3ad58af383
Model: fpadovani/zho-hans-100mb-after-ppt-shuff-dyck-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": 4.490693664550781,
|
|
"epoch": 0.0009755145839430299,
|
|
"grad_norm": 30.5,
|
|
"learning_rate": 2e-06,
|
|
"loss": 13.5237,
|
|
"mean_token_accuracy": 0.01689293053932488,
|
|
"num_tokens": 17120.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.48514404296875,
|
|
"epoch": 0.0019510291678860598,
|
|
"grad_norm": 30.875,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 13.421,
|
|
"mean_token_accuracy": 0.018032675329595804,
|
|
"num_tokens": 34182.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.931977891921997,
|
|
"epoch": 0.0029265437518290896,
|
|
"grad_norm": 36.5,
|
|
"learning_rate": 7e-06,
|
|
"loss": 13.0743,
|
|
"mean_token_accuracy": 0.012429539114236832,
|
|
"num_tokens": 51205.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 6.637991285324096,
|
|
"epoch": 0.0039020583357721197,
|
|
"grad_norm": 29.125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 12.1322,
|
|
"mean_token_accuracy": 0.008806258952245117,
|
|
"num_tokens": 67722.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 9.740472221374512,
|
|
"epoch": 0.00487757291971515,
|
|
"grad_norm": 10.8125,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 11.0704,
|
|
"mean_token_accuracy": 0.007681116322055459,
|
|
"num_tokens": 84230.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.419333457946777,
|
|
"epoch": 0.005853087503658179,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.7923,
|
|
"mean_token_accuracy": 0.011759244091808795,
|
|
"num_tokens": 100967.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.586559581756593,
|
|
"epoch": 0.00682860208760121,
|
|
"grad_norm": 3.84375,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.5501,
|
|
"mean_token_accuracy": 0.061883827298879625,
|
|
"num_tokens": 117450.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.333465480804444,
|
|
"epoch": 0.007804116671544239,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.2155,
|
|
"mean_token_accuracy": 0.07655484415590763,
|
|
"num_tokens": 135328.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.046442413330078,
|
|
"epoch": 0.00877963125548727,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.0231,
|
|
"mean_token_accuracy": 0.07796396911144257,
|
|
"num_tokens": 152571.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.165653514862061,
|
|
"epoch": 0.0097551458394303,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.8849,
|
|
"mean_token_accuracy": 0.08077023848891259,
|
|
"num_tokens": 170216.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.36428689956665,
|
|
"epoch": 0.010730660423373329,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.7759,
|
|
"mean_token_accuracy": 0.0794611006975174,
|
|
"num_tokens": 186513.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.221637153625489,
|
|
"epoch": 0.011706175007316359,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.7436,
|
|
"mean_token_accuracy": 0.07498926073312759,
|
|
"num_tokens": 202600.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.093542098999023,
|
|
"epoch": 0.01268168959125939,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.6498,
|
|
"mean_token_accuracy": 0.08184118494391442,
|
|
"num_tokens": 220270.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.226324462890625,
|
|
"epoch": 0.01365720417520242,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.5928,
|
|
"mean_token_accuracy": 0.0831097610294819,
|
|
"num_tokens": 236810.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.119788265228271,
|
|
"epoch": 0.014632718759145449,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.5686,
|
|
"mean_token_accuracy": 0.07497851252555847,
|
|
"num_tokens": 252559.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.039910221099854,
|
|
"epoch": 0.015608233343088479,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.4446,
|
|
"mean_token_accuracy": 0.08544577062129974,
|
|
"num_tokens": 268507.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.107688331604004,
|
|
"epoch": 0.01658374792703151,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.4306,
|
|
"mean_token_accuracy": 0.08484108000993729,
|
|
"num_tokens": 284776.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.037123680114746,
|
|
"epoch": 0.01755926251097454,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.3856,
|
|
"mean_token_accuracy": 0.08017717525362969,
|
|
"num_tokens": 300937.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.079811477661133,
|
|
"epoch": 0.01853477709491757,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.2975,
|
|
"mean_token_accuracy": 0.0832655370235443,
|
|
"num_tokens": 317464.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 9.896672248840332,
|
|
"epoch": 0.0195102916788606,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.1675,
|
|
"mean_token_accuracy": 0.08660522624850273,
|
|
"num_tokens": 334022.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 9.873467636108398,
|
|
"epoch": 0.02048580626280363,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.1306,
|
|
"mean_token_accuracy": 0.08643193244934082,
|
|
"num_tokens": 350545.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 9.815353202819825,
|
|
"epoch": 0.021461320846746658,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.0525,
|
|
"mean_token_accuracy": 0.0924916334450245,
|
|
"num_tokens": 368878.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 9.754250431060791,
|
|
"epoch": 0.022436835430689687,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.034,
|
|
"mean_token_accuracy": 0.08547283411026001,
|
|
"num_tokens": 388381.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.797440242767333,
|
|
"epoch": 0.023412350014632717,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.9648,
|
|
"mean_token_accuracy": 0.07924327179789543,
|
|
"num_tokens": 403727.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.65400218963623,
|
|
"epoch": 0.02438786459857575,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.9086,
|
|
"mean_token_accuracy": 0.08146455883979797,
|
|
"num_tokens": 419046.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.547494602203368,
|
|
"epoch": 0.02536337918251878,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.805,
|
|
"mean_token_accuracy": 0.08776633739471436,
|
|
"num_tokens": 435186.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.431383323669433,
|
|
"epoch": 0.02633889376646181,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.7668,
|
|
"mean_token_accuracy": 0.0854455754160881,
|
|
"num_tokens": 451552.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.342393016815185,
|
|
"epoch": 0.02731440835040484,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.7312,
|
|
"mean_token_accuracy": 0.08847364038228989,
|
|
"num_tokens": 468006.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.34831943511963,
|
|
"epoch": 0.02828992293434787,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.6737,
|
|
"mean_token_accuracy": 0.08393737226724625,
|
|
"num_tokens": 484381.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.162296390533447,
|
|
"epoch": 0.029265437518290898,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.68,
|
|
"mean_token_accuracy": 0.0858243778347969,
|
|
"num_tokens": 501309.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.130147743225098,
|
|
"epoch": 0.030240952102233928,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.6269,
|
|
"mean_token_accuracy": 0.08063350766897201,
|
|
"num_tokens": 518290.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.100608634948731,
|
|
"epoch": 0.031216466686176957,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.5909,
|
|
"mean_token_accuracy": 0.08441304340958596,
|
|
"num_tokens": 533700.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.903340816497803,
|
|
"epoch": 0.03219198127011999,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 8.4616,
|
|
"mean_token_accuracy": 0.09071405306458473,
|
|
"num_tokens": 548935.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.944788551330566,
|
|
"epoch": 0.03316749585406302,
|
|
"grad_norm": 0.6640625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 8.5225,
|
|
"mean_token_accuracy": 0.08350471183657646,
|
|
"num_tokens": 565869.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.891490459442139,
|
|
"epoch": 0.03414301043800605,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 8.5397,
|
|
"mean_token_accuracy": 0.0859730139374733,
|
|
"num_tokens": 583065.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.781160163879395,
|
|
"epoch": 0.03511852502194908,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 8.5389,
|
|
"mean_token_accuracy": 0.08567977696657181,
|
|
"num_tokens": 599875.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.857763767242432,
|
|
"epoch": 0.03609403960589211,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 8.502,
|
|
"mean_token_accuracy": 0.08799432292580604,
|
|
"num_tokens": 616296.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.845306587219238,
|
|
"epoch": 0.03706955418983514,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 8.4613,
|
|
"mean_token_accuracy": 0.08114315047860146,
|
|
"num_tokens": 632548.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.763722133636474,
|
|
"epoch": 0.03804506877377817,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 8.4714,
|
|
"mean_token_accuracy": 0.08705383539199829,
|
|
"num_tokens": 650395.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.692799091339111,
|
|
"epoch": 0.0390205833577212,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 8.4872,
|
|
"mean_token_accuracy": 0.09539326205849648,
|
|
"num_tokens": 668453.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.626627922058105,
|
|
"epoch": 0.03999609794166423,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 8.3857,
|
|
"mean_token_accuracy": 0.08746680319309234,
|
|
"num_tokens": 683914.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.74559440612793,
|
|
"epoch": 0.04097161252560726,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 8.4933,
|
|
"mean_token_accuracy": 0.08703801408410072,
|
|
"num_tokens": 700480.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.703277587890625,
|
|
"epoch": 0.041947127109550286,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.000107,
|
|
"loss": 8.472,
|
|
"mean_token_accuracy": 0.08402965739369392,
|
|
"num_tokens": 716604.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.640272426605225,
|
|
"epoch": 0.042922641693493316,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 8.4605,
|
|
"mean_token_accuracy": 0.08894563764333725,
|
|
"num_tokens": 732697.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.721662902832032,
|
|
"epoch": 0.043898156277436345,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 8.5299,
|
|
"mean_token_accuracy": 0.08261891677975655,
|
|
"num_tokens": 749072.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.660103130340577,
|
|
"epoch": 0.044873670861379375,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 8.4681,
|
|
"mean_token_accuracy": 0.08579774647951126,
|
|
"num_tokens": 767826.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.619204425811768,
|
|
"epoch": 0.045849185445322405,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 8.3936,
|
|
"mean_token_accuracy": 0.0902378536760807,
|
|
"num_tokens": 786863.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.532190132141114,
|
|
"epoch": 0.046824700029265434,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 8.3713,
|
|
"mean_token_accuracy": 0.10228274986147881,
|
|
"num_tokens": 803925.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.610904693603516,
|
|
"epoch": 0.04780021461320847,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 8.4531,
|
|
"mean_token_accuracy": 0.09021551758050919,
|
|
"num_tokens": 822088.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.60029354095459,
|
|
"epoch": 0.0487757291971515,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 8.453,
|
|
"mean_token_accuracy": 0.08811493217945099,
|
|
"num_tokens": 837991.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.63068675994873,
|
|
"epoch": 0.04975124378109453,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 8.3579,
|
|
"mean_token_accuracy": 0.09977038279175758,
|
|
"num_tokens": 855593.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.618537425994873,
|
|
"epoch": 0.05072675836503756,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 8.4751,
|
|
"mean_token_accuracy": 0.08795029670000076,
|
|
"num_tokens": 873696.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.56423215866089,
|
|
"epoch": 0.05170227294898059,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 8.3553,
|
|
"mean_token_accuracy": 0.09531263113021851,
|
|
"num_tokens": 890023.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.592487812042236,
|
|
"epoch": 0.05267778753292362,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 8.4957,
|
|
"mean_token_accuracy": 0.086310463398695,
|
|
"num_tokens": 906492.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.64133062362671,
|
|
"epoch": 0.05365330211686665,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 8.434,
|
|
"mean_token_accuracy": 0.08785242363810539,
|
|
"num_tokens": 921837.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.58052043914795,
|
|
"epoch": 0.05462881670080968,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 8.377,
|
|
"mean_token_accuracy": 0.09836494624614715,
|
|
"num_tokens": 938771.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.553132820129395,
|
|
"epoch": 0.05560433128475271,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 8.3995,
|
|
"mean_token_accuracy": 0.08714988306164742,
|
|
"num_tokens": 954562.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.662264537811279,
|
|
"epoch": 0.05657984586869574,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 8.343,
|
|
"mean_token_accuracy": 0.09556876793503762,
|
|
"num_tokens": 973700.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.443976783752442,
|
|
"epoch": 0.05755536045263877,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.000147,
|
|
"loss": 8.3889,
|
|
"mean_token_accuracy": 0.08947161361575126,
|
|
"num_tokens": 990688.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.586378479003907,
|
|
"epoch": 0.058530875036581796,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 8.4625,
|
|
"mean_token_accuracy": 0.08533673211932183,
|
|
"num_tokens": 1008144.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.544894409179687,
|
|
"epoch": 0.059506389620524826,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 8.4238,
|
|
"mean_token_accuracy": 0.08675077632069587,
|
|
"num_tokens": 1027379.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.509546852111816,
|
|
"epoch": 0.060481904204467855,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 8.3964,
|
|
"mean_token_accuracy": 0.09509446248412132,
|
|
"num_tokens": 1043999.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.641741275787354,
|
|
"epoch": 0.061457418788410885,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 8.4003,
|
|
"mean_token_accuracy": 0.08781646862626076,
|
|
"num_tokens": 1062237.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.513209438323974,
|
|
"epoch": 0.062432933372353915,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 8.3329,
|
|
"mean_token_accuracy": 0.09510535821318626,
|
|
"num_tokens": 1078092.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.517814922332764,
|
|
"epoch": 0.06340844795629695,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 8.389,
|
|
"mean_token_accuracy": 0.09345002174377441,
|
|
"num_tokens": 1095124.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.54736795425415,
|
|
"epoch": 0.06438396254023998,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 8.3712,
|
|
"mean_token_accuracy": 0.09042947217822075,
|
|
"num_tokens": 1112775.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.515040588378906,
|
|
"epoch": 0.06535947712418301,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 8.3097,
|
|
"mean_token_accuracy": 0.09608379825949669,
|
|
"num_tokens": 1129726.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.47906036376953,
|
|
"epoch": 0.06633499170812604,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 8.3571,
|
|
"mean_token_accuracy": 0.09651407599449158,
|
|
"num_tokens": 1144034.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.513033390045166,
|
|
"epoch": 0.06731050629206907,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 8.3097,
|
|
"mean_token_accuracy": 0.0950991727411747,
|
|
"num_tokens": 1159633.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.47611141204834,
|
|
"epoch": 0.0682860208760121,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 8.2604,
|
|
"mean_token_accuracy": 0.09262074902653694,
|
|
"num_tokens": 1175350.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.391336727142335,
|
|
"epoch": 0.06926153545995513,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 8.188,
|
|
"mean_token_accuracy": 0.09829908162355423,
|
|
"num_tokens": 1193121.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.497109603881835,
|
|
"epoch": 0.07023705004389816,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 8.3481,
|
|
"mean_token_accuracy": 0.09156165719032287,
|
|
"num_tokens": 1209896.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.4661789894104,
|
|
"epoch": 0.07121256462784119,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000182,
|
|
"loss": 8.3448,
|
|
"mean_token_accuracy": 0.08826714232563973,
|
|
"num_tokens": 1227011.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.423711013793945,
|
|
"epoch": 0.07218807921178422,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 8.263,
|
|
"mean_token_accuracy": 0.09375467002391816,
|
|
"num_tokens": 1241595.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 8.45018196105957,
|
|
"epoch": 0.07316359379572725,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 8.2753,
|
|
"mean_token_accuracy": 0.08940806537866593,
|
|
"num_tokens": 1256919.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.34131474494934,
|
|
"epoch": 0.07413910837967028,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 8.267,
|
|
"mean_token_accuracy": 0.10843634009361267,
|
|
"num_tokens": 1274344.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 8.417487525939942,
|
|
"epoch": 0.0751146229636133,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 8.2498,
|
|
"mean_token_accuracy": 0.09864807277917861,
|
|
"num_tokens": 1290252.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.479813480377198,
|
|
"epoch": 0.07609013754755634,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 8.3017,
|
|
"mean_token_accuracy": 0.09188697189092636,
|
|
"num_tokens": 1306987.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 8.460020828247071,
|
|
"epoch": 0.07706565213149937,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 8.3412,
|
|
"mean_token_accuracy": 0.0870269738137722,
|
|
"num_tokens": 1323031.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 8.439099597930909,
|
|
"epoch": 0.0780411667154424,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 8.2752,
|
|
"mean_token_accuracy": 0.09002957195043564,
|
|
"num_tokens": 1339592.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.53223638534546,
|
|
"epoch": 0.07901668129938542,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 8.247,
|
|
"mean_token_accuracy": 0.09930683076381683,
|
|
"num_tokens": 1358131.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 8.311397790908813,
|
|
"epoch": 0.07999219588332845,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 8.1704,
|
|
"mean_token_accuracy": 0.10103706270456314,
|
|
"num_tokens": 1375705.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 8.206231212615966,
|
|
"epoch": 0.08096771046727148,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 8.2102,
|
|
"mean_token_accuracy": 0.0998042032122612,
|
|
"num_tokens": 1392736.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 8.423250007629395,
|
|
"epoch": 0.08194322505121451,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 8.2514,
|
|
"mean_token_accuracy": 0.09237718880176544,
|
|
"num_tokens": 1408536.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 8.314301776885987,
|
|
"epoch": 0.08291873963515754,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 8.2075,
|
|
"mean_token_accuracy": 0.09687253460288048,
|
|
"num_tokens": 1425423.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 8.404624748229981,
|
|
"epoch": 0.08389425421910057,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 8.2317,
|
|
"mean_token_accuracy": 0.09046228304505348,
|
|
"num_tokens": 1442420.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 8.372211837768555,
|
|
"epoch": 0.0848697688030436,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 8.162,
|
|
"mean_token_accuracy": 0.0996602401137352,
|
|
"num_tokens": 1458835.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 8.417982482910157,
|
|
"epoch": 0.08584528338698663,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 8.2796,
|
|
"mean_token_accuracy": 0.08996990695595741,
|
|
"num_tokens": 1475563.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 8.326233100891113,
|
|
"epoch": 0.08682079797092966,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000222,
|
|
"loss": 8.2409,
|
|
"mean_token_accuracy": 0.10384741872549057,
|
|
"num_tokens": 1492687.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 8.444601440429688,
|
|
"epoch": 0.08779631255487269,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 8.2404,
|
|
"mean_token_accuracy": 0.09174655601382256,
|
|
"num_tokens": 1508394.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 8.261253166198731,
|
|
"epoch": 0.08877182713881572,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 8.2181,
|
|
"mean_token_accuracy": 0.10230232402682304,
|
|
"num_tokens": 1527112.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 8.32946844100952,
|
|
"epoch": 0.08974734172275875,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 8.2507,
|
|
"mean_token_accuracy": 0.0994840294122696,
|
|
"num_tokens": 1545401.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 8.400847578048706,
|
|
"epoch": 0.09072285630670178,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 8.1099,
|
|
"mean_token_accuracy": 0.09926176220178604,
|
|
"num_tokens": 1561621.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 8.35053997039795,
|
|
"epoch": 0.09169837089064481,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 8.2428,
|
|
"mean_token_accuracy": 0.09348660483956336,
|
|
"num_tokens": 1579225.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 8.344873905181885,
|
|
"epoch": 0.09267388547458784,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000237,
|
|
"loss": 8.1339,
|
|
"mean_token_accuracy": 0.09716273322701455,
|
|
"num_tokens": 1596125.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 8.30934934616089,
|
|
"epoch": 0.09364940005853087,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 8.2589,
|
|
"mean_token_accuracy": 0.0886540800333023,
|
|
"num_tokens": 1613451.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 8.344436740875244,
|
|
"epoch": 0.09462491464247391,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000242,
|
|
"loss": 8.2056,
|
|
"mean_token_accuracy": 0.09579794630408286,
|
|
"num_tokens": 1630929.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 8.309423828125,
|
|
"epoch": 0.09560042922641694,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 8.2009,
|
|
"mean_token_accuracy": 0.0951028324663639,
|
|
"num_tokens": 1647379.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 8.183022069931031,
|
|
"epoch": 0.09657594381035997,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.9719,
|
|
"mean_token_accuracy": 0.11050360500812531,
|
|
"num_tokens": 1664415.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 8.176769638061524,
|
|
"epoch": 0.097551458394303,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 8.0551,
|
|
"mean_token_accuracy": 0.10060225948691368,
|
|
"num_tokens": 1679556.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 8.15018105506897,
|
|
"epoch": 0.09852697297824603,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.9955,
|
|
"mean_token_accuracy": 0.10563117042183875,
|
|
"num_tokens": 1696727.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 8.249298286437988,
|
|
"epoch": 0.09950248756218906,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 8.0332,
|
|
"mean_token_accuracy": 0.11021090745925903,
|
|
"num_tokens": 1713918.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 8.252583122253418,
|
|
"epoch": 0.10047800214613209,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 8.2011,
|
|
"mean_token_accuracy": 0.0905926614999771,
|
|
"num_tokens": 1729581.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 8.262310695648193,
|
|
"epoch": 0.10145351673007512,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 8.0441,
|
|
"mean_token_accuracy": 0.09327254816889763,
|
|
"num_tokens": 1746367.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 8.325894927978515,
|
|
"epoch": 0.10242903131401815,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000262,
|
|
"loss": 8.1618,
|
|
"mean_token_accuracy": 0.09271856918931007,
|
|
"num_tokens": 1765009.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 8.254261589050293,
|
|
"epoch": 0.10340454589796118,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 8.1649,
|
|
"mean_token_accuracy": 0.09503179416060448,
|
|
"num_tokens": 1782113.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 8.215056705474854,
|
|
"epoch": 0.10438006048190421,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 8.0514,
|
|
"mean_token_accuracy": 0.09871876537799835,
|
|
"num_tokens": 1798301.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 8.213224983215332,
|
|
"epoch": 0.10535557506584724,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 8.086,
|
|
"mean_token_accuracy": 0.09899957552552223,
|
|
"num_tokens": 1815059.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 8.175263071060181,
|
|
"epoch": 0.10633108964979027,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.9918,
|
|
"mean_token_accuracy": 0.10212236493825913,
|
|
"num_tokens": 1831699.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 8.153118419647218,
|
|
"epoch": 0.1073066042337333,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 8.066,
|
|
"mean_token_accuracy": 0.09812919944524764,
|
|
"num_tokens": 1847993.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 8.155826520919799,
|
|
"epoch": 0.10828211881767633,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.8979,
|
|
"mean_token_accuracy": 0.11081337481737137,
|
|
"num_tokens": 1864753.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 8.19793872833252,
|
|
"epoch": 0.10925763340161936,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 8.0736,
|
|
"mean_token_accuracy": 0.10154270082712173,
|
|
"num_tokens": 1882154.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 8.117816829681397,
|
|
"epoch": 0.11023314798556239,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.9647,
|
|
"mean_token_accuracy": 0.10528781563043595,
|
|
"num_tokens": 1899683.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 8.081390380859375,
|
|
"epoch": 0.11120866256950541,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.9668,
|
|
"mean_token_accuracy": 0.10001010969281196,
|
|
"num_tokens": 1918489.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 8.130353212356567,
|
|
"epoch": 0.11218417715344844,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 8.011,
|
|
"mean_token_accuracy": 0.09865634441375733,
|
|
"num_tokens": 1935609.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 8.109779262542725,
|
|
"epoch": 0.11315969173739147,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 8.0395,
|
|
"mean_token_accuracy": 0.09440108239650727,
|
|
"num_tokens": 1951311.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 8.174573421478271,
|
|
"epoch": 0.1141352063213345,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 8.1061,
|
|
"mean_token_accuracy": 0.0926342748105526,
|
|
"num_tokens": 1968908.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 8.177379894256593,
|
|
"epoch": 0.11511072090527753,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.9996,
|
|
"mean_token_accuracy": 0.09846640899777412,
|
|
"num_tokens": 1983807.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 8.253669786453248,
|
|
"epoch": 0.11608623548922056,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 8.051,
|
|
"mean_token_accuracy": 0.09801550693809986,
|
|
"num_tokens": 2000219.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 8.11186671257019,
|
|
"epoch": 0.11706175007316359,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.9772,
|
|
"mean_token_accuracy": 0.10445283949375153,
|
|
"num_tokens": 2017360.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 8.043530797958374,
|
|
"epoch": 0.11803726465710662,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.9765,
|
|
"mean_token_accuracy": 0.10461995676159859,
|
|
"num_tokens": 2034953.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 8.068679714202881,
|
|
"epoch": 0.11901277924104965,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.9205,
|
|
"mean_token_accuracy": 0.10359138026833534,
|
|
"num_tokens": 2051551.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 8.153577280044555,
|
|
"epoch": 0.11998829382499268,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.9171,
|
|
"mean_token_accuracy": 0.10637792795896531,
|
|
"num_tokens": 2067188.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 8.009168004989624,
|
|
"epoch": 0.12096380840893571,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.9537,
|
|
"mean_token_accuracy": 0.10119322836399078,
|
|
"num_tokens": 2082569.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 8.181542825698852,
|
|
"epoch": 0.12193932299287874,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 8.024,
|
|
"mean_token_accuracy": 0.09720693081617356,
|
|
"num_tokens": 2099446.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 8.081124019622802,
|
|
"epoch": 0.12291483757682177,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.9494,
|
|
"mean_token_accuracy": 0.10721178874373435,
|
|
"num_tokens": 2116526.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 8.138178634643555,
|
|
"epoch": 0.1238903521607648,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.9943,
|
|
"mean_token_accuracy": 0.09462400078773499,
|
|
"num_tokens": 2134624.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.9849425792694095,
|
|
"epoch": 0.12486586674470783,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.8401,
|
|
"mean_token_accuracy": 0.10716697350144386,
|
|
"num_tokens": 2152872.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 8.098246574401855,
|
|
"epoch": 0.12584138132865086,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.9826,
|
|
"mean_token_accuracy": 0.09792573973536492,
|
|
"num_tokens": 2169480.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 8.041435432434081,
|
|
"epoch": 0.1268168959125939,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.8415,
|
|
"mean_token_accuracy": 0.11095677688717842,
|
|
"num_tokens": 2186054.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 8.054678249359132,
|
|
"epoch": 0.12779241049653692,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.9727,
|
|
"mean_token_accuracy": 0.0941509373486042,
|
|
"num_tokens": 2202320.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.981766939163208,
|
|
"epoch": 0.12876792508047996,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.8641,
|
|
"mean_token_accuracy": 0.10060839653015137,
|
|
"num_tokens": 2218817.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 8.093716478347778,
|
|
"epoch": 0.12974343966442298,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 8.0126,
|
|
"mean_token_accuracy": 0.09739565700292588,
|
|
"num_tokens": 2234845.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 8.075230646133424,
|
|
"epoch": 0.13071895424836602,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.9454,
|
|
"mean_token_accuracy": 0.09940807446837426,
|
|
"num_tokens": 2251904.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.942912292480469,
|
|
"epoch": 0.13169446883230904,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.9409,
|
|
"mean_token_accuracy": 0.10191294699907302,
|
|
"num_tokens": 2268343.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 8.05466251373291,
|
|
"epoch": 0.13266998341625208,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.9356,
|
|
"mean_token_accuracy": 0.09942738711833954,
|
|
"num_tokens": 2284524.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.954032278060913,
|
|
"epoch": 0.1336454980001951,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.8617,
|
|
"mean_token_accuracy": 0.10729206651449204,
|
|
"num_tokens": 2302350.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 8.02203860282898,
|
|
"epoch": 0.13462101258413814,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.9402,
|
|
"mean_token_accuracy": 0.09717295095324516,
|
|
"num_tokens": 2319953.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 8.024251461029053,
|
|
"epoch": 0.13559652716808115,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.8139,
|
|
"mean_token_accuracy": 0.10286439582705498,
|
|
"num_tokens": 2336698.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.851852083206177,
|
|
"epoch": 0.1365720417520242,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.7683,
|
|
"mean_token_accuracy": 0.10691581144928933,
|
|
"num_tokens": 2353986.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.9333963871002195,
|
|
"epoch": 0.1375475563359672,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.8256,
|
|
"mean_token_accuracy": 0.10445680022239685,
|
|
"num_tokens": 2370320.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.971817111968994,
|
|
"epoch": 0.13852307091991026,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.8781,
|
|
"mean_token_accuracy": 0.0994373232126236,
|
|
"num_tokens": 2385453.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.98693323135376,
|
|
"epoch": 0.13949858550385327,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.8666,
|
|
"mean_token_accuracy": 0.10084751695394516,
|
|
"num_tokens": 2401545.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.911950635910034,
|
|
"epoch": 0.14047410008779632,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.8597,
|
|
"mean_token_accuracy": 0.10480492040514947,
|
|
"num_tokens": 2418414.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.9676766872406,
|
|
"epoch": 0.14144961467173933,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.922,
|
|
"mean_token_accuracy": 0.10325973257422447,
|
|
"num_tokens": 2434973.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.979449939727783,
|
|
"epoch": 0.14242512925568238,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.9006,
|
|
"mean_token_accuracy": 0.09724714756011962,
|
|
"num_tokens": 2451053.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.946141576766967,
|
|
"epoch": 0.1434006438396254,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.8747,
|
|
"mean_token_accuracy": 0.09853564202785492,
|
|
"num_tokens": 2467280.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.954542589187622,
|
|
"epoch": 0.14437615842356843,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.8025,
|
|
"mean_token_accuracy": 0.10932159945368766,
|
|
"num_tokens": 2484588.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.866448926925659,
|
|
"epoch": 0.14535167300751145,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.8115,
|
|
"mean_token_accuracy": 0.1057325579226017,
|
|
"num_tokens": 2501200.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.84429702758789,
|
|
"epoch": 0.1463271875914545,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.7671,
|
|
"mean_token_accuracy": 0.11158974543213844,
|
|
"num_tokens": 2517199.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.894868183135986,
|
|
"epoch": 0.1473027021753975,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.8305,
|
|
"mean_token_accuracy": 0.09836434125900269,
|
|
"num_tokens": 2534824.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.745544052124023,
|
|
"epoch": 0.14827821675934055,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.7139,
|
|
"mean_token_accuracy": 0.10689699798822402,
|
|
"num_tokens": 2550842.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.920146465301514,
|
|
"epoch": 0.14925373134328357,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.6577,
|
|
"mean_token_accuracy": 0.10967442616820336,
|
|
"num_tokens": 2567878.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.803998613357544,
|
|
"epoch": 0.1502292459272266,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.7583,
|
|
"mean_token_accuracy": 0.10285873413085937,
|
|
"num_tokens": 2584148.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.811223030090332,
|
|
"epoch": 0.15120476051116966,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.7677,
|
|
"mean_token_accuracy": 0.10665770620107651,
|
|
"num_tokens": 2600067.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.864786195755005,
|
|
"epoch": 0.15218027509511267,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.747,
|
|
"mean_token_accuracy": 0.10223184376955033,
|
|
"num_tokens": 2615746.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.87882251739502,
|
|
"epoch": 0.15315578967905571,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.7799,
|
|
"mean_token_accuracy": 0.10211106389760971,
|
|
"num_tokens": 2631641.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.835959625244141,
|
|
"epoch": 0.15413130426299873,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.7807,
|
|
"mean_token_accuracy": 0.10545132532715798,
|
|
"num_tokens": 2647015.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.828943157196045,
|
|
"epoch": 0.15510681884694177,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.6984,
|
|
"mean_token_accuracy": 0.10220426917076111,
|
|
"num_tokens": 2664045.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.740712451934814,
|
|
"epoch": 0.1560823334308848,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.6759,
|
|
"mean_token_accuracy": 0.10618537291884422,
|
|
"num_tokens": 2680774.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.804680252075196,
|
|
"epoch": 0.15705784801482783,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.7804,
|
|
"mean_token_accuracy": 0.10261463448405266,
|
|
"num_tokens": 2697719.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.877059888839722,
|
|
"epoch": 0.15803336259877085,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.7416,
|
|
"mean_token_accuracy": 0.09565807282924652,
|
|
"num_tokens": 2714518.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.821208715438843,
|
|
"epoch": 0.1590088771827139,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.7914,
|
|
"mean_token_accuracy": 0.10448245778679847,
|
|
"num_tokens": 2729288.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.8001782417297365,
|
|
"epoch": 0.1599843917666569,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.782,
|
|
"mean_token_accuracy": 0.10158958658576012,
|
|
"num_tokens": 2746782.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.77209358215332,
|
|
"epoch": 0.16095990635059995,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.8125,
|
|
"mean_token_accuracy": 0.09743853360414505,
|
|
"num_tokens": 2763159.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.774577522277832,
|
|
"epoch": 0.16193542093454297,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.7575,
|
|
"mean_token_accuracy": 0.10294459313154221,
|
|
"num_tokens": 2780338.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.727686357498169,
|
|
"epoch": 0.162910935518486,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.6655,
|
|
"mean_token_accuracy": 0.1120273858308792,
|
|
"num_tokens": 2796214.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.858849382400512,
|
|
"epoch": 0.16388645010242903,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.7812,
|
|
"mean_token_accuracy": 0.09670486152172089,
|
|
"num_tokens": 2812745.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.7591468334198,
|
|
"epoch": 0.16486196468637207,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.6485,
|
|
"mean_token_accuracy": 0.1039587639272213,
|
|
"num_tokens": 2828288.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.783154487609863,
|
|
"epoch": 0.16583747927031509,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.7887,
|
|
"mean_token_accuracy": 0.09705574363470078,
|
|
"num_tokens": 2843618.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.673272943496704,
|
|
"epoch": 0.16681299385425813,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.5843,
|
|
"mean_token_accuracy": 0.11242094039916992,
|
|
"num_tokens": 2860659.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.708390426635742,
|
|
"epoch": 0.16778850843820114,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.6903,
|
|
"mean_token_accuracy": 0.09876248240470886,
|
|
"num_tokens": 2877482.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.789376258850098,
|
|
"epoch": 0.1687640230221442,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.7691,
|
|
"mean_token_accuracy": 0.09691327959299087,
|
|
"num_tokens": 2895868.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.818999862670898,
|
|
"epoch": 0.1697395376060872,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.7386,
|
|
"mean_token_accuracy": 0.1005122035741806,
|
|
"num_tokens": 2913103.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.735997247695923,
|
|
"epoch": 0.17071505219003025,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.6454,
|
|
"mean_token_accuracy": 0.107300965487957,
|
|
"num_tokens": 2928291.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.669623756408692,
|
|
"epoch": 0.17169056677397326,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.7114,
|
|
"mean_token_accuracy": 0.10503170862793923,
|
|
"num_tokens": 2945115.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.688317728042603,
|
|
"epoch": 0.1726660813579163,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.6097,
|
|
"mean_token_accuracy": 0.10320904403924942,
|
|
"num_tokens": 2962869.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.76020359992981,
|
|
"epoch": 0.17364159594185932,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.7197,
|
|
"mean_token_accuracy": 0.10083551406860351,
|
|
"num_tokens": 2979298.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.708668375015259,
|
|
"epoch": 0.17461711052580237,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.6131,
|
|
"mean_token_accuracy": 0.11331969946622848,
|
|
"num_tokens": 2996146.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.756977510452271,
|
|
"epoch": 0.17559262510974538,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.7027,
|
|
"mean_token_accuracy": 0.10274371355772019,
|
|
"num_tokens": 3013075.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.691476202011108,
|
|
"epoch": 0.17656813969368843,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.6613,
|
|
"mean_token_accuracy": 0.10025065019726753,
|
|
"num_tokens": 3029494.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.6594343185424805,
|
|
"epoch": 0.17754365427763144,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.6761,
|
|
"mean_token_accuracy": 0.1022347241640091,
|
|
"num_tokens": 3046333.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.692041826248169,
|
|
"epoch": 0.17851916886157448,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.6515,
|
|
"mean_token_accuracy": 0.09957996159791946,
|
|
"num_tokens": 3062714.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.757144641876221,
|
|
"epoch": 0.1794946834455175,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.6434,
|
|
"mean_token_accuracy": 0.10665524601936341,
|
|
"num_tokens": 3080711.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.669725751876831,
|
|
"epoch": 0.18047019802946054,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.7298,
|
|
"mean_token_accuracy": 0.09781264886260033,
|
|
"num_tokens": 3096885.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.704789543151856,
|
|
"epoch": 0.18144571261340356,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.6261,
|
|
"mean_token_accuracy": 0.10874809324741364,
|
|
"num_tokens": 3114536.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.586754035949707,
|
|
"epoch": 0.1824212271973466,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.577,
|
|
"mean_token_accuracy": 0.1104214146733284,
|
|
"num_tokens": 3131921.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.68097333908081,
|
|
"epoch": 0.18339674178128962,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.7225,
|
|
"mean_token_accuracy": 0.09999383538961411,
|
|
"num_tokens": 3148064.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.627009773254395,
|
|
"epoch": 0.18437225636523266,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.5334,
|
|
"mean_token_accuracy": 0.11227804869413376,
|
|
"num_tokens": 3165822.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.600102329254151,
|
|
"epoch": 0.18534777094917568,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.6362,
|
|
"mean_token_accuracy": 0.10948333218693733,
|
|
"num_tokens": 3183286.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.680917978286743,
|
|
"epoch": 0.18632328553311872,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.6665,
|
|
"mean_token_accuracy": 0.09648622497916222,
|
|
"num_tokens": 3198522.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.6501914978027346,
|
|
"epoch": 0.18729880011706174,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.6896,
|
|
"mean_token_accuracy": 0.10254479497671128,
|
|
"num_tokens": 3218422.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.663035202026367,
|
|
"epoch": 0.18827431470100478,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.7127,
|
|
"mean_token_accuracy": 0.09760246202349662,
|
|
"num_tokens": 3236407.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.628622388839721,
|
|
"epoch": 0.18924982928494782,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.6424,
|
|
"mean_token_accuracy": 0.10239362493157386,
|
|
"num_tokens": 3252740.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.645857572555542,
|
|
"epoch": 0.19022534386889084,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.5999,
|
|
"mean_token_accuracy": 0.10109758228063584,
|
|
"num_tokens": 3269874.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.596111202239991,
|
|
"epoch": 0.19120085845283388,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.6328,
|
|
"mean_token_accuracy": 0.10229030176997185,
|
|
"num_tokens": 3286515.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.522288608551025,
|
|
"epoch": 0.1921763730367769,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.4299,
|
|
"mean_token_accuracy": 0.12200271040201187,
|
|
"num_tokens": 3303700.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.578052568435669,
|
|
"epoch": 0.19315188762071994,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.6204,
|
|
"mean_token_accuracy": 0.10630818232893943,
|
|
"num_tokens": 3319768.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.581722211837769,
|
|
"epoch": 0.19412740220466296,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.5208,
|
|
"mean_token_accuracy": 0.11017290130257607,
|
|
"num_tokens": 3336555.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.546011447906494,
|
|
"epoch": 0.195102916788606,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.5242,
|
|
"mean_token_accuracy": 0.1080077975988388,
|
|
"num_tokens": 3353273.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.5461585521698,
|
|
"epoch": 0.19607843137254902,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999999929644166,
|
|
"loss": 7.4324,
|
|
"mean_token_accuracy": 0.11648088321089745,
|
|
"num_tokens": 3369408.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.518179798126221,
|
|
"epoch": 0.19705394595649206,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999999643823598,
|
|
"loss": 7.4768,
|
|
"mean_token_accuracy": 0.11048399433493614,
|
|
"num_tokens": 3385834.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.5287184715271,
|
|
"epoch": 0.19802946054043508,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999999138141084,
|
|
"loss": 7.5934,
|
|
"mean_token_accuracy": 0.10513608753681183,
|
|
"num_tokens": 3401407.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.622691631317139,
|
|
"epoch": 0.19900497512437812,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999998412596673,
|
|
"loss": 7.5929,
|
|
"mean_token_accuracy": 0.09907566010951996,
|
|
"num_tokens": 3418256.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.530287981033325,
|
|
"epoch": 0.19998048970832114,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999997467190435,
|
|
"loss": 7.5624,
|
|
"mean_token_accuracy": 0.10766850039362907,
|
|
"num_tokens": 3433932.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.536963415145874,
|
|
"epoch": 0.20095600429226418,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999996301922465,
|
|
"loss": 7.5978,
|
|
"mean_token_accuracy": 0.09948049932718277,
|
|
"num_tokens": 3451723.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.599093818664551,
|
|
"epoch": 0.2019315188762072,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999994916792876,
|
|
"loss": 7.5778,
|
|
"mean_token_accuracy": 0.10314931347966194,
|
|
"num_tokens": 3469170.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.5477721214294435,
|
|
"epoch": 0.20290703346015024,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999993311801802,
|
|
"loss": 7.5969,
|
|
"mean_token_accuracy": 0.10023527815937996,
|
|
"num_tokens": 3485282.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.546366262435913,
|
|
"epoch": 0.20388254804409325,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00049999914869494,
|
|
"loss": 7.5739,
|
|
"mean_token_accuracy": 0.09581654444336891,
|
|
"num_tokens": 3502206.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.614881753921509,
|
|
"epoch": 0.2048580626280363,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499998944223585,
|
|
"loss": 7.5152,
|
|
"mean_token_accuracy": 0.10448609367012977,
|
|
"num_tokens": 3520384.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.466865873336792,
|
|
"epoch": 0.2058335772119793,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999987177661351,
|
|
"loss": 7.5128,
|
|
"mean_token_accuracy": 0.10680526867508888,
|
|
"num_tokens": 3536314.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.491249132156372,
|
|
"epoch": 0.20680909179592236,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999984693226124,
|
|
"loss": 7.4862,
|
|
"mean_token_accuracy": 0.11341608539223672,
|
|
"num_tokens": 3551510.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.450982570648193,
|
|
"epoch": 0.20778460637986537,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999981988930411,
|
|
"loss": 7.4799,
|
|
"mean_token_accuracy": 0.10830849185585975,
|
|
"num_tokens": 3568515.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.528032445907593,
|
|
"epoch": 0.20876012096380842,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999979064774478,
|
|
"loss": 7.524,
|
|
"mean_token_accuracy": 0.10810093954205513,
|
|
"num_tokens": 3585183.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.467760324478149,
|
|
"epoch": 0.20973563554775143,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499997592075861,
|
|
"loss": 7.4664,
|
|
"mean_token_accuracy": 0.11346053704619408,
|
|
"num_tokens": 3601898.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.559082460403443,
|
|
"epoch": 0.21071115013169447,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999972556883113,
|
|
"loss": 7.528,
|
|
"mean_token_accuracy": 0.10768525674939156,
|
|
"num_tokens": 3616699.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.52727255821228,
|
|
"epoch": 0.2116866647156375,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999968973148318,
|
|
"loss": 7.5395,
|
|
"mean_token_accuracy": 0.10629705637693405,
|
|
"num_tokens": 3634030.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.566522407531738,
|
|
"epoch": 0.21266217929958053,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999965169554573,
|
|
"loss": 7.5379,
|
|
"mean_token_accuracy": 0.10067117214202881,
|
|
"num_tokens": 3650495.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.514937686920166,
|
|
"epoch": 0.21363769388352355,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999961146102251,
|
|
"loss": 7.4935,
|
|
"mean_token_accuracy": 0.10824285820126534,
|
|
"num_tokens": 3666926.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.427997159957886,
|
|
"epoch": 0.2146132084674666,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004999956902791746,
|
|
"loss": 7.4484,
|
|
"mean_token_accuracy": 0.11637519970536232,
|
|
"num_tokens": 3683061.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.449176025390625,
|
|
"epoch": 0.2155887230514096,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004999952439623469,
|
|
"loss": 7.5252,
|
|
"mean_token_accuracy": 0.10821306332945824,
|
|
"num_tokens": 3703013.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.500231170654297,
|
|
"epoch": 0.21656423763535265,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499994775659786,
|
|
"loss": 7.3686,
|
|
"mean_token_accuracy": 0.1167745478451252,
|
|
"num_tokens": 3719885.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.491282320022583,
|
|
"epoch": 0.21753975221929567,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999942853715375,
|
|
"loss": 7.5083,
|
|
"mean_token_accuracy": 0.10426270142197609,
|
|
"num_tokens": 3735122.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.507296085357666,
|
|
"epoch": 0.2185152668032387,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999937730976494,
|
|
"loss": 7.4958,
|
|
"mean_token_accuracy": 0.10152617171406746,
|
|
"num_tokens": 3751627.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.388977718353272,
|
|
"epoch": 0.21949078138718173,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999932388381716,
|
|
"loss": 7.5081,
|
|
"mean_token_accuracy": 0.10370905101299285,
|
|
"num_tokens": 3768165.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.584489440917968,
|
|
"epoch": 0.22046629597112477,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999926825931564,
|
|
"loss": 7.5383,
|
|
"mean_token_accuracy": 0.10599100366234779,
|
|
"num_tokens": 3784245.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.3387915134429935,
|
|
"epoch": 0.2214418105550678,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999921043626582,
|
|
"loss": 7.2752,
|
|
"mean_token_accuracy": 0.11657643169164658,
|
|
"num_tokens": 3802057.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.452451610565186,
|
|
"epoch": 0.22241732513901083,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999915041467333,
|
|
"loss": 7.475,
|
|
"mean_token_accuracy": 0.1047409564256668,
|
|
"num_tokens": 3817104.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.472776222229004,
|
|
"epoch": 0.22339283972295385,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004999908819454407,
|
|
"loss": 7.4666,
|
|
"mean_token_accuracy": 0.10979759097099304,
|
|
"num_tokens": 3833037.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.396123790740967,
|
|
"epoch": 0.2243683543068969,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004999902377588408,
|
|
"loss": 7.3222,
|
|
"mean_token_accuracy": 0.11395804211497307,
|
|
"num_tokens": 3849634.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.454972934722901,
|
|
"epoch": 0.2253438688908399,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000499989571586997,
|
|
"loss": 7.5012,
|
|
"mean_token_accuracy": 0.1047336332499981,
|
|
"num_tokens": 3865949.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.396062326431275,
|
|
"epoch": 0.22631938347478295,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999888834299739,
|
|
"loss": 7.403,
|
|
"mean_token_accuracy": 0.11621749475598335,
|
|
"num_tokens": 3884646.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.504799795150757,
|
|
"epoch": 0.227294898058726,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999881732878391,
|
|
"loss": 7.478,
|
|
"mean_token_accuracy": 0.10949801355600357,
|
|
"num_tokens": 3900740.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.4035848617553714,
|
|
"epoch": 0.228270412642669,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999874411606618,
|
|
"loss": 7.4124,
|
|
"mean_token_accuracy": 0.11259354799985885,
|
|
"num_tokens": 3918619.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.401635408401489,
|
|
"epoch": 0.22924592722661205,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999866870485137,
|
|
"loss": 7.4045,
|
|
"mean_token_accuracy": 0.10750121995806694,
|
|
"num_tokens": 3938161.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.498355913162231,
|
|
"epoch": 0.23022144181055507,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999859109514684,
|
|
"loss": 7.453,
|
|
"mean_token_accuracy": 0.11029804646968841,
|
|
"num_tokens": 3953582.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.408897161483765,
|
|
"epoch": 0.2311969563944981,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004999851128696017,
|
|
"loss": 7.4261,
|
|
"mean_token_accuracy": 0.10325548648834229,
|
|
"num_tokens": 3969747.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.495371007919312,
|
|
"epoch": 0.23217247097844113,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999842928029917,
|
|
"loss": 7.4663,
|
|
"mean_token_accuracy": 0.10589183792471886,
|
|
"num_tokens": 3984646.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.412689352035523,
|
|
"epoch": 0.23314798556238417,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999834507517184,
|
|
"loss": 7.4473,
|
|
"mean_token_accuracy": 0.10245015770196915,
|
|
"num_tokens": 4003108.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.400495195388794,
|
|
"epoch": 0.23412350014632718,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999825867158642,
|
|
"loss": 7.5222,
|
|
"mean_token_accuracy": 0.10239234641194343,
|
|
"num_tokens": 4019944.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.547888946533203,
|
|
"epoch": 0.23509901473027023,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004999817006955134,
|
|
"loss": 7.4009,
|
|
"mean_token_accuracy": 0.1101340301334858,
|
|
"num_tokens": 4037617.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.400909948348999,
|
|
"epoch": 0.23607452931421324,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999807926907527,
|
|
"loss": 7.4013,
|
|
"mean_token_accuracy": 0.10389823541045189,
|
|
"num_tokens": 4053483.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.413779258728027,
|
|
"epoch": 0.2370500438981563,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999798627016707,
|
|
"loss": 7.4679,
|
|
"mean_token_accuracy": 0.11093057245016098,
|
|
"num_tokens": 4070165.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.4767746925354,
|
|
"epoch": 0.2380255584820993,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999789107283586,
|
|
"loss": 7.4501,
|
|
"mean_token_accuracy": 0.10087850391864776,
|
|
"num_tokens": 4086208.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.351885414123535,
|
|
"epoch": 0.23900107306604235,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499977936770909,
|
|
"loss": 7.4011,
|
|
"mean_token_accuracy": 0.10884249210357666,
|
|
"num_tokens": 4101790.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.422788381576538,
|
|
"epoch": 0.23997658764998536,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999769408294173,
|
|
"loss": 7.3379,
|
|
"mean_token_accuracy": 0.115897548943758,
|
|
"num_tokens": 4117633.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.380688333511353,
|
|
"epoch": 0.2409521022339284,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999759229039807,
|
|
"loss": 7.4042,
|
|
"mean_token_accuracy": 0.11269243955612182,
|
|
"num_tokens": 4132634.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.398476409912109,
|
|
"epoch": 0.24192761681787142,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004999748829946988,
|
|
"loss": 7.4414,
|
|
"mean_token_accuracy": 0.10720136612653733,
|
|
"num_tokens": 4150702.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.424192476272583,
|
|
"epoch": 0.24290313140181446,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999738211016732,
|
|
"loss": 7.3182,
|
|
"mean_token_accuracy": 0.12101202383637429,
|
|
"num_tokens": 4168483.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.216082954406739,
|
|
"epoch": 0.24387864598575748,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999727372250076,
|
|
"loss": 7.2769,
|
|
"mean_token_accuracy": 0.11471722945570946,
|
|
"num_tokens": 4186199.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.420723295211792,
|
|
"epoch": 0.24485416056970052,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999716313648079,
|
|
"loss": 7.4253,
|
|
"mean_token_accuracy": 0.10887003168463708,
|
|
"num_tokens": 4202303.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.443055725097656,
|
|
"epoch": 0.24582967515364354,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999705035211822,
|
|
"loss": 7.4559,
|
|
"mean_token_accuracy": 0.10704999566078185,
|
|
"num_tokens": 4218541.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.378991985321045,
|
|
"epoch": 0.24680518973758658,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999693536942406,
|
|
"loss": 7.425,
|
|
"mean_token_accuracy": 0.10749276131391525,
|
|
"num_tokens": 4234025.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.444829225540161,
|
|
"epoch": 0.2477807043215296,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999681818840957,
|
|
"loss": 7.428,
|
|
"mean_token_accuracy": 0.10735326111316681,
|
|
"num_tokens": 4250798.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.360717630386352,
|
|
"epoch": 0.24875621890547264,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499966988090862,
|
|
"loss": 7.4303,
|
|
"mean_token_accuracy": 0.10274397060275078,
|
|
"num_tokens": 4266453.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.5464013576507565,
|
|
"epoch": 0.24973173348941566,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999657723146558,
|
|
"loss": 7.3895,
|
|
"mean_token_accuracy": 0.1079128511250019,
|
|
"num_tokens": 4281825.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.169006109237671,
|
|
"epoch": 0.2507072480733587,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999645345555962,
|
|
"loss": 7.2298,
|
|
"mean_token_accuracy": 0.12292835414409638,
|
|
"num_tokens": 4298821.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.373716640472412,
|
|
"epoch": 0.2516827626573017,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999632748138041,
|
|
"loss": 7.2614,
|
|
"mean_token_accuracy": 0.11685901060700417,
|
|
"num_tokens": 4314076.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.306162357330322,
|
|
"epoch": 0.25265827724124473,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999619930894025,
|
|
"loss": 7.257,
|
|
"mean_token_accuracy": 0.11965253800153733,
|
|
"num_tokens": 4330909.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.387978792190552,
|
|
"epoch": 0.2536337918251878,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999606893825168,
|
|
"loss": 7.3761,
|
|
"mean_token_accuracy": 0.11097977533936501,
|
|
"num_tokens": 4346927.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.355130195617676,
|
|
"epoch": 0.2546093064091308,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999593636932742,
|
|
"loss": 7.4053,
|
|
"mean_token_accuracy": 0.10671861544251442,
|
|
"num_tokens": 4364956.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.356976699829102,
|
|
"epoch": 0.25558482099307384,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004999580160218044,
|
|
"loss": 7.3358,
|
|
"mean_token_accuracy": 0.11136947125196457,
|
|
"num_tokens": 4383014.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.2942369937896725,
|
|
"epoch": 0.25656033557701685,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999566463682391,
|
|
"loss": 7.4324,
|
|
"mean_token_accuracy": 0.11078611016273499,
|
|
"num_tokens": 4401050.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 7.312287998199463,
|
|
"epoch": 0.2575358501609599,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999552547327119,
|
|
"loss": 7.3142,
|
|
"mean_token_accuracy": 0.10984900295734405,
|
|
"num_tokens": 4415453.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.337052583694458,
|
|
"epoch": 0.25851136474490294,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999538411153591,
|
|
"loss": 7.2751,
|
|
"mean_token_accuracy": 0.11757619455456733,
|
|
"num_tokens": 4433107.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 7.333510684967041,
|
|
"epoch": 0.25948687932884595,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999524055163187,
|
|
"loss": 7.3852,
|
|
"mean_token_accuracy": 0.10584537237882614,
|
|
"num_tokens": 4449440.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.452435064315796,
|
|
"epoch": 0.26046239391278897,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000499950947935731,
|
|
"loss": 7.3637,
|
|
"mean_token_accuracy": 0.10850140005350113,
|
|
"num_tokens": 4465327.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.347502660751343,
|
|
"epoch": 0.26143790849673204,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999494683737384,
|
|
"loss": 7.3954,
|
|
"mean_token_accuracy": 0.10589608028531075,
|
|
"num_tokens": 4481518.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.41256275177002,
|
|
"epoch": 0.26241342308067506,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004999479668304854,
|
|
"loss": 7.4012,
|
|
"mean_token_accuracy": 0.10691455230116845,
|
|
"num_tokens": 4497632.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.192644643783569,
|
|
"epoch": 0.2633889376646181,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999464433061188,
|
|
"loss": 7.164,
|
|
"mean_token_accuracy": 0.1220066249370575,
|
|
"num_tokens": 4513790.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.298626232147217,
|
|
"epoch": 0.26436445224856114,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004999448978007876,
|
|
"loss": 7.2856,
|
|
"mean_token_accuracy": 0.11468039527535438,
|
|
"num_tokens": 4530802.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.398645114898682,
|
|
"epoch": 0.26533996683250416,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999433303146426,
|
|
"loss": 7.3514,
|
|
"mean_token_accuracy": 0.1049342192709446,
|
|
"num_tokens": 4546208.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.333724117279052,
|
|
"epoch": 0.2663154814164472,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004999417408478371,
|
|
"loss": 7.3977,
|
|
"mean_token_accuracy": 0.10778557956218719,
|
|
"num_tokens": 4563753.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.251411771774292,
|
|
"epoch": 0.2672909960003902,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999401294005264,
|
|
"loss": 7.2841,
|
|
"mean_token_accuracy": 0.11472156941890717,
|
|
"num_tokens": 4580274.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 7.316902112960816,
|
|
"epoch": 0.26826651058433326,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499938495972868,
|
|
"loss": 7.3648,
|
|
"mean_token_accuracy": 0.11064173728227615,
|
|
"num_tokens": 4596085.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.4154500484466555,
|
|
"epoch": 0.2692420251682763,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999368405650214,
|
|
"loss": 7.3904,
|
|
"mean_token_accuracy": 0.10575067326426506,
|
|
"num_tokens": 4613258.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 7.198368501663208,
|
|
"epoch": 0.2702175397522193,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999351631771485,
|
|
"loss": 7.2203,
|
|
"mean_token_accuracy": 0.116555605083704,
|
|
"num_tokens": 4630128.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 7.378967189788819,
|
|
"epoch": 0.2711930543361623,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999334638094131,
|
|
"loss": 7.2537,
|
|
"mean_token_accuracy": 0.11374187767505646,
|
|
"num_tokens": 4646181.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.308010864257812,
|
|
"epoch": 0.2721685689201054,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999317424619812,
|
|
"loss": 7.3158,
|
|
"mean_token_accuracy": 0.1069622166454792,
|
|
"num_tokens": 4661804.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 7.26732611656189,
|
|
"epoch": 0.2731440835040484,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999299991350212,
|
|
"loss": 7.2252,
|
|
"mean_token_accuracy": 0.1148923471570015,
|
|
"num_tokens": 4678163.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.2540120601654055,
|
|
"epoch": 0.2741195980879914,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999282338287034,
|
|
"loss": 7.2136,
|
|
"mean_token_accuracy": 0.11390212774276734,
|
|
"num_tokens": 4695469.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 7.369423818588257,
|
|
"epoch": 0.2750951126719344,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004999264465432001,
|
|
"loss": 7.35,
|
|
"mean_token_accuracy": 0.10951042175292969,
|
|
"num_tokens": 4711599.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 7.328134298324585,
|
|
"epoch": 0.2760706272558775,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999246372786862,
|
|
"loss": 7.3479,
|
|
"mean_token_accuracy": 0.10849231481552124,
|
|
"num_tokens": 4728381.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 7.239855241775513,
|
|
"epoch": 0.2770461418398205,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004999228060353385,
|
|
"loss": 7.3519,
|
|
"mean_token_accuracy": 0.10967302173376084,
|
|
"num_tokens": 4745348.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.360491466522217,
|
|
"epoch": 0.27802165642376353,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999209528133357,
|
|
"loss": 7.3547,
|
|
"mean_token_accuracy": 0.10041134282946587,
|
|
"num_tokens": 4763011.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.366155385971069,
|
|
"epoch": 0.27899717100770655,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499919077612859,
|
|
"loss": 7.2941,
|
|
"mean_token_accuracy": 0.11149064376950264,
|
|
"num_tokens": 4779462.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.137221622467041,
|
|
"epoch": 0.2799726855916496,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999171804340917,
|
|
"loss": 7.2561,
|
|
"mean_token_accuracy": 0.11627396196126938,
|
|
"num_tokens": 4796844.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.344420099258423,
|
|
"epoch": 0.28094820017559263,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999152612772191,
|
|
"loss": 7.2756,
|
|
"mean_token_accuracy": 0.11215969026088715,
|
|
"num_tokens": 4812851.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.175891160964966,
|
|
"epoch": 0.28192371475953565,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999133201424288,
|
|
"loss": 7.2121,
|
|
"mean_token_accuracy": 0.11662106513977051,
|
|
"num_tokens": 4830144.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 7.3987799167633055,
|
|
"epoch": 0.28289922934347866,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999113570299105,
|
|
"loss": 7.3119,
|
|
"mean_token_accuracy": 0.10317229107022285,
|
|
"num_tokens": 4846981.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 7.359449481964111,
|
|
"epoch": 0.28387474392742174,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004999093719398561,
|
|
"loss": 7.456,
|
|
"mean_token_accuracy": 0.10354385450482369,
|
|
"num_tokens": 4864404.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 7.347408819198608,
|
|
"epoch": 0.28485025851136475,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999073648724592,
|
|
"loss": 7.3405,
|
|
"mean_token_accuracy": 0.10498289689421654,
|
|
"num_tokens": 4882004.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 7.3070391654968265,
|
|
"epoch": 0.28582577309530777,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999053358279164,
|
|
"loss": 7.281,
|
|
"mean_token_accuracy": 0.10592853873968125,
|
|
"num_tokens": 4899444.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 7.365157556533814,
|
|
"epoch": 0.2868012876792508,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999032848064256,
|
|
"loss": 7.2762,
|
|
"mean_token_accuracy": 0.10759353488683701,
|
|
"num_tokens": 4917214.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 7.192684745788574,
|
|
"epoch": 0.28777680226319385,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999012118081875,
|
|
"loss": 7.3657,
|
|
"mean_token_accuracy": 0.1031188927590847,
|
|
"num_tokens": 4934534.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.404789686203003,
|
|
"epoch": 0.28875231684713687,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998991168334045,
|
|
"loss": 7.2727,
|
|
"mean_token_accuracy": 0.10799477323889732,
|
|
"num_tokens": 4950740.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 7.260487079620361,
|
|
"epoch": 0.2897278314310799,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998969998822814,
|
|
"loss": 7.3667,
|
|
"mean_token_accuracy": 0.1046581894159317,
|
|
"num_tokens": 4966720.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 7.4018322944641115,
|
|
"epoch": 0.2907033460150229,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998948609550249,
|
|
"loss": 7.2424,
|
|
"mean_token_accuracy": 0.10568741858005523,
|
|
"num_tokens": 4982195.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.231603527069092,
|
|
"epoch": 0.29167886059896597,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998927000518442,
|
|
"loss": 7.3653,
|
|
"mean_token_accuracy": 0.10721067860722541,
|
|
"num_tokens": 4997487.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 7.307701826095581,
|
|
"epoch": 0.292654375182909,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998905171729505,
|
|
"loss": 7.247,
|
|
"mean_token_accuracy": 0.10762926042079926,
|
|
"num_tokens": 5012913.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 7.192307758331299,
|
|
"epoch": 0.293629889766852,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998883123185568,
|
|
"loss": 7.223,
|
|
"mean_token_accuracy": 0.11950238272547722,
|
|
"num_tokens": 5031462.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 7.29890809059143,
|
|
"epoch": 0.294605404350795,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998860854888788,
|
|
"loss": 7.2008,
|
|
"mean_token_accuracy": 0.11756352931261063,
|
|
"num_tokens": 5047354.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 7.216483163833618,
|
|
"epoch": 0.2955809189347381,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004998838366841341,
|
|
"loss": 7.2785,
|
|
"mean_token_accuracy": 0.11354635432362556,
|
|
"num_tokens": 5065268.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 7.290679788589477,
|
|
"epoch": 0.2965564335186811,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998815659045423,
|
|
"loss": 7.2672,
|
|
"mean_token_accuracy": 0.10739901438355445,
|
|
"num_tokens": 5081066.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 7.26018328666687,
|
|
"epoch": 0.2975319481026241,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004998792731503254,
|
|
"loss": 7.2949,
|
|
"mean_token_accuracy": 0.11383327096700668,
|
|
"num_tokens": 5099440.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 7.2476519584655765,
|
|
"epoch": 0.29850746268656714,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998769584217074,
|
|
"loss": 7.2505,
|
|
"mean_token_accuracy": 0.11950337737798691,
|
|
"num_tokens": 5116573.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 7.100352048873901,
|
|
"epoch": 0.2994829772705102,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998746217189145,
|
|
"loss": 7.0171,
|
|
"mean_token_accuracy": 0.1289096012711525,
|
|
"num_tokens": 5132920.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 7.349333477020264,
|
|
"epoch": 0.3004584918544532,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000499872263042175,
|
|
"loss": 7.2819,
|
|
"mean_token_accuracy": 0.10944682136178016,
|
|
"num_tokens": 5150681.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 7.147453355789184,
|
|
"epoch": 0.30143400643839624,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998698823917196,
|
|
"loss": 7.0497,
|
|
"mean_token_accuracy": 0.12986519634723664,
|
|
"num_tokens": 5167473.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 7.240125036239624,
|
|
"epoch": 0.3024095210223393,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004998674797677805,
|
|
"loss": 7.3297,
|
|
"mean_token_accuracy": 0.10615943893790245,
|
|
"num_tokens": 5183847.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 7.296258497238159,
|
|
"epoch": 0.3033850356062823,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998650551705929,
|
|
"loss": 7.2784,
|
|
"mean_token_accuracy": 0.10746836736798286,
|
|
"num_tokens": 5200019.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 7.196804428100586,
|
|
"epoch": 0.30436055019022534,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998626086003934,
|
|
"loss": 7.1546,
|
|
"mean_token_accuracy": 0.11324814632534981,
|
|
"num_tokens": 5217245.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 7.238556861877441,
|
|
"epoch": 0.30533606477416836,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004998601400574213,
|
|
"loss": 7.0515,
|
|
"mean_token_accuracy": 0.12279537171125413,
|
|
"num_tokens": 5234822.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 7.139337778091431,
|
|
"epoch": 0.30631157935811143,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998576495419177,
|
|
"loss": 7.2222,
|
|
"mean_token_accuracy": 0.10850641578435898,
|
|
"num_tokens": 5251282.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 7.156428527832031,
|
|
"epoch": 0.30728709394205445,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.000499855137054126,
|
|
"loss": 7.1658,
|
|
"mean_token_accuracy": 0.11120741963386535,
|
|
"num_tokens": 5269630.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 7.260046768188476,
|
|
"epoch": 0.30826260852599746,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998526025942917,
|
|
"loss": 7.2444,
|
|
"mean_token_accuracy": 0.1078572191298008,
|
|
"num_tokens": 5287106.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 7.320893049240112,
|
|
"epoch": 0.3092381231099405,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998500461626625,
|
|
"loss": 7.2631,
|
|
"mean_token_accuracy": 0.1063196413218975,
|
|
"num_tokens": 5303387.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 7.289645624160767,
|
|
"epoch": 0.31021363769388355,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000499847467759488,
|
|
"loss": 7.2598,
|
|
"mean_token_accuracy": 0.10823246538639068,
|
|
"num_tokens": 5320482.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 7.193205499649048,
|
|
"epoch": 0.31118915227782656,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998448673850205,
|
|
"loss": 7.2105,
|
|
"mean_token_accuracy": 0.11387670114636421,
|
|
"num_tokens": 5336420.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 7.176516199111939,
|
|
"epoch": 0.3121646668617696,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998422450395139,
|
|
"loss": 7.1626,
|
|
"mean_token_accuracy": 0.10995283350348473,
|
|
"num_tokens": 5353464.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 7.260991001129151,
|
|
"epoch": 0.3131401814457126,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998396007232244,
|
|
"loss": 7.2239,
|
|
"mean_token_accuracy": 0.11493458598852158,
|
|
"num_tokens": 5372607.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 7.189897060394287,
|
|
"epoch": 0.31411569602965567,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998369344364105,
|
|
"loss": 7.2321,
|
|
"mean_token_accuracy": 0.11545405685901641,
|
|
"num_tokens": 5390134.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 7.215340948104858,
|
|
"epoch": 0.3150912106135987,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004998342461793328,
|
|
"loss": 7.1547,
|
|
"mean_token_accuracy": 0.11492555439472199,
|
|
"num_tokens": 5407083.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 7.0581450939178465,
|
|
"epoch": 0.3160667251975417,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998315359522538,
|
|
"loss": 7.0481,
|
|
"mean_token_accuracy": 0.12926709651947021,
|
|
"num_tokens": 5424617.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 7.196384525299072,
|
|
"epoch": 0.3170422397814847,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998288037554383,
|
|
"loss": 7.1915,
|
|
"mean_token_accuracy": 0.11906242743134499,
|
|
"num_tokens": 5440913.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 7.212459516525269,
|
|
"epoch": 0.3180177543654278,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004998260495891535,
|
|
"loss": 7.2101,
|
|
"mean_token_accuracy": 0.1167129822075367,
|
|
"num_tokens": 5457157.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 7.159144496917724,
|
|
"epoch": 0.3189932689493708,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004998232734536685,
|
|
"loss": 7.1375,
|
|
"mean_token_accuracy": 0.11458515524864196,
|
|
"num_tokens": 5474520.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 7.263358926773071,
|
|
"epoch": 0.3199687835333138,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998204753492544,
|
|
"loss": 7.2081,
|
|
"mean_token_accuracy": 0.11552096009254456,
|
|
"num_tokens": 5490599.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 7.2186919212341305,
|
|
"epoch": 0.32094429811725683,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998176552761848,
|
|
"loss": 7.28,
|
|
"mean_token_accuracy": 0.10384325012564659,
|
|
"num_tokens": 5506714.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 7.2394510269165036,
|
|
"epoch": 0.3219198127011999,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998148132347352,
|
|
"loss": 7.2283,
|
|
"mean_token_accuracy": 0.10727055072784424,
|
|
"num_tokens": 5522894.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 7.196140766143799,
|
|
"epoch": 0.3228953272851429,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004998119492251832,
|
|
"loss": 7.1119,
|
|
"mean_token_accuracy": 0.11906631961464882,
|
|
"num_tokens": 5540054.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 7.2405791759490965,
|
|
"epoch": 0.32387084186908593,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998090632478088,
|
|
"loss": 7.2668,
|
|
"mean_token_accuracy": 0.10199896171689034,
|
|
"num_tokens": 5556189.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 7.2902802467346195,
|
|
"epoch": 0.32484635645302895,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000499806155302894,
|
|
"loss": 7.2854,
|
|
"mean_token_accuracy": 0.10600126460194588,
|
|
"num_tokens": 5572562.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 7.28464298248291,
|
|
"epoch": 0.325821871036972,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499803225390723,
|
|
"loss": 7.2758,
|
|
"mean_token_accuracy": 0.1067048043012619,
|
|
"num_tokens": 5588992.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 7.256864261627197,
|
|
"epoch": 0.32679738562091504,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998002735115819,
|
|
"loss": 7.19,
|
|
"mean_token_accuracy": 0.11200586631894112,
|
|
"num_tokens": 5604143.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 7.225049877166748,
|
|
"epoch": 0.32777290020485805,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004997972996657593,
|
|
"loss": 7.301,
|
|
"mean_token_accuracy": 0.10044858381152152,
|
|
"num_tokens": 5620887.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 7.232311201095581,
|
|
"epoch": 0.32874841478880107,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997943038535459,
|
|
"loss": 7.2432,
|
|
"mean_token_accuracy": 0.11001040786504745,
|
|
"num_tokens": 5637156.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 7.249419164657593,
|
|
"epoch": 0.32972392937274414,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004997912860752341,
|
|
"loss": 7.1909,
|
|
"mean_token_accuracy": 0.10798757523298264,
|
|
"num_tokens": 5654024.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 7.1812872886657715,
|
|
"epoch": 0.33069944395668716,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997882463311192,
|
|
"loss": 7.1462,
|
|
"mean_token_accuracy": 0.11451933011412621,
|
|
"num_tokens": 5671538.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 7.190932369232177,
|
|
"epoch": 0.33167495854063017,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004997851846214979,
|
|
"loss": 7.1927,
|
|
"mean_token_accuracy": 0.11635877266526222,
|
|
"num_tokens": 5688788.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 7.17593240737915,
|
|
"epoch": 0.3326504731245732,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004997821009466695,
|
|
"loss": 7.125,
|
|
"mean_token_accuracy": 0.11613107174634933,
|
|
"num_tokens": 5706066.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 7.102512502670288,
|
|
"epoch": 0.33362598770851626,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997789953069354,
|
|
"loss": 7.1113,
|
|
"mean_token_accuracy": 0.11301351860165595,
|
|
"num_tokens": 5722100.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 7.258580112457276,
|
|
"epoch": 0.3346015022924593,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 0.0004997758677025989,
|
|
"loss": 7.2387,
|
|
"mean_token_accuracy": 0.10814922899007798,
|
|
"num_tokens": 5739068.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 7.199310684204102,
|
|
"epoch": 0.3355770168764023,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004997727181339658,
|
|
"loss": 7.2005,
|
|
"mean_token_accuracy": 0.10906586721539498,
|
|
"num_tokens": 5756147.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 7.21035852432251,
|
|
"epoch": 0.3365525314603453,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004997695466013438,
|
|
"loss": 7.1651,
|
|
"mean_token_accuracy": 0.1126245193183422,
|
|
"num_tokens": 5772157.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 7.2826355457305905,
|
|
"epoch": 0.3375280460442884,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997663531050427,
|
|
"loss": 7.2089,
|
|
"mean_token_accuracy": 0.10928624793887139,
|
|
"num_tokens": 5788128.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 7.09017162322998,
|
|
"epoch": 0.3385035606282314,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004997631376453749,
|
|
"loss": 7.186,
|
|
"mean_token_accuracy": 0.1129564292728901,
|
|
"num_tokens": 5804793.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 7.164242076873779,
|
|
"epoch": 0.3394790752121744,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004997599002226541,
|
|
"loss": 7.1177,
|
|
"mean_token_accuracy": 0.11402822509407998,
|
|
"num_tokens": 5822409.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 7.144210338592529,
|
|
"epoch": 0.3404545897961175,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499756640837197,
|
|
"loss": 7.1508,
|
|
"mean_token_accuracy": 0.10974019914865493,
|
|
"num_tokens": 5839023.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 7.194488573074341,
|
|
"epoch": 0.3414301043800605,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499753359489322,
|
|
"loss": 7.165,
|
|
"mean_token_accuracy": 0.10810371488332748,
|
|
"num_tokens": 5855804.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 7.167374801635742,
|
|
"epoch": 0.3424056189640035,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997500561793498,
|
|
"loss": 7.18,
|
|
"mean_token_accuracy": 0.11254183501005173,
|
|
"num_tokens": 5872372.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 7.24317741394043,
|
|
"epoch": 0.3433811335479465,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004997467309076031,
|
|
"loss": 7.2269,
|
|
"mean_token_accuracy": 0.1065982572734356,
|
|
"num_tokens": 5888666.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 7.082931280136108,
|
|
"epoch": 0.3443566481318896,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004997433836744069,
|
|
"loss": 7.1613,
|
|
"mean_token_accuracy": 0.11193820387125016,
|
|
"num_tokens": 5905577.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 7.1858104228973385,
|
|
"epoch": 0.3453321627158326,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997400144800882,
|
|
"loss": 7.1613,
|
|
"mean_token_accuracy": 0.11466953307390212,
|
|
"num_tokens": 5922570.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 7.035737466812134,
|
|
"epoch": 0.34630767729977563,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997366233249762,
|
|
"loss": 7.0891,
|
|
"mean_token_accuracy": 0.12224273383617401,
|
|
"num_tokens": 5938995.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 7.134057426452637,
|
|
"epoch": 0.34728319188371864,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004997332102094024,
|
|
"loss": 7.102,
|
|
"mean_token_accuracy": 0.11878659799695016,
|
|
"num_tokens": 5954869.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 7.30258355140686,
|
|
"epoch": 0.3482587064676617,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997297751337004,
|
|
"loss": 7.2144,
|
|
"mean_token_accuracy": 0.1139085553586483,
|
|
"num_tokens": 5972750.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 7.116592693328857,
|
|
"epoch": 0.34923422105160473,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997263180982055,
|
|
"loss": 7.1292,
|
|
"mean_token_accuracy": 0.11655831038951874,
|
|
"num_tokens": 5989004.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 7.091948843002319,
|
|
"epoch": 0.35020973563554775,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004997228391032559,
|
|
"loss": 7.1509,
|
|
"mean_token_accuracy": 0.11381514072418213,
|
|
"num_tokens": 6004749.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 7.1248828887939455,
|
|
"epoch": 0.35118525021949076,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004997193381491913,
|
|
"loss": 7.0421,
|
|
"mean_token_accuracy": 0.11761141419410706,
|
|
"num_tokens": 6022235.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 7.1107800006866455,
|
|
"epoch": 0.35216076480343383,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000499715815236354,
|
|
"loss": 7.1905,
|
|
"mean_token_accuracy": 0.10815553218126298,
|
|
"num_tokens": 6039194.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 7.217487049102783,
|
|
"epoch": 0.35313627938737685,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.000499712270365088,
|
|
"loss": 7.0662,
|
|
"mean_token_accuracy": 0.11293599009513855,
|
|
"num_tokens": 6055376.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 7.159701347351074,
|
|
"epoch": 0.35411179397131987,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004997087035357398,
|
|
"loss": 7.1209,
|
|
"mean_token_accuracy": 0.11384262070059777,
|
|
"num_tokens": 6071105.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 7.057770109176635,
|
|
"epoch": 0.3550873085552629,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997051147486582,
|
|
"loss": 7.0503,
|
|
"mean_token_accuracy": 0.11704391539096833,
|
|
"num_tokens": 6087964.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 7.12920560836792,
|
|
"epoch": 0.35606282313920595,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004997015040041935,
|
|
"loss": 7.1108,
|
|
"mean_token_accuracy": 0.1092826284468174,
|
|
"num_tokens": 6105245.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 7.146176195144653,
|
|
"epoch": 0.35703833772314897,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996978713026986,
|
|
"loss": 7.082,
|
|
"mean_token_accuracy": 0.12028156518936158,
|
|
"num_tokens": 6121736.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 7.127839231491089,
|
|
"epoch": 0.358013852307092,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996942166445287,
|
|
"loss": 7.13,
|
|
"mean_token_accuracy": 0.11404056623578071,
|
|
"num_tokens": 6137751.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 7.152217197418213,
|
|
"epoch": 0.358989366891035,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004996905400300407,
|
|
"loss": 7.1837,
|
|
"mean_token_accuracy": 0.11267100870609284,
|
|
"num_tokens": 6154655.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 7.18564395904541,
|
|
"epoch": 0.35996488147497807,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000499686841459594,
|
|
"loss": 7.1864,
|
|
"mean_token_accuracy": 0.10949580073356628,
|
|
"num_tokens": 6172230.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 7.117382955551148,
|
|
"epoch": 0.3609403960589211,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004996831209335497,
|
|
"loss": 7.1217,
|
|
"mean_token_accuracy": 0.10805677026510238,
|
|
"num_tokens": 6188520.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 7.1415510177612305,
|
|
"epoch": 0.3619159106428641,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004996793784522719,
|
|
"loss": 7.1543,
|
|
"mean_token_accuracy": 0.10972608849406243,
|
|
"num_tokens": 6205555.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 7.2085896015167235,
|
|
"epoch": 0.3628914252268071,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004996756140161259,
|
|
"loss": 7.141,
|
|
"mean_token_accuracy": 0.11507897600531578,
|
|
"num_tokens": 6223548.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 7.129433488845825,
|
|
"epoch": 0.3638669398107502,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004996718276254797,
|
|
"loss": 7.1486,
|
|
"mean_token_accuracy": 0.10784759968519211,
|
|
"num_tokens": 6239266.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 7.1826282978057865,
|
|
"epoch": 0.3648424543946932,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004996680192807032,
|
|
"loss": 7.1199,
|
|
"mean_token_accuracy": 0.11224561482667923,
|
|
"num_tokens": 6255020.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 7.139209032058716,
|
|
"epoch": 0.3658179689786362,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004996641889821686,
|
|
"loss": 7.053,
|
|
"mean_token_accuracy": 0.11049313396215439,
|
|
"num_tokens": 6272774.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 7.10287446975708,
|
|
"epoch": 0.36679348356257924,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996603367302502,
|
|
"loss": 7.0757,
|
|
"mean_token_accuracy": 0.11213366091251373,
|
|
"num_tokens": 6290478.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 7.12583212852478,
|
|
"epoch": 0.3677689981465223,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004996564625253244,
|
|
"loss": 7.1468,
|
|
"mean_token_accuracy": 0.11182805076241494,
|
|
"num_tokens": 6308003.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 7.0979126453399655,
|
|
"epoch": 0.3687445127304653,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004996525663677697,
|
|
"loss": 7.1043,
|
|
"mean_token_accuracy": 0.10848119333386422,
|
|
"num_tokens": 6325748.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 7.112027978897094,
|
|
"epoch": 0.36972002731440834,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000499648648257967,
|
|
"loss": 7.0532,
|
|
"mean_token_accuracy": 0.117766385525465,
|
|
"num_tokens": 6344031.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 7.047448968887329,
|
|
"epoch": 0.37069554189835136,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000499644708196299,
|
|
"loss": 7.1157,
|
|
"mean_token_accuracy": 0.11333042085170746,
|
|
"num_tokens": 6359821.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 7.05104513168335,
|
|
"epoch": 0.3716710564822944,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004996407461831507,
|
|
"loss": 6.9577,
|
|
"mean_token_accuracy": 0.12579699233174324,
|
|
"num_tokens": 6376464.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 7.115139818191528,
|
|
"epoch": 0.37264657106623744,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004996367622189094,
|
|
"loss": 7.1305,
|
|
"mean_token_accuracy": 0.10904230326414108,
|
|
"num_tokens": 6392415.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 7.063139200210571,
|
|
"epoch": 0.37362208565018046,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004996327563039643,
|
|
"loss": 7.1325,
|
|
"mean_token_accuracy": 0.1099869281053543,
|
|
"num_tokens": 6409151.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 7.200403642654419,
|
|
"epoch": 0.3745976002341235,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004996287284387068,
|
|
"loss": 7.0745,
|
|
"mean_token_accuracy": 0.11576901897788047,
|
|
"num_tokens": 6426997.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 7.096438884735107,
|
|
"epoch": 0.37557311481806654,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004996246786235306,
|
|
"loss": 7.0819,
|
|
"mean_token_accuracy": 0.11352694556117057,
|
|
"num_tokens": 6442871.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 7.026518487930298,
|
|
"epoch": 0.37654862940200956,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004996206068588314,
|
|
"loss": 7.0813,
|
|
"mean_token_accuracy": 0.1129517525434494,
|
|
"num_tokens": 6459677.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 7.2005476474761965,
|
|
"epoch": 0.3775241439859526,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996165131450071,
|
|
"loss": 7.2063,
|
|
"mean_token_accuracy": 0.10632368177175522,
|
|
"num_tokens": 6477239.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 7.1526548862457275,
|
|
"epoch": 0.37849965856989565,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004996123974824576,
|
|
"loss": 7.0799,
|
|
"mean_token_accuracy": 0.11786233857274056,
|
|
"num_tokens": 6493277.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 7.055672645568848,
|
|
"epoch": 0.37947517315383866,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004996082598715852,
|
|
"loss": 7.0894,
|
|
"mean_token_accuracy": 0.11412486806511879,
|
|
"num_tokens": 6509204.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 7.012831974029541,
|
|
"epoch": 0.3804506877377817,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499604100312794,
|
|
"loss": 6.9451,
|
|
"mean_token_accuracy": 0.12578009217977523,
|
|
"num_tokens": 6525486.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 7.067043399810791,
|
|
"epoch": 0.3814262023217247,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004995999188064908,
|
|
"loss": 7.1636,
|
|
"mean_token_accuracy": 0.10759316012263298,
|
|
"num_tokens": 6542227.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 7.145499515533447,
|
|
"epoch": 0.38240171690566777,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499595715353084,
|
|
"loss": 7.2149,
|
|
"mean_token_accuracy": 0.10373876541852951,
|
|
"num_tokens": 6558951.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 7.20166802406311,
|
|
"epoch": 0.3833772314896108,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995914899529844,
|
|
"loss": 7.1288,
|
|
"mean_token_accuracy": 0.11313018873333931,
|
|
"num_tokens": 6574696.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 7.211101913452149,
|
|
"epoch": 0.3843527460735538,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004995872426066048,
|
|
"loss": 7.1401,
|
|
"mean_token_accuracy": 0.10959764048457146,
|
|
"num_tokens": 6591628.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 7.087547159194946,
|
|
"epoch": 0.3853282606574968,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995829733143602,
|
|
"loss": 7.0457,
|
|
"mean_token_accuracy": 0.11506836861371994,
|
|
"num_tokens": 6608107.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 7.08004412651062,
|
|
"epoch": 0.3863037752414399,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499578682076668,
|
|
"loss": 7.1628,
|
|
"mean_token_accuracy": 0.11517509818077087,
|
|
"num_tokens": 6626699.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 7.229003095626831,
|
|
"epoch": 0.3872792898253829,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004995743688939474,
|
|
"loss": 7.1814,
|
|
"mean_token_accuracy": 0.10261408910155297,
|
|
"num_tokens": 6644540.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 7.120494174957275,
|
|
"epoch": 0.3882548044093259,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004995700337666199,
|
|
"loss": 7.1216,
|
|
"mean_token_accuracy": 0.10787840634584427,
|
|
"num_tokens": 6660653.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 7.160486888885498,
|
|
"epoch": 0.38923031899326893,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000499565676695109,
|
|
"loss": 7.1258,
|
|
"mean_token_accuracy": 0.10839822441339493,
|
|
"num_tokens": 6677553.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 7.107635259628296,
|
|
"epoch": 0.390205833577212,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995612976798406,
|
|
"loss": 7.1104,
|
|
"mean_token_accuracy": 0.10860190391540528,
|
|
"num_tokens": 6695274.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 7.074828433990478,
|
|
"epoch": 0.391181348161155,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004995568967212425,
|
|
"loss": 7.0548,
|
|
"mean_token_accuracy": 0.11277033910155296,
|
|
"num_tokens": 6711166.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 7.0729128360748295,
|
|
"epoch": 0.39215686274509803,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004995524738197448,
|
|
"loss": 7.0148,
|
|
"mean_token_accuracy": 0.11710212528705596,
|
|
"num_tokens": 6728827.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.975606203079224,
|
|
"epoch": 0.39313237732904105,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004995480289757796,
|
|
"loss": 7.0034,
|
|
"mean_token_accuracy": 0.12345981225371361,
|
|
"num_tokens": 6745901.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 7.042986583709717,
|
|
"epoch": 0.3941078919129841,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004995435621897815,
|
|
"loss": 6.9828,
|
|
"mean_token_accuracy": 0.120838313549757,
|
|
"num_tokens": 6762176.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 7.105779600143433,
|
|
"epoch": 0.39508340649692714,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995390734621867,
|
|
"loss": 7.1412,
|
|
"mean_token_accuracy": 0.10852285772562027,
|
|
"num_tokens": 6779322.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 7.158405876159668,
|
|
"epoch": 0.39605892108087015,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995345627934338,
|
|
"loss": 7.0704,
|
|
"mean_token_accuracy": 0.11450749263167381,
|
|
"num_tokens": 6794293.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.862678384780883,
|
|
"epoch": 0.39703443566481317,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004995300301839637,
|
|
"loss": 6.8987,
|
|
"mean_token_accuracy": 0.13570844605565072,
|
|
"num_tokens": 6812880.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 7.121017122268677,
|
|
"epoch": 0.39800995024875624,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995254756342194,
|
|
"loss": 7.1007,
|
|
"mean_token_accuracy": 0.11062633246183395,
|
|
"num_tokens": 6829230.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 7.110508584976197,
|
|
"epoch": 0.39898546483269925,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995208991446458,
|
|
"loss": 7.0967,
|
|
"mean_token_accuracy": 0.11192586347460746,
|
|
"num_tokens": 6846787.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 7.028483963012695,
|
|
"epoch": 0.39996097941664227,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995163007156902,
|
|
"loss": 6.9704,
|
|
"mean_token_accuracy": 0.11334318965673447,
|
|
"num_tokens": 6862990.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 7.138707399368286,
|
|
"epoch": 0.4009364940005853,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004995116803478018,
|
|
"loss": 7.1291,
|
|
"mean_token_accuracy": 0.10785363912582398,
|
|
"num_tokens": 6879170.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 7.040028429031372,
|
|
"epoch": 0.40191200858452836,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995070380414321,
|
|
"loss": 7.1042,
|
|
"mean_token_accuracy": 0.10964220613241196,
|
|
"num_tokens": 6895635.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 7.082418775558471,
|
|
"epoch": 0.4028875231684714,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000499502373797035,
|
|
"loss": 7.0193,
|
|
"mean_token_accuracy": 0.11688834205269813,
|
|
"num_tokens": 6912836.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 7.042549419403076,
|
|
"epoch": 0.4038630377524144,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499497687615066,
|
|
"loss": 7.0527,
|
|
"mean_token_accuracy": 0.11874325275421142,
|
|
"num_tokens": 6929507.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 7.097054290771484,
|
|
"epoch": 0.4048385523363574,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000499492979495983,
|
|
"loss": 7.0704,
|
|
"mean_token_accuracy": 0.11026768907904624,
|
|
"num_tokens": 6946527.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 7.113293838500977,
|
|
"epoch": 0.4058140669203005,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994882494402462,
|
|
"loss": 7.0686,
|
|
"mean_token_accuracy": 0.11713291183114052,
|
|
"num_tokens": 6962582.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 7.083294153213501,
|
|
"epoch": 0.4067895815042435,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004994834974483178,
|
|
"loss": 7.0635,
|
|
"mean_token_accuracy": 0.11450244709849358,
|
|
"num_tokens": 6979389.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.981550216674805,
|
|
"epoch": 0.4077650960881865,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004994787235206621,
|
|
"loss": 7.041,
|
|
"mean_token_accuracy": 0.11269214749336243,
|
|
"num_tokens": 6996637.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 7.18500280380249,
|
|
"epoch": 0.4087406106721295,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004994739276577456,
|
|
"loss": 7.1306,
|
|
"mean_token_accuracy": 0.10788496881723404,
|
|
"num_tokens": 7013013.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.985776424407959,
|
|
"epoch": 0.4097161252560726,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004994691098600369,
|
|
"loss": 7.0873,
|
|
"mean_token_accuracy": 0.11788748800754548,
|
|
"num_tokens": 7031476.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 7.15326042175293,
|
|
"epoch": 0.4106916398400156,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004994642701280068,
|
|
"loss": 7.0002,
|
|
"mean_token_accuracy": 0.11540462523698806,
|
|
"num_tokens": 7047424.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 7.044336938858033,
|
|
"epoch": 0.4116671544239586,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004994594084621282,
|
|
"loss": 7.0826,
|
|
"mean_token_accuracy": 0.1102508321404457,
|
|
"num_tokens": 7063793.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 7.192307329177856,
|
|
"epoch": 0.41264266900790164,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994545248628762,
|
|
"loss": 7.1316,
|
|
"mean_token_accuracy": 0.10800800696015359,
|
|
"num_tokens": 7079026.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 7.062437677383423,
|
|
"epoch": 0.4136181835918447,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499449619330728,
|
|
"loss": 7.0481,
|
|
"mean_token_accuracy": 0.11414429694414138,
|
|
"num_tokens": 7097524.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 7.104547214508057,
|
|
"epoch": 0.41459369817578773,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000499444691866163,
|
|
"loss": 7.1283,
|
|
"mean_token_accuracy": 0.11073413416743279,
|
|
"num_tokens": 7115514.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 7.113216829299927,
|
|
"epoch": 0.41556921275973074,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994397424696625,
|
|
"loss": 7.0699,
|
|
"mean_token_accuracy": 0.11289520859718323,
|
|
"num_tokens": 7132589.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 7.062982511520386,
|
|
"epoch": 0.4165447273436738,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994347711417105,
|
|
"loss": 7.0817,
|
|
"mean_token_accuracy": 0.1103174589574337,
|
|
"num_tokens": 7149416.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 7.003421640396118,
|
|
"epoch": 0.41752024192761683,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004994297778827924,
|
|
"loss": 7.0104,
|
|
"mean_token_accuracy": 0.11797065064311027,
|
|
"num_tokens": 7165763.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 7.055677080154419,
|
|
"epoch": 0.41849575651155985,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004994247626933964,
|
|
"loss": 6.9991,
|
|
"mean_token_accuracy": 0.12271674796938896,
|
|
"num_tokens": 7183131.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.981582450866699,
|
|
"epoch": 0.41947127109550286,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994197255740124,
|
|
"loss": 7.0142,
|
|
"mean_token_accuracy": 0.12010570019483566,
|
|
"num_tokens": 7200467.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 7.1045958518981935,
|
|
"epoch": 0.42044678567944593,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004994146665251327,
|
|
"loss": 7.0218,
|
|
"mean_token_accuracy": 0.1165754571557045,
|
|
"num_tokens": 7217311.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.998889541625976,
|
|
"epoch": 0.42142230026338895,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004994095855472516,
|
|
"loss": 7.0347,
|
|
"mean_token_accuracy": 0.1161852665245533,
|
|
"num_tokens": 7235244.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 7.119374418258667,
|
|
"epoch": 0.42239781484733196,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004994044826408656,
|
|
"loss": 7.065,
|
|
"mean_token_accuracy": 0.11025517135858535,
|
|
"num_tokens": 7252235.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 7.022988224029541,
|
|
"epoch": 0.423373329431275,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004993993578064733,
|
|
"loss": 7.0747,
|
|
"mean_token_accuracy": 0.110476765781641,
|
|
"num_tokens": 7269367.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 7.157013368606568,
|
|
"epoch": 0.42434884401521805,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993942110445756,
|
|
"loss": 7.0479,
|
|
"mean_token_accuracy": 0.11119917035102844,
|
|
"num_tokens": 7287198.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 7.0396891117095945,
|
|
"epoch": 0.42532435859916107,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004993890423556753,
|
|
"loss": 6.9786,
|
|
"mean_token_accuracy": 0.11426467075943947,
|
|
"num_tokens": 7302356.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 7.056444549560547,
|
|
"epoch": 0.4262998731831041,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004993838517402775,
|
|
"loss": 6.9778,
|
|
"mean_token_accuracy": 0.12020173147320748,
|
|
"num_tokens": 7318530.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 7.040367078781128,
|
|
"epoch": 0.4272753877670471,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004993786391988894,
|
|
"loss": 6.9622,
|
|
"mean_token_accuracy": 0.11859990432858467,
|
|
"num_tokens": 7335195.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.926948690414429,
|
|
"epoch": 0.42825090235099017,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004993734047320206,
|
|
"loss": 6.9732,
|
|
"mean_token_accuracy": 0.11311818957328797,
|
|
"num_tokens": 7352233.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 7.1166057109832765,
|
|
"epoch": 0.4292264169349332,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004993681483401821,
|
|
"loss": 7.0317,
|
|
"mean_token_accuracy": 0.11632806286215783,
|
|
"num_tokens": 7368569.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.972989654541015,
|
|
"epoch": 0.4302019315188762,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004993628700238879,
|
|
"loss": 7.0812,
|
|
"mean_token_accuracy": 0.1123574584722519,
|
|
"num_tokens": 7384669.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 7.17704405784607,
|
|
"epoch": 0.4311774461028192,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004993575697836537,
|
|
"loss": 7.084,
|
|
"mean_token_accuracy": 0.10872181057929993,
|
|
"num_tokens": 7401833.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 7.023128604888916,
|
|
"epoch": 0.4321529606867623,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004993522476199975,
|
|
"loss": 6.9775,
|
|
"mean_token_accuracy": 0.11380465403199196,
|
|
"num_tokens": 7418663.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 7.082082462310791,
|
|
"epoch": 0.4331284752707053,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004993469035334392,
|
|
"loss": 6.9614,
|
|
"mean_token_accuracy": 0.12375471666455269,
|
|
"num_tokens": 7434701.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.968666362762451,
|
|
"epoch": 0.4341039898546483,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499341537524501,
|
|
"loss": 7.0388,
|
|
"mean_token_accuracy": 0.10865203589200974,
|
|
"num_tokens": 7450154.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.962765455245972,
|
|
"epoch": 0.43507950443859134,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004993361495937074,
|
|
"loss": 6.8572,
|
|
"mean_token_accuracy": 0.13519329726696014,
|
|
"num_tokens": 7468110.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 7.0003479480743405,
|
|
"epoch": 0.4360550190225344,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004993307397415848,
|
|
"loss": 6.9826,
|
|
"mean_token_accuracy": 0.11327130421996116,
|
|
"num_tokens": 7482962.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 7.152976131439209,
|
|
"epoch": 0.4370305336064774,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004993253079686619,
|
|
"loss": 7.1131,
|
|
"mean_token_accuracy": 0.10820467174053192,
|
|
"num_tokens": 7499116.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 7.034345626831055,
|
|
"epoch": 0.43800604819042044,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004993198542754692,
|
|
"loss": 7.0649,
|
|
"mean_token_accuracy": 0.11201289296150208,
|
|
"num_tokens": 7515765.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 7.100940895080567,
|
|
"epoch": 0.43898156277436345,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004993143786625401,
|
|
"loss": 7.0562,
|
|
"mean_token_accuracy": 0.11279803812503815,
|
|
"num_tokens": 7532074.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.856002759933472,
|
|
"epoch": 0.4399570773583065,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004993088811304092,
|
|
"loss": 6.891,
|
|
"mean_token_accuracy": 0.12257369831204415,
|
|
"num_tokens": 7547704.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 7.078932285308838,
|
|
"epoch": 0.44093259194224954,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004993033616796139,
|
|
"loss": 7.0064,
|
|
"mean_token_accuracy": 0.11650566309690476,
|
|
"num_tokens": 7563317.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.949041366577148,
|
|
"epoch": 0.44190810652619256,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004992978203106936,
|
|
"loss": 7.0034,
|
|
"mean_token_accuracy": 0.1107703149318695,
|
|
"num_tokens": 7580770.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 7.0201255798339846,
|
|
"epoch": 0.4428836211101356,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004992922570241896,
|
|
"loss": 6.9751,
|
|
"mean_token_accuracy": 0.1167850024998188,
|
|
"num_tokens": 7598181.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 7.028388261795044,
|
|
"epoch": 0.44385913569407864,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004992866718206457,
|
|
"loss": 6.9768,
|
|
"mean_token_accuracy": 0.11980046629905701,
|
|
"num_tokens": 7613739.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 7.049353408813476,
|
|
"epoch": 0.44483465027802166,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004992810647006077,
|
|
"loss": 7.0595,
|
|
"mean_token_accuracy": 0.11202531084418296,
|
|
"num_tokens": 7629297.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 7.0988686084747314,
|
|
"epoch": 0.4458101648619647,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004992754356646234,
|
|
"loss": 7.0359,
|
|
"mean_token_accuracy": 0.11156322211027145,
|
|
"num_tokens": 7645273.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 7.062013387680054,
|
|
"epoch": 0.4467856794459077,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004992697847132427,
|
|
"loss": 6.9982,
|
|
"mean_token_accuracy": 0.1103116363286972,
|
|
"num_tokens": 7661296.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.91034460067749,
|
|
"epoch": 0.44776119402985076,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000499264111847018,
|
|
"loss": 6.997,
|
|
"mean_token_accuracy": 0.11417637616395951,
|
|
"num_tokens": 7678658.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 7.085509729385376,
|
|
"epoch": 0.4487367086137938,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004992584170665037,
|
|
"loss": 7.0253,
|
|
"mean_token_accuracy": 0.11035038605332374,
|
|
"num_tokens": 7693678.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 7.064776134490967,
|
|
"epoch": 0.4497122231977368,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000499252700372256,
|
|
"loss": 7.0226,
|
|
"mean_token_accuracy": 0.11261648908257485,
|
|
"num_tokens": 7709526.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 7.004364538192749,
|
|
"epoch": 0.4506877377816798,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004992469617648337,
|
|
"loss": 6.9237,
|
|
"mean_token_accuracy": 0.11412907987833024,
|
|
"num_tokens": 7725055.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.889954853057861,
|
|
"epoch": 0.4516632523656229,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004992412012447976,
|
|
"loss": 6.8284,
|
|
"mean_token_accuracy": 0.132039175927639,
|
|
"num_tokens": 7742047.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 7.015885591506958,
|
|
"epoch": 0.4526387669495659,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004992354188127105,
|
|
"loss": 6.9909,
|
|
"mean_token_accuracy": 0.11513673812150955,
|
|
"num_tokens": 7758283.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.970900583267212,
|
|
"epoch": 0.4536142815335089,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004992296144691375,
|
|
"loss": 6.9359,
|
|
"mean_token_accuracy": 0.1174176998436451,
|
|
"num_tokens": 7774660.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.923218393325806,
|
|
"epoch": 0.454589796117452,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992237882146456,
|
|
"loss": 6.9417,
|
|
"mean_token_accuracy": 0.11896992549300194,
|
|
"num_tokens": 7792147.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.939533996582031,
|
|
"epoch": 0.455565310701395,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004992179400498044,
|
|
"loss": 6.8937,
|
|
"mean_token_accuracy": 0.11782030612230301,
|
|
"num_tokens": 7809021.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 7.026896572113037,
|
|
"epoch": 0.456540825285338,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004992120699751852,
|
|
"loss": 6.962,
|
|
"mean_token_accuracy": 0.1151209183037281,
|
|
"num_tokens": 7825074.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.8574577331542965,
|
|
"epoch": 0.45751633986928103,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004992061779913616,
|
|
"loss": 6.8863,
|
|
"mean_token_accuracy": 0.12193938046693802,
|
|
"num_tokens": 7843413.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 7.073199272155762,
|
|
"epoch": 0.4584918544532241,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004992002640989094,
|
|
"loss": 6.9867,
|
|
"mean_token_accuracy": 0.10821845382452011,
|
|
"num_tokens": 7859874.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.867405271530151,
|
|
"epoch": 0.4594673690371671,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004991943282984065,
|
|
"loss": 6.9132,
|
|
"mean_token_accuracy": 0.1207984820008278,
|
|
"num_tokens": 7877302.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 7.034324979782104,
|
|
"epoch": 0.46044288362111013,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991883705904328,
|
|
"loss": 7.0444,
|
|
"mean_token_accuracy": 0.11169995591044427,
|
|
"num_tokens": 7893207.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.87566819190979,
|
|
"epoch": 0.46141839820505315,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004991823909755705,
|
|
"loss": 6.8706,
|
|
"mean_token_accuracy": 0.1258732944726944,
|
|
"num_tokens": 7910239.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 7.0774555683135985,
|
|
"epoch": 0.4623939127889962,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004991763894544041,
|
|
"loss": 7.0115,
|
|
"mean_token_accuracy": 0.11220350340008736,
|
|
"num_tokens": 7928030.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.952159023284912,
|
|
"epoch": 0.46336942737293924,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991703660275199,
|
|
"loss": 6.9563,
|
|
"mean_token_accuracy": 0.11582406088709832,
|
|
"num_tokens": 7943653.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 7.076309013366699,
|
|
"epoch": 0.46434494195688225,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004991643206955064,
|
|
"loss": 7.033,
|
|
"mean_token_accuracy": 0.1133937492966652,
|
|
"num_tokens": 7960564.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 7.016517114639282,
|
|
"epoch": 0.46532045654082527,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004991582534589544,
|
|
"loss": 6.9864,
|
|
"mean_token_accuracy": 0.11657843217253686,
|
|
"num_tokens": 7978045.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 7.005275440216065,
|
|
"epoch": 0.46629597112476834,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004991521643184567,
|
|
"loss": 7.0214,
|
|
"mean_token_accuracy": 0.11196061298251152,
|
|
"num_tokens": 7995074.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 7.063782405853272,
|
|
"epoch": 0.46727148570871135,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004991460532746087,
|
|
"loss": 7.0212,
|
|
"mean_token_accuracy": 0.10701687708497047,
|
|
"num_tokens": 8011800.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.993447494506836,
|
|
"epoch": 0.46824700029265437,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000499139920328007,
|
|
"loss": 6.9919,
|
|
"mean_token_accuracy": 0.11320114657282829,
|
|
"num_tokens": 8028090.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 7.05373911857605,
|
|
"epoch": 0.4692225148765974,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004991337654792512,
|
|
"loss": 6.9645,
|
|
"mean_token_accuracy": 0.11767757162451745,
|
|
"num_tokens": 8044140.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.914071464538575,
|
|
"epoch": 0.47019802946054046,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004991275887289427,
|
|
"loss": 6.8981,
|
|
"mean_token_accuracy": 0.11747554391622543,
|
|
"num_tokens": 8060030.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.969658994674683,
|
|
"epoch": 0.47117354404448347,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004991213900776849,
|
|
"loss": 6.945,
|
|
"mean_token_accuracy": 0.11483549773693084,
|
|
"num_tokens": 8075445.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 7.0339874744415285,
|
|
"epoch": 0.4721490586284265,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004991151695260838,
|
|
"loss": 6.9459,
|
|
"mean_token_accuracy": 0.11431458592414856,
|
|
"num_tokens": 8093250.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.8671637058258055,
|
|
"epoch": 0.4731245732123695,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499108927074747,
|
|
"loss": 6.8974,
|
|
"mean_token_accuracy": 0.12990258485078812,
|
|
"num_tokens": 8109615.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.953899288177491,
|
|
"epoch": 0.4741000877963126,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004991026627242846,
|
|
"loss": 6.9952,
|
|
"mean_token_accuracy": 0.11256581172347069,
|
|
"num_tokens": 8126591.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.994833993911743,
|
|
"epoch": 0.4750756023802556,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004990963764753088,
|
|
"loss": 6.9212,
|
|
"mean_token_accuracy": 0.11618381217122078,
|
|
"num_tokens": 8141360.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 7.006396913528443,
|
|
"epoch": 0.4760511169641986,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004990900683284337,
|
|
"loss": 7.0176,
|
|
"mean_token_accuracy": 0.11735672503709793,
|
|
"num_tokens": 8159688.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.978948783874512,
|
|
"epoch": 0.4770266315481416,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004990837382842758,
|
|
"loss": 6.9747,
|
|
"mean_token_accuracy": 0.11554915532469749,
|
|
"num_tokens": 8176887.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.814501571655273,
|
|
"epoch": 0.4780021461320847,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004990773863434537,
|
|
"loss": 6.7836,
|
|
"mean_token_accuracy": 0.12544326335191727,
|
|
"num_tokens": 8193372.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.993631887435913,
|
|
"epoch": 0.4789776607160277,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004990710125065879,
|
|
"loss": 7.0062,
|
|
"mean_token_accuracy": 0.11460533291101456,
|
|
"num_tokens": 8209713.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 7.021953868865967,
|
|
"epoch": 0.4799531752999707,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004990646167743015,
|
|
"loss": 7.0021,
|
|
"mean_token_accuracy": 0.11365641131997109,
|
|
"num_tokens": 8226359.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.913775777816772,
|
|
"epoch": 0.48092868988391374,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004990581991472193,
|
|
"loss": 6.9722,
|
|
"mean_token_accuracy": 0.11557035371661187,
|
|
"num_tokens": 8243182.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 7.020796918869019,
|
|
"epoch": 0.4819042044678568,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004990517596259684,
|
|
"loss": 6.9688,
|
|
"mean_token_accuracy": 0.11420403867959976,
|
|
"num_tokens": 8259185.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 7.048989534378052,
|
|
"epoch": 0.4828797190517998,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004990452982111781,
|
|
"loss": 7.0372,
|
|
"mean_token_accuracy": 0.10982453152537346,
|
|
"num_tokens": 8275941.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.9889849662780765,
|
|
"epoch": 0.48385523363574284,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004990388149034797,
|
|
"loss": 6.9699,
|
|
"mean_token_accuracy": 0.11409663334488869,
|
|
"num_tokens": 8292535.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.946880102157593,
|
|
"epoch": 0.48483074821968586,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004990323097035069,
|
|
"loss": 6.929,
|
|
"mean_token_accuracy": 0.12251158505678177,
|
|
"num_tokens": 8310562.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.985591983795166,
|
|
"epoch": 0.48580626280362893,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004990257826118952,
|
|
"loss": 6.9546,
|
|
"mean_token_accuracy": 0.10929256454110145,
|
|
"num_tokens": 8327241.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.895032739639282,
|
|
"epoch": 0.48678177738757195,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004990192336292824,
|
|
"loss": 6.9035,
|
|
"mean_token_accuracy": 0.11808636114001274,
|
|
"num_tokens": 8343516.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.827773857116699,
|
|
"epoch": 0.48775729197151496,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004990126627563087,
|
|
"loss": 6.7639,
|
|
"mean_token_accuracy": 0.12457770556211471,
|
|
"num_tokens": 8361809.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.819586992263794,
|
|
"epoch": 0.488732806555458,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004990060699936159,
|
|
"loss": 6.8297,
|
|
"mean_token_accuracy": 0.12708571404218674,
|
|
"num_tokens": 8378632.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.9895045280456545,
|
|
"epoch": 0.48970832113940105,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004989994553418483,
|
|
"loss": 6.985,
|
|
"mean_token_accuracy": 0.11090396344661713,
|
|
"num_tokens": 8396201.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.991191768646241,
|
|
"epoch": 0.49068383572334406,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004989928188016522,
|
|
"loss": 6.8719,
|
|
"mean_token_accuracy": 0.12096665650606156,
|
|
"num_tokens": 8412851.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.712438106536865,
|
|
"epoch": 0.4916593503072871,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004989861603736762,
|
|
"loss": 6.7015,
|
|
"mean_token_accuracy": 0.13208603635430335,
|
|
"num_tokens": 8430026.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.962678480148315,
|
|
"epoch": 0.49263486489123015,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004989794800585711,
|
|
"loss": 6.9305,
|
|
"mean_token_accuracy": 0.11510602608323098,
|
|
"num_tokens": 8446696.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 7.062203788757325,
|
|
"epoch": 0.49361037947517317,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004989727778569893,
|
|
"loss": 7.0043,
|
|
"mean_token_accuracy": 0.11590273976325989,
|
|
"num_tokens": 8464827.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.9866313457489015,
|
|
"epoch": 0.4945858940591162,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004989660537695859,
|
|
"loss": 6.9741,
|
|
"mean_token_accuracy": 0.11345633417367935,
|
|
"num_tokens": 8480185.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.862218570709229,
|
|
"epoch": 0.4955614086430592,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000498959307797018,
|
|
"loss": 6.8559,
|
|
"mean_token_accuracy": 0.126577777415514,
|
|
"num_tokens": 8497511.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.9351707935333256,
|
|
"epoch": 0.49653692322700227,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004989525399399447,
|
|
"loss": 6.9272,
|
|
"mean_token_accuracy": 0.11688981875777245,
|
|
"num_tokens": 8514394.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.986079406738281,
|
|
"epoch": 0.4975124378109453,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004989457501990275,
|
|
"loss": 6.9237,
|
|
"mean_token_accuracy": 0.11213519722223282,
|
|
"num_tokens": 8531659.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.9696861743927006,
|
|
"epoch": 0.4984879523948883,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004989389385749297,
|
|
"loss": 6.972,
|
|
"mean_token_accuracy": 0.11650464758276939,
|
|
"num_tokens": 8547986.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.967264032363891,
|
|
"epoch": 0.4994634669788313,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004989321050683169,
|
|
"loss": 6.9337,
|
|
"mean_token_accuracy": 0.11631564348936081,
|
|
"num_tokens": 8565021.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.929176139831543,
|
|
"epoch": 0.5004389815627743,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000498925249679857,
|
|
"loss": 6.9337,
|
|
"mean_token_accuracy": 0.11361033692955971,
|
|
"num_tokens": 8582135.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.898085260391236,
|
|
"epoch": 0.5014144961467174,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004989183724102196,
|
|
"loss": 6.9669,
|
|
"mean_token_accuracy": 0.11791260913014412,
|
|
"num_tokens": 8599946.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 7.006285619735718,
|
|
"epoch": 0.5023900107306605,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004989114732600771,
|
|
"loss": 6.9814,
|
|
"mean_token_accuracy": 0.11188279166817665,
|
|
"num_tokens": 8615831.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.918506193161011,
|
|
"epoch": 0.5033655253146034,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004989045522301033,
|
|
"loss": 6.877,
|
|
"mean_token_accuracy": 0.11590302884578704,
|
|
"num_tokens": 8631886.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.969996213912964,
|
|
"epoch": 0.5043410398985465,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004988976093209747,
|
|
"loss": 6.922,
|
|
"mean_token_accuracy": 0.11348427534103393,
|
|
"num_tokens": 8647520.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.89022126197815,
|
|
"epoch": 0.5053165544824895,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004988906445333698,
|
|
"loss": 6.8236,
|
|
"mean_token_accuracy": 0.12668280601501464,
|
|
"num_tokens": 8663995.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.906827592849732,
|
|
"epoch": 0.5062920690664325,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004988836578679691,
|
|
"loss": 6.9132,
|
|
"mean_token_accuracy": 0.11209813728928567,
|
|
"num_tokens": 8680201.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.970617389678955,
|
|
"epoch": 0.5072675836503756,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004988766493254552,
|
|
"loss": 6.9094,
|
|
"mean_token_accuracy": 0.12233168333768844,
|
|
"num_tokens": 8696978.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.8369691371917725,
|
|
"epoch": 0.5082430982343186,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000498869618906513,
|
|
"loss": 6.9549,
|
|
"mean_token_accuracy": 0.11839013695716857,
|
|
"num_tokens": 8713335.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.996060132980347,
|
|
"epoch": 0.5092186128182616,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004988625666118296,
|
|
"loss": 6.9367,
|
|
"mean_token_accuracy": 0.11863038241863251,
|
|
"num_tokens": 8730722.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.884844493865967,
|
|
"epoch": 0.5101941274022047,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000498855492442094,
|
|
"loss": 6.8577,
|
|
"mean_token_accuracy": 0.11674225553870202,
|
|
"num_tokens": 8747430.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.927949571609497,
|
|
"epoch": 0.5111696419861477,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004988483963979975,
|
|
"loss": 6.9499,
|
|
"mean_token_accuracy": 0.1175406351685524,
|
|
"num_tokens": 8764817.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.976333093643189,
|
|
"epoch": 0.5121451565700907,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004988412784802336,
|
|
"loss": 6.9705,
|
|
"mean_token_accuracy": 0.11199398934841157,
|
|
"num_tokens": 8780412.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 7.039850282669067,
|
|
"epoch": 0.5131206711540337,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004988341386894977,
|
|
"loss": 7.0343,
|
|
"mean_token_accuracy": 0.11212069839239121,
|
|
"num_tokens": 8795526.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.928880023956299,
|
|
"epoch": 0.5140961857379768,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004988269770264876,
|
|
"loss": 6.8226,
|
|
"mean_token_accuracy": 0.1236750140786171,
|
|
"num_tokens": 8813568.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 7.019903326034546,
|
|
"epoch": 0.5150717003219198,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004988197934919029,
|
|
"loss": 6.9877,
|
|
"mean_token_accuracy": 0.11166180521249772,
|
|
"num_tokens": 8831807.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.995202112197876,
|
|
"epoch": 0.5160472149058628,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004988125880864458,
|
|
"loss": 6.9858,
|
|
"mean_token_accuracy": 0.11477422341704369,
|
|
"num_tokens": 8848875.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.766485023498535,
|
|
"epoch": 0.5170227294898059,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004988053608108203,
|
|
"loss": 6.6849,
|
|
"mean_token_accuracy": 0.12702686265110968,
|
|
"num_tokens": 8866317.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.885069274902344,
|
|
"epoch": 0.517998244073749,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004987981116657325,
|
|
"loss": 6.8418,
|
|
"mean_token_accuracy": 0.11617801636457444,
|
|
"num_tokens": 8882543.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.942510557174683,
|
|
"epoch": 0.5189737586576919,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004987908406518909,
|
|
"loss": 6.8619,
|
|
"mean_token_accuracy": 0.11533142924308777,
|
|
"num_tokens": 8898640.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.9259865283966064,
|
|
"epoch": 0.519949273241635,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000498783547770006,
|
|
"loss": 6.9629,
|
|
"mean_token_accuracy": 0.11299280896782875,
|
|
"num_tokens": 8914649.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.984437799453735,
|
|
"epoch": 0.5209247878255779,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004987762330207903,
|
|
"loss": 6.9722,
|
|
"mean_token_accuracy": 0.11515414044260978,
|
|
"num_tokens": 8931585.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.820010805130005,
|
|
"epoch": 0.521900302409521,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004987688964049587,
|
|
"loss": 6.8595,
|
|
"mean_token_accuracy": 0.12085901573300362,
|
|
"num_tokens": 8948827.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.8946051597595215,
|
|
"epoch": 0.5228758169934641,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.000498761537923228,
|
|
"loss": 6.8342,
|
|
"mean_token_accuracy": 0.1254794180393219,
|
|
"num_tokens": 8965680.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 7.019130516052246,
|
|
"epoch": 0.523851331577407,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004987541575763175,
|
|
"loss": 6.9597,
|
|
"mean_token_accuracy": 0.10987325012683868,
|
|
"num_tokens": 8982813.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.912060880661011,
|
|
"epoch": 0.5248268461613501,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000498746755364948,
|
|
"loss": 6.9388,
|
|
"mean_token_accuracy": 0.11895869076251983,
|
|
"num_tokens": 9000497.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.953133487701416,
|
|
"epoch": 0.5258023607452932,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004987393312898431,
|
|
"loss": 6.8675,
|
|
"mean_token_accuracy": 0.11721265986561775,
|
|
"num_tokens": 9016195.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.867087030410767,
|
|
"epoch": 0.5267778753292361,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004987318853517282,
|
|
"loss": 6.8329,
|
|
"mean_token_accuracy": 0.12630052193999292,
|
|
"num_tokens": 9033295.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.92639045715332,
|
|
"epoch": 0.5277533899131792,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004987244175513308,
|
|
"loss": 6.9239,
|
|
"mean_token_accuracy": 0.11546016260981559,
|
|
"num_tokens": 9050725.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.946275138854981,
|
|
"epoch": 0.5287289044971223,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004987169278893807,
|
|
"loss": 6.8693,
|
|
"mean_token_accuracy": 0.11885097920894623,
|
|
"num_tokens": 9067842.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.9172258377075195,
|
|
"epoch": 0.5297044190810652,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004987094163666098,
|
|
"loss": 6.8994,
|
|
"mean_token_accuracy": 0.1129316121339798,
|
|
"num_tokens": 9084602.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.8367022514343265,
|
|
"epoch": 0.5306799336650083,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000498701882983752,
|
|
"loss": 6.8249,
|
|
"mean_token_accuracy": 0.1250123456120491,
|
|
"num_tokens": 9100530.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.962347030639648,
|
|
"epoch": 0.5316554482489513,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004986943277415435,
|
|
"loss": 6.9101,
|
|
"mean_token_accuracy": 0.12127360850572586,
|
|
"num_tokens": 9117304.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.802248811721801,
|
|
"epoch": 0.5326309628328944,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004986867506407225,
|
|
"loss": 6.8584,
|
|
"mean_token_accuracy": 0.13018720969557762,
|
|
"num_tokens": 9133974.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.919925498962402,
|
|
"epoch": 0.5336064774168374,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004986791516820295,
|
|
"loss": 6.8217,
|
|
"mean_token_accuracy": 0.11861017867922782,
|
|
"num_tokens": 9150600.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.799954748153686,
|
|
"epoch": 0.5345819920007804,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.000498671530866207,
|
|
"loss": 6.8359,
|
|
"mean_token_accuracy": 0.11661089509725571,
|
|
"num_tokens": 9167449.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.932155656814575,
|
|
"epoch": 0.5355575065847235,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004986638881939997,
|
|
"loss": 6.7617,
|
|
"mean_token_accuracy": 0.12293269336223603,
|
|
"num_tokens": 9184570.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.8632814407348635,
|
|
"epoch": 0.5365330211686665,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004986562236661544,
|
|
"loss": 6.9606,
|
|
"mean_token_accuracy": 0.1100731372833252,
|
|
"num_tokens": 9200537.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.9976402759552006,
|
|
"epoch": 0.5375085357526095,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00049864853728342,
|
|
"loss": 6.8563,
|
|
"mean_token_accuracy": 0.1256386786699295,
|
|
"num_tokens": 9217252.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.891844272613525,
|
|
"epoch": 0.5384840503365526,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004986408290465476,
|
|
"loss": 6.9017,
|
|
"mean_token_accuracy": 0.11649853512644767,
|
|
"num_tokens": 9234108.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.9134743213653564,
|
|
"epoch": 0.5394595649204955,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004986330989562906,
|
|
"loss": 6.8092,
|
|
"mean_token_accuracy": 0.12046945318579674,
|
|
"num_tokens": 9251017.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.7959212303161625,
|
|
"epoch": 0.5404350795044386,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004986253470134042,
|
|
"loss": 6.7755,
|
|
"mean_token_accuracy": 0.1264660306274891,
|
|
"num_tokens": 9267922.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.800236415863037,
|
|
"epoch": 0.5414105940883817,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004986175732186459,
|
|
"loss": 6.7688,
|
|
"mean_token_accuracy": 0.13141302540898323,
|
|
"num_tokens": 9284954.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.9570934772491455,
|
|
"epoch": 0.5423861086723246,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004986097775727752,
|
|
"loss": 6.883,
|
|
"mean_token_accuracy": 0.12054598703980446,
|
|
"num_tokens": 9303306.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.789645624160767,
|
|
"epoch": 0.5433616232562677,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004986019600765541,
|
|
"loss": 6.7905,
|
|
"mean_token_accuracy": 0.12379697784781456,
|
|
"num_tokens": 9319754.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.855822896957397,
|
|
"epoch": 0.5443371378402108,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004985941207307462,
|
|
"loss": 6.8849,
|
|
"mean_token_accuracy": 0.11971316859126091,
|
|
"num_tokens": 9335736.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.860150671005249,
|
|
"epoch": 0.5453126524241537,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004985862595361179,
|
|
"loss": 6.8503,
|
|
"mean_token_accuracy": 0.12303772121667862,
|
|
"num_tokens": 9350435.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.943622159957886,
|
|
"epoch": 0.5462881670080968,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004985783764934372,
|
|
"loss": 6.9081,
|
|
"mean_token_accuracy": 0.11459068953990936,
|
|
"num_tokens": 9367613.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.865189838409424,
|
|
"epoch": 0.5472636815920398,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004985704716034744,
|
|
"loss": 6.8042,
|
|
"mean_token_accuracy": 0.12057539001107216,
|
|
"num_tokens": 9385590.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.917732000350952,
|
|
"epoch": 0.5482391961759828,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004985625448670019,
|
|
"loss": 6.934,
|
|
"mean_token_accuracy": 0.11029709205031395,
|
|
"num_tokens": 9403286.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.978166198730468,
|
|
"epoch": 0.5492147107599259,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004985545962847943,
|
|
"loss": 6.9123,
|
|
"mean_token_accuracy": 0.11426826044917107,
|
|
"num_tokens": 9419880.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.894027137756348,
|
|
"epoch": 0.5501902253438689,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004985466258576283,
|
|
"loss": 6.8613,
|
|
"mean_token_accuracy": 0.11296845152974129,
|
|
"num_tokens": 9436579.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.968469572067261,
|
|
"epoch": 0.5511657399278119,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004985386335862829,
|
|
"loss": 6.9412,
|
|
"mean_token_accuracy": 0.11159636527299881,
|
|
"num_tokens": 9452802.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.914433288574219,
|
|
"epoch": 0.552141254511755,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004985306194715387,
|
|
"loss": 6.9498,
|
|
"mean_token_accuracy": 0.11330530717968941,
|
|
"num_tokens": 9468297.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.955451250076294,
|
|
"epoch": 0.553116769095698,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004985225835141792,
|
|
"loss": 6.9513,
|
|
"mean_token_accuracy": 0.11002258956432343,
|
|
"num_tokens": 9484954.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 7.008716344833374,
|
|
"epoch": 0.554092283679641,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004985145257149895,
|
|
"loss": 6.9883,
|
|
"mean_token_accuracy": 0.11100693419575691,
|
|
"num_tokens": 9502211.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.928589630126953,
|
|
"epoch": 0.555067798263584,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004985064460747569,
|
|
"loss": 6.8805,
|
|
"mean_token_accuracy": 0.11256838291883468,
|
|
"num_tokens": 9518103.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.83609938621521,
|
|
"epoch": 0.5560433128475271,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000498498344594271,
|
|
"loss": 6.8144,
|
|
"mean_token_accuracy": 0.11466094553470611,
|
|
"num_tokens": 9534155.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.833941411972046,
|
|
"epoch": 0.5570188274314701,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004984902212743234,
|
|
"loss": 6.7947,
|
|
"mean_token_accuracy": 0.12757234200835227,
|
|
"num_tokens": 9549972.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.80628137588501,
|
|
"epoch": 0.5579943420154131,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004984820761157079,
|
|
"loss": 6.7243,
|
|
"mean_token_accuracy": 0.13037320226430893,
|
|
"num_tokens": 9567306.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.9516716480255125,
|
|
"epoch": 0.5589698565993562,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004984739091192205,
|
|
"loss": 6.9277,
|
|
"mean_token_accuracy": 0.1152263417840004,
|
|
"num_tokens": 9583488.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.741307401657105,
|
|
"epoch": 0.5599453711832992,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004984657202856592,
|
|
"loss": 6.7223,
|
|
"mean_token_accuracy": 0.13048833832144738,
|
|
"num_tokens": 9600030.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.8341851234436035,
|
|
"epoch": 0.5609208857672422,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498457509615824,
|
|
"loss": 6.8515,
|
|
"mean_token_accuracy": 0.12074055820703507,
|
|
"num_tokens": 9615791.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.995968627929687,
|
|
"epoch": 0.5618964003511853,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004984492771105175,
|
|
"loss": 6.9204,
|
|
"mean_token_accuracy": 0.11317621320486068,
|
|
"num_tokens": 9630955.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.782270812988282,
|
|
"epoch": 0.5628719149351282,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004984410227705439,
|
|
"loss": 6.8268,
|
|
"mean_token_accuracy": 0.1273679867386818,
|
|
"num_tokens": 9647743.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.832012748718261,
|
|
"epoch": 0.5638474295190713,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004984327465967101,
|
|
"loss": 6.7574,
|
|
"mean_token_accuracy": 0.12513990476727485,
|
|
"num_tokens": 9665495.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.813667488098145,
|
|
"epoch": 0.5648229441030144,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004984244485898246,
|
|
"loss": 6.7867,
|
|
"mean_token_accuracy": 0.12143838852643966,
|
|
"num_tokens": 9683489.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.702491760253906,
|
|
"epoch": 0.5657984586869573,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004984161287506982,
|
|
"loss": 6.7186,
|
|
"mean_token_accuracy": 0.14046730175614358,
|
|
"num_tokens": 9700491.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.982992839813233,
|
|
"epoch": 0.5667739732709004,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000498407787080144,
|
|
"loss": 6.8942,
|
|
"mean_token_accuracy": 0.11420398429036141,
|
|
"num_tokens": 9715694.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.88687162399292,
|
|
"epoch": 0.5677494878548435,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000498399423578977,
|
|
"loss": 6.9429,
|
|
"mean_token_accuracy": 0.11011143624782563,
|
|
"num_tokens": 9731317.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 7.040346956253051,
|
|
"epoch": 0.5687250024387864,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004983910382480146,
|
|
"loss": 6.925,
|
|
"mean_token_accuracy": 0.11294664517045021,
|
|
"num_tokens": 9747928.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.869180822372437,
|
|
"epoch": 0.5697005170227295,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004983826310880762,
|
|
"loss": 6.8392,
|
|
"mean_token_accuracy": 0.11410067304968834,
|
|
"num_tokens": 9765454.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.957724380493164,
|
|
"epoch": 0.5706760316066726,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004983742020999832,
|
|
"loss": 6.909,
|
|
"mean_token_accuracy": 0.11039541885256768,
|
|
"num_tokens": 9782255.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.745351552963257,
|
|
"epoch": 0.5716515461906155,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004983657512845593,
|
|
"loss": 6.7201,
|
|
"mean_token_accuracy": 0.13016780316829682,
|
|
"num_tokens": 9798680.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.912977790832519,
|
|
"epoch": 0.5726270607745586,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004983572786426302,
|
|
"loss": 6.8858,
|
|
"mean_token_accuracy": 0.116475909948349,
|
|
"num_tokens": 9813955.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.743524360656738,
|
|
"epoch": 0.5736025753585016,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004983487841750239,
|
|
"loss": 6.7628,
|
|
"mean_token_accuracy": 0.12516291812062263,
|
|
"num_tokens": 9830692.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.908202314376831,
|
|
"epoch": 0.5745780899424446,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004983402678825705,
|
|
"loss": 6.8886,
|
|
"mean_token_accuracy": 0.11570696383714676,
|
|
"num_tokens": 9848825.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.849818515777588,
|
|
"epoch": 0.5755536045263877,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004983317297661021,
|
|
"loss": 6.8759,
|
|
"mean_token_accuracy": 0.11652199402451516,
|
|
"num_tokens": 9865802.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.935366773605347,
|
|
"epoch": 0.5765291191103307,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004983231698264531,
|
|
"loss": 6.9181,
|
|
"mean_token_accuracy": 0.11485676914453506,
|
|
"num_tokens": 9883540.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.903877782821655,
|
|
"epoch": 0.5775046336942737,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004983145880644597,
|
|
"loss": 6.8614,
|
|
"mean_token_accuracy": 0.11511279791593551,
|
|
"num_tokens": 9897724.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.9072425365448,
|
|
"epoch": 0.5784801482782168,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004983059844809608,
|
|
"loss": 6.8037,
|
|
"mean_token_accuracy": 0.12381555512547493,
|
|
"num_tokens": 9914710.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.824421691894531,
|
|
"epoch": 0.5794556628621598,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004982973590767969,
|
|
"loss": 6.9211,
|
|
"mean_token_accuracy": 0.11980470642447472,
|
|
"num_tokens": 9932362.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.857925033569336,
|
|
"epoch": 0.5804311774461028,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000498288711852811,
|
|
"loss": 6.7182,
|
|
"mean_token_accuracy": 0.12366797849535942,
|
|
"num_tokens": 9949409.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.862184047698975,
|
|
"epoch": 0.5814066920300458,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000498280042809848,
|
|
"loss": 6.8736,
|
|
"mean_token_accuracy": 0.11821404024958611,
|
|
"num_tokens": 9967467.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.876873397827149,
|
|
"epoch": 0.5823822066139889,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004982713519487549,
|
|
"loss": 6.7982,
|
|
"mean_token_accuracy": 0.12363352626562119,
|
|
"num_tokens": 9983082.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.845055437088012,
|
|
"epoch": 0.5833577211979319,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004982626392703812,
|
|
"loss": 6.8781,
|
|
"mean_token_accuracy": 0.11882330104708672,
|
|
"num_tokens": 10000046.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.910937643051147,
|
|
"epoch": 0.5843332357818749,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000498253904775578,
|
|
"loss": 6.8151,
|
|
"mean_token_accuracy": 0.11773023009300232,
|
|
"num_tokens": 10014674.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.7271734237670895,
|
|
"epoch": 0.585308750365818,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004982451484651988,
|
|
"loss": 6.6986,
|
|
"mean_token_accuracy": 0.12597279995679855,
|
|
"num_tokens": 10030647.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.585308750365818,
|
|
"eval_entropy": 6.672496932747855,
|
|
"eval_loss": 6.871516227722168,
|
|
"eval_mean_token_accuracy": 0.12053095382039408,
|
|
"eval_num_tokens": 10030647.0,
|
|
"eval_runtime": 15.3632,
|
|
"eval_samples_per_second": 1079.005,
|
|
"eval_steps_per_second": 134.933,
|
|
"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
|
|
}
|