d844975093
Model: fpadovani/zho-hans-100mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.585308750365818,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 8.189694690704346,
|
|
"epoch": 0.0009755145839430299,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 2e-06,
|
|
"loss": 8.1213,
|
|
"mean_token_accuracy": 0.0928520105779171,
|
|
"num_tokens": 17120.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 8.088421869277955,
|
|
"epoch": 0.0019510291678860598,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 8.0338,
|
|
"mean_token_accuracy": 0.09805552884936333,
|
|
"num_tokens": 34182.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 8.10444598197937,
|
|
"epoch": 0.0029265437518290896,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 7e-06,
|
|
"loss": 8.0761,
|
|
"mean_token_accuracy": 0.0990721695125103,
|
|
"num_tokens": 51205.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 8.136365795135498,
|
|
"epoch": 0.0039020583357721197,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 8.1057,
|
|
"mean_token_accuracy": 0.09148216098546982,
|
|
"num_tokens": 67722.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 8.127794647216797,
|
|
"epoch": 0.00487757291971515,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 8.1015,
|
|
"mean_token_accuracy": 0.09162097275257111,
|
|
"num_tokens": 84230.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 8.140947341918945,
|
|
"epoch": 0.005853087503658179,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 8.0101,
|
|
"mean_token_accuracy": 0.10145255476236344,
|
|
"num_tokens": 100967.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 8.193094825744629,
|
|
"epoch": 0.00682860208760121,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 8.0798,
|
|
"mean_token_accuracy": 0.09109266102313995,
|
|
"num_tokens": 117450.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 8.167135286331177,
|
|
"epoch": 0.007804116671544239,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 7.9719,
|
|
"mean_token_accuracy": 0.10474523082375527,
|
|
"num_tokens": 135328.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 8.237839794158935,
|
|
"epoch": 0.00877963125548727,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 8.0049,
|
|
"mean_token_accuracy": 0.09647766500711441,
|
|
"num_tokens": 152571.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 8.21173391342163,
|
|
"epoch": 0.0097551458394303,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 7.987,
|
|
"mean_token_accuracy": 0.09857306927442551,
|
|
"num_tokens": 170216.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 8.188056182861327,
|
|
"epoch": 0.010730660423373329,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 8.0418,
|
|
"mean_token_accuracy": 0.09847658723592759,
|
|
"num_tokens": 186513.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 8.209293651580811,
|
|
"epoch": 0.011706175007316359,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 8.0308,
|
|
"mean_token_accuracy": 0.09393074885010719,
|
|
"num_tokens": 202600.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 8.16935420036316,
|
|
"epoch": 0.01268168959125939,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 7.9625,
|
|
"mean_token_accuracy": 0.10780214741826058,
|
|
"num_tokens": 220270.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 8.189718246459961,
|
|
"epoch": 0.01365720417520242,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 7.9753,
|
|
"mean_token_accuracy": 0.10615965947508813,
|
|
"num_tokens": 236810.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 8.23555679321289,
|
|
"epoch": 0.014632718759145449,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 8.0265,
|
|
"mean_token_accuracy": 0.09320793077349662,
|
|
"num_tokens": 252559.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 8.191197776794434,
|
|
"epoch": 0.015608233343088479,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 7.9595,
|
|
"mean_token_accuracy": 0.10167472660541535,
|
|
"num_tokens": 268507.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 8.220345592498779,
|
|
"epoch": 0.01658374792703151,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 7.9799,
|
|
"mean_token_accuracy": 0.09989922642707824,
|
|
"num_tokens": 284776.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 8.225536727905274,
|
|
"epoch": 0.01755926251097454,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 8.0477,
|
|
"mean_token_accuracy": 0.09435278922319412,
|
|
"num_tokens": 300937.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 8.22456979751587,
|
|
"epoch": 0.01853477709491757,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.0291,
|
|
"mean_token_accuracy": 0.09500815868377685,
|
|
"num_tokens": 317464.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 8.196868324279786,
|
|
"epoch": 0.0195102916788606,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 7.9297,
|
|
"mean_token_accuracy": 0.10513664558529853,
|
|
"num_tokens": 334022.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 8.174358654022218,
|
|
"epoch": 0.02048580626280363,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.012,
|
|
"mean_token_accuracy": 0.09847316145896912,
|
|
"num_tokens": 350545.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 8.142373085021973,
|
|
"epoch": 0.021461320846746658,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 7.8485,
|
|
"mean_token_accuracy": 0.11419763416051865,
|
|
"num_tokens": 368878.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 8.165599918365478,
|
|
"epoch": 0.022436835430689687,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.0301,
|
|
"mean_token_accuracy": 0.09600666835904122,
|
|
"num_tokens": 388381.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 8.214081382751464,
|
|
"epoch": 0.023412350014632717,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.048,
|
|
"mean_token_accuracy": 0.09097032994031906,
|
|
"num_tokens": 403727.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 8.2991042137146,
|
|
"epoch": 0.02438786459857575,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.0491,
|
|
"mean_token_accuracy": 0.0942738875746727,
|
|
"num_tokens": 419046.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 8.182039546966553,
|
|
"epoch": 0.02536337918251878,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.9433,
|
|
"mean_token_accuracy": 0.10728831514716149,
|
|
"num_tokens": 435186.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 8.232324981689453,
|
|
"epoch": 0.02633889376646181,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.0395,
|
|
"mean_token_accuracy": 0.09328199326992034,
|
|
"num_tokens": 451552.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 8.199801969528199,
|
|
"epoch": 0.02731440835040484,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.0061,
|
|
"mean_token_accuracy": 0.09671647101640701,
|
|
"num_tokens": 468006.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 8.274113845825195,
|
|
"epoch": 0.02828992293434787,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.0112,
|
|
"mean_token_accuracy": 0.09868691936135292,
|
|
"num_tokens": 484381.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.25528917312622,
|
|
"epoch": 0.029265437518290898,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.0257,
|
|
"mean_token_accuracy": 0.0955542728304863,
|
|
"num_tokens": 501309.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.226487350463866,
|
|
"epoch": 0.030240952102233928,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.9828,
|
|
"mean_token_accuracy": 0.09746505990624428,
|
|
"num_tokens": 518290.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.181639671325684,
|
|
"epoch": 0.031216466686176957,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.9965,
|
|
"mean_token_accuracy": 0.09464227110147476,
|
|
"num_tokens": 533700.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.192685508728028,
|
|
"epoch": 0.03219198127011999,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.8837,
|
|
"mean_token_accuracy": 0.10680020377039909,
|
|
"num_tokens": 548935.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.122217988967895,
|
|
"epoch": 0.03316749585406302,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.9809,
|
|
"mean_token_accuracy": 0.09729720130562783,
|
|
"num_tokens": 565869.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.255708599090577,
|
|
"epoch": 0.03414301043800605,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.9426,
|
|
"mean_token_accuracy": 0.10057656094431877,
|
|
"num_tokens": 583065.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.147002172470092,
|
|
"epoch": 0.03511852502194908,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.9597,
|
|
"mean_token_accuracy": 0.10024290233850479,
|
|
"num_tokens": 599875.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.198067951202393,
|
|
"epoch": 0.03609403960589211,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.9192,
|
|
"mean_token_accuracy": 0.1043715499341488,
|
|
"num_tokens": 616296.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.178347730636597,
|
|
"epoch": 0.03706955418983514,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.8936,
|
|
"mean_token_accuracy": 0.0991103172302246,
|
|
"num_tokens": 632548.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.182952737808227,
|
|
"epoch": 0.03804506877377817,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.9026,
|
|
"mean_token_accuracy": 0.10161520764231682,
|
|
"num_tokens": 650395.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.191309070587158,
|
|
"epoch": 0.0390205833577212,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.9511,
|
|
"mean_token_accuracy": 0.10279864966869354,
|
|
"num_tokens": 668453.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.106355381011962,
|
|
"epoch": 0.03999609794166423,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.822,
|
|
"mean_token_accuracy": 0.11003539934754372,
|
|
"num_tokens": 683914.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.108619880676269,
|
|
"epoch": 0.04097161252560726,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.9833,
|
|
"mean_token_accuracy": 0.09929522946476936,
|
|
"num_tokens": 700480.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.311169815063476,
|
|
"epoch": 0.041947127109550286,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.9705,
|
|
"mean_token_accuracy": 0.0956616073846817,
|
|
"num_tokens": 716604.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.151149940490722,
|
|
"epoch": 0.042922641693493316,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.9283,
|
|
"mean_token_accuracy": 0.09996144995093345,
|
|
"num_tokens": 732697.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.261075973510742,
|
|
"epoch": 0.043898156277436345,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 8.0403,
|
|
"mean_token_accuracy": 0.09186563193798065,
|
|
"num_tokens": 749072.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.180721092224122,
|
|
"epoch": 0.044873670861379375,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.9417,
|
|
"mean_token_accuracy": 0.09489826485514641,
|
|
"num_tokens": 767826.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.116961860656739,
|
|
"epoch": 0.045849185445322405,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.8815,
|
|
"mean_token_accuracy": 0.101999169588089,
|
|
"num_tokens": 786863.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.151587963104248,
|
|
"epoch": 0.046824700029265434,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.8594,
|
|
"mean_token_accuracy": 0.11106476187705994,
|
|
"num_tokens": 803925.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.16553840637207,
|
|
"epoch": 0.04780021461320847,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.9056,
|
|
"mean_token_accuracy": 0.09941518381237983,
|
|
"num_tokens": 822088.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.204985809326171,
|
|
"epoch": 0.0487757291971515,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.9578,
|
|
"mean_token_accuracy": 0.09502575322985649,
|
|
"num_tokens": 837991.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.094996738433839,
|
|
"epoch": 0.04975124378109453,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.8384,
|
|
"mean_token_accuracy": 0.11150547713041306,
|
|
"num_tokens": 855593.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.22648229598999,
|
|
"epoch": 0.05072675836503756,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.8555,
|
|
"mean_token_accuracy": 0.1016038067638874,
|
|
"num_tokens": 873696.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.093446922302245,
|
|
"epoch": 0.05170227294898059,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.7945,
|
|
"mean_token_accuracy": 0.1079544596374035,
|
|
"num_tokens": 890023.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.219519519805909,
|
|
"epoch": 0.05267778753292362,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 8.0193,
|
|
"mean_token_accuracy": 0.09408034533262252,
|
|
"num_tokens": 906492.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.144463109970093,
|
|
"epoch": 0.05365330211686665,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.8985,
|
|
"mean_token_accuracy": 0.09895867183804512,
|
|
"num_tokens": 921837.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.176286315917968,
|
|
"epoch": 0.05462881670080968,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.797,
|
|
"mean_token_accuracy": 0.10809003040194512,
|
|
"num_tokens": 938771.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.145763206481934,
|
|
"epoch": 0.05560433128475271,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.9095,
|
|
"mean_token_accuracy": 0.09854145273566246,
|
|
"num_tokens": 954562.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.14554295539856,
|
|
"epoch": 0.05657984586869574,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.8002,
|
|
"mean_token_accuracy": 0.10630740001797676,
|
|
"num_tokens": 973700.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.05322551727295,
|
|
"epoch": 0.05755536045263877,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.9073,
|
|
"mean_token_accuracy": 0.09839207902550698,
|
|
"num_tokens": 990688.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.224873065948486,
|
|
"epoch": 0.058530875036581796,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 8.0062,
|
|
"mean_token_accuracy": 0.09405675381422043,
|
|
"num_tokens": 1008144.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.18083577156067,
|
|
"epoch": 0.059506389620524826,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.9383,
|
|
"mean_token_accuracy": 0.09709960296750068,
|
|
"num_tokens": 1027379.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.178252029418946,
|
|
"epoch": 0.060481904204467855,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.8793,
|
|
"mean_token_accuracy": 0.10311919152736664,
|
|
"num_tokens": 1043999.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.098154592514039,
|
|
"epoch": 0.061457418788410885,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.9274,
|
|
"mean_token_accuracy": 0.09602248296141624,
|
|
"num_tokens": 1062237.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.244752025604248,
|
|
"epoch": 0.062432933372353915,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.8576,
|
|
"mean_token_accuracy": 0.10373107567429543,
|
|
"num_tokens": 1078092.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.097948360443116,
|
|
"epoch": 0.06340844795629695,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.8987,
|
|
"mean_token_accuracy": 0.10294966548681259,
|
|
"num_tokens": 1095124.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.17255973815918,
|
|
"epoch": 0.06438396254023998,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.8855,
|
|
"mean_token_accuracy": 0.09729674383997917,
|
|
"num_tokens": 1112775.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.077517557144166,
|
|
"epoch": 0.06535947712418301,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.7933,
|
|
"mean_token_accuracy": 0.10203502476215362,
|
|
"num_tokens": 1129726.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.185189342498779,
|
|
"epoch": 0.06633499170812604,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.8883,
|
|
"mean_token_accuracy": 0.10449600592255592,
|
|
"num_tokens": 1144034.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.129604816436768,
|
|
"epoch": 0.06731050629206907,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.8179,
|
|
"mean_token_accuracy": 0.10270989686250687,
|
|
"num_tokens": 1159633.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.0196063041687,
|
|
"epoch": 0.0682860208760121,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.8085,
|
|
"mean_token_accuracy": 0.0996285319328308,
|
|
"num_tokens": 1175350.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.027859020233155,
|
|
"epoch": 0.06926153545995513,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.7379,
|
|
"mean_token_accuracy": 0.10451692193746567,
|
|
"num_tokens": 1193121.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.143134546279907,
|
|
"epoch": 0.07023705004389816,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.8633,
|
|
"mean_token_accuracy": 0.09846432060003281,
|
|
"num_tokens": 1209896.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.091192197799682,
|
|
"epoch": 0.07121256462784119,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.8953,
|
|
"mean_token_accuracy": 0.09844174087047577,
|
|
"num_tokens": 1227011.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.028723001480103,
|
|
"epoch": 0.07218807921178422,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.7943,
|
|
"mean_token_accuracy": 0.09941637516021729,
|
|
"num_tokens": 1241595.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 8.113645601272584,
|
|
"epoch": 0.07316359379572725,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.8044,
|
|
"mean_token_accuracy": 0.09797000885009766,
|
|
"num_tokens": 1256919.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.04976544380188,
|
|
"epoch": 0.07413910837967028,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.7862,
|
|
"mean_token_accuracy": 0.1137398436665535,
|
|
"num_tokens": 1274344.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 8.014974355697632,
|
|
"epoch": 0.0751146229636133,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.7822,
|
|
"mean_token_accuracy": 0.10938268229365349,
|
|
"num_tokens": 1290252.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.139637756347657,
|
|
"epoch": 0.07609013754755634,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.835,
|
|
"mean_token_accuracy": 0.09761641547083855,
|
|
"num_tokens": 1306987.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 8.127484035491943,
|
|
"epoch": 0.07706565213149937,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.8599,
|
|
"mean_token_accuracy": 0.09425433501601219,
|
|
"num_tokens": 1323031.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 8.023318195343018,
|
|
"epoch": 0.0780411667154424,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.8194,
|
|
"mean_token_accuracy": 0.09804570376873016,
|
|
"num_tokens": 1339592.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.08116374015808,
|
|
"epoch": 0.07901668129938542,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.7704,
|
|
"mean_token_accuracy": 0.10749435946345329,
|
|
"num_tokens": 1358131.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 8.001975107192994,
|
|
"epoch": 0.07999219588332845,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.6943,
|
|
"mean_token_accuracy": 0.11095809042453766,
|
|
"num_tokens": 1375705.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.946876573562622,
|
|
"epoch": 0.08096771046727148,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.7367,
|
|
"mean_token_accuracy": 0.10697664991021157,
|
|
"num_tokens": 1392736.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 8.051513481140137,
|
|
"epoch": 0.08194322505121451,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.7993,
|
|
"mean_token_accuracy": 0.10061158984899521,
|
|
"num_tokens": 1408536.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.932209205627442,
|
|
"epoch": 0.08291873963515754,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.7882,
|
|
"mean_token_accuracy": 0.10027184262871743,
|
|
"num_tokens": 1425423.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 8.056283235549927,
|
|
"epoch": 0.08389425421910057,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.7772,
|
|
"mean_token_accuracy": 0.10296398922801017,
|
|
"num_tokens": 1442420.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 8.07236189842224,
|
|
"epoch": 0.0848697688030436,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.7303,
|
|
"mean_token_accuracy": 0.10705514326691627,
|
|
"num_tokens": 1458835.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 8.004169511795045,
|
|
"epoch": 0.08584528338698663,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.8228,
|
|
"mean_token_accuracy": 0.09661487340927125,
|
|
"num_tokens": 1475563.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 8.09420862197876,
|
|
"epoch": 0.08682079797092966,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.7797,
|
|
"mean_token_accuracy": 0.10943613573908806,
|
|
"num_tokens": 1492687.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 8.086115980148316,
|
|
"epoch": 0.08779631255487269,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.7887,
|
|
"mean_token_accuracy": 0.097627442330122,
|
|
"num_tokens": 1508394.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.934510850906372,
|
|
"epoch": 0.08877182713881572,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.754,
|
|
"mean_token_accuracy": 0.10472490787506103,
|
|
"num_tokens": 1527112.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 8.001490831375122,
|
|
"epoch": 0.08974734172275875,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.798,
|
|
"mean_token_accuracy": 0.10435827821493149,
|
|
"num_tokens": 1545401.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.947861576080323,
|
|
"epoch": 0.09072285630670178,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.6915,
|
|
"mean_token_accuracy": 0.10466418415307999,
|
|
"num_tokens": 1561621.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 8.044413089752197,
|
|
"epoch": 0.09169837089064481,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.8059,
|
|
"mean_token_accuracy": 0.09883959665894508,
|
|
"num_tokens": 1579225.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 8.022387886047364,
|
|
"epoch": 0.09267388547458784,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.7096,
|
|
"mean_token_accuracy": 0.10403750389814377,
|
|
"num_tokens": 1596125.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.9631647109985355,
|
|
"epoch": 0.09364940005853087,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.8258,
|
|
"mean_token_accuracy": 0.0952387198805809,
|
|
"num_tokens": 1613451.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 8.017077445983887,
|
|
"epoch": 0.09462491464247391,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.803,
|
|
"mean_token_accuracy": 0.09880654960870743,
|
|
"num_tokens": 1630929.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 8.025622653961182,
|
|
"epoch": 0.09560042922641694,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.7924,
|
|
"mean_token_accuracy": 0.10142078548669815,
|
|
"num_tokens": 1647379.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.718832302093506,
|
|
"epoch": 0.09657594381035997,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.5342,
|
|
"mean_token_accuracy": 0.12226327732205391,
|
|
"num_tokens": 1664415.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.8884869575500485,
|
|
"epoch": 0.097551458394303,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.653,
|
|
"mean_token_accuracy": 0.10562271177768708,
|
|
"num_tokens": 1679556.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.949688959121704,
|
|
"epoch": 0.09852697297824603,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.6052,
|
|
"mean_token_accuracy": 0.11016268655657768,
|
|
"num_tokens": 1696727.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.83725757598877,
|
|
"epoch": 0.09950248756218906,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.6089,
|
|
"mean_token_accuracy": 0.11472497954964637,
|
|
"num_tokens": 1713918.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.953091287612915,
|
|
"epoch": 0.10047800214613209,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.7951,
|
|
"mean_token_accuracy": 0.0945059321820736,
|
|
"num_tokens": 1729581.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.921047019958496,
|
|
"epoch": 0.10145351673007512,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.6469,
|
|
"mean_token_accuracy": 0.0992059625685215,
|
|
"num_tokens": 1746367.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.967546033859253,
|
|
"epoch": 0.10242903131401815,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.7465,
|
|
"mean_token_accuracy": 0.09730863869190216,
|
|
"num_tokens": 1765009.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.927223825454712,
|
|
"epoch": 0.10340454589796118,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.7539,
|
|
"mean_token_accuracy": 0.09873774722218513,
|
|
"num_tokens": 1782113.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.883999395370483,
|
|
"epoch": 0.10438006048190421,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.6519,
|
|
"mean_token_accuracy": 0.10443588495254516,
|
|
"num_tokens": 1798301.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.911849689483643,
|
|
"epoch": 0.10535557506584724,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.6931,
|
|
"mean_token_accuracy": 0.10224330425262451,
|
|
"num_tokens": 1815059.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.769307279586792,
|
|
"epoch": 0.10633108964979027,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.6051,
|
|
"mean_token_accuracy": 0.10878376364707946,
|
|
"num_tokens": 1831699.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.925337314605713,
|
|
"epoch": 0.1073066042337333,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.6755,
|
|
"mean_token_accuracy": 0.10547427088022232,
|
|
"num_tokens": 1847993.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.875313425064087,
|
|
"epoch": 0.10828211881767633,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.5326,
|
|
"mean_token_accuracy": 0.10610557869076728,
|
|
"num_tokens": 1864753.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.869585037231445,
|
|
"epoch": 0.10925763340161936,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.6888,
|
|
"mean_token_accuracy": 0.1044863447546959,
|
|
"num_tokens": 1882154.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.754839944839477,
|
|
"epoch": 0.11023314798556239,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.5623,
|
|
"mean_token_accuracy": 0.11065352857112884,
|
|
"num_tokens": 1899683.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.821217679977417,
|
|
"epoch": 0.11120866256950541,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.5912,
|
|
"mean_token_accuracy": 0.10635183900594711,
|
|
"num_tokens": 1918489.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.833246660232544,
|
|
"epoch": 0.11218417715344844,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.6345,
|
|
"mean_token_accuracy": 0.10072939395904541,
|
|
"num_tokens": 1935609.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.7502540111541744,
|
|
"epoch": 0.11315969173739147,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.6882,
|
|
"mean_token_accuracy": 0.09968181252479554,
|
|
"num_tokens": 1951311.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.9223309516906735,
|
|
"epoch": 0.1141352063213345,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.7251,
|
|
"mean_token_accuracy": 0.09712948650121689,
|
|
"num_tokens": 1968908.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.88884711265564,
|
|
"epoch": 0.11511072090527753,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.6394,
|
|
"mean_token_accuracy": 0.10047843605279923,
|
|
"num_tokens": 1983807.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.878595304489136,
|
|
"epoch": 0.11608623548922056,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.6755,
|
|
"mean_token_accuracy": 0.1005166418850422,
|
|
"num_tokens": 2000219.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.826176500320434,
|
|
"epoch": 0.11706175007316359,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.6359,
|
|
"mean_token_accuracy": 0.10865101143717766,
|
|
"num_tokens": 2017360.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.724283885955811,
|
|
"epoch": 0.11803726465710662,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.6093,
|
|
"mean_token_accuracy": 0.10661007612943649,
|
|
"num_tokens": 2034953.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.793875885009766,
|
|
"epoch": 0.11901277924104965,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.5775,
|
|
"mean_token_accuracy": 0.10660225003957749,
|
|
"num_tokens": 2051551.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.78004674911499,
|
|
"epoch": 0.11998829382499268,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.5478,
|
|
"mean_token_accuracy": 0.11335186585783959,
|
|
"num_tokens": 2067188.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.790237903594971,
|
|
"epoch": 0.12096380840893571,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.6232,
|
|
"mean_token_accuracy": 0.10700822845101357,
|
|
"num_tokens": 2082569.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.847408294677734,
|
|
"epoch": 0.12193932299287874,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.6786,
|
|
"mean_token_accuracy": 0.10037213563919067,
|
|
"num_tokens": 2099446.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.824612283706665,
|
|
"epoch": 0.12291483757682177,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.6309,
|
|
"mean_token_accuracy": 0.10579207465052605,
|
|
"num_tokens": 2116526.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.7642529010772705,
|
|
"epoch": 0.1238903521607648,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.6948,
|
|
"mean_token_accuracy": 0.09671583101153373,
|
|
"num_tokens": 2134624.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.721237707138061,
|
|
"epoch": 0.12486586674470783,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.5155,
|
|
"mean_token_accuracy": 0.11177115440368653,
|
|
"num_tokens": 2152872.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.853572702407837,
|
|
"epoch": 0.12584138132865086,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.6533,
|
|
"mean_token_accuracy": 0.10234769731760025,
|
|
"num_tokens": 2169480.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.71003680229187,
|
|
"epoch": 0.1268168959125939,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.51,
|
|
"mean_token_accuracy": 0.11612471118569374,
|
|
"num_tokens": 2186054.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.783114385604859,
|
|
"epoch": 0.12779241049653692,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.6688,
|
|
"mean_token_accuracy": 0.09879108145833015,
|
|
"num_tokens": 2202320.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.6497093677520756,
|
|
"epoch": 0.12876792508047996,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.5481,
|
|
"mean_token_accuracy": 0.1086566023528576,
|
|
"num_tokens": 2218817.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.880639505386353,
|
|
"epoch": 0.12974343966442298,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.7054,
|
|
"mean_token_accuracy": 0.09768114015460014,
|
|
"num_tokens": 2234845.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.780311632156372,
|
|
"epoch": 0.13071895424836602,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.6545,
|
|
"mean_token_accuracy": 0.10292254686355591,
|
|
"num_tokens": 2251904.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.706472587585449,
|
|
"epoch": 0.13169446883230904,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.6584,
|
|
"mean_token_accuracy": 0.10477369427680969,
|
|
"num_tokens": 2268343.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.830237913131714,
|
|
"epoch": 0.13266998341625208,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.651,
|
|
"mean_token_accuracy": 0.10206437036395073,
|
|
"num_tokens": 2284524.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.651451110839844,
|
|
"epoch": 0.1336454980001951,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.5627,
|
|
"mean_token_accuracy": 0.11217835396528245,
|
|
"num_tokens": 2302350.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.810202407836914,
|
|
"epoch": 0.13462101258413814,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.6484,
|
|
"mean_token_accuracy": 0.10006091371178627,
|
|
"num_tokens": 2319953.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.6707275867462155,
|
|
"epoch": 0.13559652716808115,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.5379,
|
|
"mean_token_accuracy": 0.11016602963209152,
|
|
"num_tokens": 2336698.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.65397081375122,
|
|
"epoch": 0.1365720417520242,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.5069,
|
|
"mean_token_accuracy": 0.11032541692256928,
|
|
"num_tokens": 2353986.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.720977354049682,
|
|
"epoch": 0.1375475563359672,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.5481,
|
|
"mean_token_accuracy": 0.10689252316951751,
|
|
"num_tokens": 2370320.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.749428844451904,
|
|
"epoch": 0.13852307091991026,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.6172,
|
|
"mean_token_accuracy": 0.10306816101074219,
|
|
"num_tokens": 2385453.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.7098816394805905,
|
|
"epoch": 0.13949858550385327,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.5977,
|
|
"mean_token_accuracy": 0.10320264920592308,
|
|
"num_tokens": 2401545.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.686821317672729,
|
|
"epoch": 0.14047410008779632,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.6155,
|
|
"mean_token_accuracy": 0.10371157601475715,
|
|
"num_tokens": 2418414.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.748217391967773,
|
|
"epoch": 0.14144961467173933,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.6492,
|
|
"mean_token_accuracy": 0.10145975425839424,
|
|
"num_tokens": 2434973.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.769000911712647,
|
|
"epoch": 0.14242512925568238,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.6624,
|
|
"mean_token_accuracy": 0.09807511419057846,
|
|
"num_tokens": 2451053.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.700602865219116,
|
|
"epoch": 0.1434006438396254,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.616,
|
|
"mean_token_accuracy": 0.09884371384978294,
|
|
"num_tokens": 2467280.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.650289630889892,
|
|
"epoch": 0.14437615842356843,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.5466,
|
|
"mean_token_accuracy": 0.11135434210300446,
|
|
"num_tokens": 2484588.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.705961132049561,
|
|
"epoch": 0.14535167300751145,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.5657,
|
|
"mean_token_accuracy": 0.10915652140974999,
|
|
"num_tokens": 2501200.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.66199746131897,
|
|
"epoch": 0.1463271875914545,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.5078,
|
|
"mean_token_accuracy": 0.11285350546240806,
|
|
"num_tokens": 2517199.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.6683488368988035,
|
|
"epoch": 0.1473027021753975,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.5928,
|
|
"mean_token_accuracy": 0.09981210231781006,
|
|
"num_tokens": 2534824.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.523636436462402,
|
|
"epoch": 0.14827821675934055,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.4851,
|
|
"mean_token_accuracy": 0.11066361516714096,
|
|
"num_tokens": 2550842.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.629826021194458,
|
|
"epoch": 0.14925373134328357,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.4176,
|
|
"mean_token_accuracy": 0.11151769161224365,
|
|
"num_tokens": 2567878.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.6675316333770756,
|
|
"epoch": 0.1502292459272266,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.5154,
|
|
"mean_token_accuracy": 0.10651935636997223,
|
|
"num_tokens": 2584148.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.593663120269776,
|
|
"epoch": 0.15120476051116966,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.556,
|
|
"mean_token_accuracy": 0.10755399614572525,
|
|
"num_tokens": 2600067.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.689086866378784,
|
|
"epoch": 0.15218027509511267,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.5272,
|
|
"mean_token_accuracy": 0.10445193201303482,
|
|
"num_tokens": 2615746.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.613615942001343,
|
|
"epoch": 0.15315578967905571,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.5604,
|
|
"mean_token_accuracy": 0.10300727486610413,
|
|
"num_tokens": 2631641.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.590198183059693,
|
|
"epoch": 0.15413130426299873,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.5502,
|
|
"mean_token_accuracy": 0.10660960003733636,
|
|
"num_tokens": 2647015.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.6192991733551025,
|
|
"epoch": 0.15510681884694177,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.4552,
|
|
"mean_token_accuracy": 0.10671902745962143,
|
|
"num_tokens": 2664045.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.630334043502808,
|
|
"epoch": 0.1560823334308848,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.4689,
|
|
"mean_token_accuracy": 0.10270929858088493,
|
|
"num_tokens": 2680774.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.6249841213226315,
|
|
"epoch": 0.15705784801482783,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.593,
|
|
"mean_token_accuracy": 0.10395026803016663,
|
|
"num_tokens": 2697719.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.620457458496094,
|
|
"epoch": 0.15803336259877085,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.5247,
|
|
"mean_token_accuracy": 0.09749212935566902,
|
|
"num_tokens": 2714518.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.627707242965698,
|
|
"epoch": 0.1590088771827139,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.5828,
|
|
"mean_token_accuracy": 0.10642224773764611,
|
|
"num_tokens": 2729288.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.668026733398437,
|
|
"epoch": 0.1599843917666569,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.558,
|
|
"mean_token_accuracy": 0.1009812332689762,
|
|
"num_tokens": 2746782.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.59692063331604,
|
|
"epoch": 0.16095990635059995,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.606,
|
|
"mean_token_accuracy": 0.09608046188950539,
|
|
"num_tokens": 2763159.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.587530517578125,
|
|
"epoch": 0.16193542093454297,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.5677,
|
|
"mean_token_accuracy": 0.10232978016138077,
|
|
"num_tokens": 2780338.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.5702805519104,
|
|
"epoch": 0.162910935518486,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.4619,
|
|
"mean_token_accuracy": 0.1076440267264843,
|
|
"num_tokens": 2796214.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.637975788116455,
|
|
"epoch": 0.16388645010242903,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.584,
|
|
"mean_token_accuracy": 0.09872226789593697,
|
|
"num_tokens": 2812745.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.524194765090942,
|
|
"epoch": 0.16486196468637207,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.4454,
|
|
"mean_token_accuracy": 0.10416454449295998,
|
|
"num_tokens": 2828288.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.608716773986816,
|
|
"epoch": 0.16583747927031509,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.5874,
|
|
"mean_token_accuracy": 0.0974365383386612,
|
|
"num_tokens": 2843618.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.5106102466583256,
|
|
"epoch": 0.16681299385425813,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.3893,
|
|
"mean_token_accuracy": 0.10364697575569153,
|
|
"num_tokens": 2860659.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.55679759979248,
|
|
"epoch": 0.16778850843820114,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.4876,
|
|
"mean_token_accuracy": 0.10175744146108627,
|
|
"num_tokens": 2877482.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.586041831970215,
|
|
"epoch": 0.1687640230221442,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.5667,
|
|
"mean_token_accuracy": 0.09685270413756371,
|
|
"num_tokens": 2895868.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.574951267242431,
|
|
"epoch": 0.1697395376060872,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.5706,
|
|
"mean_token_accuracy": 0.10406396687030792,
|
|
"num_tokens": 2913103.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.5868103981018065,
|
|
"epoch": 0.17071505219003025,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.4942,
|
|
"mean_token_accuracy": 0.10660254284739494,
|
|
"num_tokens": 2928291.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.551671886444092,
|
|
"epoch": 0.17169056677397326,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.5347,
|
|
"mean_token_accuracy": 0.10479419305920601,
|
|
"num_tokens": 2945115.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.54897518157959,
|
|
"epoch": 0.1726660813579163,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.4282,
|
|
"mean_token_accuracy": 0.10494303852319717,
|
|
"num_tokens": 2962869.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.5557914733886715,
|
|
"epoch": 0.17364159594185932,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.5715,
|
|
"mean_token_accuracy": 0.09901110231876373,
|
|
"num_tokens": 2979298.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.518081378936768,
|
|
"epoch": 0.17461711052580237,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.4595,
|
|
"mean_token_accuracy": 0.10685873478651046,
|
|
"num_tokens": 2996146.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.518190670013428,
|
|
"epoch": 0.17559262510974538,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.5431,
|
|
"mean_token_accuracy": 0.10059425905346871,
|
|
"num_tokens": 3013075.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.553641653060913,
|
|
"epoch": 0.17656813969368843,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.4995,
|
|
"mean_token_accuracy": 0.10074936151504517,
|
|
"num_tokens": 3029494.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.493304920196533,
|
|
"epoch": 0.17754365427763144,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.5081,
|
|
"mean_token_accuracy": 0.10531372874975205,
|
|
"num_tokens": 3046333.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.5904456615448,
|
|
"epoch": 0.17851916886157448,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.4867,
|
|
"mean_token_accuracy": 0.10380415394902229,
|
|
"num_tokens": 3062714.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.521370792388916,
|
|
"epoch": 0.1794946834455175,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.4754,
|
|
"mean_token_accuracy": 0.10096871256828308,
|
|
"num_tokens": 3080711.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.505842781066894,
|
|
"epoch": 0.18047019802946054,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.5654,
|
|
"mean_token_accuracy": 0.09803933352231979,
|
|
"num_tokens": 3096885.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.509501171112061,
|
|
"epoch": 0.18144571261340356,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.4553,
|
|
"mean_token_accuracy": 0.10695251300930977,
|
|
"num_tokens": 3114536.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.500088119506836,
|
|
"epoch": 0.1824212271973466,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.4054,
|
|
"mean_token_accuracy": 0.11017186567187309,
|
|
"num_tokens": 3131921.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.524385738372803,
|
|
"epoch": 0.18339674178128962,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.5662,
|
|
"mean_token_accuracy": 0.09947125390172004,
|
|
"num_tokens": 3148064.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.416093254089356,
|
|
"epoch": 0.18437225636523266,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.3813,
|
|
"mean_token_accuracy": 0.11295887902379036,
|
|
"num_tokens": 3165822.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.466145849227905,
|
|
"epoch": 0.18534777094917568,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.4716,
|
|
"mean_token_accuracy": 0.10708810836076736,
|
|
"num_tokens": 3183286.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.5944517135620115,
|
|
"epoch": 0.18632328553311872,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.5058,
|
|
"mean_token_accuracy": 0.10114045292139054,
|
|
"num_tokens": 3198522.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.4455090999603275,
|
|
"epoch": 0.18729880011706174,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.5287,
|
|
"mean_token_accuracy": 0.10372934117913246,
|
|
"num_tokens": 3218422.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.534113931655884,
|
|
"epoch": 0.18827431470100478,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.5642,
|
|
"mean_token_accuracy": 0.09645498842000962,
|
|
"num_tokens": 3236407.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.551708793640136,
|
|
"epoch": 0.18924982928494782,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.4922,
|
|
"mean_token_accuracy": 0.10387791618704796,
|
|
"num_tokens": 3252740.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.470359468460083,
|
|
"epoch": 0.19022534386889084,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.4286,
|
|
"mean_token_accuracy": 0.10193498730659485,
|
|
"num_tokens": 3269874.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.435076713562012,
|
|
"epoch": 0.19120085845283388,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.502,
|
|
"mean_token_accuracy": 0.10077228620648385,
|
|
"num_tokens": 3286515.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.378189039230347,
|
|
"epoch": 0.1921763730367769,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.2799,
|
|
"mean_token_accuracy": 0.12222360447049141,
|
|
"num_tokens": 3303700.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.442311334609985,
|
|
"epoch": 0.19315188762071994,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.4712,
|
|
"mean_token_accuracy": 0.10699821785092353,
|
|
"num_tokens": 3319768.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.479348468780517,
|
|
"epoch": 0.19412740220466296,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.3723,
|
|
"mean_token_accuracy": 0.1109627477824688,
|
|
"num_tokens": 3336555.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.386620044708252,
|
|
"epoch": 0.195102916788606,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.4026,
|
|
"mean_token_accuracy": 0.10794939920306205,
|
|
"num_tokens": 3353273.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.3974672794342045,
|
|
"epoch": 0.19607843137254902,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999999929644166,
|
|
"loss": 7.2766,
|
|
"mean_token_accuracy": 0.11775518953800201,
|
|
"num_tokens": 3369408.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.376392459869384,
|
|
"epoch": 0.19705394595649206,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999999643823598,
|
|
"loss": 7.332,
|
|
"mean_token_accuracy": 0.11445832625031471,
|
|
"num_tokens": 3385834.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.386595392227173,
|
|
"epoch": 0.19802946054043508,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999999138141084,
|
|
"loss": 7.4388,
|
|
"mean_token_accuracy": 0.10919031649827957,
|
|
"num_tokens": 3401407.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.5447615623474125,
|
|
"epoch": 0.19900497512437812,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999998412596673,
|
|
"loss": 7.4617,
|
|
"mean_token_accuracy": 0.10121053159236908,
|
|
"num_tokens": 3418256.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.328778457641602,
|
|
"epoch": 0.19998048970832114,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999997467190435,
|
|
"loss": 7.4308,
|
|
"mean_token_accuracy": 0.10942661762237549,
|
|
"num_tokens": 3433932.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.4000791072845455,
|
|
"epoch": 0.20095600429226418,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999996301922465,
|
|
"loss": 7.464,
|
|
"mean_token_accuracy": 0.09955221861600876,
|
|
"num_tokens": 3451723.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.486557340621948,
|
|
"epoch": 0.2019315188762072,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999994916792876,
|
|
"loss": 7.4268,
|
|
"mean_token_accuracy": 0.10579116493463517,
|
|
"num_tokens": 3469170.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.439934206008911,
|
|
"epoch": 0.20290703346015024,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999993311801802,
|
|
"loss": 7.4632,
|
|
"mean_token_accuracy": 0.10232352912425995,
|
|
"num_tokens": 3485282.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.457415437698364,
|
|
"epoch": 0.20388254804409325,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00049999914869494,
|
|
"loss": 7.449,
|
|
"mean_token_accuracy": 0.09637642353773117,
|
|
"num_tokens": 3502206.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.423295640945435,
|
|
"epoch": 0.2048580626280363,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499998944223585,
|
|
"loss": 7.391,
|
|
"mean_token_accuracy": 0.10561487749218941,
|
|
"num_tokens": 3520384.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.305895376205444,
|
|
"epoch": 0.2058335772119793,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004999987177661351,
|
|
"loss": 7.389,
|
|
"mean_token_accuracy": 0.10617925822734833,
|
|
"num_tokens": 3536314.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.391325521469116,
|
|
"epoch": 0.20680909179592236,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999984693226124,
|
|
"loss": 7.3376,
|
|
"mean_token_accuracy": 0.11349749490618706,
|
|
"num_tokens": 3551510.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.388658809661865,
|
|
"epoch": 0.20778460637986537,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999981988930411,
|
|
"loss": 7.3434,
|
|
"mean_token_accuracy": 0.11000111326575279,
|
|
"num_tokens": 3568515.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.3375438213348385,
|
|
"epoch": 0.20876012096380842,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999979064774478,
|
|
"loss": 7.3821,
|
|
"mean_token_accuracy": 0.11078001037240029,
|
|
"num_tokens": 3585183.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.363852548599243,
|
|
"epoch": 0.20973563554775143,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000499997592075861,
|
|
"loss": 7.3389,
|
|
"mean_token_accuracy": 0.11243807971477508,
|
|
"num_tokens": 3601898.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.434067678451538,
|
|
"epoch": 0.21071115013169447,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999972556883113,
|
|
"loss": 7.3884,
|
|
"mean_token_accuracy": 0.10824741944670677,
|
|
"num_tokens": 3616699.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.355287313461304,
|
|
"epoch": 0.2116866647156375,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999968973148318,
|
|
"loss": 7.4124,
|
|
"mean_token_accuracy": 0.10511938706040383,
|
|
"num_tokens": 3634030.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.44262728691101,
|
|
"epoch": 0.21266217929958053,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004999965169554573,
|
|
"loss": 7.4147,
|
|
"mean_token_accuracy": 0.10464555099606514,
|
|
"num_tokens": 3650495.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.384248971939087,
|
|
"epoch": 0.21363769388352355,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999961146102251,
|
|
"loss": 7.3562,
|
|
"mean_token_accuracy": 0.1107444167137146,
|
|
"num_tokens": 3666926.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.320687627792358,
|
|
"epoch": 0.2146132084674666,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004999956902791746,
|
|
"loss": 7.3405,
|
|
"mean_token_accuracy": 0.11776096150279045,
|
|
"num_tokens": 3683061.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.306242418289185,
|
|
"epoch": 0.2155887230514096,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004999952439623469,
|
|
"loss": 7.4162,
|
|
"mean_token_accuracy": 0.10687667801976204,
|
|
"num_tokens": 3703013.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.352738571166992,
|
|
"epoch": 0.21656423763535265,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499994775659786,
|
|
"loss": 7.2601,
|
|
"mean_token_accuracy": 0.11846758648753167,
|
|
"num_tokens": 3719885.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.383596754074096,
|
|
"epoch": 0.21753975221929567,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999942853715375,
|
|
"loss": 7.4022,
|
|
"mean_token_accuracy": 0.10562850683927535,
|
|
"num_tokens": 3735122.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.362527561187744,
|
|
"epoch": 0.2185152668032387,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004999937730976494,
|
|
"loss": 7.3778,
|
|
"mean_token_accuracy": 0.10143291056156159,
|
|
"num_tokens": 3751627.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.2828888416290285,
|
|
"epoch": 0.21949078138718173,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999932388381716,
|
|
"loss": 7.3892,
|
|
"mean_token_accuracy": 0.10415156185626984,
|
|
"num_tokens": 3768165.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.505846929550171,
|
|
"epoch": 0.22046629597112477,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999926825931564,
|
|
"loss": 7.4244,
|
|
"mean_token_accuracy": 0.10518527254462243,
|
|
"num_tokens": 3784245.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.223800945281982,
|
|
"epoch": 0.2214418105550678,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999921043626582,
|
|
"loss": 7.1589,
|
|
"mean_token_accuracy": 0.12127066403627396,
|
|
"num_tokens": 3802057.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.311485624313354,
|
|
"epoch": 0.22241732513901083,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999915041467333,
|
|
"loss": 7.3624,
|
|
"mean_token_accuracy": 0.10803040713071824,
|
|
"num_tokens": 3817104.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.385139131546021,
|
|
"epoch": 0.22339283972295385,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004999908819454407,
|
|
"loss": 7.3468,
|
|
"mean_token_accuracy": 0.10780640989542008,
|
|
"num_tokens": 3833037.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.259801578521729,
|
|
"epoch": 0.2243683543068969,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999902377588408,
|
|
"loss": 7.2262,
|
|
"mean_token_accuracy": 0.11170127764344215,
|
|
"num_tokens": 3849634.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.339283418655396,
|
|
"epoch": 0.2253438688908399,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499989571586997,
|
|
"loss": 7.4162,
|
|
"mean_token_accuracy": 0.10458956733345985,
|
|
"num_tokens": 3865949.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.189256191253662,
|
|
"epoch": 0.22631938347478295,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999888834299739,
|
|
"loss": 7.2902,
|
|
"mean_token_accuracy": 0.11521978452801704,
|
|
"num_tokens": 3884646.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.392727613449097,
|
|
"epoch": 0.227294898058726,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999881732878391,
|
|
"loss": 7.3759,
|
|
"mean_token_accuracy": 0.10717562288045883,
|
|
"num_tokens": 3900740.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.320269823074341,
|
|
"epoch": 0.228270412642669,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999874411606618,
|
|
"loss": 7.3326,
|
|
"mean_token_accuracy": 0.11450612768530846,
|
|
"num_tokens": 3918619.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.379632997512817,
|
|
"epoch": 0.22924592722661205,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999866870485137,
|
|
"loss": 7.3004,
|
|
"mean_token_accuracy": 0.11032224223017692,
|
|
"num_tokens": 3938161.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.34798526763916,
|
|
"epoch": 0.23022144181055507,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999859109514684,
|
|
"loss": 7.3542,
|
|
"mean_token_accuracy": 0.10768297165632248,
|
|
"num_tokens": 3953582.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.30758113861084,
|
|
"epoch": 0.2311969563944981,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004999851128696017,
|
|
"loss": 7.3213,
|
|
"mean_token_accuracy": 0.1020158052444458,
|
|
"num_tokens": 3969747.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.3781046867370605,
|
|
"epoch": 0.23217247097844113,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999842928029917,
|
|
"loss": 7.3586,
|
|
"mean_token_accuracy": 0.10794111490249633,
|
|
"num_tokens": 3984646.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.299358987808228,
|
|
"epoch": 0.23314798556238417,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999834507517184,
|
|
"loss": 7.3486,
|
|
"mean_token_accuracy": 0.10666156932711601,
|
|
"num_tokens": 4003108.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.3120873928070065,
|
|
"epoch": 0.23412350014632718,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999825867158642,
|
|
"loss": 7.4151,
|
|
"mean_token_accuracy": 0.1019670806825161,
|
|
"num_tokens": 4019944.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.3608317375183105,
|
|
"epoch": 0.23509901473027023,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999817006955134,
|
|
"loss": 7.2993,
|
|
"mean_token_accuracy": 0.1109683245420456,
|
|
"num_tokens": 4037617.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.282232141494751,
|
|
"epoch": 0.23607452931421324,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999807926907527,
|
|
"loss": 7.2855,
|
|
"mean_token_accuracy": 0.10396898314356803,
|
|
"num_tokens": 4053483.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.354314088821411,
|
|
"epoch": 0.2370500438981563,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999798627016707,
|
|
"loss": 7.3621,
|
|
"mean_token_accuracy": 0.10965256318449974,
|
|
"num_tokens": 4070165.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.324768304824829,
|
|
"epoch": 0.2380255584820993,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999789107283586,
|
|
"loss": 7.3414,
|
|
"mean_token_accuracy": 0.10487294420599938,
|
|
"num_tokens": 4086208.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.26507248878479,
|
|
"epoch": 0.23900107306604235,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499977936770909,
|
|
"loss": 7.303,
|
|
"mean_token_accuracy": 0.11123988702893257,
|
|
"num_tokens": 4101790.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.320441770553589,
|
|
"epoch": 0.23997658764998536,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999769408294173,
|
|
"loss": 7.2266,
|
|
"mean_token_accuracy": 0.11657417044043542,
|
|
"num_tokens": 4117633.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.265048789978027,
|
|
"epoch": 0.2409521022339284,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004999759229039807,
|
|
"loss": 7.3035,
|
|
"mean_token_accuracy": 0.11276578083634377,
|
|
"num_tokens": 4132634.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.320464944839477,
|
|
"epoch": 0.24192761681787142,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004999748829946988,
|
|
"loss": 7.3391,
|
|
"mean_token_accuracy": 0.10908927693963051,
|
|
"num_tokens": 4150702.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.26134147644043,
|
|
"epoch": 0.24290313140181446,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999738211016732,
|
|
"loss": 7.2057,
|
|
"mean_token_accuracy": 0.12152880877256393,
|
|
"num_tokens": 4168483.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.158234167098999,
|
|
"epoch": 0.24387864598575748,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999727372250076,
|
|
"loss": 7.1701,
|
|
"mean_token_accuracy": 0.11431463360786438,
|
|
"num_tokens": 4186199.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.278416919708252,
|
|
"epoch": 0.24485416056970052,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999716313648079,
|
|
"loss": 7.3169,
|
|
"mean_token_accuracy": 0.1068569652736187,
|
|
"num_tokens": 4202303.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.338901853561401,
|
|
"epoch": 0.24582967515364354,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999705035211822,
|
|
"loss": 7.3571,
|
|
"mean_token_accuracy": 0.10634541511535645,
|
|
"num_tokens": 4218541.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.319312906265258,
|
|
"epoch": 0.24680518973758658,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999693536942406,
|
|
"loss": 7.3192,
|
|
"mean_token_accuracy": 0.10624103397130966,
|
|
"num_tokens": 4234025.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.292185544967651,
|
|
"epoch": 0.2477807043215296,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999681818840957,
|
|
"loss": 7.3435,
|
|
"mean_token_accuracy": 0.10807270258665085,
|
|
"num_tokens": 4250798.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.286764860153198,
|
|
"epoch": 0.24875621890547264,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499966988090862,
|
|
"loss": 7.3177,
|
|
"mean_token_accuracy": 0.10285230055451393,
|
|
"num_tokens": 4266453.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.35591869354248,
|
|
"epoch": 0.24973173348941566,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999657723146558,
|
|
"loss": 7.2729,
|
|
"mean_token_accuracy": 0.10762197226285934,
|
|
"num_tokens": 4281825.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.098993587493896,
|
|
"epoch": 0.2507072480733587,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004999645345555962,
|
|
"loss": 7.1453,
|
|
"mean_token_accuracy": 0.12227144241333007,
|
|
"num_tokens": 4298821.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.248935031890869,
|
|
"epoch": 0.2516827626573017,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999632748138041,
|
|
"loss": 7.1552,
|
|
"mean_token_accuracy": 0.11829453259706497,
|
|
"num_tokens": 4314076.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.217565107345581,
|
|
"epoch": 0.25265827724124473,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999619930894025,
|
|
"loss": 7.1797,
|
|
"mean_token_accuracy": 0.11851233690977096,
|
|
"num_tokens": 4330909.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.284217786788941,
|
|
"epoch": 0.2536337918251878,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999606893825168,
|
|
"loss": 7.2681,
|
|
"mean_token_accuracy": 0.1124707892537117,
|
|
"num_tokens": 4346927.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.240284633636475,
|
|
"epoch": 0.2546093064091308,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004999593636932742,
|
|
"loss": 7.3215,
|
|
"mean_token_accuracy": 0.10526167303323745,
|
|
"num_tokens": 4364956.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.290760946273804,
|
|
"epoch": 0.25558482099307384,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004999580160218044,
|
|
"loss": 7.2381,
|
|
"mean_token_accuracy": 0.10958634614944458,
|
|
"num_tokens": 4383014.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.144275045394897,
|
|
"epoch": 0.25656033557701685,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004999566463682391,
|
|
"loss": 7.3101,
|
|
"mean_token_accuracy": 0.10827136710286141,
|
|
"num_tokens": 4401050.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 7.248860025405884,
|
|
"epoch": 0.2575358501609599,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999552547327119,
|
|
"loss": 7.2175,
|
|
"mean_token_accuracy": 0.11122509092092514,
|
|
"num_tokens": 4415453.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.1784752368927,
|
|
"epoch": 0.25851136474490294,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004999538411153591,
|
|
"loss": 7.183,
|
|
"mean_token_accuracy": 0.11985458731651306,
|
|
"num_tokens": 4433107.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 7.25650372505188,
|
|
"epoch": 0.25948687932884595,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999524055163187,
|
|
"loss": 7.2758,
|
|
"mean_token_accuracy": 0.10543364882469178,
|
|
"num_tokens": 4449440.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.275032186508179,
|
|
"epoch": 0.26046239391278897,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499950947935731,
|
|
"loss": 7.2647,
|
|
"mean_token_accuracy": 0.10925490632653237,
|
|
"num_tokens": 4465327.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.2784374237060545,
|
|
"epoch": 0.26143790849673204,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999494683737384,
|
|
"loss": 7.2899,
|
|
"mean_token_accuracy": 0.10701772198081017,
|
|
"num_tokens": 4481518.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.292396831512451,
|
|
"epoch": 0.26241342308067506,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004999479668304854,
|
|
"loss": 7.3115,
|
|
"mean_token_accuracy": 0.10881960839033127,
|
|
"num_tokens": 4497632.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.030213069915772,
|
|
"epoch": 0.2633889376646181,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999464433061188,
|
|
"loss": 7.0711,
|
|
"mean_token_accuracy": 0.12342782318592072,
|
|
"num_tokens": 4513790.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.235921001434326,
|
|
"epoch": 0.26436445224856114,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999448978007876,
|
|
"loss": 7.1959,
|
|
"mean_token_accuracy": 0.11445838510990143,
|
|
"num_tokens": 4530802.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.2668671131134035,
|
|
"epoch": 0.26533996683250416,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999433303146426,
|
|
"loss": 7.2485,
|
|
"mean_token_accuracy": 0.10927580818533897,
|
|
"num_tokens": 4546208.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.22170729637146,
|
|
"epoch": 0.2663154814164472,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004999417408478371,
|
|
"loss": 7.3095,
|
|
"mean_token_accuracy": 0.11063284948468208,
|
|
"num_tokens": 4563753.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.213341140747071,
|
|
"epoch": 0.2672909960003902,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999401294005264,
|
|
"loss": 7.1897,
|
|
"mean_token_accuracy": 0.11640307679772377,
|
|
"num_tokens": 4580274.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 7.195255708694458,
|
|
"epoch": 0.26826651058433326,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000499938495972868,
|
|
"loss": 7.2656,
|
|
"mean_token_accuracy": 0.10936984345316887,
|
|
"num_tokens": 4596085.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.2880692958831785,
|
|
"epoch": 0.2692420251682763,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999368405650214,
|
|
"loss": 7.3116,
|
|
"mean_token_accuracy": 0.10627636015415191,
|
|
"num_tokens": 4613258.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 7.1051576137542725,
|
|
"epoch": 0.2702175397522193,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004999351631771485,
|
|
"loss": 7.1188,
|
|
"mean_token_accuracy": 0.11826564893126487,
|
|
"num_tokens": 4630128.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 7.252414560317993,
|
|
"epoch": 0.2711930543361623,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004999334638094131,
|
|
"loss": 7.1382,
|
|
"mean_token_accuracy": 0.1179644674062729,
|
|
"num_tokens": 4646181.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.185850667953491,
|
|
"epoch": 0.2721685689201054,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999317424619812,
|
|
"loss": 7.2119,
|
|
"mean_token_accuracy": 0.10765682607889175,
|
|
"num_tokens": 4661804.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 7.16576886177063,
|
|
"epoch": 0.2731440835040484,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004999299991350212,
|
|
"loss": 7.1211,
|
|
"mean_token_accuracy": 0.11724445223808289,
|
|
"num_tokens": 4678163.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.2082353115081785,
|
|
"epoch": 0.2741195980879914,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999282338287034,
|
|
"loss": 7.1126,
|
|
"mean_token_accuracy": 0.11289523839950562,
|
|
"num_tokens": 4695469.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 7.2161016941070555,
|
|
"epoch": 0.2750951126719344,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999264465432001,
|
|
"loss": 7.2651,
|
|
"mean_token_accuracy": 0.1120416909456253,
|
|
"num_tokens": 4711599.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 7.22179012298584,
|
|
"epoch": 0.2760706272558775,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999246372786862,
|
|
"loss": 7.2664,
|
|
"mean_token_accuracy": 0.10617031827569008,
|
|
"num_tokens": 4728381.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 7.18099422454834,
|
|
"epoch": 0.2770461418398205,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999228060353385,
|
|
"loss": 7.249,
|
|
"mean_token_accuracy": 0.10983582735061645,
|
|
"num_tokens": 4745348.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.252281141281128,
|
|
"epoch": 0.27802165642376353,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999209528133357,
|
|
"loss": 7.2657,
|
|
"mean_token_accuracy": 0.10274152681231499,
|
|
"num_tokens": 4763011.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.224287223815918,
|
|
"epoch": 0.27899717100770655,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499919077612859,
|
|
"loss": 7.2037,
|
|
"mean_token_accuracy": 0.1110018789768219,
|
|
"num_tokens": 4779462.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.078258800506592,
|
|
"epoch": 0.2799726855916496,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999171804340917,
|
|
"loss": 7.1645,
|
|
"mean_token_accuracy": 0.11882285252213479,
|
|
"num_tokens": 4796844.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.212335729598999,
|
|
"epoch": 0.28094820017559263,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999152612772191,
|
|
"loss": 7.1761,
|
|
"mean_token_accuracy": 0.11435465589165687,
|
|
"num_tokens": 4812851.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.095452976226807,
|
|
"epoch": 0.28192371475953565,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999133201424288,
|
|
"loss": 7.1163,
|
|
"mean_token_accuracy": 0.11493284702301025,
|
|
"num_tokens": 4830144.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 7.22363805770874,
|
|
"epoch": 0.28289922934347866,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999113570299105,
|
|
"loss": 7.2114,
|
|
"mean_token_accuracy": 0.10577581152319908,
|
|
"num_tokens": 4846981.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 7.309843254089356,
|
|
"epoch": 0.28387474392742174,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004999093719398561,
|
|
"loss": 7.3844,
|
|
"mean_token_accuracy": 0.10269515588879585,
|
|
"num_tokens": 4864404.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 7.181564807891846,
|
|
"epoch": 0.28485025851136475,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999073648724592,
|
|
"loss": 7.2608,
|
|
"mean_token_accuracy": 0.10562214255332947,
|
|
"num_tokens": 4882004.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 7.243942594528198,
|
|
"epoch": 0.28582577309530777,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999053358279164,
|
|
"loss": 7.1962,
|
|
"mean_token_accuracy": 0.1058816634118557,
|
|
"num_tokens": 4899444.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 7.221729326248169,
|
|
"epoch": 0.2868012876792508,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999032848064256,
|
|
"loss": 7.1964,
|
|
"mean_token_accuracy": 0.10939600914716721,
|
|
"num_tokens": 4917214.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 7.120475912094117,
|
|
"epoch": 0.28777680226319385,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999012118081875,
|
|
"loss": 7.2906,
|
|
"mean_token_accuracy": 0.102950569242239,
|
|
"num_tokens": 4934534.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.26613483428955,
|
|
"epoch": 0.28875231684713687,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998991168334045,
|
|
"loss": 7.1991,
|
|
"mean_token_accuracy": 0.10897819027304649,
|
|
"num_tokens": 4950740.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 7.185323762893677,
|
|
"epoch": 0.2897278314310799,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998969998822814,
|
|
"loss": 7.2858,
|
|
"mean_token_accuracy": 0.1056202620267868,
|
|
"num_tokens": 4966720.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 7.229295015335083,
|
|
"epoch": 0.2907033460150229,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998948609550249,
|
|
"loss": 7.1584,
|
|
"mean_token_accuracy": 0.10480799153447151,
|
|
"num_tokens": 4982195.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.172478818893433,
|
|
"epoch": 0.29167886059896597,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998927000518442,
|
|
"loss": 7.2806,
|
|
"mean_token_accuracy": 0.10777373760938644,
|
|
"num_tokens": 4997487.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 7.191869068145752,
|
|
"epoch": 0.292654375182909,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998905171729505,
|
|
"loss": 7.1667,
|
|
"mean_token_accuracy": 0.10947065055370331,
|
|
"num_tokens": 5012913.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 7.098269653320313,
|
|
"epoch": 0.293629889766852,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998883123185568,
|
|
"loss": 7.1303,
|
|
"mean_token_accuracy": 0.11931669116020202,
|
|
"num_tokens": 5031462.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 7.170979738235474,
|
|
"epoch": 0.294605404350795,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998860854888788,
|
|
"loss": 7.1056,
|
|
"mean_token_accuracy": 0.11914367899298668,
|
|
"num_tokens": 5047354.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 7.102825689315796,
|
|
"epoch": 0.2955809189347381,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004998838366841341,
|
|
"loss": 7.1882,
|
|
"mean_token_accuracy": 0.11276983618736267,
|
|
"num_tokens": 5065268.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 7.182042598724365,
|
|
"epoch": 0.2965564335186811,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998815659045423,
|
|
"loss": 7.1841,
|
|
"mean_token_accuracy": 0.10845357850193978,
|
|
"num_tokens": 5081066.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 7.147319793701172,
|
|
"epoch": 0.2975319481026241,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004998792731503254,
|
|
"loss": 7.2147,
|
|
"mean_token_accuracy": 0.11445605456829071,
|
|
"num_tokens": 5099440.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 7.120917463302613,
|
|
"epoch": 0.29850746268656714,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998769584217074,
|
|
"loss": 7.1576,
|
|
"mean_token_accuracy": 0.11984050646424294,
|
|
"num_tokens": 5116573.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 7.006188821792603,
|
|
"epoch": 0.2994829772705102,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998746217189145,
|
|
"loss": 6.9406,
|
|
"mean_token_accuracy": 0.12909065559506416,
|
|
"num_tokens": 5132920.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 7.300417137145996,
|
|
"epoch": 0.3004584918544532,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000499872263042175,
|
|
"loss": 7.2107,
|
|
"mean_token_accuracy": 0.10663213208317757,
|
|
"num_tokens": 5150681.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.995895576477051,
|
|
"epoch": 0.30143400643839624,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998698823917196,
|
|
"loss": 6.9672,
|
|
"mean_token_accuracy": 0.12855525091290473,
|
|
"num_tokens": 5167473.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 7.170604419708252,
|
|
"epoch": 0.3024095210223393,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004998674797677805,
|
|
"loss": 7.2533,
|
|
"mean_token_accuracy": 0.1055234856903553,
|
|
"num_tokens": 5183847.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 7.117762517929077,
|
|
"epoch": 0.3033850356062823,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998650551705929,
|
|
"loss": 7.2047,
|
|
"mean_token_accuracy": 0.10641410052776337,
|
|
"num_tokens": 5200019.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 7.073120164871216,
|
|
"epoch": 0.30436055019022534,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998626086003934,
|
|
"loss": 7.074,
|
|
"mean_token_accuracy": 0.11620460152626037,
|
|
"num_tokens": 5217245.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 7.112638330459594,
|
|
"epoch": 0.30533606477416836,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004998601400574213,
|
|
"loss": 6.9782,
|
|
"mean_token_accuracy": 0.12163180261850357,
|
|
"num_tokens": 5234822.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 7.115424585342407,
|
|
"epoch": 0.30631157935811143,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998576495419177,
|
|
"loss": 7.1305,
|
|
"mean_token_accuracy": 0.11187227442860603,
|
|
"num_tokens": 5251282.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 7.066088104248047,
|
|
"epoch": 0.30728709394205445,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.000499855137054126,
|
|
"loss": 7.0935,
|
|
"mean_token_accuracy": 0.11060698553919793,
|
|
"num_tokens": 5269630.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 7.150989151000976,
|
|
"epoch": 0.30826260852599746,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998526025942917,
|
|
"loss": 7.1563,
|
|
"mean_token_accuracy": 0.11012233942747116,
|
|
"num_tokens": 5287106.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 7.177860069274902,
|
|
"epoch": 0.3092381231099405,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998500461626625,
|
|
"loss": 7.1918,
|
|
"mean_token_accuracy": 0.10584679394960403,
|
|
"num_tokens": 5303387.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 7.231128740310669,
|
|
"epoch": 0.31021363769388355,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000499847467759488,
|
|
"loss": 7.1797,
|
|
"mean_token_accuracy": 0.10859874933958054,
|
|
"num_tokens": 5320482.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 7.100463199615478,
|
|
"epoch": 0.31118915227782656,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004998448673850205,
|
|
"loss": 7.1404,
|
|
"mean_token_accuracy": 0.11622472479939461,
|
|
"num_tokens": 5336420.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 7.01635103225708,
|
|
"epoch": 0.3121646668617696,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998422450395139,
|
|
"loss": 7.0872,
|
|
"mean_token_accuracy": 0.11045913249254227,
|
|
"num_tokens": 5353464.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 7.137714147567749,
|
|
"epoch": 0.3131401814457126,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998396007232244,
|
|
"loss": 7.1475,
|
|
"mean_token_accuracy": 0.1154401995241642,
|
|
"num_tokens": 5372607.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 7.122408390045166,
|
|
"epoch": 0.31411569602965567,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998369344364105,
|
|
"loss": 7.1723,
|
|
"mean_token_accuracy": 0.11676934882998466,
|
|
"num_tokens": 5390134.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 7.0988771438598635,
|
|
"epoch": 0.3150912106135987,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004998342461793328,
|
|
"loss": 7.0821,
|
|
"mean_token_accuracy": 0.1153003416955471,
|
|
"num_tokens": 5407083.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.936686992645264,
|
|
"epoch": 0.3160667251975417,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998315359522538,
|
|
"loss": 6.9746,
|
|
"mean_token_accuracy": 0.12812903001904488,
|
|
"num_tokens": 5424617.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 7.118428945541382,
|
|
"epoch": 0.3170422397814847,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004998288037554383,
|
|
"loss": 7.1248,
|
|
"mean_token_accuracy": 0.12060828432440758,
|
|
"num_tokens": 5440913.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 7.1336418151855465,
|
|
"epoch": 0.3180177543654278,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998260495891535,
|
|
"loss": 7.1488,
|
|
"mean_token_accuracy": 0.11536478698253631,
|
|
"num_tokens": 5457157.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 7.052104187011719,
|
|
"epoch": 0.3189932689493708,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004998232734536685,
|
|
"loss": 7.0581,
|
|
"mean_token_accuracy": 0.11604453399777412,
|
|
"num_tokens": 5474520.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 7.146209955215454,
|
|
"epoch": 0.3199687835333138,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998204753492544,
|
|
"loss": 7.1398,
|
|
"mean_token_accuracy": 0.11600466221570968,
|
|
"num_tokens": 5490599.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 7.127297306060791,
|
|
"epoch": 0.32094429811725683,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998176552761848,
|
|
"loss": 7.2087,
|
|
"mean_token_accuracy": 0.10203930661082268,
|
|
"num_tokens": 5506714.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 7.160216569900513,
|
|
"epoch": 0.3219198127011999,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004998148132347352,
|
|
"loss": 7.1485,
|
|
"mean_token_accuracy": 0.10920300856232643,
|
|
"num_tokens": 5522894.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 7.043737173080444,
|
|
"epoch": 0.3228953272851429,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004998119492251832,
|
|
"loss": 7.0243,
|
|
"mean_token_accuracy": 0.12240474671125412,
|
|
"num_tokens": 5540054.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 7.168790626525879,
|
|
"epoch": 0.32387084186908593,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998090632478088,
|
|
"loss": 7.1947,
|
|
"mean_token_accuracy": 0.10093299672007561,
|
|
"num_tokens": 5556189.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 7.159790563583374,
|
|
"epoch": 0.32484635645302895,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000499806155302894,
|
|
"loss": 7.2081,
|
|
"mean_token_accuracy": 0.10658285319805146,
|
|
"num_tokens": 5572562.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 7.182238483428955,
|
|
"epoch": 0.325821871036972,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000499803225390723,
|
|
"loss": 7.188,
|
|
"mean_token_accuracy": 0.11000551506876946,
|
|
"num_tokens": 5588992.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 7.151162958145141,
|
|
"epoch": 0.32679738562091504,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004998002735115819,
|
|
"loss": 7.1148,
|
|
"mean_token_accuracy": 0.11034396961331368,
|
|
"num_tokens": 5604143.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 7.119655466079712,
|
|
"epoch": 0.32777290020485805,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997972996657593,
|
|
"loss": 7.2398,
|
|
"mean_token_accuracy": 0.10105421096086502,
|
|
"num_tokens": 5620887.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 7.158847618103027,
|
|
"epoch": 0.32874841478880107,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997943038535459,
|
|
"loss": 7.1709,
|
|
"mean_token_accuracy": 0.1110181026160717,
|
|
"num_tokens": 5637156.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 7.153251838684082,
|
|
"epoch": 0.32972392937274414,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004997912860752341,
|
|
"loss": 7.1217,
|
|
"mean_token_accuracy": 0.10916642993688583,
|
|
"num_tokens": 5654024.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 7.088912582397461,
|
|
"epoch": 0.33069944395668716,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997882463311192,
|
|
"loss": 7.062,
|
|
"mean_token_accuracy": 0.11368629187345505,
|
|
"num_tokens": 5671538.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 7.089573669433594,
|
|
"epoch": 0.33167495854063017,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004997851846214979,
|
|
"loss": 7.1212,
|
|
"mean_token_accuracy": 0.11628169491887093,
|
|
"num_tokens": 5688788.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 7.056381750106811,
|
|
"epoch": 0.3326504731245732,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004997821009466695,
|
|
"loss": 7.0529,
|
|
"mean_token_accuracy": 0.11595623269677162,
|
|
"num_tokens": 5706066.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 7.03841462135315,
|
|
"epoch": 0.33362598770851626,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997789953069354,
|
|
"loss": 7.0434,
|
|
"mean_token_accuracy": 0.11439799889922142,
|
|
"num_tokens": 5722100.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 7.124280977249145,
|
|
"epoch": 0.3346015022924593,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004997758677025989,
|
|
"loss": 7.1696,
|
|
"mean_token_accuracy": 0.10830180943012238,
|
|
"num_tokens": 5739068.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 7.088494777679443,
|
|
"epoch": 0.3355770168764023,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004997727181339658,
|
|
"loss": 7.1296,
|
|
"mean_token_accuracy": 0.11222045645117759,
|
|
"num_tokens": 5756147.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 7.158913946151733,
|
|
"epoch": 0.3365525314603453,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004997695466013438,
|
|
"loss": 7.1013,
|
|
"mean_token_accuracy": 0.11348066926002502,
|
|
"num_tokens": 5772157.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 7.1085058689117435,
|
|
"epoch": 0.3375280460442884,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997663531050427,
|
|
"loss": 7.133,
|
|
"mean_token_accuracy": 0.11211565360426903,
|
|
"num_tokens": 5788128.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 7.048029518127441,
|
|
"epoch": 0.3385035606282314,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997631376453749,
|
|
"loss": 7.117,
|
|
"mean_token_accuracy": 0.11303148567676544,
|
|
"num_tokens": 5804793.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 7.091092491149903,
|
|
"epoch": 0.3394790752121744,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997599002226541,
|
|
"loss": 7.0445,
|
|
"mean_token_accuracy": 0.11384404823184013,
|
|
"num_tokens": 5822409.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.988621425628662,
|
|
"epoch": 0.3404545897961175,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499756640837197,
|
|
"loss": 7.0837,
|
|
"mean_token_accuracy": 0.11030225455760956,
|
|
"num_tokens": 5839023.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 7.136508464813232,
|
|
"epoch": 0.3414301043800605,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499753359489322,
|
|
"loss": 7.1018,
|
|
"mean_token_accuracy": 0.10952565595507621,
|
|
"num_tokens": 5855804.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 7.064236307144165,
|
|
"epoch": 0.3424056189640035,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997500561793498,
|
|
"loss": 7.1143,
|
|
"mean_token_accuracy": 0.11261064410209656,
|
|
"num_tokens": 5872372.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 7.140656232833862,
|
|
"epoch": 0.3433811335479465,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004997467309076031,
|
|
"loss": 7.1523,
|
|
"mean_token_accuracy": 0.1071063719689846,
|
|
"num_tokens": 5888666.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.9952013969421385,
|
|
"epoch": 0.3443566481318896,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004997433836744069,
|
|
"loss": 7.0905,
|
|
"mean_token_accuracy": 0.1121178537607193,
|
|
"num_tokens": 5905577.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 7.113792610168457,
|
|
"epoch": 0.3453321627158326,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997400144800882,
|
|
"loss": 7.065,
|
|
"mean_token_accuracy": 0.11290777698159218,
|
|
"num_tokens": 5922570.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.972097253799438,
|
|
"epoch": 0.34630767729977563,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997366233249762,
|
|
"loss": 7.0204,
|
|
"mean_token_accuracy": 0.12438111305236817,
|
|
"num_tokens": 5938995.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 7.042465877532959,
|
|
"epoch": 0.34728319188371864,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004997332102094024,
|
|
"loss": 7.0303,
|
|
"mean_token_accuracy": 0.1208010382950306,
|
|
"num_tokens": 5954869.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 7.181672048568726,
|
|
"epoch": 0.3482587064676617,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004997297751337004,
|
|
"loss": 7.1467,
|
|
"mean_token_accuracy": 0.11480126529932022,
|
|
"num_tokens": 5972750.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 7.021099853515625,
|
|
"epoch": 0.34923422105160473,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004997263180982055,
|
|
"loss": 7.0622,
|
|
"mean_token_accuracy": 0.11614978462457656,
|
|
"num_tokens": 5989004.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 7.017993831634522,
|
|
"epoch": 0.35020973563554775,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004997228391032559,
|
|
"loss": 7.0776,
|
|
"mean_token_accuracy": 0.11161015629768371,
|
|
"num_tokens": 6004749.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.965499401092529,
|
|
"epoch": 0.35118525021949076,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004997193381491913,
|
|
"loss": 6.9504,
|
|
"mean_token_accuracy": 0.11921020373702049,
|
|
"num_tokens": 6022235.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 7.04525671005249,
|
|
"epoch": 0.35216076480343383,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000499715815236354,
|
|
"loss": 7.1238,
|
|
"mean_token_accuracy": 0.10555350333452225,
|
|
"num_tokens": 6039194.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 7.0818140506744385,
|
|
"epoch": 0.35313627938737685,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000499712270365088,
|
|
"loss": 6.9903,
|
|
"mean_token_accuracy": 0.11186902597546577,
|
|
"num_tokens": 6055376.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 7.07976222038269,
|
|
"epoch": 0.35411179397131987,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004997087035357398,
|
|
"loss": 7.0482,
|
|
"mean_token_accuracy": 0.1155602365732193,
|
|
"num_tokens": 6071105.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.994044351577759,
|
|
"epoch": 0.3550873085552629,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997051147486582,
|
|
"loss": 6.9829,
|
|
"mean_token_accuracy": 0.11727840378880501,
|
|
"num_tokens": 6087964.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.997056674957276,
|
|
"epoch": 0.35606282313920595,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004997015040041935,
|
|
"loss": 7.0576,
|
|
"mean_token_accuracy": 0.10933208093047142,
|
|
"num_tokens": 6105245.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 7.0379139423370365,
|
|
"epoch": 0.35703833772314897,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996978713026986,
|
|
"loss": 7.0079,
|
|
"mean_token_accuracy": 0.12135875448584557,
|
|
"num_tokens": 6121736.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 7.041876888275146,
|
|
"epoch": 0.358013852307092,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996942166445287,
|
|
"loss": 7.0581,
|
|
"mean_token_accuracy": 0.11438895165920257,
|
|
"num_tokens": 6137751.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 7.019932746887207,
|
|
"epoch": 0.358989366891035,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004996905400300407,
|
|
"loss": 7.1101,
|
|
"mean_token_accuracy": 0.1149475984275341,
|
|
"num_tokens": 6154655.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 7.147087574005127,
|
|
"epoch": 0.35996488147497807,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000499686841459594,
|
|
"loss": 7.1113,
|
|
"mean_token_accuracy": 0.10812506079673767,
|
|
"num_tokens": 6172230.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.977477312088013,
|
|
"epoch": 0.3609403960589211,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996831209335497,
|
|
"loss": 7.072,
|
|
"mean_token_accuracy": 0.10572083070874214,
|
|
"num_tokens": 6188520.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 7.082860088348388,
|
|
"epoch": 0.3619159106428641,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004996793784522719,
|
|
"loss": 7.0966,
|
|
"mean_token_accuracy": 0.11021933704614639,
|
|
"num_tokens": 6205555.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 7.090164709091186,
|
|
"epoch": 0.3628914252268071,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004996756140161259,
|
|
"loss": 7.0792,
|
|
"mean_token_accuracy": 0.11376980021595955,
|
|
"num_tokens": 6223548.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 7.03369836807251,
|
|
"epoch": 0.3638669398107502,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004996718276254797,
|
|
"loss": 7.089,
|
|
"mean_token_accuracy": 0.1082814022898674,
|
|
"num_tokens": 6239266.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 7.072378301620484,
|
|
"epoch": 0.3648424543946932,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004996680192807032,
|
|
"loss": 7.0513,
|
|
"mean_token_accuracy": 0.11285683810710907,
|
|
"num_tokens": 6255020.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 7.046410369873047,
|
|
"epoch": 0.3658179689786362,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004996641889821686,
|
|
"loss": 6.9917,
|
|
"mean_token_accuracy": 0.1103696033358574,
|
|
"num_tokens": 6272774.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.994774389266968,
|
|
"epoch": 0.36679348356257924,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996603367302502,
|
|
"loss": 7.0055,
|
|
"mean_token_accuracy": 0.11505129560828209,
|
|
"num_tokens": 6290478.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 7.055514526367188,
|
|
"epoch": 0.3677689981465223,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004996564625253244,
|
|
"loss": 7.0872,
|
|
"mean_token_accuracy": 0.11461991667747498,
|
|
"num_tokens": 6308003.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 7.011760663986206,
|
|
"epoch": 0.3687445127304653,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004996525663677697,
|
|
"loss": 7.0486,
|
|
"mean_token_accuracy": 0.10762766152620315,
|
|
"num_tokens": 6325748.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 7.06716947555542,
|
|
"epoch": 0.36972002731440834,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499648648257967,
|
|
"loss": 6.9936,
|
|
"mean_token_accuracy": 0.12201232090592384,
|
|
"num_tokens": 6344031.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.942547082901001,
|
|
"epoch": 0.37069554189835136,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000499644708196299,
|
|
"loss": 7.0461,
|
|
"mean_token_accuracy": 0.11835477128624916,
|
|
"num_tokens": 6359821.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.970766019821167,
|
|
"epoch": 0.3716710564822944,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004996407461831507,
|
|
"loss": 6.888,
|
|
"mean_token_accuracy": 0.1269619345664978,
|
|
"num_tokens": 6376464.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 7.020088863372803,
|
|
"epoch": 0.37264657106623744,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004996367622189094,
|
|
"loss": 7.0657,
|
|
"mean_token_accuracy": 0.1099945642054081,
|
|
"num_tokens": 6392415.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.974881839752197,
|
|
"epoch": 0.37362208565018046,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004996327563039643,
|
|
"loss": 7.0612,
|
|
"mean_token_accuracy": 0.11171750500798225,
|
|
"num_tokens": 6409151.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 7.1153641700744625,
|
|
"epoch": 0.3745976002341235,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004996287284387068,
|
|
"loss": 7.0241,
|
|
"mean_token_accuracy": 0.11637166067957878,
|
|
"num_tokens": 6426997.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.979948997497559,
|
|
"epoch": 0.37557311481806654,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004996246786235306,
|
|
"loss": 7.0189,
|
|
"mean_token_accuracy": 0.11474493220448494,
|
|
"num_tokens": 6442871.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.961305904388428,
|
|
"epoch": 0.37654862940200956,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996206068588314,
|
|
"loss": 7.0048,
|
|
"mean_token_accuracy": 0.11208005249500275,
|
|
"num_tokens": 6459677.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 7.101429510116577,
|
|
"epoch": 0.3775241439859526,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004996165131450071,
|
|
"loss": 7.1353,
|
|
"mean_token_accuracy": 0.10877176895737647,
|
|
"num_tokens": 6477239.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 7.059422874450684,
|
|
"epoch": 0.37849965856989565,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004996123974824576,
|
|
"loss": 7.0037,
|
|
"mean_token_accuracy": 0.11793602928519249,
|
|
"num_tokens": 6493277.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.967101335525513,
|
|
"epoch": 0.37947517315383866,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004996082598715852,
|
|
"loss": 7.0137,
|
|
"mean_token_accuracy": 0.11420942023396492,
|
|
"num_tokens": 6509204.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.933266544342041,
|
|
"epoch": 0.3804506877377817,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499604100312794,
|
|
"loss": 6.8819,
|
|
"mean_token_accuracy": 0.1260261982679367,
|
|
"num_tokens": 6525486.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.971220445632935,
|
|
"epoch": 0.3814262023217247,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004995999188064908,
|
|
"loss": 7.0954,
|
|
"mean_token_accuracy": 0.1095791406929493,
|
|
"num_tokens": 6542227.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 7.0703741073608395,
|
|
"epoch": 0.38240171690566777,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499595715353084,
|
|
"loss": 7.1663,
|
|
"mean_token_accuracy": 0.1052120178937912,
|
|
"num_tokens": 6558951.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 7.107343959808349,
|
|
"epoch": 0.3833772314896108,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995914899529844,
|
|
"loss": 7.0602,
|
|
"mean_token_accuracy": 0.11332785338163376,
|
|
"num_tokens": 6574696.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 7.097244834899902,
|
|
"epoch": 0.3843527460735538,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004995872426066048,
|
|
"loss": 7.0934,
|
|
"mean_token_accuracy": 0.10992669835686683,
|
|
"num_tokens": 6591628.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 7.00416316986084,
|
|
"epoch": 0.3853282606574968,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995829733143602,
|
|
"loss": 6.9752,
|
|
"mean_token_accuracy": 0.11769431084394455,
|
|
"num_tokens": 6608107.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 7.009332847595215,
|
|
"epoch": 0.3863037752414399,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000499578682076668,
|
|
"loss": 7.1112,
|
|
"mean_token_accuracy": 0.11527311876416206,
|
|
"num_tokens": 6626699.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 7.1108642578125,
|
|
"epoch": 0.3872792898253829,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995743688939474,
|
|
"loss": 7.1356,
|
|
"mean_token_accuracy": 0.10339468270540238,
|
|
"num_tokens": 6644540.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 7.082017087936402,
|
|
"epoch": 0.3882548044093259,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004995700337666199,
|
|
"loss": 7.0632,
|
|
"mean_token_accuracy": 0.10787386372685433,
|
|
"num_tokens": 6660653.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 7.05488920211792,
|
|
"epoch": 0.38923031899326893,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000499565676695109,
|
|
"loss": 7.055,
|
|
"mean_token_accuracy": 0.10950738564133644,
|
|
"num_tokens": 6677553.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 7.056804180145264,
|
|
"epoch": 0.390205833577212,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995612976798406,
|
|
"loss": 7.0546,
|
|
"mean_token_accuracy": 0.10897849723696709,
|
|
"num_tokens": 6695274.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.96084771156311,
|
|
"epoch": 0.391181348161155,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004995568967212425,
|
|
"loss": 6.9898,
|
|
"mean_token_accuracy": 0.1134484887123108,
|
|
"num_tokens": 6711166.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.97249550819397,
|
|
"epoch": 0.39215686274509803,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995524738197448,
|
|
"loss": 6.9709,
|
|
"mean_token_accuracy": 0.11566549465060234,
|
|
"num_tokens": 6728827.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.880181360244751,
|
|
"epoch": 0.39313237732904105,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004995480289757796,
|
|
"loss": 6.9491,
|
|
"mean_token_accuracy": 0.12184445783495904,
|
|
"num_tokens": 6745901.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.927216005325318,
|
|
"epoch": 0.3941078919129841,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004995435621897815,
|
|
"loss": 6.9157,
|
|
"mean_token_accuracy": 0.12079904079437256,
|
|
"num_tokens": 6762176.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.997888612747192,
|
|
"epoch": 0.39508340649692714,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995390734621867,
|
|
"loss": 7.0721,
|
|
"mean_token_accuracy": 0.10900324806571007,
|
|
"num_tokens": 6779322.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 7.120794105529785,
|
|
"epoch": 0.39605892108087015,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004995345627934338,
|
|
"loss": 7.0008,
|
|
"mean_token_accuracy": 0.1168686531484127,
|
|
"num_tokens": 6794293.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.7111622333526615,
|
|
"epoch": 0.39703443566481317,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004995300301839637,
|
|
"loss": 6.8367,
|
|
"mean_token_accuracy": 0.13236104398965837,
|
|
"num_tokens": 6812880.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 7.063685464859009,
|
|
"epoch": 0.39800995024875624,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004995254756342194,
|
|
"loss": 7.0484,
|
|
"mean_token_accuracy": 0.1098434530198574,
|
|
"num_tokens": 6829230.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 7.021308040618896,
|
|
"epoch": 0.39898546483269925,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004995208991446458,
|
|
"loss": 7.0422,
|
|
"mean_token_accuracy": 0.11086834147572518,
|
|
"num_tokens": 6846787.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.921110916137695,
|
|
"epoch": 0.39996097941664227,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995163007156902,
|
|
"loss": 6.9141,
|
|
"mean_token_accuracy": 0.11068061590194703,
|
|
"num_tokens": 6862990.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 7.045805883407593,
|
|
"epoch": 0.4009364940005853,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995116803478018,
|
|
"loss": 7.0557,
|
|
"mean_token_accuracy": 0.10982215702533722,
|
|
"num_tokens": 6879170.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.93969578742981,
|
|
"epoch": 0.40191200858452836,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004995070380414321,
|
|
"loss": 7.0471,
|
|
"mean_token_accuracy": 0.11072775200009347,
|
|
"num_tokens": 6895635.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 7.018460369110107,
|
|
"epoch": 0.4028875231684714,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499502373797035,
|
|
"loss": 6.9495,
|
|
"mean_token_accuracy": 0.11848736256361007,
|
|
"num_tokens": 6912836.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.938055992126465,
|
|
"epoch": 0.4038630377524144,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499497687615066,
|
|
"loss": 6.9925,
|
|
"mean_token_accuracy": 0.11958426535129547,
|
|
"num_tokens": 6929507.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 7.012846374511719,
|
|
"epoch": 0.4048385523363574,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000499492979495983,
|
|
"loss": 7.0108,
|
|
"mean_token_accuracy": 0.11071802526712418,
|
|
"num_tokens": 6946527.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 7.006974458694458,
|
|
"epoch": 0.4058140669203005,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994882494402462,
|
|
"loss": 7.0069,
|
|
"mean_token_accuracy": 0.11493440046906471,
|
|
"num_tokens": 6962582.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 7.00134916305542,
|
|
"epoch": 0.4067895815042435,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004994834974483178,
|
|
"loss": 6.9966,
|
|
"mean_token_accuracy": 0.1160830058157444,
|
|
"num_tokens": 6979389.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.925145530700684,
|
|
"epoch": 0.4077650960881865,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004994787235206621,
|
|
"loss": 6.9717,
|
|
"mean_token_accuracy": 0.11536258235573768,
|
|
"num_tokens": 6996637.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 7.0829870223999025,
|
|
"epoch": 0.4087406106721295,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004994739276577456,
|
|
"loss": 7.0683,
|
|
"mean_token_accuracy": 0.10761817693710327,
|
|
"num_tokens": 7013013.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.928919935226441,
|
|
"epoch": 0.4097161252560726,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004994691098600369,
|
|
"loss": 7.0302,
|
|
"mean_token_accuracy": 0.11743959337472916,
|
|
"num_tokens": 7031476.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 7.063517665863037,
|
|
"epoch": 0.4106916398400156,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004994642701280068,
|
|
"loss": 6.9326,
|
|
"mean_token_accuracy": 0.11514554470777512,
|
|
"num_tokens": 7047424.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.928591346740722,
|
|
"epoch": 0.4116671544239586,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004994594084621282,
|
|
"loss": 7.0055,
|
|
"mean_token_accuracy": 0.110958231985569,
|
|
"num_tokens": 7063793.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 7.087340021133423,
|
|
"epoch": 0.41264266900790164,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004994545248628762,
|
|
"loss": 7.0733,
|
|
"mean_token_accuracy": 0.10909361913800239,
|
|
"num_tokens": 7079026.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.97515983581543,
|
|
"epoch": 0.4136181835918447,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499449619330728,
|
|
"loss": 7.0004,
|
|
"mean_token_accuracy": 0.1165304310619831,
|
|
"num_tokens": 7097524.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 7.0495555877685545,
|
|
"epoch": 0.41459369817578773,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000499444691866163,
|
|
"loss": 7.0737,
|
|
"mean_token_accuracy": 0.11175737231969833,
|
|
"num_tokens": 7115514.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.996109342575073,
|
|
"epoch": 0.41556921275973074,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994397424696625,
|
|
"loss": 7.0165,
|
|
"mean_token_accuracy": 0.1140232503414154,
|
|
"num_tokens": 7132589.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 7.000941753387451,
|
|
"epoch": 0.4165447273436738,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004994347711417105,
|
|
"loss": 7.0172,
|
|
"mean_token_accuracy": 0.1115983322262764,
|
|
"num_tokens": 7149416.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.923533773422241,
|
|
"epoch": 0.41752024192761683,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994297778827924,
|
|
"loss": 6.9598,
|
|
"mean_token_accuracy": 0.11849450021982193,
|
|
"num_tokens": 7165763.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.934512424468994,
|
|
"epoch": 0.41849575651155985,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004994247626933964,
|
|
"loss": 6.9401,
|
|
"mean_token_accuracy": 0.12275434285402298,
|
|
"num_tokens": 7183131.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.95603723526001,
|
|
"epoch": 0.41947127109550286,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004994197255740124,
|
|
"loss": 6.968,
|
|
"mean_token_accuracy": 0.1182591237127781,
|
|
"num_tokens": 7200467.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.983357381820679,
|
|
"epoch": 0.42044678567944593,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004994146665251327,
|
|
"loss": 6.9547,
|
|
"mean_token_accuracy": 0.11873010322451591,
|
|
"num_tokens": 7217311.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.967365360260009,
|
|
"epoch": 0.42142230026338895,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004994095855472516,
|
|
"loss": 6.9618,
|
|
"mean_token_accuracy": 0.11772591844201089,
|
|
"num_tokens": 7235244.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.99353609085083,
|
|
"epoch": 0.42239781484733196,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004994044826408656,
|
|
"loss": 6.9931,
|
|
"mean_token_accuracy": 0.11206987127661705,
|
|
"num_tokens": 7252235.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.952538728713989,
|
|
"epoch": 0.423373329431275,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004993993578064733,
|
|
"loss": 7.0059,
|
|
"mean_token_accuracy": 0.11217687204480171,
|
|
"num_tokens": 7269367.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 7.075891733169556,
|
|
"epoch": 0.42434884401521805,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993942110445756,
|
|
"loss": 6.9881,
|
|
"mean_token_accuracy": 0.1137772336602211,
|
|
"num_tokens": 7287198.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.9127795696258545,
|
|
"epoch": 0.42532435859916107,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004993890423556753,
|
|
"loss": 6.9142,
|
|
"mean_token_accuracy": 0.11559901610016823,
|
|
"num_tokens": 7302356.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.960020351409912,
|
|
"epoch": 0.4262998731831041,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004993838517402775,
|
|
"loss": 6.9235,
|
|
"mean_token_accuracy": 0.12155768349766731,
|
|
"num_tokens": 7318530.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.953242349624634,
|
|
"epoch": 0.4272753877670471,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004993786391988894,
|
|
"loss": 6.9095,
|
|
"mean_token_accuracy": 0.11496350169181824,
|
|
"num_tokens": 7335195.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.883234643936158,
|
|
"epoch": 0.42825090235099017,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004993734047320206,
|
|
"loss": 6.9147,
|
|
"mean_token_accuracy": 0.11316282376646995,
|
|
"num_tokens": 7352233.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.983979988098144,
|
|
"epoch": 0.4292264169349332,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004993681483401821,
|
|
"loss": 6.9696,
|
|
"mean_token_accuracy": 0.11637645065784455,
|
|
"num_tokens": 7368569.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.933692598342896,
|
|
"epoch": 0.4302019315188762,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004993628700238879,
|
|
"loss": 7.0137,
|
|
"mean_token_accuracy": 0.114168231934309,
|
|
"num_tokens": 7384669.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 7.095562601089478,
|
|
"epoch": 0.4311774461028192,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004993575697836537,
|
|
"loss": 7.0289,
|
|
"mean_token_accuracy": 0.11071271151304245,
|
|
"num_tokens": 7401833.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.924860429763794,
|
|
"epoch": 0.4321529606867623,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004993522476199975,
|
|
"loss": 6.9162,
|
|
"mean_token_accuracy": 0.1127213828265667,
|
|
"num_tokens": 7418663.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.971612501144409,
|
|
"epoch": 0.4331284752707053,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004993469035334392,
|
|
"loss": 6.9014,
|
|
"mean_token_accuracy": 0.1250322349369526,
|
|
"num_tokens": 7434701.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.9419066429138185,
|
|
"epoch": 0.4341039898546483,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000499341537524501,
|
|
"loss": 6.9828,
|
|
"mean_token_accuracy": 0.10986461192369461,
|
|
"num_tokens": 7450154.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.791154384613037,
|
|
"epoch": 0.43507950443859134,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004993361495937074,
|
|
"loss": 6.7912,
|
|
"mean_token_accuracy": 0.13519535660743714,
|
|
"num_tokens": 7468110.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.939401054382325,
|
|
"epoch": 0.4360550190225344,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004993307397415848,
|
|
"loss": 6.9107,
|
|
"mean_token_accuracy": 0.11550685539841651,
|
|
"num_tokens": 7482962.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 7.027690649032593,
|
|
"epoch": 0.4370305336064774,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004993253079686619,
|
|
"loss": 7.0536,
|
|
"mean_token_accuracy": 0.1094849169254303,
|
|
"num_tokens": 7499116.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.978180360794068,
|
|
"epoch": 0.43800604819042044,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004993198542754692,
|
|
"loss": 6.9999,
|
|
"mean_token_accuracy": 0.11379628702998161,
|
|
"num_tokens": 7515765.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.975172281265259,
|
|
"epoch": 0.43898156277436345,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004993143786625401,
|
|
"loss": 6.9918,
|
|
"mean_token_accuracy": 0.11214097291231155,
|
|
"num_tokens": 7532074.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.84090781211853,
|
|
"epoch": 0.4399570773583065,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004993088811304092,
|
|
"loss": 6.8176,
|
|
"mean_token_accuracy": 0.1292093053460121,
|
|
"num_tokens": 7547704.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.949747610092163,
|
|
"epoch": 0.44093259194224954,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004993033616796139,
|
|
"loss": 6.9434,
|
|
"mean_token_accuracy": 0.11486721858382225,
|
|
"num_tokens": 7563317.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.861780452728271,
|
|
"epoch": 0.44190810652619256,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004992978203106936,
|
|
"loss": 6.9432,
|
|
"mean_token_accuracy": 0.11190066412091255,
|
|
"num_tokens": 7580770.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.96252031326294,
|
|
"epoch": 0.4428836211101356,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004992922570241896,
|
|
"loss": 6.9184,
|
|
"mean_token_accuracy": 0.11765873730182648,
|
|
"num_tokens": 7598181.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.973319005966187,
|
|
"epoch": 0.44385913569407864,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004992866718206457,
|
|
"loss": 6.9181,
|
|
"mean_token_accuracy": 0.11969833001494408,
|
|
"num_tokens": 7613739.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.935301446914673,
|
|
"epoch": 0.44483465027802166,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004992810647006077,
|
|
"loss": 7.0022,
|
|
"mean_token_accuracy": 0.1112263709306717,
|
|
"num_tokens": 7629297.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 7.030787324905395,
|
|
"epoch": 0.4458101648619647,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004992754356646234,
|
|
"loss": 6.9824,
|
|
"mean_token_accuracy": 0.11118089407682419,
|
|
"num_tokens": 7645273.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.963811206817627,
|
|
"epoch": 0.4467856794459077,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004992697847132427,
|
|
"loss": 6.9328,
|
|
"mean_token_accuracy": 0.11047199815511703,
|
|
"num_tokens": 7661296.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.7955968379974365,
|
|
"epoch": 0.44776119402985076,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000499264111847018,
|
|
"loss": 6.9373,
|
|
"mean_token_accuracy": 0.11633702144026756,
|
|
"num_tokens": 7678658.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 7.02021017074585,
|
|
"epoch": 0.4487367086137938,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004992584170665037,
|
|
"loss": 6.9728,
|
|
"mean_token_accuracy": 0.11074585020542145,
|
|
"num_tokens": 7693678.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.931669616699219,
|
|
"epoch": 0.4497122231977368,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000499252700372256,
|
|
"loss": 6.9621,
|
|
"mean_token_accuracy": 0.11443416476249695,
|
|
"num_tokens": 7709526.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.949428653717041,
|
|
"epoch": 0.4506877377816798,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004992469617648337,
|
|
"loss": 6.8567,
|
|
"mean_token_accuracy": 0.11352990642189979,
|
|
"num_tokens": 7725055.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.787866640090942,
|
|
"epoch": 0.4516632523656229,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004992412012447976,
|
|
"loss": 6.7685,
|
|
"mean_token_accuracy": 0.13319482654333115,
|
|
"num_tokens": 7742047.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.923736810684204,
|
|
"epoch": 0.4526387669495659,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004992354188127105,
|
|
"loss": 6.9335,
|
|
"mean_token_accuracy": 0.11316853016614914,
|
|
"num_tokens": 7758283.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.89393982887268,
|
|
"epoch": 0.4536142815335089,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004992296144691375,
|
|
"loss": 6.8739,
|
|
"mean_token_accuracy": 0.11695389747619629,
|
|
"num_tokens": 7774660.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.8337976932525635,
|
|
"epoch": 0.454589796117452,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992237882146456,
|
|
"loss": 6.8903,
|
|
"mean_token_accuracy": 0.12075782865285874,
|
|
"num_tokens": 7792147.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.886572599411011,
|
|
"epoch": 0.455565310701395,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004992179400498044,
|
|
"loss": 6.8362,
|
|
"mean_token_accuracy": 0.12014108300209045,
|
|
"num_tokens": 7809021.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.939410781860351,
|
|
"epoch": 0.456540825285338,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004992120699751852,
|
|
"loss": 6.9025,
|
|
"mean_token_accuracy": 0.11456301808357239,
|
|
"num_tokens": 7825074.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.76352219581604,
|
|
"epoch": 0.45751633986928103,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004992061779913616,
|
|
"loss": 6.8407,
|
|
"mean_token_accuracy": 0.11945309415459633,
|
|
"num_tokens": 7843413.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.984707689285278,
|
|
"epoch": 0.4584918544532241,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004992002640989094,
|
|
"loss": 6.9299,
|
|
"mean_token_accuracy": 0.10952871888875962,
|
|
"num_tokens": 7859874.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.80113639831543,
|
|
"epoch": 0.4594673690371671,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004991943282984065,
|
|
"loss": 6.865,
|
|
"mean_token_accuracy": 0.12114636227488518,
|
|
"num_tokens": 7877302.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.925329256057739,
|
|
"epoch": 0.46044288362111013,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004991883705904328,
|
|
"loss": 6.976,
|
|
"mean_token_accuracy": 0.11222620382905006,
|
|
"num_tokens": 7893207.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.8837878704071045,
|
|
"epoch": 0.46141839820505315,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004991823909755705,
|
|
"loss": 6.8151,
|
|
"mean_token_accuracy": 0.12659919783473014,
|
|
"num_tokens": 7910239.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.920702743530273,
|
|
"epoch": 0.4623939127889962,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004991763894544041,
|
|
"loss": 6.958,
|
|
"mean_token_accuracy": 0.11296103447675705,
|
|
"num_tokens": 7928030.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.890843772888184,
|
|
"epoch": 0.46336942737293924,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004991703660275199,
|
|
"loss": 6.8931,
|
|
"mean_token_accuracy": 0.11770829334855079,
|
|
"num_tokens": 7943653.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.974278211593628,
|
|
"epoch": 0.46434494195688225,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004991643206955064,
|
|
"loss": 6.9705,
|
|
"mean_token_accuracy": 0.11404236927628517,
|
|
"num_tokens": 7960564.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.9140668392181395,
|
|
"epoch": 0.46532045654082527,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004991582534589544,
|
|
"loss": 6.9254,
|
|
"mean_token_accuracy": 0.1193073645234108,
|
|
"num_tokens": 7978045.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.957419967651367,
|
|
"epoch": 0.46629597112476834,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004991521643184567,
|
|
"loss": 6.9591,
|
|
"mean_token_accuracy": 0.11141033694148064,
|
|
"num_tokens": 7995074.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.947557401657105,
|
|
"epoch": 0.46727148570871135,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004991460532746087,
|
|
"loss": 6.9844,
|
|
"mean_token_accuracy": 0.10783464983105659,
|
|
"num_tokens": 8011800.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.9592297077178955,
|
|
"epoch": 0.46824700029265437,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499139920328007,
|
|
"loss": 6.9432,
|
|
"mean_token_accuracy": 0.1144430011510849,
|
|
"num_tokens": 8028090.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.912628507614135,
|
|
"epoch": 0.4692225148765974,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004991337654792512,
|
|
"loss": 6.9,
|
|
"mean_token_accuracy": 0.11696527898311615,
|
|
"num_tokens": 8044140.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.872697257995606,
|
|
"epoch": 0.47019802946054046,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004991275887289427,
|
|
"loss": 6.8495,
|
|
"mean_token_accuracy": 0.1179678663611412,
|
|
"num_tokens": 8060030.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.8621447563171385,
|
|
"epoch": 0.47117354404448347,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004991213900776849,
|
|
"loss": 6.8854,
|
|
"mean_token_accuracy": 0.11339947506785393,
|
|
"num_tokens": 8075445.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.974141788482666,
|
|
"epoch": 0.4721490586284265,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004991151695260838,
|
|
"loss": 6.8922,
|
|
"mean_token_accuracy": 0.11236568167805672,
|
|
"num_tokens": 8093250.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.816811847686767,
|
|
"epoch": 0.4731245732123695,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499108927074747,
|
|
"loss": 6.837,
|
|
"mean_token_accuracy": 0.12727442309260367,
|
|
"num_tokens": 8109615.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.8544200420379635,
|
|
"epoch": 0.4741000877963126,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004991026627242846,
|
|
"loss": 6.9403,
|
|
"mean_token_accuracy": 0.11186167597770691,
|
|
"num_tokens": 8126591.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.9048929691314695,
|
|
"epoch": 0.4750756023802556,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004990963764753088,
|
|
"loss": 6.8668,
|
|
"mean_token_accuracy": 0.11707579866051673,
|
|
"num_tokens": 8141360.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.942644453048706,
|
|
"epoch": 0.4760511169641986,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004990900683284337,
|
|
"loss": 6.9608,
|
|
"mean_token_accuracy": 0.12016337439417839,
|
|
"num_tokens": 8159688.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.867148971557617,
|
|
"epoch": 0.4770266315481416,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004990837382842758,
|
|
"loss": 6.9146,
|
|
"mean_token_accuracy": 0.11586871594190598,
|
|
"num_tokens": 8176887.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.805676031112671,
|
|
"epoch": 0.4780021461320847,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004990773863434537,
|
|
"loss": 6.7335,
|
|
"mean_token_accuracy": 0.12699671015143393,
|
|
"num_tokens": 8193372.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.888016700744629,
|
|
"epoch": 0.4789776607160277,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004990710125065879,
|
|
"loss": 6.9435,
|
|
"mean_token_accuracy": 0.1139527752995491,
|
|
"num_tokens": 8209713.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.959731769561768,
|
|
"epoch": 0.4799531752999707,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004990646167743015,
|
|
"loss": 6.9477,
|
|
"mean_token_accuracy": 0.11611981242895127,
|
|
"num_tokens": 8226359.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.841183757781982,
|
|
"epoch": 0.48092868988391374,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004990581991472193,
|
|
"loss": 6.9187,
|
|
"mean_token_accuracy": 0.11466511264443398,
|
|
"num_tokens": 8243182.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.923015356063843,
|
|
"epoch": 0.4819042044678568,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004990517596259684,
|
|
"loss": 6.9206,
|
|
"mean_token_accuracy": 0.1125547505915165,
|
|
"num_tokens": 8259185.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.927219390869141,
|
|
"epoch": 0.4828797190517998,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004990452982111781,
|
|
"loss": 6.983,
|
|
"mean_token_accuracy": 0.11010222509503365,
|
|
"num_tokens": 8275941.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.935208940505982,
|
|
"epoch": 0.48385523363574284,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004990388149034797,
|
|
"loss": 6.9253,
|
|
"mean_token_accuracy": 0.11687990576028824,
|
|
"num_tokens": 8292535.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.887890434265136,
|
|
"epoch": 0.48483074821968586,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004990323097035069,
|
|
"loss": 6.8769,
|
|
"mean_token_accuracy": 0.12070949226617814,
|
|
"num_tokens": 8310562.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.870615386962891,
|
|
"epoch": 0.48580626280362893,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004990257826118952,
|
|
"loss": 6.9097,
|
|
"mean_token_accuracy": 0.1069605253636837,
|
|
"num_tokens": 8327241.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.865695381164551,
|
|
"epoch": 0.48678177738757195,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004990192336292824,
|
|
"loss": 6.8423,
|
|
"mean_token_accuracy": 0.12054572403430938,
|
|
"num_tokens": 8343516.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.737391328811645,
|
|
"epoch": 0.48775729197151496,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004990126627563087,
|
|
"loss": 6.709,
|
|
"mean_token_accuracy": 0.12692616656422614,
|
|
"num_tokens": 8361809.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.767363262176514,
|
|
"epoch": 0.488732806555458,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004990060699936159,
|
|
"loss": 6.7707,
|
|
"mean_token_accuracy": 0.13018333539366722,
|
|
"num_tokens": 8378632.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.899938678741455,
|
|
"epoch": 0.48970832113940105,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004989994553418483,
|
|
"loss": 6.9353,
|
|
"mean_token_accuracy": 0.110991932451725,
|
|
"num_tokens": 8396201.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.8594200134277346,
|
|
"epoch": 0.49068383572334406,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004989928188016522,
|
|
"loss": 6.8072,
|
|
"mean_token_accuracy": 0.12356401160359383,
|
|
"num_tokens": 8412851.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.718408012390137,
|
|
"epoch": 0.4916593503072871,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004989861603736762,
|
|
"loss": 6.6376,
|
|
"mean_token_accuracy": 0.13155316412448884,
|
|
"num_tokens": 8430026.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.828795909881592,
|
|
"epoch": 0.49263486489123015,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004989794800585711,
|
|
"loss": 6.8795,
|
|
"mean_token_accuracy": 0.11511812061071396,
|
|
"num_tokens": 8446696.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.973077297210693,
|
|
"epoch": 0.49361037947517317,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004989727778569893,
|
|
"loss": 6.9693,
|
|
"mean_token_accuracy": 0.11310434341430664,
|
|
"num_tokens": 8464827.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.9201208591461185,
|
|
"epoch": 0.4945858940591162,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004989660537695859,
|
|
"loss": 6.9251,
|
|
"mean_token_accuracy": 0.11566059663891792,
|
|
"num_tokens": 8480185.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.761337852478027,
|
|
"epoch": 0.4955614086430592,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000498959307797018,
|
|
"loss": 6.8128,
|
|
"mean_token_accuracy": 0.12708098366856574,
|
|
"num_tokens": 8497511.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.904820108413697,
|
|
"epoch": 0.49653692322700227,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004989525399399447,
|
|
"loss": 6.8702,
|
|
"mean_token_accuracy": 0.11620474085211754,
|
|
"num_tokens": 8514394.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.879853820800781,
|
|
"epoch": 0.4975124378109453,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004989457501990275,
|
|
"loss": 6.8792,
|
|
"mean_token_accuracy": 0.11609909012913704,
|
|
"num_tokens": 8531659.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.903630208969116,
|
|
"epoch": 0.4984879523948883,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004989389385749297,
|
|
"loss": 6.9287,
|
|
"mean_token_accuracy": 0.11620916053652763,
|
|
"num_tokens": 8547986.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.872329998016357,
|
|
"epoch": 0.4994634669788313,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004989321050683169,
|
|
"loss": 6.8751,
|
|
"mean_token_accuracy": 0.11848173439502716,
|
|
"num_tokens": 8565021.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.9056610584259035,
|
|
"epoch": 0.5004389815627743,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000498925249679857,
|
|
"loss": 6.8744,
|
|
"mean_token_accuracy": 0.11459636986255646,
|
|
"num_tokens": 8582135.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.792390298843384,
|
|
"epoch": 0.5014144961467174,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004989183724102196,
|
|
"loss": 6.8993,
|
|
"mean_token_accuracy": 0.11787593364715576,
|
|
"num_tokens": 8599946.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.958661413192749,
|
|
"epoch": 0.5023900107306605,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004989114732600771,
|
|
"loss": 6.923,
|
|
"mean_token_accuracy": 0.11336629018187523,
|
|
"num_tokens": 8615831.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.779950428009033,
|
|
"epoch": 0.5033655253146034,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004989045522301033,
|
|
"loss": 6.8112,
|
|
"mean_token_accuracy": 0.11558634489774704,
|
|
"num_tokens": 8631886.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.94764461517334,
|
|
"epoch": 0.5043410398985465,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004988976093209747,
|
|
"loss": 6.8613,
|
|
"mean_token_accuracy": 0.11486466601490974,
|
|
"num_tokens": 8647520.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.8138525009155275,
|
|
"epoch": 0.5053165544824895,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004988906445333698,
|
|
"loss": 6.7713,
|
|
"mean_token_accuracy": 0.12794217690825463,
|
|
"num_tokens": 8663995.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.822241306304932,
|
|
"epoch": 0.5062920690664325,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004988836578679691,
|
|
"loss": 6.8511,
|
|
"mean_token_accuracy": 0.11445828303694724,
|
|
"num_tokens": 8680201.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.8948572158813475,
|
|
"epoch": 0.5072675836503756,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004988766493254552,
|
|
"loss": 6.8433,
|
|
"mean_token_accuracy": 0.12341629490256309,
|
|
"num_tokens": 8696978.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.804700136184692,
|
|
"epoch": 0.5082430982343186,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000498869618906513,
|
|
"loss": 6.8946,
|
|
"mean_token_accuracy": 0.11857298016548157,
|
|
"num_tokens": 8713335.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.870307731628418,
|
|
"epoch": 0.5092186128182616,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004988625666118296,
|
|
"loss": 6.8823,
|
|
"mean_token_accuracy": 0.1196676455438137,
|
|
"num_tokens": 8730722.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.774832820892334,
|
|
"epoch": 0.5101941274022047,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000498855492442094,
|
|
"loss": 6.7952,
|
|
"mean_token_accuracy": 0.12054291889071464,
|
|
"num_tokens": 8747430.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.9103686809539795,
|
|
"epoch": 0.5111696419861477,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004988483963979975,
|
|
"loss": 6.8884,
|
|
"mean_token_accuracy": 0.11560614630579949,
|
|
"num_tokens": 8764817.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.927261114120483,
|
|
"epoch": 0.5121451565700907,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004988412784802336,
|
|
"loss": 6.9015,
|
|
"mean_token_accuracy": 0.11360720023512841,
|
|
"num_tokens": 8780412.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.932803821563721,
|
|
"epoch": 0.5131206711540337,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004988341386894977,
|
|
"loss": 6.9679,
|
|
"mean_token_accuracy": 0.1152969904243946,
|
|
"num_tokens": 8795526.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.7840962409973145,
|
|
"epoch": 0.5140961857379768,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004988269770264876,
|
|
"loss": 6.7672,
|
|
"mean_token_accuracy": 0.12347180098295212,
|
|
"num_tokens": 8813568.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.938270092010498,
|
|
"epoch": 0.5150717003219198,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004988197934919029,
|
|
"loss": 6.9232,
|
|
"mean_token_accuracy": 0.1144092097878456,
|
|
"num_tokens": 8831807.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.955628967285156,
|
|
"epoch": 0.5160472149058628,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004988125880864458,
|
|
"loss": 6.9261,
|
|
"mean_token_accuracy": 0.11702951192855834,
|
|
"num_tokens": 8848875.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.676701450347901,
|
|
"epoch": 0.5170227294898059,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004988053608108203,
|
|
"loss": 6.6355,
|
|
"mean_token_accuracy": 0.12377685308456421,
|
|
"num_tokens": 8866317.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.782362079620361,
|
|
"epoch": 0.517998244073749,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004987981116657325,
|
|
"loss": 6.7683,
|
|
"mean_token_accuracy": 0.11874385476112366,
|
|
"num_tokens": 8882543.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.862992858886718,
|
|
"epoch": 0.5189737586576919,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004987908406518909,
|
|
"loss": 6.7972,
|
|
"mean_token_accuracy": 0.11631387770175934,
|
|
"num_tokens": 8898640.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.851989984512329,
|
|
"epoch": 0.519949273241635,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000498783547770006,
|
|
"loss": 6.9017,
|
|
"mean_token_accuracy": 0.11561635807156563,
|
|
"num_tokens": 8914649.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.909957075119019,
|
|
"epoch": 0.5209247878255779,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004987762330207903,
|
|
"loss": 6.9236,
|
|
"mean_token_accuracy": 0.11679632440209389,
|
|
"num_tokens": 8931585.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.771302366256714,
|
|
"epoch": 0.521900302409521,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004987688964049587,
|
|
"loss": 6.7928,
|
|
"mean_token_accuracy": 0.12180419787764549,
|
|
"num_tokens": 8948827.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.790069627761841,
|
|
"epoch": 0.5228758169934641,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000498761537923228,
|
|
"loss": 6.7745,
|
|
"mean_token_accuracy": 0.1269575834274292,
|
|
"num_tokens": 8965680.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.952053117752075,
|
|
"epoch": 0.523851331577407,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004987541575763175,
|
|
"loss": 6.9065,
|
|
"mean_token_accuracy": 0.11049905940890312,
|
|
"num_tokens": 8982813.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.867544031143188,
|
|
"epoch": 0.5248268461613501,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000498746755364948,
|
|
"loss": 6.8833,
|
|
"mean_token_accuracy": 0.11713560670614243,
|
|
"num_tokens": 9000497.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.830367136001587,
|
|
"epoch": 0.5258023607452932,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004987393312898431,
|
|
"loss": 6.8102,
|
|
"mean_token_accuracy": 0.11786004677414894,
|
|
"num_tokens": 9016195.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.761811113357544,
|
|
"epoch": 0.5267778753292361,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004987318853517282,
|
|
"loss": 6.7723,
|
|
"mean_token_accuracy": 0.12615545392036437,
|
|
"num_tokens": 9033295.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.844594049453735,
|
|
"epoch": 0.5277533899131792,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004987244175513308,
|
|
"loss": 6.872,
|
|
"mean_token_accuracy": 0.1141127772629261,
|
|
"num_tokens": 9050725.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.833688688278198,
|
|
"epoch": 0.5287289044971223,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004987169278893807,
|
|
"loss": 6.8168,
|
|
"mean_token_accuracy": 0.11935415118932724,
|
|
"num_tokens": 9067842.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.86349515914917,
|
|
"epoch": 0.5297044190810652,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004987094163666098,
|
|
"loss": 6.8351,
|
|
"mean_token_accuracy": 0.11330854967236519,
|
|
"num_tokens": 9084602.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.789287185668945,
|
|
"epoch": 0.5306799336650083,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000498701882983752,
|
|
"loss": 6.7657,
|
|
"mean_token_accuracy": 0.12709601148962973,
|
|
"num_tokens": 9100530.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.867527198791504,
|
|
"epoch": 0.5316554482489513,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004986943277415435,
|
|
"loss": 6.8614,
|
|
"mean_token_accuracy": 0.12204445227980613,
|
|
"num_tokens": 9117304.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.752386522293091,
|
|
"epoch": 0.5326309628328944,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004986867506407225,
|
|
"loss": 6.806,
|
|
"mean_token_accuracy": 0.13167238086462021,
|
|
"num_tokens": 9133974.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.860329008102417,
|
|
"epoch": 0.5336064774168374,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004986791516820295,
|
|
"loss": 6.772,
|
|
"mean_token_accuracy": 0.12175974771380424,
|
|
"num_tokens": 9150600.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.737002849578857,
|
|
"epoch": 0.5345819920007804,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.000498671530866207,
|
|
"loss": 6.7722,
|
|
"mean_token_accuracy": 0.11789723262190818,
|
|
"num_tokens": 9167449.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.818783092498779,
|
|
"epoch": 0.5355575065847235,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004986638881939997,
|
|
"loss": 6.7219,
|
|
"mean_token_accuracy": 0.12201179042458535,
|
|
"num_tokens": 9184570.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.784221220016479,
|
|
"epoch": 0.5365330211686665,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004986562236661544,
|
|
"loss": 6.9045,
|
|
"mean_token_accuracy": 0.10912108793854713,
|
|
"num_tokens": 9200537.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.902917003631591,
|
|
"epoch": 0.5375085357526095,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.00049864853728342,
|
|
"loss": 6.8037,
|
|
"mean_token_accuracy": 0.12473463490605355,
|
|
"num_tokens": 9217252.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.864479970932007,
|
|
"epoch": 0.5384840503365526,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004986408290465476,
|
|
"loss": 6.8555,
|
|
"mean_token_accuracy": 0.11590055152773857,
|
|
"num_tokens": 9234108.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.812731981277466,
|
|
"epoch": 0.5394595649204955,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004986330989562906,
|
|
"loss": 6.7575,
|
|
"mean_token_accuracy": 0.12097472175955773,
|
|
"num_tokens": 9251017.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.7629071235656735,
|
|
"epoch": 0.5404350795044386,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004986253470134042,
|
|
"loss": 6.7091,
|
|
"mean_token_accuracy": 0.1275697208940983,
|
|
"num_tokens": 9267922.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.700593709945679,
|
|
"epoch": 0.5414105940883817,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004986175732186459,
|
|
"loss": 6.703,
|
|
"mean_token_accuracy": 0.13123294040560723,
|
|
"num_tokens": 9284954.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.885139465332031,
|
|
"epoch": 0.5423861086723246,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004986097775727752,
|
|
"loss": 6.8334,
|
|
"mean_token_accuracy": 0.12190918251872063,
|
|
"num_tokens": 9303306.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.733374404907226,
|
|
"epoch": 0.5433616232562677,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004986019600765541,
|
|
"loss": 6.7219,
|
|
"mean_token_accuracy": 0.12711875960230828,
|
|
"num_tokens": 9319754.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.743921375274658,
|
|
"epoch": 0.5443371378402108,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004985941207307462,
|
|
"loss": 6.8122,
|
|
"mean_token_accuracy": 0.12274460345506669,
|
|
"num_tokens": 9335736.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.8163683891296385,
|
|
"epoch": 0.5453126524241537,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985862595361179,
|
|
"loss": 6.7784,
|
|
"mean_token_accuracy": 0.12290315851569175,
|
|
"num_tokens": 9350435.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.86185622215271,
|
|
"epoch": 0.5462881670080968,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004985783764934372,
|
|
"loss": 6.8427,
|
|
"mean_token_accuracy": 0.11779003739356994,
|
|
"num_tokens": 9367613.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.787689065933227,
|
|
"epoch": 0.5472636815920398,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004985704716034744,
|
|
"loss": 6.749,
|
|
"mean_token_accuracy": 0.1232517659664154,
|
|
"num_tokens": 9385590.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.836340427398682,
|
|
"epoch": 0.5482391961759828,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004985625448670019,
|
|
"loss": 6.8774,
|
|
"mean_token_accuracy": 0.11052649319171906,
|
|
"num_tokens": 9403286.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.910646963119507,
|
|
"epoch": 0.5492147107599259,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004985545962847943,
|
|
"loss": 6.8702,
|
|
"mean_token_accuracy": 0.1125256858766079,
|
|
"num_tokens": 9419880.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.7993169784545895,
|
|
"epoch": 0.5501902253438689,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004985466258576283,
|
|
"loss": 6.8319,
|
|
"mean_token_accuracy": 0.11432699039578438,
|
|
"num_tokens": 9436579.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.884487915039062,
|
|
"epoch": 0.5511657399278119,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004985386335862829,
|
|
"loss": 6.8841,
|
|
"mean_token_accuracy": 0.11265967264771462,
|
|
"num_tokens": 9452802.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.851714277267456,
|
|
"epoch": 0.552141254511755,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985306194715387,
|
|
"loss": 6.8927,
|
|
"mean_token_accuracy": 0.11446214690804482,
|
|
"num_tokens": 9468297.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.883763599395752,
|
|
"epoch": 0.553116769095698,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004985225835141792,
|
|
"loss": 6.8999,
|
|
"mean_token_accuracy": 0.11260369718074799,
|
|
"num_tokens": 9484954.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.9504420280456545,
|
|
"epoch": 0.554092283679641,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004985145257149895,
|
|
"loss": 6.9496,
|
|
"mean_token_accuracy": 0.1100885510444641,
|
|
"num_tokens": 9502211.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.860951280593872,
|
|
"epoch": 0.555067798263584,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004985064460747569,
|
|
"loss": 6.8337,
|
|
"mean_token_accuracy": 0.11309531480073928,
|
|
"num_tokens": 9518103.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.764395809173584,
|
|
"epoch": 0.5560433128475271,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000498498344594271,
|
|
"loss": 6.7779,
|
|
"mean_token_accuracy": 0.11637641638517379,
|
|
"num_tokens": 9534155.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.738689994812011,
|
|
"epoch": 0.5570188274314701,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004984902212743234,
|
|
"loss": 6.7507,
|
|
"mean_token_accuracy": 0.12972750812768935,
|
|
"num_tokens": 9549972.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.696974754333496,
|
|
"epoch": 0.5579943420154131,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004984820761157079,
|
|
"loss": 6.6617,
|
|
"mean_token_accuracy": 0.13014516234397888,
|
|
"num_tokens": 9567306.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.883365678787231,
|
|
"epoch": 0.5589698565993562,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004984739091192205,
|
|
"loss": 6.885,
|
|
"mean_token_accuracy": 0.11657564714550972,
|
|
"num_tokens": 9583488.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.694728088378906,
|
|
"epoch": 0.5599453711832992,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004984657202856592,
|
|
"loss": 6.6662,
|
|
"mean_token_accuracy": 0.13098273277282715,
|
|
"num_tokens": 9600030.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.725077056884766,
|
|
"epoch": 0.5609208857672422,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000498457509615824,
|
|
"loss": 6.7896,
|
|
"mean_token_accuracy": 0.12264834940433503,
|
|
"num_tokens": 9615791.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.910763216018677,
|
|
"epoch": 0.5618964003511853,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004984492771105175,
|
|
"loss": 6.8578,
|
|
"mean_token_accuracy": 0.11508372128009796,
|
|
"num_tokens": 9630955.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.71947979927063,
|
|
"epoch": 0.5628719149351282,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004984410227705439,
|
|
"loss": 6.7604,
|
|
"mean_token_accuracy": 0.1295547068119049,
|
|
"num_tokens": 9647743.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.745148420333862,
|
|
"epoch": 0.5638474295190713,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004984327465967101,
|
|
"loss": 6.7171,
|
|
"mean_token_accuracy": 0.12684635668992997,
|
|
"num_tokens": 9665495.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.785642194747925,
|
|
"epoch": 0.5648229441030144,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004984244485898246,
|
|
"loss": 6.7367,
|
|
"mean_token_accuracy": 0.12310076728463173,
|
|
"num_tokens": 9683489.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.579546022415161,
|
|
"epoch": 0.5657984586869573,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004984161287506982,
|
|
"loss": 6.6762,
|
|
"mean_token_accuracy": 0.1427179493010044,
|
|
"num_tokens": 9700491.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.925921773910522,
|
|
"epoch": 0.5667739732709004,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000498407787080144,
|
|
"loss": 6.8309,
|
|
"mean_token_accuracy": 0.11485328450798989,
|
|
"num_tokens": 9715694.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.817408847808838,
|
|
"epoch": 0.5677494878548435,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000498399423578977,
|
|
"loss": 6.8899,
|
|
"mean_token_accuracy": 0.11257752552628517,
|
|
"num_tokens": 9731317.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.870456409454346,
|
|
"epoch": 0.5687250024387864,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004983910382480146,
|
|
"loss": 6.8671,
|
|
"mean_token_accuracy": 0.11242569237947464,
|
|
"num_tokens": 9747928.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.837937736511231,
|
|
"epoch": 0.5697005170227295,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004983826310880762,
|
|
"loss": 6.8039,
|
|
"mean_token_accuracy": 0.11309616193175316,
|
|
"num_tokens": 9765454.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.897300434112549,
|
|
"epoch": 0.5706760316066726,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004983742020999832,
|
|
"loss": 6.8669,
|
|
"mean_token_accuracy": 0.10900059267878533,
|
|
"num_tokens": 9782255.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.696663665771484,
|
|
"epoch": 0.5716515461906155,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004983657512845593,
|
|
"loss": 6.6753,
|
|
"mean_token_accuracy": 0.12878145053982734,
|
|
"num_tokens": 9798680.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.806471347808838,
|
|
"epoch": 0.5726270607745586,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004983572786426302,
|
|
"loss": 6.8175,
|
|
"mean_token_accuracy": 0.11593940034508705,
|
|
"num_tokens": 9813955.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.701576662063599,
|
|
"epoch": 0.5736025753585016,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004983487841750239,
|
|
"loss": 6.711,
|
|
"mean_token_accuracy": 0.129136098921299,
|
|
"num_tokens": 9830692.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.839662647247314,
|
|
"epoch": 0.5745780899424446,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004983402678825705,
|
|
"loss": 6.8308,
|
|
"mean_token_accuracy": 0.11594207361340522,
|
|
"num_tokens": 9848825.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.809984397888184,
|
|
"epoch": 0.5755536045263877,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004983317297661021,
|
|
"loss": 6.8305,
|
|
"mean_token_accuracy": 0.12007160931825638,
|
|
"num_tokens": 9865802.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.848187828063965,
|
|
"epoch": 0.5765291191103307,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004983231698264531,
|
|
"loss": 6.8632,
|
|
"mean_token_accuracy": 0.11418323591351509,
|
|
"num_tokens": 9883540.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.871307277679444,
|
|
"epoch": 0.5775046336942737,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004983145880644597,
|
|
"loss": 6.8059,
|
|
"mean_token_accuracy": 0.1159649781882763,
|
|
"num_tokens": 9897724.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.807016468048095,
|
|
"epoch": 0.5784801482782168,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004983059844809608,
|
|
"loss": 6.7525,
|
|
"mean_token_accuracy": 0.12290950119495392,
|
|
"num_tokens": 9914710.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.785981321334839,
|
|
"epoch": 0.5794556628621598,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004982973590767969,
|
|
"loss": 6.8696,
|
|
"mean_token_accuracy": 0.12116017490625382,
|
|
"num_tokens": 9932362.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.751751852035523,
|
|
"epoch": 0.5804311774461028,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000498288711852811,
|
|
"loss": 6.6607,
|
|
"mean_token_accuracy": 0.12567465156316757,
|
|
"num_tokens": 9949409.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.827619361877441,
|
|
"epoch": 0.5814066920300458,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000498280042809848,
|
|
"loss": 6.8126,
|
|
"mean_token_accuracy": 0.11727285012602806,
|
|
"num_tokens": 9967467.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.7890321731567385,
|
|
"epoch": 0.5823822066139889,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004982713519487549,
|
|
"loss": 6.7552,
|
|
"mean_token_accuracy": 0.1225271537899971,
|
|
"num_tokens": 9983082.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.790068006515503,
|
|
"epoch": 0.5833577211979319,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004982626392703812,
|
|
"loss": 6.8259,
|
|
"mean_token_accuracy": 0.11854807063937187,
|
|
"num_tokens": 10000046.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.802617406845092,
|
|
"epoch": 0.5843332357818749,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000498253904775578,
|
|
"loss": 6.7577,
|
|
"mean_token_accuracy": 0.11755326986312867,
|
|
"num_tokens": 10014674.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.694525718688965,
|
|
"epoch": 0.585308750365818,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004982451484651988,
|
|
"loss": 6.6491,
|
|
"mean_token_accuracy": 0.12509795725345613,
|
|
"num_tokens": 10030647.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.585308750365818,
|
|
"eval_entropy": 6.631029434728553,
|
|
"eval_loss": 6.8121867179870605,
|
|
"eval_mean_token_accuracy": 0.12184531028524896,
|
|
"eval_num_tokens": 10030647.0,
|
|
"eval_runtime": 15.3329,
|
|
"eval_samples_per_second": 1081.139,
|
|
"eval_steps_per_second": 135.199,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"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": 1.3581706696704e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|