092163086,
|
|
"epoch": 0.5804311774461028,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.000498288711852811,
|
|
"loss": 6.6973,
|
|
"mean_token_accuracy": 0.12667495682835578,
|
|
"num_tokens": 9949409.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.98042368888855,
|
|
"epoch": 0.5814066920300458,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.000498280042809848,
|
|
"loss": 6.8482,
|
|
"mean_token_accuracy": 0.11787872463464737,
|
|
"num_tokens": 9967467.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.998588705062867,
|
|
"epoch": 0.5823822066139889,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004982713519487549,
|
|
"loss": 6.7842,
|
|
"mean_token_accuracy": 0.12298471853137016,
|
|
"num_tokens": 9983082.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.938471794128418,
|
|
"epoch": 0.5833577211979319,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004982626392703812,
|
|
"loss": 6.858,
|
|
"mean_token_accuracy": 0.11961809620261192,
|
|
"num_tokens": 10000046.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.994626903533936,
|
|
"epoch": 0.5843332357818749,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000498253904775578,
|
|
"loss": 6.8025,
|
|
"mean_token_accuracy": 0.11904862523078918,
|
|
"num_tokens": 10014674.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.878867435455322,
|
|
"epoch": 0.585308750365818,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004982451484651988,
|
|
"loss": 6.6971,
|
|
"mean_token_accuracy": 0.1258040711283684,
|
|
"num_tokens": 10030647.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.585308750365818,
|
|
"eval_entropy": 6.76918303995275,
|
|
"eval_loss": 6.83972692489624,
|
|
"eval_mean_token_accuracy": 0.12215694767866397,
|
|
"eval_num_tokens": 10030647.0,
|
|
"eval_runtime": 11.9815,
|
|
"eval_samples_per_second": 1383.553,
|
|
"eval_steps_per_second": 173.017,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 6.971354532241821,
|
|
"epoch": 0.586284264949761,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004982363703400995,
|
|
"loss": 6.7644,
|
|
"mean_token_accuracy": 0.12146863415837288,
|
|
"num_tokens": 10046468.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 6.980833387374878,
|
|
"epoch": 0.587259779533704,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004982275704011377,
|
|
"loss": 6.8702,
|
|
"mean_token_accuracy": 0.11535399183630943,
|
|
"num_tokens": 10063062.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 6.948950576782226,
|
|
"epoch": 0.5882352941176471,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004982187486491734,
|
|
"loss": 6.8154,
|
|
"mean_token_accuracy": 0.11990444809198379,
|
|
"num_tokens": 10079616.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 6.8908740997314455,
|
|
"epoch": 0.58921080870159,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004982099050850685,
|
|
"loss": 6.8066,
|
|
"mean_token_accuracy": 0.12121739611029625,
|
|
"num_tokens": 10096830.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 6.935375642776489,
|
|
"epoch": 0.5901863232855331,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004982010397096871,
|
|
"loss": 6.8103,
|
|
"mean_token_accuracy": 0.1206529051065445,
|
|
"num_tokens": 10114041.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 6.94181261062622,
|
|
"epoch": 0.5911618378694762,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004981921525238957,
|
|
"loss": 6.7618,
|
|
"mean_token_accuracy": 0.1229528732597828,
|
|
"num_tokens": 10130075.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 6.948442220687866,
|
|
"epoch": 0.5921373524534191,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004981832435285626,
|
|
"loss": 6.8969,
|
|
"mean_token_accuracy": 0.11569212973117829,
|
|
"num_tokens": 10146716.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 7.023716068267822,
|
|
"epoch": 0.5931128670373622,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004981743127245584,
|
|
"loss": 6.8118,
|
|
"mean_token_accuracy": 0.11930184066295624,
|
|
"num_tokens": 10162116.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 7.03991322517395,
|
|
"epoch": 0.5940883816213053,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004981653601127557,
|
|
"loss": 6.9134,
|
|
"mean_token_accuracy": 0.1151185616850853,
|
|
"num_tokens": 10179326.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 6.973568487167358,
|
|
"epoch": 0.5950638962052482,
|
|
"grad_norm": 0.69921875,
|
|
"learning_rate": 0.0004981563856940295,
|
|
"loss": 6.8254,
|
|
"mean_token_accuracy": 0.12193559929728508,
|
|
"num_tokens": 10195278.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 6.918364095687866,
|
|
"epoch": 0.5960394107891913,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004981473894692565,
|
|
"loss": 6.7649,
|
|
"mean_token_accuracy": 0.12461652830243111,
|
|
"num_tokens": 10210175.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 6.996428918838501,
|
|
"epoch": 0.5970149253731343,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.000498138371439316,
|
|
"loss": 6.8739,
|
|
"mean_token_accuracy": 0.11507434919476509,
|
|
"num_tokens": 10225600.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 6.79698076248169,
|
|
"epoch": 0.5979904399570773,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004981293316050891,
|
|
"loss": 6.5671,
|
|
"mean_token_accuracy": 0.14690572917461395,
|
|
"num_tokens": 10243451.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.994850587844849,
|
|
"epoch": 0.5989659545410204,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004981202699674592,
|
|
"loss": 6.8425,
|
|
"mean_token_accuracy": 0.11861263886094094,
|
|
"num_tokens": 10260392.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 7.001251840591431,
|
|
"epoch": 0.5999414691249634,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004981111865273117,
|
|
"loss": 6.8699,
|
|
"mean_token_accuracy": 0.11388373672962189,
|
|
"num_tokens": 10277016.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 6.879996013641358,
|
|
"epoch": 0.6009169837089064,
|
|
"grad_norm": 0.65625,
|
|
"learning_rate": 0.0004981020812855342,
|
|
"loss": 6.7507,
|
|
"mean_token_accuracy": 0.1295882523059845,
|
|
"num_tokens": 10295927.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 6.993920993804932,
|
|
"epoch": 0.6018924982928495,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004980929542430165,
|
|
"loss": 6.8329,
|
|
"mean_token_accuracy": 0.11890860050916671,
|
|
"num_tokens": 10311140.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 6.960379981994629,
|
|
"epoch": 0.6028680128767925,
|
|
"grad_norm": 0.69140625,
|
|
"learning_rate": 0.0004980838054006504,
|
|
"loss": 6.8587,
|
|
"mean_token_accuracy": 0.1214517556130886,
|
|
"num_tokens": 10328496.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 7.008327531814575,
|
|
"epoch": 0.6038435274607356,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.00049807463475933,
|
|
"loss": 6.8217,
|
|
"mean_token_accuracy": 0.11556787639856339,
|
|
"num_tokens": 10345232.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 7.036677360534668,
|
|
"epoch": 0.6048190420446786,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004980654423199513,
|
|
"loss": 6.9389,
|
|
"mean_token_accuracy": 0.11975807175040246,
|
|
"num_tokens": 10361777.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 6.971032047271729,
|
|
"epoch": 0.6057945566286216,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004980562280834126,
|
|
"loss": 6.8701,
|
|
"mean_token_accuracy": 0.12089675441384315,
|
|
"num_tokens": 10377117.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 6.784434175491333,
|
|
"epoch": 0.6067700712125647,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004980469920506142,
|
|
"loss": 6.5092,
|
|
"mean_token_accuracy": 0.14501469656825067,
|
|
"num_tokens": 10394506.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 6.840110397338867,
|
|
"epoch": 0.6077455857965076,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004980377342224588,
|
|
"loss": 6.6379,
|
|
"mean_token_accuracy": 0.13481251671910285,
|
|
"num_tokens": 10410281.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 6.951754188537597,
|
|
"epoch": 0.6087211003804507,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004980284545998509,
|
|
"loss": 6.8446,
|
|
"mean_token_accuracy": 0.11817321032285691,
|
|
"num_tokens": 10425165.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 7.05452823638916,
|
|
"epoch": 0.6096966149643938,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004980191531836973,
|
|
"loss": 6.8071,
|
|
"mean_token_accuracy": 0.11531015262007713,
|
|
"num_tokens": 10441643.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 6.973208570480347,
|
|
"epoch": 0.6106721295483367,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004980098299749068,
|
|
"loss": 6.8364,
|
|
"mean_token_accuracy": 0.11369196400046348,
|
|
"num_tokens": 10457436.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 6.992639255523682,
|
|
"epoch": 0.6116476441322798,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004980004849743908,
|
|
"loss": 6.8483,
|
|
"mean_token_accuracy": 0.11586210727691651,
|
|
"num_tokens": 10475020.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 6.743567657470703,
|
|
"epoch": 0.6126231587162229,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.000497991118183062,
|
|
"loss": 6.6285,
|
|
"mean_token_accuracy": 0.1310638964176178,
|
|
"num_tokens": 10492029.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 6.873231649398804,
|
|
"epoch": 0.6135986733001658,
|
|
"grad_norm": 0.69140625,
|
|
"learning_rate": 0.0004979817296018359,
|
|
"loss": 6.643,
|
|
"mean_token_accuracy": 0.13233043402433395,
|
|
"num_tokens": 10510145.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 7.017053270339966,
|
|
"epoch": 0.6145741878841089,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004979723192316299,
|
|
"loss": 6.9018,
|
|
"mean_token_accuracy": 0.11942457631230355,
|
|
"num_tokens": 10527192.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 7.0023205280303955,
|
|
"epoch": 0.6155497024680519,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004979628870733637,
|
|
"loss": 6.8516,
|
|
"mean_token_accuracy": 0.116268490254879,
|
|
"num_tokens": 10542269.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 6.93566780090332,
|
|
"epoch": 0.6165252170519949,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004979534331279586,
|
|
"loss": 6.8302,
|
|
"mean_token_accuracy": 0.12175990268588066,
|
|
"num_tokens": 10559425.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 6.9975471019744875,
|
|
"epoch": 0.617500731635938,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004979439573963388,
|
|
"loss": 6.839,
|
|
"mean_token_accuracy": 0.12211178392171859,
|
|
"num_tokens": 10576818.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 6.85965371131897,
|
|
"epoch": 0.618476246219881,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004979344598794299,
|
|
"loss": 6.7367,
|
|
"mean_token_accuracy": 0.12202020436525345,
|
|
"num_tokens": 10593456.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 6.9792022705078125,
|
|
"epoch": 0.619451760803824,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004979249405781602,
|
|
"loss": 6.9228,
|
|
"mean_token_accuracy": 0.11239298284053803,
|
|
"num_tokens": 10609049.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 6.888062763214111,
|
|
"epoch": 0.6204272753877671,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004979153994934599,
|
|
"loss": 6.7552,
|
|
"mean_token_accuracy": 0.12140298858284951,
|
|
"num_tokens": 10626921.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 6.968019676208496,
|
|
"epoch": 0.6214027899717101,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004979058366262613,
|
|
"loss": 6.8202,
|
|
"mean_token_accuracy": 0.11590099334716797,
|
|
"num_tokens": 10643447.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 7.020182180404663,
|
|
"epoch": 0.6223783045556531,
|
|
"grad_norm": 0.703125,
|
|
"learning_rate": 0.0004978962519774987,
|
|
"loss": 6.8755,
|
|
"mean_token_accuracy": 0.11583337187767029,
|
|
"num_tokens": 10659896.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 6.922072839736939,
|
|
"epoch": 0.6233538191395961,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004978866455481087,
|
|
"loss": 6.7377,
|
|
"mean_token_accuracy": 0.12401159852743149,
|
|
"num_tokens": 10675331.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 6.971674585342408,
|
|
"epoch": 0.6243293337235392,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004978770173390301,
|
|
"loss": 6.9015,
|
|
"mean_token_accuracy": 0.11571613252162934,
|
|
"num_tokens": 10692678.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 7.009605169296265,
|
|
"epoch": 0.6253048483074822,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004978673673512039,
|
|
"loss": 6.8141,
|
|
"mean_token_accuracy": 0.11516330763697624,
|
|
"num_tokens": 10708500.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 6.8936890125274655,
|
|
"epoch": 0.6262803628914252,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004978576955855727,
|
|
"loss": 6.7517,
|
|
"mean_token_accuracy": 0.1231576718389988,
|
|
"num_tokens": 10725424.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 6.968296861648559,
|
|
"epoch": 0.6272558774753683,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.0004978480020430818,
|
|
"loss": 6.7581,
|
|
"mean_token_accuracy": 0.12610347270965577,
|
|
"num_tokens": 10740960.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 6.948654890060425,
|
|
"epoch": 0.6282313920593113,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004978382867246784,
|
|
"loss": 6.8209,
|
|
"mean_token_accuracy": 0.11509297043085098,
|
|
"num_tokens": 10756426.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 6.917970371246338,
|
|
"epoch": 0.6292069066432543,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004978285496313119,
|
|
"loss": 6.6964,
|
|
"mean_token_accuracy": 0.12817489728331566,
|
|
"num_tokens": 10772748.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 6.841717290878296,
|
|
"epoch": 0.6301824212271974,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004978187907639336,
|
|
"loss": 6.7149,
|
|
"mean_token_accuracy": 0.12700891867280006,
|
|
"num_tokens": 10790024.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 6.974415254592896,
|
|
"epoch": 0.6311579358111403,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004978090101234972,
|
|
"loss": 6.8363,
|
|
"mean_token_accuracy": 0.11339662298560142,
|
|
"num_tokens": 10806280.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 6.911774730682373,
|
|
"epoch": 0.6321334503950834,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004977992077109585,
|
|
"loss": 6.714,
|
|
"mean_token_accuracy": 0.12501749396324158,
|
|
"num_tokens": 10822166.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 6.948117733001709,
|
|
"epoch": 0.6331089649790265,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004977893835272754,
|
|
"loss": 6.8729,
|
|
"mean_token_accuracy": 0.11643462181091309,
|
|
"num_tokens": 10839833.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 6.969990062713623,
|
|
"epoch": 0.6340844795629694,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004977795375734075,
|
|
"loss": 6.8165,
|
|
"mean_token_accuracy": 0.11839312538504601,
|
|
"num_tokens": 10856803.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 6.889529848098755,
|
|
"epoch": 0.6350599941469125,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004977696698503174,
|
|
"loss": 6.7033,
|
|
"mean_token_accuracy": 0.12753864228725434,
|
|
"num_tokens": 10874245.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 6.935065746307373,
|
|
"epoch": 0.6360355087308556,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.000497759780358969,
|
|
"loss": 6.704,
|
|
"mean_token_accuracy": 0.12439623698592187,
|
|
"num_tokens": 10890380.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 6.930328321456909,
|
|
"epoch": 0.6370110233147985,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004977498691003288,
|
|
"loss": 6.7748,
|
|
"mean_token_accuracy": 0.11711260378360748,
|
|
"num_tokens": 10906927.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 6.982646179199219,
|
|
"epoch": 0.6379865378987416,
|
|
"grad_norm": 0.703125,
|
|
"learning_rate": 0.0004977399360753654,
|
|
"loss": 6.8386,
|
|
"mean_token_accuracy": 0.1155098669230938,
|
|
"num_tokens": 10922922.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 6.9320755958557125,
|
|
"epoch": 0.6389620524826846,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004977299812850492,
|
|
"loss": 6.8422,
|
|
"mean_token_accuracy": 0.11715407073497772,
|
|
"num_tokens": 10939607.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 6.900005102157593,
|
|
"epoch": 0.6399375670666276,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004977200047303532,
|
|
"loss": 6.7399,
|
|
"mean_token_accuracy": 0.12560465782880784,
|
|
"num_tokens": 10956830.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 6.848585224151611,
|
|
"epoch": 0.6409130816505707,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.000497710006412252,
|
|
"loss": 6.694,
|
|
"mean_token_accuracy": 0.12370459362864494,
|
|
"num_tokens": 10974364.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 6.928380727767944,
|
|
"epoch": 0.6418885962345137,
|
|
"grad_norm": 0.6953125,
|
|
"learning_rate": 0.0004976999863317228,
|
|
"loss": 6.7689,
|
|
"mean_token_accuracy": 0.12565389275550842,
|
|
"num_tokens": 10990645.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 6.897617673873901,
|
|
"epoch": 0.6428641108184567,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004976899444897446,
|
|
"loss": 6.7605,
|
|
"mean_token_accuracy": 0.1243349239230156,
|
|
"num_tokens": 11007952.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 6.764959287643433,
|
|
"epoch": 0.6438396254023998,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004976798808872987,
|
|
"loss": 6.6652,
|
|
"mean_token_accuracy": 0.13330203369259835,
|
|
"num_tokens": 11024708.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 6.962576961517334,
|
|
"epoch": 0.6448151399863428,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004976697955253685,
|
|
"loss": 6.7926,
|
|
"mean_token_accuracy": 0.12123866230249405,
|
|
"num_tokens": 11040447.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 6.958606195449829,
|
|
"epoch": 0.6457906545702858,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004976596884049395,
|
|
"loss": 6.8239,
|
|
"mean_token_accuracy": 0.12116182371973991,
|
|
"num_tokens": 11057359.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 6.893990612030029,
|
|
"epoch": 0.6467661691542289,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004976495595269994,
|
|
"loss": 6.6703,
|
|
"mean_token_accuracy": 0.12662564367055892,
|
|
"num_tokens": 11072997.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 6.96226396560669,
|
|
"epoch": 0.6477416837381719,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004976394088925377,
|
|
"loss": 6.8927,
|
|
"mean_token_accuracy": 0.1141204409301281,
|
|
"num_tokens": 11089951.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 6.864245653152466,
|
|
"epoch": 0.6487171983221149,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004976292365025465,
|
|
"loss": 6.597,
|
|
"mean_token_accuracy": 0.13091558888554572,
|
|
"num_tokens": 11107929.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 6.717951726913452,
|
|
"epoch": 0.6496927129060579,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004976190423580199,
|
|
"loss": 6.5718,
|
|
"mean_token_accuracy": 0.13630027323961258,
|
|
"num_tokens": 11125479.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 6.938672971725464,
|
|
"epoch": 0.650668227490001,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004976088264599538,
|
|
"loss": 6.8021,
|
|
"mean_token_accuracy": 0.11664176806807518,
|
|
"num_tokens": 11142316.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 6.971683025360107,
|
|
"epoch": 0.651643742073944,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004975985888093467,
|
|
"loss": 6.8741,
|
|
"mean_token_accuracy": 0.11375871375203132,
|
|
"num_tokens": 11158664.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 6.9573437690734865,
|
|
"epoch": 0.652619256657887,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004975883294071987,
|
|
"loss": 6.7835,
|
|
"mean_token_accuracy": 0.11682680621743202,
|
|
"num_tokens": 11175732.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 6.974673128128051,
|
|
"epoch": 0.6535947712418301,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004975780482545125,
|
|
"loss": 6.8449,
|
|
"mean_token_accuracy": 0.11121880188584328,
|
|
"num_tokens": 11191921.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 6.826222610473633,
|
|
"epoch": 0.6545702858257731,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004975677453522928,
|
|
"loss": 6.6366,
|
|
"mean_token_accuracy": 0.13361973837018012,
|
|
"num_tokens": 11208119.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 6.97097954750061,
|
|
"epoch": 0.6555458004097161,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004975574207015462,
|
|
"loss": 6.7956,
|
|
"mean_token_accuracy": 0.12413982227444649,
|
|
"num_tokens": 11224501.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 6.916935682296753,
|
|
"epoch": 0.6565213149936592,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004975470743032817,
|
|
"loss": 6.8278,
|
|
"mean_token_accuracy": 0.12103914692997933,
|
|
"num_tokens": 11240211.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 6.91620397567749,
|
|
"epoch": 0.6574968295776021,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004975367061585102,
|
|
"loss": 6.7557,
|
|
"mean_token_accuracy": 0.12164314091205597,
|
|
"num_tokens": 11257921.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 6.934234094619751,
|
|
"epoch": 0.6584723441615452,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004975263162682449,
|
|
"loss": 6.7287,
|
|
"mean_token_accuracy": 0.1259515516459942,
|
|
"num_tokens": 11274526.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 6.911838579177856,
|
|
"epoch": 0.6594478587454883,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.000497515904633501,
|
|
"loss": 6.7273,
|
|
"mean_token_accuracy": 0.11922330558300018,
|
|
"num_tokens": 11290883.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 6.92472825050354,
|
|
"epoch": 0.6604233733294312,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004975054712552963,
|
|
"loss": 6.7835,
|
|
"mean_token_accuracy": 0.1197446919977665,
|
|
"num_tokens": 11307406.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 6.809523963928223,
|
|
"epoch": 0.6613988879133743,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004974950161346496,
|
|
"loss": 6.5924,
|
|
"mean_token_accuracy": 0.1301891379058361,
|
|
"num_tokens": 11322728.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 6.826287841796875,
|
|
"epoch": 0.6623744024973174,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000497484539272583,
|
|
"loss": 6.608,
|
|
"mean_token_accuracy": 0.1312587134540081,
|
|
"num_tokens": 11338995.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 6.799115085601807,
|
|
"epoch": 0.6633499170812603,
|
|
"grad_norm": 0.6953125,
|
|
"learning_rate": 0.0004974740406701203,
|
|
"loss": 6.5944,
|
|
"mean_token_accuracy": 0.13588437139987947,
|
|
"num_tokens": 11356154.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 6.858565187454223,
|
|
"epoch": 0.6643254316652034,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004974635203282873,
|
|
"loss": 6.7417,
|
|
"mean_token_accuracy": 0.12239173427224159,
|
|
"num_tokens": 11372755.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 6.8473937034606935,
|
|
"epoch": 0.6653009462491464,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004974529782481119,
|
|
"loss": 6.6903,
|
|
"mean_token_accuracy": 0.13023437485098838,
|
|
"num_tokens": 11389424.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 6.932476234436035,
|
|
"epoch": 0.6662764608330894,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004974424144306241,
|
|
"loss": 6.7714,
|
|
"mean_token_accuracy": 0.11823516711592674,
|
|
"num_tokens": 11406515.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 6.846168279647827,
|
|
"epoch": 0.6672519754170325,
|
|
"grad_norm": 0.66796875,
|
|
"learning_rate": 0.0004974318288768566,
|
|
"loss": 6.6895,
|
|
"mean_token_accuracy": 0.12960817366838456,
|
|
"num_tokens": 11423195.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 6.909561538696289,
|
|
"epoch": 0.6682274900009755,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004974212215878435,
|
|
"loss": 6.7917,
|
|
"mean_token_accuracy": 0.11856053993105889,
|
|
"num_tokens": 11440011.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 6.941532611846924,
|
|
"epoch": 0.6692030045849185,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004974105925646213,
|
|
"loss": 6.7777,
|
|
"mean_token_accuracy": 0.12304110378026963,
|
|
"num_tokens": 11456131.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 6.864895820617676,
|
|
"epoch": 0.6701785191688616,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004973999418082287,
|
|
"loss": 6.6953,
|
|
"mean_token_accuracy": 0.12367683872580529,
|
|
"num_tokens": 11471420.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 6.813220643997193,
|
|
"epoch": 0.6711540337528046,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004973892693197064,
|
|
"loss": 6.6382,
|
|
"mean_token_accuracy": 0.13035640120506287,
|
|
"num_tokens": 11488453.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 6.9454748153686525,
|
|
"epoch": 0.6721295483367477,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004973785751000974,
|
|
"loss": 6.8137,
|
|
"mean_token_accuracy": 0.11750316396355628,
|
|
"num_tokens": 11505144.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 6.9203866481781,
|
|
"epoch": 0.6731050629206906,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004973678591504464,
|
|
"loss": 6.7676,
|
|
"mean_token_accuracy": 0.11730754151940345,
|
|
"num_tokens": 11521249.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 6.842479419708252,
|
|
"epoch": 0.6740805775046337,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.000497357121471801,
|
|
"loss": 6.6794,
|
|
"mean_token_accuracy": 0.12591022923588752,
|
|
"num_tokens": 11537977.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 6.8730206966400145,
|
|
"epoch": 0.6750560920885768,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.00049734636206521,
|
|
"loss": 6.729,
|
|
"mean_token_accuracy": 0.12295481860637665,
|
|
"num_tokens": 11556642.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 6.968209218978882,
|
|
"epoch": 0.6760316066725197,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.000497335580931725,
|
|
"loss": 6.9087,
|
|
"mean_token_accuracy": 0.11316120624542236,
|
|
"num_tokens": 11574727.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 6.815659666061402,
|
|
"epoch": 0.6770071212564628,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004973247780723995,
|
|
"loss": 6.591,
|
|
"mean_token_accuracy": 0.13115289285779,
|
|
"num_tokens": 11592982.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 6.8102446556091305,
|
|
"epoch": 0.6779826358404059,
|
|
"grad_norm": 0.703125,
|
|
"learning_rate": 0.0004973139534882891,
|
|
"loss": 6.6677,
|
|
"mean_token_accuracy": 0.1322997495532036,
|
|
"num_tokens": 11609250.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 6.9131616115570065,
|
|
"epoch": 0.6789581504243488,
|
|
"grad_norm": 0.67578125,
|
|
"learning_rate": 0.0004973031071804515,
|
|
"loss": 6.7187,
|
|
"mean_token_accuracy": 0.12043091505765915,
|
|
"num_tokens": 11626269.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 6.9214027404785154,
|
|
"epoch": 0.6799336650082919,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004972922391499465,
|
|
"loss": 6.7309,
|
|
"mean_token_accuracy": 0.12038269191980362,
|
|
"num_tokens": 11642721.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 6.75933871269226,
|
|
"epoch": 0.680909179592235,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004972813493978361,
|
|
"loss": 6.6504,
|
|
"mean_token_accuracy": 0.12679386734962464,
|
|
"num_tokens": 11659729.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 6.961459970474243,
|
|
"epoch": 0.6818846941761779,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004972704379251845,
|
|
"loss": 6.6688,
|
|
"mean_token_accuracy": 0.12035673260688781,
|
|
"num_tokens": 11675568.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 6.843527603149414,
|
|
"epoch": 0.682860208760121,
|
|
"grad_norm": 0.6796875,
|
|
"learning_rate": 0.000497259504733058,
|
|
"loss": 6.7834,
|
|
"mean_token_accuracy": 0.12744610011577606,
|
|
"num_tokens": 11692827.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 6.941056203842163,
|
|
"epoch": 0.683835723344064,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004972485498225247,
|
|
"loss": 6.765,
|
|
"mean_token_accuracy": 0.11636646166443824,
|
|
"num_tokens": 11708730.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 6.862214183807373,
|
|
"epoch": 0.684811237928007,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004972375731946554,
|
|
"loss": 6.7426,
|
|
"mean_token_accuracy": 0.1167958676815033,
|
|
"num_tokens": 11725031.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 6.9891633033752445,
|
|
"epoch": 0.6857867525119501,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004972265748505224,
|
|
"loss": 6.8239,
|
|
"mean_token_accuracy": 0.11784549057483673,
|
|
"num_tokens": 11742419.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 6.825957345962524,
|
|
"epoch": 0.686762267095893,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004972155547912005,
|
|
"loss": 6.7007,
|
|
"mean_token_accuracy": 0.12056224197149276,
|
|
"num_tokens": 11757474.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 6.997213459014892,
|
|
"epoch": 0.6877377816798361,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004972045130177666,
|
|
"loss": 6.7964,
|
|
"mean_token_accuracy": 0.11312601268291474,
|
|
"num_tokens": 11774467.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 6.854748487472534,
|
|
"epoch": 0.6887132962637792,
|
|
"grad_norm": 0.69921875,
|
|
"learning_rate": 0.0004971934495312996,
|
|
"loss": 6.6734,
|
|
"mean_token_accuracy": 0.12496352568268776,
|
|
"num_tokens": 11790597.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 6.871389770507813,
|
|
"epoch": 0.6896888108477222,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004971823643328807,
|
|
"loss": 6.6705,
|
|
"mean_token_accuracy": 0.1322397232055664,
|
|
"num_tokens": 11806459.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 6.849933719635009,
|
|
"epoch": 0.6906643254316652,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.000497171257423593,
|
|
"loss": 6.7525,
|
|
"mean_token_accuracy": 0.12183298766613007,
|
|
"num_tokens": 11823410.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 6.9140894412994385,
|
|
"epoch": 0.6916398400156082,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004971601288045219,
|
|
"loss": 6.7269,
|
|
"mean_token_accuracy": 0.11563545688986779,
|
|
"num_tokens": 11838684.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 6.8813008785247805,
|
|
"epoch": 0.6926153545995513,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004971489784767547,
|
|
"loss": 6.7207,
|
|
"mean_token_accuracy": 0.12400435954332352,
|
|
"num_tokens": 11854324.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 6.87965202331543,
|
|
"epoch": 0.6935908691834943,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004971378064413813,
|
|
"loss": 6.7193,
|
|
"mean_token_accuracy": 0.12013452425599098,
|
|
"num_tokens": 11871992.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 6.895497274398804,
|
|
"epoch": 0.6945663837674373,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004971266126994929,
|
|
"loss": 6.8306,
|
|
"mean_token_accuracy": 0.1152260959148407,
|
|
"num_tokens": 11889195.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 6.934719657897949,
|
|
"epoch": 0.6955418983513804,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004971153972521837,
|
|
"loss": 6.8047,
|
|
"mean_token_accuracy": 0.1126394160091877,
|
|
"num_tokens": 11906316.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 6.9438189506530765,
|
|
"epoch": 0.6965174129353234,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004971041601005495,
|
|
"loss": 6.8061,
|
|
"mean_token_accuracy": 0.11559802293777466,
|
|
"num_tokens": 11924097.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 6.9797369003295895,
|
|
"epoch": 0.6974929275192664,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004970929012456884,
|
|
"loss": 6.8229,
|
|
"mean_token_accuracy": 0.11528982520103455,
|
|
"num_tokens": 11942344.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 6.878084182739258,
|
|
"epoch": 0.6984684421032095,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004970816206887005,
|
|
"loss": 6.6484,
|
|
"mean_token_accuracy": 0.12871936112642288,
|
|
"num_tokens": 11959045.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 6.865055084228516,
|
|
"epoch": 0.6994439566871524,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004970703184306881,
|
|
"loss": 6.6829,
|
|
"mean_token_accuracy": 0.12164130881428718,
|
|
"num_tokens": 11976244.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 6.904210090637207,
|
|
"epoch": 0.7004194712710955,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004970589944727558,
|
|
"loss": 6.7348,
|
|
"mean_token_accuracy": 0.11487542986869811,
|
|
"num_tokens": 11993644.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 6.8497203350067135,
|
|
"epoch": 0.7013949858550386,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004970476488160098,
|
|
"loss": 6.6351,
|
|
"mean_token_accuracy": 0.12481557428836823,
|
|
"num_tokens": 12010419.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 6.817058944702149,
|
|
"epoch": 0.7023705004389815,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004970362814615592,
|
|
"loss": 6.6596,
|
|
"mean_token_accuracy": 0.1269736722111702,
|
|
"num_tokens": 12027199.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 6.722502756118774,
|
|
"epoch": 0.7033460150229246,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004970248924105144,
|
|
"loss": 6.6585,
|
|
"mean_token_accuracy": 0.12805789709091187,
|
|
"num_tokens": 12044267.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 6.950384855270386,
|
|
"epoch": 0.7043215296068677,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004970134816639884,
|
|
"loss": 6.7289,
|
|
"mean_token_accuracy": 0.11833627745509148,
|
|
"num_tokens": 12062838.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 6.884724140167236,
|
|
"epoch": 0.7052970441908106,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004970020492230963,
|
|
"loss": 6.8052,
|
|
"mean_token_accuracy": 0.11489307954907417,
|
|
"num_tokens": 12079144.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 6.805343961715698,
|
|
"epoch": 0.7062725587747537,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.000496990595088955,
|
|
"loss": 6.6564,
|
|
"mean_token_accuracy": 0.1315965011715889,
|
|
"num_tokens": 12096477.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 6.910393524169922,
|
|
"epoch": 0.7072480733586967,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.0004969791192626841,
|
|
"loss": 6.6867,
|
|
"mean_token_accuracy": 0.12259871289134025,
|
|
"num_tokens": 12113307.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 6.887083864212036,
|
|
"epoch": 0.7082235879426397,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004969676217454048,
|
|
"loss": 6.8314,
|
|
"mean_token_accuracy": 0.12023497670888901,
|
|
"num_tokens": 12131814.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 6.94140100479126,
|
|
"epoch": 0.7091991025265828,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004969561025382405,
|
|
"loss": 6.6658,
|
|
"mean_token_accuracy": 0.11797266453504562,
|
|
"num_tokens": 12147110.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 6.77401876449585,
|
|
"epoch": 0.7101746171105258,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004969445616423171,
|
|
"loss": 6.6404,
|
|
"mean_token_accuracy": 0.12329901158809661,
|
|
"num_tokens": 12162954.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 6.7825218677520756,
|
|
"epoch": 0.7111501316944688,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000496932999058762,
|
|
"loss": 6.538,
|
|
"mean_token_accuracy": 0.12825463935732842,
|
|
"num_tokens": 12181169.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 6.980176115036011,
|
|
"epoch": 0.7121256462784119,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004969214147887053,
|
|
"loss": 6.8629,
|
|
"mean_token_accuracy": 0.11837400645017623,
|
|
"num_tokens": 12198367.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 6.836658382415772,
|
|
"epoch": 0.7131011608623549,
|
|
"grad_norm": 0.70703125,
|
|
"learning_rate": 0.0004969098088332789,
|
|
"loss": 6.6785,
|
|
"mean_token_accuracy": 0.12349804788827896,
|
|
"num_tokens": 12215614.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 6.866107368469239,
|
|
"epoch": 0.7140766754462979,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.0004968981811936169,
|
|
"loss": 6.6618,
|
|
"mean_token_accuracy": 0.12607742547988893,
|
|
"num_tokens": 12232123.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 6.835193109512329,
|
|
"epoch": 0.7150521900302409,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004968865318708555,
|
|
"loss": 6.7412,
|
|
"mean_token_accuracy": 0.11978078857064248,
|
|
"num_tokens": 12248417.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 6.930547761917114,
|
|
"epoch": 0.716027704614184,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004968748608661328,
|
|
"loss": 6.6955,
|
|
"mean_token_accuracy": 0.1204741932451725,
|
|
"num_tokens": 12264388.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 6.861438274383545,
|
|
"epoch": 0.717003219198127,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004968631681805897,
|
|
"loss": 6.7626,
|
|
"mean_token_accuracy": 0.1161635011434555,
|
|
"num_tokens": 12282157.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 6.91240611076355,
|
|
"epoch": 0.71797873378207,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004968514538153685,
|
|
"loss": 6.7533,
|
|
"mean_token_accuracy": 0.11711755543947219,
|
|
"num_tokens": 12298368.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 6.814522075653076,
|
|
"epoch": 0.7189542483660131,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.000496839717771614,
|
|
"loss": 6.6728,
|
|
"mean_token_accuracy": 0.13156055882573128,
|
|
"num_tokens": 12314860.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 6.889157772064209,
|
|
"epoch": 0.7199297629499561,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004968279600504729,
|
|
"loss": 6.6777,
|
|
"mean_token_accuracy": 0.12462076321244239,
|
|
"num_tokens": 12331424.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 6.876849699020386,
|
|
"epoch": 0.7209052775338991,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.000496816180653094,
|
|
"loss": 6.795,
|
|
"mean_token_accuracy": 0.11927400529384613,
|
|
"num_tokens": 12348358.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 6.926297378540039,
|
|
"epoch": 0.7218807921178422,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004968043795806285,
|
|
"loss": 6.7068,
|
|
"mean_token_accuracy": 0.12441435232758521,
|
|
"num_tokens": 12364932.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 6.8722264766693115,
|
|
"epoch": 0.7228563067017852,
|
|
"grad_norm": 0.70703125,
|
|
"learning_rate": 0.0004967925568342297,
|
|
"loss": 6.7608,
|
|
"mean_token_accuracy": 0.12208452895283699,
|
|
"num_tokens": 12381852.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 6.87236704826355,
|
|
"epoch": 0.7238318212857282,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004967807124150527,
|
|
"loss": 6.7627,
|
|
"mean_token_accuracy": 0.11639531627297402,
|
|
"num_tokens": 12397164.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 6.872754096984863,
|
|
"epoch": 0.7248073358696713,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004967688463242549,
|
|
"loss": 6.7223,
|
|
"mean_token_accuracy": 0.12488391622900963,
|
|
"num_tokens": 12412520.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 6.890386629104614,
|
|
"epoch": 0.7257828504536142,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004967569585629958,
|
|
"loss": 6.7214,
|
|
"mean_token_accuracy": 0.12492261677980424,
|
|
"num_tokens": 12427039.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 6.863151788711548,
|
|
"epoch": 0.7267583650375573,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004967450491324371,
|
|
"loss": 6.7132,
|
|
"mean_token_accuracy": 0.12078892961144447,
|
|
"num_tokens": 12441903.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 6.7802776336669925,
|
|
"epoch": 0.7277338796215004,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004967331180337425,
|
|
"loss": 6.6055,
|
|
"mean_token_accuracy": 0.13271844163537025,
|
|
"num_tokens": 12458883.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 6.881054210662842,
|
|
"epoch": 0.7287093942054433,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004967211652680779,
|
|
"loss": 6.7679,
|
|
"mean_token_accuracy": 0.11975318491458893,
|
|
"num_tokens": 12475347.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 6.916751766204834,
|
|
"epoch": 0.7296849087893864,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004967091908366113,
|
|
"loss": 6.7719,
|
|
"mean_token_accuracy": 0.1122885838150978,
|
|
"num_tokens": 12490393.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 6.9106982231140135,
|
|
"epoch": 0.7306604233733295,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004966971947405127,
|
|
"loss": 6.7359,
|
|
"mean_token_accuracy": 0.12715291306376458,
|
|
"num_tokens": 12505679.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 6.815823125839233,
|
|
"epoch": 0.7316359379572724,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004966851769809543,
|
|
"loss": 6.6947,
|
|
"mean_token_accuracy": 0.12405739873647689,
|
|
"num_tokens": 12522316.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 6.915488767623901,
|
|
"epoch": 0.7326114525412155,
|
|
"grad_norm": 0.6953125,
|
|
"learning_rate": 0.0004966731375591106,
|
|
"loss": 6.7777,
|
|
"mean_token_accuracy": 0.12145805954933167,
|
|
"num_tokens": 12539638.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 6.83672833442688,
|
|
"epoch": 0.7335869671251585,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004966610764761579,
|
|
"loss": 6.6487,
|
|
"mean_token_accuracy": 0.1220085933804512,
|
|
"num_tokens": 12556296.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 6.913520956039429,
|
|
"epoch": 0.7345624817091015,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004966489937332748,
|
|
"loss": 6.7348,
|
|
"mean_token_accuracy": 0.1224577359855175,
|
|
"num_tokens": 12573248.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 6.7470988750457765,
|
|
"epoch": 0.7355379962930446,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004966368893316421,
|
|
"loss": 6.546,
|
|
"mean_token_accuracy": 0.13732796162366867,
|
|
"num_tokens": 12590918.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 6.83383264541626,
|
|
"epoch": 0.7365135108769876,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004966247632724425,
|
|
"loss": 6.6715,
|
|
"mean_token_accuracy": 0.1286282256245613,
|
|
"num_tokens": 12607037.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 6.74222960472107,
|
|
"epoch": 0.7374890254609306,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004966126155568609,
|
|
"loss": 6.6479,
|
|
"mean_token_accuracy": 0.12643883302807807,
|
|
"num_tokens": 12623934.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 6.853955793380737,
|
|
"epoch": 0.7384645400448737,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004966004461860843,
|
|
"loss": 6.6254,
|
|
"mean_token_accuracy": 0.13455675318837165,
|
|
"num_tokens": 12640607.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 6.886895704269409,
|
|
"epoch": 0.7394400546288167,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004965882551613019,
|
|
"loss": 6.677,
|
|
"mean_token_accuracy": 0.12057202681899071,
|
|
"num_tokens": 12656671.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 6.882707595825195,
|
|
"epoch": 0.7404155692127597,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.000496576042483705,
|
|
"loss": 6.7665,
|
|
"mean_token_accuracy": 0.1095873698592186,
|
|
"num_tokens": 12673271.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 6.735909795761108,
|
|
"epoch": 0.7413910837967027,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004965638081544869,
|
|
"loss": 6.612,
|
|
"mean_token_accuracy": 0.13734203428030015,
|
|
"num_tokens": 12691005.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 6.885260820388794,
|
|
"epoch": 0.7423665983806458,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004965515521748432,
|
|
"loss": 6.7221,
|
|
"mean_token_accuracy": 0.12221511453390121,
|
|
"num_tokens": 12706170.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 6.802320289611816,
|
|
"epoch": 0.7433421129645889,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004965392745459714,
|
|
"loss": 6.6195,
|
|
"mean_token_accuracy": 0.1268913231790066,
|
|
"num_tokens": 12722794.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 6.887222528457642,
|
|
"epoch": 0.7443176275485318,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004965269752690713,
|
|
"loss": 6.7414,
|
|
"mean_token_accuracy": 0.11664727255702019,
|
|
"num_tokens": 12739676.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 6.868304491043091,
|
|
"epoch": 0.7452931421324749,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004965146543453446,
|
|
"loss": 6.7606,
|
|
"mean_token_accuracy": 0.11783709302544594,
|
|
"num_tokens": 12756231.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 6.696615982055664,
|
|
"epoch": 0.746268656716418,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004965023117759954,
|
|
"loss": 6.5842,
|
|
"mean_token_accuracy": 0.139546649903059,
|
|
"num_tokens": 12771877.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 6.843790674209595,
|
|
"epoch": 0.7472441713003609,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004964899475622299,
|
|
"loss": 6.7098,
|
|
"mean_token_accuracy": 0.11726301610469818,
|
|
"num_tokens": 12790698.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 6.866194105148315,
|
|
"epoch": 0.748219685884304,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000496477561705256,
|
|
"loss": 6.7205,
|
|
"mean_token_accuracy": 0.12282049432396888,
|
|
"num_tokens": 12806160.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 6.913184595108032,
|
|
"epoch": 0.749195200468247,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004964651542062841,
|
|
"loss": 6.7469,
|
|
"mean_token_accuracy": 0.11354261115193368,
|
|
"num_tokens": 12822382.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 6.85291485786438,
|
|
"epoch": 0.75017071505219,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004964527250665268,
|
|
"loss": 6.6822,
|
|
"mean_token_accuracy": 0.12251990661025047,
|
|
"num_tokens": 12839421.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 6.820757102966309,
|
|
"epoch": 0.7511462296361331,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004964402742871983,
|
|
"loss": 6.5181,
|
|
"mean_token_accuracy": 0.13693133518099784,
|
|
"num_tokens": 12856609.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 6.836749744415283,
|
|
"epoch": 0.752121744220076,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004964278018695156,
|
|
"loss": 6.7122,
|
|
"mean_token_accuracy": 0.1190156877040863,
|
|
"num_tokens": 12871659.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 6.834482717514038,
|
|
"epoch": 0.7530972588040191,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004964153078146971,
|
|
"loss": 6.7065,
|
|
"mean_token_accuracy": 0.12238730788230896,
|
|
"num_tokens": 12889029.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 6.850099325180054,
|
|
"epoch": 0.7540727733879622,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004964027921239639,
|
|
"loss": 6.6775,
|
|
"mean_token_accuracy": 0.12874920144677163,
|
|
"num_tokens": 12905735.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 6.8155913829803465,
|
|
"epoch": 0.7550482879719052,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000496390254798539,
|
|
"loss": 6.6739,
|
|
"mean_token_accuracy": 0.12168620973825454,
|
|
"num_tokens": 12921886.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 6.785326719284058,
|
|
"epoch": 0.7560238025558482,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004963776958396475,
|
|
"loss": 6.595,
|
|
"mean_token_accuracy": 0.13358651474118233,
|
|
"num_tokens": 12938658.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 6.8535278797149655,
|
|
"epoch": 0.7569993171397913,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004963651152485165,
|
|
"loss": 6.7644,
|
|
"mean_token_accuracy": 0.11841047778725625,
|
|
"num_tokens": 12955788.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 6.820044136047363,
|
|
"epoch": 0.7579748317237343,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004963525130263753,
|
|
"loss": 6.5843,
|
|
"mean_token_accuracy": 0.12640172615647316,
|
|
"num_tokens": 12972590.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 6.85112624168396,
|
|
"epoch": 0.7589503463076773,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004963398891744557,
|
|
"loss": 6.7088,
|
|
"mean_token_accuracy": 0.1206489697098732,
|
|
"num_tokens": 12989560.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 6.897453546524048,
|
|
"epoch": 0.7599258608916203,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004963272436939908,
|
|
"loss": 6.6685,
|
|
"mean_token_accuracy": 0.1290850006043911,
|
|
"num_tokens": 13005584.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 6.7919103622436525,
|
|
"epoch": 0.7609013754755634,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004963145765862166,
|
|
"loss": 6.7339,
|
|
"mean_token_accuracy": 0.11665016934275627,
|
|
"num_tokens": 13021635.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 6.850520372390747,
|
|
"epoch": 0.7618768900595064,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004963018878523706,
|
|
"loss": 6.6489,
|
|
"mean_token_accuracy": 0.12423578575253487,
|
|
"num_tokens": 13037838.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 6.751602411270142,
|
|
"epoch": 0.7628524046434494,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004962891774936929,
|
|
"loss": 6.5997,
|
|
"mean_token_accuracy": 0.13325338512659074,
|
|
"num_tokens": 13054596.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 6.822785234451294,
|
|
"epoch": 0.7638279192273925,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004962764455114255,
|
|
"loss": 6.6503,
|
|
"mean_token_accuracy": 0.12804142460227014,
|
|
"num_tokens": 13070462.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 6.811359786987305,
|
|
"epoch": 0.7648034338113355,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004962636919068125,
|
|
"loss": 6.602,
|
|
"mean_token_accuracy": 0.12725940197706223,
|
|
"num_tokens": 13086686.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 6.869592094421387,
|
|
"epoch": 0.7657789483952785,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004962509166811001,
|
|
"loss": 6.7426,
|
|
"mean_token_accuracy": 0.118138125538826,
|
|
"num_tokens": 13102430.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 6.769513463973999,
|
|
"epoch": 0.7667544629792216,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004962381198355367,
|
|
"loss": 6.6418,
|
|
"mean_token_accuracy": 0.13009895756840706,
|
|
"num_tokens": 13118944.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 6.859700155258179,
|
|
"epoch": 0.7677299775631645,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004962253013713726,
|
|
"loss": 6.6633,
|
|
"mean_token_accuracy": 0.12389598563313484,
|
|
"num_tokens": 13136393.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 6.864688920974731,
|
|
"epoch": 0.7687054921471076,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004962124612898607,
|
|
"loss": 6.7263,
|
|
"mean_token_accuracy": 0.12108601555228234,
|
|
"num_tokens": 13153834.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 6.779188823699951,
|
|
"epoch": 0.7696810067310507,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004961995995922553,
|
|
"loss": 6.5954,
|
|
"mean_token_accuracy": 0.12793506905436516,
|
|
"num_tokens": 13170904.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 6.898433589935303,
|
|
"epoch": 0.7706565213149936,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004961867162798136,
|
|
"loss": 6.6993,
|
|
"mean_token_accuracy": 0.11985084265470505,
|
|
"num_tokens": 13187274.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 6.73800253868103,
|
|
"epoch": 0.7716320358989367,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004961738113537943,
|
|
"loss": 6.6606,
|
|
"mean_token_accuracy": 0.13147602826356888,
|
|
"num_tokens": 13203448.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 6.8765260696411135,
|
|
"epoch": 0.7726075504828798,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004961608848154583,
|
|
"loss": 6.6882,
|
|
"mean_token_accuracy": 0.12293643951416015,
|
|
"num_tokens": 13220460.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 6.779353904724121,
|
|
"epoch": 0.7735830650668227,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.000496147936666069,
|
|
"loss": 6.6237,
|
|
"mean_token_accuracy": 0.12585968971252443,
|
|
"num_tokens": 13237502.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 6.837219905853272,
|
|
"epoch": 0.7745585796507658,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004961349669068913,
|
|
"loss": 6.675,
|
|
"mean_token_accuracy": 0.12033172324299812,
|
|
"num_tokens": 13254314.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 6.8742271900177006,
|
|
"epoch": 0.7755340942347088,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000496121975539193,
|
|
"loss": 6.7451,
|
|
"mean_token_accuracy": 0.12173012867569924,
|
|
"num_tokens": 13271737.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 6.855631542205811,
|
|
"epoch": 0.7765096088186518,
|
|
"grad_norm": 0.69140625,
|
|
"learning_rate": 0.0004961089625642433,
|
|
"loss": 6.682,
|
|
"mean_token_accuracy": 0.12479467093944549,
|
|
"num_tokens": 13288546.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 6.82043776512146,
|
|
"epoch": 0.7774851234025949,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004960959279833137,
|
|
"loss": 6.5859,
|
|
"mean_token_accuracy": 0.13233416080474852,
|
|
"num_tokens": 13304309.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 6.809996461868286,
|
|
"epoch": 0.7784606379865379,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004960828717976781,
|
|
"loss": 6.6695,
|
|
"mean_token_accuracy": 0.12356394901871681,
|
|
"num_tokens": 13319797.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 6.740135049819946,
|
|
"epoch": 0.7794361525704809,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004960697940086121,
|
|
"loss": 6.4899,
|
|
"mean_token_accuracy": 0.14280401170253754,
|
|
"num_tokens": 13336040.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 6.843725204467773,
|
|
"epoch": 0.780411667154424,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.0004960566946173939,
|
|
"loss": 6.647,
|
|
"mean_token_accuracy": 0.12348217517137527,
|
|
"num_tokens": 13352762.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 6.818170690536499,
|
|
"epoch": 0.781387181738367,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004960435736253034,
|
|
"loss": 6.6353,
|
|
"mean_token_accuracy": 0.12317405268549919,
|
|
"num_tokens": 13368577.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 6.876036167144775,
|
|
"epoch": 0.78236269632231,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004960304310336226,
|
|
"loss": 6.7629,
|
|
"mean_token_accuracy": 0.11409945338964463,
|
|
"num_tokens": 13384170.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 6.764006280899048,
|
|
"epoch": 0.783338210906253,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004960172668436359,
|
|
"loss": 6.5486,
|
|
"mean_token_accuracy": 0.13554680570960045,
|
|
"num_tokens": 13400143.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 6.798735809326172,
|
|
"epoch": 0.7843137254901961,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004960040810566295,
|
|
"loss": 6.6641,
|
|
"mean_token_accuracy": 0.12530111894011497,
|
|
"num_tokens": 13416553.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 6.792158937454223,
|
|
"epoch": 0.7852892400741391,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004959908736738921,
|
|
"loss": 6.6734,
|
|
"mean_token_accuracy": 0.11895274966955185,
|
|
"num_tokens": 13432694.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 6.8122483253479,
|
|
"epoch": 0.7862647546580821,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004959776446967141,
|
|
"loss": 6.6921,
|
|
"mean_token_accuracy": 0.11880224645137787,
|
|
"num_tokens": 13450333.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 6.699470853805542,
|
|
"epoch": 0.7872402692420252,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004959643941263882,
|
|
"loss": 6.5084,
|
|
"mean_token_accuracy": 0.13090393021702768,
|
|
"num_tokens": 13467150.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 6.796896123886109,
|
|
"epoch": 0.7882157838259682,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004959511219642092,
|
|
"loss": 6.6452,
|
|
"mean_token_accuracy": 0.127489648014307,
|
|
"num_tokens": 13484796.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 6.82787938117981,
|
|
"epoch": 0.7891912984099112,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004959378282114741,
|
|
"loss": 6.5784,
|
|
"mean_token_accuracy": 0.13011280819773674,
|
|
"num_tokens": 13501533.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 6.875354433059693,
|
|
"epoch": 0.7901668129938543,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004959245128694819,
|
|
"loss": 6.7604,
|
|
"mean_token_accuracy": 0.11298960968852043,
|
|
"num_tokens": 13518270.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 6.76537013053894,
|
|
"epoch": 0.7911423275777972,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.0004959111759395337,
|
|
"loss": 6.5438,
|
|
"mean_token_accuracy": 0.13087853342294692,
|
|
"num_tokens": 13535356.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 6.794853591918946,
|
|
"epoch": 0.7921178421617403,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004958978174229326,
|
|
"loss": 6.5757,
|
|
"mean_token_accuracy": 0.12415336892008781,
|
|
"num_tokens": 13550530.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 6.713842153549194,
|
|
"epoch": 0.7930933567456834,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004958844373209843,
|
|
"loss": 6.557,
|
|
"mean_token_accuracy": 0.1338584341108799,
|
|
"num_tokens": 13569492.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 6.8896129608154295,
|
|
"epoch": 0.7940688713296263,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004958710356349958,
|
|
"loss": 6.7652,
|
|
"mean_token_accuracy": 0.11738318726420402,
|
|
"num_tokens": 13585096.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 6.867253160476684,
|
|
"epoch": 0.7950443859135694,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.000495857612366277,
|
|
"loss": 6.7211,
|
|
"mean_token_accuracy": 0.1207522250711918,
|
|
"num_tokens": 13600667.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 6.892461585998535,
|
|
"epoch": 0.7960199004975125,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004958441675161395,
|
|
"loss": 6.741,
|
|
"mean_token_accuracy": 0.11513039320707322,
|
|
"num_tokens": 13618212.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 6.822042798995971,
|
|
"epoch": 0.7969954150814554,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.000495830701085897,
|
|
"loss": 6.6654,
|
|
"mean_token_accuracy": 0.12702780589461327,
|
|
"num_tokens": 13634067.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 6.7282881259918215,
|
|
"epoch": 0.7979709296653985,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004958172130768655,
|
|
"loss": 6.6038,
|
|
"mean_token_accuracy": 0.13232214823365213,
|
|
"num_tokens": 13651306.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 6.8347203731536865,
|
|
"epoch": 0.7989464442493416,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004958037034903628,
|
|
"loss": 6.6467,
|
|
"mean_token_accuracy": 0.12047887295484543,
|
|
"num_tokens": 13667563.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 6.7118918895721436,
|
|
"epoch": 0.7999219588332845,
|
|
"grad_norm": 0.62890625,
|
|
"learning_rate": 0.0004957901723277093,
|
|
"loss": 6.52,
|
|
"mean_token_accuracy": 0.1359785683453083,
|
|
"num_tokens": 13684857.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 6.897461986541748,
|
|
"epoch": 0.8008974734172276,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004957766195902271,
|
|
"loss": 6.7512,
|
|
"mean_token_accuracy": 0.11656382903456688,
|
|
"num_tokens": 13700356.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 6.772191047668457,
|
|
"epoch": 0.8018729880011706,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004957630452792404,
|
|
"loss": 6.5877,
|
|
"mean_token_accuracy": 0.13443109020590782,
|
|
"num_tokens": 13717146.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 6.811573266983032,
|
|
"epoch": 0.8028485025851136,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004957494493960757,
|
|
"loss": 6.6657,
|
|
"mean_token_accuracy": 0.12005516067147255,
|
|
"num_tokens": 13732520.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 6.917568254470825,
|
|
"epoch": 0.8038240171690567,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004957358319420617,
|
|
"loss": 6.7725,
|
|
"mean_token_accuracy": 0.1172066181898117,
|
|
"num_tokens": 13749135.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 6.787263631820679,
|
|
"epoch": 0.8047995317529997,
|
|
"grad_norm": 0.70703125,
|
|
"learning_rate": 0.0004957221929185288,
|
|
"loss": 6.4831,
|
|
"mean_token_accuracy": 0.14020401015877723,
|
|
"num_tokens": 13766218.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 6.796660661697388,
|
|
"epoch": 0.8057750463369427,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004957085323268099,
|
|
"loss": 6.711,
|
|
"mean_token_accuracy": 0.12132370844483376,
|
|
"num_tokens": 13784421.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 6.807187271118164,
|
|
"epoch": 0.8067505609208858,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004956948501682399,
|
|
"loss": 6.594,
|
|
"mean_token_accuracy": 0.13043712675571442,
|
|
"num_tokens": 13800054.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 6.8141875743865965,
|
|
"epoch": 0.8077260755048288,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004956811464441556,
|
|
"loss": 6.6124,
|
|
"mean_token_accuracy": 0.12478702291846275,
|
|
"num_tokens": 13816433.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 6.840706634521484,
|
|
"epoch": 0.8087015900887718,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004956674211558963,
|
|
"loss": 6.7293,
|
|
"mean_token_accuracy": 0.11568222343921661,
|
|
"num_tokens": 13832441.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 6.826780509948731,
|
|
"epoch": 0.8096771046727148,
|
|
"grad_norm": 0.6875,
|
|
"learning_rate": 0.000495653674304803,
|
|
"loss": 6.6707,
|
|
"mean_token_accuracy": 0.12574417218565942,
|
|
"num_tokens": 13849012.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 6.882092380523682,
|
|
"epoch": 0.8106526192566579,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004956399058922192,
|
|
"loss": 6.7261,
|
|
"mean_token_accuracy": 0.11556809395551682,
|
|
"num_tokens": 13866486.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 6.804460954666138,
|
|
"epoch": 0.811628133840601,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.00049562611591949,
|
|
"loss": 6.5694,
|
|
"mean_token_accuracy": 0.12842900604009627,
|
|
"num_tokens": 13882453.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 6.789235782623291,
|
|
"epoch": 0.8126036484245439,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004956123043879632,
|
|
"loss": 6.659,
|
|
"mean_token_accuracy": 0.12401216328144074,
|
|
"num_tokens": 13898090.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 6.843680000305175,
|
|
"epoch": 0.813579163008487,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004955984712989882,
|
|
"loss": 6.6156,
|
|
"mean_token_accuracy": 0.12544377148151398,
|
|
"num_tokens": 13914818.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 6.87191858291626,
|
|
"epoch": 0.81455467759243,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004955846166539169,
|
|
"loss": 6.7113,
|
|
"mean_token_accuracy": 0.11897660940885543,
|
|
"num_tokens": 13930690.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 6.879695653915405,
|
|
"epoch": 0.815530192176373,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000495570740454103,
|
|
"loss": 6.7077,
|
|
"mean_token_accuracy": 0.12430903613567353,
|
|
"num_tokens": 13946128.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 6.7762197971344,
|
|
"epoch": 0.8165057067603161,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004955568427009024,
|
|
"loss": 6.6227,
|
|
"mean_token_accuracy": 0.12779104858636856,
|
|
"num_tokens": 13961766.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 6.738035869598389,
|
|
"epoch": 0.817481221344259,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004955429233956733,
|
|
"loss": 6.5886,
|
|
"mean_token_accuracy": 0.13068413659930228,
|
|
"num_tokens": 13978632.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 6.8669201850891115,
|
|
"epoch": 0.8184567359282021,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004955289825397757,
|
|
"loss": 6.6561,
|
|
"mean_token_accuracy": 0.12052980437874794,
|
|
"num_tokens": 13995297.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 6.793001890182495,
|
|
"epoch": 0.8194322505121452,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000495515020134572,
|
|
"loss": 6.6771,
|
|
"mean_token_accuracy": 0.12439461797475815,
|
|
"num_tokens": 14010439.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 6.828063297271728,
|
|
"epoch": 0.8204077650960881,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004955010361814264,
|
|
"loss": 6.6755,
|
|
"mean_token_accuracy": 0.12615011483430863,
|
|
"num_tokens": 14028538.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 6.87235050201416,
|
|
"epoch": 0.8213832796800312,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004954870306817054,
|
|
"loss": 6.7019,
|
|
"mean_token_accuracy": 0.11807957738637924,
|
|
"num_tokens": 14045290.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 6.747262716293335,
|
|
"epoch": 0.8223587942639743,
|
|
"grad_norm": 0.67578125,
|
|
"learning_rate": 0.0004954730036367776,
|
|
"loss": 6.6087,
|
|
"mean_token_accuracy": 0.1285885103046894,
|
|
"num_tokens": 14062247.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 6.75828709602356,
|
|
"epoch": 0.8233343088479173,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004954589550480137,
|
|
"loss": 6.6322,
|
|
"mean_token_accuracy": 0.1285369873046875,
|
|
"num_tokens": 14078599.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 6.843633508682251,
|
|
"epoch": 0.8243098234318603,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004954448849167864,
|
|
"loss": 6.6333,
|
|
"mean_token_accuracy": 0.1259762838482857,
|
|
"num_tokens": 14094686.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 6.757554244995117,
|
|
"epoch": 0.8252853380158033,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004954307932444707,
|
|
"loss": 6.6524,
|
|
"mean_token_accuracy": 0.1225406251847744,
|
|
"num_tokens": 14110255.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 6.8054452419281,
|
|
"epoch": 0.8262608525997464,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004954166800324434,
|
|
"loss": 6.649,
|
|
"mean_token_accuracy": 0.12180253192782402,
|
|
"num_tokens": 14127160.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 6.787542724609375,
|
|
"epoch": 0.8272363671836894,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.0004954025452820837,
|
|
"loss": 6.5592,
|
|
"mean_token_accuracy": 0.12789287120103837,
|
|
"num_tokens": 14144704.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 6.767620849609375,
|
|
"epoch": 0.8282118817676324,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000495388388994773,
|
|
"loss": 6.6383,
|
|
"mean_token_accuracy": 0.12094874009490013,
|
|
"num_tokens": 14162125.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 6.778093576431274,
|
|
"epoch": 0.8291873963515755,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004953742111718942,
|
|
"loss": 6.5492,
|
|
"mean_token_accuracy": 0.1256315030157566,
|
|
"num_tokens": 14179735.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 6.78254075050354,
|
|
"epoch": 0.8301629109355185,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000495360011814833,
|
|
"loss": 6.7516,
|
|
"mean_token_accuracy": 0.12098669707775116,
|
|
"num_tokens": 14196964.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 6.782737112045288,
|
|
"epoch": 0.8311384255194615,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004953457909249768,
|
|
"loss": 6.5769,
|
|
"mean_token_accuracy": 0.13020500764250756,
|
|
"num_tokens": 14212802.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 6.7880768299102785,
|
|
"epoch": 0.8321139401034046,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004953315485037152,
|
|
"loss": 6.5946,
|
|
"mean_token_accuracy": 0.126256163418293,
|
|
"num_tokens": 14229183.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 6.801061344146729,
|
|
"epoch": 0.8330894546873476,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004953172845524401,
|
|
"loss": 6.6156,
|
|
"mean_token_accuracy": 0.12138534784317016,
|
|
"num_tokens": 14245859.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 6.839641523361206,
|
|
"epoch": 0.8340649692712906,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004953029990725452,
|
|
"loss": 6.6721,
|
|
"mean_token_accuracy": 0.131340454518795,
|
|
"num_tokens": 14261689.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 6.7324224472045895,
|
|
"epoch": 0.8350404838552337,
|
|
"grad_norm": 0.6875,
|
|
"learning_rate": 0.0004952886920654262,
|
|
"loss": 6.5178,
|
|
"mean_token_accuracy": 0.13167475908994675,
|
|
"num_tokens": 14280638.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 6.755913496017456,
|
|
"epoch": 0.8360159984391766,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004952743635324813,
|
|
"loss": 6.5244,
|
|
"mean_token_accuracy": 0.13342704251408577,
|
|
"num_tokens": 14296595.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 6.7735639095306395,
|
|
"epoch": 0.8369915130231197,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004952600134751109,
|
|
"loss": 6.7091,
|
|
"mean_token_accuracy": 0.12113286629319191,
|
|
"num_tokens": 14312384.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 6.84943528175354,
|
|
"epoch": 0.8379670276070628,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004952456418947168,
|
|
"loss": 6.6269,
|
|
"mean_token_accuracy": 0.12358014136552811,
|
|
"num_tokens": 14327852.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 6.765071725845337,
|
|
"epoch": 0.8389425421910057,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004952312487927037,
|
|
"loss": 6.6346,
|
|
"mean_token_accuracy": 0.12314010709524155,
|
|
"num_tokens": 14343666.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 6.811249542236328,
|
|
"epoch": 0.8399180567749488,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.0004952168341704778,
|
|
"loss": 6.5957,
|
|
"mean_token_accuracy": 0.13368313536047935,
|
|
"num_tokens": 14359819.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 6.889675617218018,
|
|
"epoch": 0.8408935713588919,
|
|
"grad_norm": 0.70703125,
|
|
"learning_rate": 0.0004952023980294478,
|
|
"loss": 6.7272,
|
|
"mean_token_accuracy": 0.1174446813762188,
|
|
"num_tokens": 14377762.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 6.720572853088379,
|
|
"epoch": 0.8418690859428348,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004951879403710242,
|
|
"loss": 6.5713,
|
|
"mean_token_accuracy": 0.12481369227170944,
|
|
"num_tokens": 14393995.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 6.8302874088287355,
|
|
"epoch": 0.8428446005267779,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004951734611966199,
|
|
"loss": 6.611,
|
|
"mean_token_accuracy": 0.1313945785164833,
|
|
"num_tokens": 14411959.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 6.797599983215332,
|
|
"epoch": 0.8438201151107209,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004951589605076495,
|
|
"loss": 6.704,
|
|
"mean_token_accuracy": 0.12197732776403428,
|
|
"num_tokens": 14427659.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 6.655198812484741,
|
|
"epoch": 0.8447956296946639,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004951444383055304,
|
|
"loss": 6.4376,
|
|
"mean_token_accuracy": 0.1433950185775757,
|
|
"num_tokens": 14443887.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 6.814894914627075,
|
|
"epoch": 0.845771144278607,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004951298945916812,
|
|
"loss": 6.6344,
|
|
"mean_token_accuracy": 0.12630745470523835,
|
|
"num_tokens": 14461907.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 6.758886051177979,
|
|
"epoch": 0.84674665886255,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004951153293675235,
|
|
"loss": 6.5903,
|
|
"mean_token_accuracy": 0.12540938183665276,
|
|
"num_tokens": 14476912.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 6.709046125411987,
|
|
"epoch": 0.847722173446493,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004951007426344801,
|
|
"loss": 6.485,
|
|
"mean_token_accuracy": 0.132861640304327,
|
|
"num_tokens": 14493499.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 6.849710130691529,
|
|
"epoch": 0.8486976880304361,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004950861343939767,
|
|
"loss": 6.6523,
|
|
"mean_token_accuracy": 0.12545099183917047,
|
|
"num_tokens": 14511266.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 6.784698057174682,
|
|
"epoch": 0.8496732026143791,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004950715046474405,
|
|
"loss": 6.6494,
|
|
"mean_token_accuracy": 0.12234164550900459,
|
|
"num_tokens": 14528930.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 6.791780567169189,
|
|
"epoch": 0.8506487171983221,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004950568533963013,
|
|
"loss": 6.6141,
|
|
"mean_token_accuracy": 0.13539324551820756,
|
|
"num_tokens": 14546637.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 6.700049972534179,
|
|
"epoch": 0.8516242317822651,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004950421806419907,
|
|
"loss": 6.634,
|
|
"mean_token_accuracy": 0.12353199869394302,
|
|
"num_tokens": 14563332.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 6.672889137268067,
|
|
"epoch": 0.8525997463662082,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004950274863859425,
|
|
"loss": 6.495,
|
|
"mean_token_accuracy": 0.1342873267829418,
|
|
"num_tokens": 14579806.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 6.857314729690552,
|
|
"epoch": 0.8535752609501512,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004950127706295923,
|
|
"loss": 6.6913,
|
|
"mean_token_accuracy": 0.12031725123524666,
|
|
"num_tokens": 14597129.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 6.641730070114136,
|
|
"epoch": 0.8545507755340942,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004949980333743786,
|
|
"loss": 6.455,
|
|
"mean_token_accuracy": 0.14024292007088662,
|
|
"num_tokens": 14615000.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 6.792471790313721,
|
|
"epoch": 0.8555262901180373,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000494983274621741,
|
|
"loss": 6.6101,
|
|
"mean_token_accuracy": 0.13477565497159957,
|
|
"num_tokens": 14631338.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 6.721571540832519,
|
|
"epoch": 0.8565018047019803,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004949684943731219,
|
|
"loss": 6.5923,
|
|
"mean_token_accuracy": 0.12976597473025323,
|
|
"num_tokens": 14647886.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 6.831157398223877,
|
|
"epoch": 0.8574773192859233,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004949536926299654,
|
|
"loss": 6.586,
|
|
"mean_token_accuracy": 0.1255404345691204,
|
|
"num_tokens": 14665054.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 6.741514253616333,
|
|
"epoch": 0.8584528338698664,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000494938869393718,
|
|
"loss": 6.6187,
|
|
"mean_token_accuracy": 0.12345570176839829,
|
|
"num_tokens": 14679413.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 6.764444637298584,
|
|
"epoch": 0.8594283484538093,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004949240246658283,
|
|
"loss": 6.5567,
|
|
"mean_token_accuracy": 0.1324881926178932,
|
|
"num_tokens": 14696562.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 6.683461141586304,
|
|
"epoch": 0.8604038630377524,
|
|
"grad_norm": 0.69921875,
|
|
"learning_rate": 0.0004949091584477465,
|
|
"loss": 6.4758,
|
|
"mean_token_accuracy": 0.13379047736525534,
|
|
"num_tokens": 14713782.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 6.813050842285156,
|
|
"epoch": 0.8613793776216955,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004948942707409257,
|
|
"loss": 6.7229,
|
|
"mean_token_accuracy": 0.12056387960910797,
|
|
"num_tokens": 14730139.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 6.774748706817627,
|
|
"epoch": 0.8623548922056384,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004948793615468205,
|
|
"loss": 6.6514,
|
|
"mean_token_accuracy": 0.1171096384525299,
|
|
"num_tokens": 14746830.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 6.885052013397217,
|
|
"epoch": 0.8633304067895815,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004948644308668877,
|
|
"loss": 6.6756,
|
|
"mean_token_accuracy": 0.12350480332970619,
|
|
"num_tokens": 14762410.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 6.806125831604004,
|
|
"epoch": 0.8643059213735246,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004948494787025863,
|
|
"loss": 6.5821,
|
|
"mean_token_accuracy": 0.11751062721014023,
|
|
"num_tokens": 14778283.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 6.6851105213165285,
|
|
"epoch": 0.8652814359574675,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004948345050553774,
|
|
"loss": 6.5346,
|
|
"mean_token_accuracy": 0.12511444240808486,
|
|
"num_tokens": 14797005.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 6.850437498092651,
|
|
"epoch": 0.8662569505414106,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004948195099267242,
|
|
"loss": 6.666,
|
|
"mean_token_accuracy": 0.11475102826952935,
|
|
"num_tokens": 14814548.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 6.758647727966308,
|
|
"epoch": 0.8672324651253536,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004948044933180919,
|
|
"loss": 6.6,
|
|
"mean_token_accuracy": 0.12812071293592453,
|
|
"num_tokens": 14830630.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 6.749329328536987,
|
|
"epoch": 0.8682079797092966,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.000494789455230948,
|
|
"loss": 6.6148,
|
|
"mean_token_accuracy": 0.12402471080422402,
|
|
"num_tokens": 14846247.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 6.870501232147217,
|
|
"epoch": 0.8691834942932397,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004947743956667617,
|
|
"loss": 6.6441,
|
|
"mean_token_accuracy": 0.12242101430892945,
|
|
"num_tokens": 14864480.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 6.799664640426636,
|
|
"epoch": 0.8701590088771827,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004947593146270049,
|
|
"loss": 6.6951,
|
|
"mean_token_accuracy": 0.1268666312098503,
|
|
"num_tokens": 14881382.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 6.830371522903443,
|
|
"epoch": 0.8711345234611257,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.000494744212113151,
|
|
"loss": 6.6326,
|
|
"mean_token_accuracy": 0.12118108049035073,
|
|
"num_tokens": 14897546.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 6.770023393630981,
|
|
"epoch": 0.8721100380450688,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004947290881266759,
|
|
"loss": 6.5803,
|
|
"mean_token_accuracy": 0.12531674653291702,
|
|
"num_tokens": 14913995.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 6.808616733551025,
|
|
"epoch": 0.8730855526290118,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004947139426690576,
|
|
"loss": 6.6502,
|
|
"mean_token_accuracy": 0.11557586416602135,
|
|
"num_tokens": 14931097.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 6.751026296615601,
|
|
"epoch": 0.8740610672129548,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004946987757417757,
|
|
"loss": 6.5316,
|
|
"mean_token_accuracy": 0.1314692623913288,
|
|
"num_tokens": 14948010.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 6.641950511932373,
|
|
"epoch": 0.8750365817968979,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004946835873463126,
|
|
"loss": 6.5044,
|
|
"mean_token_accuracy": 0.1403428703546524,
|
|
"num_tokens": 14966940.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 6.885153436660767,
|
|
"epoch": 0.8760120963808409,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004946683774841522,
|
|
"loss": 6.6889,
|
|
"mean_token_accuracy": 0.12155811414122582,
|
|
"num_tokens": 14983482.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 6.663387298583984,
|
|
"epoch": 0.876987610964784,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.000494653146156781,
|
|
"loss": 6.5454,
|
|
"mean_token_accuracy": 0.13059545159339905,
|
|
"num_tokens": 15000709.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 6.759126377105713,
|
|
"epoch": 0.8779631255487269,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004946378933656871,
|
|
"loss": 6.5147,
|
|
"mean_token_accuracy": 0.1331453800201416,
|
|
"num_tokens": 15016584.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 6.731809616088867,
|
|
"epoch": 0.87893864013267,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.000494622619112361,
|
|
"loss": 6.6785,
|
|
"mean_token_accuracy": 0.12640314400196076,
|
|
"num_tokens": 15033598.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 6.868506622314453,
|
|
"epoch": 0.879914154716613,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004946073233982954,
|
|
"loss": 6.6472,
|
|
"mean_token_accuracy": 0.1223464123904705,
|
|
"num_tokens": 15049842.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 6.674413633346558,
|
|
"epoch": 0.880889669300556,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004945920062249849,
|
|
"loss": 6.4023,
|
|
"mean_token_accuracy": 0.13988135606050492,
|
|
"num_tokens": 15066278.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 6.739884948730468,
|
|
"epoch": 0.8818651838844991,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004945766675939261,
|
|
"loss": 6.6204,
|
|
"mean_token_accuracy": 0.13241141065955161,
|
|
"num_tokens": 15083316.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 6.716450834274292,
|
|
"epoch": 0.8828406984684422,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004945613075066181,
|
|
"loss": 6.6327,
|
|
"mean_token_accuracy": 0.12506671622395515,
|
|
"num_tokens": 15103135.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 6.686972808837891,
|
|
"epoch": 0.8838162130523851,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004945459259645614,
|
|
"loss": 6.4776,
|
|
"mean_token_accuracy": 0.14397581964731215,
|
|
"num_tokens": 15122441.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 6.854146814346313,
|
|
"epoch": 0.8847917276363282,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004945305229692594,
|
|
"loss": 6.6118,
|
|
"mean_token_accuracy": 0.12402639538049698,
|
|
"num_tokens": 15139526.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 6.750254392623901,
|
|
"epoch": 0.8857672422202711,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004945150985222171,
|
|
"loss": 6.5797,
|
|
"mean_token_accuracy": 0.12443638741970062,
|
|
"num_tokens": 15156139.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 6.711096096038818,
|
|
"epoch": 0.8867427568042142,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004944996526249419,
|
|
"loss": 6.4983,
|
|
"mean_token_accuracy": 0.1341721974313259,
|
|
"num_tokens": 15172894.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 6.792566633224487,
|
|
"epoch": 0.8877182713881573,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004944841852789427,
|
|
"loss": 6.6161,
|
|
"mean_token_accuracy": 0.12743620723485946,
|
|
"num_tokens": 15190900.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 6.774860572814942,
|
|
"epoch": 0.8886937859721002,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004944686964857314,
|
|
"loss": 6.5761,
|
|
"mean_token_accuracy": 0.12179967761039734,
|
|
"num_tokens": 15208018.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 6.800430154800415,
|
|
"epoch": 0.8896693005560433,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004944531862468211,
|
|
"loss": 6.6115,
|
|
"mean_token_accuracy": 0.13014492616057396,
|
|
"num_tokens": 15222781.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 6.702226018905639,
|
|
"epoch": 0.8906448151399864,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004944376545637277,
|
|
"loss": 6.6306,
|
|
"mean_token_accuracy": 0.12729200273752211,
|
|
"num_tokens": 15241405.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 6.87046251296997,
|
|
"epoch": 0.8916203297239294,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004944221014379688,
|
|
"loss": 6.6392,
|
|
"mean_token_accuracy": 0.12803873419761658,
|
|
"num_tokens": 15258340.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 6.7284410953521725,
|
|
"epoch": 0.8925958443078724,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004944065268710641,
|
|
"loss": 6.6,
|
|
"mean_token_accuracy": 0.1251739464700222,
|
|
"num_tokens": 15274655.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 6.815349483489991,
|
|
"epoch": 0.8935713588918154,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004943909308645356,
|
|
"loss": 6.6328,
|
|
"mean_token_accuracy": 0.12074843198060989,
|
|
"num_tokens": 15291197.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 6.8040018558502195,
|
|
"epoch": 0.8945468734757585,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004943753134199072,
|
|
"loss": 6.6251,
|
|
"mean_token_accuracy": 0.12435000613331795,
|
|
"num_tokens": 15306879.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 6.816485643386841,
|
|
"epoch": 0.8955223880597015,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004943596745387052,
|
|
"loss": 6.6457,
|
|
"mean_token_accuracy": 0.12217252254486084,
|
|
"num_tokens": 15322880.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 6.700962114334106,
|
|
"epoch": 0.8964979026436445,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004943440142224575,
|
|
"loss": 6.5612,
|
|
"mean_token_accuracy": 0.13031849563121795,
|
|
"num_tokens": 15338282.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 6.797181940078735,
|
|
"epoch": 0.8974734172275876,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004943283324726944,
|
|
"loss": 6.58,
|
|
"mean_token_accuracy": 0.12809989228844643,
|
|
"num_tokens": 15354507.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 6.824423503875733,
|
|
"epoch": 0.8984489318115306,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004943126292909485,
|
|
"loss": 6.6154,
|
|
"mean_token_accuracy": 0.12091436758637428,
|
|
"num_tokens": 15373204.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 6.682150363922119,
|
|
"epoch": 0.8994244463954736,
|
|
"grad_norm": 0.69140625,
|
|
"learning_rate": 0.0004942969046787541,
|
|
"loss": 6.4471,
|
|
"mean_token_accuracy": 0.1395374931395054,
|
|
"num_tokens": 15390743.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 6.764989423751831,
|
|
"epoch": 0.9003999609794167,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.0004942811586376476,
|
|
"loss": 6.5675,
|
|
"mean_token_accuracy": 0.12196485474705696,
|
|
"num_tokens": 15408565.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 6.6711536884307865,
|
|
"epoch": 0.9013754755633596,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004942653911691679,
|
|
"loss": 6.5112,
|
|
"mean_token_accuracy": 0.13643354699015617,
|
|
"num_tokens": 15425747.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 6.705211782455445,
|
|
"epoch": 0.9023509901473027,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.0004942496022748557,
|
|
"loss": 6.5274,
|
|
"mean_token_accuracy": 0.12619738802313804,
|
|
"num_tokens": 15441882.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 6.748261642456055,
|
|
"epoch": 0.9033265047312458,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004942337919562539,
|
|
"loss": 6.5199,
|
|
"mean_token_accuracy": 0.12423703745007515,
|
|
"num_tokens": 15458003.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 6.5898370265960695,
|
|
"epoch": 0.9043020193151887,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004942179602149071,
|
|
"loss": 6.4215,
|
|
"mean_token_accuracy": 0.1416545756161213,
|
|
"num_tokens": 15473798.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 6.681325674057007,
|
|
"epoch": 0.9052775338991318,
|
|
"grad_norm": 0.69921875,
|
|
"learning_rate": 0.0004942021070523626,
|
|
"loss": 6.4423,
|
|
"mean_token_accuracy": 0.13908602744340898,
|
|
"num_tokens": 15490620.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 6.644861221313477,
|
|
"epoch": 0.9062530484830749,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004941862324701695,
|
|
"loss": 6.4652,
|
|
"mean_token_accuracy": 0.13896602317690848,
|
|
"num_tokens": 15506777.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 6.765894794464112,
|
|
"epoch": 0.9072285630670178,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004941703364698789,
|
|
"loss": 6.6892,
|
|
"mean_token_accuracy": 0.11812538206577301,
|
|
"num_tokens": 15523416.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 6.748886585235596,
|
|
"epoch": 0.9082040776509609,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004941544190530442,
|
|
"loss": 6.4563,
|
|
"mean_token_accuracy": 0.13743775188922883,
|
|
"num_tokens": 15541064.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 6.814270162582398,
|
|
"epoch": 0.909179592234904,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.0004941384802212207,
|
|
"loss": 6.7114,
|
|
"mean_token_accuracy": 0.12126853093504905,
|
|
"num_tokens": 15559391.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 6.7333392143249515,
|
|
"epoch": 0.9101551068188469,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000494122519975966,
|
|
"loss": 6.5182,
|
|
"mean_token_accuracy": 0.12647362649440766,
|
|
"num_tokens": 15576842.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 6.691408348083496,
|
|
"epoch": 0.91113062140279,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004941065383188396,
|
|
"loss": 6.5005,
|
|
"mean_token_accuracy": 0.1361497737467289,
|
|
"num_tokens": 15592442.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 6.76990122795105,
|
|
"epoch": 0.912106135986733,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004940905352514032,
|
|
"loss": 6.5732,
|
|
"mean_token_accuracy": 0.1252450466156006,
|
|
"num_tokens": 15608402.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 6.770832586288452,
|
|
"epoch": 0.913081650570676,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004940745107752205,
|
|
"loss": 6.5469,
|
|
"mean_token_accuracy": 0.1261501595377922,
|
|
"num_tokens": 15624349.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 6.744387102127075,
|
|
"epoch": 0.9140571651546191,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004940584648918573,
|
|
"loss": 6.6197,
|
|
"mean_token_accuracy": 0.13034187108278275,
|
|
"num_tokens": 15640901.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 6.82858304977417,
|
|
"epoch": 0.9150326797385621,
|
|
"grad_norm": 0.6796875,
|
|
"learning_rate": 0.0004940423976028819,
|
|
"loss": 6.6701,
|
|
"mean_token_accuracy": 0.12326755970716477,
|
|
"num_tokens": 15658947.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 6.826796579360962,
|
|
"epoch": 0.9160081943225051,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004940263089098639,
|
|
"loss": 6.6859,
|
|
"mean_token_accuracy": 0.12220687046647072,
|
|
"num_tokens": 15674459.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 6.694485902786255,
|
|
"epoch": 0.9169837089064482,
|
|
"grad_norm": 0.67578125,
|
|
"learning_rate": 0.0004940101988143757,
|
|
"loss": 6.5766,
|
|
"mean_token_accuracy": 0.13081153780221938,
|
|
"num_tokens": 15691951.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 6.772763395309449,
|
|
"epoch": 0.9179592234903912,
|
|
"grad_norm": 0.703125,
|
|
"learning_rate": 0.0004939940673179914,
|
|
"loss": 6.623,
|
|
"mean_token_accuracy": 0.1193988211452961,
|
|
"num_tokens": 15708539.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 6.742880630493164,
|
|
"epoch": 0.9189347380743342,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.0004939779144222873,
|
|
"loss": 6.6111,
|
|
"mean_token_accuracy": 0.1290360175073147,
|
|
"num_tokens": 15727108.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 6.794376230239868,
|
|
"epoch": 0.9199102526582772,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004939617401288419,
|
|
"loss": 6.5645,
|
|
"mean_token_accuracy": 0.12572109922766686,
|
|
"num_tokens": 15743436.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 6.805693864822388,
|
|
"epoch": 0.9208857672422203,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004939455444392357,
|
|
"loss": 6.6725,
|
|
"mean_token_accuracy": 0.12285950481891632,
|
|
"num_tokens": 15761438.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 6.7437115669250485,
|
|
"epoch": 0.9218612818261633,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004939293273550512,
|
|
"loss": 6.5325,
|
|
"mean_token_accuracy": 0.12812544032931328,
|
|
"num_tokens": 15777064.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 6.772646713256836,
|
|
"epoch": 0.9228367964101063,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004939130888778731,
|
|
"loss": 6.5485,
|
|
"mean_token_accuracy": 0.1265196196734905,
|
|
"num_tokens": 15793346.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 6.717227554321289,
|
|
"epoch": 0.9238123109940494,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004938968290092883,
|
|
"loss": 6.5641,
|
|
"mean_token_accuracy": 0.12451535612344741,
|
|
"num_tokens": 15809557.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 6.812444877624512,
|
|
"epoch": 0.9247878255779924,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004938805477508853,
|
|
"loss": 6.6014,
|
|
"mean_token_accuracy": 0.12167017161846161,
|
|
"num_tokens": 15826717.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 6.781039237976074,
|
|
"epoch": 0.9257633401619354,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004938642451042554,
|
|
"loss": 6.5891,
|
|
"mean_token_accuracy": 0.12501516789197922,
|
|
"num_tokens": 15842472.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 6.646473693847656,
|
|
"epoch": 0.9267388547458785,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004938479210709915,
|
|
"loss": 6.4892,
|
|
"mean_token_accuracy": 0.13338827788829805,
|
|
"num_tokens": 15860136.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 6.748292922973633,
|
|
"epoch": 0.9277143693298214,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004938315756526886,
|
|
"loss": 6.5399,
|
|
"mean_token_accuracy": 0.13835914805531502,
|
|
"num_tokens": 15878538.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 6.746389293670655,
|
|
"epoch": 0.9286898839137645,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004938152088509442,
|
|
"loss": 6.5928,
|
|
"mean_token_accuracy": 0.12372750118374824,
|
|
"num_tokens": 15892875.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 6.720780229568481,
|
|
"epoch": 0.9296653984977076,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004937988206673576,
|
|
"loss": 6.4411,
|
|
"mean_token_accuracy": 0.1332447350025177,
|
|
"num_tokens": 15909366.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 6.649787092208863,
|
|
"epoch": 0.9306409130816505,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004937824111035298,
|
|
"loss": 6.5203,
|
|
"mean_token_accuracy": 0.13143991231918334,
|
|
"num_tokens": 15927712.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 6.829579162597656,
|
|
"epoch": 0.9316164276655936,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.0004937659801610647,
|
|
"loss": 6.639,
|
|
"mean_token_accuracy": 0.11892245039343834,
|
|
"num_tokens": 15943474.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 6.768540239334106,
|
|
"epoch": 0.9325919422495367,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004937495278415677,
|
|
"loss": 6.6072,
|
|
"mean_token_accuracy": 0.11697220504283905,
|
|
"num_tokens": 15959546.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 6.811228799819946,
|
|
"epoch": 0.9335674568334796,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004937330541466465,
|
|
"loss": 6.5266,
|
|
"mean_token_accuracy": 0.12453490197658539,
|
|
"num_tokens": 15975669.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 6.6306641578674315,
|
|
"epoch": 0.9345429714174227,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004937165590779108,
|
|
"loss": 6.4901,
|
|
"mean_token_accuracy": 0.1434645287692547,
|
|
"num_tokens": 15992898.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 6.71198616027832,
|
|
"epoch": 0.9355184860013657,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004937000426369724,
|
|
"loss": 6.5159,
|
|
"mean_token_accuracy": 0.12428527399897575,
|
|
"num_tokens": 16010102.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 6.786551809310913,
|
|
"epoch": 0.9364940005853087,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004936835048254453,
|
|
"loss": 6.6019,
|
|
"mean_token_accuracy": 0.12086697742342949,
|
|
"num_tokens": 16027167.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 6.738112688064575,
|
|
"epoch": 0.9374695151692518,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004936669456449455,
|
|
"loss": 6.5661,
|
|
"mean_token_accuracy": 0.1264267936348915,
|
|
"num_tokens": 16042873.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 6.754957389831543,
|
|
"epoch": 0.9384450297531948,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004936503650970912,
|
|
"loss": 6.6127,
|
|
"mean_token_accuracy": 0.12498534545302391,
|
|
"num_tokens": 16060814.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 6.770929384231567,
|
|
"epoch": 0.9394205443371378,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004936337631835024,
|
|
"loss": 6.5681,
|
|
"mean_token_accuracy": 0.11996268555521965,
|
|
"num_tokens": 16078378.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 6.622520875930786,
|
|
"epoch": 0.9403960589210809,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004936171399058017,
|
|
"loss": 6.3601,
|
|
"mean_token_accuracy": 0.1373235210776329,
|
|
"num_tokens": 16094601.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 6.608865737915039,
|
|
"epoch": 0.9413715735050239,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004936004952656131,
|
|
"loss": 6.438,
|
|
"mean_token_accuracy": 0.13593896329402924,
|
|
"num_tokens": 16113189.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 6.81975564956665,
|
|
"epoch": 0.9423470880889669,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004935838292645632,
|
|
"loss": 6.6653,
|
|
"mean_token_accuracy": 0.12186609581112862,
|
|
"num_tokens": 16131225.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 6.6545158386230465,
|
|
"epoch": 0.9433226026729099,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.0004935671419042805,
|
|
"loss": 6.5253,
|
|
"mean_token_accuracy": 0.12359081655740738,
|
|
"num_tokens": 16149733.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 6.720641279220581,
|
|
"epoch": 0.944298117256853,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004935504331863958,
|
|
"loss": 6.4727,
|
|
"mean_token_accuracy": 0.13165752291679383,
|
|
"num_tokens": 16167499.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 6.565612554550171,
|
|
"epoch": 0.945273631840796,
|
|
"grad_norm": 0.68359375,
|
|
"learning_rate": 0.0004935337031125416,
|
|
"loss": 6.4102,
|
|
"mean_token_accuracy": 0.1429556801915169,
|
|
"num_tokens": 16184858.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 6.739479970932007,
|
|
"epoch": 0.946249146424739,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004935169516843528,
|
|
"loss": 6.5855,
|
|
"mean_token_accuracy": 0.13273394852876663,
|
|
"num_tokens": 16201824.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 6.63283143043518,
|
|
"epoch": 0.9472246610086821,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004935001789034664,
|
|
"loss": 6.3914,
|
|
"mean_token_accuracy": 0.13475433140993118,
|
|
"num_tokens": 16219551.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 6.6811065673828125,
|
|
"epoch": 0.9482001755926251,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004934833847715212,
|
|
"loss": 6.5167,
|
|
"mean_token_accuracy": 0.13799150735139848,
|
|
"num_tokens": 16237447.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 6.79054708480835,
|
|
"epoch": 0.9491756901765681,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004934665692901583,
|
|
"loss": 6.6764,
|
|
"mean_token_accuracy": 0.12293369993567467,
|
|
"num_tokens": 16254377.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 6.722975063323974,
|
|
"epoch": 0.9501512047605112,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000493449732461021,
|
|
"loss": 6.4917,
|
|
"mean_token_accuracy": 0.1348854698240757,
|
|
"num_tokens": 16271669.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 6.669310092926025,
|
|
"epoch": 0.9511267193444543,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004934328742857543,
|
|
"loss": 6.4782,
|
|
"mean_token_accuracy": 0.13384035527706145,
|
|
"num_tokens": 16287088.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 6.598203420639038,
|
|
"epoch": 0.9521022339283972,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004934159947660057,
|
|
"loss": 6.4218,
|
|
"mean_token_accuracy": 0.13421206250786782,
|
|
"num_tokens": 16303646.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 6.715553188323975,
|
|
"epoch": 0.9530777485123403,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004933990939034244,
|
|
"loss": 6.4996,
|
|
"mean_token_accuracy": 0.1288976863026619,
|
|
"num_tokens": 16320610.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 6.681740617752075,
|
|
"epoch": 0.9540532630962832,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004933821716996621,
|
|
"loss": 6.4432,
|
|
"mean_token_accuracy": 0.13466012477874756,
|
|
"num_tokens": 16337983.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 6.667843151092529,
|
|
"epoch": 0.9550287776802263,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004933652281563723,
|
|
"loss": 6.4834,
|
|
"mean_token_accuracy": 0.1254363052546978,
|
|
"num_tokens": 16356645.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 6.710570240020752,
|
|
"epoch": 0.9560042922641694,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004933482632752107,
|
|
"loss": 6.5141,
|
|
"mean_token_accuracy": 0.12365303486585617,
|
|
"num_tokens": 16371619.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 6.654227542877197,
|
|
"epoch": 0.9569798068481123,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.0004933312770578351,
|
|
"loss": 6.5061,
|
|
"mean_token_accuracy": 0.13438002169132232,
|
|
"num_tokens": 16389831.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 6.792648553848267,
|
|
"epoch": 0.9579553214320554,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004933142695059052,
|
|
"loss": 6.5603,
|
|
"mean_token_accuracy": 0.12337814420461654,
|
|
"num_tokens": 16406132.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 6.713674640655517,
|
|
"epoch": 0.9589308360159985,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004932972406210829,
|
|
"loss": 6.5524,
|
|
"mean_token_accuracy": 0.12808084711432458,
|
|
"num_tokens": 16422442.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 6.687591648101806,
|
|
"epoch": 0.9599063505999414,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004932801904050323,
|
|
"loss": 6.4688,
|
|
"mean_token_accuracy": 0.13278883695602417,
|
|
"num_tokens": 16440290.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 6.7589030265808105,
|
|
"epoch": 0.9608818651838845,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004932631188594195,
|
|
"loss": 6.5871,
|
|
"mean_token_accuracy": 0.13077618703246116,
|
|
"num_tokens": 16456904.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 6.70479097366333,
|
|
"epoch": 0.9618573797678275,
|
|
"grad_norm": 0.70703125,
|
|
"learning_rate": 0.0004932460259859127,
|
|
"loss": 6.5177,
|
|
"mean_token_accuracy": 0.1314974159002304,
|
|
"num_tokens": 16473777.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 6.662526702880859,
|
|
"epoch": 0.9628328943517706,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004932289117861819,
|
|
"loss": 6.455,
|
|
"mean_token_accuracy": 0.13177084550261497,
|
|
"num_tokens": 16490401.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 6.732591867446899,
|
|
"epoch": 0.9638084089357136,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004932117762618997,
|
|
"loss": 6.495,
|
|
"mean_token_accuracy": 0.12733167111873628,
|
|
"num_tokens": 16508582.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 6.736188125610352,
|
|
"epoch": 0.9647839235196566,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004931946194147404,
|
|
"loss": 6.5596,
|
|
"mean_token_accuracy": 0.12850298583507538,
|
|
"num_tokens": 16523939.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 6.613898992538452,
|
|
"epoch": 0.9657594381035997,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004931774412463806,
|
|
"loss": 6.5158,
|
|
"mean_token_accuracy": 0.13246511295437813,
|
|
"num_tokens": 16541139.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 6.822346258163452,
|
|
"epoch": 0.9667349526875427,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.0004931602417584989,
|
|
"loss": 6.5544,
|
|
"mean_token_accuracy": 0.12631049007177353,
|
|
"num_tokens": 16558351.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 6.7431432723999025,
|
|
"epoch": 0.9677104672714857,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004931430209527759,
|
|
"loss": 6.6083,
|
|
"mean_token_accuracy": 0.12207760289311409,
|
|
"num_tokens": 16575777.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 6.760752964019775,
|
|
"epoch": 0.9686859818554288,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004931257788308943,
|
|
"loss": 6.5647,
|
|
"mean_token_accuracy": 0.1282369688153267,
|
|
"num_tokens": 16592490.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 6.711967134475708,
|
|
"epoch": 0.9696614964393717,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000493108515394539,
|
|
"loss": 6.5665,
|
|
"mean_token_accuracy": 0.13015906438231467,
|
|
"num_tokens": 16610378.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 6.7380143165588375,
|
|
"epoch": 0.9706370110233148,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004930912306453971,
|
|
"loss": 6.6119,
|
|
"mean_token_accuracy": 0.11969036087393761,
|
|
"num_tokens": 16625445.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 6.786689710617066,
|
|
"epoch": 0.9716125256072579,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004930739245851571,
|
|
"loss": 6.5987,
|
|
"mean_token_accuracy": 0.12239839658141136,
|
|
"num_tokens": 16641821.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 6.774446868896485,
|
|
"epoch": 0.9725880401912008,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.0004930565972155106,
|
|
"loss": 6.5786,
|
|
"mean_token_accuracy": 0.1215771459043026,
|
|
"num_tokens": 16658418.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 6.752751779556275,
|
|
"epoch": 0.9735635547751439,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004930392485381506,
|
|
"loss": 6.5744,
|
|
"mean_token_accuracy": 0.1281782269477844,
|
|
"num_tokens": 16674218.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 6.711444234848022,
|
|
"epoch": 0.974539069359087,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004930218785547724,
|
|
"loss": 6.5776,
|
|
"mean_token_accuracy": 0.13218012377619742,
|
|
"num_tokens": 16692171.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 6.837441635131836,
|
|
"epoch": 0.9755145839430299,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004930044872670733,
|
|
"loss": 6.6483,
|
|
"mean_token_accuracy": 0.11807728856801987,
|
|
"num_tokens": 16709231.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 6.753890657424927,
|
|
"epoch": 0.976490098526973,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004929870746767525,
|
|
"loss": 6.5461,
|
|
"mean_token_accuracy": 0.12596854642033578,
|
|
"num_tokens": 16726281.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 6.7414265155792235,
|
|
"epoch": 0.977465613110916,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004929696407855118,
|
|
"loss": 6.6032,
|
|
"mean_token_accuracy": 0.12050205171108246,
|
|
"num_tokens": 16744821.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 6.71658673286438,
|
|
"epoch": 0.978441127694859,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004929521855950546,
|
|
"loss": 6.4142,
|
|
"mean_token_accuracy": 0.13205682188272477,
|
|
"num_tokens": 16762564.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 6.627632141113281,
|
|
"epoch": 0.9794166422788021,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004929347091070866,
|
|
"loss": 6.3838,
|
|
"mean_token_accuracy": 0.14066333025693895,
|
|
"num_tokens": 16777681.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 6.71387095451355,
|
|
"epoch": 0.9803921568627451,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004929172113233157,
|
|
"loss": 6.6117,
|
|
"mean_token_accuracy": 0.12575932070612908,
|
|
"num_tokens": 16793820.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 6.765808057785034,
|
|
"epoch": 0.9813676714466881,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004928996922454515,
|
|
"loss": 6.6082,
|
|
"mean_token_accuracy": 0.12675923630595207,
|
|
"num_tokens": 16811445.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 6.736690473556519,
|
|
"epoch": 0.9823431860306312,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004928821518752059,
|
|
"loss": 6.5633,
|
|
"mean_token_accuracy": 0.1284546084702015,
|
|
"num_tokens": 16827961.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 6.75536699295044,
|
|
"epoch": 0.9833187006145742,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004928645902142931,
|
|
"loss": 6.459,
|
|
"mean_token_accuracy": 0.12689751759171486,
|
|
"num_tokens": 16844074.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 6.673928117752075,
|
|
"epoch": 0.9842942151985172,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.000492847007264429,
|
|
"loss": 6.508,
|
|
"mean_token_accuracy": 0.125472192466259,
|
|
"num_tokens": 16862004.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 6.715847206115723,
|
|
"epoch": 0.9852697297824603,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004928294030273317,
|
|
"loss": 6.5069,
|
|
"mean_token_accuracy": 0.12556252405047416,
|
|
"num_tokens": 16879738.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 6.657883405685425,
|
|
"epoch": 0.9862452443664033,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004928117775047215,
|
|
"loss": 6.4555,
|
|
"mean_token_accuracy": 0.13658895194530488,
|
|
"num_tokens": 16896565.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 6.712939119338989,
|
|
"epoch": 0.9872207589503463,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004927941306983207,
|
|
"loss": 6.5533,
|
|
"mean_token_accuracy": 0.12876136377453803,
|
|
"num_tokens": 16912443.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 6.820679187774658,
|
|
"epoch": 0.9881962735342893,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004927764626098537,
|
|
"loss": 6.594,
|
|
"mean_token_accuracy": 0.12440543174743653,
|
|
"num_tokens": 16928292.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 6.673741292953491,
|
|
"epoch": 0.9891717881182324,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000492758773241047,
|
|
"loss": 6.5559,
|
|
"mean_token_accuracy": 0.1299467831850052,
|
|
"num_tokens": 16945432.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 6.639361906051636,
|
|
"epoch": 0.9901473027021754,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.000492741062593629,
|
|
"loss": 6.3842,
|
|
"mean_token_accuracy": 0.13867289051413537,
|
|
"num_tokens": 16962440.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 6.7092818260192875,
|
|
"epoch": 0.9911228172861184,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004927233306693305,
|
|
"loss": 6.4853,
|
|
"mean_token_accuracy": 0.13430802673101425,
|
|
"num_tokens": 16979227.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 6.788237524032593,
|
|
"epoch": 0.9920983318700615,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004927055774698839,
|
|
"loss": 6.5521,
|
|
"mean_token_accuracy": 0.12267785742878914,
|
|
"num_tokens": 16994873.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 6.724420690536499,
|
|
"epoch": 0.9930738464540045,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004926878029970245,
|
|
"loss": 6.6071,
|
|
"mean_token_accuracy": 0.12418792396783829,
|
|
"num_tokens": 17011516.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 6.748596858978272,
|
|
"epoch": 0.9940493610379475,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004926700072524887,
|
|
"loss": 6.5097,
|
|
"mean_token_accuracy": 0.12452549487352371,
|
|
"num_tokens": 17029407.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 6.7219456195831295,
|
|
"epoch": 0.9950248756218906,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004926521902380154,
|
|
"loss": 6.5653,
|
|
"mean_token_accuracy": 0.12338426634669304,
|
|
"num_tokens": 17044451.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 6.621499013900757,
|
|
"epoch": 0.9960003902058335,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004926343519553461,
|
|
"loss": 6.4186,
|
|
"mean_token_accuracy": 0.13842255100607873,
|
|
"num_tokens": 17060420.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 6.758805131912231,
|
|
"epoch": 0.9969759047897766,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004926164924062234,
|
|
"loss": 6.5342,
|
|
"mean_token_accuracy": 0.12775072008371352,
|
|
"num_tokens": 17076562.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 6.663560485839843,
|
|
"epoch": 0.9979514193737197,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.0004925986115923927,
|
|
"loss": 6.5631,
|
|
"mean_token_accuracy": 0.14136235266923905,
|
|
"num_tokens": 17092441.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 6.714413261413574,
|
|
"epoch": 0.9989269339576626,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004925807095156013,
|
|
"loss": 6.58,
|
|
"mean_token_accuracy": 0.12429802343249322,
|
|
"num_tokens": 17109447.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 6.678040838241577,
|
|
"epoch": 0.9999024485416057,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004925627861775983,
|
|
"loss": 6.4605,
|
|
"mean_token_accuracy": 0.13339569941163062,
|
|
"num_tokens": 17125795.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 6.66641018125746,
|
|
"epoch": 1.0007804116671544,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004925448415801353,
|
|
"loss": 6.4625,
|
|
"mean_token_accuracy": 0.13256488823228413,
|
|
"num_tokens": 17139062.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 6.775556802749634,
|
|
"epoch": 1.0017559262510976,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004925268757249657,
|
|
"loss": 6.524,
|
|
"mean_token_accuracy": 0.12040288001298904,
|
|
"num_tokens": 17155465.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 6.767190074920654,
|
|
"epoch": 1.0027314408350405,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004925088886138451,
|
|
"loss": 6.403,
|
|
"mean_token_accuracy": 0.12848262935876847,
|
|
"num_tokens": 17171284.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 6.548037385940551,
|
|
"epoch": 1.0037069554189835,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004924908802485311,
|
|
"loss": 6.3262,
|
|
"mean_token_accuracy": 0.1382754310965538,
|
|
"num_tokens": 17190823.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 6.737587547302246,
|
|
"epoch": 1.0046824700029267,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004924728506307835,
|
|
"loss": 6.4463,
|
|
"mean_token_accuracy": 0.12853201925754548,
|
|
"num_tokens": 17208866.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 6.745419311523437,
|
|
"epoch": 1.0056579845868696,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000492454799762364,
|
|
"loss": 6.5282,
|
|
"mean_token_accuracy": 0.12446813806891441,
|
|
"num_tokens": 17225609.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 6.77004976272583,
|
|
"epoch": 1.0066334991708126,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004924367276450364,
|
|
"loss": 6.5127,
|
|
"mean_token_accuracy": 0.12857401371002197,
|
|
"num_tokens": 17242198.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 6.751516389846802,
|
|
"epoch": 1.0076090137547555,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004924186342805669,
|
|
"loss": 6.4982,
|
|
"mean_token_accuracy": 0.1260545641183853,
|
|
"num_tokens": 17258712.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 6.665580415725708,
|
|
"epoch": 1.0085845283386987,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004924005196707233,
|
|
"loss": 6.4786,
|
|
"mean_token_accuracy": 0.13178402408957482,
|
|
"num_tokens": 17274790.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 6.793641424179077,
|
|
"epoch": 1.0095600429226417,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004923823838172756,
|
|
"loss": 6.4185,
|
|
"mean_token_accuracy": 0.1280883103609085,
|
|
"num_tokens": 17290526.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 6.7109826564788815,
|
|
"epoch": 1.0105355575065846,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004923642267219962,
|
|
"loss": 6.4996,
|
|
"mean_token_accuracy": 0.12554331347346306,
|
|
"num_tokens": 17306022.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 6.74385027885437,
|
|
"epoch": 1.0115110720905278,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004923460483866593,
|
|
"loss": 6.4778,
|
|
"mean_token_accuracy": 0.1298864670097828,
|
|
"num_tokens": 17321601.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 6.659259891510009,
|
|
"epoch": 1.0124865866744708,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004923278488130412,
|
|
"loss": 6.3554,
|
|
"mean_token_accuracy": 0.1357702985405922,
|
|
"num_tokens": 17337997.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 6.687304067611694,
|
|
"epoch": 1.0134621012584137,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004923096280029202,
|
|
"loss": 6.438,
|
|
"mean_token_accuracy": 0.12693195194005966,
|
|
"num_tokens": 17354809.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 6.622614955902099,
|
|
"epoch": 1.014437615842357,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000492291385958077,
|
|
"loss": 6.3054,
|
|
"mean_token_accuracy": 0.14085084572434425,
|
|
"num_tokens": 17371548.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 6.66763744354248,
|
|
"epoch": 1.0154131304262999,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004922731226802939,
|
|
"loss": 6.4198,
|
|
"mean_token_accuracy": 0.13362706527113916,
|
|
"num_tokens": 17388891.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 6.643477487564087,
|
|
"epoch": 1.0163886450102428,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004922548381713556,
|
|
"loss": 6.3933,
|
|
"mean_token_accuracy": 0.13453625813126563,
|
|
"num_tokens": 17407501.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 6.694887447357178,
|
|
"epoch": 1.017364159594186,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004922365324330489,
|
|
"loss": 6.4431,
|
|
"mean_token_accuracy": 0.1309220626950264,
|
|
"num_tokens": 17425541.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 6.6731573104858395,
|
|
"epoch": 1.018339674178129,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004922182054671625,
|
|
"loss": 6.3862,
|
|
"mean_token_accuracy": 0.12441431358456612,
|
|
"num_tokens": 17441588.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 6.690103912353516,
|
|
"epoch": 1.019315188762072,
|
|
"grad_norm": 0.6953125,
|
|
"learning_rate": 0.0004921998572754872,
|
|
"loss": 6.3806,
|
|
"mean_token_accuracy": 0.13286701664328576,
|
|
"num_tokens": 17458874.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 6.61646671295166,
|
|
"epoch": 1.0202907033460151,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004921814878598159,
|
|
"loss": 6.3453,
|
|
"mean_token_accuracy": 0.13452423810958863,
|
|
"num_tokens": 17475815.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 6.6693840503692625,
|
|
"epoch": 1.021266217929958,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004921630972219437,
|
|
"loss": 6.3912,
|
|
"mean_token_accuracy": 0.13091225922107697,
|
|
"num_tokens": 17492068.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 6.665246868133545,
|
|
"epoch": 1.022241732513901,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004921446853636676,
|
|
"loss": 6.3846,
|
|
"mean_token_accuracy": 0.12640874460339546,
|
|
"num_tokens": 17508156.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 6.730614852905274,
|
|
"epoch": 1.023217247097844,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004921262522867869,
|
|
"loss": 6.455,
|
|
"mean_token_accuracy": 0.12842260375618936,
|
|
"num_tokens": 17525374.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 6.711771392822266,
|
|
"epoch": 1.0241927616817872,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004921077979931026,
|
|
"loss": 6.3564,
|
|
"mean_token_accuracy": 0.13285744339227676,
|
|
"num_tokens": 17541453.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 6.6745575904846195,
|
|
"epoch": 1.0251682762657301,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.000492089322484418,
|
|
"loss": 6.4187,
|
|
"mean_token_accuracy": 0.12960034757852554,
|
|
"num_tokens": 17557981.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 6.634501791000366,
|
|
"epoch": 1.026143790849673,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004920708257625386,
|
|
"loss": 6.3344,
|
|
"mean_token_accuracy": 0.13548049628734588,
|
|
"num_tokens": 17573094.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 6.732572078704834,
|
|
"epoch": 1.0271193054336163,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004920523078292718,
|
|
"loss": 6.5424,
|
|
"mean_token_accuracy": 0.12724708914756774,
|
|
"num_tokens": 17589933.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 6.800477790832519,
|
|
"epoch": 1.0280948200175593,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004920337686864269,
|
|
"loss": 6.4752,
|
|
"mean_token_accuracy": 0.12684278413653374,
|
|
"num_tokens": 17607008.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 6.6964335441589355,
|
|
"epoch": 1.0290703346015022,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004920152083358158,
|
|
"loss": 6.442,
|
|
"mean_token_accuracy": 0.13671548590064048,
|
|
"num_tokens": 17624160.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 6.66519513130188,
|
|
"epoch": 1.0300458491854454,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.000491996626779252,
|
|
"loss": 6.3865,
|
|
"mean_token_accuracy": 0.1336288832128048,
|
|
"num_tokens": 17640067.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 6.7353168487548825,
|
|
"epoch": 1.0310213637693884,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004919780240185512,
|
|
"loss": 6.466,
|
|
"mean_token_accuracy": 0.13027292266488075,
|
|
"num_tokens": 17658278.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 6.734882402420044,
|
|
"epoch": 1.0319968783533313,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004919594000555311,
|
|
"loss": 6.4693,
|
|
"mean_token_accuracy": 0.12381713688373566,
|
|
"num_tokens": 17673878.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 6.6431962013244625,
|
|
"epoch": 1.0329723929372745,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004919407548920118,
|
|
"loss": 6.3972,
|
|
"mean_token_accuracy": 0.1301102578639984,
|
|
"num_tokens": 17688872.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 6.724818134307862,
|
|
"epoch": 1.0339479075212175,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.000491922088529815,
|
|
"loss": 6.4332,
|
|
"mean_token_accuracy": 0.1287728391587734,
|
|
"num_tokens": 17704284.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 6.6159436225891115,
|
|
"epoch": 1.0349234221051604,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004919034009707651,
|
|
"loss": 6.3049,
|
|
"mean_token_accuracy": 0.13987264707684516,
|
|
"num_tokens": 17721296.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 6.710259580612183,
|
|
"epoch": 1.0358989366891036,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004918846922166877,
|
|
"loss": 6.4935,
|
|
"mean_token_accuracy": 0.12761796936392783,
|
|
"num_tokens": 17738549.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 6.683872652053833,
|
|
"epoch": 1.0368744512730466,
|
|
"grad_norm": 0.6875,
|
|
"learning_rate": 0.0004918659622694111,
|
|
"loss": 6.369,
|
|
"mean_token_accuracy": 0.13762161359190941,
|
|
"num_tokens": 17755297.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 6.639872026443482,
|
|
"epoch": 1.0378499658569895,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004918472111307658,
|
|
"loss": 6.4206,
|
|
"mean_token_accuracy": 0.1318216621875763,
|
|
"num_tokens": 17771459.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 6.645898008346558,
|
|
"epoch": 1.0388254804409325,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004918284388025837,
|
|
"loss": 6.423,
|
|
"mean_token_accuracy": 0.13523929491639136,
|
|
"num_tokens": 17787009.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 6.692308807373047,
|
|
"epoch": 1.0398009950248757,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004918096452866995,
|
|
"loss": 6.4425,
|
|
"mean_token_accuracy": 0.12655118778347968,
|
|
"num_tokens": 17804643.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 6.751505661010742,
|
|
"epoch": 1.0407765096088186,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004917908305849493,
|
|
"loss": 6.4924,
|
|
"mean_token_accuracy": 0.12636105418205262,
|
|
"num_tokens": 17821104.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 6.776487350463867,
|
|
"epoch": 1.0417520241927616,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.000491771994699172,
|
|
"loss": 6.4741,
|
|
"mean_token_accuracy": 0.13109548911452293,
|
|
"num_tokens": 17838094.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 6.548758411407471,
|
|
"epoch": 1.0427275387767048,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004917531376312079,
|
|
"loss": 6.3283,
|
|
"mean_token_accuracy": 0.13365790396928787,
|
|
"num_tokens": 17853856.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 6.7276613235473635,
|
|
"epoch": 1.0437030533606477,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004917342593828997,
|
|
"loss": 6.4476,
|
|
"mean_token_accuracy": 0.12195442393422126,
|
|
"num_tokens": 17870032.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 6.61826457977295,
|
|
"epoch": 1.0446785679445907,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.000491715359956092,
|
|
"loss": 6.3503,
|
|
"mean_token_accuracy": 0.13930656909942626,
|
|
"num_tokens": 17886384.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 6.824443340301514,
|
|
"epoch": 1.0456540825285339,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004916964393526319,
|
|
"loss": 6.5407,
|
|
"mean_token_accuracy": 0.1281147450208664,
|
|
"num_tokens": 17903444.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 6.716145277023315,
|
|
"epoch": 1.0466295971124768,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004916774975743679,
|
|
"loss": 6.4149,
|
|
"mean_token_accuracy": 0.13091564178466797,
|
|
"num_tokens": 17920042.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 6.596774625778198,
|
|
"epoch": 1.0476051116964198,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004916585346231513,
|
|
"loss": 6.3885,
|
|
"mean_token_accuracy": 0.14468008503317834,
|
|
"num_tokens": 17937115.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 6.6912314891815186,
|
|
"epoch": 1.048580626280363,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004916395505008347,
|
|
"loss": 6.4416,
|
|
"mean_token_accuracy": 0.12908195033669473,
|
|
"num_tokens": 17953582.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 6.624496173858643,
|
|
"epoch": 1.049556140864306,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004916205452092735,
|
|
"loss": 6.4382,
|
|
"mean_token_accuracy": 0.13025539964437485,
|
|
"num_tokens": 17970457.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 6.7728667736053465,
|
|
"epoch": 1.050531655448249,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004916015187503245,
|
|
"loss": 6.4213,
|
|
"mean_token_accuracy": 0.13091359362006189,
|
|
"num_tokens": 17987168.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 6.544854354858399,
|
|
"epoch": 1.051507170032192,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004915824711258472,
|
|
"loss": 6.343,
|
|
"mean_token_accuracy": 0.1395393043756485,
|
|
"num_tokens": 18004964.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 6.718837261199951,
|
|
"epoch": 1.052482684616135,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004915634023377026,
|
|
"loss": 6.4339,
|
|
"mean_token_accuracy": 0.13042836785316467,
|
|
"num_tokens": 18021778.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 6.530203485488892,
|
|
"epoch": 1.053458199200078,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004915443123877543,
|
|
"loss": 6.2749,
|
|
"mean_token_accuracy": 0.1345466211438179,
|
|
"num_tokens": 18037620.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 6.711172676086425,
|
|
"epoch": 1.0544337137840212,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004915252012778676,
|
|
"loss": 6.3851,
|
|
"mean_token_accuracy": 0.13336986005306245,
|
|
"num_tokens": 18054623.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 6.642951917648316,
|
|
"epoch": 1.0554092283679641,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004915060690099098,
|
|
"loss": 6.3888,
|
|
"mean_token_accuracy": 0.12971734926104544,
|
|
"num_tokens": 18071271.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 6.694894647598266,
|
|
"epoch": 1.056384742951907,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004914869155857506,
|
|
"loss": 6.4663,
|
|
"mean_token_accuracy": 0.12497211396694183,
|
|
"num_tokens": 18087661.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 6.611609220504761,
|
|
"epoch": 1.05736025753585,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004914677410072616,
|
|
"loss": 6.3605,
|
|
"mean_token_accuracy": 0.13634153380990027,
|
|
"num_tokens": 18106116.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 6.6791966438293455,
|
|
"epoch": 1.0583357721197932,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004914485452763165,
|
|
"loss": 6.4663,
|
|
"mean_token_accuracy": 0.12572635114192962,
|
|
"num_tokens": 18122420.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 6.752566480636597,
|
|
"epoch": 1.0593112867037362,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.000491429328394791,
|
|
"loss": 6.4879,
|
|
"mean_token_accuracy": 0.12334733307361603,
|
|
"num_tokens": 18137974.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 6.570928621292114,
|
|
"epoch": 1.0602868012876792,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004914100903645629,
|
|
"loss": 6.3134,
|
|
"mean_token_accuracy": 0.138327506929636,
|
|
"num_tokens": 18154711.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 6.671850109100342,
|
|
"epoch": 1.0612623158716223,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.000491390831187512,
|
|
"loss": 6.4848,
|
|
"mean_token_accuracy": 0.13198621571063995,
|
|
"num_tokens": 18172422.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 6.607759046554565,
|
|
"epoch": 1.0622378304555653,
|
|
"grad_norm": 0.6953125,
|
|
"learning_rate": 0.0004913715508655203,
|
|
"loss": 6.3623,
|
|
"mean_token_accuracy": 0.14050986021757125,
|
|
"num_tokens": 18189517.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 6.676476526260376,
|
|
"epoch": 1.0632133450395083,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004913522494004719,
|
|
"loss": 6.4282,
|
|
"mean_token_accuracy": 0.12278890684247017,
|
|
"num_tokens": 18206339.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 6.621167373657227,
|
|
"epoch": 1.0641888596234514,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004913329267942527,
|
|
"loss": 6.2786,
|
|
"mean_token_accuracy": 0.1429550103843212,
|
|
"num_tokens": 18223953.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 6.703151082992553,
|
|
"epoch": 1.0651643742073944,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.000491313583048751,
|
|
"loss": 6.3918,
|
|
"mean_token_accuracy": 0.1308993436396122,
|
|
"num_tokens": 18241361.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 6.617687940597534,
|
|
"epoch": 1.0661398887913374,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004912942181658569,
|
|
"loss": 6.4288,
|
|
"mean_token_accuracy": 0.1319567382335663,
|
|
"num_tokens": 18257897.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 6.7096789360046385,
|
|
"epoch": 1.0671154033752805,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004912748321474627,
|
|
"loss": 6.4399,
|
|
"mean_token_accuracy": 0.1284070260822773,
|
|
"num_tokens": 18274935.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 6.626771402359009,
|
|
"epoch": 1.0680909179592235,
|
|
"grad_norm": 0.69140625,
|
|
"learning_rate": 0.0004912554249954626,
|
|
"loss": 6.4725,
|
|
"mean_token_accuracy": 0.1313377559185028,
|
|
"num_tokens": 18292529.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 6.708932971954345,
|
|
"epoch": 1.0690664325431665,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004912359967117532,
|
|
"loss": 6.414,
|
|
"mean_token_accuracy": 0.1303751938045025,
|
|
"num_tokens": 18310278.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 6.6816552639007565,
|
|
"epoch": 1.0700419471271096,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004912165472982329,
|
|
"loss": 6.4114,
|
|
"mean_token_accuracy": 0.13700110092759132,
|
|
"num_tokens": 18326972.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 6.67582950592041,
|
|
"epoch": 1.0710174617110526,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004911970767568022,
|
|
"loss": 6.5295,
|
|
"mean_token_accuracy": 0.12791246697306632,
|
|
"num_tokens": 18345065.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 6.680382585525512,
|
|
"epoch": 1.0719929762949956,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004911775850893637,
|
|
"loss": 6.465,
|
|
"mean_token_accuracy": 0.1301020234823227,
|
|
"num_tokens": 18363251.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 6.640507984161377,
|
|
"epoch": 1.0729684908789388,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000491158072297822,
|
|
"loss": 6.3057,
|
|
"mean_token_accuracy": 0.13701991215348244,
|
|
"num_tokens": 18378650.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 6.654048728942871,
|
|
"epoch": 1.0739440054628817,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004911385383840839,
|
|
"loss": 6.4437,
|
|
"mean_token_accuracy": 0.12968962118029595,
|
|
"num_tokens": 18394533.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 6.732221889495849,
|
|
"epoch": 1.0749195200468247,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004911189833500582,
|
|
"loss": 6.4963,
|
|
"mean_token_accuracy": 0.12610382363200187,
|
|
"num_tokens": 18410752.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 6.591818809509277,
|
|
"epoch": 1.0758950346307676,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004910994071976556,
|
|
"loss": 6.2878,
|
|
"mean_token_accuracy": 0.14000853896141052,
|
|
"num_tokens": 18428027.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 6.624272203445434,
|
|
"epoch": 1.0768705492147108,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004910798099287894,
|
|
"loss": 6.3569,
|
|
"mean_token_accuracy": 0.13512597978115082,
|
|
"num_tokens": 18446380.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 6.5514075756073,
|
|
"epoch": 1.0778460637986538,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.000491060191545374,
|
|
"loss": 6.2983,
|
|
"mean_token_accuracy": 0.14754979014396669,
|
|
"num_tokens": 18464628.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 6.657880020141602,
|
|
"epoch": 1.0788215783825967,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004910405520493268,
|
|
"loss": 6.3937,
|
|
"mean_token_accuracy": 0.13371370360255241,
|
|
"num_tokens": 18479995.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 6.685855531692505,
|
|
"epoch": 1.07979709296654,
|
|
"grad_norm": 0.70703125,
|
|
"learning_rate": 0.0004910208914425669,
|
|
"loss": 6.4647,
|
|
"mean_token_accuracy": 0.13200382590293885,
|
|
"num_tokens": 18497143.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 6.725846004486084,
|
|
"epoch": 1.0807726075504829,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004910012097270153,
|
|
"loss": 6.4361,
|
|
"mean_token_accuracy": 0.12880364283919335,
|
|
"num_tokens": 18513428.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 6.694793558120727,
|
|
"epoch": 1.0817481221344258,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004909815069045955,
|
|
"loss": 6.527,
|
|
"mean_token_accuracy": 0.12542932257056236,
|
|
"num_tokens": 18529475.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 6.743012714385986,
|
|
"epoch": 1.082723636718369,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004909617829772325,
|
|
"loss": 6.4558,
|
|
"mean_token_accuracy": 0.13135768324136735,
|
|
"num_tokens": 18546156.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 6.538674926757812,
|
|
"epoch": 1.083699151302312,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004909420379468537,
|
|
"loss": 6.226,
|
|
"mean_token_accuracy": 0.1575108826160431,
|
|
"num_tokens": 18562719.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 6.610511445999146,
|
|
"epoch": 1.084674665886255,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004909222718153887,
|
|
"loss": 6.4027,
|
|
"mean_token_accuracy": 0.13855721578001975,
|
|
"num_tokens": 18580123.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 6.644355344772339,
|
|
"epoch": 1.0856501804701981,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004909024845847689,
|
|
"loss": 6.3206,
|
|
"mean_token_accuracy": 0.13565552458167077,
|
|
"num_tokens": 18597003.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 6.654948425292969,
|
|
"epoch": 1.086625695054141,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004908826762569276,
|
|
"loss": 6.4153,
|
|
"mean_token_accuracy": 0.12837702333927153,
|
|
"num_tokens": 18613812.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 6.550436210632324,
|
|
"epoch": 1.087601209638084,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004908628468338008,
|
|
"loss": 6.3446,
|
|
"mean_token_accuracy": 0.14207774847745896,
|
|
"num_tokens": 18630333.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 6.743047523498535,
|
|
"epoch": 1.088576724222027,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000490842996317326,
|
|
"loss": 6.451,
|
|
"mean_token_accuracy": 0.12841144651174546,
|
|
"num_tokens": 18646784.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 6.620843887329102,
|
|
"epoch": 1.0895522388059702,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004908231247094427,
|
|
"loss": 6.3988,
|
|
"mean_token_accuracy": 0.13459007814526558,
|
|
"num_tokens": 18664358.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 6.587128686904907,
|
|
"epoch": 1.0905277533899131,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004908032320120929,
|
|
"loss": 6.3068,
|
|
"mean_token_accuracy": 0.13738037571310996,
|
|
"num_tokens": 18681849.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 6.701042318344117,
|
|
"epoch": 1.091503267973856,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004907833182272204,
|
|
"loss": 6.4313,
|
|
"mean_token_accuracy": 0.12790991887450218,
|
|
"num_tokens": 18697127.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 6.546111965179444,
|
|
"epoch": 1.0924787825577993,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004907633833567711,
|
|
"loss": 6.3966,
|
|
"mean_token_accuracy": 0.13843503072857857,
|
|
"num_tokens": 18714859.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 6.715994548797608,
|
|
"epoch": 1.0934542971417422,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000490743427402693,
|
|
"loss": 6.3988,
|
|
"mean_token_accuracy": 0.13089461177587508,
|
|
"num_tokens": 18730083.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 6.585872983932495,
|
|
"epoch": 1.0944298117256852,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.0004907234503669361,
|
|
"loss": 6.3398,
|
|
"mean_token_accuracy": 0.13227880895137786,
|
|
"num_tokens": 18746694.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 6.679169988632202,
|
|
"epoch": 1.0954053263096284,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004907034522514524,
|
|
"loss": 6.4064,
|
|
"mean_token_accuracy": 0.1359878845512867,
|
|
"num_tokens": 18764333.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 6.652048063278198,
|
|
"epoch": 1.0963808408935714,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004906834330581963,
|
|
"loss": 6.4086,
|
|
"mean_token_accuracy": 0.13088691458106042,
|
|
"num_tokens": 18780309.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 6.642991352081299,
|
|
"epoch": 1.0973563554775143,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004906633927891237,
|
|
"loss": 6.4257,
|
|
"mean_token_accuracy": 0.13425244763493538,
|
|
"num_tokens": 18797322.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 6.685306215286255,
|
|
"epoch": 1.0983318700614575,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.000490643331446193,
|
|
"loss": 6.4527,
|
|
"mean_token_accuracy": 0.12810489162802696,
|
|
"num_tokens": 18813185.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 6.594469022750855,
|
|
"epoch": 1.0993073846454005,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004906232490313646,
|
|
"loss": 6.3502,
|
|
"mean_token_accuracy": 0.1350200243294239,
|
|
"num_tokens": 18829445.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 6.663929033279419,
|
|
"epoch": 1.1002828992293434,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.0004906031455466008,
|
|
"loss": 6.5098,
|
|
"mean_token_accuracy": 0.12947288230061532,
|
|
"num_tokens": 18846229.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 6.666509294509888,
|
|
"epoch": 1.1012584138132866,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004905830209938659,
|
|
"loss": 6.4589,
|
|
"mean_token_accuracy": 0.12613297030329704,
|
|
"num_tokens": 18861904.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 6.671247339248657,
|
|
"epoch": 1.1022339283972296,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004905628753751267,
|
|
"loss": 6.4855,
|
|
"mean_token_accuracy": 0.131856919080019,
|
|
"num_tokens": 18879160.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 6.750661563873291,
|
|
"epoch": 1.1032094429811725,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004905427086923515,
|
|
"loss": 6.4685,
|
|
"mean_token_accuracy": 0.12142312452197075,
|
|
"num_tokens": 18895388.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 6.6516388893127445,
|
|
"epoch": 1.1041849575651157,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000490522520947511,
|
|
"loss": 6.4209,
|
|
"mean_token_accuracy": 0.13159624487161636,
|
|
"num_tokens": 18912392.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 6.668423652648926,
|
|
"epoch": 1.1051604721490587,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004905023121425779,
|
|
"loss": 6.4049,
|
|
"mean_token_accuracy": 0.12961547523736955,
|
|
"num_tokens": 18928721.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 6.743476009368896,
|
|
"epoch": 1.1061359867330016,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.000490482082279527,
|
|
"loss": 6.4621,
|
|
"mean_token_accuracy": 0.12877821922302246,
|
|
"num_tokens": 18947144.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 6.64358172416687,
|
|
"epoch": 1.1071115013169446,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000490461831360335,
|
|
"loss": 6.4025,
|
|
"mean_token_accuracy": 0.1294254705309868,
|
|
"num_tokens": 18963682.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 6.646685361862183,
|
|
"epoch": 1.1080870159008878,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004904415593869806,
|
|
"loss": 6.4349,
|
|
"mean_token_accuracy": 0.13145952075719833,
|
|
"num_tokens": 18980812.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 6.685733413696289,
|
|
"epoch": 1.1090625304848307,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004904212663614452,
|
|
"loss": 6.4096,
|
|
"mean_token_accuracy": 0.13307010233402253,
|
|
"num_tokens": 18996816.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 6.65976357460022,
|
|
"epoch": 1.1100380450687737,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004904009522857111,
|
|
"loss": 6.4134,
|
|
"mean_token_accuracy": 0.13011026680469512,
|
|
"num_tokens": 19012324.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 6.569528198242187,
|
|
"epoch": 1.1110135596527169,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004903806171617638,
|
|
"loss": 6.2724,
|
|
"mean_token_accuracy": 0.1427002802491188,
|
|
"num_tokens": 19030195.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 6.615478897094727,
|
|
"epoch": 1.1119890742366598,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004903602609915901,
|
|
"loss": 6.2713,
|
|
"mean_token_accuracy": 0.1444464348256588,
|
|
"num_tokens": 19048467.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 6.573026704788208,
|
|
"epoch": 1.1129645888206028,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004903398837771794,
|
|
"loss": 6.3736,
|
|
"mean_token_accuracy": 0.1355668507516384,
|
|
"num_tokens": 19066290.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 6.547164678573608,
|
|
"epoch": 1.113940103404546,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004903194855205227,
|
|
"loss": 6.309,
|
|
"mean_token_accuracy": 0.13921879306435586,
|
|
"num_tokens": 19083455.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 6.6671836376190186,
|
|
"epoch": 1.114915617988489,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004902990662236132,
|
|
"loss": 6.3625,
|
|
"mean_token_accuracy": 0.1306440532207489,
|
|
"num_tokens": 19100347.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 6.616393947601319,
|
|
"epoch": 1.1158911325724319,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004902786258884463,
|
|
"loss": 6.4056,
|
|
"mean_token_accuracy": 0.13444274812936782,
|
|
"num_tokens": 19117379.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 6.642831945419312,
|
|
"epoch": 1.116866647156375,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004902581645170194,
|
|
"loss": 6.3482,
|
|
"mean_token_accuracy": 0.13978055119514465,
|
|
"num_tokens": 19134751.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 6.684342908859253,
|
|
"epoch": 1.117842161740318,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004902376821113319,
|
|
"loss": 6.4028,
|
|
"mean_token_accuracy": 0.13067695498466492,
|
|
"num_tokens": 19150647.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 6.559720897674561,
|
|
"epoch": 1.118817676324261,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004902171786733852,
|
|
"loss": 6.3812,
|
|
"mean_token_accuracy": 0.12842901200056075,
|
|
"num_tokens": 19166654.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 6.624632978439331,
|
|
"epoch": 1.1197931909082042,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004901966542051828,
|
|
"loss": 6.3835,
|
|
"mean_token_accuracy": 0.1331341616809368,
|
|
"num_tokens": 19182787.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 6.631909608840942,
|
|
"epoch": 1.1207687054921471,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004901761087087303,
|
|
"loss": 6.3836,
|
|
"mean_token_accuracy": 0.13309904858469962,
|
|
"num_tokens": 19200218.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 6.682715845108032,
|
|
"epoch": 1.12174422007609,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.0004901555421860354,
|
|
"loss": 6.457,
|
|
"mean_token_accuracy": 0.1308098055422306,
|
|
"num_tokens": 19217310.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 6.716567516326904,
|
|
"epoch": 1.1227197346600333,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004901349546391078,
|
|
"loss": 6.4236,
|
|
"mean_token_accuracy": 0.12677840366959572,
|
|
"num_tokens": 19233293.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 6.575149297714233,
|
|
"epoch": 1.1236952492439762,
|
|
"grad_norm": 0.68359375,
|
|
"learning_rate": 0.0004901143460699592,
|
|
"loss": 6.3101,
|
|
"mean_token_accuracy": 0.14391597360372543,
|
|
"num_tokens": 19250606.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 6.556329154968262,
|
|
"epoch": 1.1246707638279192,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004900937164806033,
|
|
"loss": 6.2791,
|
|
"mean_token_accuracy": 0.14172640591859817,
|
|
"num_tokens": 19267848.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 6.629824781417847,
|
|
"epoch": 1.1256462784118622,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0004900730658730561,
|
|
"loss": 6.3894,
|
|
"mean_token_accuracy": 0.13513770177960396,
|
|
"num_tokens": 19284317.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 6.5947864055633545,
|
|
"epoch": 1.1266217929958053,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004900523942493353,
|
|
"loss": 6.3441,
|
|
"mean_token_accuracy": 0.13602813705801964,
|
|
"num_tokens": 19300766.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 6.6020715713500975,
|
|
"epoch": 1.1275973075797483,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004900317016114611,
|
|
"loss": 6.3374,
|
|
"mean_token_accuracy": 0.13461187109351158,
|
|
"num_tokens": 19316966.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 6.619129276275634,
|
|
"epoch": 1.1285728221636913,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004900109879614554,
|
|
"loss": 6.4208,
|
|
"mean_token_accuracy": 0.13072850778698922,
|
|
"num_tokens": 19334389.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 6.707594394683838,
|
|
"epoch": 1.1295483367476344,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004899902533013423,
|
|
"loss": 6.4447,
|
|
"mean_token_accuracy": 0.1313069298863411,
|
|
"num_tokens": 19350238.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 6.696889781951905,
|
|
"epoch": 1.1305238513315774,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004899694976331478,
|
|
"loss": 6.3802,
|
|
"mean_token_accuracy": 0.12932651340961457,
|
|
"num_tokens": 19367244.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 6.632756853103638,
|
|
"epoch": 1.1314993659155204,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004899487209589001,
|
|
"loss": 6.3823,
|
|
"mean_token_accuracy": 0.1323982857167721,
|
|
"num_tokens": 19384949.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 6.724039888381958,
|
|
"epoch": 1.1324748804994635,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004899279232806297,
|
|
"loss": 6.4707,
|
|
"mean_token_accuracy": 0.12855388969182968,
|
|
"num_tokens": 19402149.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 6.613909006118774,
|
|
"epoch": 1.1334503950834065,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004899071046003686,
|
|
"loss": 6.3536,
|
|
"mean_token_accuracy": 0.13113636001944542,
|
|
"num_tokens": 19419032.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 6.664272737503052,
|
|
"epoch": 1.1344259096673495,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004898862649201511,
|
|
"loss": 6.3958,
|
|
"mean_token_accuracy": 0.13540283665060998,
|
|
"num_tokens": 19435656.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 6.5540718078613285,
|
|
"epoch": 1.1354014242512926,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004898654042420137,
|
|
"loss": 6.3055,
|
|
"mean_token_accuracy": 0.14141770228743553,
|
|
"num_tokens": 19451482.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 6.670750999450684,
|
|
"epoch": 1.1363769388352356,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004898445225679948,
|
|
"loss": 6.4503,
|
|
"mean_token_accuracy": 0.12857600823044776,
|
|
"num_tokens": 19467758.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 6.7150050640106205,
|
|
"epoch": 1.1373524534191786,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004898236199001347,
|
|
"loss": 6.46,
|
|
"mean_token_accuracy": 0.12699505016207696,
|
|
"num_tokens": 19483673.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 6.723792457580567,
|
|
"epoch": 1.1383279680031215,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004898026962404762,
|
|
"loss": 6.4957,
|
|
"mean_token_accuracy": 0.12662889510393144,
|
|
"num_tokens": 19500171.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 6.597092199325561,
|
|
"epoch": 1.1393034825870647,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004897817515910639,
|
|
"loss": 6.3396,
|
|
"mean_token_accuracy": 0.14062442034482955,
|
|
"num_tokens": 19516531.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 6.637167119979859,
|
|
"epoch": 1.1402789971710077,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 0.0004897607859539443,
|
|
"loss": 6.4474,
|
|
"mean_token_accuracy": 0.12786830067634583,
|
|
"num_tokens": 19534289.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 6.501178407669068,
|
|
"epoch": 1.1412545117549509,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000489739799331166,
|
|
"loss": 6.2248,
|
|
"mean_token_accuracy": 0.14179659634828568,
|
|
"num_tokens": 19550190.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 6.547660446166992,
|
|
"epoch": 1.1422300263388938,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00048971879172478,
|
|
"loss": 6.1803,
|
|
"mean_token_accuracy": 0.14779152572155,
|
|
"num_tokens": 19567774.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 6.672373247146607,
|
|
"epoch": 1.1432055409228368,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004896977631368389,
|
|
"loss": 6.4455,
|
|
"mean_token_accuracy": 0.12590477764606475,
|
|
"num_tokens": 19583690.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 6.616320371627808,
|
|
"epoch": 1.1441810555067797,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004896767135693976,
|
|
"loss": 6.3105,
|
|
"mean_token_accuracy": 0.14223466739058493,
|
|
"num_tokens": 19600563.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 6.600705289840699,
|
|
"epoch": 1.145156570090723,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.000489655643024513,
|
|
"loss": 6.361,
|
|
"mean_token_accuracy": 0.13528573215007783,
|
|
"num_tokens": 19618043.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 6.6126306533813475,
|
|
"epoch": 1.1461320846746659,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004896345515042439,
|
|
"loss": 6.4262,
|
|
"mean_token_accuracy": 0.13719907999038697,
|
|
"num_tokens": 19634807.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 6.594249296188354,
|
|
"epoch": 1.1471075992586088,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004896134390106515,
|
|
"loss": 6.2596,
|
|
"mean_token_accuracy": 0.14358468651771544,
|
|
"num_tokens": 19650814.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 6.463556385040283,
|
|
"epoch": 1.148083113842552,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004895923055457987,
|
|
"loss": 6.1996,
|
|
"mean_token_accuracy": 0.15321391299366952,
|
|
"num_tokens": 19666293.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 6.543978071212768,
|
|
"epoch": 1.149058628426495,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004895711511117506,
|
|
"loss": 6.2865,
|
|
"mean_token_accuracy": 0.13918946087360382,
|
|
"num_tokens": 19682549.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 6.63197774887085,
|
|
"epoch": 1.150034143010438,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004895499757105743,
|
|
"loss": 6.4002,
|
|
"mean_token_accuracy": 0.13200041577219962,
|
|
"num_tokens": 19697776.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 6.558183336257935,
|
|
"epoch": 1.1510096575943811,
|
|
"grad_norm": 0.7265625,
|
|
"learning_rate": 0.0004895287793443391,
|
|
"loss": 6.3226,
|
|
"mean_token_accuracy": 0.14139684811234474,
|
|
"num_tokens": 19715219.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 6.5683740139007565,
|
|
"epoch": 1.151985172178324,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004895075620151162,
|
|
"loss": 6.349,
|
|
"mean_token_accuracy": 0.13668934926390647,
|
|
"num_tokens": 19731934.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 6.569689989089966,
|
|
"epoch": 1.152960686762267,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004894863237249789,
|
|
"loss": 6.3495,
|
|
"mean_token_accuracy": 0.14094047397375106,
|
|
"num_tokens": 19748933.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 6.635212469100952,
|
|
"epoch": 1.1539362013462102,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004894650644760024,
|
|
"loss": 6.3845,
|
|
"mean_token_accuracy": 0.13661593869328498,
|
|
"num_tokens": 19765430.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 6.685774326324463,
|
|
"epoch": 1.1549117159301532,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004894437842702642,
|
|
"loss": 6.4335,
|
|
"mean_token_accuracy": 0.13267421275377272,
|
|
"num_tokens": 19783626.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 6.671398448944092,
|
|
"epoch": 1.1558872305140961,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004894224831098437,
|
|
"loss": 6.4184,
|
|
"mean_token_accuracy": 0.1284372940659523,
|
|
"num_tokens": 19800269.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 6.6291906356811525,
|
|
"epoch": 1.156862745098039,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004894011609968224,
|
|
"loss": 6.3729,
|
|
"mean_token_accuracy": 0.13110356554389,
|
|
"num_tokens": 19816837.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 6.701706790924073,
|
|
"epoch": 1.1578382596819823,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004893798179332837,
|
|
"loss": 6.5231,
|
|
"mean_token_accuracy": 0.12532807216048242,
|
|
"num_tokens": 19833029.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 6.589848613739013,
|
|
"epoch": 1.1588137742659252,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004893584539213134,
|
|
"loss": 6.2702,
|
|
"mean_token_accuracy": 0.14492437988519669,
|
|
"num_tokens": 19851600.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 6.621820163726807,
|
|
"epoch": 1.1597892888498684,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004893370689629988,
|
|
"loss": 6.388,
|
|
"mean_token_accuracy": 0.1321663297712803,
|
|
"num_tokens": 19867152.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 6.562496519088745,
|
|
"epoch": 1.1607648034338114,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004893156630604298,
|
|
"loss": 6.2431,
|
|
"mean_token_accuracy": 0.14173942282795907,
|
|
"num_tokens": 19884035.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 6.6429548263549805,
|
|
"epoch": 1.1617403180177543,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.000489294236215698,
|
|
"loss": 6.3661,
|
|
"mean_token_accuracy": 0.13595289885997772,
|
|
"num_tokens": 19899186.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 6.635700511932373,
|
|
"epoch": 1.1627158326016973,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004892727884308972,
|
|
"loss": 6.3829,
|
|
"mean_token_accuracy": 0.13369623348116874,
|
|
"num_tokens": 19914162.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 6.618590497970581,
|
|
"epoch": 1.1636913471856405,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004892513197081233,
|
|
"loss": 6.3488,
|
|
"mean_token_accuracy": 0.1281696803867817,
|
|
"num_tokens": 19931758.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 6.6221672058105465,
|
|
"epoch": 1.1646668617695835,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.000489229830049474,
|
|
"loss": 6.4189,
|
|
"mean_token_accuracy": 0.13361834362149239,
|
|
"num_tokens": 19949397.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 6.578804302215576,
|
|
"epoch": 1.1656423763535264,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0004892083194570492,
|
|
"loss": 6.3284,
|
|
"mean_token_accuracy": 0.13478664979338645,
|
|
"num_tokens": 19967356.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 6.626962375640869,
|
|
"epoch": 1.1666178909374696,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004891867879329509,
|
|
"loss": 6.2753,
|
|
"mean_token_accuracy": 0.14181281626224518,
|
|
"num_tokens": 19984343.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 6.685523223876953,
|
|
"epoch": 1.1675934055214126,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004891652354792831,
|
|
"loss": 6.4475,
|
|
"mean_token_accuracy": 0.13213640004396437,
|
|
"num_tokens": 20001600.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 6.594034481048584,
|
|
"epoch": 1.1685689201053555,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004891436620981517,
|
|
"loss": 6.3835,
|
|
"mean_token_accuracy": 0.13011895418167113,
|
|
"num_tokens": 20016816.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 6.684434700012207,
|
|
"epoch": 1.1695444346892987,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004891220677916649,
|
|
"loss": 6.3983,
|
|
"mean_token_accuracy": 0.13212305828928947,
|
|
"num_tokens": 20033754.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 6.542210102081299,
|
|
"epoch": 1.1705199492732417,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004891004525619327,
|
|
"loss": 6.3269,
|
|
"mean_token_accuracy": 0.1427649289369583,
|
|
"num_tokens": 20051899.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 1.1705199492732417,
|
|
"eval_entropy": 6.405090353883411,
|
|
"eval_loss": 6.446770668029785,
|
|
"eval_mean_token_accuracy": 0.1353223039276693,
|
|
"eval_num_tokens": 20051899.0,
|
|
"eval_runtime": 12.0232,
|
|
"eval_samples_per_second": 1378.756,
|
|
"eval_steps_per_second": 172.417,
|
|
"step": 6000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 51250,
|
|
"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": 4008127880724480.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|