0eacfb25ac
Model: fpadovani/ind-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed455 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": 0.2334176230305388,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 7.34880576133728,
|
|
"epoch": 0.00038902937171756465,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 7.0252,
|
|
"mean_token_accuracy": 0.10256106480956077,
|
|
"num_tokens": 9243.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.446655797958374,
|
|
"epoch": 0.0007780587434351293,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 7.1577,
|
|
"mean_token_accuracy": 0.0929850086569786,
|
|
"num_tokens": 18424.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.352576017379761,
|
|
"epoch": 0.001167088115152694,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 7.0451,
|
|
"mean_token_accuracy": 0.0964082270860672,
|
|
"num_tokens": 27006.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.343383884429931,
|
|
"epoch": 0.0015561174868702586,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 7.0864,
|
|
"mean_token_accuracy": 0.0972217358648777,
|
|
"num_tokens": 35577.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.42727689743042,
|
|
"epoch": 0.0019451468585878235,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 7.0596,
|
|
"mean_token_accuracy": 0.09545032754540443,
|
|
"num_tokens": 43706.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.413392829895019,
|
|
"epoch": 0.002334176230305388,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 7.0333,
|
|
"mean_token_accuracy": 0.09936482384800911,
|
|
"num_tokens": 52571.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.465293312072754,
|
|
"epoch": 0.0027232056020229526,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 7.0159,
|
|
"mean_token_accuracy": 0.09479603916406631,
|
|
"num_tokens": 61900.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 7.500431871414184,
|
|
"epoch": 0.0031122349737405172,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 7.0403,
|
|
"mean_token_accuracy": 0.0956958994269371,
|
|
"num_tokens": 71234.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 7.569026231765747,
|
|
"epoch": 0.003501264345458082,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 7.1142,
|
|
"mean_token_accuracy": 0.09231705740094184,
|
|
"num_tokens": 79610.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.532996749877929,
|
|
"epoch": 0.003890293717175647,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 6.9294,
|
|
"mean_token_accuracy": 0.1006363645195961,
|
|
"num_tokens": 87527.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.560778427124023,
|
|
"epoch": 0.004279323088893211,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 7.0757,
|
|
"mean_token_accuracy": 0.09589893892407417,
|
|
"num_tokens": 95512.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.501343441009522,
|
|
"epoch": 0.004668352460610776,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 7.0864,
|
|
"mean_token_accuracy": 0.09744687899947166,
|
|
"num_tokens": 104395.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.478601932525635,
|
|
"epoch": 0.0050573818323283405,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 6.9791,
|
|
"mean_token_accuracy": 0.10184086710214615,
|
|
"num_tokens": 112562.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 7.405571556091308,
|
|
"epoch": 0.005446411204045905,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 6.86,
|
|
"mean_token_accuracy": 0.09663667231798172,
|
|
"num_tokens": 121962.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 7.51507978439331,
|
|
"epoch": 0.00583544057576347,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 7.126,
|
|
"mean_token_accuracy": 0.09231036975979805,
|
|
"num_tokens": 130714.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.520365238189697,
|
|
"epoch": 0.0062244699474810344,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 6.9241,
|
|
"mean_token_accuracy": 0.10009283497929573,
|
|
"num_tokens": 139674.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.47720103263855,
|
|
"epoch": 0.006613499319198599,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.9803,
|
|
"mean_token_accuracy": 0.09953748062252998,
|
|
"num_tokens": 148654.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.46751070022583,
|
|
"epoch": 0.007002528690916164,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 6.8751,
|
|
"mean_token_accuracy": 0.10261099562048911,
|
|
"num_tokens": 156180.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.383714389801026,
|
|
"epoch": 0.007391558062633729,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 6.9565,
|
|
"mean_token_accuracy": 0.09331886917352676,
|
|
"num_tokens": 165608.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.432891321182251,
|
|
"epoch": 0.007780587434351294,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.936,
|
|
"mean_token_accuracy": 0.10059967562556267,
|
|
"num_tokens": 173871.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 7.461685752868652,
|
|
"epoch": 0.008169616806068859,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 7.0248,
|
|
"mean_token_accuracy": 0.09571366757154465,
|
|
"num_tokens": 182356.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.499224996566772,
|
|
"epoch": 0.008558646177786422,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 7.0179,
|
|
"mean_token_accuracy": 0.09466839730739593,
|
|
"num_tokens": 190361.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.435716581344605,
|
|
"epoch": 0.008947675549503988,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 6.9827,
|
|
"mean_token_accuracy": 0.0984235167503357,
|
|
"num_tokens": 199253.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 7.429847049713135,
|
|
"epoch": 0.009336704921221552,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 6.9557,
|
|
"mean_token_accuracy": 0.09870526567101479,
|
|
"num_tokens": 208181.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.515597820281982,
|
|
"epoch": 0.009725734292939117,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 6.9546,
|
|
"mean_token_accuracy": 0.09591879844665527,
|
|
"num_tokens": 216898.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 7.421197032928466,
|
|
"epoch": 0.010114763664656681,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.0039,
|
|
"mean_token_accuracy": 0.09688223078846932,
|
|
"num_tokens": 226051.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 7.492958879470825,
|
|
"epoch": 0.010503793036374246,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.042,
|
|
"mean_token_accuracy": 0.09841900020837784,
|
|
"num_tokens": 235018.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.432940196990967,
|
|
"epoch": 0.01089282240809181,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 6.9703,
|
|
"mean_token_accuracy": 0.09938597083091735,
|
|
"num_tokens": 244268.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.446199369430542,
|
|
"epoch": 0.011281851779809376,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 6.9842,
|
|
"mean_token_accuracy": 0.09659678265452384,
|
|
"num_tokens": 253545.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 7.365108060836792,
|
|
"epoch": 0.01167088115152694,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.8048,
|
|
"mean_token_accuracy": 0.10624724552035332,
|
|
"num_tokens": 261767.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.435336446762085,
|
|
"epoch": 0.012059910523244505,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 6.9655,
|
|
"mean_token_accuracy": 0.10120068341493607,
|
|
"num_tokens": 270372.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 7.463044929504394,
|
|
"epoch": 0.012448939894962069,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.026,
|
|
"mean_token_accuracy": 0.09834155589342117,
|
|
"num_tokens": 279726.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.4832648754119875,
|
|
"epoch": 0.012837969266679634,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.9905,
|
|
"mean_token_accuracy": 0.10089058354496956,
|
|
"num_tokens": 288955.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.449814510345459,
|
|
"epoch": 0.013226998638397198,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.9218,
|
|
"mean_token_accuracy": 0.09420814290642739,
|
|
"num_tokens": 297898.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.396070957183838,
|
|
"epoch": 0.013616028010114764,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.9188,
|
|
"mean_token_accuracy": 0.10343953669071197,
|
|
"num_tokens": 306189.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.427816915512085,
|
|
"epoch": 0.014005057381832327,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.9462,
|
|
"mean_token_accuracy": 0.09905305579304695,
|
|
"num_tokens": 314881.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.363733434677124,
|
|
"epoch": 0.014394086753549893,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.9415,
|
|
"mean_token_accuracy": 0.09854480773210525,
|
|
"num_tokens": 323357.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.500346422195435,
|
|
"epoch": 0.014783116125267459,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 6.9926,
|
|
"mean_token_accuracy": 0.09660296440124512,
|
|
"num_tokens": 331799.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.395345211029053,
|
|
"epoch": 0.015172145496985022,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.904,
|
|
"mean_token_accuracy": 0.10265823528170585,
|
|
"num_tokens": 340320.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.404849243164063,
|
|
"epoch": 0.015561174868702588,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.8857,
|
|
"mean_token_accuracy": 0.1047187753021717,
|
|
"num_tokens": 348990.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.39699239730835,
|
|
"epoch": 0.01595020424042015,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.9065,
|
|
"mean_token_accuracy": 0.09710254445672035,
|
|
"num_tokens": 357661.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.321025276184082,
|
|
"epoch": 0.016339233612137717,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 6.8787,
|
|
"mean_token_accuracy": 0.10586154833436012,
|
|
"num_tokens": 366099.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.5005217552185055,
|
|
"epoch": 0.016728262983855283,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.0379,
|
|
"mean_token_accuracy": 0.09788483828306198,
|
|
"num_tokens": 374926.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.418247509002685,
|
|
"epoch": 0.017117292355572845,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.946,
|
|
"mean_token_accuracy": 0.098393777012825,
|
|
"num_tokens": 383846.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.378245735168457,
|
|
"epoch": 0.01750632172729041,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.8894,
|
|
"mean_token_accuracy": 0.1021482452750206,
|
|
"num_tokens": 393678.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.4670178413391115,
|
|
"epoch": 0.017895351099007976,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.9755,
|
|
"mean_token_accuracy": 0.09847855567932129,
|
|
"num_tokens": 401866.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.473496532440185,
|
|
"epoch": 0.01828438047072554,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.9365,
|
|
"mean_token_accuracy": 0.10552924722433091,
|
|
"num_tokens": 411057.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.397612524032593,
|
|
"epoch": 0.018673409842443103,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.9395,
|
|
"mean_token_accuracy": 0.10260751843452454,
|
|
"num_tokens": 419083.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.325595569610596,
|
|
"epoch": 0.01906243921416067,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.7993,
|
|
"mean_token_accuracy": 0.10741342976689339,
|
|
"num_tokens": 427503.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.431865072250366,
|
|
"epoch": 0.019451468585878234,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.9643,
|
|
"mean_token_accuracy": 0.09718445464968681,
|
|
"num_tokens": 435820.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.301518154144287,
|
|
"epoch": 0.0198404979575958,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.8424,
|
|
"mean_token_accuracy": 0.10523844137787819,
|
|
"num_tokens": 444692.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.322385978698731,
|
|
"epoch": 0.020229527329313362,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.8813,
|
|
"mean_token_accuracy": 0.09604761153459548,
|
|
"num_tokens": 453536.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.500930261611939,
|
|
"epoch": 0.020618556701030927,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.9135,
|
|
"mean_token_accuracy": 0.10178809389472007,
|
|
"num_tokens": 462264.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.466741132736206,
|
|
"epoch": 0.021007586072748493,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.0681,
|
|
"mean_token_accuracy": 0.09854813367128372,
|
|
"num_tokens": 471819.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.39691653251648,
|
|
"epoch": 0.02139661544446606,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.9438,
|
|
"mean_token_accuracy": 0.0978664368391037,
|
|
"num_tokens": 480878.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.483294820785522,
|
|
"epoch": 0.02178564481618362,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.9213,
|
|
"mean_token_accuracy": 0.1020102322101593,
|
|
"num_tokens": 489454.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.298464393615722,
|
|
"epoch": 0.022174674187901186,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.8179,
|
|
"mean_token_accuracy": 0.10413895472884178,
|
|
"num_tokens": 498378.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.501266813278198,
|
|
"epoch": 0.02256370355961875,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.0766,
|
|
"mean_token_accuracy": 0.09656166881322861,
|
|
"num_tokens": 507638.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.435027980804444,
|
|
"epoch": 0.022952732931336317,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.9631,
|
|
"mean_token_accuracy": 0.10347767695784568,
|
|
"num_tokens": 517047.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.468677520751953,
|
|
"epoch": 0.02334176230305388,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.8928,
|
|
"mean_token_accuracy": 0.10784424841403961,
|
|
"num_tokens": 525287.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.284840393066406,
|
|
"epoch": 0.023730791674771445,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.827,
|
|
"mean_token_accuracy": 0.09975214079022407,
|
|
"num_tokens": 533266.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.383808851242065,
|
|
"epoch": 0.02411982104648901,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.9865,
|
|
"mean_token_accuracy": 0.09793580844998359,
|
|
"num_tokens": 542448.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.3777937412261965,
|
|
"epoch": 0.024508850418206576,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.8559,
|
|
"mean_token_accuracy": 0.10171961411833763,
|
|
"num_tokens": 550872.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.398427724838257,
|
|
"epoch": 0.024897879789924138,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.945,
|
|
"mean_token_accuracy": 0.10726686492562294,
|
|
"num_tokens": 559616.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.43606333732605,
|
|
"epoch": 0.025286909161641703,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.892,
|
|
"mean_token_accuracy": 0.1080216646194458,
|
|
"num_tokens": 568379.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.339574384689331,
|
|
"epoch": 0.02567593853335927,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.9344,
|
|
"mean_token_accuracy": 0.09556459337472915,
|
|
"num_tokens": 577288.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.394017219543457,
|
|
"epoch": 0.026064967905076834,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.8893,
|
|
"mean_token_accuracy": 0.09673169776797294,
|
|
"num_tokens": 587054.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.3556236743927,
|
|
"epoch": 0.026453997276794396,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.0419,
|
|
"mean_token_accuracy": 0.10046090409159661,
|
|
"num_tokens": 595405.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.431601905822754,
|
|
"epoch": 0.026843026648511962,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.8507,
|
|
"mean_token_accuracy": 0.10375126153230667,
|
|
"num_tokens": 604095.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.273375415802002,
|
|
"epoch": 0.027232056020229527,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.9004,
|
|
"mean_token_accuracy": 0.10230252891778946,
|
|
"num_tokens": 613518.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.408315944671631,
|
|
"epoch": 0.027621085391947093,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.7702,
|
|
"mean_token_accuracy": 0.1080463670194149,
|
|
"num_tokens": 621212.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.285730218887329,
|
|
"epoch": 0.028010114763664655,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.8426,
|
|
"mean_token_accuracy": 0.1072110302746296,
|
|
"num_tokens": 629326.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.37860689163208,
|
|
"epoch": 0.02839914413538222,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.8696,
|
|
"mean_token_accuracy": 0.10251942202448845,
|
|
"num_tokens": 637034.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.277339124679566,
|
|
"epoch": 0.028788173507099786,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.7723,
|
|
"mean_token_accuracy": 0.10722191333770752,
|
|
"num_tokens": 645924.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.407964897155762,
|
|
"epoch": 0.02917720287881735,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.0054,
|
|
"mean_token_accuracy": 0.10154261440038681,
|
|
"num_tokens": 655020.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.300928163528442,
|
|
"epoch": 0.029566232250534917,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.8082,
|
|
"mean_token_accuracy": 0.10665615424513816,
|
|
"num_tokens": 663451.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.367715358734131,
|
|
"epoch": 0.02995526162225248,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.9123,
|
|
"mean_token_accuracy": 0.1059771090745926,
|
|
"num_tokens": 671973.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.3022441387176515,
|
|
"epoch": 0.030344290993970045,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.797,
|
|
"mean_token_accuracy": 0.10909434482455253,
|
|
"num_tokens": 680583.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.2918174266815186,
|
|
"epoch": 0.03073332036568761,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.8136,
|
|
"mean_token_accuracy": 0.10621452257037163,
|
|
"num_tokens": 689000.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.341504812240601,
|
|
"epoch": 0.031122349737405176,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.8056,
|
|
"mean_token_accuracy": 0.10639143735170364,
|
|
"num_tokens": 698047.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.3614107131958,
|
|
"epoch": 0.03151137910912274,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.9386,
|
|
"mean_token_accuracy": 0.10114315450191498,
|
|
"num_tokens": 707192.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.2852061748504635,
|
|
"epoch": 0.0319004084808403,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.735,
|
|
"mean_token_accuracy": 0.11116274818778038,
|
|
"num_tokens": 715895.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.310044527053833,
|
|
"epoch": 0.03228943785255787,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.847,
|
|
"mean_token_accuracy": 0.10309791564941406,
|
|
"num_tokens": 724891.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.340569972991943,
|
|
"epoch": 0.032678467224275434,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.8936,
|
|
"mean_token_accuracy": 0.10329565331339836,
|
|
"num_tokens": 733378.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.354770565032959,
|
|
"epoch": 0.033067496595993,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.875,
|
|
"mean_token_accuracy": 0.10341520011425018,
|
|
"num_tokens": 741098.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.338204622268677,
|
|
"epoch": 0.033456525967710565,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.8378,
|
|
"mean_token_accuracy": 0.10154023990035058,
|
|
"num_tokens": 749902.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.19447169303894,
|
|
"epoch": 0.033845555339428124,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.8057,
|
|
"mean_token_accuracy": 0.10481407195329666,
|
|
"num_tokens": 758638.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.39279146194458,
|
|
"epoch": 0.03423458471114569,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.9067,
|
|
"mean_token_accuracy": 0.10383950993418693,
|
|
"num_tokens": 768170.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.251432418823242,
|
|
"epoch": 0.034623614082863255,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.7917,
|
|
"mean_token_accuracy": 0.10390266478061676,
|
|
"num_tokens": 776745.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.344013214111328,
|
|
"epoch": 0.03501264345458082,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.9049,
|
|
"mean_token_accuracy": 0.10472740978002548,
|
|
"num_tokens": 785030.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.348719453811645,
|
|
"epoch": 0.035401672826298386,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.8656,
|
|
"mean_token_accuracy": 0.10142385959625244,
|
|
"num_tokens": 793543.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.12188196182251,
|
|
"epoch": 0.03579070219801595,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.7096,
|
|
"mean_token_accuracy": 0.1019783414900303,
|
|
"num_tokens": 802401.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.367281770706176,
|
|
"epoch": 0.03617973156973352,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.8284,
|
|
"mean_token_accuracy": 0.10576049014925956,
|
|
"num_tokens": 811625.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.186238098144531,
|
|
"epoch": 0.03656876094145108,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.7775,
|
|
"mean_token_accuracy": 0.10242061167955399,
|
|
"num_tokens": 820742.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.257758092880249,
|
|
"epoch": 0.03695779031316864,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.8914,
|
|
"mean_token_accuracy": 0.10146046429872513,
|
|
"num_tokens": 829580.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.289563941955566,
|
|
"epoch": 0.03734681968488621,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.8122,
|
|
"mean_token_accuracy": 0.10589663460850715,
|
|
"num_tokens": 838818.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.339207744598388,
|
|
"epoch": 0.03773584905660377,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.8286,
|
|
"mean_token_accuracy": 0.09875347390770912,
|
|
"num_tokens": 847804.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.0710687160491945,
|
|
"epoch": 0.03812487842832134,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.5909,
|
|
"mean_token_accuracy": 0.11272379085421562,
|
|
"num_tokens": 856395.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.308010816574097,
|
|
"epoch": 0.0385139078000389,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.8648,
|
|
"mean_token_accuracy": 0.10699901208281518,
|
|
"num_tokens": 865219.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.108584594726563,
|
|
"epoch": 0.03890293717175647,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.6471,
|
|
"mean_token_accuracy": 0.1104583702981472,
|
|
"num_tokens": 873868.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.20792145729065,
|
|
"epoch": 0.039291966543474034,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.7601,
|
|
"mean_token_accuracy": 0.10320616662502288,
|
|
"num_tokens": 882698.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.190888500213623,
|
|
"epoch": 0.0396809959151916,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.6947,
|
|
"mean_token_accuracy": 0.11407066881656647,
|
|
"num_tokens": 891280.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.244538879394531,
|
|
"epoch": 0.04007002528690916,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.7425,
|
|
"mean_token_accuracy": 0.09894983395934105,
|
|
"num_tokens": 900044.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.08066873550415,
|
|
"epoch": 0.040459054658626724,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.7217,
|
|
"mean_token_accuracy": 0.0992046169936657,
|
|
"num_tokens": 909297.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.1543323516845705,
|
|
"epoch": 0.04084808403034429,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.7075,
|
|
"mean_token_accuracy": 0.10772032216191292,
|
|
"num_tokens": 917514.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.194704627990722,
|
|
"epoch": 0.041237113402061855,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.6951,
|
|
"mean_token_accuracy": 0.1101997010409832,
|
|
"num_tokens": 925842.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.067590141296387,
|
|
"epoch": 0.04162614277377942,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.8094,
|
|
"mean_token_accuracy": 0.09961830377578736,
|
|
"num_tokens": 934676.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.194618606567383,
|
|
"epoch": 0.042015172145496986,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.7182,
|
|
"mean_token_accuracy": 0.10596418976783753,
|
|
"num_tokens": 943763.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.158230352401733,
|
|
"epoch": 0.04240420151721455,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.7183,
|
|
"mean_token_accuracy": 0.1088571310043335,
|
|
"num_tokens": 952721.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.143984985351563,
|
|
"epoch": 0.04279323088893212,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.7143,
|
|
"mean_token_accuracy": 0.11388995125889778,
|
|
"num_tokens": 960899.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.069172191619873,
|
|
"epoch": 0.04318226026064968,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.7067,
|
|
"mean_token_accuracy": 0.1085039384663105,
|
|
"num_tokens": 969362.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.178910207748413,
|
|
"epoch": 0.04357128963236724,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.6775,
|
|
"mean_token_accuracy": 0.11293213590979576,
|
|
"num_tokens": 978028.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.113482236862183,
|
|
"epoch": 0.04396031900408481,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.6594,
|
|
"mean_token_accuracy": 0.11223076805472373,
|
|
"num_tokens": 985709.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.220449066162109,
|
|
"epoch": 0.04434934837580237,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.7666,
|
|
"mean_token_accuracy": 0.10906944498419761,
|
|
"num_tokens": 994769.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.125522947311401,
|
|
"epoch": 0.04473837774751994,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.7365,
|
|
"mean_token_accuracy": 0.11124032214283944,
|
|
"num_tokens": 1003997.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.162062454223633,
|
|
"epoch": 0.0451274071192375,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.7353,
|
|
"mean_token_accuracy": 0.10934066548943519,
|
|
"num_tokens": 1012931.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.170513248443603,
|
|
"epoch": 0.04551643649095507,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.7534,
|
|
"mean_token_accuracy": 0.10608652755618095,
|
|
"num_tokens": 1021149.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.184502792358399,
|
|
"epoch": 0.045905465862672634,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.7344,
|
|
"mean_token_accuracy": 0.11254923641681672,
|
|
"num_tokens": 1029421.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.233080053329468,
|
|
"epoch": 0.0462944952343902,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.8544,
|
|
"mean_token_accuracy": 0.10738511979579926,
|
|
"num_tokens": 1037222.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.11895523071289,
|
|
"epoch": 0.04668352460610776,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.7686,
|
|
"mean_token_accuracy": 0.10719419568777085,
|
|
"num_tokens": 1046903.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.1854307651519775,
|
|
"epoch": 0.047072553977825324,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.8112,
|
|
"mean_token_accuracy": 0.10291046276688576,
|
|
"num_tokens": 1055516.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.158183145523071,
|
|
"epoch": 0.04746158334954289,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.738,
|
|
"mean_token_accuracy": 0.10869069769978523,
|
|
"num_tokens": 1063846.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.114259338378906,
|
|
"epoch": 0.047850612721260455,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.7027,
|
|
"mean_token_accuracy": 0.10939538329839707,
|
|
"num_tokens": 1072500.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 7.126255798339844,
|
|
"epoch": 0.04823964209297802,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.7245,
|
|
"mean_token_accuracy": 0.10950846374034881,
|
|
"num_tokens": 1081399.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.04192967414856,
|
|
"epoch": 0.048628671464695586,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.6774,
|
|
"mean_token_accuracy": 0.11167947575449944,
|
|
"num_tokens": 1089666.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.143467807769776,
|
|
"epoch": 0.04901770083641315,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.5626,
|
|
"mean_token_accuracy": 0.11535401195287705,
|
|
"num_tokens": 1097496.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.058351707458496,
|
|
"epoch": 0.04940673020813072,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.7028,
|
|
"mean_token_accuracy": 0.11161455810070038,
|
|
"num_tokens": 1105840.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.135726547241211,
|
|
"epoch": 0.049795759579848276,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.7684,
|
|
"mean_token_accuracy": 0.10728443264961243,
|
|
"num_tokens": 1115507.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.041813230514526,
|
|
"epoch": 0.05018478895156584,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.7167,
|
|
"mean_token_accuracy": 0.10211084112524986,
|
|
"num_tokens": 1124820.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.087520885467529,
|
|
"epoch": 0.05057381832328341,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.5609,
|
|
"mean_token_accuracy": 0.11316258385777474,
|
|
"num_tokens": 1133641.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.982738447189331,
|
|
"epoch": 0.05096284769500097,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.616,
|
|
"mean_token_accuracy": 0.11105628833174705,
|
|
"num_tokens": 1142182.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.091386175155639,
|
|
"epoch": 0.05135187706671854,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.6894,
|
|
"mean_token_accuracy": 0.11387185752391815,
|
|
"num_tokens": 1150737.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.989086723327636,
|
|
"epoch": 0.0517409064384361,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.5525,
|
|
"mean_token_accuracy": 0.11128119602799416,
|
|
"num_tokens": 1158899.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.124065494537353,
|
|
"epoch": 0.05212993581015367,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.6359,
|
|
"mean_token_accuracy": 0.11705312058329582,
|
|
"num_tokens": 1167397.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.050602674484253,
|
|
"epoch": 0.052518965181871234,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.6545,
|
|
"mean_token_accuracy": 0.10680999159812928,
|
|
"num_tokens": 1177044.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.930141878128052,
|
|
"epoch": 0.05290799455358879,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.524,
|
|
"mean_token_accuracy": 0.11300303936004638,
|
|
"num_tokens": 1185740.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.976816177368164,
|
|
"epoch": 0.05329702392530636,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.6738,
|
|
"mean_token_accuracy": 0.11296947225928307,
|
|
"num_tokens": 1194970.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.070580577850341,
|
|
"epoch": 0.053686053297023924,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.6134,
|
|
"mean_token_accuracy": 0.11393867209553718,
|
|
"num_tokens": 1203565.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.023531770706176,
|
|
"epoch": 0.05407508266874149,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.6592,
|
|
"mean_token_accuracy": 0.10934962257742882,
|
|
"num_tokens": 1213226.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.905843925476074,
|
|
"epoch": 0.054464112040459055,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.5837,
|
|
"mean_token_accuracy": 0.10722511857748032,
|
|
"num_tokens": 1221710.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.033835506439209,
|
|
"epoch": 0.05485314141217662,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.6413,
|
|
"mean_token_accuracy": 0.10701307356357574,
|
|
"num_tokens": 1231125.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.04109468460083,
|
|
"epoch": 0.055242170783894186,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.5952,
|
|
"mean_token_accuracy": 0.11328281164169311,
|
|
"num_tokens": 1239521.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.99030909538269,
|
|
"epoch": 0.05563120015561175,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.4967,
|
|
"mean_token_accuracy": 0.11905190572142602,
|
|
"num_tokens": 1247363.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.949197673797608,
|
|
"epoch": 0.05602022952732931,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.5756,
|
|
"mean_token_accuracy": 0.10785499513149262,
|
|
"num_tokens": 1255395.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.050080490112305,
|
|
"epoch": 0.056409258899046875,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.6461,
|
|
"mean_token_accuracy": 0.10883620008826256,
|
|
"num_tokens": 1264135.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.0190126419067385,
|
|
"epoch": 0.05679828827076444,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.5703,
|
|
"mean_token_accuracy": 0.1117468774318695,
|
|
"num_tokens": 1272375.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.988955736160278,
|
|
"epoch": 0.057187317642482006,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.6249,
|
|
"mean_token_accuracy": 0.10667285323143005,
|
|
"num_tokens": 1280960.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.041416883468628,
|
|
"epoch": 0.05757634701419957,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.6797,
|
|
"mean_token_accuracy": 0.11113242357969284,
|
|
"num_tokens": 1289273.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.986820077896118,
|
|
"epoch": 0.05796537638591714,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.5673,
|
|
"mean_token_accuracy": 0.11231251433491707,
|
|
"num_tokens": 1297571.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.002435827255249,
|
|
"epoch": 0.0583544057576347,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.6165,
|
|
"mean_token_accuracy": 0.11419098302721978,
|
|
"num_tokens": 1305686.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.96313853263855,
|
|
"epoch": 0.05874343512935227,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.6372,
|
|
"mean_token_accuracy": 0.1087796851992607,
|
|
"num_tokens": 1314483.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.946442985534668,
|
|
"epoch": 0.059132464501069834,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.5161,
|
|
"mean_token_accuracy": 0.10849898308515549,
|
|
"num_tokens": 1323183.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.952772951126098,
|
|
"epoch": 0.05952149387278739,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.6204,
|
|
"mean_token_accuracy": 0.11015321984887123,
|
|
"num_tokens": 1331964.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.933269834518432,
|
|
"epoch": 0.05991052324450496,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.5707,
|
|
"mean_token_accuracy": 0.11390582174062729,
|
|
"num_tokens": 1340185.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.053455209732055,
|
|
"epoch": 0.060299552616222524,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.6715,
|
|
"mean_token_accuracy": 0.1104957066476345,
|
|
"num_tokens": 1349522.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.057522010803223,
|
|
"epoch": 0.06068858198794009,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.6406,
|
|
"mean_token_accuracy": 0.10729108974337578,
|
|
"num_tokens": 1357893.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.856075191497803,
|
|
"epoch": 0.061077611359657655,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.5272,
|
|
"mean_token_accuracy": 0.11494160592555999,
|
|
"num_tokens": 1366685.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.961356449127197,
|
|
"epoch": 0.06146664073137522,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.4661,
|
|
"mean_token_accuracy": 0.11778462678194046,
|
|
"num_tokens": 1375245.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.9094297885894775,
|
|
"epoch": 0.061855670103092786,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.6459,
|
|
"mean_token_accuracy": 0.1119820773601532,
|
|
"num_tokens": 1383724.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.064331769943237,
|
|
"epoch": 0.06224469947481035,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.6246,
|
|
"mean_token_accuracy": 0.11086539849638939,
|
|
"num_tokens": 1392455.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.040333318710327,
|
|
"epoch": 0.06263372884652792,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.6322,
|
|
"mean_token_accuracy": 0.11222699806094169,
|
|
"num_tokens": 1401262.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.833669853210449,
|
|
"epoch": 0.06302275821824548,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.528,
|
|
"mean_token_accuracy": 0.11181755363941193,
|
|
"num_tokens": 1409991.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.826368951797486,
|
|
"epoch": 0.06341178758996305,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.5143,
|
|
"mean_token_accuracy": 0.11217057034373283,
|
|
"num_tokens": 1418208.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.009344673156738,
|
|
"epoch": 0.0638008169616806,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.5279,
|
|
"mean_token_accuracy": 0.1156628392636776,
|
|
"num_tokens": 1426665.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.799173259735108,
|
|
"epoch": 0.06418984633339817,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.4582,
|
|
"mean_token_accuracy": 0.11917970553040505,
|
|
"num_tokens": 1435247.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.870002889633179,
|
|
"epoch": 0.06457887570511574,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.5052,
|
|
"mean_token_accuracy": 0.11340074241161346,
|
|
"num_tokens": 1443678.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.767337274551392,
|
|
"epoch": 0.0649679050768333,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.4409,
|
|
"mean_token_accuracy": 0.12152031734585762,
|
|
"num_tokens": 1451567.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.837034368515015,
|
|
"epoch": 0.06535693444855087,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.4578,
|
|
"mean_token_accuracy": 0.11555799394845963,
|
|
"num_tokens": 1460618.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.84786286354065,
|
|
"epoch": 0.06574596382026843,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.521,
|
|
"mean_token_accuracy": 0.1165824718773365,
|
|
"num_tokens": 1469821.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.948866891860962,
|
|
"epoch": 0.066134993191986,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.596,
|
|
"mean_token_accuracy": 0.11146286725997925,
|
|
"num_tokens": 1477989.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.937360382080078,
|
|
"epoch": 0.06652402256370356,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.6151,
|
|
"mean_token_accuracy": 0.11400183513760567,
|
|
"num_tokens": 1486822.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.887311553955078,
|
|
"epoch": 0.06691305193542113,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.4833,
|
|
"mean_token_accuracy": 0.11117951571941376,
|
|
"num_tokens": 1496604.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.801223611831665,
|
|
"epoch": 0.06730208130713869,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.5104,
|
|
"mean_token_accuracy": 0.11625081971287728,
|
|
"num_tokens": 1504725.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.889442777633667,
|
|
"epoch": 0.06769111067885625,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.5156,
|
|
"mean_token_accuracy": 0.11729802563786507,
|
|
"num_tokens": 1513222.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.880262184143066,
|
|
"epoch": 0.06808014005057382,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.4837,
|
|
"mean_token_accuracy": 0.1164153091609478,
|
|
"num_tokens": 1522183.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.819140386581421,
|
|
"epoch": 0.06846916942229138,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.5135,
|
|
"mean_token_accuracy": 0.11310733184218406,
|
|
"num_tokens": 1531316.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.924764108657837,
|
|
"epoch": 0.06885819879400895,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.579,
|
|
"mean_token_accuracy": 0.11591333150863647,
|
|
"num_tokens": 1540053.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.83437933921814,
|
|
"epoch": 0.06924722816572651,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.4385,
|
|
"mean_token_accuracy": 0.1197456382215023,
|
|
"num_tokens": 1549391.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.9253668785095215,
|
|
"epoch": 0.06963625753744408,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.5571,
|
|
"mean_token_accuracy": 0.1145814374089241,
|
|
"num_tokens": 1557364.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.799445247650146,
|
|
"epoch": 0.07002528690916164,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.3947,
|
|
"mean_token_accuracy": 0.1110591433942318,
|
|
"num_tokens": 1567011.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.749784517288208,
|
|
"epoch": 0.0704143162808792,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.5116,
|
|
"mean_token_accuracy": 0.11603075638413429,
|
|
"num_tokens": 1575441.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.821898317337036,
|
|
"epoch": 0.07080334565259677,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.4575,
|
|
"mean_token_accuracy": 0.11487730145454407,
|
|
"num_tokens": 1583757.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.860511064529419,
|
|
"epoch": 0.07119237502431433,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.5019,
|
|
"mean_token_accuracy": 0.11874779388308525,
|
|
"num_tokens": 1592406.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.792093992233276,
|
|
"epoch": 0.0715814043960319,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.4787,
|
|
"mean_token_accuracy": 0.11637907922267914,
|
|
"num_tokens": 1601665.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.8411633491516115,
|
|
"epoch": 0.07197043376774946,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.502,
|
|
"mean_token_accuracy": 0.11683260723948478,
|
|
"num_tokens": 1609788.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.7901835441589355,
|
|
"epoch": 0.07235946313946703,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.5025,
|
|
"mean_token_accuracy": 0.11982274875044822,
|
|
"num_tokens": 1618030.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.767443609237671,
|
|
"epoch": 0.07274849251118459,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.5022,
|
|
"mean_token_accuracy": 0.11648002341389656,
|
|
"num_tokens": 1626901.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.773926687240601,
|
|
"epoch": 0.07313752188290217,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.3908,
|
|
"mean_token_accuracy": 0.1169219508767128,
|
|
"num_tokens": 1635372.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.745931243896484,
|
|
"epoch": 0.07352655125461972,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.4347,
|
|
"mean_token_accuracy": 0.1165583461523056,
|
|
"num_tokens": 1643791.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.671934700012207,
|
|
"epoch": 0.07391558062633728,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.4064,
|
|
"mean_token_accuracy": 0.12068933174014092,
|
|
"num_tokens": 1652161.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.832337713241577,
|
|
"epoch": 0.07430460999805485,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.4351,
|
|
"mean_token_accuracy": 0.11309069246053696,
|
|
"num_tokens": 1661077.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.688000345230103,
|
|
"epoch": 0.07469363936977241,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.4195,
|
|
"mean_token_accuracy": 0.11566439867019654,
|
|
"num_tokens": 1669010.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.826863241195679,
|
|
"epoch": 0.07508266874148999,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.5798,
|
|
"mean_token_accuracy": 0.11118761152029037,
|
|
"num_tokens": 1678002.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.840054130554199,
|
|
"epoch": 0.07547169811320754,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.532,
|
|
"mean_token_accuracy": 0.11202086359262467,
|
|
"num_tokens": 1687403.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.791687536239624,
|
|
"epoch": 0.07586072748492512,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.4514,
|
|
"mean_token_accuracy": 0.11927441358566285,
|
|
"num_tokens": 1695512.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.763000774383545,
|
|
"epoch": 0.07624975685664268,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.4496,
|
|
"mean_token_accuracy": 0.1148236095905304,
|
|
"num_tokens": 1705116.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.659470129013061,
|
|
"epoch": 0.07663878622836025,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.3587,
|
|
"mean_token_accuracy": 0.11876563057303428,
|
|
"num_tokens": 1713715.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.745743465423584,
|
|
"epoch": 0.0770278156000778,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.4189,
|
|
"mean_token_accuracy": 0.11852910742163658,
|
|
"num_tokens": 1721881.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.7183277130126955,
|
|
"epoch": 0.07741684497179536,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.4432,
|
|
"mean_token_accuracy": 0.1176742009818554,
|
|
"num_tokens": 1730716.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.888888120651245,
|
|
"epoch": 0.07780587434351294,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.5998,
|
|
"mean_token_accuracy": 0.11513158455491065,
|
|
"num_tokens": 1740257.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.787261962890625,
|
|
"epoch": 0.0781949037152305,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999999989075146,
|
|
"loss": 6.5037,
|
|
"mean_token_accuracy": 0.1148828312754631,
|
|
"num_tokens": 1749071.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.743206596374511,
|
|
"epoch": 0.07858393308694807,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999999944692927,
|
|
"loss": 6.5174,
|
|
"mean_token_accuracy": 0.10950450450181962,
|
|
"num_tokens": 1757952.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.725841903686524,
|
|
"epoch": 0.07897296245866563,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499999986617054,
|
|
"loss": 6.4453,
|
|
"mean_token_accuracy": 0.11559172496199607,
|
|
"num_tokens": 1766027.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.709922885894775,
|
|
"epoch": 0.0793619918303832,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999999753507986,
|
|
"loss": 6.4473,
|
|
"mean_token_accuracy": 0.11136003509163857,
|
|
"num_tokens": 1775039.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.766154432296753,
|
|
"epoch": 0.07975102120210076,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999999606705267,
|
|
"loss": 6.4508,
|
|
"mean_token_accuracy": 0.12302565276622772,
|
|
"num_tokens": 1783971.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.6978371143341064,
|
|
"epoch": 0.08014005057381832,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999999425762385,
|
|
"loss": 6.3723,
|
|
"mean_token_accuracy": 0.11690968126058579,
|
|
"num_tokens": 1792743.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.746917724609375,
|
|
"epoch": 0.08052907994553589,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999999210679344,
|
|
"loss": 6.5249,
|
|
"mean_token_accuracy": 0.10790274739265442,
|
|
"num_tokens": 1801435.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.829019927978516,
|
|
"epoch": 0.08091810931725345,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999998961456145,
|
|
"loss": 6.4185,
|
|
"mean_token_accuracy": 0.11439956873655319,
|
|
"num_tokens": 1810147.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.664861822128296,
|
|
"epoch": 0.08130713868897102,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999998678092794,
|
|
"loss": 6.3459,
|
|
"mean_token_accuracy": 0.12141675725579262,
|
|
"num_tokens": 1818672.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.779337644577026,
|
|
"epoch": 0.08169616806068858,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999998360589293,
|
|
"loss": 6.5038,
|
|
"mean_token_accuracy": 0.11229550465941429,
|
|
"num_tokens": 1827590.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.68260350227356,
|
|
"epoch": 0.08208519743240615,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499999800894565,
|
|
"loss": 6.4138,
|
|
"mean_token_accuracy": 0.11804961189627647,
|
|
"num_tokens": 1836467.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.659322786331177,
|
|
"epoch": 0.08247422680412371,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999997623161866,
|
|
"loss": 6.3545,
|
|
"mean_token_accuracy": 0.11814910471439362,
|
|
"num_tokens": 1845537.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.668975210189819,
|
|
"epoch": 0.08286325617584128,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999997203237951,
|
|
"loss": 6.3591,
|
|
"mean_token_accuracy": 0.12657058462500573,
|
|
"num_tokens": 1854433.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.699471855163575,
|
|
"epoch": 0.08325228554755884,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499999674917391,
|
|
"loss": 6.4629,
|
|
"mean_token_accuracy": 0.11414268612861633,
|
|
"num_tokens": 1863708.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.6790022373199465,
|
|
"epoch": 0.0836413149192764,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999996260969748,
|
|
"loss": 6.3401,
|
|
"mean_token_accuracy": 0.12237241193652153,
|
|
"num_tokens": 1871854.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.618637943267823,
|
|
"epoch": 0.08403034429099397,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999995738625475,
|
|
"loss": 6.2953,
|
|
"mean_token_accuracy": 0.12108489871025085,
|
|
"num_tokens": 1880471.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.6455847263336185,
|
|
"epoch": 0.08441937366271153,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999995182141099,
|
|
"loss": 6.3643,
|
|
"mean_token_accuracy": 0.12223557531833648,
|
|
"num_tokens": 1889882.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.545784616470337,
|
|
"epoch": 0.0848084030344291,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999994591516626,
|
|
"loss": 6.255,
|
|
"mean_token_accuracy": 0.12821755334734916,
|
|
"num_tokens": 1898701.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.611828470230103,
|
|
"epoch": 0.08519743240614666,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999993966752066,
|
|
"loss": 6.3715,
|
|
"mean_token_accuracy": 0.11571631282567978,
|
|
"num_tokens": 1908165.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.640139150619507,
|
|
"epoch": 0.08558646177786423,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499999330784743,
|
|
"loss": 6.4811,
|
|
"mean_token_accuracy": 0.1190013438463211,
|
|
"num_tokens": 1916295.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.72911229133606,
|
|
"epoch": 0.08597549114958179,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999992614802725,
|
|
"loss": 6.3657,
|
|
"mean_token_accuracy": 0.12518487498164177,
|
|
"num_tokens": 1924643.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.63273024559021,
|
|
"epoch": 0.08636452052129936,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999991887617966,
|
|
"loss": 6.3742,
|
|
"mean_token_accuracy": 0.11607154682278634,
|
|
"num_tokens": 1933822.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.567139911651611,
|
|
"epoch": 0.08675354989301692,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999991126293158,
|
|
"loss": 6.3671,
|
|
"mean_token_accuracy": 0.119285686314106,
|
|
"num_tokens": 1943278.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.764870882034302,
|
|
"epoch": 0.08714257926473448,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004999990330828318,
|
|
"loss": 6.4038,
|
|
"mean_token_accuracy": 0.11785744428634644,
|
|
"num_tokens": 1951883.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.537186765670777,
|
|
"epoch": 0.08753160863645205,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999989501223456,
|
|
"loss": 6.2868,
|
|
"mean_token_accuracy": 0.12786889150738717,
|
|
"num_tokens": 1959567.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.700858688354492,
|
|
"epoch": 0.08792063800816961,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999988637478584,
|
|
"loss": 6.3722,
|
|
"mean_token_accuracy": 0.12128480300307273,
|
|
"num_tokens": 1968190.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.507136249542237,
|
|
"epoch": 0.08830966737988719,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999987739593716,
|
|
"loss": 6.2919,
|
|
"mean_token_accuracy": 0.1241019494831562,
|
|
"num_tokens": 1977519.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.6155976295471195,
|
|
"epoch": 0.08869869675160474,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004999986807568865,
|
|
"loss": 6.2728,
|
|
"mean_token_accuracy": 0.12157176062464714,
|
|
"num_tokens": 1985796.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.703161907196045,
|
|
"epoch": 0.08908772612332232,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999985841404045,
|
|
"loss": 6.4198,
|
|
"mean_token_accuracy": 0.11606316342949867,
|
|
"num_tokens": 1993874.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.698982381820679,
|
|
"epoch": 0.08947675549503988,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999984841099271,
|
|
"loss": 6.3686,
|
|
"mean_token_accuracy": 0.12184037938714028,
|
|
"num_tokens": 2001663.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.559295749664306,
|
|
"epoch": 0.08986578486675743,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000499998380665456,
|
|
"loss": 6.3539,
|
|
"mean_token_accuracy": 0.1229154959321022,
|
|
"num_tokens": 2010179.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.653844833374023,
|
|
"epoch": 0.090254814238475,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999982738069924,
|
|
"loss": 6.2589,
|
|
"mean_token_accuracy": 0.12252619490027428,
|
|
"num_tokens": 2020013.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.594068193435669,
|
|
"epoch": 0.09064384361019256,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004999981635345382,
|
|
"loss": 6.3751,
|
|
"mean_token_accuracy": 0.12590979486703874,
|
|
"num_tokens": 2028396.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.726529788970947,
|
|
"epoch": 0.09103287298191014,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999980498480949,
|
|
"loss": 6.4733,
|
|
"mean_token_accuracy": 0.11403553262352943,
|
|
"num_tokens": 2036947.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.585730981826782,
|
|
"epoch": 0.0914219023536277,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999979327476644,
|
|
"loss": 6.3254,
|
|
"mean_token_accuracy": 0.11759492009878159,
|
|
"num_tokens": 2045162.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.6485522270202635,
|
|
"epoch": 0.09181093172534527,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999978122332485,
|
|
"loss": 6.4095,
|
|
"mean_token_accuracy": 0.11743757203221321,
|
|
"num_tokens": 2054198.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.583405160903931,
|
|
"epoch": 0.09219996109706283,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999976883048487,
|
|
"loss": 6.3297,
|
|
"mean_token_accuracy": 0.11797131523489952,
|
|
"num_tokens": 2062558.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.551700019836426,
|
|
"epoch": 0.0925889904687804,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004999975609624673,
|
|
"loss": 6.2095,
|
|
"mean_token_accuracy": 0.11727948859333992,
|
|
"num_tokens": 2070816.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.552899169921875,
|
|
"epoch": 0.09297801984049796,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999974302061059,
|
|
"loss": 6.2712,
|
|
"mean_token_accuracy": 0.12385502606630325,
|
|
"num_tokens": 2079058.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.530488681793213,
|
|
"epoch": 0.09336704921221552,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999972960357666,
|
|
"loss": 6.2343,
|
|
"mean_token_accuracy": 0.12390355318784714,
|
|
"num_tokens": 2086679.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.622032976150512,
|
|
"epoch": 0.09375607858393309,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004999971584514516,
|
|
"loss": 6.3462,
|
|
"mean_token_accuracy": 0.12203274443745613,
|
|
"num_tokens": 2095788.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.5792169094085695,
|
|
"epoch": 0.09414510795565065,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999970174531627,
|
|
"loss": 6.3628,
|
|
"mean_token_accuracy": 0.11934652253985405,
|
|
"num_tokens": 2105435.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.570254611968994,
|
|
"epoch": 0.09453413732736822,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999968730409022,
|
|
"loss": 6.3156,
|
|
"mean_token_accuracy": 0.1212031789124012,
|
|
"num_tokens": 2114318.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.521538877487183,
|
|
"epoch": 0.09492316669908578,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999967252146723,
|
|
"loss": 6.245,
|
|
"mean_token_accuracy": 0.13023234903812408,
|
|
"num_tokens": 2122707.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.497583961486816,
|
|
"epoch": 0.09531219607080335,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999965739744752,
|
|
"loss": 6.3365,
|
|
"mean_token_accuracy": 0.1240180067718029,
|
|
"num_tokens": 2131176.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.681749296188355,
|
|
"epoch": 0.09570122544252091,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999964193203132,
|
|
"loss": 6.3785,
|
|
"mean_token_accuracy": 0.12624216973781585,
|
|
"num_tokens": 2139872.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.508302974700928,
|
|
"epoch": 0.09609025481423847,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999962612521888,
|
|
"loss": 6.2386,
|
|
"mean_token_accuracy": 0.1306472271680832,
|
|
"num_tokens": 2148668.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.534418439865112,
|
|
"epoch": 0.09647928418595604,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999960997701041,
|
|
"loss": 6.24,
|
|
"mean_token_accuracy": 0.12787432298064233,
|
|
"num_tokens": 2156628.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.563996267318726,
|
|
"epoch": 0.0968683135576736,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999959348740618,
|
|
"loss": 6.3335,
|
|
"mean_token_accuracy": 0.11790938824415206,
|
|
"num_tokens": 2165620.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.626491832733154,
|
|
"epoch": 0.09725734292939117,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004999957665640641,
|
|
"loss": 6.3967,
|
|
"mean_token_accuracy": 0.11869805678725243,
|
|
"num_tokens": 2174493.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.55765929222107,
|
|
"epoch": 0.09764637230110873,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000499995594840114,
|
|
"loss": 6.2909,
|
|
"mean_token_accuracy": 0.11683699488639832,
|
|
"num_tokens": 2183258.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.548435878753662,
|
|
"epoch": 0.0980354016728263,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999954197022138,
|
|
"loss": 6.3454,
|
|
"mean_token_accuracy": 0.11895403861999512,
|
|
"num_tokens": 2192263.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.651948308944702,
|
|
"epoch": 0.09842443104454386,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999952411503661,
|
|
"loss": 6.3889,
|
|
"mean_token_accuracy": 0.1177945502102375,
|
|
"num_tokens": 2201797.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.354124736785889,
|
|
"epoch": 0.09881346041626143,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999950591845738,
|
|
"loss": 6.1299,
|
|
"mean_token_accuracy": 0.1311613693833351,
|
|
"num_tokens": 2209454.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.649595832824707,
|
|
"epoch": 0.09920248978797899,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999948738048397,
|
|
"loss": 6.3022,
|
|
"mean_token_accuracy": 0.12611282840371132,
|
|
"num_tokens": 2217761.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.47292742729187,
|
|
"epoch": 0.09959151915969655,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004999946850111663,
|
|
"loss": 6.2906,
|
|
"mean_token_accuracy": 0.12207216396927834,
|
|
"num_tokens": 2225793.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.592188453674316,
|
|
"epoch": 0.09998054853141412,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999944928035569,
|
|
"loss": 6.1805,
|
|
"mean_token_accuracy": 0.1319039449095726,
|
|
"num_tokens": 2234620.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.4829436302185055,
|
|
"epoch": 0.10036957790313168,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499994297182014,
|
|
"loss": 6.2643,
|
|
"mean_token_accuracy": 0.12326281145215034,
|
|
"num_tokens": 2242829.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.57083477973938,
|
|
"epoch": 0.10075860727484925,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999940981465408,
|
|
"loss": 6.3014,
|
|
"mean_token_accuracy": 0.11634257808327675,
|
|
"num_tokens": 2251356.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.523905658721924,
|
|
"epoch": 0.10114763664656681,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999938956971404,
|
|
"loss": 6.3684,
|
|
"mean_token_accuracy": 0.11852610781788826,
|
|
"num_tokens": 2259327.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.59006552696228,
|
|
"epoch": 0.10153666601828439,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999936898338156,
|
|
"loss": 6.3871,
|
|
"mean_token_accuracy": 0.11884624063968659,
|
|
"num_tokens": 2267948.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.446884679794311,
|
|
"epoch": 0.10192569539000194,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999934805565698,
|
|
"loss": 6.194,
|
|
"mean_token_accuracy": 0.1225943498313427,
|
|
"num_tokens": 2275828.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.5004541873931885,
|
|
"epoch": 0.10231472476171952,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499993267865406,
|
|
"loss": 6.1373,
|
|
"mean_token_accuracy": 0.1289021112024784,
|
|
"num_tokens": 2284246.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.385093450546265,
|
|
"epoch": 0.10270375413343708,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999930517603275,
|
|
"loss": 6.1261,
|
|
"mean_token_accuracy": 0.13380536437034607,
|
|
"num_tokens": 2291837.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.546138572692871,
|
|
"epoch": 0.10309278350515463,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999928322413374,
|
|
"loss": 6.206,
|
|
"mean_token_accuracy": 0.12851327955722808,
|
|
"num_tokens": 2299853.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.574787330627442,
|
|
"epoch": 0.1034818128768722,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999926093084394,
|
|
"loss": 6.3075,
|
|
"mean_token_accuracy": 0.1206931158900261,
|
|
"num_tokens": 2308416.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.507684230804443,
|
|
"epoch": 0.10387084224858976,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999923829616365,
|
|
"loss": 6.3388,
|
|
"mean_token_accuracy": 0.12228097319602967,
|
|
"num_tokens": 2318104.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.501170110702515,
|
|
"epoch": 0.10425987162030734,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999921532009323,
|
|
"loss": 6.2612,
|
|
"mean_token_accuracy": 0.12383703589439392,
|
|
"num_tokens": 2326807.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.528704977035522,
|
|
"epoch": 0.1046489009920249,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999919200263304,
|
|
"loss": 6.259,
|
|
"mean_token_accuracy": 0.12394311875104905,
|
|
"num_tokens": 2335921.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.505633020401001,
|
|
"epoch": 0.10503793036374247,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999916834378342,
|
|
"loss": 6.2739,
|
|
"mean_token_accuracy": 0.12304315939545632,
|
|
"num_tokens": 2344914.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.447750616073608,
|
|
"epoch": 0.10542695973546003,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999914434354472,
|
|
"loss": 6.2044,
|
|
"mean_token_accuracy": 0.125525876134634,
|
|
"num_tokens": 2353211.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.4893646240234375,
|
|
"epoch": 0.10581598910717759,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999912000191733,
|
|
"loss": 6.3487,
|
|
"mean_token_accuracy": 0.12199961394071579,
|
|
"num_tokens": 2361717.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.525090074539184,
|
|
"epoch": 0.10620501847889516,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499990953189016,
|
|
"loss": 6.2712,
|
|
"mean_token_accuracy": 0.13059643879532815,
|
|
"num_tokens": 2370114.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.630150699615479,
|
|
"epoch": 0.10659404785061272,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999907029449791,
|
|
"loss": 6.263,
|
|
"mean_token_accuracy": 0.12237593159079552,
|
|
"num_tokens": 2378820.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.354615974426269,
|
|
"epoch": 0.10698307722233029,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999904492870663,
|
|
"loss": 6.1715,
|
|
"mean_token_accuracy": 0.12704389467835425,
|
|
"num_tokens": 2387119.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.53058009147644,
|
|
"epoch": 0.10737210659404785,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999901922152816,
|
|
"loss": 6.2259,
|
|
"mean_token_accuracy": 0.12630244940519333,
|
|
"num_tokens": 2396246.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.406842041015625,
|
|
"epoch": 0.10776113596576542,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999899317296288,
|
|
"loss": 6.2855,
|
|
"mean_token_accuracy": 0.12351492792367935,
|
|
"num_tokens": 2405428.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.490512895584106,
|
|
"epoch": 0.10815016533748298,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999896678301121,
|
|
"loss": 6.2421,
|
|
"mean_token_accuracy": 0.1267989382147789,
|
|
"num_tokens": 2414669.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.563437604904175,
|
|
"epoch": 0.10853919470920055,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999894005167352,
|
|
"loss": 6.3,
|
|
"mean_token_accuracy": 0.12090388685464859,
|
|
"num_tokens": 2423193.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.500105094909668,
|
|
"epoch": 0.10892822408091811,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499989129789502,
|
|
"loss": 6.2664,
|
|
"mean_token_accuracy": 0.12048013284802436,
|
|
"num_tokens": 2431150.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.445392656326294,
|
|
"epoch": 0.10931725345263567,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999888556484172,
|
|
"loss": 6.2446,
|
|
"mean_token_accuracy": 0.12127585709095001,
|
|
"num_tokens": 2440337.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.441078138351441,
|
|
"epoch": 0.10970628282435324,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999885780934845,
|
|
"loss": 6.1736,
|
|
"mean_token_accuracy": 0.1296399176120758,
|
|
"num_tokens": 2449246.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.434943819046021,
|
|
"epoch": 0.1100953121960708,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999882971247081,
|
|
"loss": 6.1752,
|
|
"mean_token_accuracy": 0.13090624362230302,
|
|
"num_tokens": 2457982.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.44070029258728,
|
|
"epoch": 0.11048434156778837,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999880127420926,
|
|
"loss": 6.1661,
|
|
"mean_token_accuracy": 0.12823255807161332,
|
|
"num_tokens": 2466697.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.419079399108886,
|
|
"epoch": 0.11087337093950593,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999877249456421,
|
|
"loss": 6.1397,
|
|
"mean_token_accuracy": 0.13144427835941314,
|
|
"num_tokens": 2475457.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.336713647842407,
|
|
"epoch": 0.1112624003112235,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999874337353609,
|
|
"loss": 6.1393,
|
|
"mean_token_accuracy": 0.12938348650932313,
|
|
"num_tokens": 2484753.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.465570974349975,
|
|
"epoch": 0.11165142968294106,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999871391112535,
|
|
"loss": 6.2556,
|
|
"mean_token_accuracy": 0.124443519115448,
|
|
"num_tokens": 2492921.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.46670618057251,
|
|
"epoch": 0.11204045905465862,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999868410733244,
|
|
"loss": 6.224,
|
|
"mean_token_accuracy": 0.12451541647315026,
|
|
"num_tokens": 2501371.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.471292209625244,
|
|
"epoch": 0.11242948842637619,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000499986539621578,
|
|
"loss": 6.1023,
|
|
"mean_token_accuracy": 0.12834953069686889,
|
|
"num_tokens": 2509521.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.416775035858154,
|
|
"epoch": 0.11281851779809375,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999862347560191,
|
|
"loss": 6.2143,
|
|
"mean_token_accuracy": 0.12635174617171288,
|
|
"num_tokens": 2518316.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.514144420623779,
|
|
"epoch": 0.11320754716981132,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999859264766521,
|
|
"loss": 6.309,
|
|
"mean_token_accuracy": 0.1220340982079506,
|
|
"num_tokens": 2527549.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.501974773406983,
|
|
"epoch": 0.11359657654152888,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999856147834817,
|
|
"loss": 6.33,
|
|
"mean_token_accuracy": 0.12365049570798874,
|
|
"num_tokens": 2536341.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.390389823913575,
|
|
"epoch": 0.11398560591324645,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999852996765129,
|
|
"loss": 6.2144,
|
|
"mean_token_accuracy": 0.13640521019697188,
|
|
"num_tokens": 2544869.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.442426967620849,
|
|
"epoch": 0.11437463528496401,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999849811557502,
|
|
"loss": 6.1124,
|
|
"mean_token_accuracy": 0.1380823515355587,
|
|
"num_tokens": 2553432.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.435215473175049,
|
|
"epoch": 0.11476366465668159,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999846592211984,
|
|
"loss": 6.245,
|
|
"mean_token_accuracy": 0.12433946654200553,
|
|
"num_tokens": 2561996.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.435883617401123,
|
|
"epoch": 0.11515269402839914,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999843338728626,
|
|
"loss": 6.1732,
|
|
"mean_token_accuracy": 0.13035295605659486,
|
|
"num_tokens": 2571315.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.433837747573852,
|
|
"epoch": 0.1155417234001167,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999840051107476,
|
|
"loss": 6.2935,
|
|
"mean_token_accuracy": 0.12482402846217155,
|
|
"num_tokens": 2579589.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.433605575561524,
|
|
"epoch": 0.11593075277183428,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999836729348584,
|
|
"loss": 6.0607,
|
|
"mean_token_accuracy": 0.1283522941172123,
|
|
"num_tokens": 2588528.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.3824395656585695,
|
|
"epoch": 0.11631978214355183,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999833373452,
|
|
"loss": 6.1744,
|
|
"mean_token_accuracy": 0.12705983147025107,
|
|
"num_tokens": 2596820.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.30913896560669,
|
|
"epoch": 0.1167088115152694,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999829983417778,
|
|
"loss": 6.1168,
|
|
"mean_token_accuracy": 0.12735813558101655,
|
|
"num_tokens": 2605502.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.378449249267578,
|
|
"epoch": 0.11709784088698696,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999826559245965,
|
|
"loss": 6.1193,
|
|
"mean_token_accuracy": 0.13392857909202577,
|
|
"num_tokens": 2613974.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.370792722702026,
|
|
"epoch": 0.11748687025870454,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999823100936615,
|
|
"loss": 6.1965,
|
|
"mean_token_accuracy": 0.12880947291851044,
|
|
"num_tokens": 2622581.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.402956151962281,
|
|
"epoch": 0.1178758996304221,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999819608489781,
|
|
"loss": 6.0841,
|
|
"mean_token_accuracy": 0.1251236990094185,
|
|
"num_tokens": 2631868.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.339415788650513,
|
|
"epoch": 0.11826492900213967,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999816081905515,
|
|
"loss": 6.1093,
|
|
"mean_token_accuracy": 0.1355234570801258,
|
|
"num_tokens": 2640501.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.433193206787109,
|
|
"epoch": 0.11865395837385723,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999812521183872,
|
|
"loss": 6.1035,
|
|
"mean_token_accuracy": 0.13361863121390344,
|
|
"num_tokens": 2648916.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.406140279769898,
|
|
"epoch": 0.11904298774557479,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999808926324903,
|
|
"loss": 6.1896,
|
|
"mean_token_accuracy": 0.1334061346948147,
|
|
"num_tokens": 2657725.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.353977298736572,
|
|
"epoch": 0.11943201711729236,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999805297328665,
|
|
"loss": 6.1751,
|
|
"mean_token_accuracy": 0.1281532824039459,
|
|
"num_tokens": 2665983.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.392253303527832,
|
|
"epoch": 0.11982104648900992,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999801634195214,
|
|
"loss": 6.1957,
|
|
"mean_token_accuracy": 0.13333539366722108,
|
|
"num_tokens": 2674546.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.389540004730224,
|
|
"epoch": 0.12021007586072749,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999797936924603,
|
|
"loss": 6.1091,
|
|
"mean_token_accuracy": 0.13411504104733468,
|
|
"num_tokens": 2684088.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.37681622505188,
|
|
"epoch": 0.12059910523244505,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499979420551689,
|
|
"loss": 6.1664,
|
|
"mean_token_accuracy": 0.12699728310108185,
|
|
"num_tokens": 2693289.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.318667316436768,
|
|
"epoch": 0.12098813460416262,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499979043997213,
|
|
"loss": 6.095,
|
|
"mean_token_accuracy": 0.13104904145002366,
|
|
"num_tokens": 2701744.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.411156368255615,
|
|
"epoch": 0.12137716397588018,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999786640290381,
|
|
"loss": 6.1499,
|
|
"mean_token_accuracy": 0.12439182624220849,
|
|
"num_tokens": 2710584.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.411997509002686,
|
|
"epoch": 0.12176619334759774,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999782806471701,
|
|
"loss": 6.1491,
|
|
"mean_token_accuracy": 0.13031079471111298,
|
|
"num_tokens": 2719478.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.465567684173584,
|
|
"epoch": 0.12215522271931531,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999778938516147,
|
|
"loss": 6.2286,
|
|
"mean_token_accuracy": 0.12305473163723946,
|
|
"num_tokens": 2729105.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.401231145858764,
|
|
"epoch": 0.12254425209103287,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499977503642378,
|
|
"loss": 6.1908,
|
|
"mean_token_accuracy": 0.1272389329969883,
|
|
"num_tokens": 2738300.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.384681034088135,
|
|
"epoch": 0.12293328146275044,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999771100194656,
|
|
"loss": 6.1335,
|
|
"mean_token_accuracy": 0.12494338452816009,
|
|
"num_tokens": 2747236.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.289424848556519,
|
|
"epoch": 0.123322310834468,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999767129828837,
|
|
"loss": 6.0956,
|
|
"mean_token_accuracy": 0.13419784530997275,
|
|
"num_tokens": 2755919.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.305175161361694,
|
|
"epoch": 0.12371134020618557,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999763125326383,
|
|
"loss": 6.0768,
|
|
"mean_token_accuracy": 0.1307978369295597,
|
|
"num_tokens": 2764469.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.355486297607422,
|
|
"epoch": 0.12410036957790313,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999759086687355,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.1366819642484188,
|
|
"num_tokens": 2772663.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.419379472732544,
|
|
"epoch": 0.1244893989496207,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999755013911813,
|
|
"loss": 6.1161,
|
|
"mean_token_accuracy": 0.12876046895980836,
|
|
"num_tokens": 2780719.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.330186557769776,
|
|
"epoch": 0.12487842832133826,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499975090699982,
|
|
"loss": 6.1714,
|
|
"mean_token_accuracy": 0.128857558965683,
|
|
"num_tokens": 2789186.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.337528562545776,
|
|
"epoch": 0.12526745769305583,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999746765951438,
|
|
"loss": 6.0856,
|
|
"mean_token_accuracy": 0.13346567153930664,
|
|
"num_tokens": 2797993.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.312220811843872,
|
|
"epoch": 0.1256564870647734,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999742590766729,
|
|
"loss": 6.0464,
|
|
"mean_token_accuracy": 0.13435178622603416,
|
|
"num_tokens": 2806375.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.440674829483032,
|
|
"epoch": 0.12604551643649095,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999738381445757,
|
|
"loss": 6.1942,
|
|
"mean_token_accuracy": 0.13562749326229095,
|
|
"num_tokens": 2814772.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.202065896987915,
|
|
"epoch": 0.1264345458082085,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999734137988586,
|
|
"loss": 6.0582,
|
|
"mean_token_accuracy": 0.13596921488642694,
|
|
"num_tokens": 2824231.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.376500511169434,
|
|
"epoch": 0.1268235751799261,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499972986039528,
|
|
"loss": 6.1245,
|
|
"mean_token_accuracy": 0.12782634794712067,
|
|
"num_tokens": 2833470.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.353403902053833,
|
|
"epoch": 0.12721260455164365,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999725548665904,
|
|
"loss": 6.1327,
|
|
"mean_token_accuracy": 0.1281338281929493,
|
|
"num_tokens": 2843010.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.346253395080566,
|
|
"epoch": 0.1276016339233612,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999721202800524,
|
|
"loss": 6.0231,
|
|
"mean_token_accuracy": 0.13678104057908058,
|
|
"num_tokens": 2851545.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.269683694839477,
|
|
"epoch": 0.12799066329507877,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999716822799206,
|
|
"loss": 6.1796,
|
|
"mean_token_accuracy": 0.11961811035871506,
|
|
"num_tokens": 2861230.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.395336675643921,
|
|
"epoch": 0.12837969266679633,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999712408662016,
|
|
"loss": 6.1356,
|
|
"mean_token_accuracy": 0.1289409004151821,
|
|
"num_tokens": 2869436.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.306952619552613,
|
|
"epoch": 0.12876872203851392,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999707960389021,
|
|
"loss": 5.9996,
|
|
"mean_token_accuracy": 0.13151076734066008,
|
|
"num_tokens": 2877688.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.365733051300049,
|
|
"epoch": 0.12915775141023147,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999703477980288,
|
|
"loss": 6.1389,
|
|
"mean_token_accuracy": 0.13166750520467757,
|
|
"num_tokens": 2887043.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.262747430801392,
|
|
"epoch": 0.12954678078194903,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999698961435885,
|
|
"loss": 6.0721,
|
|
"mean_token_accuracy": 0.13516117706894876,
|
|
"num_tokens": 2895732.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.256302070617676,
|
|
"epoch": 0.1299358101536666,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999694410755882,
|
|
"loss": 6.039,
|
|
"mean_token_accuracy": 0.13851652070879936,
|
|
"num_tokens": 2904162.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.356344509124756,
|
|
"epoch": 0.13032483952538418,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999689825940347,
|
|
"loss": 6.1758,
|
|
"mean_token_accuracy": 0.13067347109317778,
|
|
"num_tokens": 2912783.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.319488096237182,
|
|
"epoch": 0.13071386889710174,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999685206989349,
|
|
"loss": 6.0558,
|
|
"mean_token_accuracy": 0.13287809044122695,
|
|
"num_tokens": 2921027.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.344622087478638,
|
|
"epoch": 0.1311028982688193,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999680553902959,
|
|
"loss": 6.093,
|
|
"mean_token_accuracy": 0.13244052454829217,
|
|
"num_tokens": 2930398.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.316963481903076,
|
|
"epoch": 0.13149192764053685,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999675866681247,
|
|
"loss": 6.1126,
|
|
"mean_token_accuracy": 0.1291515350341797,
|
|
"num_tokens": 2938703.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.272860383987426,
|
|
"epoch": 0.1318809570122544,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999671145324286,
|
|
"loss": 6.0394,
|
|
"mean_token_accuracy": 0.13433808013796805,
|
|
"num_tokens": 2947007.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.319776296615601,
|
|
"epoch": 0.132269986383972,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999666389832144,
|
|
"loss": 6.1923,
|
|
"mean_token_accuracy": 0.13449379578232765,
|
|
"num_tokens": 2955485.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.353970575332641,
|
|
"epoch": 0.13265901575568956,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999661600204897,
|
|
"loss": 6.0481,
|
|
"mean_token_accuracy": 0.1327715963125229,
|
|
"num_tokens": 2964416.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.239326429367066,
|
|
"epoch": 0.13304804512740712,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999656776442615,
|
|
"loss": 6.0398,
|
|
"mean_token_accuracy": 0.1316245622932911,
|
|
"num_tokens": 2972737.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.29252290725708,
|
|
"epoch": 0.13343707449912467,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999651918545372,
|
|
"loss": 6.084,
|
|
"mean_token_accuracy": 0.13347245752811432,
|
|
"num_tokens": 2981166.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.313875722885132,
|
|
"epoch": 0.13382610387084226,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999647026513243,
|
|
"loss": 6.124,
|
|
"mean_token_accuracy": 0.13230146765708922,
|
|
"num_tokens": 2989689.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.354332733154297,
|
|
"epoch": 0.13421513324255982,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00049996421003463,
|
|
"loss": 6.0353,
|
|
"mean_token_accuracy": 0.1331894539296627,
|
|
"num_tokens": 2998793.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.235461759567261,
|
|
"epoch": 0.13460416261427738,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999637140044619,
|
|
"loss": 6.1931,
|
|
"mean_token_accuracy": 0.12982380986213685,
|
|
"num_tokens": 3007320.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.328571414947509,
|
|
"epoch": 0.13499319198599494,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999632145608275,
|
|
"loss": 6.0911,
|
|
"mean_token_accuracy": 0.13207585886120796,
|
|
"num_tokens": 3015024.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.351219606399536,
|
|
"epoch": 0.1353822213577125,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999627117037343,
|
|
"loss": 6.1831,
|
|
"mean_token_accuracy": 0.1294490687549114,
|
|
"num_tokens": 3023058.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.363010501861572,
|
|
"epoch": 0.13577125072943008,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00049996220543319,
|
|
"loss": 6.0924,
|
|
"mean_token_accuracy": 0.13458985537290574,
|
|
"num_tokens": 3031308.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.337850189208984,
|
|
"epoch": 0.13616028010114764,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999616957492025,
|
|
"loss": 6.1513,
|
|
"mean_token_accuracy": 0.1289216734468937,
|
|
"num_tokens": 3039598.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.253518009185791,
|
|
"epoch": 0.1365493094728652,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999611826517793,
|
|
"loss": 5.9714,
|
|
"mean_token_accuracy": 0.1398603707551956,
|
|
"num_tokens": 3047598.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.273720216751099,
|
|
"epoch": 0.13693833884458276,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999606661409281,
|
|
"loss": 6.1199,
|
|
"mean_token_accuracy": 0.1361253760755062,
|
|
"num_tokens": 3055702.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.330643892288208,
|
|
"epoch": 0.13732736821630034,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999601462166569,
|
|
"loss": 5.9841,
|
|
"mean_token_accuracy": 0.14291464164853096,
|
|
"num_tokens": 3063908.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.251221227645874,
|
|
"epoch": 0.1377163975880179,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999596228789736,
|
|
"loss": 6.0754,
|
|
"mean_token_accuracy": 0.1333239495754242,
|
|
"num_tokens": 3072077.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.303908920288086,
|
|
"epoch": 0.13810542695973546,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999590961278859,
|
|
"loss": 6.0791,
|
|
"mean_token_accuracy": 0.13312057927250862,
|
|
"num_tokens": 3080498.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.31710524559021,
|
|
"epoch": 0.13849445633145302,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999585659634021,
|
|
"loss": 6.0814,
|
|
"mean_token_accuracy": 0.1339930735528469,
|
|
"num_tokens": 3089055.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.248744344711303,
|
|
"epoch": 0.13888348570317058,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999580323855301,
|
|
"loss": 6.0718,
|
|
"mean_token_accuracy": 0.1378532275557518,
|
|
"num_tokens": 3096944.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.228180599212647,
|
|
"epoch": 0.13927251507488816,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999574953942781,
|
|
"loss": 5.965,
|
|
"mean_token_accuracy": 0.13897001892328262,
|
|
"num_tokens": 3105596.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.191677761077881,
|
|
"epoch": 0.13966154444660572,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999569549896541,
|
|
"loss": 5.958,
|
|
"mean_token_accuracy": 0.14424095302820206,
|
|
"num_tokens": 3114349.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.258058547973633,
|
|
"epoch": 0.14005057381832328,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999564111716665,
|
|
"loss": 6.0799,
|
|
"mean_token_accuracy": 0.12551943436264992,
|
|
"num_tokens": 3122490.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.355373287200928,
|
|
"epoch": 0.14043960319004084,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999558639403232,
|
|
"loss": 6.1203,
|
|
"mean_token_accuracy": 0.13192636370658875,
|
|
"num_tokens": 3130988.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.246408748626709,
|
|
"epoch": 0.1408286325617584,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999553132956328,
|
|
"loss": 5.9784,
|
|
"mean_token_accuracy": 0.13481251522898674,
|
|
"num_tokens": 3139488.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.221766948699951,
|
|
"epoch": 0.14121766193347599,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999547592376035,
|
|
"loss": 6.0288,
|
|
"mean_token_accuracy": 0.13629044219851494,
|
|
"num_tokens": 3147955.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.249310064315796,
|
|
"epoch": 0.14160669130519354,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999542017662438,
|
|
"loss": 6.0759,
|
|
"mean_token_accuracy": 0.1276159830391407,
|
|
"num_tokens": 3157608.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.328677940368652,
|
|
"epoch": 0.1419957206769111,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999536408815623,
|
|
"loss": 6.0303,
|
|
"mean_token_accuracy": 0.130377709120512,
|
|
"num_tokens": 3166124.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.159740209579468,
|
|
"epoch": 0.14238475004862866,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999530765835672,
|
|
"loss": 6.0358,
|
|
"mean_token_accuracy": 0.13254115357995033,
|
|
"num_tokens": 3175069.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.292894077301026,
|
|
"epoch": 0.14277377942034625,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999525088722673,
|
|
"loss": 6.0664,
|
|
"mean_token_accuracy": 0.13529409915208818,
|
|
"num_tokens": 3184259.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.275870656967163,
|
|
"epoch": 0.1431628087920638,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999519377476711,
|
|
"loss": 5.9672,
|
|
"mean_token_accuracy": 0.1381848506629467,
|
|
"num_tokens": 3193015.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.267138957977295,
|
|
"epoch": 0.14355183816378136,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999513632097872,
|
|
"loss": 5.9147,
|
|
"mean_token_accuracy": 0.14502743408083915,
|
|
"num_tokens": 3201624.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.208207750320435,
|
|
"epoch": 0.14394086753549892,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999507852586245,
|
|
"loss": 6.0294,
|
|
"mean_token_accuracy": 0.13966942057013512,
|
|
"num_tokens": 3209474.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.183934068679809,
|
|
"epoch": 0.14432989690721648,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999502038941917,
|
|
"loss": 6.0023,
|
|
"mean_token_accuracy": 0.13654958382248877,
|
|
"num_tokens": 3218550.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.118973255157471,
|
|
"epoch": 0.14471892627893407,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999496191164975,
|
|
"loss": 5.9653,
|
|
"mean_token_accuracy": 0.13626407235860824,
|
|
"num_tokens": 3227108.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.250623989105224,
|
|
"epoch": 0.14510795565065163,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499949030925551,
|
|
"loss": 6.0032,
|
|
"mean_token_accuracy": 0.13892803117632865,
|
|
"num_tokens": 3235785.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.293147802352905,
|
|
"epoch": 0.14549698502236919,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999484393213609,
|
|
"loss": 6.0377,
|
|
"mean_token_accuracy": 0.1293921411037445,
|
|
"num_tokens": 3244180.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.158266830444336,
|
|
"epoch": 0.14588601439408674,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999478443039363,
|
|
"loss": 5.9157,
|
|
"mean_token_accuracy": 0.14264118522405625,
|
|
"num_tokens": 3253098.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.26281852722168,
|
|
"epoch": 0.14627504376580433,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999472458732862,
|
|
"loss": 5.962,
|
|
"mean_token_accuracy": 0.14164620488882065,
|
|
"num_tokens": 3261726.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.122699928283692,
|
|
"epoch": 0.1466640731375219,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999466440294198,
|
|
"loss": 5.9218,
|
|
"mean_token_accuracy": 0.13797034472227096,
|
|
"num_tokens": 3270362.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.218784666061401,
|
|
"epoch": 0.14705310250923945,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499946038772346,
|
|
"loss": 5.9119,
|
|
"mean_token_accuracy": 0.1409492813050747,
|
|
"num_tokens": 3278332.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.106905126571656,
|
|
"epoch": 0.147442131880957,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999454301020741,
|
|
"loss": 5.8984,
|
|
"mean_token_accuracy": 0.14537974447011948,
|
|
"num_tokens": 3286800.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.261422252655029,
|
|
"epoch": 0.14783116125267456,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999448180186133,
|
|
"loss": 6.1243,
|
|
"mean_token_accuracy": 0.12735687866806983,
|
|
"num_tokens": 3296186.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.170867204666138,
|
|
"epoch": 0.14822019062439215,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499944202521973,
|
|
"loss": 5.9874,
|
|
"mean_token_accuracy": 0.14373966082930564,
|
|
"num_tokens": 3303973.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.154075765609742,
|
|
"epoch": 0.1486092199961097,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999435836121624,
|
|
"loss": 5.9417,
|
|
"mean_token_accuracy": 0.13721608817577363,
|
|
"num_tokens": 3312550.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.231463432312012,
|
|
"epoch": 0.14899824936782727,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499942961289191,
|
|
"loss": 6.0136,
|
|
"mean_token_accuracy": 0.13601985946297646,
|
|
"num_tokens": 3321342.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.136085319519043,
|
|
"epoch": 0.14938727873954483,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999423355530683,
|
|
"loss": 5.8833,
|
|
"mean_token_accuracy": 0.14982874765992166,
|
|
"num_tokens": 3329293.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.077541828155518,
|
|
"epoch": 0.1497763081112624,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999417064038035,
|
|
"loss": 5.947,
|
|
"mean_token_accuracy": 0.135797318816185,
|
|
"num_tokens": 3338278.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.248018217086792,
|
|
"epoch": 0.15016533748297997,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999410738414065,
|
|
"loss": 6.0446,
|
|
"mean_token_accuracy": 0.1355997994542122,
|
|
"num_tokens": 3346757.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.1532470226287845,
|
|
"epoch": 0.15055436685469753,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999404378658866,
|
|
"loss": 6.0451,
|
|
"mean_token_accuracy": 0.1347198210656643,
|
|
"num_tokens": 3355903.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.208436155319214,
|
|
"epoch": 0.1509433962264151,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999397984772536,
|
|
"loss": 6.0141,
|
|
"mean_token_accuracy": 0.12824626341462136,
|
|
"num_tokens": 3365440.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.216444635391236,
|
|
"epoch": 0.15133242559813265,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999391556755172,
|
|
"loss": 5.9763,
|
|
"mean_token_accuracy": 0.1436944492161274,
|
|
"num_tokens": 3373672.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.172102642059326,
|
|
"epoch": 0.15172145496985023,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999385094606872,
|
|
"loss": 5.9552,
|
|
"mean_token_accuracy": 0.13290092200040818,
|
|
"num_tokens": 3382733.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.100259685516358,
|
|
"epoch": 0.1521104843415678,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999378598327733,
|
|
"loss": 5.9076,
|
|
"mean_token_accuracy": 0.1429830349981785,
|
|
"num_tokens": 3390842.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.200795269012451,
|
|
"epoch": 0.15249951371328535,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999372067917854,
|
|
"loss": 6.061,
|
|
"mean_token_accuracy": 0.13028706163167952,
|
|
"num_tokens": 3399761.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.219650220870972,
|
|
"epoch": 0.1528885430850029,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999365503377335,
|
|
"loss": 5.9837,
|
|
"mean_token_accuracy": 0.13638316243886947,
|
|
"num_tokens": 3408986.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.199184322357178,
|
|
"epoch": 0.1532775724567205,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999358904706273,
|
|
"loss": 5.9356,
|
|
"mean_token_accuracy": 0.13719403147697448,
|
|
"num_tokens": 3418051.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.225965929031372,
|
|
"epoch": 0.15366660182843805,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999352271904771,
|
|
"loss": 6.0436,
|
|
"mean_token_accuracy": 0.13756765872240068,
|
|
"num_tokens": 3427185.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.179631471633911,
|
|
"epoch": 0.1540556312001556,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999345604972928,
|
|
"loss": 5.9495,
|
|
"mean_token_accuracy": 0.13750605583190917,
|
|
"num_tokens": 3435367.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.154869127273559,
|
|
"epoch": 0.15444466057187317,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999338903910846,
|
|
"loss": 5.9934,
|
|
"mean_token_accuracy": 0.1389468789100647,
|
|
"num_tokens": 3443451.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.200529718399048,
|
|
"epoch": 0.15483368994359073,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999332168718626,
|
|
"loss": 5.9893,
|
|
"mean_token_accuracy": 0.1442691780626774,
|
|
"num_tokens": 3451038.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.408123874664307,
|
|
"epoch": 0.15522271931530832,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999325399396371,
|
|
"loss": 6.1241,
|
|
"mean_token_accuracy": 0.1256192870438099,
|
|
"num_tokens": 3459693.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.269746255874634,
|
|
"epoch": 0.15561174868702587,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999318595944183,
|
|
"loss": 6.0106,
|
|
"mean_token_accuracy": 0.13469778150320053,
|
|
"num_tokens": 3468347.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.145987224578858,
|
|
"epoch": 0.15600077805874343,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999311758362166,
|
|
"loss": 5.986,
|
|
"mean_token_accuracy": 0.13514223098754882,
|
|
"num_tokens": 3476030.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.12372317314148,
|
|
"epoch": 0.156389807430461,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999304886650422,
|
|
"loss": 5.9609,
|
|
"mean_token_accuracy": 0.13282474353909493,
|
|
"num_tokens": 3484840.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.290483140945435,
|
|
"epoch": 0.15677883680217858,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999297980809058,
|
|
"loss": 6.0489,
|
|
"mean_token_accuracy": 0.13376422077417374,
|
|
"num_tokens": 3492662.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.2352056980133055,
|
|
"epoch": 0.15716786617389614,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999291040838176,
|
|
"loss": 5.9688,
|
|
"mean_token_accuracy": 0.13237249329686165,
|
|
"num_tokens": 3501582.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.179763507843018,
|
|
"epoch": 0.1575568955456137,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999284066737884,
|
|
"loss": 5.9639,
|
|
"mean_token_accuracy": 0.14239997863769532,
|
|
"num_tokens": 3510141.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.209929418563843,
|
|
"epoch": 0.15794592491733125,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999277058508285,
|
|
"loss": 6.0049,
|
|
"mean_token_accuracy": 0.14213063940405846,
|
|
"num_tokens": 3518530.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.1083790302276615,
|
|
"epoch": 0.1583349542890488,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999270016149486,
|
|
"loss": 5.9775,
|
|
"mean_token_accuracy": 0.1358012966811657,
|
|
"num_tokens": 3526815.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.179563379287719,
|
|
"epoch": 0.1587239836607664,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999262939661596,
|
|
"loss": 6.0282,
|
|
"mean_token_accuracy": 0.13272086828947066,
|
|
"num_tokens": 3535840.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.240152835845947,
|
|
"epoch": 0.15911301303248396,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999255829044721,
|
|
"loss": 6.0579,
|
|
"mean_token_accuracy": 0.13129353299736976,
|
|
"num_tokens": 3544876.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.140031433105468,
|
|
"epoch": 0.15950204240420152,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999248684298968,
|
|
"loss": 5.7949,
|
|
"mean_token_accuracy": 0.14725889563560485,
|
|
"num_tokens": 3553018.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.0304547309875485,
|
|
"epoch": 0.15989107177591907,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999241505424447,
|
|
"loss": 5.8511,
|
|
"mean_token_accuracy": 0.1435144364833832,
|
|
"num_tokens": 3560909.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.116934061050415,
|
|
"epoch": 0.16028010114763663,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999234292421265,
|
|
"loss": 5.9999,
|
|
"mean_token_accuracy": 0.1397472143173218,
|
|
"num_tokens": 3569235.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.105283117294311,
|
|
"epoch": 0.16066913051935422,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999227045289535,
|
|
"loss": 5.8792,
|
|
"mean_token_accuracy": 0.14063235372304916,
|
|
"num_tokens": 3577646.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.068844556808472,
|
|
"epoch": 0.16105815989107178,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999219764029363,
|
|
"loss": 5.9745,
|
|
"mean_token_accuracy": 0.1359837457537651,
|
|
"num_tokens": 3586499.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.221855163574219,
|
|
"epoch": 0.16144718926278934,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999212448640861,
|
|
"loss": 5.9812,
|
|
"mean_token_accuracy": 0.14166299402713775,
|
|
"num_tokens": 3595391.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.117988729476929,
|
|
"epoch": 0.1618362186345069,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999205099124141,
|
|
"loss": 5.903,
|
|
"mean_token_accuracy": 0.14056897163391113,
|
|
"num_tokens": 3603774.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.214944982528687,
|
|
"epoch": 0.16222524800622448,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999197715479313,
|
|
"loss": 5.9841,
|
|
"mean_token_accuracy": 0.13269646242260932,
|
|
"num_tokens": 3611980.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.1437524318695065,
|
|
"epoch": 0.16261427737794204,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999190297706489,
|
|
"loss": 5.902,
|
|
"mean_token_accuracy": 0.1393118217587471,
|
|
"num_tokens": 3620902.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.299076747894287,
|
|
"epoch": 0.1630033067496596,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999182845805783,
|
|
"loss": 6.1871,
|
|
"mean_token_accuracy": 0.12861791327595712,
|
|
"num_tokens": 3628924.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.2256190299987795,
|
|
"epoch": 0.16339233612137716,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999175359777306,
|
|
"loss": 6.0231,
|
|
"mean_token_accuracy": 0.13702933117747307,
|
|
"num_tokens": 3637538.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.148886060714721,
|
|
"epoch": 0.16378136549309472,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999167839621174,
|
|
"loss": 6.0424,
|
|
"mean_token_accuracy": 0.130807376652956,
|
|
"num_tokens": 3646309.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.18635630607605,
|
|
"epoch": 0.1641703948648123,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999160285337501,
|
|
"loss": 5.8807,
|
|
"mean_token_accuracy": 0.14085181877017022,
|
|
"num_tokens": 3655204.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.139962005615234,
|
|
"epoch": 0.16455942423652986,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999152696926399,
|
|
"loss": 6.031,
|
|
"mean_token_accuracy": 0.1334392912685871,
|
|
"num_tokens": 3663939.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.174469661712647,
|
|
"epoch": 0.16494845360824742,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999145074387985,
|
|
"loss": 5.9681,
|
|
"mean_token_accuracy": 0.13877132534980774,
|
|
"num_tokens": 3673167.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.170883893966675,
|
|
"epoch": 0.16533748297996498,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999137417722374,
|
|
"loss": 5.9079,
|
|
"mean_token_accuracy": 0.1417030766606331,
|
|
"num_tokens": 3682234.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.110505771636963,
|
|
"epoch": 0.16572651235168256,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999129726929684,
|
|
"loss": 5.904,
|
|
"mean_token_accuracy": 0.14176712557673454,
|
|
"num_tokens": 3690835.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.160515642166137,
|
|
"epoch": 0.16611554172340012,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999122002010029,
|
|
"loss": 5.9654,
|
|
"mean_token_accuracy": 0.13802013844251632,
|
|
"num_tokens": 3699348.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.086480808258057,
|
|
"epoch": 0.16650457109511768,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999114242963527,
|
|
"loss": 5.8711,
|
|
"mean_token_accuracy": 0.1402495212852955,
|
|
"num_tokens": 3708205.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.106543445587159,
|
|
"epoch": 0.16689360046683524,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999106449790298,
|
|
"loss": 5.9423,
|
|
"mean_token_accuracy": 0.1402938574552536,
|
|
"num_tokens": 3717016.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.246592807769775,
|
|
"epoch": 0.1672826298385528,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999098622490458,
|
|
"loss": 5.9544,
|
|
"mean_token_accuracy": 0.13701125010848045,
|
|
"num_tokens": 3725509.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.154575967788697,
|
|
"epoch": 0.16767165921027039,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999090761064125,
|
|
"loss": 6.0286,
|
|
"mean_token_accuracy": 0.1339248612523079,
|
|
"num_tokens": 3734674.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.060240173339844,
|
|
"epoch": 0.16806068858198794,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499908286551142,
|
|
"loss": 5.8456,
|
|
"mean_token_accuracy": 0.1407431736588478,
|
|
"num_tokens": 3742930.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.154189491271973,
|
|
"epoch": 0.1684497179537055,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999074935832463,
|
|
"loss": 5.9369,
|
|
"mean_token_accuracy": 0.1409689135849476,
|
|
"num_tokens": 3751314.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.216179037094117,
|
|
"epoch": 0.16883874732542306,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999066972027373,
|
|
"loss": 6.0535,
|
|
"mean_token_accuracy": 0.13319066762924195,
|
|
"num_tokens": 3760229.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.285803413391113,
|
|
"epoch": 0.16922777669714065,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999058974096271,
|
|
"loss": 6.0545,
|
|
"mean_token_accuracy": 0.1335298717021942,
|
|
"num_tokens": 3769037.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.052758312225341,
|
|
"epoch": 0.1696168060688582,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499905094203928,
|
|
"loss": 5.9238,
|
|
"mean_token_accuracy": 0.13934388458728791,
|
|
"num_tokens": 3777686.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.218620347976684,
|
|
"epoch": 0.17000583544057576,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499904287585652,
|
|
"loss": 6.0044,
|
|
"mean_token_accuracy": 0.13825156837701796,
|
|
"num_tokens": 3786412.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.192234373092651,
|
|
"epoch": 0.17039486481229332,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999034775548113,
|
|
"loss": 6.0351,
|
|
"mean_token_accuracy": 0.13853697702288628,
|
|
"num_tokens": 3794981.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.155090808868408,
|
|
"epoch": 0.17078389418401088,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999026641114185,
|
|
"loss": 5.9303,
|
|
"mean_token_accuracy": 0.14125299602746963,
|
|
"num_tokens": 3803069.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.151627492904663,
|
|
"epoch": 0.17117292355572847,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999018472554857,
|
|
"loss": 6.0112,
|
|
"mean_token_accuracy": 0.1394211769104004,
|
|
"num_tokens": 3811986.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.219188404083252,
|
|
"epoch": 0.17156195292744603,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999010269870253,
|
|
"loss": 5.9302,
|
|
"mean_token_accuracy": 0.13892962485551835,
|
|
"num_tokens": 3820626.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.105683422088623,
|
|
"epoch": 0.17195098229916359,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999002033060498,
|
|
"loss": 5.9254,
|
|
"mean_token_accuracy": 0.1396380692720413,
|
|
"num_tokens": 3828608.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.041509485244751,
|
|
"epoch": 0.17234001167088114,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998993762125716,
|
|
"loss": 5.8795,
|
|
"mean_token_accuracy": 0.1437774755060673,
|
|
"num_tokens": 3837059.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.148551082611084,
|
|
"epoch": 0.17272904104259873,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998985457066034,
|
|
"loss": 5.8953,
|
|
"mean_token_accuracy": 0.13735355138778688,
|
|
"num_tokens": 3845137.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.128031158447266,
|
|
"epoch": 0.1731180704143163,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998977117881576,
|
|
"loss": 5.8861,
|
|
"mean_token_accuracy": 0.14574987590312957,
|
|
"num_tokens": 3854012.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.015646696090698,
|
|
"epoch": 0.17350709978603385,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998968744572472,
|
|
"loss": 5.8295,
|
|
"mean_token_accuracy": 0.1409018814563751,
|
|
"num_tokens": 3862308.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.067210721969604,
|
|
"epoch": 0.1738961291577514,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998960337138845,
|
|
"loss": 5.7717,
|
|
"mean_token_accuracy": 0.13879043981432915,
|
|
"num_tokens": 3870975.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.087196779251099,
|
|
"epoch": 0.17428515852946896,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998951895580826,
|
|
"loss": 5.9544,
|
|
"mean_token_accuracy": 0.14272485896945,
|
|
"num_tokens": 3879621.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.093369865417481,
|
|
"epoch": 0.17467418790118655,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998943419898542,
|
|
"loss": 5.9166,
|
|
"mean_token_accuracy": 0.13817212730646133,
|
|
"num_tokens": 3889214.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.146738815307617,
|
|
"epoch": 0.1750632172729041,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998934910092119,
|
|
"loss": 5.9504,
|
|
"mean_token_accuracy": 0.14284390732645988,
|
|
"num_tokens": 3898250.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.129539108276367,
|
|
"epoch": 0.17545224664462167,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998926366161689,
|
|
"loss": 5.9798,
|
|
"mean_token_accuracy": 0.13206198140978814,
|
|
"num_tokens": 3906971.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.1653541088104244,
|
|
"epoch": 0.17584127601633923,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998917788107383,
|
|
"loss": 6.0139,
|
|
"mean_token_accuracy": 0.13972242698073387,
|
|
"num_tokens": 3916663.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.103351974487305,
|
|
"epoch": 0.17623030538805678,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998909175929326,
|
|
"loss": 5.8942,
|
|
"mean_token_accuracy": 0.14154435321688652,
|
|
"num_tokens": 3926848.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.034053564071655,
|
|
"epoch": 0.17661933475977437,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998900529627653,
|
|
"loss": 5.8613,
|
|
"mean_token_accuracy": 0.1404354229569435,
|
|
"num_tokens": 3935729.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.141492509841919,
|
|
"epoch": 0.17700836413149193,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998891849202495,
|
|
"loss": 5.8766,
|
|
"mean_token_accuracy": 0.1424740418791771,
|
|
"num_tokens": 3943408.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.052723979949951,
|
|
"epoch": 0.1773973935032095,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499888313465398,
|
|
"loss": 5.8509,
|
|
"mean_token_accuracy": 0.14049414843320845,
|
|
"num_tokens": 3952473.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.178114128112793,
|
|
"epoch": 0.17778642287492705,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998874385982247,
|
|
"loss": 6.0018,
|
|
"mean_token_accuracy": 0.13325022533535957,
|
|
"num_tokens": 3960878.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.208947801589966,
|
|
"epoch": 0.17817545224664463,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998865603187421,
|
|
"loss": 5.945,
|
|
"mean_token_accuracy": 0.13925340324640273,
|
|
"num_tokens": 3969282.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.132673740386963,
|
|
"epoch": 0.1785644816183622,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499885678626964,
|
|
"loss": 5.9267,
|
|
"mean_token_accuracy": 0.14256497994065284,
|
|
"num_tokens": 3978516.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.066269874572754,
|
|
"epoch": 0.17895351099007975,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998847935229038,
|
|
"loss": 5.7855,
|
|
"mean_token_accuracy": 0.15060577318072318,
|
|
"num_tokens": 3986580.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.910192060470581,
|
|
"epoch": 0.1793425403617973,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998839050065746,
|
|
"loss": 5.8052,
|
|
"mean_token_accuracy": 0.14743324518203735,
|
|
"num_tokens": 3995144.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.101610565185547,
|
|
"epoch": 0.17973156973351487,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998830130779902,
|
|
"loss": 5.8075,
|
|
"mean_token_accuracy": 0.13889141082763673,
|
|
"num_tokens": 4003887.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.0803686618804935,
|
|
"epoch": 0.18012059910523245,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499882117737164,
|
|
"loss": 5.9209,
|
|
"mean_token_accuracy": 0.14422064125537873,
|
|
"num_tokens": 4012607.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.053954172134399,
|
|
"epoch": 0.18050962847695,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998812189841096,
|
|
"loss": 6.0034,
|
|
"mean_token_accuracy": 0.13622427582740784,
|
|
"num_tokens": 4021950.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.1665068626403805,
|
|
"epoch": 0.18089865784866757,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998803168188407,
|
|
"loss": 5.9668,
|
|
"mean_token_accuracy": 0.1415689304471016,
|
|
"num_tokens": 4031076.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.990097284317017,
|
|
"epoch": 0.18128768722038513,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998794112413708,
|
|
"loss": 5.8054,
|
|
"mean_token_accuracy": 0.14801988750696182,
|
|
"num_tokens": 4040414.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.18867506980896,
|
|
"epoch": 0.18167671659210272,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998785022517137,
|
|
"loss": 5.8924,
|
|
"mean_token_accuracy": 0.14523087441921234,
|
|
"num_tokens": 4048931.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.915593385696411,
|
|
"epoch": 0.18206574596382027,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998775898498835,
|
|
"loss": 5.7899,
|
|
"mean_token_accuracy": 0.1424514263868332,
|
|
"num_tokens": 4057688.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.047796154022217,
|
|
"epoch": 0.18245477533553783,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998766740358936,
|
|
"loss": 5.9117,
|
|
"mean_token_accuracy": 0.14413589462637902,
|
|
"num_tokens": 4066365.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.0719398021697994,
|
|
"epoch": 0.1828438047072554,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998757548097582,
|
|
"loss": 5.7968,
|
|
"mean_token_accuracy": 0.14763821363449098,
|
|
"num_tokens": 4075136.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.112574434280395,
|
|
"epoch": 0.18323283407897295,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998748321714911,
|
|
"loss": 5.9058,
|
|
"mean_token_accuracy": 0.1457724839448929,
|
|
"num_tokens": 4083337.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.00722303390503,
|
|
"epoch": 0.18362186345069054,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998739061211065,
|
|
"loss": 5.8555,
|
|
"mean_token_accuracy": 0.14413827881217003,
|
|
"num_tokens": 4091201.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.140283298492432,
|
|
"epoch": 0.1840108928224081,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998729766586181,
|
|
"loss": 5.9072,
|
|
"mean_token_accuracy": 0.14183114990592002,
|
|
"num_tokens": 4099480.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.984076595306396,
|
|
"epoch": 0.18439992219412565,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998720437840403,
|
|
"loss": 5.8158,
|
|
"mean_token_accuracy": 0.1437339261174202,
|
|
"num_tokens": 4108151.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.961683034896851,
|
|
"epoch": 0.1847889515658432,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998711074973871,
|
|
"loss": 5.8251,
|
|
"mean_token_accuracy": 0.1457428365945816,
|
|
"num_tokens": 4117380.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.036372423171997,
|
|
"epoch": 0.1851779809375608,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998701677986728,
|
|
"loss": 5.8689,
|
|
"mean_token_accuracy": 0.14735556095838548,
|
|
"num_tokens": 4126757.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.031168508529663,
|
|
"epoch": 0.18556701030927836,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998692246879116,
|
|
"loss": 5.7891,
|
|
"mean_token_accuracy": 0.146223184466362,
|
|
"num_tokens": 4135326.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.053634834289551,
|
|
"epoch": 0.18595603968099592,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998682781651178,
|
|
"loss": 5.7988,
|
|
"mean_token_accuracy": 0.15181397199630736,
|
|
"num_tokens": 4143624.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.992155838012695,
|
|
"epoch": 0.18634506905271347,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998673282303059,
|
|
"loss": 5.7659,
|
|
"mean_token_accuracy": 0.14670938700437547,
|
|
"num_tokens": 4152193.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.03981647491455,
|
|
"epoch": 0.18673409842443103,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998663748834901,
|
|
"loss": 5.8835,
|
|
"mean_token_accuracy": 0.141094571352005,
|
|
"num_tokens": 4160614.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.138073205947876,
|
|
"epoch": 0.18712312779614862,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998654181246851,
|
|
"loss": 5.9151,
|
|
"mean_token_accuracy": 0.1435561805963516,
|
|
"num_tokens": 4168715.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.1046959400177006,
|
|
"epoch": 0.18751215716786618,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998644579539052,
|
|
"loss": 5.956,
|
|
"mean_token_accuracy": 0.1427804246544838,
|
|
"num_tokens": 4176676.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.041570472717285,
|
|
"epoch": 0.18790118653958374,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499863494371165,
|
|
"loss": 5.9196,
|
|
"mean_token_accuracy": 0.13990830332040788,
|
|
"num_tokens": 4185613.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.056922721862793,
|
|
"epoch": 0.1882902159113013,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998625273764793,
|
|
"loss": 5.9221,
|
|
"mean_token_accuracy": 0.1435866177082062,
|
|
"num_tokens": 4193985.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.057398271560669,
|
|
"epoch": 0.18867924528301888,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998615569698626,
|
|
"loss": 5.8347,
|
|
"mean_token_accuracy": 0.1472941130399704,
|
|
"num_tokens": 4202713.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.15912766456604,
|
|
"epoch": 0.18906827465473644,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998605831513296,
|
|
"loss": 5.9598,
|
|
"mean_token_accuracy": 0.13513548597693442,
|
|
"num_tokens": 4210858.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.027268743515014,
|
|
"epoch": 0.189457304026454,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998596059208953,
|
|
"loss": 5.876,
|
|
"mean_token_accuracy": 0.14263733327388764,
|
|
"num_tokens": 4219570.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.034002113342285,
|
|
"epoch": 0.18984633339817156,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998586252785743,
|
|
"loss": 5.7873,
|
|
"mean_token_accuracy": 0.14603268951177598,
|
|
"num_tokens": 4228026.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.043663167953492,
|
|
"epoch": 0.19023536276988912,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998576412243816,
|
|
"loss": 5.8084,
|
|
"mean_token_accuracy": 0.14466246217489243,
|
|
"num_tokens": 4235993.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.009197854995728,
|
|
"epoch": 0.1906243921416067,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998566537583321,
|
|
"loss": 5.8151,
|
|
"mean_token_accuracy": 0.147155824303627,
|
|
"num_tokens": 4244225.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.965597009658813,
|
|
"epoch": 0.19101342151332426,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998556628804408,
|
|
"loss": 5.7885,
|
|
"mean_token_accuracy": 0.1485578991472721,
|
|
"num_tokens": 4252989.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.069110679626465,
|
|
"epoch": 0.19140245088504182,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998546685907225,
|
|
"loss": 5.8298,
|
|
"mean_token_accuracy": 0.14657569378614427,
|
|
"num_tokens": 4261297.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.0928350448608395,
|
|
"epoch": 0.19179148025675938,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998536708891927,
|
|
"loss": 5.9644,
|
|
"mean_token_accuracy": 0.13758677765727043,
|
|
"num_tokens": 4270299.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.128661823272705,
|
|
"epoch": 0.19218050962847694,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998526697758663,
|
|
"loss": 5.9728,
|
|
"mean_token_accuracy": 0.13565355464816092,
|
|
"num_tokens": 4279662.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.051914119720459,
|
|
"epoch": 0.19256953900019452,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998516652507585,
|
|
"loss": 5.7902,
|
|
"mean_token_accuracy": 0.1471126437187195,
|
|
"num_tokens": 4287876.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.014107513427734,
|
|
"epoch": 0.19295856837191208,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998506573138846,
|
|
"loss": 5.9218,
|
|
"mean_token_accuracy": 0.14491380155086517,
|
|
"num_tokens": 4296415.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.982778406143188,
|
|
"epoch": 0.19334759774362964,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998496459652598,
|
|
"loss": 5.7484,
|
|
"mean_token_accuracy": 0.14843220636248589,
|
|
"num_tokens": 4304434.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.051380062103272,
|
|
"epoch": 0.1937366271153472,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998486312048995,
|
|
"loss": 5.9265,
|
|
"mean_token_accuracy": 0.1381976492702961,
|
|
"num_tokens": 4313266.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.0365697860717775,
|
|
"epoch": 0.19412565648706478,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998476130328193,
|
|
"loss": 5.8013,
|
|
"mean_token_accuracy": 0.14801377803087234,
|
|
"num_tokens": 4322121.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.980331611633301,
|
|
"epoch": 0.19451468585878234,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998465914490343,
|
|
"loss": 5.8202,
|
|
"mean_token_accuracy": 0.14618535935878754,
|
|
"num_tokens": 4330596.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.062447881698608,
|
|
"epoch": 0.1949037152304999,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00049984556645356,
|
|
"loss": 5.9022,
|
|
"mean_token_accuracy": 0.1466861292719841,
|
|
"num_tokens": 4337779.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.0627391815185545,
|
|
"epoch": 0.19529274460221746,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998445380464124,
|
|
"loss": 5.7454,
|
|
"mean_token_accuracy": 0.14693358018994332,
|
|
"num_tokens": 4346623.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.929016637802124,
|
|
"epoch": 0.19568177397393502,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998435062276066,
|
|
"loss": 5.8526,
|
|
"mean_token_accuracy": 0.14088083803653717,
|
|
"num_tokens": 4355435.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.1320250034332275,
|
|
"epoch": 0.1960708033456526,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998424709971586,
|
|
"loss": 5.902,
|
|
"mean_token_accuracy": 0.14303931146860122,
|
|
"num_tokens": 4363636.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.970055866241455,
|
|
"epoch": 0.19645983271737016,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998414323550839,
|
|
"loss": 5.7269,
|
|
"mean_token_accuracy": 0.15075851678848268,
|
|
"num_tokens": 4372337.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.979619741439819,
|
|
"epoch": 0.19684886208908772,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998403903013984,
|
|
"loss": 5.7561,
|
|
"mean_token_accuracy": 0.15269921571016312,
|
|
"num_tokens": 4380528.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.998526477813721,
|
|
"epoch": 0.19723789146080528,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998393448361179,
|
|
"loss": 5.8501,
|
|
"mean_token_accuracy": 0.13916658014059066,
|
|
"num_tokens": 4389464.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.082704496383667,
|
|
"epoch": 0.19762692083252287,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499838295959258,
|
|
"loss": 5.9085,
|
|
"mean_token_accuracy": 0.14364177733659744,
|
|
"num_tokens": 4397879.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.062457323074341,
|
|
"epoch": 0.19801595020424043,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499837243670835,
|
|
"loss": 5.932,
|
|
"mean_token_accuracy": 0.14348311796784402,
|
|
"num_tokens": 4406145.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.0163922786712645,
|
|
"epoch": 0.19840497957595798,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998361879708646,
|
|
"loss": 5.8382,
|
|
"mean_token_accuracy": 0.14055323377251625,
|
|
"num_tokens": 4415480.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.038650321960449,
|
|
"epoch": 0.19879400894767554,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499835128859363,
|
|
"loss": 5.8457,
|
|
"mean_token_accuracy": 0.14373011589050294,
|
|
"num_tokens": 4423355.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.971053647994995,
|
|
"epoch": 0.1991830383193931,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998340663363461,
|
|
"loss": 5.7288,
|
|
"mean_token_accuracy": 0.15200028717517852,
|
|
"num_tokens": 4432059.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.9389901638031,
|
|
"epoch": 0.1995720676911107,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998330004018301,
|
|
"loss": 5.8266,
|
|
"mean_token_accuracy": 0.14117742702364922,
|
|
"num_tokens": 4441146.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.973790550231934,
|
|
"epoch": 0.19996109706282825,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998319310558312,
|
|
"loss": 5.6701,
|
|
"mean_token_accuracy": 0.15412732362747192,
|
|
"num_tokens": 4448553.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.836313152313233,
|
|
"epoch": 0.2003501264345458,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998308582983657,
|
|
"loss": 5.7375,
|
|
"mean_token_accuracy": 0.15181366503238677,
|
|
"num_tokens": 4456930.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.073364543914795,
|
|
"epoch": 0.20073915580626336,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998297821294497,
|
|
"loss": 5.9386,
|
|
"mean_token_accuracy": 0.14404268860816954,
|
|
"num_tokens": 4464932.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.992941284179688,
|
|
"epoch": 0.20112818517798095,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998287025490995,
|
|
"loss": 5.6672,
|
|
"mean_token_accuracy": 0.15902086794376374,
|
|
"num_tokens": 4473695.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.925492858886718,
|
|
"epoch": 0.2015172145496985,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998276195573317,
|
|
"loss": 5.8921,
|
|
"mean_token_accuracy": 0.14221425950527192,
|
|
"num_tokens": 4483375.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.11337890625,
|
|
"epoch": 0.20190624392141607,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998265331541627,
|
|
"loss": 5.9193,
|
|
"mean_token_accuracy": 0.13467642813920974,
|
|
"num_tokens": 4491695.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.003162908554077,
|
|
"epoch": 0.20229527329313363,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998254433396088,
|
|
"loss": 5.8721,
|
|
"mean_token_accuracy": 0.1440841868519783,
|
|
"num_tokens": 4500361.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.987391805648803,
|
|
"epoch": 0.20268430266485118,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998243501136867,
|
|
"loss": 5.8079,
|
|
"mean_token_accuracy": 0.14264530092477798,
|
|
"num_tokens": 4509368.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.039334154129028,
|
|
"epoch": 0.20307333203656877,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998232534764129,
|
|
"loss": 5.7889,
|
|
"mean_token_accuracy": 0.14281965047121048,
|
|
"num_tokens": 4518146.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.01565580368042,
|
|
"epoch": 0.20346236140828633,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998221534278041,
|
|
"loss": 5.8405,
|
|
"mean_token_accuracy": 0.14281932562589644,
|
|
"num_tokens": 4526128.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.036164903640747,
|
|
"epoch": 0.2038513907800039,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998210499678769,
|
|
"loss": 5.8847,
|
|
"mean_token_accuracy": 0.14803217351436615,
|
|
"num_tokens": 4534724.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.968258047103882,
|
|
"epoch": 0.20424042015172145,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998199430966481,
|
|
"loss": 5.7427,
|
|
"mean_token_accuracy": 0.14365783631801604,
|
|
"num_tokens": 4543725.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.012339067459107,
|
|
"epoch": 0.20462944952343903,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998188328141346,
|
|
"loss": 5.8252,
|
|
"mean_token_accuracy": 0.14723241925239564,
|
|
"num_tokens": 4551758.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.894060182571411,
|
|
"epoch": 0.2050184788951566,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998177191203531,
|
|
"loss": 5.7079,
|
|
"mean_token_accuracy": 0.15085572972893715,
|
|
"num_tokens": 4559990.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.93325366973877,
|
|
"epoch": 0.20540750826687415,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998166020153204,
|
|
"loss": 5.7558,
|
|
"mean_token_accuracy": 0.1438131585717201,
|
|
"num_tokens": 4568651.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.900708532333374,
|
|
"epoch": 0.2057965376385917,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998154814990538,
|
|
"loss": 5.6758,
|
|
"mean_token_accuracy": 0.15049925595521926,
|
|
"num_tokens": 4577981.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.955266237258911,
|
|
"epoch": 0.20618556701030927,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00049981435757157,
|
|
"loss": 5.8312,
|
|
"mean_token_accuracy": 0.147544726729393,
|
|
"num_tokens": 4586480.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.980217790603637,
|
|
"epoch": 0.20657459638202685,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998132302328862,
|
|
"loss": 5.7291,
|
|
"mean_token_accuracy": 0.1525867000222206,
|
|
"num_tokens": 4595554.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.923847293853759,
|
|
"epoch": 0.2069636257537444,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998120994830195,
|
|
"loss": 5.7566,
|
|
"mean_token_accuracy": 0.15113697126507758,
|
|
"num_tokens": 4604091.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.023667430877685,
|
|
"epoch": 0.20735265512546197,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499810965321987,
|
|
"loss": 5.8615,
|
|
"mean_token_accuracy": 0.14118051454424857,
|
|
"num_tokens": 4612603.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.032278680801392,
|
|
"epoch": 0.20774168449717953,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998098277498059,
|
|
"loss": 5.7592,
|
|
"mean_token_accuracy": 0.1470929801464081,
|
|
"num_tokens": 4621041.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.90060658454895,
|
|
"epoch": 0.2081307138688971,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998086867664934,
|
|
"loss": 5.7983,
|
|
"mean_token_accuracy": 0.15032607913017274,
|
|
"num_tokens": 4629849.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.054356479644776,
|
|
"epoch": 0.20851974324061467,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499807542372067,
|
|
"loss": 5.8687,
|
|
"mean_token_accuracy": 0.14306920617818833,
|
|
"num_tokens": 4639426.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.9633255958557125,
|
|
"epoch": 0.20890877261233223,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998063945665439,
|
|
"loss": 5.7888,
|
|
"mean_token_accuracy": 0.14868860244750975,
|
|
"num_tokens": 4647257.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.958910369873047,
|
|
"epoch": 0.2092978019840498,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998052433499416,
|
|
"loss": 5.7688,
|
|
"mean_token_accuracy": 0.14971182197332383,
|
|
"num_tokens": 4655773.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.995905542373658,
|
|
"epoch": 0.20968683135576735,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998040887222776,
|
|
"loss": 5.8141,
|
|
"mean_token_accuracy": 0.14208999648690224,
|
|
"num_tokens": 4664292.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.006470203399658,
|
|
"epoch": 0.21007586072748494,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998029306835693,
|
|
"loss": 5.8357,
|
|
"mean_token_accuracy": 0.1457445926964283,
|
|
"num_tokens": 4672774.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.1288737773895265,
|
|
"epoch": 0.2104648900992025,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998017692338344,
|
|
"loss": 5.954,
|
|
"mean_token_accuracy": 0.14017487764358522,
|
|
"num_tokens": 4681855.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.958335494995117,
|
|
"epoch": 0.21085391947092005,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998006043730905,
|
|
"loss": 5.7565,
|
|
"mean_token_accuracy": 0.14842477068305016,
|
|
"num_tokens": 4689771.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.003065395355224,
|
|
"epoch": 0.2112429488426376,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997994361013551,
|
|
"loss": 5.8986,
|
|
"mean_token_accuracy": 0.1353430561721325,
|
|
"num_tokens": 4698808.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.980752849578858,
|
|
"epoch": 0.21163197821435517,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997982644186461,
|
|
"loss": 5.7782,
|
|
"mean_token_accuracy": 0.14798913151025772,
|
|
"num_tokens": 4707627.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.949896383285522,
|
|
"epoch": 0.21202100758607276,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997970893249813,
|
|
"loss": 5.7576,
|
|
"mean_token_accuracy": 0.14555923044681549,
|
|
"num_tokens": 4716091.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.944676637649536,
|
|
"epoch": 0.21241003695779032,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997959108203785,
|
|
"loss": 5.788,
|
|
"mean_token_accuracy": 0.1488296665251255,
|
|
"num_tokens": 4724042.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.887519454956054,
|
|
"epoch": 0.21279906632950787,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997947289048554,
|
|
"loss": 5.7058,
|
|
"mean_token_accuracy": 0.15533653944730758,
|
|
"num_tokens": 4731745.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.945332145690918,
|
|
"epoch": 0.21318809570122543,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997935435784302,
|
|
"loss": 5.872,
|
|
"mean_token_accuracy": 0.146851022541523,
|
|
"num_tokens": 4740386.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.041448068618775,
|
|
"epoch": 0.21357712507294302,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997923548411208,
|
|
"loss": 5.8834,
|
|
"mean_token_accuracy": 0.1391231372952461,
|
|
"num_tokens": 4749809.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.063974905014038,
|
|
"epoch": 0.21396615444466058,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499791162692945,
|
|
"loss": 5.9768,
|
|
"mean_token_accuracy": 0.1409013733267784,
|
|
"num_tokens": 4759507.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.960179090499878,
|
|
"epoch": 0.21435518381637814,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997899671339214,
|
|
"loss": 5.7479,
|
|
"mean_token_accuracy": 0.1449030451476574,
|
|
"num_tokens": 4768793.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.029723405838013,
|
|
"epoch": 0.2147442131880957,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997887681640675,
|
|
"loss": 5.9008,
|
|
"mean_token_accuracy": 0.14465020522475242,
|
|
"num_tokens": 4777344.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.030321025848389,
|
|
"epoch": 0.21513324255981325,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997875657834021,
|
|
"loss": 5.8127,
|
|
"mean_token_accuracy": 0.1441117987036705,
|
|
"num_tokens": 4785934.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.947022724151611,
|
|
"epoch": 0.21552227193153084,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997863599919432,
|
|
"loss": 5.7731,
|
|
"mean_token_accuracy": 0.1485394760966301,
|
|
"num_tokens": 4794889.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.944930124282837,
|
|
"epoch": 0.2159113013032484,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997851507897089,
|
|
"loss": 5.8881,
|
|
"mean_token_accuracy": 0.14024131819605828,
|
|
"num_tokens": 4803597.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.933191776275635,
|
|
"epoch": 0.21630033067496596,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997839381767178,
|
|
"loss": 5.6613,
|
|
"mean_token_accuracy": 0.15584157705307006,
|
|
"num_tokens": 4812706.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.90777177810669,
|
|
"epoch": 0.21668936004668352,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997827221529882,
|
|
"loss": 5.7295,
|
|
"mean_token_accuracy": 0.1480869472026825,
|
|
"num_tokens": 4821790.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.968650197982788,
|
|
"epoch": 0.2170783894184011,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997815027185386,
|
|
"loss": 5.7899,
|
|
"mean_token_accuracy": 0.1485279232263565,
|
|
"num_tokens": 4830123.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.94366946220398,
|
|
"epoch": 0.21746741879011866,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997802798733874,
|
|
"loss": 5.7194,
|
|
"mean_token_accuracy": 0.1537564590573311,
|
|
"num_tokens": 4838066.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.9353564262390135,
|
|
"epoch": 0.21785644816183622,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997790536175534,
|
|
"loss": 5.7944,
|
|
"mean_token_accuracy": 0.14718551486730574,
|
|
"num_tokens": 4846877.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.991869354248047,
|
|
"epoch": 0.21824547753355378,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997778239510548,
|
|
"loss": 5.8426,
|
|
"mean_token_accuracy": 0.14051205813884735,
|
|
"num_tokens": 4856960.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.004691219329834,
|
|
"epoch": 0.21863450690527134,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997765908739106,
|
|
"loss": 5.8542,
|
|
"mean_token_accuracy": 0.14763535112142562,
|
|
"num_tokens": 4865440.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.893306064605713,
|
|
"epoch": 0.21902353627698892,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997753543861395,
|
|
"loss": 5.7417,
|
|
"mean_token_accuracy": 0.1489579737186432,
|
|
"num_tokens": 4874187.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.102828645706177,
|
|
"epoch": 0.21941256564870648,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00049977411448776,
|
|
"loss": 5.8831,
|
|
"mean_token_accuracy": 0.14227399230003357,
|
|
"num_tokens": 4883151.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.983131647109985,
|
|
"epoch": 0.21980159502042404,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997728711787912,
|
|
"loss": 5.7977,
|
|
"mean_token_accuracy": 0.14272094666957855,
|
|
"num_tokens": 4890968.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.879379606246948,
|
|
"epoch": 0.2201906243921416,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997716244592518,
|
|
"loss": 5.6825,
|
|
"mean_token_accuracy": 0.15600915551185607,
|
|
"num_tokens": 4899389.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.905595302581787,
|
|
"epoch": 0.22057965376385918,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997703743291607,
|
|
"loss": 5.7509,
|
|
"mean_token_accuracy": 0.15158967077732086,
|
|
"num_tokens": 4907622.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.943753623962403,
|
|
"epoch": 0.22096868313557674,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499769120788537,
|
|
"loss": 5.7491,
|
|
"mean_token_accuracy": 0.1479824811220169,
|
|
"num_tokens": 4916151.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.892854356765747,
|
|
"epoch": 0.2213577125072943,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997678638373995,
|
|
"loss": 5.6692,
|
|
"mean_token_accuracy": 0.15641618967056276,
|
|
"num_tokens": 4923938.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.87450475692749,
|
|
"epoch": 0.22174674187901186,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997666034757676,
|
|
"loss": 5.7613,
|
|
"mean_token_accuracy": 0.16034080535173417,
|
|
"num_tokens": 4932027.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.947768974304199,
|
|
"epoch": 0.22213577125072942,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997653397036603,
|
|
"loss": 5.7766,
|
|
"mean_token_accuracy": 0.1560262620449066,
|
|
"num_tokens": 4940229.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.907529211044311,
|
|
"epoch": 0.222524800622447,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997640725210965,
|
|
"loss": 5.8405,
|
|
"mean_token_accuracy": 0.14572847858071328,
|
|
"num_tokens": 4948662.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.958647584915161,
|
|
"epoch": 0.22291382999416456,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997628019280958,
|
|
"loss": 5.7854,
|
|
"mean_token_accuracy": 0.1521115556359291,
|
|
"num_tokens": 4956847.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.970917129516602,
|
|
"epoch": 0.22330285936588212,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997615279246773,
|
|
"loss": 5.7205,
|
|
"mean_token_accuracy": 0.14754560068249703,
|
|
"num_tokens": 4965139.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.0411519527435305,
|
|
"epoch": 0.22369188873759968,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997602505108603,
|
|
"loss": 5.8952,
|
|
"mean_token_accuracy": 0.14166620448231698,
|
|
"num_tokens": 4973671.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.933946704864502,
|
|
"epoch": 0.22408091810931724,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997589696866644,
|
|
"loss": 5.7652,
|
|
"mean_token_accuracy": 0.14397089332342147,
|
|
"num_tokens": 4981970.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.935157251358032,
|
|
"epoch": 0.22446994748103483,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997576854521088,
|
|
"loss": 5.7921,
|
|
"mean_token_accuracy": 0.14724297374486922,
|
|
"num_tokens": 4990591.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.9578015327453615,
|
|
"epoch": 0.22485897685275238,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499756397807213,
|
|
"loss": 5.7954,
|
|
"mean_token_accuracy": 0.14315731078386307,
|
|
"num_tokens": 4999623.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.011578512191773,
|
|
"epoch": 0.22524800622446994,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997551067519966,
|
|
"loss": 5.8545,
|
|
"mean_token_accuracy": 0.1422098271548748,
|
|
"num_tokens": 5008387.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.949732828140259,
|
|
"epoch": 0.2256370355961875,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997538122864792,
|
|
"loss": 5.7775,
|
|
"mean_token_accuracy": 0.1461174599826336,
|
|
"num_tokens": 5016788.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.023969125747681,
|
|
"epoch": 0.2260260649679051,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997525144106804,
|
|
"loss": 5.8104,
|
|
"mean_token_accuracy": 0.14314667582511903,
|
|
"num_tokens": 5025508.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.927273511886597,
|
|
"epoch": 0.22641509433962265,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00049975121312462,
|
|
"loss": 5.7821,
|
|
"mean_token_accuracy": 0.14801414608955382,
|
|
"num_tokens": 5035081.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.879549169540406,
|
|
"epoch": 0.2268041237113402,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997499084283177,
|
|
"loss": 5.7173,
|
|
"mean_token_accuracy": 0.15523723959922792,
|
|
"num_tokens": 5043655.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.91579909324646,
|
|
"epoch": 0.22719315308305776,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997486003217932,
|
|
"loss": 5.74,
|
|
"mean_token_accuracy": 0.15187966972589492,
|
|
"num_tokens": 5052080.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.888910627365112,
|
|
"epoch": 0.22758218245477532,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997472888050664,
|
|
"loss": 5.7076,
|
|
"mean_token_accuracy": 0.15852134227752684,
|
|
"num_tokens": 5061325.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.961522054672241,
|
|
"epoch": 0.2279712118264929,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997459738781573,
|
|
"loss": 5.8208,
|
|
"mean_token_accuracy": 0.15095880776643752,
|
|
"num_tokens": 5069461.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.988435316085815,
|
|
"epoch": 0.22836024119821047,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997446555410857,
|
|
"loss": 5.7807,
|
|
"mean_token_accuracy": 0.14658573567867278,
|
|
"num_tokens": 5077747.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.988274765014649,
|
|
"epoch": 0.22874927056992803,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997433337938716,
|
|
"loss": 5.8365,
|
|
"mean_token_accuracy": 0.15124830231070518,
|
|
"num_tokens": 5086300.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.844106388092041,
|
|
"epoch": 0.22913829994164558,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997420086365351,
|
|
"loss": 5.6151,
|
|
"mean_token_accuracy": 0.15467342734336853,
|
|
"num_tokens": 5094762.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.89040789604187,
|
|
"epoch": 0.22952732931336317,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997406800690966,
|
|
"loss": 5.7742,
|
|
"mean_token_accuracy": 0.14963481277227403,
|
|
"num_tokens": 5103364.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.023597526550293,
|
|
"epoch": 0.22991635868508073,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997393480915758,
|
|
"loss": 5.8799,
|
|
"mean_token_accuracy": 0.14407353550195695,
|
|
"num_tokens": 5111730.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.970983409881592,
|
|
"epoch": 0.2303053880567983,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997380127039931,
|
|
"loss": 5.6786,
|
|
"mean_token_accuracy": 0.1486763596534729,
|
|
"num_tokens": 5119878.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.9219104766845705,
|
|
"epoch": 0.23069441742851585,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997366739063688,
|
|
"loss": 5.7901,
|
|
"mean_token_accuracy": 0.1522405095398426,
|
|
"num_tokens": 5129146.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.892798137664795,
|
|
"epoch": 0.2310834468002334,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997353316987231,
|
|
"loss": 5.8065,
|
|
"mean_token_accuracy": 0.14348602443933486,
|
|
"num_tokens": 5137989.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.039399528503418,
|
|
"epoch": 0.231472476171951,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997339860810765,
|
|
"loss": 5.8268,
|
|
"mean_token_accuracy": 0.14684822633862496,
|
|
"num_tokens": 5146722.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.007096481323242,
|
|
"epoch": 0.23186150554366855,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997326370534495,
|
|
"loss": 5.8128,
|
|
"mean_token_accuracy": 0.14832943975925444,
|
|
"num_tokens": 5154902.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.963329792022705,
|
|
"epoch": 0.2322505349153861,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997312846158622,
|
|
"loss": 5.827,
|
|
"mean_token_accuracy": 0.14517123103141785,
|
|
"num_tokens": 5163594.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.939759683609009,
|
|
"epoch": 0.23263956428710367,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997299287683355,
|
|
"loss": 5.7065,
|
|
"mean_token_accuracy": 0.1531409054994583,
|
|
"num_tokens": 5172139.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.937909650802612,
|
|
"epoch": 0.23302859365882125,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997285695108898,
|
|
"loss": 5.8315,
|
|
"mean_token_accuracy": 0.15084856152534484,
|
|
"num_tokens": 5180077.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.849994754791259,
|
|
"epoch": 0.2334176230305388,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997272068435458,
|
|
"loss": 5.6851,
|
|
"mean_token_accuracy": 0.14938049018383026,
|
|
"num_tokens": 5188500.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2334176230305388,
|
|
"eval_entropy": 5.659352120260876,
|
|
"eval_loss": 5.808426856994629,
|
|
"eval_mean_token_accuracy": 0.15537977798754946,
|
|
"eval_num_tokens": 5188500.0,
|
|
"eval_runtime": 21.8125,
|
|
"eval_samples_per_second": 1905.236,
|
|
"eval_steps_per_second": 238.166,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 128520,
|
|
"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": 1038909989191680.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|